184 files changed, 14753 insertions, 6707 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index cb43289e447f..416684be0ad3 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -1,4 +1,3 @@
-PERF-BUILD-OPTIONS
 PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index bd498d496952..4626a398836a 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -178,8 +178,8 @@ install-pdf: pdf
         $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir)
         $(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir)
 
-install-html: html
-        '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
+#install-html: html
+#       '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
 
 ../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
         $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE
@@ -288,15 +288,16 @@ $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
         sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
         mv $@+ $@
 
-install-webdoc : html
-        '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
+# UNIMPLEMENTED
+#install-webdoc : html
+#       '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST)
 
-quick-install: quick-install-man
+# quick-install: quick-install-man
 
-quick-install-man:
-        '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
+# quick-install-man:
+#       '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir)
 
-quick-install-html:
-        '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
+#quick-install-html:
+#       '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir)
 
 .PHONY: .FORCE-PERF-VERSION-FILE
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 5164a655c39f..6f5a498608b2 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -8,7 +8,7 @@ perf-annotate - Read perf.data (created by perf record) and display annotated co
 SYNOPSIS
 --------
 [verse]
-'perf annotate' [-i <file> | --input=file] symbol_name
+'perf annotate' [-i <file> | --input=file] [symbol_name]
 
 DESCRIPTION
 -----------
@@ -24,6 +24,48 @@ OPTIONS
 --input=::
         Input file name. (default: perf.data)
 
+-d::
+--dsos=<dso[,dso...]>::
+        Only consider symbols in these dsos.
+-s::
+--symbol=<symbol>::
+        Symbol to annotate.
+
+-f::
+--force::
+        Don't complain, do it.
+
+-v::
+--verbose::
+        Be more verbose. (Show symbol address, etc)
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel.
+
+-l::
+--print-line::
+        Print matching source lines (may be slow).
+
+-P::
+--full-paths::
+        Don't shorten the displayed pathnames.
+
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface Use of --tui requires a tty, if one is not
+        present, as when piping to other commands, the stdio interface is
+        used. This interfaces starts by centering on the line with more
+        samples, TAB/UNTAB cycles through the lines with more samples.
+
 SEE ALSO
 --------
-linkperf:perf-record[1]
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 01b642c0bf8f..5eaac6f26d51 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -18,6 +18,9 @@ perf report.
 
 OPTIONS
 -------
+-H::
+--with-hits::
+        Show only DSOs with hits.
 -i::
 --input=::
         Input file name. (default: perf.data)
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 20d97d84ea1c..74d7481ed7a6 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -19,6 +19,18 @@ If no parameters are passed it will assume perf.data.old and perf.data.
 
 OPTIONS
 -------
+-M::
+--displacement::
+        Show position displacement relative to baseline.
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel
+
 -d::
 --dsos=::
         Only consider symbols in these dsos. CSV that understands
@@ -42,7 +54,7 @@ OPTIONS
 --field-separator=::
 
         Use a special separator character and don't pad with spaces, replacing
-        all occurances of this separator in symbol names (and other output)
+        all occurrences of this separator in symbol names (and other output)
         with a '.' character, that thus it's the only non valid separator.
 
 -v::
@@ -50,6 +62,13 @@ OPTIONS
         Be verbose, for instance, show the raw counts in addition to the
         diff.
 
+-f::
+--force::
+       Don't complain, do it.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
new file mode 100644
index 000000000000..0cada9e053dc
--- /dev/null
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -0,0 +1,26 @@
+perf-evlist(1)
+==============
+
+NAME
+----
+perf-evlist - List the event names in a perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf evlist <options>'
+
+DESCRIPTION
+-----------
+This command displays the names of events sampled in a perf.data file.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data)
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-list[1],
+linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index d004e19fe6d6..dd84cb2f0a88 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -22,7 +22,7 @@ There are a couple of variants of perf kvm:
   a performance counter profile of guest os in realtime
   of an arbitrary workload.
 
-  'perf kvm record <command>' to record the performance couinter profile
+  'perf kvm record <command>' to record the performance counter profile
   of an arbitrary workload and save it into a perf data file. If both
   --host and --guest are input, the perf data file name is perf.data.kvm.
   If there is  no --host but --guest, the file name is perf.data.guest.
@@ -40,6 +40,12 @@ There are a couple of variants of perf kvm:
 
 OPTIONS
 -------
+-i::
+--input=::
+        Input file name.
+-o::
+--output::
+        Output file name.
 --host=::
         Collect host side performance profile.
 --guest=::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 43e3dd284b90..7a527f7e9da9 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,13 +8,30 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list'
+'perf list' [hw|sw|cache|tracepoint|event_glob]
 
 DESCRIPTION
 -----------
 This command displays the symbolic event types which can be selected in the
 various perf commands with the -e option.
 
+EVENT MODIFIERS
+---------------
+
+Events can optionally have a modifer by appending a colon and one or
+more modifiers.  Modifiers allow the user to restrict when events are
+counted with 'u' for user-space, 'k' for kernel, 'h' for hypervisor.
+
+The 'p' modifier can be used for specifying how precise the instruction
+address should be. The 'p' modifier is currently only implemented for
+Intel PEBS and can be specified multiple times:
+  0 - SAMPLE_IP can have arbitrary skid
+  1 - SAMPLE_IP must have constant skid
+  2 - SAMPLE_IP requested to have 0 skid
+  3 - SAMPLE_IP must have 0 skid
+
+The PEBS implementation now supports up to 2.
+
 RAW HARDWARE EVENT DESCRIPTOR
 -----------------------------
 Even when an event is not available in a symbolic form within perf right now,
@@ -46,7 +63,26 @@ details. Some of them are referenced in the SEE ALSO section below.
 
 OPTIONS
 -------
-None
+
+Without options all known events will be listed.
+
+To limit the list use:
+
+. 'hw' or 'hardware' to list hardware events such as cache-misses, etc.
+
+. 'sw' or 'software' to list software events such as context switches, etc.
+
+. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc.
+
+. 'tracepoint' to list all tracepoint events, alternatively use
+  'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
+  block, etc.
+
+. If none of the above is matched, it will apply the supplied glob to all
+  events, printing the ones that match.
+
+One or more types can be used at the same time, listing the events for the
+types specified.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index b317102138c8..4a26a2f3a6a3 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -24,6 +24,29 @@ and statistics with this 'perf lock' command.
 
   'perf lock report' reports statistical data.
 
+COMMON OPTIONS
+--------------
+
+-i::
+--input=<file>::
+        Input file name.
+
+-v::
+--verbose::
+        Be more verbose (show symbol address, etc).
+
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
+REPORT OPTIONS
+--------------
+
+-k::
+--key=<value>::
+        Sorting key. Possible values: acquired (default), contended,
+        wait_total, wait_max, wait_min.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 27d52dae5a43..02bafce4b341 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -16,7 +16,9 @@ or
 or
 'perf probe' --list
 or
-'perf probe' --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
+'perf probe' [options] --line='LINE'
+or
+'perf probe' [options] --vars='PROBEPOINT'
 
 DESCRIPTION
 -----------
@@ -31,6 +33,11 @@ OPTIONS
 --vmlinux=PATH::
         Specify vmlinux path which has debuginfo (Dwarf binary).
 
+-m::
+--module=MODNAME::
+        Specify module name in which perf-probe searches probe points
+        or lines.
+
 -s::
 --source=PATH::
         Specify path to kernel source.
@@ -57,6 +64,26 @@ OPTIONS
         Show source code lines which can be probed. This needs an argument
         which specifies a range of the source code. (see LINE SYNTAX for detail)
 
+-V::
+--vars=::
+        Show available local variables at given probe point. The argument
+        syntax is same as PROBE SYNTAX, but NO ARGs.
+
+--externs::
+        (Only for --vars) Show external defined variables in addition to local
+        variables.
+
+-F::
+--funcs::
+        Show available functions in given module or kernel.
+
+--filter=FILTER::
+        (Only for --vars and --funcs) Set filter. FILTER is a combination of glob
+        pattern, see FILTER PATTERN for detail.
+        Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*"
+        for --funcs.
+        If several filters are specified, only the last filter is used.
+
 -f::
 --force::
         Forcibly add events with existing name.
@@ -99,15 +126,16 @@ Each probe argument follows below syntax.
 
 LINE SYNTAX
 -----------
-Line range is descripted by following syntax.
+Line range is described by following syntax.
 
- "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]"
+ "FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
 
 FUNC specifies the function name of showing lines. 'RLN' is the start line
 number from function entry line, and 'RLN2' is the end line number. As same as
 probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
 and 'ALN2' is end line number in the file. It is also possible to specify how
-many lines to show by using 'NUM'.
+many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good
+for searching a specific function when several functions share same name.
 So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
 
 LAZY MATCHING
@@ -119,6 +147,14 @@ e.g.
 
 This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
 
+FILTER PATTERN
+--------------
+ The filter pattern is a glob matching pattern(s) to filter variables.
+ In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
+
+e.g.
+ With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
+ With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out.
 
 EXAMPLES
 --------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3ee27dccfde9..5a520f825295 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -39,19 +39,31 @@ OPTIONS
           be passed as follows: '\mem:addr[:[r][w][x]]'.
           If you want to profile read-write accesses in 0x1000, just set
           'mem:0x1000:rw'.
+
+--filter=<filter>::
+        Event filter.
+
 -a::
-        System-wide collection.
+--all-cpus::
+        System-wide collection from all CPUs.
 
 -l::
         Scale counter values.
 
 -p::
 --pid=::
-        Record events on existing pid.
+        Record events on existing process ID.
+
+-t::
+--tid=::
+        Record events on existing thread ID.
 
 -r::
 --realtime=::
         Collect data with this RT SCHED_FIFO priority.
+-D::
+--no-delay::
+        Collect data without buffering.
 -A::
 --append::
         Append to the output file to do incremental profiling.
@@ -83,6 +95,10 @@ OPTIONS
 --call-graph::
         Do call-graph (stack chain/backtrace) recording.
 
+-q::
+--quiet::
+        Don't print any message, useful for scripting.
+
 -v::
 --verbose::
         Be more verbose (show counter open errors, etc).
@@ -95,6 +111,11 @@ OPTIONS
 --data::
         Sample addresses.
 
+-T::
+--timestamp::
+        Sample timestamps. Use it with 'perf report -D' to see the timestamps,
+        for instance.
+
 -n::
 --no-samples::
         Don't sample.
@@ -105,8 +126,8 @@ Collect raw sample records from all opened counters (default for tracepoint coun
 
 -C::
 --cpu::
-Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 In per-thread mode with inheritance mode on (default), samples are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
@@ -116,6 +137,17 @@ Do not update the builid cache. This saves some overhead in situations
 where the information in the perf.data file (which includes buildids)
 is sufficient.
 
+-G name,...::
+--cgroup name,...::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
 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 abfabe9147a4..8ba03d6e5398 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -20,6 +20,11 @@ OPTIONS
 -i::
 --input=::
         Input file name. (default: perf.data)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 -d::
 --dsos=::
         Only consider symbols in these dsos. CSV that understands
@@ -27,6 +32,10 @@ OPTIONS
 -n::
 --show-nr-samples::
         Show the number of samples for each symbol
+
+--showcpuutilization::
+        Show sample percentage for different cpu modes.
+
 -T::
 --threads::
         Show per-thread event counters
@@ -39,12 +48,24 @@ OPTIONS
         Only consider these symbols. CSV that understands
         file://filename entries.
 
+-U::
+--hide-unresolved::
+        Only display entries resolved to a symbol.
+
 -s::
 --sort=::
         Sort by key(s): pid, comm, dso, symbol, parent.
 
+-p::
+--parent=<regex>::
+        regex filter to identify parent, see: '--sort parent'
+
+-x::
+--exclude-other::
+        Only display entries with parent-match.
+
 -w::
---field-width=::
+--column-widths=<width[,width...]>::
         Force each column width to the provided list, for large terminal
         readability.
 
@@ -52,19 +73,52 @@ OPTIONS
 --field-separator=::
 
         Use a special separator character and don't pad with spaces, replacing
-        all occurances of this separator in symbol names (and other output)
+        all occurrences of this separator in symbol names (and other output)
         with a '.' character, that thus it's the only non valid separator.
 
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+
 -g [type,min]::
 --call-graph::
-        Display callchains using type and min percent threshold.
+        Display call chains using type and min percent threshold.
         type can be either:
-        - flat: single column, linear exposure of callchains.
+        - flat: single column, linear exposure of call chains.
         - graph: use a graph tree, displaying absolute overhead rates.
         - fractal: like graph, but displays relative rates. Each branch of
                  the tree is considered as a new profiled object. +
         Default: fractal,0.5.
 
+--pretty=<key>::
+        Pretty printing style.  key: normal, raw
+
+--stdio:: Use the stdio interface.
+
+--tui:: Use the TUI interface, that is integrated with annotate and allows
+        zooming into DSOs or threads, among other features. Use of --tui
+        requires a tty, if one is not present, as when piping to other
+        commands, the stdio interface is used.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+-m::
+--modules::
+        Load module symbols. WARNING: This should only be used with -k and
+        a LIVE kernel.
+
+-f::
+--force::
+        Don't complain, do it.
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 8417644a6166..46822d5fde1c 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,11 +8,11 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|replay|trace}
+'perf sched' {record|latency|map|replay|trace}
 
 DESCRIPTION
 -----------
-There are four variants of perf sched:
+There are five variants of perf sched:
 
   'perf sched record <command>' to record the scheduling events
   of an arbitrary workload.
@@ -30,8 +30,22 @@ There are four variants of perf sched:
   of the workload as it occurred when it was recorded - and can repeat
   it a number of times, measuring its performance.)
 
+  'perf sched map' to print a textual context-switching outline of
+  workload captured via perf sched record.  Columns stand for
+  individual CPUs, and the two-letter shortcuts stand for tasks that
+  are running on a CPU. A '*' denotes the CPU that had the event, and
+  a dot signals an idle CPU.
+
 OPTIONS
 -------
+-i::
+--input=<file>::
+        Input file name. (default: perf.data)
+
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
+
 -D::
 --dump-raw-trace=::
         Display verbose dump of the sched data.
diff --git a/tools/perf/Documentation/perf-trace-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index ee6525ee6d69..3152cca15501 100644
--- a/tools/perf/Documentation/perf-trace-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -1,19 +1,19 @@
-perf-trace-perl(1)
+perf-script-perl(1)
 ==================
 
 NAME
 ----
-perf-trace-perl - Process trace data with a Perl script
+perf-script-perl - Process trace data with a Perl script
 
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [Perl]:script[.pl] ]
+'perf script' [-s [Perl]:script[.pl] ]
 
 DESCRIPTION
 -----------
 
-This perf trace option is used to process perf trace data using perf's
+This perf script option is used to process perf script data using perf's
 built-in Perl interpreter.  It reads and processes the input file and
 displays the results of the trace analysis implemented in the given
 Perl script, if any.
@@ -21,7 +21,7 @@ Perl script, if any.
 STARTER SCRIPTS
 ---------------
 
-You can avoid reading the rest of this document by running 'perf trace
+You can avoid reading the rest of this document by running 'perf script
 -g perl' in the same directory as an existing perf.data trace file.
 That will generate a starter script containing a handler for each of
 the event types in the trace file; it simply prints every available
@@ -30,13 +30,13 @@ field for each event in the trace file.
 You can also look at the existing scripts in
 ~/libexec/perf-core/scripts/perl for typical examples showing how to
 do basic things like aggregate event data, print results, etc.  Also,
-the check-perf-trace.pl script, while not interesting for its results,
+the check-perf-script.pl script, while not interesting for its results,
 attempts to exercise all of the main scripting features.
 
 EVENT HANDLERS
 --------------
 
-When perf trace is invoked using a trace script, a user-defined
+When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
 ignored (or passed to a 'trace_handled' function, see below) and the
@@ -63,7 +63,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
@@ -112,13 +111,13 @@ write a useful trace script.  The sections below cover the rest.
 SCRIPT LAYOUT
 -------------
 
-Every perf trace Perl script should start by setting up a Perl module
+Every perf script Perl script should start by setting up a Perl module
 search path and 'use'ing a few support modules (see module
 descriptions below):
 
 ----
- use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
- use lib "./Perf-Trace-Util/lib";
+ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/perf-script-Util/lib";
+ use lib "./perf-script-Util/lib";
  use Perf::Trace::Core;
  use Perf::Trace::Context;
  use Perf::Trace::Util;
@@ -162,7 +161,7 @@ sub trace_unhandled
 ----
 
 The remaining sections provide descriptions of each of the available
-built-in perf trace Perl modules and their associated functions.
+built-in perf script Perl modules and their associated functions.
 
 AVAILABLE MODULES AND FUNCTIONS
 -------------------------------
@@ -170,7 +169,7 @@ AVAILABLE MODULES AND FUNCTIONS
 The following sections describe the functions and variables available
 via the various Perf::Trace::* Perl modules.  To use the functions and
 variables from the given module, add the corresponding 'use
-Perf::Trace::XXX' line to your perf trace script.
+Perf::Trace::XXX' line to your perf script script.
 
 Perf::Trace::Core Module
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -204,7 +203,7 @@ argument.
 Perf::Trace::Util Module
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-Various utility functions for use with perf trace:
+Various utility functions for use with perf script:
 
   nsecs($secs, $nsecs) - returns total nsecs given secs/nsecs pair
   nsecs_secs($nsecs) - returns whole secs portion given nsecs
@@ -214,4 +213,4 @@ Various utility functions for use with perf trace:
 
 SEE ALSO
 --------
-linkperf:perf-trace[1]
+linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf-trace-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 693be804dd3d..471022069119 100644
--- a/tools/perf/Documentation/perf-trace-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -1,19 +1,19 @@
-perf-trace-python(1)
+perf-script-python(1)
 ====================
 
 NAME
 ----
-perf-trace-python - Process trace data with a Python script
+perf-script-python - Process trace data with a Python script
 
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [Python]:script[.py] ]
+'perf script' [-s [Python]:script[.py] ]
 
 DESCRIPTION
 -----------
 
-This perf trace option is used to process perf trace data using perf's
+This perf script option is used to process perf script data using perf's
 built-in Python interpreter.  It reads and processes the input file and
 displays the results of the trace analysis implemented in the given
 Python script, if any.
@@ -23,15 +23,15 @@ A QUICK EXAMPLE
 
 This section shows the process, start to finish, of creating a working
 Python script that aggregates and extracts useful information from a
-raw perf trace stream.  You can avoid reading the rest of this
+raw perf script stream.  You can avoid reading the rest of this
 document if an example is enough for you; the rest of the document
 provides more details on each step and lists the library functions
 available to script writers.
 
 This example actually details the steps that were used to create the
-'syscall-counts' script you see when you list the available perf trace
-scripts via 'perf trace -l'.  As such, this script also shows how to
-integrate your script into the list of general-purpose 'perf trace'
+'syscall-counts' script you see when you list the available perf script
+scripts via 'perf script -l'.  As such, this script also shows how to
+integrate your script into the list of general-purpose 'perf script'
 scripts listed by that command.
 
 The syscall-counts script is a simple script, but demonstrates all the
@@ -105,31 +105,31 @@ That single stream will be recorded in a file in the current directory
 called perf.data.
 
 Once we have a perf.data file containing our data, we can use the -g
-'perf trace' option to generate a Python script that will contain a
+'perf script' option to generate a Python script that will contain a
 callback handler for each event type found in the perf.data trace
 stream (for more details, see the STARTER SCRIPTS section).
 
 ----
-# perf trace -g python
-generated Python script: perf-trace.py
+# perf script -g python
+generated Python script: perf-script.py
 
 The output file created also in the current directory is named
-perf-trace.py.  Here's the file in its entirety:
+perf-script.py.  Here's the file in its entirety:
 
-# perf trace event handlers, generated by perf trace -g python
+# perf script event handlers, generated by perf script -g python
 # Licensed under the terms of the GNU GPL License version 2
 
 # The common_* event handler fields are the most useful fields common to
 # all events.  They don't necessarily correspond to the 'common_*' fields
 # in the format files.  Those fields not available as handler params can
 # be retrieved using Python functions of the form common_*(context).
-# See the perf-trace-python Documentation for the list of available functions.
+# See the perf-script-python Documentation for the list of available functions.
 
 import os
 import sys
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+        '/scripts/python/perf-script-Util/lib/Perf/Trace')
 
 from perf_trace_context import *
 from Core import *
@@ -160,7 +160,7 @@ def print_header(event_name, cpu, secs, nsecs, pid, comm):
 ----
 
 At the top is a comment block followed by some import statements and a
-path append which every perf trace script should include.
+path append which every perf script script should include.
 
 Following that are a couple generated functions, trace_begin() and
 trace_end(), which are called at the beginning and the end of the
@@ -189,8 +189,8 @@ simply a utility function used for that purpose.  Let's rename the
 script and run it to see the default output:
 
 ----
-# mv perf-trace.py syscall-counts.py
-# perf trace -s syscall-counts.py
+# mv perf-script.py syscall-counts.py
+# perf script -s syscall-counts.py
 
 raw_syscalls__sys_enter     1 00840.847582083     7506 perf                  id=1, args=
 raw_syscalls__sys_enter     1 00840.847595764     7506 perf                  id=1, args=
@@ -216,7 +216,7 @@ import os
 import sys
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+        '/scripts/python/perf-script-Util/lib/Perf/Trace')
 
 from perf_trace_context import *
 from Core import *
@@ -279,7 +279,7 @@ import os
 import sys
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+        '/scripts/python/perf-script-Util/lib/Perf/Trace')
 
 from perf_trace_context import *
 from Core import *
@@ -315,7 +315,7 @@ def print_syscall_totals():
 
 The script can be run just as before:
 
-  # perf trace -s syscall-counts.py
+  # perf script -s syscall-counts.py
 
 So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
@@ -324,17 +324,17 @@ interested in by looking at the list of available events shown by
 'perf list' and/or look in /sys/kernel/debug/tracing events for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
-generate a skeleton script using 'perf trace -g python' and modify the
+generate a skeleton script using 'perf script -g python' and modify the
 code to aggregate and display it for your particular needs.
 
 After you've done that you may end up with a general-purpose script
 that you want to keep around and have available for future use.  By
 writing a couple of very simple shell scripts and putting them in the
 right place, you can have your script listed alongside the other
-scripts listed by the 'perf trace -l' command e.g.:
+scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf trace -l
+root@tropicana:~# perf script -l
 List of available trace scripts:
   workqueue-stats                      workqueue stats (ins/exe/create/destroy)
   wakeup-latency                       system-wide min/max/avg wakeup latency
@@ -365,14 +365,14 @@ perf record -a -e raw_syscalls:sys_enter
 The 'report' script is also a shell script with the same base name as
 your script, but with -report appended.  It should also be located in
 the perf/scripts/python/bin directory.  In that script, you write the
-'perf trace -s' command-line needed for running your script:
+'perf script -s' command-line needed for running your script:
 
 ----
 # cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-report
 
 #!/bin/bash
 # description: system-wide syscall counts
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py
+perf script -s ~/libexec/perf-core/scripts/python/syscall-counts.py
 ----
 
 Note that the location of the Python script given in the shell script
@@ -390,17 +390,17 @@ total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
 drwxr-xr-x 2 trz trz 4096 2010-01-26 22:29 bin
--rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-trace.py
-drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 Perf-Trace-Util
+-rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-script.py
+drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 perf-script-Util
 -rw-r--r-- 1 trz trz 1462 2010-01-26 22:30 syscall-counts.py
 ----
 
 Once you've done that (don't forget to do a new 'make install',
-otherwise your script won't show up at run-time), 'perf trace -l'
+otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf trace -l
+root@tropicana:~# perf script -l
 List of available trace scripts:
   workqueue-stats                      workqueue stats (ins/exe/create/destroy)
   wakeup-latency                       system-wide min/max/avg wakeup latency
@@ -409,19 +409,19 @@ List of available trace scripts:
   syscall-counts                       system-wide syscall counts
 ----
 
-You can now perform the record step via 'perf trace record':
+You can now perform the record step via 'perf script record':
 
-  # perf trace record syscall-counts
+  # perf script record syscall-counts
 
-and display the output using 'perf trace report':
+and display the output using 'perf script report':
 
-  # perf trace report syscall-counts
+  # perf script report syscall-counts
 
 STARTER SCRIPTS
 ---------------
 
 You can quickly get started writing a script for a particular set of
-trace data by generating a skeleton script using 'perf trace -g
+trace data by generating a skeleton script using 'perf script -g
 python' in the same directory as an existing perf.data trace file.
 That will generate a starter script containing a handler for each of
 the event types in the trace file; it simply prints every available
@@ -430,13 +430,13 @@ field for each event in the trace file.
 You can also look at the existing scripts in
 ~/libexec/perf-core/scripts/python for typical examples showing how to
 do basic things like aggregate event data, print results, etc.  Also,
-the check-perf-trace.py script, while not interesting for its results,
+the check-perf-script.py script, while not interesting for its results,
 attempts to exercise all of the main scripting features.
 
 EVENT HANDLERS
 --------------
 
-When perf trace is invoked using a trace script, a user-defined
+When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
 ignored (or passed to a 'trace_handled' function, see below) and the
@@ -463,7 +463,6 @@ The format file for the sched_wakep event defines the following fields
         field:unsigned char common_flags;
         field:unsigned char common_preempt_count;
         field:int common_pid;
-        field:int common_lock_depth;
 
         field:char comm[TASK_COMM_LEN];
         field:pid_t pid;
@@ -510,7 +509,7 @@ write a useful trace script.  The sections below cover the rest.
 SCRIPT LAYOUT
 -------------
 
-Every perf trace Python script should start by setting up a Python
+Every perf script Python script should start by setting up a Python
 module search path and 'import'ing a few support modules (see module
 descriptions below):
 
@@ -519,7 +518,7 @@ descriptions below):
  import sys
 
  sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-              '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+              '/scripts/python/perf-script-Util/lib/Perf/Trace')
 
  from perf_trace_context import *
  from Core import *
@@ -559,15 +558,15 @@ def trace_unhandled(event_name, context, common_cpu, common_secs,
 ----
 
 The remaining sections provide descriptions of each of the available
-built-in perf trace Python modules and their associated functions.
+built-in perf script Python modules and their associated functions.
 
 AVAILABLE MODULES AND FUNCTIONS
 -------------------------------
 
 The following sections describe the functions and variables available
-via the various perf trace Python modules.  To use the functions and
+via the various perf script Python modules.  To use the functions and
 variables from the given module, add the corresponding 'from XXXX
-import' line to your perf trace script.
+import' line to your perf script script.
 
 Core.py Module
 ~~~~~~~~~~~~~~
@@ -610,7 +609,7 @@ argument.
 Util.py Module
 ~~~~~~~~~~~~~~
 
-Various utility functions for use with perf trace:
+Various utility functions for use with perf script:
 
   nsecs(secs, nsecs) - returns total nsecs given secs/nsecs pair
   nsecs_secs(nsecs) - returns whole secs portion given nsecs
@@ -620,4 +619,4 @@ Various utility functions for use with perf trace:
 
 SEE ALSO
 --------
-linkperf:perf-trace[1]
+linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
new file mode 100644
index 000000000000..86c87e214b11
--- /dev/null
+++ b/tools/perf/Documentation/perf-script.txt
@@ -0,0 +1,188 @@
+perf-script(1)
+=============
+
+NAME
+----
+perf-script - Read perf.data (created by perf record) and display trace output
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [<options>]
+'perf script' [<options>] record <script> [<record-options>] <command>
+'perf script' [<options>] report <script> [script-args]
+'perf script' [<options>] <script> <required-script-args> [<record-options>] <command>
+'perf script' [<options>] <top-script> [script-args]
+
+DESCRIPTION
+-----------
+This command reads the input file and displays the trace recorded.
+
+There are several variants of perf script:
+
+  'perf script' to see a detailed trace of the workload that was
+  recorded.
+
+  You can also run a set of pre-canned scripts that aggregate and
+  summarize the raw trace data in various ways (the list of scripts is
+  available via 'perf script -l').  The following variants allow you to
+  record and run those scripts:
+
+  'perf script record <script> <command>' to record the events required
+  for 'perf script report'.  <script> is the name displayed in the
+  output of 'perf script --list' i.e. the actual script name minus any
+  language extension.  If <command> is not specified, the events are
+  recorded using the -a (system-wide) 'perf record' option.
+
+  'perf script report <script> [args]' to run and display the results
+  of <script>.  <script> is the name displayed in the output of 'perf
+  trace --list' i.e. the actual script name minus any language
+  extension.  The perf.data output from a previous run of 'perf script
+  record <script>' is used and should be present for this command to
+  succeed.  [args] refers to the (mainly optional) args expected by
+  the script.
+
+  'perf script <script> <required-script-args> <command>' to both
+  record the events required for <script> and to run the <script>
+  using 'live-mode' i.e. without writing anything to disk.  <script>
+  is the name displayed in the output of 'perf script --list' i.e. the
+  actual script name minus any language extension.  If <command> is
+  not specified, the events are recorded using the -a (system-wide)
+  'perf record' option.  If <script> has any required args, they
+  should be specified before <command>.  This mode doesn't allow for
+  optional script args to be specified; if optional script args are
+  desired, they can be specified using separate 'perf script record'
+  and 'perf script report' commands, with the stdout of the record step
+  piped to the stdin of the report script, using the '-o -' and '-i -'
+  options of the corresponding commands.
+
+  'perf script <top-script>' to both record the events required for
+  <top-script> and to run the <top-script> using 'live-mode'
+  i.e. without writing anything to disk.  <top-script> is the name
+  displayed in the output of 'perf script --list' i.e. the actual
+  script name minus any language extension; a <top-script> is defined
+  as any script name ending with the string 'top'.
+
+  [<record-options>] can be passed to the record steps of 'perf script
+  record' and 'live-mode' variants; this isn't possible however for
+  <top-script> 'live-mode' or 'perf script report' variants.
+
+  See the 'SEE ALSO' section for links to language-specific
+  information on how to write and run your own trace scripts.
+
+OPTIONS
+-------
+<command>...::
+        Any command you can specify in a shell.
+
+-D::
+--dump-raw-script=::
+        Display verbose dump of the trace data.
+
+-L::
+--Latency=::
+        Show latency attributes (irqs/preemption disabled, etc).
+
+-l::
+--list=::
+        Display a list of available trace scripts.
+
+-s ['lang']::
+--script=::
+        Process trace data with the given script ([lang]:script[.ext]).
+        If the string 'lang' is specified in place of a script name, a
+        list of supported languages will be displayed instead.
+
+-g::
+--gen-script=::
+        Generate perf-script.[ext] starter script for given language,
+        using current perf.data.
+
+-a::
+        Force system-wide collection.  Scripts run without a <command>
+        normally use -a by default, while scripts run with a <command>
+        normally don't - this option allows the latter to be run in
+        system-wide mode.
+
+-i::
+--input=::
+        Input file name.
+
+-d::
+--debug-mode::
+        Do various checks like samples ordering and lost events.
+
+-f::
+--fields::
+        Comma separated list of fields to print. Options are:
+        comm, tid, pid, time, cpu, event, trace, sym. 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,sym  and -f trace:time,cpu,trace
+
+                perf script -f <fields>
+
+        is equivalent to:
+
+                perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
+    
+        i.e., the specified fields apply to all event types if the type string
+        is not given.
+    
+        The arguments are processed in the order received. A later usage can
+        reset a prior request. e.g.:
+    
+                -f trace: -f comm,tid,time,sym
+    
+        The first -f suppresses trace events (field list is ""), but then the
+        second invocation sets the fields to comm,tid,time,sym. In this case a
+        warning is given to the user:
+    
+                "Overriding previous field request for all events."
+    
+        Alternativey, consider the order:
+    
+                -f comm,tid,time,sym -f trace:
+    
+        The first -f sets the fields for all events and the second -f
+        suppresses trace events. The user is given a warning message about
+        the override, and the result of the above is that only S/W and H/W
+        events are displayed with the given fields.
+    
+        For the 'wildcard' option if a user selected field is invalid for an
+        event type, a message is displayed to the user that the option is
+        ignored for that type. For example:
+    
+                $ perf script -f comm,tid,trace
+                'trace' not valid for hardware events. Ignoring.
+                'trace' not valid for software events. Ignoring.
+    
+        Alternatively, if the type is given an invalid field is specified it
+        is an error. For example:
+    
+        perf script -v -f sw:comm,tid,trace
+        'trace' not valid for software events.
+    
+        At this point usage is displayed, and perf-script exits.
+    
+        Finally, a user may not set fields to none for all event types.
+        i.e., -f "" is not allowed.
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-G::
+--hide-call-graph::
+        When printing symbols do not display call chain.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-script-perl[1],
+linkperf:perf-script-python[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4b3a2d46b437..918cc38ee6d1 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -8,8 +8,8 @@ perf-stat - Run a command and gather performance counter statistics
 SYNOPSIS
 --------
 [verse]
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] <command>
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] -- <command> [<options>]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
@@ -35,24 +35,65 @@ OPTIONS
         child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing pid
+        stat events on existing process id
+
+-t::
+--tid=<tid>::
+        stat events on existing thread id
+
 
 -a::
-        system-wide collection
+--all-cpus::
+        system-wide collection from all CPUs
 
 -c::
-        scale counter values
+--scale::
+        scale/normalize counter values
+
+-r::
+--repeat=<n>::
+        repeat command and print average + stddev (max: 100)
 
 -B::
+--big-num::
         print large numbers with thousands' separators according to locale
 
 -C::
 --cpu=::
-Count only on the list of cpus provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Count only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 In per-thread mode, this option is ignored. The -a option is still necessary
 to activate system-wide monitoring. Default is to count on all CPUs.
 
+-A::
+--no-aggr::
+Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
+This option is only valid in system-wide mode.
+
+-n::
+--null::
+        null run - don't start any counters
+
+-v::
+--verbose::
+        be more verbose (show counter open errors, etc)
+
+-x SEP::
+--field-separator SEP::
+print counts using a CSV-style output to make it easy to import directly into
+spreadsheets. Columns are separated by the string specified in SEP.
+
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 1c4b5f5b7f71..2c3b462f64b0 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command does assorted sanity tests, initially thru linked routines but
+This command does assorted sanity tests, initially through linked routines but
 also will look for a directory with more tests in the form of scripts.
 
 OPTIONS
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 4b1788355eca..d7b79e2ba2ad 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -38,6 +38,8 @@ OPTIONS
 --process::
         Select the processes to display, by name or PID
 
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 1f9687663f2a..f6eb1cdafb77 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command generates and displays a performance counter profile in realtime.
+This command generates and displays a performance counter profile in real time.
 
 
 OPTIONS
@@ -27,8 +27,8 @@ OPTIONS
 
 -C <cpu-list>::
 --cpu=<cpu>::
-Monitor only on the list of cpus provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 Default is to monitor all CPUS.
 
 -d <seconds>::
@@ -50,6 +50,10 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
         Only display functions with more events than this.
 
+-g::
+--group::
+        Put the counters into a counter group.
+
 -F <freq>::
 --freq=<freq>::
         Profile at this frequency.
@@ -68,7 +72,11 @@ Default is to monitor all CPUS.
 
 -p <pid>::
 --pid=<pid>::
-        Profile events on existing pid.
+        Profile events on existing Process ID.
+
+-t <tid>::
+--tid=<tid>::
+        Profile events on existing thread ID.
 
 -r <priority>::
 --realtime=<priority>::
@@ -78,6 +86,18 @@ Default is to monitor all CPUS.
 --sym-annotate=<symbol>::
         Annotate this symbol.
 
+-K::
+--hide_kernel_symbols::
+        Hide kernel symbols.
+
+-U::
+--hide_user_symbols::
+        Hide user symbols.
+
+-D::
+--dump-symtab::
+        Dump the symbol table used for profiling.
+
 -v::
 --verbose::
         Be more verbose (show counter open errors, etc).
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
deleted file mode 100644
index 122ec9dc4853..000000000000
--- a/tools/perf/Documentation/perf-trace.txt
+++ /dev/null
@@ -1,70 +0,0 @@
-perf-trace(1)
-=============
-
-NAME
-----
-perf-trace - Read perf.data (created by perf record) and display trace output
-
-SYNOPSIS
---------
-[verse]
-'perf trace' {record <script> | report <script> [args] }
-
-DESCRIPTION
------------
-This command reads the input file and displays the trace recorded.
-
-There are several variants of perf trace:
-
-  'perf trace' to see a detailed trace of the workload that was
-  recorded.
-
-  You can also run a set of pre-canned scripts that aggregate and
-  summarize the raw trace data in various ways (the list of scripts is
-  available via 'perf trace -l').  The following variants allow you to
-  record and run those scripts:
-
-  'perf trace record <script>' to record the events required for 'perf
-  trace report'.  <script> is the name displayed in the output of
-  'perf trace --list' i.e. the actual script name minus any language
-  extension.
-
-  'perf trace report <script>' to run and display the results of
-  <script>.  <script> is the name displayed in the output of 'perf
-  trace --list' i.e. the actual script name minus any language
-  extension.  The perf.data output from a previous run of 'perf trace
-  record <script>' is used and should be present for this command to
-  succeed.
-
-  See the 'SEE ALSO' section for links to language-specific
-  information on how to write and run your own trace scripts.
-
-OPTIONS
--------
--D::
---dump-raw-trace=::
-        Display verbose dump of the trace data.
-
--L::
---Latency=::
-        Show latency attributes (irqs/preemption disabled, etc).
-
--l::
---list=::
-        Display a list of available trace scripts.
-
--s ['lang']::
---script=::
-        Process trace data with the given script ([lang]:script[.ext]).
-        If the string 'lang' is specified in place of a script name, a
-        list of supported languages will be displayed instead.
-
--g::
---gen-script=::
-        Generate perf-trace.[ext] starter script for given language,
-        using current perf.data.
-
-SEE ALSO
---------
-linkperf:perf-record[1], linkperf:perf-trace-perl[1],
-linkperf:perf-trace-python[1]
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8c7fc0c8f0b8..c12659d8cb26 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -7,6 +7,7 @@ include/linux/stringify.h
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
+arch/*/lib/memcpy*.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 1950e19af1cf..940257b5774e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -3,7 +3,9 @@ ifeq ("$(origin O)", "command line")
 endif
 
 # The default target of this Makefile is...
-all::
+all:
+
+include config/utilities.mak
 
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
@@ -11,152 +13,18 @@ OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
-# Define V=1 to have a more verbose compile.
-# Define V=2 to have an even more verbose compile.
-#
-# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf()
-# or vsnprintf() return -1 instead of number of characters which would
-# have been written to the final string if enough space had been available.
-#
-# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds
-# when attempting to read from an fopen'ed directory.
-#
-# Define NO_OPENSSL environment variable if you do not have OpenSSL.
-# This also implies MOZILLA_SHA1.
-#
-# Define CURLDIR=/foo/bar if your curl header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define EXPATDIR=/foo/bar if your expat header and library files are in
-# /foo/bar/include and /foo/bar/lib directories.
-#
-# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent.
-#
-# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks
-# d_type in struct dirent (latest Cygwin -- will be fixed soonish).
-#
-# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.)
-# do not support the 'size specifiers' introduced by C99, namely ll, hh,
-# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t).
-# some C compilers supported these specifiers prior to C99 as an extension.
-#
-# Define NO_STRCASESTR if you don't have strcasestr.
-#
-# Define NO_MEMMEM if you don't have memmem.
-#
-# Define NO_STRTOUMAX if you don't have strtoumax in the C library.
-# If your compiler also does not support long long or does not have
-# strtoull, define NO_STRTOULL.
-#
-# Define NO_SETENV if you don't have setenv in the C library.
-#
-# Define NO_UNSETENV if you don't have unsetenv in the C library.
-#
-# Define NO_MKDTEMP if you don't have mkdtemp in the C library.
-#
-# Define NO_SYS_SELECT_H if you don't have sys/select.h.
-#
-# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link.
-# Enable it on Windows.  By default, symrefs are still used.
-#
-# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability
-# tests.  These tests take up a significant amount of the total test time
-# but are not needed unless you plan to talk to SVN repos.
-#
-# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink
-# installed in /sw, but don't want PERF to link against any libraries
-# installed there.  If defined you may specify your own (or Fink's)
-# include directories and library directories by defining CFLAGS
-# and LDFLAGS appropriately.
-#
-# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X,
-# have DarwinPorts installed in /opt/local, but don't want PERF to
-# link against any libraries installed there.  If defined you may
-# specify your own (or DarwinPort's) include directories and
-# library directories by defining CFLAGS and LDFLAGS appropriately.
-#
-# Define PPC_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for PowerPC.
-#
-# Define ARM_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine optimized for ARM.
-#
-# Define MOZILLA_SHA1 environment variable when running make to make use of
-# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast
-# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default
-# choice) has very fast version optimized for i586.
+# Define V to have a more verbose compile.
 #
-# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin).
+# Define PYTHON to point to the python binary if the default
+# `python' is not correct; for example: PYTHON=python2
 #
-# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin).
-#
-# Define NEEDS_SOCKET if linking with libc is not enough (SunOS,
-# Patrick Mauritz).
-#
-# Define NO_MMAP if you want to avoid mmap.
-#
-# Define NO_PTHREADS if you do not have or do not want to use Pthreads.
-#
-# Define NO_PREAD if you have a problem with pread() system call (e.g.
-# cygwin.dll before v1.5.22).
-#
-# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is
-# generally faster on your platform than accessing the working directory.
-#
-# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support
-# the executable mode bit, but doesn't really do so.
-#
-# Define NO_IPV6 if you lack IPv6 support and getaddrinfo().
-#
-# Define NO_SOCKADDR_STORAGE if your platform does not have struct
-# sockaddr_storage.
-#
-# Define NO_ICONV if your libc does not properly support iconv.
-#
-# Define OLD_ICONV if your library has an old iconv(), where the second
-# (input buffer pointer) parameter is declared with type (const char **).
-#
-# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound.
-#
-# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib"
-# that tells runtime paths to dynamic libraries;
-# "-Wl,-rpath=/path/lib" is used instead.
-#
-# Define USE_NSEC below if you want perf to care about sub-second file mtimes
-# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and
-# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely
-# randomly break unless your underlying filesystem supports those sub-second
-# times (my ext3 doesn't).
-#
-# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of
-# "st_ctim"
-#
-# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec"
-# available.  This automatically turns USE_NSEC off.
-#
-# Define USE_STDEV below if you want perf to care about the underlying device
-# change being considered an inode change from the update-index perspective.
-#
-# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks
-# field that counts the on-disk footprint in 512-byte blocks.
+# Define PYTHON_CONFIG to point to the python-config binary if
+# the default `$(PYTHON)-config' is not correct.
 #
 # Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8
 #
 # Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72.
 #
-# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's
-# MakeMaker (e.g. using ActiveState under Cygwin).
-#
-# Define NO_PERL if you do not want Perl scripts or libraries at all.
-#
-# Define INTERNAL_QSORT to use Git's implementation of qsort(), which
-# is a simplified version of the merge sort used in glibc. This is
-# recommended if Git triggers O(n^2) behavior in your platform's qsort().
-#
-# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call
-# your external grep (e.g., if your system lacks grep, if its grep is
-# broken, or spawning external process is slower than built-in grep perf has).
-#
 # Define LDFLAGS=-static to build a static binary.
 #
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
@@ -167,12 +35,7 @@ $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
         @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 -include $(OUTPUT)PERF-VERSION-FILE
 
-uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not')
-uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not')
-uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not')
-uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not')
-uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not')
-uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not')
+uname_M := $(shell uname -m 2>/dev/null || echo not)
 
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/arm.*/arm/ -e s/sa110/arm/ \
@@ -180,16 +43,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
                                   -e s/sh[234].*/sh/ )
 
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
 # Additional ARCH settings for x86
 ifeq ($(ARCH),i386)
         ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
-        ARCH := x86
+        ARCH := x86
+        IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1)
+        ifeq (${IS_X86_64}, 1)
+                RAW_ARCH := x86_64
+                ARCH_CFLAGS := -DARCH_X86_64
+                ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+        endif
 endif
 
-# CFLAGS and LDFLAGS are for the users to override from the command line.
-
 #
 # Include saner warnings here, which can catch bugs:
 #
@@ -201,13 +71,11 @@ EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wshadow
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Winit-self
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wpacked
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wredundant-decls
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstack-protector
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-aliasing=3
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-default
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-enum
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wno-system-headers
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wundef
-EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wvolatile-register-var
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wwrite-strings
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wbad-function-cast
 EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-declarations
@@ -224,7 +92,7 @@ ifndef PERF_DEBUG
   CFLAGS_OPTIMIZE = -O6
 endif
 
-CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
@@ -265,32 +133,28 @@ lib = lib
 
 export prefix bindir sharedir sysconfdir
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
 RM = rm -f
 MKDIR = mkdir
-TAR = tar
 FIND = find
 INSTALL = install
-RPMBUILD = rpmbuild
-PTHREAD_LIBS = -lpthread
 
 # sparse is architecture-neutral, which means that we need to tell it
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
-ifeq ($(V), 2)
-        QUIET_STDERR = ">/dev/null"
-else
-        QUIET_STDERR = ">/dev/null 2>&1"
-endif
-
--include feature-tests.mak
+-include config/feature-tests.mak
 
 ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y)
         CFLAGS := $(CFLAGS) -fstack-protector-all
 endif
 
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wstack-protector),y)
+       CFLAGS := $(CFLAGS) -Wstack-protector
+endif
+
+ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -Wvolatile-register-var),y)
+       CFLAGS := $(CFLAGS) -Wvolatile-register-var
+endif
 
 ### --- END CONFIGURATION SECTION ---
 
@@ -302,46 +166,39 @@ BASIC_LDFLAGS =
 
 # Guard against environment variables
 BUILTIN_OBJS =
-BUILT_INS =
-COMPAT_CFLAGS =
-COMPAT_OBJS =
 LIB_H =
 LIB_OBJS =
-SCRIPT_PERL =
+PYRF_OBJS =
 SCRIPT_SH =
-TEST_PROGRAMS =
 
 SCRIPT_SH += perf-archive.sh
 
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
+
+$(OUTPUT)python/perf.so: $(PYRF_OBJS)
+        $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
+          --quiet build_ext \
+          --build-lib='$(OUTPUT)python' \
+          --build-temp='$(OUTPUT)python/temp'
 #
 # No Perl scripts right now:
 #
 
-# SCRIPT_PERL += perf-add--interactive.perl
-
-SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \
-          $(patsubst %.perl,%,$(SCRIPT_PERL))
-
-# Empty...
-EXTRA_PROGRAMS =
-
-# ... and all the rest that could be moved out of bindir to perfexecdir
-PROGRAMS += $(EXTRA_PROGRAMS)
+SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
 #
 # Single 'perf' binary right now:
 #
 PROGRAMS += $(OUTPUT)perf
 
-# List built-in command $C whose implementation cmd_$C() is not in
-# builtin-$C.o but is linked in as part of some other command.
-#
+LANG_BINDINGS =
 
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
 # what 'all' will build but not install in perfexecdir
-OTHER_PROGRAMS = $(OUTPUT)perf$X
+OTHER_PROGRAMS = $(OUTPUT)perf
 
 # Set paths to tools early so that they can be used for version tests.
 ifndef SHELL_PATH
@@ -358,11 +215,13 @@ LIB_FILE=$(OUTPUT)libperf.a
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/linux/const.h
 LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
 LIB_H += util/include/linux/compiler.h
+LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
@@ -372,6 +231,7 @@ LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
 LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
+LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += util/include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
@@ -380,13 +240,18 @@ LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
 LIB_H += util/include/dwarf-regs.h
+LIB_H += util/include/asm/dwarf2.h
+LIB_H += util/include/asm/cpufeature.h
 LIB_H += perf.h
+LIB_H += util/annotate.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/event.h
+LIB_H += util/evsel.h
+LIB_H += util/evlist.h
 LIB_H += util/exec_cmd.h
 LIB_H += util/types.h
 LIB_H += util/levenshtein.h
@@ -395,11 +260,13 @@ LIB_H += util/parse-options.h
 LIB_H += util/parse-events.h
 LIB_H += util/quote.h
 LIB_H += util/util.h
+LIB_H += util/xyarray.h
 LIB_H += util/header.h
 LIB_H += util/help.h
 LIB_H += util/session.h
 LIB_H += util/strbuf.h
 LIB_H += util/strlist.h
+LIB_H += util/strfilter.h
 LIB_H += util/svghelper.h
 LIB_H += util/run-command.h
 LIB_H += util/sigchain.h
@@ -409,20 +276,27 @@ LIB_H += util/values.h
 LIB_H += util/sort.h
 LIB_H += util/hist.h
 LIB_H += util/thread.h
+LIB_H += util/thread_map.h
 LIB_H += util/trace-event.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
+LIB_H += util/top.h
+LIB_H += $(ARCH_INCLUDE)
+LIB_H += util/cgroup.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
+LIB_OBJS += $(OUTPUT)util/annotate.o
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
 LIB_OBJS += $(OUTPUT)util/debugfs.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
+LIB_OBJS += $(OUTPUT)util/evlist.o
+LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
 LIB_OBJS += $(OUTPUT)util/help.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
@@ -437,6 +311,8 @@ LIB_OBJS += $(OUTPUT)util/quote.o
 LIB_OBJS += $(OUTPUT)util/strbuf.o
 LIB_OBJS += $(OUTPUT)util/string.o
 LIB_OBJS += $(OUTPUT)util/strlist.o
+LIB_OBJS += $(OUTPUT)util/strfilter.o
+LIB_OBJS += $(OUTPUT)util/top.o
 LIB_OBJS += $(OUTPUT)util/usage.o
 LIB_OBJS += $(OUTPUT)util/wrapper.o
 LIB_OBJS += $(OUTPUT)util/sigchain.o
@@ -451,6 +327,7 @@ LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
 LIB_OBJS += $(OUTPUT)util/thread.o
+LIB_OBJS += $(OUTPUT)util/thread_map.o
 LIB_OBJS += $(OUTPUT)util/trace-event-parse.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
@@ -460,7 +337,9 @@ LIB_OBJS += $(OUTPUT)util/sort.o
 LIB_OBJS += $(OUTPUT)util/hist.o
 LIB_OBJS += $(OUTPUT)util/probe-event.o
 LIB_OBJS += $(OUTPUT)util/util.o
+LIB_OBJS += $(OUTPUT)util/xyarray.o
 LIB_OBJS += $(OUTPUT)util/cpumap.o
+LIB_OBJS += $(OUTPUT)util/cgroup.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 
@@ -469,9 +348,13 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+ifeq ($(RAW_ARCH),x86_64)
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
+BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
 BUILTIN_OBJS += $(OUTPUT)builtin-help.o
 BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
 BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
@@ -482,7 +365,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-report.o
 BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
 BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
 BUILTIN_OBJS += $(OUTPUT)builtin-top.o
-BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+BUILTIN_OBJS += $(OUTPUT)builtin-script.o
 BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
 BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
 BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
@@ -492,6 +375,20 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 
 PERFLIBS = $(LIB_FILE)
 
+# Files needed for the python binding, perf.so
+# pyrf is just an internal name needed for all those wrappers.
+# This has to be in sync with what is in the 'sources' variable in
+# tools/perf/util/setup.py
+
+PYRF_OBJS += $(OUTPUT)util/cpumap.o
+PYRF_OBJS += $(OUTPUT)util/ctype.o
+PYRF_OBJS += $(OUTPUT)util/evlist.o
+PYRF_OBJS += $(OUTPUT)util/evsel.o
+PYRF_OBJS += $(OUTPUT)util/python.o
+PYRF_OBJS += $(OUTPUT)util/thread_map.o
+PYRF_OBJS += $(OUTPUT)util/util.o
+PYRF_OBJS += $(OUTPUT)util/xyarray.o
+
 #
 # Platform specific tweaks
 #
@@ -504,7 +401,7 @@ PERFLIBS = $(LIB_FILE)
 -include config.mak
 
 ifndef NO_DWARF
-FLAGS_DWARF=$(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
+FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
 ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y)
         msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
         NO_DWARF := 1
@@ -513,22 +410,6 @@ endif # NO_DWARF
 
 -include arch/$(ARCH)/Makefile
 
-ifeq ($(uname_S),Darwin)
-        ifndef NO_FINK
-                ifeq ($(shell test -d /sw/lib && echo y),y)
-                        BASIC_CFLAGS += -I/sw/include
-                        BASIC_LDFLAGS += -L/sw/lib
-                endif
-        endif
-        ifndef NO_DARWIN_PORTS
-                ifeq ($(shell test -d /opt/local/lib && echo y),y)
-                        BASIC_CFLAGS += -I/opt/local/include
-                        BASIC_LDFLAGS += -L/opt/local/lib
-                endif
-        endif
-        PTHREAD_LIBS =
-endif
-
 ifneq ($(OUTPUT),)
         BASIC_CFLAGS += -I$(OUTPUT)
 endif
@@ -551,7 +432,7 @@ ifndef NO_DWARF
 ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
         msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
 else
-        BASIC_CFLAGS += -I/usr/include/elfutils -DDWARF_SUPPORT
+        BASIC_CFLAGS += -DDWARF_SUPPORT
         EXTLIBS += -lelf -ldw
         LIB_OBJS += $(OUTPUT)util/probe-finder.o
 endif # PERF_HAVE_DWARF_REGS
@@ -573,6 +454,7 @@ else
                 LIB_OBJS += $(OUTPUT)util/ui/browsers/annotate.o
                 LIB_OBJS += $(OUTPUT)util/ui/browsers/hists.o
                 LIB_OBJS += $(OUTPUT)util/ui/browsers/map.o
+                LIB_OBJS += $(OUTPUT)util/ui/browsers/top.o
                 LIB_OBJS += $(OUTPUT)util/ui/helpline.o
                 LIB_OBJS += $(OUTPUT)util/ui/progress.o
                 LIB_OBJS += $(OUTPUT)util/ui/util.o
@@ -582,38 +464,97 @@ else
                 LIB_H += util/ui/libslang.h
                 LIB_H += util/ui/progress.h
                 LIB_H += util/ui/util.h
+                LIB_H += util/ui/ui.h
         endif
 endif
 
 ifdef NO_LIBPERL
         BASIC_CFLAGS += -DNO_LIBPERL
 else
-        PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
+       PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
+       PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
+       PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
         PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
         FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
         ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED)),y)
                 BASIC_CFLAGS += -DNO_LIBPERL
         else
-                ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
+               ALL_LDFLAGS += $(PERL_EMBED_LDFLAGS)
+               EXTLIBS += $(PERL_EMBED_LIBADD)
                 LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o
                 LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o
         endif
 endif
 
-ifdef NO_LIBPYTHON
-        BASIC_CFLAGS += -DNO_LIBPYTHON
+disable-python = $(eval $(disable-python_code))
+define disable-python_code
+  BASIC_CFLAGS += -DNO_LIBPYTHON
+  $(if $(1),$(warning No $(1) was found))
+  $(warning Python support won't be built)
+endef
+
+override PYTHON := \
+  $(call get-executable-or-default,PYTHON,python)
+
+ifndef PYTHON
+  $(call disable-python,python interpreter)
+  python-clean :=
 else
-        PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
-        PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
-        FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-        ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
-                BASIC_CFLAGS += -DNO_LIBPYTHON
-        else
-                ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
-                LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
-                LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
-        endif
+
+  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
+
+  python-clean := $(PYTHON_WORD) util/setup.py clean \
+    --build-lib='$(OUTPUT)python' \
+    --build-temp='$(OUTPUT)python/temp'
+
+  ifdef NO_LIBPYTHON
+    $(call disable-python)
+  else
+
+    override PYTHON_CONFIG := \
+      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+
+    ifndef PYTHON_CONFIG
+      $(call disable-python,python-config tool)
+    else
+
+      PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+      PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+      PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
+      PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+      FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+
+      ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y)
+        $(call disable-python,Python.h (for Python 2.x))
+      else
+
+        ifneq ($(call try-cc,$(SOURCE_PYTHON_VERSION),$(FLAGS_PYTHON_EMBED)),y)
+          $(warning Python 3 is not yet supported; please set)
+          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
+          $(warning If you also have Python 2 installed, then)
+          $(warning try something like:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make PYTHON=python2)
+          $(warning $(and ,))
+          $(warning Otherwise, disable Python support entirely:)
+          $(warning $(and ,))
+          $(warning $(and ,)  make NO_LIBPYTHON=1)
+          $(warning $(and ,))
+          $(error   $(and ,))
+        else
+          ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+          EXTLIBS += $(PYTHON_EMBED_LIBADD)
+          LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o
+          LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o
+          LANG_BINDINGS += $(OUTPUT)python/perf.so
+        endif
+
+      endif
+    endif
+  endif
 endif
 
 ifdef NO_DEMANGLE
@@ -653,186 +594,14 @@ else
         endif
 endif
 
-ifndef CC_LD_DYNPATH
-        ifdef NO_R_TO_GCC_LINKER
-                # Some gcc does not accept and pass -R to the linker to specify
-                # the runtime dynamic library path.
-                CC_LD_DYNPATH = -Wl,-rpath,
-        else
-                CC_LD_DYNPATH = -R
-        endif
-endif
 
-ifdef NEEDS_SOCKET
-        EXTLIBS += -lsocket
-endif
-ifdef NEEDS_NSL
-        EXTLIBS += -lnsl
-endif
-ifdef NO_D_TYPE_IN_DIRENT
-        BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT
-endif
-ifdef NO_D_INO_IN_DIRENT
-        BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT
-endif
-ifdef NO_ST_BLOCKS_IN_STRUCT_STAT
-        BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT
-endif
-ifdef USE_NSEC
-        BASIC_CFLAGS += -DUSE_NSEC
-endif
-ifdef USE_ST_TIMESPEC
-        BASIC_CFLAGS += -DUSE_ST_TIMESPEC
-endif
-ifdef NO_NSEC
-        BASIC_CFLAGS += -DNO_NSEC
-endif
-ifdef NO_C99_FORMAT
-        BASIC_CFLAGS += -DNO_C99_FORMAT
-endif
-ifdef SNPRINTF_RETURNS_BOGUS
-        COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS
-        COMPAT_OBJS += $(OUTPUT)compat/snprintf.o
-endif
-ifdef FREAD_READS_DIRECTORIES
-        COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES
-        COMPAT_OBJS += $(OUTPUT)compat/fopen.o
-endif
-ifdef NO_SYMLINK_HEAD
-        BASIC_CFLAGS += -DNO_SYMLINK_HEAD
-endif
-ifdef NO_STRCASESTR
-        COMPAT_CFLAGS += -DNO_STRCASESTR
-        COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o
-endif
-ifdef NO_STRTOUMAX
-        COMPAT_CFLAGS += -DNO_STRTOUMAX
-        COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o
-endif
-ifdef NO_STRTOULL
-        COMPAT_CFLAGS += -DNO_STRTOULL
-endif
-ifdef NO_SETENV
-        COMPAT_CFLAGS += -DNO_SETENV
-        COMPAT_OBJS += $(OUTPUT)compat/setenv.o
-endif
-ifdef NO_MKDTEMP
-        COMPAT_CFLAGS += -DNO_MKDTEMP
-        COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o
-endif
-ifdef NO_UNSETENV
-        COMPAT_CFLAGS += -DNO_UNSETENV
-        COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o
-endif
-ifdef NO_SYS_SELECT_H
-        BASIC_CFLAGS += -DNO_SYS_SELECT_H
-endif
-ifdef NO_MMAP
-        COMPAT_CFLAGS += -DNO_MMAP
-        COMPAT_OBJS += $(OUTPUT)compat/mmap.o
+ifdef NO_STRLCPY
+        BASIC_CFLAGS += -DNO_STRLCPY
 else
-        ifdef USE_WIN32_MMAP
-                COMPAT_CFLAGS += -DUSE_WIN32_MMAP
-                COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o
+        ifneq ($(call try-cc,$(SOURCE_STRLCPY),),y)
+                BASIC_CFLAGS += -DNO_STRLCPY
         endif
 endif
-ifdef NO_PREAD
-        COMPAT_CFLAGS += -DNO_PREAD
-        COMPAT_OBJS += $(OUTPUT)compat/pread.o
-endif
-ifdef NO_FAST_WORKING_DIRECTORY
-        BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
-endif
-ifdef NO_TRUSTABLE_FILEMODE
-        BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE
-endif
-ifdef NO_IPV6
-        BASIC_CFLAGS += -DNO_IPV6
-endif
-ifdef NO_UINTMAX_T
-        BASIC_CFLAGS += -Duintmax_t=uint32_t
-endif
-ifdef NO_SOCKADDR_STORAGE
-ifdef NO_IPV6
-        BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in
-else
-        BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6
-endif
-endif
-ifdef NO_INET_NTOP
-        LIB_OBJS += $(OUTPUT)compat/inet_ntop.o
-endif
-ifdef NO_INET_PTON
-        LIB_OBJS += $(OUTPUT)compat/inet_pton.o
-endif
-
-ifdef NO_ICONV
-        BASIC_CFLAGS += -DNO_ICONV
-endif
-
-ifdef OLD_ICONV
-        BASIC_CFLAGS += -DOLD_ICONV
-endif
-
-ifdef NO_DEFLATE_BOUND
-        BASIC_CFLAGS += -DNO_DEFLATE_BOUND
-endif
-
-ifdef PPC_SHA1
-        SHA1_HEADER = "ppc/sha1.h"
-        LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o
-else
-ifdef ARM_SHA1
-        SHA1_HEADER = "arm/sha1.h"
-        LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o
-else
-ifdef MOZILLA_SHA1
-        SHA1_HEADER = "mozilla-sha1/sha1.h"
-        LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o
-else
-        SHA1_HEADER = <openssl/sha.h>
-        EXTLIBS += $(LIB_4_CRYPTO)
-endif
-endif
-endif
-ifdef NO_PERL_MAKEMAKER
-        export NO_PERL_MAKEMAKER
-endif
-ifdef NO_HSTRERROR
-        COMPAT_CFLAGS += -DNO_HSTRERROR
-        COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o
-endif
-ifdef NO_MEMMEM
-        COMPAT_CFLAGS += -DNO_MEMMEM
-        COMPAT_OBJS += $(OUTPUT)compat/memmem.o
-endif
-ifdef INTERNAL_QSORT
-        COMPAT_CFLAGS += -DINTERNAL_QSORT
-        COMPAT_OBJS += $(OUTPUT)compat/qsort.o
-endif
-ifdef RUNTIME_PREFIX
-        COMPAT_CFLAGS += -DRUNTIME_PREFIX
-endif
-
-ifdef DIR_HAS_BSD_GROUP_SEMANTICS
-        COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS
-endif
-ifdef NO_EXTERNAL_GREP
-        BASIC_CFLAGS += -DNO_EXTERNAL_GREP
-endif
-
-ifeq ($(PERL_PATH),)
-NO_PERL=NoThanks
-endif
-
-QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
-QUIET_SUBDIR1  =
-
-ifneq ($(findstring $(MAKEFLAGS),w),w)
-PRINT_DIR = --no-print-directory
-else # "make -w"
-NO_SUBDIR = :
-endif
 
 ifneq ($(findstring $(MAKEFLAGS),s),s)
 ifndef V
@@ -840,14 +609,7 @@ ifndef V
         QUIET_AR       = @echo '   ' AR $@;
         QUIET_LINK     = @echo '   ' LINK $@;
         QUIET_MKDIR    = @echo '   ' MKDIR $@;
-        QUIET_BUILT_IN = @echo '   ' BUILTIN $@;
         QUIET_GEN      = @echo '   ' GEN $@;
-        QUIET_SUBDIR0  = +@subdir=
-        QUIET_SUBDIR1  = ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
-                         $(MAKE) $(PRINT_DIR) -C $$subdir
-        export V
-        export QUIET_GEN
-        export QUIET_BUILT_IN
 endif
 endif
 
@@ -857,7 +619,6 @@ endif
 
 # Shell quote (do not use $(call) to accommodate ancient setups);
 
-SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER))
 ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
 
 DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
@@ -871,47 +632,38 @@ htmldir_SQ = $(subst ','\'',$(htmldir))
 prefix_SQ = $(subst ','\'',$(prefix))
 
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
-PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
-
-LIBS = $(PERFLIBS) $(EXTLIBS)
 
-BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
-        $(COMPAT_CFLAGS)
-LIB_OBJS += $(COMPAT_OBJS)
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
+ALL_CFLAGS += $(ARCH_CFLAGS)
 ALL_LDFLAGS += $(BASIC_LDFLAGS)
 
-export TAR INSTALL DESTDIR SHELL_PATH
+export INSTALL SHELL_PATH
 
 
 ### Build rules
 
 SHELL = $(SHELL_PATH)
 
-all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS
-ifneq (,$X)
-        $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
-endif
-
-all::
+all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 
 please_set_SHELL_PATH_to_a_more_modern_shell:
         @$$(:)
 
 shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell
 
-strip: $(PROGRAMS) $(OUTPUT)perf$X
-        $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X
+strip: $(PROGRAMS) $(OUTPUT)perf
+        $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf
 
 $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \
                 '-DPERF_HTML_PATH="$(htmldir_SQ)"' \
                 $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@
 
-$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
-        $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(OUTPUT)perf.o \
-                $(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS)
+$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS)
+        $(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \
+               $(BUILTIN_OBJS) $(LIBS) -o $@
 
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
@@ -925,39 +677,17 @@ $(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPU
                 '-DPERF_MAN_PATH="$(mandir_SQ)"' \
                 '-DPERF_INFO_PATH="$(infodir_SQ)"' $<
 
-$(BUILT_INS): $(OUTPUT)perf$X
-        $(QUIET_BUILT_IN)$(RM) $@ && \
-        ln perf$X $@ 2>/dev/null || \
-        ln -s perf$X $@ 2>/dev/null || \
-        cp perf$X $@
-
 $(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt
 
 $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
         $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
-$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
-        $(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \
-        sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \
-            -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \
-            -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \
-            -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
-            -e 's/@@NO_CURL@@/$(NO_CURL)/g' \
-            $@.sh > $(OUTPUT)$@+ && \
-        chmod +x $(OUTPUT)$@+ && \
-        mv $(OUTPUT)$@+ $(OUTPUT)$@
-
-configure: configure.ac
-        $(QUIET_GEN)$(RM) $@ $<+ && \
-        sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \
-            $< > $<+ && \
-        autoconf -o $@ $<+ && \
-        $(RM) $<+
+$(SCRIPTS) : % : %.sh
+        $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
 
 # These can record PERF_VERSION
 $(OUTPUT)perf.o perf.spec \
-        $(patsubst %.sh,%,$(SCRIPT_SH)) \
-        $(patsubst %.perl,%,$(SCRIPT_PERL)) \
+        $(SCRIPTS) \
         : $(OUTPUT)PERF-VERSION-FILE
 
 $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
@@ -974,9 +704,6 @@ $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
                 '-DPREFIX="$(prefix_SQ)"' \
                 $<
 
-$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $<
-
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
@@ -986,6 +713,9 @@ $(OUTPUT)util/ui/browser.o: util/ui/browser.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/ui/browsers/annotate.o: util/ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
+$(OUTPUT)util/ui/browsers/top.o: util/ui/browsers/top.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
+
 $(OUTPUT)util/ui/browsers/hists.o: util/ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
@@ -1007,12 +737,11 @@ $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/tra
 $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
-$(OUTPUT)perf-%$X: %.o $(PERFLIBS)
+$(OUTPUT)perf-%: %.o $(PERFLIBS)
         $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
-$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
-builtin-revert.o wt-status.o: wt-status.h
+$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
 
 # we compile into subdirectories. if the target directory is not the source directory, they might not exists. So
 # we depend the various files onto their directories.
@@ -1025,6 +754,36 @@ $(sort $(dir $(DIRECTORY_DEPS))):
 $(LIB_FILE): $(LIB_OBJS)
         $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS)
 
+help:
+        @echo 'Perf make targets:'
+        @echo '  doc            - make *all* documentation (see below)'
+        @echo '  man            - make manpage documentation (access with man <foo>)'
+        @echo '  html           - make html documentation'
+        @echo '  info           - make GNU info documentation (access with info <foo>)'
+        @echo '  pdf            - make pdf documentation'
+        @echo '  TAGS           - use etags to make tag information for source browsing'
+        @echo '  tags           - use ctags to make tag information for source browsing'
+        @echo '  cscope - use cscope to make interactive browsing database'
+        @echo ''
+        @echo 'Perf install targets:'
+        @echo '  NOTE: documentation build requires asciidoc, xmlto packages to be installed'
+        @echo '  HINT: use "make prefix=<path> <install target>" to install to a particular'
+        @echo '        path like make prefix=/usr/local install install-doc'
+        @echo '  install        - install compiled binaries'
+        @echo '  install-doc    - install *all* documentation'
+        @echo '  install-man    - install manpage documentation'
+        @echo '  install-html   - install html documentation'
+        @echo '  install-info   - install GNU info documentation'
+        @echo '  install-pdf    - install pdf documentation'
+        @echo ''
+        @echo '  quick-install-doc      - alias for quick-install-man'
+        @echo '  quick-install-man      - install the documentation quickly'
+        @echo '  quick-install-html     - install the html documentation quickly'
+        @echo ''
+        @echo 'Perf maintainer targets:'
+        @echo '  distclean              - alias to clean'
+        @echo '  clean                  - clean all binary objects and build output'
+
 doc:
         $(MAKE) -C Documentation all
 
@@ -1063,30 +822,12 @@ $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
                 echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \
             fi
 
-# We need to apply sq twice, once to protect from the shell
-# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it
-# and the first level quoting from the shell that runs "echo".
-$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS
-        @echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@
-        @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
-        @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
-        @echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
-
 ### Testing rules
 
-#
-# None right now:
-#
-# TEST_PROGRAMS += test-something$X
-
-all:: $(TEST_PROGRAMS)
-
 # GNU make supports exporting all variables by "export" without parameters.
 # However, the environment gets quite big, and some programs have problems
 # with that.
 
-export NO_SVN_TESTS
-
 check: $(OUTPUT)common-cmds.h
         if sparse; \
         then \
@@ -1095,33 +836,21 @@ check: $(OUTPUT)common-cmds.h
                         sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \
                 done; \
         else \
-                echo 2>&1 "Did you mean 'make test'?"; \
                 exit 1; \
         fi
 
-remove-dashes:
-        ./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS)
-
 ### Installation rules
 
-ifneq ($(filter /%,$(firstword $(template_dir))),)
-template_instdir = $(template_dir)
-else
-template_instdir = $(prefix)/$(template_dir)
-endif
-export template_instdir
-
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
-export perfexec_instdir
 
 install: all
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
-        $(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
+        $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
         $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -1134,14 +863,6 @@ install: all
         $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
         $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 
-ifdef BUILT_INS
-        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-        $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
-ifneq (,$X)
-        $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';)
-endif
-endif
-
 install-doc:
         $(MAKE) -C Documentation install
 
@@ -1166,104 +887,16 @@ quick-install-man:
 quick-install-html:
         $(MAKE) -C Documentation quick-install-html
 
-
-### Maintainer's dist rules
-#
-# None right now
-#
-#
-# perf.spec: perf.spec.in
-#       sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+
-#       mv $@+ $@
-#
-# PERF_TARNAME=perf-$(PERF_VERSION)
-# dist: perf.spec perf-archive$(X) configure
-#       ./perf-archive --format=tar \
-#               --prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar
-#       @mkdir -p $(PERF_TARNAME)
-#       @cp perf.spec configure $(PERF_TARNAME)
-#       @echo $(PERF_VERSION) > $(PERF_TARNAME)/version
-#       $(TAR) rf $(PERF_TARNAME).tar \
-#               $(PERF_TARNAME)/perf.spec \
-#               $(PERF_TARNAME)/configure \
-#               $(PERF_TARNAME)/version
-#       @$(RM) -r $(PERF_TARNAME)
-#       gzip -f -9 $(PERF_TARNAME).tar
-#
-# htmldocs = perf-htmldocs-$(PERF_VERSION)
-# manpages = perf-manpages-$(PERF_VERSION)
-# dist-doc:
-#       $(RM) -r .doc-tmp-dir
-#       mkdir .doc-tmp-dir
-#       $(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc
-#       cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar .
-#       gzip -n -9 -f $(htmldocs).tar
-#       :
-#       $(RM) -r .doc-tmp-dir
-#       mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7
-#       $(MAKE) -C Documentation DESTDIR=./ \
-#               man1dir=../.doc-tmp-dir/man1 \
-#               man5dir=../.doc-tmp-dir/man5 \
-#               man7dir=../.doc-tmp-dir/man7 \
-#               install
-#       cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar .
-#       gzip -n -9 -f $(manpages).tar
-#       $(RM) -r .doc-tmp-dir
-#
-# rpm: dist
-#       $(RPMBUILD) -ta $(PERF_TARNAME).tar.gz
-
 ### Cleaning rules
 
-distclean: clean
-#       $(RM) configure
-
 clean:
-        $(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE)
-        $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X
-        $(RM) $(TEST_PROGRAMS)
+        $(RM) $(OUTPUT){*.o,*/*.o,*/*/*.o,*/*/*/*.o,$(LIB_FILE),perf-archive}
+        $(RM) $(ALL_PROGRAMS) perf
         $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope*
-        $(RM) -r autom4te.cache
-        $(RM) config.log config.mak.autogen config.mak.append config.status config.cache
-        $(RM) -r $(PERF_TARNAME) .doc-tmp-dir
-        $(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz
-        $(RM) $(htmldocs).tar.gz $(manpages).tar.gz
         $(MAKE) -C Documentation/ clean
-        $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS
+        $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS
+        $(python-clean)
 
 .PHONY: all install clean strip
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
 .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
-.PHONY: .FORCE-PERF-BUILD-OPTIONS
-
-### Make sure built-ins do not have dups and listed in perf.c
-#
-check-builtins::
-        ./check-builtins.sh
-
-### Test suite coverage testing
-#
-# None right now
-#
-# .PHONY: coverage coverage-clean coverage-build coverage-report
-#
-# coverage:
-#       $(MAKE) coverage-build
-#       $(MAKE) coverage-report
-#
-# coverage-clean:
-#       rm -f *.gcda *.gcno
-#
-# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs
-# COVERAGE_LDFLAGS = $(CFLAGS)  -O0 -lgcov
-#
-# coverage-build: coverage-clean
-#       $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all
-#       $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \
-#               -j1 test
-#
-# coverage-report:
-#       gcov -b *.c */*.c
-#       grep '^function.*called 0 ' *.c.gcov */*.c.gcov \
-#               | sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \
-#               | tee coverage-untested-functions
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
new file mode 100644
index 000000000000..15130b50dfe3
--- /dev/null
+++ b/tools/perf/arch/s390/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
diff --git a/tools/perf/arch/s390/util/dwarf-regs.c b/tools/perf/arch/s390/util/dwarf-regs.c
new file mode 100644
index 000000000000..e19653e025fa
--- /dev/null
+++ b/tools/perf/arch/s390/util/dwarf-regs.c
@@ -0,0 +1,22 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ *    Copyright IBM Corp. 2010
+ *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *
+ */
+
+#include <libio.h>
+#include <dwarf-regs.h>
+
+#define NUM_GPRS 16
+
+static const char *gpr_names[NUM_GPRS] = {
+        "%r0", "%r1",  "%r2",  "%r3",  "%r4",  "%r5",  "%r6",  "%r7",
+        "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+};
+
+const char *get_arch_regstr(unsigned int n)
+{
+        return (n >= NUM_GPRS) ? NULL : gpr_names[n];
+}
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
new file mode 100644
index 000000000000..a72e36cb5394
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMCPY_FN(fn, name, desc)               \
+        extern void *fn(void *, const void *, size_t);
+
+#include "mem-memcpy-x86-64-asm-def.h"
+
+#undef MEMCPY_FN
+
+#endif
+
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
new file mode 100644
index 000000000000..d588b87696fc
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -0,0 +1,4 @@
+
+MEMCPY_FN(__memcpy,
+        "x86-64-unrolled",
+        "unrolled memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
new file mode 100644
index 000000000000..a57b66e853c2
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -0,0 +1,2 @@
+
+#include "../../../arch/x86/lib/memcpy_64.S"
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 38dae7465142..db82021f4b91 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -12,6 +12,7 @@
 #include "../util/parse-options.h"
 #include "../util/header.h"
 #include "bench.h"
+#include "mem-memcpy-arch.h"
 
 #include <stdio.h>
 #include <stdlib.h>
@@ -23,8 +24,10 @@
 
 static const char       *length_str     = "1MB";
 static const char       *routine        = "default";
-static bool             use_clock       = false;
+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",
@@ -34,19 +37,33 @@ static const struct option options[] = {
                     "Specify routine to copy"),
         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 memcpy()"),
+        OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+                    "Show only the result without page faults before memcpy()"),
         OPT_END()
 };
 
+typedef void *(*memcpy_t)(void *, const void *, size_t);
+
 struct routine {
         const char *name;
         const char *desc;
-        void * (*fn)(void *dst, const void *src, size_t len);
+        memcpy_t fn;
 };
 
 struct routine routines[] = {
         { "default",
           "Default memcpy() provided by glibc",
           memcpy },
+#ifdef ARCH_X86_64
+
+#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memcpy-x86-64-asm-def.h"
+#undef MEMCPY_FN
+
+#endif
+
         { NULL,
           NULL,
           NULL   }
@@ -89,29 +106,98 @@ static double timeval2double(struct timeval *ts)
                 (double)ts->tv_usec / (double)1000000;
 }
 
+static void alloc_mem(void **dst, void **src, size_t length)
+{
+        *dst = zalloc(length);
+        if (!dst)
+                die("memory allocation failed - maybe length is too large?\n");
+
+        *src = zalloc(length);
+        if (!src)
+                die("memory allocation failed - maybe length is too large?\n");
+}
+
+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;
+
+        alloc_mem(&src, &dst, len);
+
+        if (prefault)
+                fn(dst, src, len);
+
+        clock_start = get_clock();
+        fn(dst, src, len);
+        clock_end = get_clock();
+
+        free(src);
+        free(dst);
+        return clock_end - clock_start;
+}
+
+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;
+
+        alloc_mem(&src, &dst, len);
+
+        if (prefault)
+                fn(dst, src, len);
+
+        BUG_ON(gettimeofday(&tv_start, NULL));
+        fn(dst, src, len);
+        BUG_ON(gettimeofday(&tv_end, NULL));
+
+        timersub(&tv_end, &tv_start, &tv_diff);
+
+        free(src);
+        free(dst);
+        return (double)((double)len / timeval2double(&tv_diff));
+}
+
+#define pf (no_prefault ? 0 : 1)
+
+#define print_bps(x) do {                                       \
+                if (x < K)                                      \
+                        printf(" %14lf B/Sec", x);              \
+                else if (x < K * K)                             \
+                        printf(" %14lfd KB/Sec", x / K);        \
+                else if (x < K * K * K)                         \
+                        printf(" %14lf MB/Sec", x / K / K);     \
+                else                                            \
+                        printf(" %14lf GB/Sec", x / K / K / K); \
+        } while (0)
+
 int bench_mem_memcpy(int argc, const char **argv,
                      const char *prefix __used)
 {
         int i;
-        void *dst, *src;
-        size_t length;
-        double bps = 0.0;
-        struct timeval tv_start, tv_end, tv_diff;
-        u64 clock_start, clock_end, clock_diff;
+        size_t len;
+        double result_bps[2];
+        u64 result_clock[2];
 
-        clock_start = clock_end = clock_diff = 0ULL;
         argc = parse_options(argc, argv, options,
                              bench_mem_memcpy_usage, 0);
 
-        tv_diff.tv_sec = 0;
-        tv_diff.tv_usec = 0;
-        length = (size_t)perf_atoll((char *)length_str);
+        if (use_clock)
+                init_clock();
+
+        len = (size_t)perf_atoll((char *)length_str);
 
-        if ((s64)length <= 0) {
+        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;
@@ -126,61 +212,80 @@ int bench_mem_memcpy(int argc, const char **argv,
                 return 1;
         }
 
-        dst = zalloc(length);
-        if (!dst)
-                die("memory allocation failed - maybe length is too large?\n");
-
-        src = zalloc(length);
-        if (!src)
-                die("memory allocation failed - maybe length is too large?\n");
-
-        if (bench_format == BENCH_FORMAT_DEFAULT) {
-                printf("# Copying %s Bytes from %p to %p ...\n\n",
-                       length_str, src, dst);
-        }
-
-        if (use_clock) {
-                init_clock();
-                clock_start = get_clock();
-        } else {
-                BUG_ON(gettimeofday(&tv_start, NULL));
-        }
-
-        routines[i].fn(dst, src, length);
+        if (bench_format == BENCH_FORMAT_DEFAULT)
+                printf("# Copying %s Bytes ...\n\n", length_str);
 
-        if (use_clock) {
-                clock_end = get_clock();
-                clock_diff = clock_end - clock_start;
+        if (!only_prefault && !no_prefault) {
+                /* show both of results */
+                if (use_clock) {
+                        result_clock[0] =
+                                do_memcpy_clock(routines[i].fn, len, false);
+                        result_clock[1] =
+                                do_memcpy_clock(routines[i].fn, len, true);
+                } else {
+                        result_bps[0] =
+                                do_memcpy_gettimeofday(routines[i].fn,
+                                                len, false);
+                        result_bps[1] =
+                                do_memcpy_gettimeofday(routines[i].fn,
+                                                len, true);
+                }
         } else {
-                BUG_ON(gettimeofday(&tv_end, NULL));
-                timersub(&tv_end, &tv_start, &tv_diff);
-                bps = (double)((double)length / timeval2double(&tv_diff));
+                if (use_clock) {
+                        result_clock[pf] =
+                                do_memcpy_clock(routines[i].fn,
+                                                len, only_prefault);
+                } else {
+                        result_bps[pf] =
+                                do_memcpy_gettimeofday(routines[i].fn,
+                                                len, only_prefault);
+                }
         }
 
         switch (bench_format) {
         case BENCH_FORMAT_DEFAULT:
-                if (use_clock) {
-                        printf(" %14lf Clock/Byte\n",
-                               (double)clock_diff / (double)length);
-                } else {
-                        if (bps < K)
-                                printf(" %14lf B/Sec\n", bps);
-                        else if (bps < K * K)
-                                printf(" %14lfd KB/Sec\n", bps / 1024);
-                        else if (bps < K * K * K)
-                                printf(" %14lf MB/Sec\n", bps / 1024 / 1024);
-                        else {
-                                printf(" %14lf GB/Sec\n",
-                                       bps / 1024 / 1024 / 1024);
+                if (!only_prefault && !no_prefault) {
+                        if (use_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 (use_clock) {
-                        printf("%14lf\n",
-                               (double)clock_diff / (double)length);
-                } else
-                        printf("%lf\n", bps);
+                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: */
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index d9ab3ce446ac..0c7454f8b8a9 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -55,7 +55,7 @@ int bench_sched_pipe(int argc, const char **argv,
          * discarding returned value of read(), write()
          * causes error in building environment for perf
          */
-        int ret, wait_stat;
+        int __used ret, wait_stat;
         pid_t pid, retpid;
 
         argc = parse_options(argc, argv, options,
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1478dc64bf15..7b139e1e7e86 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,7 +8,6 @@
 #include "builtin.h"
 
 #include "util/util.h"
-
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
@@ -18,6 +17,9 @@
 #include "perf.h"
 #include "util/debug.h"
 
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/annotate.h"
 #include "util/event.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -28,7 +30,7 @@
 
 static char             const *input_name = "perf.data";
 
-static bool             force;
+static bool             force, use_tui, use_stdio;
 
 static bool             full_paths;
 
@@ -36,9 +38,13 @@ static bool		print_line;
 
 static const char *sym_hist_filter;
 
-static int hists__add_entry(struct hists *self, struct addr_location *al)
+static int perf_evlist__add_sample(struct perf_evlist *evlist,
+                                   struct perf_sample *sample,
+                                   struct perf_evsel *evsel,
+                                   struct addr_location *al)
 {
         struct hist_entry *he;
+        int ret;
 
         if (sym_hist_filter != NULL &&
             (al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
@@ -51,25 +57,41 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
                 return 0;
         }
 
-        he = __hists__add_entry(self, al, NULL, 1);
+        he = __hists__add_entry(&evsel->hists, al, NULL, 1);
         if (he == NULL)
                 return -ENOMEM;
 
-        return hist_entry__inc_addr_samples(he, al->addr);
+        ret = 0;
+        if (he->ms.sym != NULL) {
+                struct annotation *notes = symbol__annotation(he->ms.sym);
+                if (notes->src == NULL &&
+                    symbol__alloc_hist(he->ms.sym, evlist->nr_entries) < 0)
+                        return -ENOMEM;
+
+                ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+        }
+
+        evsel->hists.stats.total_period += sample->period;
+        hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+        return ret;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel,
+                                struct perf_session *session)
 {
         struct addr_location al;
-        struct sample_data data;
 
-        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+        if (perf_event__preprocess_sample(event, session, &al, sample,
+                                          symbol__annotate_init) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
         }
 
-        if (!al.filtered && hists__add_entry(&session->hists, &al)) {
+        if (!al.filtered &&
+            perf_evlist__add_sample(session->evlist, sample, evsel, &al)) {
                 pr_warning("problem incrementing symbol count, "
                            "skipping event\n");
                 return -1;
@@ -78,261 +100,26 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         return 0;
 }
 
-static int objdump_line__print(struct objdump_line *self,
-                               struct list_head *head,
-                               struct hist_entry *he, u64 len)
-{
-        struct symbol *sym = he->ms.sym;
-        static const char *prev_line;
-        static const char *prev_color;
-
-        if (self->offset != -1) {
-                const char *path = NULL;
-                unsigned int hits = 0;
-                double percent = 0.0;
-                const char *color;
-                struct sym_priv *priv = symbol__priv(sym);
-                struct sym_ext *sym_ext = priv->ext;
-                struct sym_hist *h = priv->hist;
-                s64 offset = self->offset;
-                struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
-                while (offset < (s64)len &&
-                       (next == NULL || offset < next->offset)) {
-                        if (sym_ext) {
-                                if (path == NULL)
-                                        path = sym_ext[offset].path;
-                                percent += sym_ext[offset].percent;
-                        } else
-                                hits += h->ip[offset];
-
-                        ++offset;
-                }
-
-                if (sym_ext == NULL && h->sum)
-                        percent = 100.0 * hits / h->sum;
-
-                color = get_percent_color(percent);
-
-                /*
-                 * Also color the filename and line if needed, with
-                 * the same color than the percentage. Don't print it
-                 * twice for close colored ip with the same filename:line
-                 */
-                if (path) {
-                        if (!prev_line || strcmp(prev_line, path)
-                                       || color != prev_color) {
-                                color_fprintf(stdout, color, " %s", path);
-                                prev_line = path;
-                                prev_color = color;
-                        }
-                }
-
-                color_fprintf(stdout, color, " %7.2f", percent);
-                printf(" :      ");
-                color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line);
-        } else {
-                if (!*self->line)
-                        printf("         :\n");
-                else
-                        printf("         :      %s\n", self->line);
-        }
-
-        return 0;
-}
-
-static struct rb_root root_sym_ext;
-
-static void insert_source_line(struct sym_ext *sym_ext)
+static int hist_entry__tty_annotate(struct hist_entry *he, int evidx)
 {
-        struct sym_ext *iter;
-        struct rb_node **p = &root_sym_ext.rb_node;
-        struct rb_node *parent = NULL;
-
-        while (*p != NULL) {
-                parent = *p;
-                iter = rb_entry(parent, struct sym_ext, node);
-
-                if (sym_ext->percent > iter->percent)
-                        p = &(*p)->rb_left;
-                else
-                        p = &(*p)->rb_right;
-        }
-
-        rb_link_node(&sym_ext->node, parent, p);
-        rb_insert_color(&sym_ext->node, &root_sym_ext);
+        return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx,
+                                    print_line, full_paths, 0, 0);
 }
 
-static void free_source_line(struct hist_entry *he, int len)
+static void hists__find_annotations(struct hists *self, int evidx)
 {
-        struct sym_priv *priv = symbol__priv(he->ms.sym);
-        struct sym_ext *sym_ext = priv->ext;
-        int i;
-
-        if (!sym_ext)
-                return;
-
-        for (i = 0; i < len; i++)
-                free(sym_ext[i].path);
-        free(sym_ext);
-
-        priv->ext = NULL;
-        root_sym_ext = RB_ROOT;
-}
-
-/* Get the filename:line for the colored entries */
-static void
-get_source_line(struct hist_entry *he, int len, const char *filename)
-{
-        struct symbol *sym = he->ms.sym;
-        u64 start;
-        int i;
-        char cmd[PATH_MAX * 2];
-        struct sym_ext *sym_ext;
-        struct sym_priv *priv = symbol__priv(sym);
-        struct sym_hist *h = priv->hist;
-
-        if (!h->sum)
-                return;
-
-        sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext));
-        if (!priv->ext)
-                return;
-
-        start = he->ms.map->unmap_ip(he->ms.map, sym->start);
-
-        for (i = 0; i < len; i++) {
-                char *path = NULL;
-                size_t line_len;
-                u64 offset;
-                FILE *fp;
-
-                sym_ext[i].percent = 100.0 * h->ip[i] / h->sum;
-                if (sym_ext[i].percent <= 0.5)
-                        continue;
-
-                offset = start + i;
-                sprintf(cmd, "addr2line -e %s %016llx", filename, offset);
-                fp = popen(cmd, "r");
-                if (!fp)
-                        continue;
-
-                if (getline(&path, &line_len, fp) < 0 || !line_len)
-                        goto next;
-
-                sym_ext[i].path = malloc(sizeof(char) * line_len + 1);
-                if (!sym_ext[i].path)
-                        goto next;
-
-                strcpy(sym_ext[i].path, path);
-                insert_source_line(&sym_ext[i]);
-
-        next:
-                pclose(fp);
-        }
-}
-
-static void print_summary(const char *filename)
-{
-        struct sym_ext *sym_ext;
-        struct rb_node *node;
-
-        printf("\nSorted summary for file %s\n", filename);
-        printf("----------------------------------------------\n\n");
-
-        if (RB_EMPTY_ROOT(&root_sym_ext)) {
-                printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
-                return;
-        }
-
-        node = rb_first(&root_sym_ext);
-        while (node) {
-                double percent;
-                const char *color;
-                char *path;
-
-                sym_ext = rb_entry(node, struct sym_ext, node);
-                percent = sym_ext->percent;
-                color = get_percent_color(percent);
-                path = sym_ext->path;
-
-                color_fprintf(stdout, color, " %7.2f %s", percent, path);
-                node = rb_next(node);
-        }
-}
-
-static void hist_entry__print_hits(struct hist_entry *self)
-{
-        struct symbol *sym = self->ms.sym;
-        struct sym_priv *priv = symbol__priv(sym);
-        struct sym_hist *h = priv->hist;
-        u64 len = sym->end - sym->start, offset;
-
-        for (offset = 0; offset < len; ++offset)
-                if (h->ip[offset] != 0)
-                        printf("%*Lx: %Lu\n", BITS_PER_LONG / 2,
-                               sym->start + offset, h->ip[offset]);
-        printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
-}
-
-static int hist_entry__tty_annotate(struct hist_entry *he)
-{
-        struct map *map = he->ms.map;
-        struct dso *dso = map->dso;
-        struct symbol *sym = he->ms.sym;
-        const char *filename = dso->long_name, *d_filename;
-        u64 len;
-        LIST_HEAD(head);
-        struct objdump_line *pos, *n;
-
-        if (hist_entry__annotate(he, &head, 0) < 0)
-                return -1;
-
-        if (full_paths)
-                d_filename = filename;
-        else
-                d_filename = basename(filename);
-
-        len = sym->end - sym->start;
-
-        if (print_line) {
-                get_source_line(he, len, filename);
-                print_summary(filename);
-        }
-
-        printf("\n\n------------------------------------------------\n");
-        printf(" Percent |      Source code & Disassembly of %s\n", d_filename);
-        printf("------------------------------------------------\n");
-
-        if (verbose)
-                hist_entry__print_hits(he);
-
-        list_for_each_entry_safe(pos, n, &head, node) {
-                objdump_line__print(pos, &head, he, len);
-                list_del(&pos->node);
-                objdump_line__free(pos);
-        }
-
-        if (print_line)
-                free_source_line(he, len);
-
-        return 0;
-}
-
-static void hists__find_annotations(struct hists *self)
-{
-        struct rb_node *first = rb_first(&self->entries), *nd = first;
+        struct rb_node *nd = rb_first(&self->entries), *next;
         int key = KEY_RIGHT;
 
         while (nd) {
                 struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-                struct sym_priv *priv;
+                struct annotation *notes;
 
                 if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
                         goto find_next;
 
-                priv = symbol__priv(he->ms.sym);
-                if (priv->hist == NULL) {
+                notes = symbol__annotation(he->ms.sym);
+                if (notes->src == NULL) {
 find_next:
                         if (key == KEY_LEFT)
                                 nd = rb_prev(nd);
@@ -342,48 +129,51 @@ find_next:
                 }
 
                 if (use_browser > 0) {
-                        key = hist_entry__tui_annotate(he);
-                        if (is_exit_key(key))
-                                break;
+                        key = hist_entry__tui_annotate(he, evidx);
                         switch (key) {
                         case KEY_RIGHT:
-                        case '\t':
-                                nd = rb_next(nd);
+                                next = rb_next(nd);
                                 break;
                         case KEY_LEFT:
-                                if (nd == first)
-                                        continue;
-                                nd = rb_prev(nd);
-                        default:
+                                next = rb_prev(nd);
                                 break;
+                        default:
+                                return;
                         }
+
+                        if (next != NULL)
+                                nd = next;
                 } else {
-                        hist_entry__tty_annotate(he);
+                        hist_entry__tty_annotate(he, evidx);
                         nd = rb_next(nd);
                         /*
                          * Since we have a hist_entry per IP for the same
-                         * symbol, free he->ms.sym->hist to signal we already
+                         * symbol, free he->ms.sym->src to signal we already
                          * processed this symbol.
                          */
-                        free(priv->hist);
-                        priv->hist = NULL;
+                        free(notes->src);
+                        notes->src = NULL;
                 }
         }
 }
 
 static struct perf_event_ops event_ops = {
         .sample = process_sample_event,
-        .mmap   = event__process_mmap,
-        .comm   = event__process_comm,
-        .fork   = event__process_task,
+        .mmap   = perf_event__process_mmap,
+        .comm   = perf_event__process_comm,
+        .fork   = perf_event__process_task,
+        .ordered_samples = true,
+        .ordering_requires_timestamps = true,
 };
 
 static int __cmd_annotate(void)
 {
         int ret;
         struct perf_session *session;
+        struct perf_evsel *pos;
+        u64 total_nr_samples;
 
-        session = perf_session__new(input_name, O_RDONLY, force, false);
+        session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -402,12 +192,36 @@ static int __cmd_annotate(void)
         if (verbose > 2)
                 perf_session__fprintf_dsos(session, stdout);
 
-        hists__collapse_resort(&session->hists);
-        hists__output_resort(&session->hists);
-        hists__find_annotations(&session->hists);
-out_delete:
-        perf_session__delete(session);
+        total_nr_samples = 0;
+        list_for_each_entry(pos, &session->evlist->entries, node) {
+                struct hists *hists = &pos->hists;
+                u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+                if (nr_samples > 0) {
+                        total_nr_samples += nr_samples;
+                        hists__collapse_resort(hists);
+                        hists__output_resort(hists);
+                        hists__find_annotations(hists, pos->idx);
+                }
+        }
 
+        if (total_nr_samples == 0) {
+                ui__warning("The %s file has no samples!\n", input_name);
+                goto out_delete;
+        }
+out_delete:
+        /*
+         * Speed up the exit process, for large files this can
+         * take quite a while.
+         *
+         * XXX Enable this when using valgrind or if we ever
+         * librarize this command.
+         *
+         * Also experiment with obstacks to see how much speed
+         * up we'll get here.
+         *
+         * perf_session__delete(session);
+         */
         return ret;
 }
 
@@ -428,6 +242,8 @@ static const struct option options[] = {
                     "be more verbose (show symbol address, etc)"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
+        OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+        OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
@@ -443,9 +259,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used)
 {
         argc = parse_options(argc, argv, options, annotate_usage, 0);
 
-        setup_browser();
+        if (use_stdio)
+                use_browser = 0;
+        else if (use_tui)
+                use_browser = 1;
+
+        setup_browser(true);
 
-        symbol_conf.priv_size = sizeof(struct sym_priv);
+        symbol_conf.priv_size = sizeof(struct annotation);
         symbol_conf.try_vmlinux_path = true;
 
         if (symbol__init() < 0)
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 44a47e13bd67..5af32ae9031e 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -36,10 +36,10 @@ static const struct option options[] = {
 
 static int __cmd_buildid_list(void)
 {
-        int err = -1;
         struct perf_session *session;
 
-        session = perf_session__new(input_name, O_RDONLY, force, false);
+        session = perf_session__new(input_name, O_RDONLY, force, false,
+                                    &build_id__mark_dso_hit_ops);
         if (session == NULL)
                 return -1;
 
@@ -49,7 +49,7 @@ static int __cmd_buildid_list(void)
         perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 
         perf_session__delete(session);
-        return err;
+        return 0;
 }
 
 int cmd_buildid_list(int argc, const char **argv, const char *prefix __used)
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index fca1d4402910..e8219990f8b8 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -30,12 +30,14 @@ static int hists__add_entry(struct hists *self,
         return -ENOMEM;
 }
 
-static int diff__process_sample_event(event_t *event, struct perf_session *session)
+static int diff__process_sample_event(union perf_event *event,
+                                      struct perf_sample *sample,
+                                      struct perf_evsel *evsel __used,
+                                      struct perf_session *session)
 {
         struct addr_location al;
-        struct sample_data data = { .period = 1, };
 
-        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+        if (perf_event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -44,22 +46,24 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
         if (al.filtered || al.sym == NULL)
                 return 0;
 
-        if (hists__add_entry(&session->hists, &al, data.period)) {
+        if (hists__add_entry(&session->hists, &al, sample->period)) {
                 pr_warning("problem incrementing symbol period, skipping event\n");
                 return -1;
         }
 
-        session->hists.stats.total_period += data.period;
+        session->hists.stats.total_period += sample->period;
         return 0;
 }
 
 static struct perf_event_ops event_ops = {
         .sample = diff__process_sample_event,
-        .mmap   = event__process_mmap,
-        .comm   = event__process_comm,
-        .exit   = event__process_task,
-        .fork   = event__process_task,
-        .lost   = event__process_lost,
+        .mmap   = perf_event__process_mmap,
+        .comm   = perf_event__process_comm,
+        .exit   = perf_event__process_task,
+        .fork   = perf_event__process_task,
+        .lost   = perf_event__process_lost,
+        .ordered_samples = true,
+        .ordering_requires_timestamps = true,
 };
 
 static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
@@ -141,8 +145,8 @@ static int __cmd_diff(void)
         int ret, i;
         struct perf_session *session[2];
 
-        session[0] = perf_session__new(input_old, O_RDONLY, force, false);
-        session[1] = perf_session__new(input_new, O_RDONLY, force, false);
+        session[0] = perf_session__new(input_old, O_RDONLY, force, false, &event_ops);
+        session[1] = perf_session__new(input_new, O_RDONLY, force, false, &event_ops);
         if (session[0] == NULL || session[1] == NULL)
                 return -ENOMEM;
 
@@ -173,7 +177,7 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show symbol address, etc)"),
-        OPT_BOOLEAN('m', "displacement", &show_displacement,
+        OPT_BOOLEAN('M', "displacement", &show_displacement,
                     "Show position displacement relative to baseline"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
@@ -191,6 +195,8 @@ static const struct option options[] = {
         OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
                    "separator for columns, no spaces will be added between "
                    "columns '.' is reserved."),
+        OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+                    "Look for files with symbols relative to this directory"),
         OPT_END()
 };
 
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
new file mode 100644
index 000000000000..4c5e9e04a41f
--- /dev/null
+++ b/tools/perf/builtin-evlist.c
@@ -0,0 +1,54 @@
+/*
+ * Builtin evlist command: Show the list of event selectors present
+ * in a perf.data file.
+ */
+#include "builtin.h"
+
+#include "util/util.h"
+
+#include <linux/list.h>
+
+#include "perf.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/parse-events.h"
+#include "util/parse-options.h"
+#include "util/session.h"
+
+static char const *input_name = "perf.data";
+
+static int __cmd_evlist(void)
+{
+        struct perf_session *session;
+        struct perf_evsel *pos;
+
+        session = perf_session__new(input_name, O_RDONLY, 0, false, NULL);
+        if (session == NULL)
+                return -ENOMEM;
+
+        list_for_each_entry(pos, &session->evlist->entries, node)
+                printf("%s\n", event_name(pos));
+
+        perf_session__delete(session);
+        return 0;
+}
+
+static const char * const evlist_usage[] = {
+        "perf evlist [<options>]",
+        NULL
+};
+
+static const struct option options[] = {
+        OPT_STRING('i', "input", &input_name, "file",
+                    "input file name"),
+        OPT_END()
+};
+
+int cmd_evlist(int argc, const char **argv, const char *prefix __used)
+{
+        argc = parse_options(argc, argv, options, evlist_usage, 0);
+        if (argc)
+                usage_with_options(evlist_usage, options);
+
+        return __cmd_evlist();
+}
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8e3e47b064ce..8dfc12bb119b 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,8 +16,8 @@
 static char             const *input_name = "-";
 static bool             inject_build_ids;
 
-static int event__repipe(event_t *event __used,
-                         struct perf_session *session __used)
+static int perf_event__repipe_synth(union perf_event *event,
+                                    struct perf_session *session __used)
 {
         uint32_t size;
         void *buf = event;
@@ -36,33 +36,52 @@ static int event__repipe(event_t *event __used,
         return 0;
 }
 
-static int event__repipe_mmap(event_t *self, struct perf_session *session)
+static int perf_event__repipe(union perf_event *event,
+                              struct perf_sample *sample __used,
+                              struct perf_session *session)
+{
+        return perf_event__repipe_synth(event, session);
+}
+
+static int perf_event__repipe_sample(union perf_event *event,
+                              struct perf_sample *sample __used,
+                              struct perf_evsel *evsel __used,
+                              struct perf_session *session)
+{
+        return perf_event__repipe_synth(event, session);
+}
+
+static int perf_event__repipe_mmap(union perf_event *event,
+                                   struct perf_sample *sample,
+                                   struct perf_session *session)
 {
         int err;
 
-        err = event__process_mmap(self, session);
-        event__repipe(self, session);
+        err = perf_event__process_mmap(event, sample, session);
+        perf_event__repipe(event, sample, session);
 
         return err;
 }
 
-static int event__repipe_task(event_t *self, struct perf_session *session)
+static int perf_event__repipe_task(union perf_event *event,
+                                   struct perf_sample *sample,
+                                   struct perf_session *session)
 {
         int err;
 
-        err = event__process_task(self, session);
-        event__repipe(self, session);
+        err = perf_event__process_task(event, sample, session);
+        perf_event__repipe(event, sample, session);
 
         return err;
 }
 
-static int event__repipe_tracing_data(event_t *self,
-                                      struct perf_session *session)
+static int perf_event__repipe_tracing_data(union perf_event *event,
+                                           struct perf_session *session)
 {
         int err;
 
-        event__repipe(self, session);
-        err = event__process_tracing_data(self, session);
+        perf_event__repipe_synth(event, session);
+        err = perf_event__process_tracing_data(event, session);
 
         return err;
 }
@@ -101,8 +120,8 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session)
         if (self->kernel)
                 misc = PERF_RECORD_MISC_KERNEL;
 
-        err = event__synthesize_build_id(self, misc, event__repipe,
-                                         machine, session);
+        err = perf_event__synthesize_build_id(self, misc, perf_event__repipe,
+                                              machine, session);
         if (err) {
                 pr_err("Can't synthesize build_id event for %s\n", self->long_name);
                 return -1;
@@ -111,7 +130,10 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session)
         return 0;
 }
 
-static int event__inject_buildid(event_t *event, struct perf_session *session)
+static int perf_event__inject_buildid(union perf_event *event,
+                                      struct perf_sample *sample,
+                                      struct perf_evsel *evsel __used,
+                                      struct perf_session *session)
 {
         struct addr_location al;
         struct thread *thread;
@@ -146,24 +168,24 @@ static int event__inject_buildid(event_t *event, struct perf_session *session)
         }
 
 repipe:
-        event__repipe(event, session);
+        perf_event__repipe(event, sample, session);
         return 0;
 }
 
 struct perf_event_ops inject_ops = {
-        .sample         = event__repipe,
-        .mmap           = event__repipe,
-        .comm           = event__repipe,
-        .fork           = event__repipe,
-        .exit           = event__repipe,
-        .lost           = event__repipe,
-        .read           = event__repipe,
-        .throttle       = event__repipe,
-        .unthrottle     = event__repipe,
-        .attr           = event__repipe,
-        .event_type     = event__repipe,
-        .tracing_data   = event__repipe,
-        .build_id       = event__repipe,
+        .sample         = perf_event__repipe_sample,
+        .mmap           = perf_event__repipe,
+        .comm           = perf_event__repipe,
+        .fork           = perf_event__repipe,
+        .exit           = perf_event__repipe,
+        .lost           = perf_event__repipe,
+        .read           = perf_event__repipe,
+        .throttle       = perf_event__repipe,
+        .unthrottle     = perf_event__repipe,
+        .attr           = perf_event__repipe_synth,
+        .event_type     = perf_event__repipe_synth,
+        .tracing_data   = perf_event__repipe_synth,
+        .build_id       = perf_event__repipe_synth,
 };
 
 extern volatile int session_done;
@@ -181,13 +203,13 @@ static int __cmd_inject(void)
         signal(SIGINT, sig_handler);
 
         if (inject_build_ids) {
-                inject_ops.sample       = event__inject_buildid;
-                inject_ops.mmap         = event__repipe_mmap;
-                inject_ops.fork         = event__repipe_task;
-                inject_ops.tracing_data = event__repipe_tracing_data;
+                inject_ops.sample       = perf_event__inject_buildid;
+                inject_ops.mmap         = perf_event__repipe_mmap;
+                inject_ops.fork         = perf_event__repipe_task;
+                inject_ops.tracing_data = perf_event__repipe_tracing_data;
         }
 
-        session = perf_session__new(input_name, O_RDONLY, false, true);
+        session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops);
         if (session == NULL)
                 return -ENOMEM;
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 31f60a2535e0..225e963df105 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -275,9 +275,8 @@ static void process_free_event(void *data,
         s_alloc->alloc_cpu = -1;
 }
 
-static void
-process_raw_event(event_t *raw_event __used, void *data,
-                  int cpu, u64 timestamp, struct thread *thread)
+static void process_raw_event(union perf_event *raw_event __used, void *data,
+                              int cpu, u64 timestamp, struct thread *thread)
 {
         struct event *event;
         int type;
@@ -304,22 +303,13 @@ process_raw_event(event_t *raw_event __used, void *data,
         }
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel __used,
+                                struct perf_session *session)
 {
-        struct sample_data data;
-        struct thread *thread;
+        struct thread *thread = perf_session__findnew(session, event->ip.pid);
 
-        memset(&data, 0, sizeof(data));
-        data.time = -1;
-        data.cpu = -1;
-        data.period = 1;
-
-        event__parse_sample(event, session->sample_type, &data);
-
-        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-                    data.pid, data.tid, data.ip, data.period);
-
-        thread = perf_session__findnew(session, event->ip.pid);
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
                          event->header.type);
@@ -328,15 +318,15 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-        process_raw_event(event, data.raw_data, data.cpu,
-                          data.time, thread);
+        process_raw_event(event, sample->raw_data, sample->cpu,
+                          sample->time, thread);
 
         return 0;
 }
 
 static struct perf_event_ops event_ops = {
         .sample                 = process_sample_event,
-        .comm                   = event__process_comm,
+        .comm                   = perf_event__process_comm,
         .ordered_samples        = true,
 };
 
@@ -382,10 +372,10 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
                         addr = data->ptr;
 
                 if (sym != NULL)
-                        snprintf(buf, sizeof(buf), "%s+%Lx", sym->name,
+                        snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name,
                                  addr - map->unmap_ip(map, sym->start));
                 else
-                        snprintf(buf, sizeof(buf), "%#Lx", addr);
+                        snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr);
                 printf(" %-34s |", buf);
 
                 printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
@@ -492,7 +482,8 @@ static void sort_result(void)
 static int __cmd_kmem(void)
 {
         int err = -EINVAL;
-        struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+        struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+                                                         0, false, &event_ops);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -747,6 +738,9 @@ static int __cmd_record(int argc, const char **argv)
         rec_argc = ARRAY_SIZE(record_args) + argc - 1;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+        if (rec_argv == NULL)
+                return -ENOMEM;
+
         for (i = 0; i < ARRAY_SIZE(record_args); i++)
                 rec_argv[i] = strdup(record_args[i]);
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index d88c6961274c..6313b6eb3ebb 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -5,6 +5,7 @@
  *
  * Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de>
  * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
  */
 #include "builtin.h"
 
@@ -13,9 +14,47 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 
-int cmd_list(int argc __used, const char **argv __used, const char *prefix __used)
+int cmd_list(int argc, const char **argv, const char *prefix __used)
 {
         setup_pager();
-        print_events();
+
+        if (argc == 1)
+                print_events(NULL);
+        else {
+                int i;
+
+                for (i = 1; i < argc; ++i) {
+                        if (i > 1)
+                                putchar('\n');
+                        if (strncmp(argv[i], "tracepoint", 10) == 0)
+                                print_tracepoint_events(NULL, NULL);
+                        else if (strcmp(argv[i], "hw") == 0 ||
+                                 strcmp(argv[i], "hardware") == 0)
+                                print_events_type(PERF_TYPE_HARDWARE);
+                        else if (strcmp(argv[i], "sw") == 0 ||
+                                 strcmp(argv[i], "software") == 0)
+                                print_events_type(PERF_TYPE_SOFTWARE);
+                        else if (strcmp(argv[i], "cache") == 0 ||
+                                 strcmp(argv[i], "hwcache") == 0)
+                                print_hwcache_events(NULL);
+                        else {
+                                char *sep = strchr(argv[i], ':'), *s;
+                                int sep_idx;
+
+                                if (sep == NULL) {
+                                        print_events(argv[i]);
+                                        continue;
+                                }
+                                sep_idx = sep - argv[i];
+                                s = strdup(argv[i]);
+                                if (s == NULL)
+                                        return -1;
+
+                                s[sep_idx] = '\0';
+                                print_tracepoint_events(s, s + sep_idx + 1);
+                                free(s);
+                        }
+                }
+        }
         return 0;
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 821c1586a22b..9ac05aafd9b2 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -202,9 +202,20 @@ static struct thread_stat *thread_stat_findnew_first(u32 tid)
 SINGLE_KEY(nr_acquired)
 SINGLE_KEY(nr_contended)
 SINGLE_KEY(wait_time_total)
-SINGLE_KEY(wait_time_min)
 SINGLE_KEY(wait_time_max)
 
+static int lock_stat_key_wait_time_min(struct lock_stat *one,
+                                        struct lock_stat *two)
+{
+        u64 s1 = one->wait_time_min;
+        u64 s2 = two->wait_time_min;
+        if (s1 == ULLONG_MAX)
+                s1 = 0;
+        if (s2 == ULLONG_MAX)
+                s2 = 0;
+        return s1 > s2;
+}
+
 struct lock_key {
         /*
          * name: the value for specify by user
@@ -782,9 +793,9 @@ static void print_result(void)
                 pr_info("%10u ", st->nr_acquired);
                 pr_info("%10u ", st->nr_contended);
 
-                pr_info("%15llu ", st->wait_time_total);
-                pr_info("%15llu ", st->wait_time_max);
-                pr_info("%15llu ", st->wait_time_min == ULLONG_MAX ?
+                pr_info("%15" PRIu64 " ", st->wait_time_total);
+                pr_info("%15" PRIu64 " ", st->wait_time_max);
+                pr_info("%15" PRIu64 " ", st->wait_time_min == ULLONG_MAX ?
                        0 : st->wait_time_min);
                 pr_info("\n");
         }
@@ -834,35 +845,33 @@ static void dump_info(void)
                 die("Unknown type of information\n");
 }
 
-static int process_sample_event(event_t *self, struct perf_session *s)
+static int process_sample_event(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel __used,
+                                struct perf_session *s)
 {
-        struct sample_data data;
-        struct thread *thread;
+        struct thread *thread = perf_session__findnew(s, sample->tid);
 
-        bzero(&data, sizeof(data));
-        event__parse_sample(self, s->sample_type, &data);
-
-        thread = perf_session__findnew(s, data.tid);
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
-                        self->header.type);
+                        event->header.type);
                 return -1;
         }
 
-        process_raw_event(data.raw_data, data.cpu, data.time, thread);
+        process_raw_event(sample->raw_data, sample->cpu, sample->time, thread);
 
         return 0;
 }
 
 static struct perf_event_ops eops = {
         .sample                 = process_sample_event,
-        .comm                   = event__process_comm,
+        .comm                   = perf_event__process_comm,
         .ordered_samples        = true,
 };
 
 static int read_events(void)
 {
-        session = perf_session__new(input_name, O_RDONLY, 0, false);
+        session = perf_session__new(input_name, O_RDONLY, 0, false, &eops);
         if (!session)
                 die("Initializing perf session failed\n");
 
@@ -897,7 +906,7 @@ static const char * const report_usage[] = {
 
 static const struct option report_options[] = {
         OPT_STRING('k', "key", &sort_key, "acquired",
-                    "key for sorting"),
+                    "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"),
         /* TODO: type */
         OPT_END()
 };
@@ -947,6 +956,9 @@ static int __cmd_record(int argc, const char **argv)
         rec_argc = ARRAY_SIZE(record_args) + argc - 1;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+        if (rec_argv == NULL)
+                return -ENOMEM;
+
         for (i = 0; i < ARRAY_SIZE(record_args); i++)
                 rec_argv[i] = strdup(record_args[i]);
 
@@ -982,9 +994,9 @@ int cmd_lock(int argc, const char **argv, const char *prefix __used)
                                 usage_with_options(report_usage, report_options);
                 }
                 __cmd_report();
-        } else if (!strcmp(argv[0], "trace")) {
-                /* Aliased to 'perf trace' */
-                return cmd_trace(argc, argv, prefix);
+        } else if (!strcmp(argv[0], "script")) {
+                /* Aliased to 'perf script' */
+                return cmd_script(argc, argv, prefix);
         } else if (!strcmp(argv[0], "info")) {
                 if (argc) {
                         argc = parse_options(argc, argv,
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 199d5e19554f..2c0e64d0b4aa 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -36,6 +36,7 @@
 #include "builtin.h"
 #include "util/util.h"
 #include "util/strlist.h"
+#include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
 #include "util/debugfs.h"
@@ -43,6 +44,8 @@
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 
+#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
+#define DEFAULT_FUNC_FILTER "!_*"
 #define MAX_PATH_LEN 256
 
 /* Session management structure */
@@ -50,14 +53,19 @@ static struct {
         bool list_events;
         bool force_add;
         bool show_lines;
+        bool show_vars;
+        bool show_ext_vars;
+        bool show_funcs;
+        bool mod_events;
         int nevents;
         struct perf_probe_event events[MAX_PROBES];
         struct strlist *dellist;
         struct line_range line_range;
+        const char *target_module;
         int max_probe_points;
+        struct strfilter *filter;
 } params;
 
-
 /* Parse an event definition. Note that any error must die. */
 static int parse_probe_event(const char *str)
 {
@@ -92,6 +100,7 @@ static int parse_probe_event_argv(int argc, const char **argv)
         len = 0;
         for (i = 0; i < argc; i++)
                 len += sprintf(&buf[len], "%s ", argv[i]);
+        params.mod_events = true;
         ret = parse_probe_event(buf);
         free(buf);
         return ret;
@@ -100,9 +109,10 @@ static int parse_probe_event_argv(int argc, const char **argv)
 static int opt_add_probe_event(const struct option *opt __used,
                               const char *str, int unset __used)
 {
-        if (str)
+        if (str) {
+                params.mod_events = true;
                 return parse_probe_event(str);
-        else
+        } else
                 return 0;
 }
 
@@ -110,6 +120,7 @@ static int opt_del_probe_event(const struct option *opt __used,
                                const char *str, int unset __used)
 {
         if (str) {
+                params.mod_events = true;
                 if (!params.dellist)
                         params.dellist = strlist__new(true, NULL);
                 strlist__add(params.dellist, str);
@@ -130,15 +141,56 @@ static int opt_show_lines(const struct option *opt __used,
 
         return ret;
 }
+
+static int opt_show_vars(const struct option *opt __used,
+                         const char *str, int unset __used)
+{
+        struct perf_probe_event *pev = &params.events[params.nevents];
+        int ret;
+
+        if (!str)
+                return 0;
+
+        ret = parse_probe_event(str);
+        if (!ret && pev->nargs != 0) {
+                pr_err("  Error: '--vars' doesn't accept arguments.\n");
+                return -EINVAL;
+        }
+        params.show_vars = true;
+
+        return ret;
+}
 #endif
 
+static int opt_set_filter(const struct option *opt __used,
+                          const char *str, int unset __used)
+{
+        const char *err;
+
+        if (str) {
+                pr_debug2("Set filter: %s\n", str);
+                if (params.filter)
+                        strfilter__delete(params.filter);
+                params.filter = strfilter__new(str, &err);
+                if (!params.filter) {
+                        pr_err("Filter parse error at %td.\n", err - str + 1);
+                        pr_err("Source: \"%s\"\n", str);
+                        pr_err("         %*c\n", (int)(err - str + 1), '^');
+                        return -EINVAL;
+                }
+        }
+
+        return 0;
+}
+
 static const char * const probe_usage[] = {
         "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
         "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
         "perf probe [<options>] --del '[GROUP:]EVENT' ...",
         "perf probe --list",
 #ifdef DWARF_SUPPORT
-        "perf probe --line 'LINEDESC'",
+        "perf probe [<options>] --line 'LINEDESC'",
+        "perf probe [<options>] --vars 'PROBEPOINT'",
 #endif
         NULL
 };
@@ -180,14 +232,28 @@ static const struct option options[] = {
         OPT_CALLBACK('L', "line", NULL,
                      "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]",
                      "Show source code lines.", opt_show_lines),
+        OPT_CALLBACK('V', "vars", NULL,
+                     "FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
+                     "Show accessible variables on PROBEDEF", opt_show_vars),
+        OPT_BOOLEAN('\0', "externs", &params.show_ext_vars,
+                    "Show external variables too (with --vars only)"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_STRING('s', "source", &symbol_conf.source_prefix,
                    "directory", "path to kernel source"),
+        OPT_STRING('m', "module", &params.target_module,
+                   "modname", "target module name"),
 #endif
         OPT__DRY_RUN(&probe_event_dry_run),
         OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
                  "Set how many probe points can be found for a probe."),
+        OPT_BOOLEAN('F', "funcs", &params.show_funcs,
+                    "Show potential probe-able functions."),
+        OPT_CALLBACK('\0', "filter", NULL,
+                     "[!]FILTER", "Set a filter (with --vars/funcs only)\n"
+                     "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
+                     "\t\t\t \"" DEFAULT_FUNC_FILTER "\" for --funcs)",
+                     opt_set_filter),
         OPT_END()
 };
 
@@ -213,11 +279,16 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                 params.max_probe_points = MAX_PROBES;
 
         if ((!params.nevents && !params.dellist && !params.list_events &&
-             !params.show_lines))
+             !params.show_lines && !params.show_funcs))
                 usage_with_options(probe_usage, options);
 
+        /*
+         * Only consider the user's kernel image path if given.
+         */
+        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+
         if (params.list_events) {
-                if (params.nevents != 0 || params.dellist) {
+                if (params.mod_events) {
                         pr_err("  Error: Don't use --list with --add/--del.\n");
                         usage_with_options(probe_usage, options);
                 }
@@ -225,26 +296,83 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                         pr_err("  Error: Don't use --list with --line.\n");
                         usage_with_options(probe_usage, options);
                 }
+                if (params.show_vars) {
+                        pr_err(" Error: Don't use --list with --vars.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                if (params.show_funcs) {
+                        pr_err("  Error: Don't use --list with --funcs.\n");
+                        usage_with_options(probe_usage, options);
+                }
                 ret = show_perf_probe_events();
                 if (ret < 0)
                         pr_err("  Error: Failed to show event list. (%d)\n",
                                ret);
                 return ret;
         }
+        if (params.show_funcs) {
+                if (params.nevents != 0 || params.dellist) {
+                        pr_err("  Error: Don't use --funcs with"
+                               " --add/--del.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                if (params.show_lines) {
+                        pr_err("  Error: Don't use --funcs with --line.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                if (params.show_vars) {
+                        pr_err("  Error: Don't use --funcs with --vars.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                if (!params.filter)
+                        params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
+                                                       NULL);
+                ret = show_available_funcs(params.target_module,
+                                           params.filter);
+                strfilter__delete(params.filter);
+                if (ret < 0)
+                        pr_err("  Error: Failed to show functions."
+                               " (%d)\n", ret);
+                return ret;
+        }
 
 #ifdef DWARF_SUPPORT
         if (params.show_lines) {
-                if (params.nevents != 0 || params.dellist) {
-                        pr_warning("  Error: Don't use --line with"
-                                   " --add/--del.\n");
+                if (params.mod_events) {
+                        pr_err("  Error: Don't use --line with"
+                               " --add/--del.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                if (params.show_vars) {
+                        pr_err(" Error: Don't use --line with --vars.\n");
                         usage_with_options(probe_usage, options);
                 }
 
-                ret = show_line_range(&params.line_range);
+                ret = show_line_range(&params.line_range, params.target_module);
                 if (ret < 0)
                         pr_err("  Error: Failed to show lines. (%d)\n", ret);
                 return ret;
         }
+        if (params.show_vars) {
+                if (params.mod_events) {
+                        pr_err("  Error: Don't use --vars with"
+                               " --add/--del.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                if (!params.filter)
+                        params.filter = strfilter__new(DEFAULT_VAR_FILTER,
+                                                       NULL);
+
+                ret = show_available_vars(params.events, params.nevents,
+                                          params.max_probe_points,
+                                          params.target_module,
+                                          params.filter,
+                                          params.show_ext_vars);
+                strfilter__delete(params.filter);
+                if (ret < 0)
+                        pr_err("  Error: Failed to show vars. (%d)\n", ret);
+                return ret;
+        }
 #endif
 
         if (params.dellist) {
@@ -258,8 +386,9 @@ 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.force_add,
-                                            params.max_probe_points);
+                                            params.max_probe_points,
+                                            params.target_module,
+                                            params.force_add);
                 if (ret < 0) {
                         pr_err("  Error: Failed to add events. (%d)\n", ret);
                         return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ff77b805de71..8e2c85798185 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -18,41 +18,43 @@
 
 #include "util/header.h"
 #include "util/event.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/debug.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/cpumap.h"
+#include "util/thread_map.h"
 
 #include <unistd.h>
 #include <sched.h>
 #include <sys/mman.h>
 
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
 enum write_mode_t {
         WRITE_FORCE,
         WRITE_APPEND
 };
 
-static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
-
 static u64                      user_interval                   = ULLONG_MAX;
 static u64                      default_interval                =      0;
 
-static int                      nr_cpus                         =      0;
 static unsigned int             page_size;
-static unsigned int             mmap_pages                      =    128;
+static unsigned int             mmap_pages                      = UINT_MAX;
 static unsigned int             user_freq                       = UINT_MAX;
 static int                      freq                            =   1000;
 static int                      output;
 static int                      pipe_output                     =      0;
-static const char               *output_name                    = "perf.data";
+static const char               *output_name                    = NULL;
 static int                      group                           =      0;
 static int                      realtime_prio                   =      0;
+static bool                     nodelay                         =  false;
 static bool                     raw_samples                     =  false;
+static bool                     sample_id_all_avail             =   true;
 static bool                     system_wide                     =  false;
 static pid_t                    target_pid                      =     -1;
 static pid_t                    target_tid                      =     -1;
-static pid_t                    *all_tids                       =      NULL;
-static int                      thread_num                      =      0;
 static pid_t                    child_pid                       =     -1;
 static bool                     no_inherit                      =  false;
 static enum write_mode_t        write_mode                      = WRITE_FORCE;
@@ -60,53 +62,20 @@ static bool			call_graph			=  false;
 static bool                     inherit_stat                    =  false;
 static bool                     no_samples                      =  false;
 static bool                     sample_address                  =  false;
+static bool                     sample_time                     =  false;
 static bool                     no_buildid                      =  false;
+static bool                     no_buildid_cache                =  false;
+static struct perf_evlist       *evsel_list;
 
 static long                     samples                         =      0;
 static u64                      bytes_written                   =      0;
 
-static struct pollfd            *event_array;
-
-static int                      nr_poll                         =      0;
-static int                      nr_cpu                          =      0;
-
 static int                      file_new                        =      1;
 static off_t                    post_processing_offset;
 
 static struct perf_session      *session;
 static const char               *cpu_list;
 
-struct mmap_data {
-        int                     counter;
-        void                    *base;
-        unsigned int            mask;
-        unsigned int            prev;
-};
-
-static struct mmap_data         mmap_array[MAX_NR_CPUS];
-
-static unsigned long mmap_read_head(struct mmap_data *md)
-{
-        struct perf_event_mmap_page *pc = md->base;
-        long head;
-
-        head = pc->data_head;
-        rmb();
-
-        return head;
-}
-
-static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
-{
-        struct perf_event_mmap_page *pc = md->base;
-
-        /*
-         * ensure all reads are done before we write the tail out.
-         */
-        /* mb(); */
-        pc->data_tail = tail;
-}
-
 static void advance_output(size_t size)
 {
         bytes_written += size;
@@ -127,41 +96,26 @@ static void write_output(void *buf, size_t size)
         }
 }
 
-static int process_synthesized_event(event_t *event,
+static int process_synthesized_event(union perf_event *event,
+                                     struct perf_sample *sample __used,
                                      struct perf_session *self __used)
 {
         write_output(event, event->header.size);
         return 0;
 }
 
-static void mmap_read(struct mmap_data *md)
+static void mmap_read(struct perf_mmap *md)
 {
-        unsigned int head = mmap_read_head(md);
+        unsigned int head = perf_mmap__read_head(md);
         unsigned int old = md->prev;
         unsigned char *data = md->base + page_size;
         unsigned long size;
         void *buf;
-        int diff;
 
-        /*
-         * If we're further behind than half the buffer, there's a chance
-         * the writer will bite our tail and mess up the samples under us.
-         *
-         * If we somehow ended up ahead of the head, we got messed up.
-         *
-         * In either case, truncate and restart at head.
-         */
-        diff = head - old;
-        if (diff < 0) {
-                fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
-                /*
-                 * head points to a known good entry, start there.
-                 */
-                old = head;
-        }
+        if (old == head)
+                return;
 
-        if (old != head)
-                samples++;
+        samples++;
 
         size = head - old;
 
@@ -180,7 +134,7 @@ static void mmap_read(struct mmap_data *md)
         write_output(buf, size);
 
         md->prev = old;
-        mmap_write_tail(md, old);
+        perf_mmap__write_tail(md, old);
 }
 
 static volatile int done = 0;
@@ -197,55 +151,26 @@ static void sig_atexit(void)
         if (child_pid > 0)
                 kill(child_pid, SIGTERM);
 
-        if (signr == -1)
+        if (signr == -1 || signr == SIGUSR1)
                 return;
 
         signal(signr, SIG_DFL);
         kill(getpid(), signr);
 }
 
-static int group_fd;
-
-static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int nr)
-{
-        struct perf_header_attr *h_attr;
-
-        if (nr < session->header.attrs) {
-                h_attr = session->header.attr[nr];
-        } else {
-                h_attr = perf_header_attr__new(a);
-                if (h_attr != NULL)
-                        if (perf_header__add_attr(&session->header, h_attr) < 0) {
-                                perf_header_attr__delete(h_attr);
-                                h_attr = NULL;
-                        }
-        }
-
-        return h_attr;
-}
-
-static void create_counter(int counter, int cpu)
+static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 {
-        char *filter = filters[counter];
-        struct perf_event_attr *attr = attrs + counter;
-        struct perf_header_attr *h_attr;
-        int track = !counter; /* only the first counter needs these */
-        int thread_index;
-        int ret;
-        struct {
-                u64 count;
-                u64 time_enabled;
-                u64 time_running;
-                u64 id;
-        } read_data;
+        struct perf_event_attr *attr = &evsel->attr;
+        int track = !evsel->idx; /* only the first counter needs these */
 
+        attr->inherit           = !no_inherit;
         attr->read_format       = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                   PERF_FORMAT_TOTAL_TIME_RUNNING |
                                   PERF_FORMAT_ID;
 
         attr->sample_type       |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
-        if (nr_counters > 1)
+        if (evlist->nr_entries > 1)
                 attr->sample_type |= PERF_SAMPLE_ID;
 
         /*
@@ -280,35 +205,94 @@ static void create_counter(int counter, int cpu)
         if (system_wide)
                 attr->sample_type       |= PERF_SAMPLE_CPU;
 
+        if (sample_id_all_avail &&
+            (sample_time || system_wide || !no_inherit || cpu_list))
+                attr->sample_type       |= PERF_SAMPLE_TIME;
+
         if (raw_samples) {
                 attr->sample_type       |= PERF_SAMPLE_TIME;
                 attr->sample_type       |= PERF_SAMPLE_RAW;
                 attr->sample_type       |= PERF_SAMPLE_CPU;
         }
 
+        if (nodelay) {
+                attr->watermark = 0;
+                attr->wakeup_events = 1;
+        }
+
         attr->mmap              = track;
         attr->comm              = track;
-        attr->inherit           = !no_inherit;
+
         if (target_pid == -1 && target_tid == -1 && !system_wide) {
                 attr->disabled = 1;
                 attr->enable_on_exec = 1;
         }
+}
 
-        for (thread_index = 0; thread_index < thread_num; thread_index++) {
-try_again:
-                fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
-                                all_tids[thread_index], cpu, group_fd, 0);
+static bool perf_evlist__equal(struct perf_evlist *evlist,
+                               struct perf_evlist *other)
+{
+        struct perf_evsel *pos, *pair;
+
+        if (evlist->nr_entries != other->nr_entries)
+                return false;
+
+        pair = list_entry(other->entries.next, struct perf_evsel, node);
 
-                if (fd[nr_cpu][counter][thread_index] < 0) {
+        list_for_each_entry(pos, &evlist->entries, node) {
+                if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
+                        return false;
+                pair = list_entry(pair->node.next, struct perf_evsel, node);
+        }
+
+        return true;
+}
+
+static void open_counters(struct perf_evlist *evlist)
+{
+        struct perf_evsel *pos;
+
+        if (evlist->cpus->map[0] < 0)
+                no_inherit = true;
+
+        list_for_each_entry(pos, &evlist->entries, node) {
+                struct perf_event_attr *attr = &pos->attr;
+                /*
+                 * Check if parse_single_tracepoint_event has already asked for
+                 * PERF_SAMPLE_TIME.
+                 *
+                 * XXX this is kludgy but short term fix for problems introduced by
+                 * eac23d1c that broke 'perf script' by having different sample_types
+                 * when using multiple tracepoint events when we use a perf binary
+                 * that tries to use sample_id_all on an older kernel.
+                 *
+                 * We need to move counter creation to perf_session, support
+                 * different sample_types, etc.
+                 */
+                bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
+
+                config_attr(pos, evlist);
+retry_sample_id:
+                attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+try_again:
+                if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
                         int err = errno;
 
-                        if (err == EPERM || err == EACCES)
-                                die("Permission error - are you root?\n"
-                                        "\t Consider tweaking"
-                                        " /proc/sys/kernel/perf_event_paranoid.\n");
-                        else if (err ==  ENODEV && cpu_list) {
+                        if (err == EPERM || err == EACCES) {
+                                ui__warning_paranoid();
+                                exit(EXIT_FAILURE);
+                        } else if (err ==  ENODEV && cpu_list) {
                                 die("No such device - did you specify"
                                         " an out-of-range profile CPU?\n");
+                        } else if (err == EINVAL && sample_id_all_avail) {
+                                /*
+                                 * Old kernel, no attr->sample_id_type_all field
+                                 */
+                                sample_id_all_avail = false;
+                                if (!sample_time && !raw_samples && !time_needed)
+                                        attr->sample_type &= ~PERF_SAMPLE_TIME;
+
+                                goto retry_sample_id;
                         }
 
                         /*
@@ -320,14 +304,22 @@ try_again:
                                         && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
 
                                 if (verbose)
-                                        warning(" ... trying to fall back to cpu-clock-ticks\n");
+                                        ui__warning("The cycles event is not supported, "
+                                                    "trying to fall back to cpu-clock-ticks\n");
                                 attr->type = PERF_TYPE_SOFTWARE;
                                 attr->config = PERF_COUNT_SW_CPU_CLOCK;
                                 goto try_again;
                         }
+
+                        if (err == ENOENT) {
+                                ui__warning("The %s event is not supported.\n",
+                                            event_name(pos));
+                                exit(EXIT_FAILURE);
+                        }
+
                         printf("\n");
-                        error("perfcounter syscall returned with %d (%s)\n",
-                                        fd[nr_cpu][counter][thread_index], strerror(err));
+                        error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
+                              err, strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)
                         if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
@@ -338,85 +330,28 @@ try_again:
 #endif
 
                         die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-                        exit(-1);
                 }
+        }
 
-                h_attr = get_header_attr(attr, counter);
-                if (h_attr == NULL)
-                        die("nomem\n");
-
-                if (!file_new) {
-                        if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
-                                fprintf(stderr, "incompatible append\n");
-                                exit(-1);
-                        }
-                }
+        if (perf_evlist__set_filters(evlist)) {
+                error("failed to set filter with %d (%s)\n", errno,
+                        strerror(errno));
+                exit(-1);
+        }
 
-                if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
-                        perror("Unable to read perf file descriptor\n");
-                        exit(-1);
-                }
+        if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
+                die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 
-                if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
-                        pr_warning("Not enough memory to add id\n");
+        if (file_new)
+                session->evlist = evlist;
+        else {
+                if (!perf_evlist__equal(session->evlist, evlist)) {
+                        fprintf(stderr, "incompatible append\n");
                         exit(-1);
                 }
+        }
 
-                assert(fd[nr_cpu][counter][thread_index] >= 0);
-                fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
-
-                /*
-                 * First counter acts as the group leader:
-                 */
-                if (group && group_fd == -1)
-                        group_fd = fd[nr_cpu][counter][thread_index];
-
-                if (counter || thread_index) {
-                        ret = ioctl(fd[nr_cpu][counter][thread_index],
-                                        PERF_EVENT_IOC_SET_OUTPUT,
-                                        fd[nr_cpu][0][0]);
-                        if (ret) {
-                                error("failed to set output: %d (%s)\n", errno,
-                                                strerror(errno));
-                                exit(-1);
-                        }
-                } else {
-                        mmap_array[nr_cpu].counter = counter;
-                        mmap_array[nr_cpu].prev = 0;
-                        mmap_array[nr_cpu].mask = mmap_pages*page_size - 1;
-                        mmap_array[nr_cpu].base = mmap(NULL, (mmap_pages+1)*page_size,
-                                PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
-                        if (mmap_array[nr_cpu].base == MAP_FAILED) {
-                                error("failed to mmap with %d (%s)\n", errno, strerror(errno));
-                                exit(-1);
-                        }
-
-                        event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
-                        event_array[nr_poll].events = POLLIN;
-                        nr_poll++;
-                }
-
-                if (filter != NULL) {
-                        ret = ioctl(fd[nr_cpu][counter][thread_index],
-                                        PERF_EVENT_IOC_SET_FILTER, filter);
-                        if (ret) {
-                                error("failed to set filter with %d (%s)\n", errno,
-                                                strerror(errno));
-                                exit(-1);
-                        }
-                }
-        }
-}
-
-static void open_counters(int cpu)
-{
-        int counter;
-
-        group_fd = -1;
-        for (counter = 0; counter < nr_counters; counter++)
-                create_counter(counter, cpu);
-
-        nr_cpu++;
+        perf_session__update_sample_type(session);
 }
 
 static int process_buildids(void)
@@ -437,14 +372,16 @@ static void atexit_header(void)
         if (!pipe_output) {
                 session->header.data_size += bytes_written;
 
-                process_buildids();
-                perf_header__write(&session->header, output, true);
+                if (!no_buildid)
+                        process_buildids();
+                perf_session__write_header(session, evsel_list, output, true);
                 perf_session__delete(session);
+                perf_evlist__delete(evsel_list);
                 symbol__exit();
         }
 }
 
-static void event__synthesize_guest_os(struct machine *machine, void *data)
+static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
 {
         int err;
         struct perf_session *psession = data;
@@ -460,8 +397,8 @@ static void event__synthesize_guest_os(struct machine *machine, void *data)
          *method is used to avoid symbol missing when the first addr is
          *in module instead of in guest kernel.
          */
-        err = event__synthesize_modules(process_synthesized_event,
-                                        psession, machine);
+        err = perf_event__synthesize_modules(process_synthesized_event,
+                                             psession, machine);
         if (err < 0)
                 pr_err("Couldn't record guest kernel [%d]'s reference"
                        " relocation symbol.\n", machine->pid);
@@ -470,11 +407,12 @@ static void event__synthesize_guest_os(struct machine *machine, void *data)
          * We use _stext for guest kernel because guest kernel's /proc/kallsyms
          * have no _text sometimes.
          */
-        err = event__synthesize_kernel_mmap(process_synthesized_event,
-                                            psession, machine, "_text");
+        err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+                                                 psession, machine, "_text");
         if (err < 0)
-                err = event__synthesize_kernel_mmap(process_synthesized_event,
-                                                    psession, machine, "_stext");
+                err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+                                                         psession, machine,
+                                                         "_stext");
         if (err < 0)
                 pr_err("Couldn't record guest kernel [%d]'s reference"
                        " relocation symbol.\n", machine->pid);
@@ -489,9 +427,9 @@ static void mmap_read_all(void)
 {
         int i;
 
-        for (i = 0; i < nr_cpu; i++) {
-                if (mmap_array[i].base)
-                        mmap_read(&mmap_array[i]);
+        for (i = 0; i < evsel_list->nr_mmaps; i++) {
+                if (evsel_list->mmap[i].base)
+                        mmap_read(&evsel_list->mmap[i]);
         }
 
         if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
@@ -500,7 +438,7 @@ static void mmap_read_all(void)
 
 static int __cmd_record(int argc, const char **argv)
 {
-        int i, counter;
+        int i;
         struct stat st;
         int flags;
         int err;
@@ -515,24 +453,33 @@ static int __cmd_record(int argc, const char **argv)
         atexit(sig_atexit);
         signal(SIGCHLD, sig_handler);
         signal(SIGINT, sig_handler);
+        signal(SIGUSR1, sig_handler);
 
         if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
                 perror("failed to create pipes");
                 exit(-1);
         }
 
-        if (!strcmp(output_name, "-"))
-                pipe_output = 1;
-        else if (!stat(output_name, &st) && st.st_size) {
-                if (write_mode == WRITE_FORCE) {
-                        char oldname[PATH_MAX];
-                        snprintf(oldname, sizeof(oldname), "%s.old",
-                                 output_name);
-                        unlink(oldname);
-                        rename(output_name, oldname);
+        if (!output_name) {
+                if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
+                        pipe_output = 1;
+                else
+                        output_name = "perf.data";
+        }
+        if (output_name) {
+                if (!strcmp(output_name, "-"))
+                        pipe_output = 1;
+                else if (!stat(output_name, &st) && st.st_size) {
+                        if (write_mode == WRITE_FORCE) {
+                                char oldname[PATH_MAX];
+                                snprintf(oldname, sizeof(oldname), "%s.old",
+                                         output_name);
+                                unlink(oldname);
+                                rename(output_name, oldname);
+                        }
+                } else if (write_mode == WRITE_APPEND) {
+                        write_mode = WRITE_FORCE;
                 }
-        } else if (write_mode == WRITE_APPEND) {
-                write_mode = WRITE_FORCE;
         }
 
         flags = O_CREAT|O_RDWR;
@@ -551,25 +498,27 @@ static int __cmd_record(int argc, const char **argv)
         }
 
         session = perf_session__new(output_name, O_WRONLY,
-                                    write_mode == WRITE_FORCE, false);
+                                    write_mode == WRITE_FORCE, false, NULL);
         if (session == NULL) {
                 pr_err("Not enough memory for reading perf file header\n");
                 return -1;
         }
 
+        if (!no_buildid)
+                perf_header__set_feat(&session->header, HEADER_BUILD_ID);
+
         if (!file_new) {
-                err = perf_header__read(session, output);
+                err = perf_session__read_header(session, output);
                 if (err < 0)
                         goto out_delete_session;
         }
 
-        if (have_tracepoints(attrs, nr_counters))
+        if (have_tracepoints(&evsel_list->entries))
                 perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
-        /*
-         * perf_session__delete(session) will be called at atexit_header()
-         */
-        atexit(atexit_header);
+        /* 512 kiB: default amount of unprivileged mlocked memory */
+        if (mmap_pages == UINT_MAX)
+                mmap_pages = (512 * 1024) / page_size;
 
         if (forks) {
                 child_pid = fork();
@@ -606,11 +555,12 @@ static int __cmd_record(int argc, const char **argv)
                         execvp(argv[0], (char **)argv);
 
                         perror(argv[0]);
+                        kill(getppid(), SIGUSR1);
                         exit(-1);
                 }
 
                 if (!system_wide && target_tid == -1 && target_pid == -1)
-                        all_tids[0] = child_pid;
+                        evsel_list->threads->map[0] = child_pid;
 
                 close(child_ready_pipe[1]);
                 close(go_pipe[0]);
@@ -624,25 +574,20 @@ static int __cmd_record(int argc, const char **argv)
                 close(child_ready_pipe[0]);
         }
 
-        nr_cpus = read_cpu_map(cpu_list);
-        if (nr_cpus < 1) {
-                perror("failed to collect number of CPUs\n");
-                return -1;
-        }
+        open_counters(evsel_list);
 
-        if (!system_wide && no_inherit && !cpu_list) {
-                open_counters(-1);
-        } else {
-                for (i = 0; i < nr_cpus; i++)
-                        open_counters(cpumap[i]);
-        }
+        /*
+         * perf_session__delete(session) will be called at atexit_header()
+         */
+        atexit(atexit_header);
 
         if (pipe_output) {
                 err = perf_header__write_pipe(output);
                 if (err < 0)
                         return err;
         } else if (file_new) {
-                err = perf_header__write(&session->header, output, false);
+                err = perf_session__write_header(session, evsel_list,
+                                                 output, false);
                 if (err < 0)
                         return err;
         }
@@ -650,22 +595,21 @@ static int __cmd_record(int argc, const char **argv)
         post_processing_offset = lseek(output, 0, SEEK_CUR);
 
         if (pipe_output) {
-                err = event__synthesize_attrs(&session->header,
-                                              process_synthesized_event,
-                                              session);
+                err = perf_session__synthesize_attrs(session,
+                                                     process_synthesized_event);
                 if (err < 0) {
                         pr_err("Couldn't synthesize attrs.\n");
                         return err;
                 }
 
-                err = event__synthesize_event_types(process_synthesized_event,
-                                                    session);
+                err = perf_event__synthesize_event_types(process_synthesized_event,
+                                                         session);
                 if (err < 0) {
                         pr_err("Couldn't synthesize event_types.\n");
                         return err;
                 }
 
-                if (have_tracepoints(attrs, nr_counters)) {
+                if (have_tracepoints(&evsel_list->entries)) {
                         /*
                          * FIXME err <= 0 here actually means that
                          * there were no tracepoints so its not really
@@ -674,10 +618,9 @@ static int __cmd_record(int argc, const char **argv)
                          * return this more properly and also
                          * propagate errors that now are calling die()
                          */
-                        err = event__synthesize_tracing_data(output, attrs,
-                                                             nr_counters,
-                                                             process_synthesized_event,
-                                                             session);
+                        err = perf_event__synthesize_tracing_data(output, evsel_list,
+                                                                  process_synthesized_event,
+                                                                  session);
                         if (err <= 0) {
                                 pr_err("Couldn't record tracing data.\n");
                                 return err;
@@ -692,30 +635,34 @@ static int __cmd_record(int argc, const char **argv)
                 return -1;
         }
 
-        err = event__synthesize_kernel_mmap(process_synthesized_event,
-                                            session, machine, "_text");
+        err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+                                                 session, machine, "_text");
         if (err < 0)
-                err = event__synthesize_kernel_mmap(process_synthesized_event,
-                                                    session, machine, "_stext");
-        if (err < 0) {
-                pr_err("Couldn't record kernel reference relocation symbol.\n");
-                return err;
-        }
+                err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
+                                                         session, machine, "_stext");
+        if (err < 0)
+                pr_err("Couldn't record kernel reference relocation symbol\n"
+                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                       "Check /proc/kallsyms permission or run as root.\n");
+
+        err = perf_event__synthesize_modules(process_synthesized_event,
+                                             session, machine);
+        if (err < 0)
+                pr_err("Couldn't record kernel module information.\n"
+                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                       "Check /proc/modules permission or run as root.\n");
 
-        err = event__synthesize_modules(process_synthesized_event,
-                                        session, machine);
-        if (err < 0) {
-                pr_err("Couldn't record kernel reference relocation symbol.\n");
-                return err;
-        }
         if (perf_guest)
-                perf_session__process_machines(session, event__synthesize_guest_os);
+                perf_session__process_machines(session,
+                                               perf_event__synthesize_guest_os);
 
         if (!system_wide)
-                event__synthesize_thread(target_tid, process_synthesized_event,
-                                         session);
+                perf_event__synthesize_thread_map(evsel_list->threads,
+                                                  process_synthesized_event,
+                                                  session);
         else
-                event__synthesize_threads(process_synthesized_event, session);
+                perf_event__synthesize_threads(process_synthesized_event,
+                                               session);
 
         if (realtime_prio) {
                 struct sched_param param;
@@ -742,32 +689,35 @@ static int __cmd_record(int argc, const char **argv)
                 if (hits == samples) {
                         if (done)
                                 break;
-                        err = poll(event_array, nr_poll, -1);
+                        err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
                         waking++;
                 }
 
                 if (done) {
-                        for (i = 0; i < nr_cpu; i++) {
-                                for (counter = 0;
-                                        counter < nr_counters;
-                                        counter++) {
+                        for (i = 0; i < evsel_list->cpus->nr; i++) {
+                                struct perf_evsel *pos;
+
+                                list_for_each_entry(pos, &evsel_list->entries, node) {
                                         for (thread = 0;
-                                                thread < thread_num;
+                                                thread < evsel_list->threads->nr;
                                                 thread++)
-                                                ioctl(fd[i][counter][thread],
+                                                ioctl(FD(pos, i, thread),
                                                         PERF_EVENT_IOC_DISABLE);
                                 }
                         }
                 }
         }
 
+        if (quiet || signr == SIGUSR1)
+                return 0;
+
         fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
 
         /*
          * Approximate RIP event size: 24 bytes.
          */
         fprintf(stderr,
-                "[ perf record: Captured and wrote %.3f MB %s (~%lld samples) ]\n",
+                "[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
                 (double)bytes_written / 1024.0 / 1024.0,
                 output_name,
                 bytes_written / 24);
@@ -787,11 +737,11 @@ static const char * const record_usage[] = {
 
 static bool force, append_file;
 
-static const struct option options[] = {
-        OPT_CALLBACK('e', "event", NULL, "event",
+const struct option record_options[] = {
+        OPT_CALLBACK('e', "event", &evsel_list, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events),
-        OPT_CALLBACK(0, "filter", NULL, "filter",
+        OPT_CALLBACK(0, "filter", &evsel_list, "filter",
                      "event filter", parse_filter),
         OPT_INTEGER('p', "pid", &target_pid,
                     "record events on existing process id"),
@@ -799,6 +749,8 @@ static const struct option options[] = {
                     "record events on existing thread id"),
         OPT_INTEGER('r', "realtime", &realtime_prio,
                     "collect data with this RT SCHED_FIFO priority"),
+        OPT_BOOLEAN('D', "no-delay", &nodelay,
+                    "collect data without buffering"),
         OPT_BOOLEAN('R', "raw-samples", &raw_samples,
                     "collect raw sample records from all opened counters"),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
@@ -820,74 +772,92 @@ static const struct option options[] = {
                     "do call-graph (stack chain/backtrace) recording"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show counter open errors, etc)"),
+        OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
         OPT_BOOLEAN('s', "stat", &inherit_stat,
                     "per thread counts"),
         OPT_BOOLEAN('d', "data", &sample_address,
                     "Sample addresses"),
+        OPT_BOOLEAN('T', "timestamp", &sample_time, "Sample timestamps"),
         OPT_BOOLEAN('n', "no-samples", &no_samples,
                     "don't sample"),
-        OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid,
+        OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid_cache,
                     "do not update the buildid cache"),
+        OPT_BOOLEAN('B', "no-buildid", &no_buildid,
+                    "do not collect buildids in perf.data"),
+        OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+                     "monitor event in cgroup name only",
+                     parse_cgroups),
         OPT_END()
 };
 
 int cmd_record(int argc, const char **argv, const char *prefix __used)
 {
-        int i, j, err = -ENOMEM;
+        int err = -ENOMEM;
+        struct perf_evsel *pos;
 
-        argc = parse_options(argc, argv, options, record_usage,
+        evsel_list = perf_evlist__new(NULL, NULL);
+        if (evsel_list == NULL)
+                return -ENOMEM;
+
+        argc = parse_options(argc, argv, record_options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
         if (!argc && target_pid == -1 && target_tid == -1 &&
                 !system_wide && !cpu_list)
-                usage_with_options(record_usage, options);
+                usage_with_options(record_usage, record_options);
 
         if (force && append_file) {
                 fprintf(stderr, "Can't overwrite and append at the same time."
                                 " You need to choose between -f and -A");
-                usage_with_options(record_usage, options);
+                usage_with_options(record_usage, record_options);
         } else if (append_file) {
                 write_mode = WRITE_APPEND;
         } else {
                 write_mode = WRITE_FORCE;
         }
 
+        if (nr_cgroups && !system_wide) {
+                fprintf(stderr, "cgroup monitoring only available in"
+                        " system-wide mode\n");
+                usage_with_options(record_usage, record_options);
+        }
+
         symbol__init();
-        if (no_buildid)
+
+        if (symbol_conf.kptr_restrict)
+                pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+
+        if (no_buildid_cache || no_buildid)
                 disable_buildid_cache();
 
-        if (!nr_counters) {
-                nr_counters     = 1;
-                attrs[0].type   = PERF_TYPE_HARDWARE;
-                attrs[0].config = PERF_COUNT_HW_CPU_CYCLES;
+        if (evsel_list->nr_entries == 0 &&
+            perf_evlist__add_default(evsel_list) < 0) {
+                pr_err("Not enough memory for event selector list\n");
+                goto out_symbol_exit;
         }
 
-        if (target_pid != -1) {
+        if (target_pid != -1)
                 target_tid = target_pid;
-                thread_num = find_all_tid(target_pid, &all_tids);
-                if (thread_num <= 0) {
-                        fprintf(stderr, "Can't find all threads of pid %d\n",
-                                        target_pid);
-                        usage_with_options(record_usage, options);
-                }
-        } else {
-                all_tids=malloc(sizeof(pid_t));
-                if (!all_tids)
-                        goto out_symbol_exit;
 
-                all_tids[0] = target_tid;
-                thread_num = 1;
-        }
+        if (perf_evlist__create_maps(evsel_list, target_pid,
+                                     target_tid, cpu_list) < 0)
+                usage_with_options(record_usage, record_options);
 
-        for (i = 0; i < MAX_NR_CPUS; i++) {
-                for (j = 0; j < MAX_COUNTERS; j++) {
-                        fd[i][j] = malloc(sizeof(int)*thread_num);
-                        if (!fd[i][j])
-                                goto out_free_fd;
-                }
+        list_for_each_entry(pos, &evsel_list->entries, node) {
+                if (perf_evsel__alloc_fd(pos, evsel_list->cpus->nr,
+                                         evsel_list->threads->nr) < 0)
+                        goto out_free_fd;
+                if (perf_header__push_event(pos->attr.config, event_name(pos)))
+                        goto out_free_fd;
         }
-        event_array = malloc(
-                sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
-        if (!event_array)
+
+        if (perf_evlist__alloc_pollfd(evsel_list) < 0)
                 goto out_free_fd;
 
         if (user_interval != ULLONG_MAX)
@@ -905,20 +875,12 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
         } else {
                 fprintf(stderr, "frequency and count are zero, aborting\n");
                 err = -EINVAL;
-                goto out_free_event_array;
+                goto out_free_fd;
         }
 
         err = __cmd_record(argc, argv);
-
-out_free_event_array:
-        free(event_array);
 out_free_fd:
-        for (i = 0; i < MAX_NR_CPUS; i++) {
-                for (j = 0; j < MAX_COUNTERS; j++)
-                        free(fd[i][j]);
-        }
-        free(all_tids);
-        all_tids = NULL;
+        perf_evlist__delete_maps(evsel_list);
 out_symbol_exit:
         symbol__exit();
         return err;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 55fc1f46892a..287a173523a7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -9,6 +9,7 @@
 
 #include "util/util.h"
 
+#include "util/annotate.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
@@ -20,6 +21,8 @@
 
 #include "perf.h"
 #include "util/debug.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/header.h"
 #include "util/session.h"
 
@@ -32,7 +35,7 @@
 
 static char             const *input_name = "perf.data";
 
-static bool             force;
+static bool             force, use_tui, use_stdio;
 static bool             hide_unresolved;
 static bool             dont_use_callchains;
 
@@ -43,119 +46,68 @@ static const char	default_pretty_printing_style[] = "normal";
 static const char       *pretty_printing_style = default_pretty_printing_style;
 
 static char             callchain_default_opt[] = "fractal,0.5";
+static symbol_filter_t  annotate_init;
 
-static struct hists *perf_session__hists_findnew(struct perf_session *self,
-                                                 u64 event_stream, u32 type,
-                                                 u64 config)
-{
-        struct rb_node **p = &self->hists_tree.rb_node;
-        struct rb_node *parent = NULL;
-        struct hists *iter, *new;
-
-        while (*p != NULL) {
-                parent = *p;
-                iter = rb_entry(parent, struct hists, rb_node);
-                if (iter->config == config)
-                        return iter;
-
-
-                if (config > iter->config)
-                        p = &(*p)->rb_right;
-                else
-                        p = &(*p)->rb_left;
-        }
-
-        new = malloc(sizeof(struct hists));
-        if (new == NULL)
-                return NULL;
-        memset(new, 0, sizeof(struct hists));
-        new->event_stream = event_stream;
-        new->config = config;
-        new->type = type;
-        rb_link_node(&new->rb_node, parent, p);
-        rb_insert_color(&new->rb_node, &self->hists_tree);
-        return new;
-}
-
-static int perf_session__add_hist_entry(struct perf_session *self,
+static int perf_session__add_hist_entry(struct perf_session *session,
                                         struct addr_location *al,
-                                        struct sample_data *data)
+                                        struct perf_sample *sample,
+                                        struct perf_evsel *evsel)
 {
-        struct map_symbol *syms = NULL;
         struct symbol *parent = NULL;
-        int err = -ENOMEM;
+        int err = 0;
         struct hist_entry *he;
-        struct hists *hists;
-        struct perf_event_attr *attr;
-
-        if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) {
-                syms = perf_session__resolve_callchain(self, al->thread,
-                                                       data->callchain, &parent);
-                if (syms == NULL)
-                        return -ENOMEM;
+
+        if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
+                err = perf_session__resolve_callchain(session, al->thread,
+                                                      sample->callchain, &parent);
+                if (err)
+                        return err;
         }
 
-        attr = perf_header__find_attr(data->id, &self->header);
-        if (attr)
-                hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config);
-        else
-                hists = perf_session__hists_findnew(self, data->id, 0, 0);
-        if (hists == NULL)
-                goto out_free_syms;
-        he = __hists__add_entry(hists, al, parent, data->period);
+        he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
         if (he == NULL)
-                goto out_free_syms;
-        err = 0;
+                return -ENOMEM;
+
         if (symbol_conf.use_callchain) {
-                err = append_chain(he->callchain, data->callchain, syms, data->period);
+                err = callchain_append(he->callchain, &session->callchain_cursor,
+                                       sample->period);
                 if (err)
-                        goto out_free_syms;
+                        return err;
         }
         /*
          * Only in the newt browser we are doing integrated annotation,
          * so we don't allocated the extra space needed because the stdio
          * code will not use it.
          */
-        if (use_browser > 0)
-                err = hist_entry__inc_addr_samples(he, al->addr);
-out_free_syms:
-        free(syms);
-        return err;
-}
+        if (al->sym != NULL && use_browser > 0) {
+                struct annotation *notes = symbol__annotation(he->ms.sym);
 
-static int add_event_total(struct perf_session *session,
-                           struct sample_data *data,
-                           struct perf_event_attr *attr)
-{
-        struct hists *hists;
+                assert(evsel != NULL);
 
-        if (attr)
-                hists = perf_session__hists_findnew(session, data->id,
-                                                    attr->type, attr->config);
-        else
-                hists = perf_session__hists_findnew(session, data->id, 0, 0);
+                err = -ENOMEM;
+                if (notes->src == NULL &&
+                    symbol__alloc_hist(he->ms.sym, session->evlist->nr_entries) < 0)
+                        goto out;
 
-        if (!hists)
-                return -ENOMEM;
+                err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+        }
 
-        hists->stats.total_period += data->period;
-        /*
-         * FIXME: add_event_total should be moved from here to
-         * perf_session__process_event so that the proper hist is passed to
-         * the event_op methods.
-         */
-        hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
-        session->hists.stats.total_period += data->period;
-        return 0;
+        evsel->hists.stats.total_period += sample->period;
+        hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+out:
+        return err;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+
+static int process_sample_event(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel,
+                                struct perf_session *session)
 {
-        struct sample_data data = { .period = 1, };
         struct addr_location al;
-        struct perf_event_attr *attr;
 
-        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+        if (perf_event__preprocess_sample(event, session, &al, sample,
+                                          annotate_init) < 0) {
                 fprintf(stderr, "problem processing %d event, skipping it.\n",
                         event->header.type);
                 return -1;
@@ -164,30 +116,25 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         if (al.filtered || (hide_unresolved && al.sym == NULL))
                 return 0;
 
-        if (perf_session__add_hist_entry(session, &al, &data)) {
-                pr_debug("problem incrementing symbol period, skipping event\n");
-                return -1;
-        }
+        if (al.map != NULL)
+                al.map->dso->hit = 1;
 
-        attr = perf_header__find_attr(data.id, &session->header);
-
-        if (add_event_total(session, &data, attr)) {
-                pr_debug("problem adding event period\n");
+        if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
+                pr_debug("problem incrementing symbol period, skipping event\n");
                 return -1;
         }
 
         return 0;
 }
 
-static int process_read_event(event_t *event, struct perf_session *session __used)
+static int process_read_event(union perf_event *event,
+                              struct perf_sample *sample __used,
+                              struct perf_session *session)
 {
-        struct perf_event_attr *attr;
-
-        attr = perf_header__find_attr(event->read.id, &session->header);
-
+        struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist,
+                                                         event->read.id);
         if (show_threads) {
-                const char *name = attr ? __event_name(attr->type, attr->config)
-                                   : "unknown";
+                const char *name = evsel ? event_name(evsel) : "unknown";
                 perf_read_values_add_value(&show_threads_values,
                                            event->read.pid, event->read.tid,
                                            event->read.id,
@@ -195,8 +142,8 @@ static int process_read_event(event_t *event, struct perf_session *session __use
                                            event->read.value);
         }
 
-        dump_printf(": %d %d %s %Lu\n", event->read.pid, event->read.tid,
-                    attr ? __event_name(attr->type, attr->config) : "FAIL",
+        dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
+                    evsel ? event_name(evsel) : "FAIL",
                     event->read.value);
 
         return 0;
@@ -220,7 +167,7 @@ static int perf_session__setup_sample_type(struct perf_session *self)
         } else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
                    !symbol_conf.use_callchain) {
                         symbol_conf.use_callchain = true;
-                        if (register_callchain_param(&callchain_param) < 0) {
+                        if (callchain_register_param(&callchain_param) < 0) {
                                 fprintf(stderr, "Can't register callchain"
                                                 " params\n");
                                 return -EINVAL;
@@ -231,17 +178,19 @@ static int perf_session__setup_sample_type(struct perf_session *self)
 }
 
 static struct perf_event_ops event_ops = {
-        .sample = process_sample_event,
-        .mmap   = event__process_mmap,
-        .comm   = event__process_comm,
-        .exit   = event__process_task,
-        .fork   = event__process_task,
-        .lost   = event__process_lost,
-        .read   = process_read_event,
-        .attr   = event__process_attr,
-        .event_type = event__process_event_type,
-        .tracing_data = event__process_tracing_data,
-        .build_id = event__process_build_id,
+        .sample          = process_sample_event,
+        .mmap            = perf_event__process_mmap,
+        .comm            = perf_event__process_comm,
+        .exit            = perf_event__process_task,
+        .fork            = perf_event__process_task,
+        .lost            = perf_event__process_lost,
+        .read            = process_read_event,
+        .attr            = perf_event__process_attr,
+        .event_type      = perf_event__process_event_type,
+        .tracing_data    = perf_event__process_tracing_data,
+        .build_id        = perf_event__process_build_id,
+        .ordered_samples = true,
+        .ordering_requires_timestamps = true,
 };
 
 extern volatile int session_done;
@@ -265,21 +214,21 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
         return ret + fprintf(fp, "\n#\n");
 }
 
-static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
+static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
+                                         const char *help)
 {
-        struct rb_node *next = rb_first(tree);
+        struct perf_evsel *pos;
 
-        while (next) {
-                struct hists *hists = rb_entry(next, struct hists, rb_node);
+        list_for_each_entry(pos, &evlist->entries, node) {
+                struct hists *hists = &pos->hists;
                 const char *evname = NULL;
 
                 if (rb_first(&hists->entries) != rb_last(&hists->entries))
-                        evname = __event_name(hists->type, hists->config);
+                        evname = event_name(pos);
 
                 hists__fprintf_nr_sample_events(hists, evname, stdout);
                 hists__fprintf(hists, NULL, false, stdout);
                 fprintf(stdout, "\n\n");
-                next = rb_next(&hists->rb_node);
         }
 
         if (sort_order == default_sort_order &&
@@ -300,13 +249,16 @@ static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
 static int __cmd_report(void)
 {
         int ret = -EINVAL;
+        u64 nr_samples;
         struct perf_session *session;
-        struct rb_node *next;
+        struct perf_evsel *pos;
+        struct map *kernel_map;
+        struct kmap *kernel_kmap;
         const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
         signal(SIGINT, sig_handler);
 
-        session = perf_session__new(input_name, O_RDONLY, force, false);
+        session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -321,6 +273,24 @@ static int __cmd_report(void)
         if (ret)
                 goto out_delete;
 
+        kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION];
+        kernel_kmap = map__kmap(kernel_map);
+        if (kernel_map == NULL ||
+            (kernel_map->dso->hit &&
+             (kernel_kmap->ref_reloc_sym == NULL ||
+              kernel_kmap->ref_reloc_sym->addr == 0))) {
+                const struct dso *kdso = kernel_map->dso;
+
+                ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+                            RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION]) ?
+"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+"can't be resolved." :
+"If some relocation was applied (e.g. kexec) symbols may be misresolved.");
+        }
+
         if (dump_trace) {
                 perf_session__fprintf_nr_events(session, stdout);
                 goto out_delete;
@@ -332,20 +302,24 @@ static int __cmd_report(void)
         if (verbose > 2)
                 perf_session__fprintf_dsos(session, stdout);
 
-        next = rb_first(&session->hists_tree);
-        while (next) {
-                struct hists *hists;
+        nr_samples = 0;
+        list_for_each_entry(pos, &session->evlist->entries, node) {
+                struct hists *hists = &pos->hists;
 
-                hists = rb_entry(next, struct hists, rb_node);
                 hists__collapse_resort(hists);
                 hists__output_resort(hists);
-                next = rb_next(&hists->rb_node);
+                nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
+        }
+
+        if (nr_samples == 0) {
+                ui__warning("The %s file has no samples!\n", input_name);
+                goto out_delete;
         }
 
         if (use_browser > 0)
-                hists__tui_browse_tree(&session->hists_tree, help);
+                perf_evlist__tui_browse_hists(session->evlist, help);
         else
-                hists__tty_browse_tree(&session->hists_tree, help);
+                perf_evlist__tty_browse_hists(session->evlist, help);
 
 out_delete:
         /*
@@ -420,7 +394,7 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
         if (tok2)
                 callchain_param.print_limit = strtod(tok2, &endptr);
 setup:
-        if (register_callchain_param(&callchain_param) < 0) {
+        if (callchain_register_param(&callchain_param) < 0) {
                 fprintf(stderr, "Can't register callchain params\n");
                 return -1;
         }
@@ -441,6 +415,8 @@ static const struct option options[] = {
                     "dump raw trace in ASCII"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
+        OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+                   "file", "kallsyms pathname"),
         OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
         OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
                     "load module symbols - WARNING: use only with -k and LIVE kernel"),
@@ -450,6 +426,8 @@ static const struct option options[] = {
                     "Show per-thread event counters"),
         OPT_STRING(0, "pretty", &pretty_printing_style, "key",
                    "pretty printing style key: normal raw"),
+        OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+        OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
         OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
                    "sort by key(s): pid, comm, dso, symbol, parent"),
         OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -475,6 +453,8 @@ static const struct option options[] = {
                    "columns '.' is reserved."),
         OPT_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
                     "Only display entries resolved to a symbol"),
+        OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+                    "Look for files with symbols relative to this directory"),
         OPT_END()
 };
 
@@ -482,15 +462,23 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
 {
         argc = parse_options(argc, argv, options, report_usage, 0);
 
+        if (use_stdio)
+                use_browser = 0;
+        else if (use_tui)
+                use_browser = 1;
+
         if (strcmp(input_name, "-") != 0)
-                setup_browser();
+                setup_browser(true);
+        else
+                use_browser = 0;
         /*
          * Only in the newt browser we are doing integrated annotation,
          * so don't allocate extra space that won't be used in the stdio
          * implementation.
          */
         if (use_browser > 0) {
-                symbol_conf.priv_size = sizeof(struct sym_priv);
+                symbol_conf.priv_size = sizeof(struct annotation);
+                annotate_init         = symbol__annotate_init;
                 /*
                  * For searching by name on the "Browse map details".
                  * providing it only in verbose mode not to bloat too
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 55f3b5dcc731..dcfe8873c9a1 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -193,7 +193,7 @@ static void calibrate_run_measurement_overhead(void)
         }
         run_measurement_overhead = min_delta;
 
-        printf("run measurement overhead: %Ld nsecs\n", min_delta);
+        printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static void calibrate_sleep_measurement_overhead(void)
@@ -211,7 +211,7 @@ static void calibrate_sleep_measurement_overhead(void)
         min_delta -= 10000;
         sleep_measurement_overhead = min_delta;
 
-        printf("sleep measurement overhead: %Ld nsecs\n", min_delta);
+        printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
 }
 
 static struct sched_atom *
@@ -369,11 +369,6 @@ static void
 process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom)
 {
         int ret = 0;
-        u64 now;
-        long long delta;
-
-        now = get_nsecs();
-        delta = start_time + atom->timestamp - now;
 
         switch (atom->type) {
                 case SCHED_EVENT_RUN:
@@ -489,7 +484,8 @@ static void create_tasks(void)
 
         err = pthread_attr_init(&attr);
         BUG_ON(err);
-        err = pthread_attr_setstacksize(&attr, (size_t)(16*1024));
+        err = pthread_attr_setstacksize(&attr,
+                        (size_t) max(16 * 1024, PTHREAD_STACK_MIN));
         BUG_ON(err);
         err = pthread_mutex_lock(&start_work_mutex);
         BUG_ON(err);
@@ -561,7 +557,7 @@ static void wait_for_tasks(void)
 
 static void run_one_test(void)
 {
-        u64 T0, T1, delta, avg_delta, fluct, std_dev;
+        u64 T0, T1, delta, avg_delta, fluct;
 
         T0 = get_nsecs();
         wait_for_tasks();
@@ -577,7 +573,6 @@ static void run_one_test(void)
         else
                 fluct = delta - avg_delta;
         sum_fluct += fluct;
-        std_dev = sum_fluct / nr_runs / sqrt(nr_runs);
         if (!run_avg)
                 run_avg = delta;
         run_avg = (run_avg*9 + delta)/10;
@@ -616,13 +611,13 @@ static void test_calibrations(void)
         burn_nsecs(1e6);
         T1 = get_nsecs();
 
-        printf("the run test took %Ld nsecs\n", T1-T0);
+        printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
 
         T0 = get_nsecs();
         sleep_nsecs(1e6);
         T1 = get_nsecs();
 
-        printf("the sleep test took %Ld nsecs\n", T1-T0);
+        printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
 }
 
 #define FILL_FIELD(ptr, field, event, data)     \
@@ -798,7 +793,7 @@ replay_switch_event(struct trace_switch_event *switch_event,
                     u64 timestamp,
                     struct thread *thread __used)
 {
-        struct task_desc *prev, *next;
+        struct task_desc *prev, __used *next;
         u64 timestamp0;
         s64 delta;
 
@@ -815,10 +810,10 @@ replay_switch_event(struct trace_switch_event *switch_event,
                 delta = 0;
 
         if (delta < 0)
-                die("hm, delta: %Ld < 0 ?\n", delta);
+                die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
         if (verbose) {
-                printf(" ... switch from %s/%d to %s/%d [ran %Ld nsecs]\n",
+                printf(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
                         switch_event->prev_comm, switch_event->prev_pid,
                         switch_event->next_comm, switch_event->next_pid,
                         delta);
@@ -1047,7 +1042,7 @@ latency_switch_event(struct trace_switch_event *switch_event,
                 delta = 0;
 
         if (delta < 0)
-                die("hm, delta: %Ld < 0 ?\n", delta);
+                die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 
         sched_out = perf_session__findnew(session, switch_event->prev_pid);
@@ -1220,7 +1215,7 @@ static void output_lat_thread(struct work_atoms *work_list)
 
         avg = work_list->total_lat / work_list->nb_atoms;
 
-        printf("|%11.3f ms |%9llu | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
+        printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
               (double)work_list->total_runtime / 1e6,
                  work_list->nb_atoms, (double)avg / 1e6,
                  (double)work_list->max_lat / 1e6,
@@ -1403,7 +1398,7 @@ map_switch_event(struct trace_switch_event *switch_event,
                  u64 timestamp,
                  struct thread *thread __used)
 {
-        struct thread *sched_out, *sched_in;
+        struct thread *sched_out __used, *sched_in;
         int new_shortname;
         u64 timestamp0;
         s64 delta;
@@ -1422,7 +1417,7 @@ map_switch_event(struct trace_switch_event *switch_event,
                 delta = 0;
 
         if (delta < 0)
-                die("hm, delta: %Ld < 0 ?\n", delta);
+                die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
 
 
         sched_out = perf_session__findnew(session, switch_event->prev_pid);
@@ -1579,9 +1574,9 @@ process_sched_migrate_task_event(void *data, struct perf_session *session,
                                                  event, cpu, timestamp, thread);
 }
 
-static void
-process_raw_event(event_t *raw_event __used, struct perf_session *session,
-                  void *data, int cpu, u64 timestamp, struct thread *thread)
+static void process_raw_event(union perf_event *raw_event __used,
+                              struct perf_session *session, void *data, int cpu,
+                              u64 timestamp, struct thread *thread)
 {
         struct event *event;
         int type;
@@ -1606,25 +1601,17 @@ process_raw_event(event_t *raw_event __used, struct perf_session *session,
                 process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread);
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel __used,
+                                struct perf_session *session)
 {
-        struct sample_data data;
         struct thread *thread;
 
         if (!(session->sample_type & PERF_SAMPLE_RAW))
                 return 0;
 
-        memset(&data, 0, sizeof(data));
-        data.time = -1;
-        data.cpu = -1;
-        data.period = -1;
-
-        event__parse_sample(event, session->sample_type, &data);
-
-        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-                    data.pid, data.tid, data.ip, data.period);
-
-        thread = perf_session__findnew(session, data.pid);
+        thread = perf_session__findnew(session, sample->pid);
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
                          event->header.type);
@@ -1633,26 +1620,28 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
 
-        if (profile_cpu != -1 && profile_cpu != (int)data.cpu)
+        if (profile_cpu != -1 && profile_cpu != (int)sample->cpu)
                 return 0;
 
-        process_raw_event(event, session, data.raw_data, data.cpu, data.time, thread);
+        process_raw_event(event, session, sample->raw_data, sample->cpu,
+                          sample->time, thread);
 
         return 0;
 }
 
 static struct perf_event_ops event_ops = {
         .sample                 = process_sample_event,
-        .comm                   = event__process_comm,
-        .lost                   = event__process_lost,
-        .fork                   = event__process_task,
+        .comm                   = perf_event__process_comm,
+        .lost                   = perf_event__process_lost,
+        .fork                   = perf_event__process_task,
         .ordered_samples        = true,
 };
 
 static int read_events(void)
 {
         int err = -EINVAL;
-        struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+        struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+                                                         0, false, &event_ops);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -1720,7 +1709,7 @@ static void __cmd_lat(void)
         }
 
         printf(" -----------------------------------------------------------------------------------------\n");
-        printf("  TOTAL:                |%11.3f ms |%9Ld |\n",
+        printf("  TOTAL:                |%11.3f ms |%9" PRIu64 " |\n",
                 (double)all_runtime/1e6, all_count);
 
         printf(" ---------------------------------------------------\n");
@@ -1850,15 +1839,15 @@ static const char *record_args[] = {
         "-f",
         "-m", "1024",
         "-c", "1",
-        "-e", "sched:sched_switch:r",
-        "-e", "sched:sched_stat_wait:r",
-        "-e", "sched:sched_stat_sleep:r",
-        "-e", "sched:sched_stat_iowait:r",
-        "-e", "sched:sched_stat_runtime:r",
-        "-e", "sched:sched_process_exit:r",
-        "-e", "sched:sched_process_fork:r",
-        "-e", "sched:sched_wakeup:r",
-        "-e", "sched:sched_migrate_task:r",
+        "-e", "sched:sched_switch",
+        "-e", "sched:sched_stat_wait",
+        "-e", "sched:sched_stat_sleep",
+        "-e", "sched:sched_stat_iowait",
+        "-e", "sched:sched_stat_runtime",
+        "-e", "sched:sched_process_exit",
+        "-e", "sched:sched_process_fork",
+        "-e", "sched:sched_wakeup",
+        "-e", "sched:sched_migrate_task",
 };
 
 static int __cmd_record(int argc, const char **argv)
@@ -1869,6 +1858,9 @@ static int __cmd_record(int argc, const char **argv)
         rec_argc = ARRAY_SIZE(record_args) + argc - 1;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
+        if (rec_argv == NULL)
+                return -ENOMEM;
+
         for (i = 0; i < ARRAY_SIZE(record_args); i++)
                 rec_argv[i] = strdup(record_args[i]);
 
@@ -1888,10 +1880,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __used)
                 usage_with_options(sched_usage, sched_options);
 
         /*
-         * Aliased to 'perf trace' for now:
+         * Aliased to 'perf script' for now:
          */
-        if (!strcmp(argv[0], "trace"))
-                return cmd_trace(argc, argv, prefix);
+        if (!strcmp(argv[0], "script"))
+                return cmd_script(argc, argv, prefix);
 
         symbol__init();
         if (!strncmp(argv[0], "rec", 3)) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
new file mode 100644
index 000000000000..22747de7234b
--- /dev/null
+++ b/tools/perf/builtin-script.c
@@ -0,0 +1,1230 @@
+#include "builtin.h"
+
+#include "perf.h"
+#include "util/cache.h"
+#include "util/debug.h"
+#include "util/exec_cmd.h"
+#include "util/header.h"
+#include "util/parse-options.h"
+#include "util/session.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+#include "util/trace-event.h"
+#include "util/util.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+
+static char const               *script_name;
+static char const               *generate_script_lang;
+static bool                     debug_mode;
+static u64                      last_timestamp;
+static u64                      nr_unordered;
+extern const struct option      record_options[];
+static bool                     no_callchain;
+
+enum perf_output_field {
+        PERF_OUTPUT_COMM            = 1U << 0,
+        PERF_OUTPUT_TID             = 1U << 1,
+        PERF_OUTPUT_PID             = 1U << 2,
+        PERF_OUTPUT_TIME            = 1U << 3,
+        PERF_OUTPUT_CPU             = 1U << 4,
+        PERF_OUTPUT_EVNAME          = 1U << 5,
+        PERF_OUTPUT_TRACE           = 1U << 6,
+        PERF_OUTPUT_SYM             = 1U << 7,
+};
+
+struct output_option {
+        const char *str;
+        enum perf_output_field field;
+} all_output_options[] = {
+        {.str = "comm",  .field = PERF_OUTPUT_COMM},
+        {.str = "tid",   .field = PERF_OUTPUT_TID},
+        {.str = "pid",   .field = PERF_OUTPUT_PID},
+        {.str = "time",  .field = PERF_OUTPUT_TIME},
+        {.str = "cpu",   .field = PERF_OUTPUT_CPU},
+        {.str = "event", .field = PERF_OUTPUT_EVNAME},
+        {.str = "trace", .field = PERF_OUTPUT_TRACE},
+        {.str = "sym",   .field = PERF_OUTPUT_SYM},
+};
+
+/* default set to maintain compatibility with current format */
+static struct {
+        bool user_set;
+        bool wildcard_set;
+        u64 fields;
+        u64 invalid_fields;
+} output[PERF_TYPE_MAX] = {
+
+        [PERF_TYPE_HARDWARE] = {
+                .user_set = false,
+
+                .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+                              PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+                              PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+                .invalid_fields = PERF_OUTPUT_TRACE,
+        },
+
+        [PERF_TYPE_SOFTWARE] = {
+                .user_set = false,
+
+                .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+                              PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+                              PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+                .invalid_fields = PERF_OUTPUT_TRACE,
+        },
+
+        [PERF_TYPE_TRACEPOINT] = {
+                .user_set = false,
+
+                .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+                                  PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+                                  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+        },
+
+        [PERF_TYPE_RAW] = {
+                .user_set = false,
+
+                .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+                              PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+                              PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+                .invalid_fields = PERF_OUTPUT_TRACE,
+        },
+};
+
+static bool output_set_by_user(void)
+{
+        int j;
+        for (j = 0; j < PERF_TYPE_MAX; ++j) {
+                if (output[j].user_set)
+                        return true;
+        }
+        return false;
+}
+
+static const char *output_field2str(enum perf_output_field field)
+{
+        int i, imax = ARRAY_SIZE(all_output_options);
+        const char *str = "";
+
+        for (i = 0; i < imax; ++i) {
+                if (all_output_options[i].field == field) {
+                        str = all_output_options[i].str;
+                        break;
+                }
+        }
+        return str;
+}
+
+#define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
+
+static int perf_event_attr__check_stype(struct perf_event_attr *attr,
+                                  u64 sample_type, const char *sample_msg,
+                                  enum perf_output_field field)
+{
+        int type = attr->type;
+        const char *evname;
+
+        if (attr->sample_type & sample_type)
+                return 0;
+
+        if (output[type].user_set) {
+                evname = __event_name(attr->type, attr->config);
+                pr_err("Samples for '%s' event do not have %s attribute set. "
+                       "Cannot print '%s' field.\n",
+                       evname, sample_msg, output_field2str(field));
+                return -1;
+        }
+
+        /* user did not ask for it explicitly so remove from the default list */
+        output[type].fields &= ~field;
+        evname = __event_name(attr->type, attr->config);
+        pr_debug("Samples for '%s' event do not have %s attribute set. "
+                 "Skipping '%s' field.\n",
+                 evname, sample_msg, output_field2str(field));
+
+        return 0;
+}
+
+static int perf_evsel__check_attr(struct perf_evsel *evsel,
+                                  struct perf_session *session)
+{
+        struct perf_event_attr *attr = &evsel->attr;
+
+        if (PRINT_FIELD(TRACE) &&
+                !perf_session__has_traces(session, "record -R"))
+                return -EINVAL;
+
+        if (PRINT_FIELD(SYM)) {
+                if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP",
+                                           PERF_OUTPUT_SYM))
+                        return -EINVAL;
+
+                if (!no_callchain &&
+                    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
+                        symbol_conf.use_callchain = false;
+        }
+
+        if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
+                perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID",
+                                       PERF_OUTPUT_TID|PERF_OUTPUT_PID))
+                return -EINVAL;
+
+        if (PRINT_FIELD(TIME) &&
+                perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME",
+                                       PERF_OUTPUT_TIME))
+                return -EINVAL;
+
+        if (PRINT_FIELD(CPU) &&
+                perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU",
+                                       PERF_OUTPUT_CPU))
+                return -EINVAL;
+
+        return 0;
+}
+
+/*
+ * verify all user requested events exist and the samples
+ * have the expected data
+ */
+static int perf_session__check_output_opt(struct perf_session *session)
+{
+        int j;
+        struct perf_evsel *evsel;
+
+        for (j = 0; j < PERF_TYPE_MAX; ++j) {
+                evsel = perf_session__find_first_evtype(session, j);
+
+                /*
+                 * even if fields is set to 0 (ie., show nothing) event must
+                 * exist if user explicitly includes it on the command line
+                 */
+                if (!evsel && output[j].user_set && !output[j].wildcard_set) {
+                        pr_err("%s events do not exist. "
+                               "Remove corresponding -f option to proceed.\n",
+                               event_type(j));
+                        return -1;
+                }
+
+                if (evsel && output[j].fields &&
+                        perf_evsel__check_attr(evsel, session))
+                        return -1;
+        }
+
+        return 0;
+}
+
+static void print_sample_start(struct perf_sample *sample,
+                               struct thread *thread,
+                               struct perf_event_attr *attr)
+{
+        int type;
+        struct event *event;
+        const char *evname = NULL;
+        unsigned long secs;
+        unsigned long usecs;
+        unsigned long long nsecs;
+
+        if (PRINT_FIELD(COMM)) {
+                if (latency_format)
+                        printf("%8.8s ", thread->comm);
+                else if (PRINT_FIELD(SYM) && symbol_conf.use_callchain)
+                        printf("%s ", thread->comm);
+                else
+                        printf("%16s ", thread->comm);
+        }
+
+        if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
+                printf("%5d/%-5d ", sample->pid, sample->tid);
+        else if (PRINT_FIELD(PID))
+                printf("%5d ", sample->pid);
+        else if (PRINT_FIELD(TID))
+                printf("%5d ", sample->tid);
+
+        if (PRINT_FIELD(CPU)) {
+                if (latency_format)
+                        printf("%3d ", sample->cpu);
+                else
+                        printf("[%03d] ", sample->cpu);
+        }
+
+        if (PRINT_FIELD(TIME)) {
+                nsecs = sample->time;
+                secs = nsecs / NSECS_PER_SEC;
+                nsecs -= secs * NSECS_PER_SEC;
+                usecs = nsecs / NSECS_PER_USEC;
+                printf("%5lu.%06lu: ", secs, usecs);
+        }
+
+        if (PRINT_FIELD(EVNAME)) {
+                if (attr->type == PERF_TYPE_TRACEPOINT) {
+                        type = trace_parse_common_type(sample->raw_data);
+                        event = trace_find_event(type);
+                        if (event)
+                                evname = event->name;
+                } else
+                        evname = __event_name(attr->type, attr->config);
+
+                printf("%s: ", evname ? evname : "(unknown)");
+        }
+}
+
+static void process_event(union perf_event *event __unused,
+                          struct perf_sample *sample,
+                          struct perf_evsel *evsel,
+                          struct perf_session *session,
+                          struct thread *thread)
+{
+        struct perf_event_attr *attr = &evsel->attr;
+
+        if (output[attr->type].fields == 0)
+                return;
+
+        print_sample_start(sample, thread, attr);
+
+        if (PRINT_FIELD(TRACE))
+                print_trace_event(sample->cpu, sample->raw_data,
+                                  sample->raw_size);
+
+        if (PRINT_FIELD(SYM)) {
+                if (!symbol_conf.use_callchain)
+                        printf(" ");
+                else
+                        printf("\n");
+                perf_session__print_symbols(event, sample, session);
+        }
+
+        printf("\n");
+}
+
+static int default_start_script(const char *script __unused,
+                                int argc __unused,
+                                const char **argv __unused)
+{
+        return 0;
+}
+
+static int default_stop_script(void)
+{
+        return 0;
+}
+
+static int default_generate_script(const char *outfile __unused)
+{
+        return 0;
+}
+
+static struct scripting_ops default_scripting_ops = {
+        .start_script           = default_start_script,
+        .stop_script            = default_stop_script,
+        .process_event          = process_event,
+        .generate_script        = default_generate_script,
+};
+
+static struct scripting_ops     *scripting_ops;
+
+static void setup_scripting(void)
+{
+        setup_perl_scripting();
+        setup_python_scripting();
+
+        scripting_ops = &default_scripting_ops;
+}
+
+static int cleanup_scripting(void)
+{
+        pr_debug("\nperf script stopped\n");
+
+        return scripting_ops->stop_script();
+}
+
+static char const               *input_name = "perf.data";
+
+static int process_sample_event(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel,
+                                struct perf_session *session)
+{
+        struct thread *thread = perf_session__findnew(session, event->ip.pid);
+
+        if (thread == NULL) {
+                pr_debug("problem processing %d event, skipping it.\n",
+                         event->header.type);
+                return -1;
+        }
+
+        if (debug_mode) {
+                if (sample->time < last_timestamp) {
+                        pr_err("Samples misordered, previous: %" PRIu64
+                                " this: %" PRIu64 "\n", last_timestamp,
+                                sample->time);
+                        nr_unordered++;
+                }
+                last_timestamp = sample->time;
+                return 0;
+        }
+        scripting_ops->process_event(event, sample, evsel, session, thread);
+
+        session->hists.stats.total_period += sample->period;
+        return 0;
+}
+
+static struct perf_event_ops event_ops = {
+        .sample          = process_sample_event,
+        .mmap            = perf_event__process_mmap,
+        .comm            = perf_event__process_comm,
+        .exit            = perf_event__process_task,
+        .fork            = perf_event__process_task,
+        .attr            = perf_event__process_attr,
+        .event_type      = perf_event__process_event_type,
+        .tracing_data    = perf_event__process_tracing_data,
+        .build_id        = perf_event__process_build_id,
+        .ordered_samples = true,
+        .ordering_requires_timestamps = true,
+};
+
+extern volatile int session_done;
+
+static void sig_handler(int sig __unused)
+{
+        session_done = 1;
+}
+
+static int __cmd_script(struct perf_session *session)
+{
+        int ret;
+
+        signal(SIGINT, sig_handler);
+
+        ret = perf_session__process_events(session, &event_ops);
+
+        if (debug_mode)
+                pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
+
+        return ret;
+}
+
+struct script_spec {
+        struct list_head        node;
+        struct scripting_ops    *ops;
+        char                    spec[0];
+};
+
+static LIST_HEAD(script_specs);
+
+static struct script_spec *script_spec__new(const char *spec,
+                                            struct scripting_ops *ops)
+{
+        struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1);
+
+        if (s != NULL) {
+                strcpy(s->spec, spec);
+                s->ops = ops;
+        }
+
+        return s;
+}
+
+static void script_spec__delete(struct script_spec *s)
+{
+        free(s->spec);
+        free(s);
+}
+
+static void script_spec__add(struct script_spec *s)
+{
+        list_add_tail(&s->node, &script_specs);
+}
+
+static struct script_spec *script_spec__find(const char *spec)
+{
+        struct script_spec *s;
+
+        list_for_each_entry(s, &script_specs, node)
+                if (strcasecmp(s->spec, spec) == 0)
+                        return s;
+        return NULL;
+}
+
+static struct script_spec *script_spec__findnew(const char *spec,
+                                                struct scripting_ops *ops)
+{
+        struct script_spec *s = script_spec__find(spec);
+
+        if (s)
+                return s;
+
+        s = script_spec__new(spec, ops);
+        if (!s)
+                goto out_delete_spec;
+
+        script_spec__add(s);
+
+        return s;
+
+out_delete_spec:
+        script_spec__delete(s);
+
+        return NULL;
+}
+
+int script_spec_register(const char *spec, struct scripting_ops *ops)
+{
+        struct script_spec *s;
+
+        s = script_spec__find(spec);
+        if (s)
+                return -1;
+
+        s = script_spec__findnew(spec, ops);
+        if (!s)
+                return -1;
+
+        return 0;
+}
+
+static struct scripting_ops *script_spec__lookup(const char *spec)
+{
+        struct script_spec *s = script_spec__find(spec);
+        if (!s)
+                return NULL;
+
+        return s->ops;
+}
+
+static void list_available_languages(void)
+{
+        struct script_spec *s;
+
+        fprintf(stderr, "\n");
+        fprintf(stderr, "Scripting language extensions (used in "
+                "perf script -s [spec:]script.[spec]):\n\n");
+
+        list_for_each_entry(s, &script_specs, node)
+                fprintf(stderr, "  %-42s [%s]\n", s->spec, s->ops->name);
+
+        fprintf(stderr, "\n");
+}
+
+static int parse_scriptname(const struct option *opt __used,
+                            const char *str, int unset __used)
+{
+        char spec[PATH_MAX];
+        const char *script, *ext;
+        int len;
+
+        if (strcmp(str, "lang") == 0) {
+                list_available_languages();
+                exit(0);
+        }
+
+        script = strchr(str, ':');
+        if (script) {
+                len = script - str;
+                if (len >= PATH_MAX) {
+                        fprintf(stderr, "invalid language specifier");
+                        return -1;
+                }
+                strncpy(spec, str, len);
+                spec[len] = '\0';
+                scripting_ops = script_spec__lookup(spec);
+                if (!scripting_ops) {
+                        fprintf(stderr, "invalid language specifier");
+                        return -1;
+                }
+                script++;
+        } else {
+                script = str;
+                ext = strrchr(script, '.');
+                if (!ext) {
+                        fprintf(stderr, "invalid script extension");
+                        return -1;
+                }
+                scripting_ops = script_spec__lookup(++ext);
+                if (!scripting_ops) {
+                        fprintf(stderr, "invalid script extension");
+                        return -1;
+                }
+        }
+
+        script_name = strdup(script);
+
+        return 0;
+}
+
+static int parse_output_fields(const struct option *opt __used,
+                            const char *arg, int unset __used)
+{
+        char *tok;
+        int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
+        int j;
+        int rc = 0;
+        char *str = strdup(arg);
+        int type = -1;
+
+        if (!str)
+                return -ENOMEM;
+
+        /* first word can state for which event type the user is specifying
+         * the fields. If no type exists, the specified fields apply to all
+         * event types found in the file minus the invalid fields for a type.
+         */
+        tok = strchr(str, ':');
+        if (tok) {
+                *tok = '\0';
+                tok++;
+                if (!strcmp(str, "hw"))
+                        type = PERF_TYPE_HARDWARE;
+                else if (!strcmp(str, "sw"))
+                        type = PERF_TYPE_SOFTWARE;
+                else if (!strcmp(str, "trace"))
+                        type = PERF_TYPE_TRACEPOINT;
+                else if (!strcmp(str, "raw"))
+                        type = PERF_TYPE_RAW;
+                else {
+                        fprintf(stderr, "Invalid event type in field string.\n");
+                        return -EINVAL;
+                }
+
+                if (output[type].user_set)
+                        pr_warning("Overriding previous field request for %s events.\n",
+                                   event_type(type));
+
+                output[type].fields = 0;
+                output[type].user_set = true;
+                output[type].wildcard_set = false;
+
+        } else {
+                tok = str;
+                if (strlen(str) == 0) {
+                        fprintf(stderr,
+                                "Cannot set fields to 'none' for all event types.\n");
+                        rc = -EINVAL;
+                        goto out;
+                }
+
+                if (output_set_by_user())
+                        pr_warning("Overriding previous field request for all events.\n");
+
+                for (j = 0; j < PERF_TYPE_MAX; ++j) {
+                        output[j].fields = 0;
+                        output[j].user_set = true;
+                        output[j].wildcard_set = true;
+                }
+        }
+
+        tok = strtok(tok, ",");
+        while (tok) {
+                for (i = 0; i < imax; ++i) {
+                        if (strcmp(tok, all_output_options[i].str) == 0)
+                                break;
+                }
+                if (i == imax) {
+                        fprintf(stderr, "Invalid field requested.\n");
+                        rc = -EINVAL;
+                        goto out;
+                }
+
+                if (type == -1) {
+                        /* add user option to all events types for
+                         * which it is valid
+                         */
+                        for (j = 0; j < PERF_TYPE_MAX; ++j) {
+                                if (output[j].invalid_fields & all_output_options[i].field) {
+                                        pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
+                                                   all_output_options[i].str, event_type(j));
+                                } else
+                                        output[j].fields |= all_output_options[i].field;
+                        }
+                } else {
+                        if (output[type].invalid_fields & all_output_options[i].field) {
+                                fprintf(stderr, "\'%s\' not valid for %s events.\n",
+                                         all_output_options[i].str, event_type(type));
+
+                                rc = -EINVAL;
+                                goto out;
+                        }
+                        output[type].fields |= all_output_options[i].field;
+                }
+
+                tok = strtok(NULL, ",");
+        }
+
+        if (type >= 0) {
+                if (output[type].fields == 0) {
+                        pr_debug("No fields requested for %s type. "
+                                 "Events will not be displayed.\n", event_type(type));
+                }
+        }
+
+out:
+        free(str);
+        return rc;
+}
+
+/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
+static int is_directory(const char *base_path, const struct dirent *dent)
+{
+        char path[PATH_MAX];
+        struct stat st;
+
+        sprintf(path, "%s/%s", base_path, dent->d_name);
+        if (stat(path, &st))
+                return 0;
+
+        return S_ISDIR(st.st_mode);
+}
+
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
+        while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&     \
+               lang_next)                                               \
+                if ((lang_dirent.d_type == DT_DIR ||                    \
+                     (lang_dirent.d_type == DT_UNKNOWN &&               \
+                      is_directory(scripts_path, &lang_dirent))) &&     \
+                    (strcmp(lang_dirent.d_name, ".")) &&                \
+                    (strcmp(lang_dirent.d_name, "..")))
+
+#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
+        while (!readdir_r(lang_dir, &script_dirent, &script_next) &&    \
+               script_next)                                             \
+                if (script_dirent.d_type != DT_DIR &&                   \
+                    (script_dirent.d_type != DT_UNKNOWN ||              \
+                     !is_directory(lang_path, &script_dirent)))
+
+
+#define RECORD_SUFFIX                   "-record"
+#define REPORT_SUFFIX                   "-report"
+
+struct script_desc {
+        struct list_head        node;
+        char                    *name;
+        char                    *half_liner;
+        char                    *args;
+};
+
+static LIST_HEAD(script_descs);
+
+static struct script_desc *script_desc__new(const char *name)
+{
+        struct script_desc *s = zalloc(sizeof(*s));
+
+        if (s != NULL && name)
+                s->name = strdup(name);
+
+        return s;
+}
+
+static void script_desc__delete(struct script_desc *s)
+{
+        free(s->name);
+        free(s->half_liner);
+        free(s->args);
+        free(s);
+}
+
+static void script_desc__add(struct script_desc *s)
+{
+        list_add_tail(&s->node, &script_descs);
+}
+
+static struct script_desc *script_desc__find(const char *name)
+{
+        struct script_desc *s;
+
+        list_for_each_entry(s, &script_descs, node)
+                if (strcasecmp(s->name, name) == 0)
+                        return s;
+        return NULL;
+}
+
+static struct script_desc *script_desc__findnew(const char *name)
+{
+        struct script_desc *s = script_desc__find(name);
+
+        if (s)
+                return s;
+
+        s = script_desc__new(name);
+        if (!s)
+                goto out_delete_desc;
+
+        script_desc__add(s);
+
+        return s;
+
+out_delete_desc:
+        script_desc__delete(s);
+
+        return NULL;
+}
+
+static const char *ends_with(const char *str, const char *suffix)
+{
+        size_t suffix_len = strlen(suffix);
+        const char *p = str;
+
+        if (strlen(str) > suffix_len) {
+                p = str + strlen(str) - suffix_len;
+                if (!strncmp(p, suffix, suffix_len))
+                        return p;
+        }
+
+        return NULL;
+}
+
+static char *ltrim(char *str)
+{
+        int len = strlen(str);
+
+        while (len && isspace(*str)) {
+                len--;
+                str++;
+        }
+
+        return str;
+}
+
+static int read_script_info(struct script_desc *desc, const char *filename)
+{
+        char line[BUFSIZ], *p;
+        FILE *fp;
+
+        fp = fopen(filename, "r");
+        if (!fp)
+                return -1;
+
+        while (fgets(line, sizeof(line), fp)) {
+                p = ltrim(line);
+                if (strlen(p) == 0)
+                        continue;
+                if (*p != '#')
+                        continue;
+                p++;
+                if (strlen(p) && *p == '!')
+                        continue;
+
+                p = ltrim(p);
+                if (strlen(p) && p[strlen(p) - 1] == '\n')
+                        p[strlen(p) - 1] = '\0';
+
+                if (!strncmp(p, "description:", strlen("description:"))) {
+                        p += strlen("description:");
+                        desc->half_liner = strdup(ltrim(p));
+                        continue;
+                }
+
+                if (!strncmp(p, "args:", strlen("args:"))) {
+                        p += strlen("args:");
+                        desc->args = strdup(ltrim(p));
+                        continue;
+                }
+        }
+
+        fclose(fp);
+
+        return 0;
+}
+
+static int list_available_scripts(const struct option *opt __used,
+                                  const char *s __used, int unset __used)
+{
+        struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+        char scripts_path[MAXPATHLEN];
+        DIR *scripts_dir, *lang_dir;
+        char script_path[MAXPATHLEN];
+        char lang_path[MAXPATHLEN];
+        struct script_desc *desc;
+        char first_half[BUFSIZ];
+        char *script_root;
+        char *str;
+
+        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+
+        scripts_dir = opendir(scripts_path);
+        if (!scripts_dir)
+                return -1;
+
+        for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+                snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
+                         lang_dirent.d_name);
+                lang_dir = opendir(lang_path);
+                if (!lang_dir)
+                        continue;
+
+                for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+                        script_root = strdup(script_dirent.d_name);
+                        str = (char *)ends_with(script_root, REPORT_SUFFIX);
+                        if (str) {
+                                *str = '\0';
+                                desc = script_desc__findnew(script_root);
+                                snprintf(script_path, MAXPATHLEN, "%s/%s",
+                                         lang_path, script_dirent.d_name);
+                                read_script_info(desc, script_path);
+                        }
+                        free(script_root);
+                }
+        }
+
+        fprintf(stdout, "List of available trace scripts:\n");
+        list_for_each_entry(desc, &script_descs, node) {
+                sprintf(first_half, "%s %s", desc->name,
+                        desc->args ? desc->args : "");
+                fprintf(stdout, "  %-36s %s\n", first_half,
+                        desc->half_liner ? desc->half_liner : "");
+        }
+
+        exit(0);
+}
+
+static char *get_script_path(const char *script_root, const char *suffix)
+{
+        struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+        char scripts_path[MAXPATHLEN];
+        char script_path[MAXPATHLEN];
+        DIR *scripts_dir, *lang_dir;
+        char lang_path[MAXPATHLEN];
+        char *str, *__script_root;
+        char *path = NULL;
+
+        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
+
+        scripts_dir = opendir(scripts_path);
+        if (!scripts_dir)
+                return NULL;
+
+        for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+                snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
+                         lang_dirent.d_name);
+                lang_dir = opendir(lang_path);
+                if (!lang_dir)
+                        continue;
+
+                for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+                        __script_root = strdup(script_dirent.d_name);
+                        str = (char *)ends_with(__script_root, suffix);
+                        if (str) {
+                                *str = '\0';
+                                if (strcmp(__script_root, script_root))
+                                        continue;
+                                snprintf(script_path, MAXPATHLEN, "%s/%s",
+                                         lang_path, script_dirent.d_name);
+                                path = strdup(script_path);
+                                free(__script_root);
+                                break;
+                        }
+                        free(__script_root);
+                }
+        }
+
+        return path;
+}
+
+static bool is_top_script(const char *script_path)
+{
+        return ends_with(script_path, "top") == NULL ? false : true;
+}
+
+static int has_required_arg(char *script_path)
+{
+        struct script_desc *desc;
+        int n_args = 0;
+        char *p;
+
+        desc = script_desc__new(NULL);
+
+        if (read_script_info(desc, script_path))
+                goto out;
+
+        if (!desc->args)
+                goto out;
+
+        for (p = desc->args; *p; p++)
+                if (*p == '<')
+                        n_args++;
+out:
+        script_desc__delete(desc);
+
+        return n_args;
+}
+
+static const char * const script_usage[] = {
+        "perf script [<options>]",
+        "perf script [<options>] record <script> [<record-options>] <command>",
+        "perf script [<options>] report <script> [script-args]",
+        "perf script [<options>] <script> [<record-options>] <command>",
+        "perf script [<options>] <top-script> [script-args]",
+        NULL
+};
+
+static const struct option options[] = {
+        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
+                    "dump raw trace in ASCII"),
+        OPT_INCR('v', "verbose", &verbose,
+                    "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('L', "Latency", &latency_format,
+                    "show latency attributes (irqs/preemption disabled, etc)"),
+        OPT_CALLBACK_NOOPT('l', "list", NULL, NULL, "list available scripts",
+                           list_available_scripts),
+        OPT_CALLBACK('s', "script", NULL, "name",
+                     "script file name (lang:script name, script name, or *)",
+                     parse_scriptname),
+        OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
+                   "generate perf-script.xx script in specified language"),
+        OPT_STRING('i', "input", &input_name, "file",
+                    "input file name"),
+        OPT_BOOLEAN('d', "debug-mode", &debug_mode,
+                   "do various checks like samples ordering and lost events"),
+        OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+                   "file", "vmlinux pathname"),
+        OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+                   "file", "kallsyms pathname"),
+        OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
+                    "When printing symbols do not display call chain"),
+        OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+                    "Look for files with symbols relative to this directory"),
+        OPT_CALLBACK('f', "fields", NULL, "str",
+                     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,sym",
+                     parse_output_fields),
+
+        OPT_END()
+};
+
+static bool have_cmd(int argc, const char **argv)
+{
+        char **__argv = malloc(sizeof(const char *) * argc);
+
+        if (!__argv)
+                die("malloc");
+        memcpy(__argv, argv, sizeof(const char *) * argc);
+        argc = parse_options(argc, (const char **)__argv, record_options,
+                             NULL, PARSE_OPT_STOP_AT_NON_OPTION);
+        free(__argv);
+
+        return argc != 0;
+}
+
+int cmd_script(int argc, const char **argv, const char *prefix __used)
+{
+        char *rec_script_path = NULL;
+        char *rep_script_path = NULL;
+        struct perf_session *session;
+        char *script_path = NULL;
+        const char **__argv;
+        bool system_wide;
+        int i, j, err;
+
+        setup_scripting();
+
+        argc = parse_options(argc, argv, options, script_usage,
+                             PARSE_OPT_STOP_AT_NON_OPTION);
+
+        if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
+                rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+                if (!rec_script_path)
+                        return cmd_record(argc, argv, NULL);
+        }
+
+        if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
+                rep_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+                if (!rep_script_path) {
+                        fprintf(stderr,
+                                "Please specify a valid report script"
+                                "(see 'perf script -l' for listing)\n");
+                        return -1;
+                }
+        }
+
+        /* make sure PERF_EXEC_PATH is set for scripts */
+        perf_set_argv_exec_path(perf_exec_path());
+
+        if (argc && !script_name && !rec_script_path && !rep_script_path) {
+                int live_pipe[2];
+                int rep_args;
+                pid_t pid;
+
+                rec_script_path = get_script_path(argv[0], RECORD_SUFFIX);
+                rep_script_path = get_script_path(argv[0], REPORT_SUFFIX);
+
+                if (!rec_script_path && !rep_script_path) {
+                        fprintf(stderr, " Couldn't find script %s\n\n See perf"
+                                " script -l for available scripts.\n", argv[0]);
+                        usage_with_options(script_usage, options);
+                }
+
+                if (is_top_script(argv[0])) {
+                        rep_args = argc - 1;
+                } else {
+                        int rec_args;
+
+                        rep_args = has_required_arg(rep_script_path);
+                        rec_args = (argc - 1) - rep_args;
+                        if (rec_args < 0) {
+                                fprintf(stderr, " %s script requires options."
+                                        "\n\n See perf script -l for available "
+                                        "scripts and options.\n", argv[0]);
+                                usage_with_options(script_usage, options);
+                        }
+                }
+
+                if (pipe(live_pipe) < 0) {
+                        perror("failed to create pipe");
+                        exit(-1);
+                }
+
+                pid = fork();
+                if (pid < 0) {
+                        perror("failed to fork");
+                        exit(-1);
+                }
+
+                if (!pid) {
+                        system_wide = true;
+                        j = 0;
+
+                        dup2(live_pipe[1], 1);
+                        close(live_pipe[0]);
+
+                        if (!is_top_script(argv[0]))
+                                system_wide = !have_cmd(argc - rep_args,
+                                                        &argv[rep_args]);
+
+                        __argv = malloc((argc + 6) * sizeof(const char *));
+                        if (!__argv)
+                                die("malloc");
+
+                        __argv[j++] = "/bin/sh";
+                        __argv[j++] = rec_script_path;
+                        if (system_wide)
+                                __argv[j++] = "-a";
+                        __argv[j++] = "-q";
+                        __argv[j++] = "-o";
+                        __argv[j++] = "-";
+                        for (i = rep_args + 1; i < argc; i++)
+                                __argv[j++] = argv[i];
+                        __argv[j++] = NULL;
+
+                        execvp("/bin/sh", (char **)__argv);
+                        free(__argv);
+                        exit(-1);
+                }
+
+                dup2(live_pipe[0], 0);
+                close(live_pipe[1]);
+
+                __argv = malloc((argc + 4) * sizeof(const char *));
+                if (!__argv)
+                        die("malloc");
+                j = 0;
+                __argv[j++] = "/bin/sh";
+                __argv[j++] = rep_script_path;
+                for (i = 1; i < rep_args + 1; i++)
+                        __argv[j++] = argv[i];
+                __argv[j++] = "-i";
+                __argv[j++] = "-";
+                __argv[j++] = NULL;
+
+                execvp("/bin/sh", (char **)__argv);
+                free(__argv);
+                exit(-1);
+        }
+
+        if (rec_script_path)
+                script_path = rec_script_path;
+        if (rep_script_path)
+                script_path = rep_script_path;
+
+        if (script_path) {
+                system_wide = false;
+                j = 0;
+
+                if (rec_script_path)
+                        system_wide = !have_cmd(argc - 1, &argv[1]);
+
+                __argv = malloc((argc + 2) * sizeof(const char *));
+                if (!__argv)
+                        die("malloc");
+                __argv[j++] = "/bin/sh";
+                __argv[j++] = script_path;
+                if (system_wide)
+                        __argv[j++] = "-a";
+                for (i = 2; i < argc; i++)
+                        __argv[j++] = argv[i];
+                __argv[j++] = NULL;
+
+                execvp("/bin/sh", (char **)__argv);
+                free(__argv);
+                exit(-1);
+        }
+
+        if (symbol__init() < 0)
+                return -1;
+        if (!script_name)
+                setup_pager();
+
+        session = perf_session__new(input_name, O_RDONLY, 0, false, &event_ops);
+        if (session == NULL)
+                return -ENOMEM;
+
+        if (!no_callchain)
+                symbol_conf.use_callchain = true;
+        else
+                symbol_conf.use_callchain = false;
+
+        if (generate_script_lang) {
+                struct stat perf_stat;
+                int input;
+
+                if (output_set_by_user()) {
+                        fprintf(stderr,
+                                "custom fields not supported for generated scripts");
+                        return -1;
+                }
+
+                input = open(input_name, O_RDONLY);
+                if (input < 0) {
+                        perror("failed to open file");
+                        exit(-1);
+                }
+
+                err = fstat(input, &perf_stat);
+                if (err < 0) {
+                        perror("failed to stat file");
+                        exit(-1);
+                }
+
+                if (!perf_stat.st_size) {
+                        fprintf(stderr, "zero-sized file, nothing to do!\n");
+                        exit(0);
+                }
+
+                scripting_ops = script_spec__lookup(generate_script_lang);
+                if (!scripting_ops) {
+                        fprintf(stderr, "invalid language specifier");
+                        return -1;
+                }
+
+                err = scripting_ops->generate_script("perf-script");
+                goto out;
+        }
+
+        if (script_name) {
+                err = scripting_ops->start_script(script_name, argc, argv);
+                if (err)
+                        goto out;
+                pr_debug("perf script started with script %s\n\n", script_name);
+        }
+
+
+        err = perf_session__check_output_opt(session);
+        if (err < 0)
+                goto out;
+
+        err = __cmd_script(session);
+
+        perf_session__delete(session);
+        cleanup_scripting();
+out:
+        return err;
+}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a6b4d44f9502..a9f06715e44d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -6,24 +6,28 @@
  *
  * Sample output:
 
-   $ perf stat ~/hackbench 10
-   Time: 0.104
+   $ perf stat ./hackbench 10
 
-    Performance counter stats for '/home/mingo/hackbench':
+  Time: 0.118
 
-       1255.538611  task clock ticks     #      10.143 CPU utilization factor
-             54011  context switches     #       0.043 M/sec
-               385  CPU migrations       #       0.000 M/sec
-             17755  pagefaults           #       0.014 M/sec
-        3808323185  CPU cycles           #    3033.219 M/sec
-        1575111190  instructions         #    1254.530 M/sec
-          17367895  cache references     #      13.833 M/sec
-           7674421  cache misses         #       6.112 M/sec
+  Performance counter stats for './hackbench 10':
 
-    Wall-clock time elapsed:   123.786620 msecs
+       1708.761321 task-clock                #   11.037 CPUs utilized
+            41,190 context-switches          #    0.024 M/sec
+             6,735 CPU-migrations            #    0.004 M/sec
+            17,318 page-faults               #    0.010 M/sec
+     5,205,202,243 cycles                    #    3.046 GHz
+     3,856,436,920 stalled-cycles-frontend   #   74.09% frontend cycles idle
+     1,600,790,871 stalled-cycles-backend    #   30.75% backend  cycles idle
+     2,603,501,247 instructions              #    0.50  insns per cycle
+                                             #    1.48  stalled cycles per insn
+       484,357,498 branches                  #  283.455 M/sec
+         6,388,934 branch-misses             #    1.32% of all branches
+
+        0.154822978  seconds time elapsed
 
  *
- * Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
  *
  * Improvements and fixes by:
  *
@@ -43,15 +47,21 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/event.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/debug.h"
+#include "util/color.h"
 #include "util/header.h"
 #include "util/cpumap.h"
 #include "util/thread.h"
+#include "util/thread_map.h"
 
 #include <sys/prctl.h>
 #include <math.h>
 #include <locale.h>
 
+#define DEFAULT_SEPARATOR       " "
+
 static struct perf_event_attr default_attrs[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK              },
@@ -60,34 +70,127 @@ static struct perf_event_attr default_attrs[] = {
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS             },
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES              },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND  },
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS            },
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS     },
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES           },
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES        },
-  { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES            },
 
 };
 
+/*
+ * Detailed stats (-d), covering the L1 and last level data caches:
+ */
+static struct perf_event_attr detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_L1D                <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_L1D                <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_LL                 <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_LL                 <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)                          },
+};
+
+/*
+ * Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
+ */
+static struct perf_event_attr very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_L1I                <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_L1I                <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)                          },
+
+};
+
+/*
+ * Very, very detailed stats (-d -d -d), adding prefetch events:
+ */
+static struct perf_event_attr very_very_detailed_attrs[] = {
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_L1D                <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)                          },
+
+  { .type = PERF_TYPE_HW_CACHE,
+    .config =
+         PERF_COUNT_HW_CACHE_L1D                <<  0  |
+        (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+        (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)                          },
+};
+
+
+
+struct perf_evlist              *evsel_list;
+
 static bool                     system_wide                     =  false;
-static int                      nr_cpus                         =  0;
 static int                      run_idx                         =  0;
 
 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 pid_t                    *all_tids                       =  NULL;
-static int                      thread_num                      =  0;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
-static bool                     big_num                         =  false;
+static int                      detailed_run                    =  0;
+static bool                     sync_run                        =  false;
+static bool                     big_num                         =  true;
+static int                      big_num_opt                     =  -1;
 static const char               *cpu_list;
-
-
-static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
-
-static int                      event_scaled[MAX_COUNTERS];
+static const char               *csv_sep                        = NULL;
+static bool                     csv_output                      = false;
 
 static volatile int done = 0;
 
@@ -96,6 +199,22 @@ struct stats
         double n, mean, M2;
 };
 
+struct perf_stat {
+        struct stats      res_stats[3];
+};
+
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+{
+        evsel->priv = zalloc(sizeof(struct perf_stat));
+        return evsel->priv == NULL ? -ENOMEM : 0;
+}
+
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+        free(evsel->priv);
+        evsel->priv = NULL;
+}
+
 static void update_stats(struct stats *stats, u64 val)
 {
         double delta;
@@ -135,154 +254,143 @@ static double stddev_stats(struct stats *stats)
         return sqrt(variance_mean);
 }
 
-struct stats                    event_res_stats[MAX_COUNTERS][3];
-struct stats                    runtime_nsecs_stats;
+struct stats                    runtime_nsecs_stats[MAX_NR_CPUS];
+struct stats                    runtime_cycles_stats[MAX_NR_CPUS];
+struct stats                    runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
+struct stats                    runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
+struct stats                    runtime_branches_stats[MAX_NR_CPUS];
+struct stats                    runtime_cacherefs_stats[MAX_NR_CPUS];
+struct stats                    runtime_l1_dcache_stats[MAX_NR_CPUS];
+struct stats                    runtime_l1_icache_stats[MAX_NR_CPUS];
+struct stats                    runtime_ll_cache_stats[MAX_NR_CPUS];
+struct stats                    runtime_itlb_cache_stats[MAX_NR_CPUS];
+struct stats                    runtime_dtlb_cache_stats[MAX_NR_CPUS];
 struct stats                    walltime_nsecs_stats;
-struct stats                    runtime_cycles_stats;
-struct stats                    runtime_branches_stats;
-
-#define MATCH_EVENT(t, c, counter)                      \
-        (attrs[counter].type == PERF_TYPE_##t &&        \
-         attrs[counter].config == PERF_COUNT_##c)
 
-#define ERR_PERF_OPEN \
-"Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
-
-static int create_perf_stat_counter(int counter)
+static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
-        struct perf_event_attr *attr = attrs + counter;
-        int thread;
-        int ncreated = 0;
+        struct perf_event_attr *attr = &evsel->attr;
 
         if (scale)
                 attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                     PERF_FORMAT_TOTAL_TIME_RUNNING;
 
-        if (system_wide) {
-                int cpu;
-
-                for (cpu = 0; cpu < nr_cpus; cpu++) {
-                        fd[cpu][counter][0] = sys_perf_event_open(attr,
-                                        -1, cpumap[cpu], -1, 0);
-                        if (fd[cpu][counter][0] < 0)
-                                pr_debug(ERR_PERF_OPEN, counter,
-                                         fd[cpu][counter][0], strerror(errno));
-                        else
-                                ++ncreated;
-                }
-        } else {
-                attr->inherit = !no_inherit;
-                if (target_pid == -1 && target_tid == -1) {
-                        attr->disabled = 1;
-                        attr->enable_on_exec = 1;
-                }
-                for (thread = 0; thread < thread_num; thread++) {
-                        fd[0][counter][thread] = sys_perf_event_open(attr,
-                                all_tids[thread], -1, -1, 0);
-                        if (fd[0][counter][thread] < 0)
-                                pr_debug(ERR_PERF_OPEN, counter,
-                                         fd[0][counter][thread],
-                                         strerror(errno));
-                        else
-                                ++ncreated;
-                }
+        attr->inherit = !no_inherit;
+
+        if (system_wide)
+                return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
+
+        if (target_pid == -1 && target_tid == -1) {
+                attr->disabled = 1;
+                attr->enable_on_exec = 1;
         }
 
-        return ncreated;
+        return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
 }
 
 /*
  * Does the counter have nsecs as a unit?
  */
-static inline int nsec_counter(int counter)
+static inline int nsec_counter(struct perf_evsel *evsel)
 {
-        if (MATCH_EVENT(SOFTWARE, SW_CPU_CLOCK, counter) ||
-            MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
+        if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+            perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
                 return 1;
 
         return 0;
 }
 
 /*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
+{
+        if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+                update_stats(&runtime_nsecs_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+                update_stats(&runtime_cycles_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+                update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+                update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+                update_stats(&runtime_branches_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+                update_stats(&runtime_cacherefs_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+                update_stats(&runtime_l1_dcache_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+                update_stats(&runtime_l1_icache_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+                update_stats(&runtime_ll_cache_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+                update_stats(&runtime_dtlb_cache_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+                update_stats(&runtime_itlb_cache_stats[0], count[0]);
+}
+
+/*
  * Read out the results of a single counter:
+ * aggregate counts across CPUs in system-wide mode
  */
-static void read_counter(int counter)
+static int read_counter_aggr(struct perf_evsel *counter)
 {
-        u64 count[3], single_count[3];
-        int cpu;
-        size_t res, nv;
-        int scaled;
-        int i, thread;
+        struct perf_stat *ps = counter->priv;
+        u64 *count = counter->counts->aggr.values;
+        int i;
 
-        count[0] = count[1] = count[2] = 0;
+        if (__perf_evsel__read(counter, evsel_list->cpus->nr,
+                               evsel_list->threads->nr, scale) < 0)
+                return -1;
 
-        nv = scale ? 3 : 1;
-        for (cpu = 0; cpu < nr_cpus; cpu++) {
-                for (thread = 0; thread < thread_num; thread++) {
-                        if (fd[cpu][counter][thread] < 0)
-                                continue;
+        for (i = 0; i < 3; i++)
+                update_stats(&ps->res_stats[i], count[i]);
 
-                        res = read(fd[cpu][counter][thread],
-                                        single_count, nv * sizeof(u64));
-                        assert(res == nv * sizeof(u64));
+        if (verbose) {
+                fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+                        event_name(counter), count[0], count[1], count[2]);
+        }
 
-                        close(fd[cpu][counter][thread]);
-                        fd[cpu][counter][thread] = -1;
+        /*
+         * Save the full runtime - to allow normalization during printout:
+         */
+        update_shadow_stats(counter, count);
 
-                        count[0] += single_count[0];
-                        if (scale) {
-                                count[1] += single_count[1];
-                                count[2] += single_count[2];
-                        }
-                }
-        }
+        return 0;
+}
 
-        scaled = 0;
-        if (scale) {
-                if (count[2] == 0) {
-                        event_scaled[counter] = -1;
-                        count[0] = 0;
-                        return;
-                }
+/*
+ * Read out the results of a single counter:
+ * do not aggregate counts across CPUs in system-wide mode
+ */
+static int read_counter(struct perf_evsel *counter)
+{
+        u64 *count;
+        int cpu;
 
-                if (count[2] < count[1]) {
-                        event_scaled[counter] = 1;
-                        count[0] = (unsigned long long)
-                                ((double)count[0] * count[1] / count[2] + 0.5);
-                }
-        }
+        for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
+                if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
+                        return -1;
 
-        for (i = 0; i < 3; i++)
-                update_stats(&event_res_stats[counter][i], count[i]);
+                count = counter->counts->cpu[cpu].values;
 
-        if (verbose) {
-                fprintf(stderr, "%s: %Ld %Ld %Ld\n", event_name(counter),
-                                count[0], count[1], count[2]);
+                update_shadow_stats(counter, count);
         }
 
-        /*
-         * Save the full runtime - to allow normalization during printout:
-         */
-        if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
-                update_stats(&runtime_nsecs_stats, count[0]);
-        if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter))
-                update_stats(&runtime_cycles_stats, count[0]);
-        if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter))
-                update_stats(&runtime_branches_stats, count[0]);
+        return 0;
 }
 
 static int run_perf_stat(int argc __used, const char **argv)
 {
         unsigned long long t0, t1;
+        struct perf_evsel *counter;
         int status = 0;
-        int counter, ncreated = 0;
         int child_ready_pipe[2], go_pipe[2];
         const bool forks = (argc > 0);
         char buf;
 
-        if (!system_wide)
-                nr_cpus = 1;
-
         if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
                 perror("failed to create pipes");
                 exit(1);
@@ -322,7 +430,7 @@ static int run_perf_stat(int argc __used, const char **argv)
                 }
 
                 if (target_tid == -1 && target_pid == -1 && !system_wide)
-                        all_tids[0] = child_pid;
+                        evsel_list->threads->map[0] = child_pid;
 
                 /*
                  * Wait for the child to be ready to exec.
@@ -334,15 +442,35 @@ static int run_perf_stat(int argc __used, const char **argv)
                 close(child_ready_pipe[0]);
         }
 
-        for (counter = 0; counter < nr_counters; counter++)
-                ncreated += create_perf_stat_counter(counter);
+        list_for_each_entry(counter, &evsel_list->entries, node) {
+                if (create_perf_stat_counter(counter) < 0) {
+                        if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
+                                if (verbose)
+                                        ui__warning("%s event is not supported by the kernel.\n",
+                                                    event_name(counter));
+                                continue;
+                        }
+
+                        if (errno == EPERM || errno == EACCES) {
+                                error("You may not have permission to collect %sstats.\n"
+                                      "\t Consider tweaking"
+                                      " /proc/sys/kernel/perf_event_paranoid or running as root.",
+                                      system_wide ? "system-wide " : "");
+                        } else {
+                                error("open_counter returned with %d (%s). "
+                                      "/bin/dmesg may provide additional information.\n",
+                                       errno, strerror(errno));
+                        }
+                        if (child_pid != -1)
+                                kill(child_pid, SIGTERM);
+                        die("Not all events could be opened.\n");
+                        return -1;
+                }
+        }
 
-        if (ncreated == 0) {
-                pr_err("No permission to collect %sstats.\n"
-                       "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
-                       system_wide ? "system-wide " : "");
-                if (child_pid != -1)
-                        kill(child_pid, SIGTERM);
+        if (perf_evlist__set_filters(evsel_list)) {
+                error("failed to set filter with %d (%s)\n", errno,
+                        strerror(errno));
                 return -1;
         }
 
@@ -362,136 +490,501 @@ static int run_perf_stat(int argc __used, const char **argv)
 
         update_stats(&walltime_nsecs_stats, t1 - t0);
 
-        for (counter = 0; counter < nr_counters; counter++)
-                read_counter(counter);
+        if (no_aggr) {
+                list_for_each_entry(counter, &evsel_list->entries, node) {
+                        read_counter(counter);
+                        perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1);
+                }
+        } else {
+                list_for_each_entry(counter, &evsel_list->entries, node) {
+                        read_counter_aggr(counter);
+                        perf_evsel__close_fd(counter, evsel_list->cpus->nr,
+                                             evsel_list->threads->nr);
+                }
+        }
 
         return WEXITSTATUS(status);
 }
 
-static void print_noise(int counter, double avg)
+static void print_noise_pct(double total, double avg)
+{
+        double pct = 0.0;
+
+        if (avg)
+                pct = 100.0*total/avg;
+
+        fprintf(stderr, "  ( +-%6.2f%% )", pct);
+}
+
+static void print_noise(struct perf_evsel *evsel, double avg)
 {
+        struct perf_stat *ps;
+
         if (run_count == 1)
                 return;
 
-        fprintf(stderr, "   ( +- %7.3f%% )",
-                        100 * stddev_stats(&event_res_stats[counter][0]) / avg);
+        ps = evsel->priv;
+        print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void nsec_printout(int counter, double avg)
+static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
         double msecs = avg / 1e6;
+        char cpustr[16] = { '\0', };
+        const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
 
-        fprintf(stderr, " %18.6f  %-24s", msecs, event_name(counter));
+        if (no_aggr)
+                sprintf(cpustr, "CPU%*d%s",
+                        csv_output ? 0 : -4,
+                        evsel_list->cpus->map[cpu], csv_sep);
 
-        if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) {
-                fprintf(stderr, " # %10.3f CPUs ",
-                                avg / avg_stats(&walltime_nsecs_stats));
-        }
+        fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel));
+
+        if (evsel->cgrp)
+                fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+
+        if (csv_output)
+                return;
+
+        if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
+                fprintf(stderr, " # %8.3f CPUs utilized          ", avg / avg_stats(&walltime_nsecs_stats));
+}
+
+static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_cycles_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 50.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 30.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_cycles_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 75.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 50.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 20.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_branches_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " of all L1-dcache hits  ");
 }
 
-static void abs_printout(int counter, double avg)
+static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
 {
         double total, ratio = 0.0;
+        const char *color;
 
-        if (big_num)
-                fprintf(stderr, " %'18.0f  %-24s", avg, event_name(counter));
+        total = avg_stats(&runtime_l1_icache_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_itlb_cache_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_ll_cache_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #  ");
+        color_fprintf(stderr, color, "%6.2f%%", ratio);
+        fprintf(stderr, " of all LL-cache hits   ");
+}
+
+static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
+{
+        double total, ratio = 0.0;
+        char cpustr[16] = { '\0', };
+        const char *fmt;
+
+        if (csv_output)
+                fmt = "%s%.0f%s%s";
+        else if (big_num)
+                fmt = "%s%'18.0f%s%-25s";
         else
-                fprintf(stderr, " %18.0f  %-24s", avg, event_name(counter));
+                fmt = "%s%18.0f%s%-25s";
 
-        if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
-                total = avg_stats(&runtime_cycles_stats);
+        if (no_aggr)
+                sprintf(cpustr, "CPU%*d%s",
+                        csv_output ? 0 : -4,
+                        evsel_list->cpus->map[cpu], csv_sep);
+        else
+                cpu = 0;
+
+        fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel));
+
+        if (evsel->cgrp)
+                fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
+
+        if (csv_output)
+                return;
+
+        if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+                total = avg_stats(&runtime_cycles_stats[cpu]);
 
                 if (total)
                         ratio = avg / total;
 
-                fprintf(stderr, " # %10.3f IPC  ", ratio);
-        } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) &&
-                        runtime_branches_stats.n != 0) {
-                total = avg_stats(&runtime_branches_stats);
+                fprintf(stderr, " #   %5.2f  insns per cycle        ", ratio);
+
+                total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
+                total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
+
+                if (total && avg) {
+                        ratio = total / avg;
+                        fprintf(stderr, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+                }
+
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+                        runtime_branches_stats[cpu].n != 0) {
+                print_branch_misses(cpu, evsel, avg);
+        } else if (
+                evsel->attr.type == PERF_TYPE_HW_CACHE &&
+                evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+                                        ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+                        runtime_l1_dcache_stats[cpu].n != 0) {
+                print_l1_dcache_misses(cpu, evsel, avg);
+        } else if (
+                evsel->attr.type == PERF_TYPE_HW_CACHE &&
+                evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+                                        ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+                        runtime_l1_icache_stats[cpu].n != 0) {
+                print_l1_icache_misses(cpu, evsel, avg);
+        } else if (
+                evsel->attr.type == PERF_TYPE_HW_CACHE &&
+                evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+                                        ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+                        runtime_dtlb_cache_stats[cpu].n != 0) {
+                print_dtlb_cache_misses(cpu, evsel, avg);
+        } else if (
+                evsel->attr.type == PERF_TYPE_HW_CACHE &&
+                evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+                                        ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+                        runtime_itlb_cache_stats[cpu].n != 0) {
+                print_itlb_cache_misses(cpu, evsel, avg);
+        } else if (
+                evsel->attr.type == PERF_TYPE_HW_CACHE &&
+                evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+                                        ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+                        runtime_ll_cache_stats[cpu].n != 0) {
+                print_ll_cache_misses(cpu, evsel, avg);
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+                        runtime_cacherefs_stats[cpu].n != 0) {
+                total = avg_stats(&runtime_cacherefs_stats[cpu]);
 
                 if (total)
                         ratio = avg * 100 / total;
 
-                fprintf(stderr, " # %10.3f %%    ", ratio);
+                fprintf(stderr, " # %8.3f %% of all cache refs    ", ratio);
+
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+                print_stalled_cycles_frontend(cpu, evsel, avg);
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+                print_stalled_cycles_backend(cpu, evsel, avg);
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+                total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+                if (total)
+                        ratio = 1.0 * avg / total;
 
-        } else if (runtime_nsecs_stats.n != 0) {
-                total = avg_stats(&runtime_nsecs_stats);
+                fprintf(stderr, " # %8.3f GHz                    ", ratio);
+        } else if (runtime_nsecs_stats[cpu].n != 0) {
+                total = avg_stats(&runtime_nsecs_stats[cpu]);
 
                 if (total)
                         ratio = 1000.0 * avg / total;
 
-                fprintf(stderr, " # %10.3f M/sec", ratio);
+                fprintf(stderr, " # %8.3f M/sec                  ", ratio);
+        } else {
+                fprintf(stderr, "                                   ");
         }
 }
 
 /*
  * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
  */
-static void print_counter(int counter)
+static void print_counter_aggr(struct perf_evsel *counter)
 {
-        double avg = avg_stats(&event_res_stats[counter][0]);
-        int scaled = event_scaled[counter];
+        struct perf_stat *ps = counter->priv;
+        double avg = avg_stats(&ps->res_stats[0]);
+        int scaled = counter->counts->scaled;
 
         if (scaled == -1) {
-                fprintf(stderr, " %18s  %-24s\n",
-                        "<not counted>", event_name(counter));
+                fprintf(stderr, "%*s%s%*s",
+                        csv_output ? 0 : 18,
+                        "<not counted>",
+                        csv_sep,
+                        csv_output ? 0 : -24,
+                        event_name(counter));
+
+                if (counter->cgrp)
+                        fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+
+                fputc('\n', stderr);
                 return;
         }
 
         if (nsec_counter(counter))
-                nsec_printout(counter, avg);
+                nsec_printout(-1, counter, avg);
         else
-                abs_printout(counter, avg);
+                abs_printout(-1, counter, avg);
+
+        if (csv_output) {
+                fputc('\n', stderr);
+                return;
+        }
 
         print_noise(counter, avg);
 
         if (scaled) {
                 double avg_enabled, avg_running;
 
-                avg_enabled = avg_stats(&event_res_stats[counter][1]);
-                avg_running = avg_stats(&event_res_stats[counter][2]);
+                avg_enabled = avg_stats(&ps->res_stats[1]);
+                avg_running = avg_stats(&ps->res_stats[2]);
 
-                fprintf(stderr, "  (scaled from %.2f%%)",
-                                100 * avg_running / avg_enabled);
+                fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled);
         }
-
         fprintf(stderr, "\n");
 }
 
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(struct perf_evsel *counter)
+{
+        u64 ena, run, val;
+        int cpu;
+
+        for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
+                val = counter->counts->cpu[cpu].val;
+                ena = counter->counts->cpu[cpu].ena;
+                run = counter->counts->cpu[cpu].run;
+                if (run == 0 || ena == 0) {
+                        fprintf(stderr, "CPU%*d%s%*s%s%*s",
+                                csv_output ? 0 : -4,
+                                evsel_list->cpus->map[cpu], csv_sep,
+                                csv_output ? 0 : 18,
+                                "<not counted>", csv_sep,
+                                csv_output ? 0 : -24,
+                                event_name(counter));
+
+                        if (counter->cgrp)
+                                fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
+
+                        fputc('\n', stderr);
+                        continue;
+                }
+
+                if (nsec_counter(counter))
+                        nsec_printout(cpu, counter, val);
+                else
+                        abs_printout(cpu, counter, val);
+
+                if (!csv_output) {
+                        print_noise(counter, 1.0);
+
+                        if (run != ena)
+                                fprintf(stderr, "  (%.2f%%)", 100.0 * run / ena);
+                }
+                fputc('\n', stderr);
+        }
+}
+
 static void print_stat(int argc, const char **argv)
 {
-        int i, counter;
+        struct perf_evsel *counter;
+        int i;
 
         fflush(stdout);
 
-        fprintf(stderr, "\n");
-        fprintf(stderr, " Performance counter stats for ");
-        if(target_pid == -1 && target_tid == -1) {
-                fprintf(stderr, "\'%s", argv[0]);
-                for (i = 1; i < argc; i++)
-                        fprintf(stderr, " %s", argv[i]);
-        } else if (target_pid != -1)
-                fprintf(stderr, "process id \'%d", target_pid);
-        else
-                fprintf(stderr, "thread id \'%d", target_tid);
-
-        fprintf(stderr, "\'");
-        if (run_count > 1)
-                fprintf(stderr, " (%d runs)", run_count);
-        fprintf(stderr, ":\n\n");
+        if (!csv_output) {
+                fprintf(stderr, "\n");
+                fprintf(stderr, " Performance counter stats for ");
+                if(target_pid == -1 && target_tid == -1) {
+                        fprintf(stderr, "\'%s", argv[0]);
+                        for (i = 1; i < argc; i++)
+                                fprintf(stderr, " %s", argv[i]);
+                } else if (target_pid != -1)
+                        fprintf(stderr, "process id \'%d", target_pid);
+                else
+                        fprintf(stderr, "thread id \'%d", target_tid);
+
+                fprintf(stderr, "\'");
+                if (run_count > 1)
+                        fprintf(stderr, " (%d runs)", run_count);
+                fprintf(stderr, ":\n\n");
+        }
 
-        for (counter = 0; counter < nr_counters; counter++)
-                print_counter(counter);
+        if (no_aggr) {
+                list_for_each_entry(counter, &evsel_list->entries, node)
+                        print_counter(counter);
+        } else {
+                list_for_each_entry(counter, &evsel_list->entries, node)
+                        print_counter_aggr(counter);
+        }
 
-        fprintf(stderr, "\n");
-        fprintf(stderr, " %18.9f  seconds time elapsed",
-                        avg_stats(&walltime_nsecs_stats)/1e9);
-        if (run_count > 1) {
-                fprintf(stderr, "   ( +- %7.3f%% )",
-                                100*stddev_stats(&walltime_nsecs_stats) /
-                                avg_stats(&walltime_nsecs_stats));
+        if (!csv_output) {
+                if (!null_run)
+                        fprintf(stderr, "\n");
+                fprintf(stderr, " %17.9f seconds time elapsed",
+                                avg_stats(&walltime_nsecs_stats)/1e9);
+                if (run_count > 1) {
+                        fprintf(stderr, "                                        ");
+                        print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+                                        avg_stats(&walltime_nsecs_stats));
+                }
+                fprintf(stderr, "\n\n");
         }
-        fprintf(stderr, "\n\n");
 }
 
 static volatile int signr = -1;
@@ -521,10 +1014,19 @@ static const char * const stat_usage[] = {
         NULL
 };
 
+static int stat__set_big_num(const struct option *opt __used,
+                             const char *s __used, int unset)
+{
+        big_num_opt = unset ? 0 : 1;
+        return 0;
+}
+
 static const struct option options[] = {
-        OPT_CALLBACK('e', "event", NULL, "event",
+        OPT_CALLBACK('e', "event", &evsel_list, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events),
+        OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+                     "event filter", parse_filter),
         OPT_BOOLEAN('i', "no-inherit", &no_inherit,
                     "child tasks do not inherit counters"),
         OPT_INTEGER('p', "pid", &target_pid,
@@ -541,64 +1043,162 @@ static const struct option options[] = {
                     "repeat command and print average + stddev (max: 100)"),
         OPT_BOOLEAN('n', "null", &null_run,
                     "null run - dont start any counters"),
-        OPT_BOOLEAN('B', "big-num", &big_num,
-                    "print large numbers with thousands\' separators"),
+        OPT_INCR('d', "detailed", &detailed_run,
+                    "detailed run - start a lot of events"),
+        OPT_BOOLEAN('S', "sync", &sync_run,
+                    "call sync() before starting a run"),
+        OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
+                           "print large numbers with thousands\' separators",
+                           stat__set_big_num),
         OPT_STRING('C', "cpu", &cpu_list, "cpu",
                     "list of cpus to monitor in system-wide"),
+        OPT_BOOLEAN('A', "no-aggr", &no_aggr,
+                    "disable CPU count aggregation"),
+        OPT_STRING('x', "field-separator", &csv_sep, "separator",
+                   "print counts with custom separator"),
+        OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+                     "monitor event in cgroup name only",
+                     parse_cgroups),
         OPT_END()
 };
 
+/*
+ * Add default attributes, if there were no attributes specified or
+ * if -d/--detailed, -d -d or -d -d -d is used:
+ */
+static int add_default_attributes(void)
+{
+        struct perf_evsel *pos;
+        size_t attr_nr = 0;
+        size_t c;
+
+        /* Set attrs if no event is selected and !null_run: */
+        if (null_run)
+                return 0;
+
+        if (!evsel_list->nr_entries) {
+                for (c = 0; c < ARRAY_SIZE(default_attrs); c++) {
+                        pos = perf_evsel__new(default_attrs + c, c + attr_nr);
+                        if (pos == NULL)
+                                return -1;
+                        perf_evlist__add(evsel_list, pos);
+                }
+                attr_nr += c;
+        }
+
+        /* Detailed events get appended to the event list: */
+
+        if (detailed_run <  1)
+                return 0;
+
+        /* Append detailed run extra attributes: */
+        for (c = 0; c < ARRAY_SIZE(detailed_attrs); c++) {
+                pos = perf_evsel__new(detailed_attrs + c, c + attr_nr);
+                if (pos == NULL)
+                        return -1;
+                perf_evlist__add(evsel_list, pos);
+        }
+        attr_nr += c;
+
+        if (detailed_run < 2)
+                return 0;
+
+        /* Append very detailed run extra attributes: */
+        for (c = 0; c < ARRAY_SIZE(very_detailed_attrs); c++) {
+                pos = perf_evsel__new(very_detailed_attrs + c, c + attr_nr);
+                if (pos == NULL)
+                        return -1;
+                perf_evlist__add(evsel_list, pos);
+        }
+
+        if (detailed_run < 3)
+                return 0;
+
+        /* Append very, very detailed run extra attributes: */
+        for (c = 0; c < ARRAY_SIZE(very_very_detailed_attrs); c++) {
+                pos = perf_evsel__new(very_very_detailed_attrs + c, c + attr_nr);
+                if (pos == NULL)
+                        return -1;
+                perf_evlist__add(evsel_list, pos);
+        }
+
+
+        return 0;
+}
+
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
-        int status;
-        int i,j;
+        struct perf_evsel *pos;
+        int status = -ENOMEM;
 
         setlocale(LC_ALL, "");
 
+        evsel_list = perf_evlist__new(NULL, NULL);
+        if (evsel_list == NULL)
+                return -ENOMEM;
+
         argc = parse_options(argc, argv, options, stat_usage,
                 PARSE_OPT_STOP_AT_NON_OPTION);
+
+        if (csv_sep)
+                csv_output = true;
+        else
+                csv_sep = DEFAULT_SEPARATOR;
+
+        /*
+         * let the spreadsheet do the pretty-printing
+         */
+        if (csv_output) {
+                /* User explicitely passed -B? */
+                if (big_num_opt == 1) {
+                        fprintf(stderr, "-B option not supported with -x\n");
+                        usage_with_options(stat_usage, options);
+                } else /* Nope, so disable big number formatting */
+                        big_num = false;
+        } else if (big_num_opt == 0) /* User passed --no-big-num */
+                big_num = false;
+
         if (!argc && target_pid == -1 && target_tid == -1)
                 usage_with_options(stat_usage, options);
         if (run_count <= 0)
                 usage_with_options(stat_usage, options);
 
-        /* Set attrs and nr_counters if no event is selected and !null_run */
-        if (!null_run && !nr_counters) {
-                memcpy(attrs, default_attrs, sizeof(default_attrs));
-                nr_counters = ARRAY_SIZE(default_attrs);
+        /* no_aggr, cgroup are for system-wide only */
+        if ((no_aggr || nr_cgroups) && !system_wide) {
+                fprintf(stderr, "both cgroup and no-aggregation "
+                        "modes only available in system-wide mode\n");
+
+                usage_with_options(stat_usage, options);
         }
 
-        if (system_wide)
-                nr_cpus = read_cpu_map(cpu_list);
-        else
-                nr_cpus = 1;
+        if (add_default_attributes())
+                goto out;
 
-        if (nr_cpus < 1)
+        if (target_pid != -1)
+                target_tid = target_pid;
+
+        evsel_list->threads = thread_map__new(target_pid, target_tid);
+        if (evsel_list->threads == NULL) {
+                pr_err("Problems finding threads of monitor\n");
                 usage_with_options(stat_usage, options);
+        }
 
-        if (target_pid != -1) {
-                target_tid = target_pid;
-                thread_num = find_all_tid(target_pid, &all_tids);
-                if (thread_num <= 0) {
-                        fprintf(stderr, "Can't find all threads of pid %d\n",
-                                        target_pid);
-                        usage_with_options(stat_usage, options);
-                }
-        } else {
-                all_tids=malloc(sizeof(pid_t));
-                if (!all_tids)
-                        return -ENOMEM;
+        if (system_wide)
+                evsel_list->cpus = cpu_map__new(cpu_list);
+        else
+                evsel_list->cpus = cpu_map__dummy_new();
 
-                all_tids[0] = target_tid;
-                thread_num = 1;
+        if (evsel_list->cpus == NULL) {
+                perror("failed to parse CPUs map");
+                usage_with_options(stat_usage, options);
+                return -1;
         }
 
-        for (i = 0; i < MAX_NR_CPUS; i++) {
-                for (j = 0; j < MAX_COUNTERS; j++) {
-                        fd[i][j] = malloc(sizeof(int)*thread_num);
-                        if (!fd[i][j])
-                                return -ENOMEM;
-                }
+        list_for_each_entry(pos, &evsel_list->entries, node) {
+                if (perf_evsel__alloc_stat_priv(pos) < 0 ||
+                    perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0 ||
+                    perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, evsel_list->threads->nr) < 0)
+                        goto out_free_fd;
         }
 
         /*
@@ -616,11 +1216,20 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
         for (run_idx = 0; run_idx < run_count; run_idx++) {
                 if (run_count != 1 && verbose)
                         fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
+
+                if (sync_run)
+                        sync();
+
                 status = run_perf_stat(argc, argv);
         }
 
         if (status != -1)
                 print_stat(argc, argv);
-
+out_free_fd:
+        list_for_each_entry(pos, &evsel_list->entries, node)
+                perf_evsel__free_stat_priv(pos);
+        perf_evlist__delete_maps(evsel_list);
+out:
+        perf_evlist__delete(evsel_list);
         return status;
 }
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 035b9fa063a9..2da9162262b0 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -7,10 +7,11 @@
 
 #include "util/cache.h"
 #include "util/debug.h"
+#include "util/evlist.h"
 #include "util/parse-options.h"
-#include "util/session.h"
+#include "util/parse-events.h"
 #include "util/symbol.h"
-#include "util/thread.h"
+#include "util/thread_map.h"
 
 static long page_size;
 
@@ -119,10 +120,16 @@ static int test__vmlinux_matches_kallsyms(void)
          * end addresses too.
          */
         for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
-                struct symbol *pair;
+                struct symbol *pair, *first_pair;
+                bool backwards = true;
 
                 sym  = rb_entry(nd, struct symbol, rb_node);
-                pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
+
+                if (sym->start == sym->end)
+                        continue;
+
+                first_pair = machine__find_kernel_symbol(&kallsyms, type, sym->start, NULL, NULL);
+                pair = first_pair;
 
                 if (pair && pair->start == sym->start) {
 next_pair:
@@ -140,11 +147,13 @@ next_pair:
                                 if (llabs(skew) < page_size)
                                         continue;
 
-                                pr_debug("%#Lx: diff end addr for %s v: %#Lx k: %#Lx\n",
+                                pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
                                          sym->start, sym->name, sym->end, pair->end);
                         } else {
-                                struct rb_node *nnd = rb_prev(&pair->rb_node);
-
+                                struct rb_node *nnd;
+detour:
+                                nnd = backwards ? rb_prev(&pair->rb_node) :
+                                                  rb_next(&pair->rb_node);
                                 if (nnd) {
                                         struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
 
@@ -153,11 +162,18 @@ next_pair:
                                                 goto next_pair;
                                         }
                                 }
-                                pr_debug("%#Lx: diff name v: %s k: %s\n",
+
+                                if (backwards) {
+                                        backwards = false;
+                                        pair = first_pair;
+                                        goto detour;
+                                }
+
+                                pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
                                          sym->start, sym->name, pair->name);
                         }
                 } else
-                        pr_debug("%#Lx: %s not on kallsyms\n", sym->start, sym->name);
+                        pr_debug("%#" PRIx64 ": %s not on kallsyms\n", sym->start, sym->name);
 
                 err = -1;
         }
@@ -196,10 +212,10 @@ next_pair:
 
                 if (pair->start == pos->start) {
                         pair->priv = 1;
-                        pr_info(" %Lx-%Lx %Lx %s in kallsyms as",
+                        pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
                                 pos->start, pos->end, pos->pgoff, pos->dso->name);
                         if (pos->pgoff != pair->pgoff || pos->end != pair->end)
-                                pr_info(": \n*%Lx-%Lx %Lx",
+                                pr_info(": \n*%" PRIx64 "-%" PRIx64 " %" PRIx64 "",
                                         pair->start, pair->end, pair->pgoff);
                         pr_info(" %s\n", pair->dso->name);
                         pair->priv = 1;
@@ -219,6 +235,371 @@ out:
         return err;
 }
 
+#include "util/cpumap.h"
+#include "util/evsel.h"
+#include <sys/types.h>
+
+static int trace_event__id(const char *evname)
+{
+        char *filename;
+        int err = -1, fd;
+
+        if (asprintf(&filename,
+                     "/sys/kernel/debug/tracing/events/syscalls/%s/id",
+                     evname) < 0)
+                return -1;
+
+        fd = open(filename, O_RDONLY);
+        if (fd >= 0) {
+                char id[16];
+                if (read(fd, id, sizeof(id)) > 0)
+                        err = atoi(id);
+                close(fd);
+        }
+
+        free(filename);
+        return err;
+}
+
+static int test__open_syscall_event(void)
+{
+        int err = -1, fd;
+        struct thread_map *threads;
+        struct perf_evsel *evsel;
+        struct perf_event_attr attr;
+        unsigned int nr_open_calls = 111, i;
+        int id = trace_event__id("sys_enter_open");
+
+        if (id < 0) {
+                pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+                return -1;
+        }
+
+        threads = thread_map__new(-1, getpid());
+        if (threads == NULL) {
+                pr_debug("thread_map__new\n");
+                return -1;
+        }
+
+        memset(&attr, 0, sizeof(attr));
+        attr.type = PERF_TYPE_TRACEPOINT;
+        attr.config = id;
+        evsel = perf_evsel__new(&attr, 0);
+        if (evsel == NULL) {
+                pr_debug("perf_evsel__new\n");
+                goto out_thread_map_delete;
+        }
+
+        if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
+                pr_debug("failed to open counter: %s, "
+                         "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+                         strerror(errno));
+                goto out_evsel_delete;
+        }
+
+        for (i = 0; i < nr_open_calls; ++i) {
+                fd = open("/etc/passwd", O_RDONLY);
+                close(fd);
+        }
+
+        if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
+                pr_debug("perf_evsel__read_on_cpu\n");
+                goto out_close_fd;
+        }
+
+        if (evsel->counts->cpu[0].val != nr_open_calls) {
+                pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
+                         nr_open_calls, evsel->counts->cpu[0].val);
+                goto out_close_fd;
+        }
+        
+        err = 0;
+out_close_fd:
+        perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+        perf_evsel__delete(evsel);
+out_thread_map_delete:
+        thread_map__delete(threads);
+        return err;
+}
+
+#include <sched.h>
+
+static int test__open_syscall_event_on_all_cpus(void)
+{
+        int err = -1, fd, cpu;
+        struct thread_map *threads;
+        struct cpu_map *cpus;
+        struct perf_evsel *evsel;
+        struct perf_event_attr attr;
+        unsigned int nr_open_calls = 111, i;
+        cpu_set_t cpu_set;
+        int id = trace_event__id("sys_enter_open");
+
+        if (id < 0) {
+                pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
+                return -1;
+        }
+
+        threads = thread_map__new(-1, getpid());
+        if (threads == NULL) {
+                pr_debug("thread_map__new\n");
+                return -1;
+        }
+
+        cpus = cpu_map__new(NULL);
+        if (cpus == NULL) {
+                pr_debug("cpu_map__new\n");
+                goto out_thread_map_delete;
+        }
+
+
+        CPU_ZERO(&cpu_set);
+
+        memset(&attr, 0, sizeof(attr));
+        attr.type = PERF_TYPE_TRACEPOINT;
+        attr.config = id;
+        evsel = perf_evsel__new(&attr, 0);
+        if (evsel == NULL) {
+                pr_debug("perf_evsel__new\n");
+                goto out_thread_map_delete;
+        }
+
+        if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
+                pr_debug("failed to open counter: %s, "
+                         "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+                         strerror(errno));
+                goto out_evsel_delete;
+        }
+
+        for (cpu = 0; cpu < cpus->nr; ++cpu) {
+                unsigned int ncalls = nr_open_calls + cpu;
+                /*
+                 * XXX eventually lift this restriction in a way that
+                 * keeps perf building on older glibc installations
+                 * without CPU_ALLOC. 1024 cpus in 2010 still seems
+                 * a reasonable upper limit tho :-)
+                 */
+                if (cpus->map[cpu] >= CPU_SETSIZE) {
+                        pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+                        continue;
+                }
+
+                CPU_SET(cpus->map[cpu], &cpu_set);
+                if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+                        pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+                                 cpus->map[cpu],
+                                 strerror(errno));
+                        goto out_close_fd;
+                }
+                for (i = 0; i < ncalls; ++i) {
+                        fd = open("/etc/passwd", O_RDONLY);
+                        close(fd);
+                }
+                CPU_CLR(cpus->map[cpu], &cpu_set);
+        }
+
+        /*
+         * Here we need to explicitely preallocate the counts, as if
+         * we use the auto allocation it will allocate just for 1 cpu,
+         * as we start by cpu 0.
+         */
+        if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+                pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
+                goto out_close_fd;
+        }
+
+        err = 0;
+
+        for (cpu = 0; cpu < cpus->nr; ++cpu) {
+                unsigned int expected;
+
+                if (cpus->map[cpu] >= CPU_SETSIZE)
+                        continue;
+
+                if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+                        pr_debug("perf_evsel__read_on_cpu\n");
+                        err = -1;
+                        break;
+                }
+
+                expected = nr_open_calls + cpu;
+                if (evsel->counts->cpu[cpu].val != expected) {
+                        pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
+                                 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+                        err = -1;
+                }
+        }
+
+out_close_fd:
+        perf_evsel__close_fd(evsel, 1, threads->nr);
+out_evsel_delete:
+        perf_evsel__delete(evsel);
+out_thread_map_delete:
+        thread_map__delete(threads);
+        return err;
+}
+
+/*
+ * This test will generate random numbers of calls to some getpid syscalls,
+ * then establish an mmap for a group of events that are created to monitor
+ * the syscalls.
+ *
+ * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated
+ * sample.id field to map back to its respective perf_evsel instance.
+ *
+ * Then it checks if the number of syscalls reported as perf events by
+ * the kernel corresponds to the number of syscalls made.
+ */
+static int test__basic_mmap(void)
+{
+        int err = -1;
+        union perf_event *event;
+        struct thread_map *threads;
+        struct cpu_map *cpus;
+        struct perf_evlist *evlist;
+        struct perf_event_attr attr = {
+                .type           = PERF_TYPE_TRACEPOINT,
+                .read_format    = PERF_FORMAT_ID,
+                .sample_type    = PERF_SAMPLE_ID,
+                .watermark      = 0,
+        };
+        cpu_set_t cpu_set;
+        const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
+                                        "getpgid", };
+        pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
+                                      (void*)getpgid };
+#define nsyscalls ARRAY_SIZE(syscall_names)
+        int ids[nsyscalls];
+        unsigned int nr_events[nsyscalls],
+                     expected_nr_events[nsyscalls], i, j;
+        struct perf_evsel *evsels[nsyscalls], *evsel;
+        int sample_size = __perf_evsel__sample_size(attr.sample_type);
+
+        for (i = 0; i < nsyscalls; ++i) {
+                char name[64];
+
+                snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
+                ids[i] = trace_event__id(name);
+                if (ids[i] < 0) {
+                        pr_debug("Is debugfs mounted on /sys/kernel/debug?\n");
+                        return -1;
+                }
+                nr_events[i] = 0;
+                expected_nr_events[i] = random() % 257;
+        }
+
+        threads = thread_map__new(-1, getpid());
+        if (threads == NULL) {
+                pr_debug("thread_map__new\n");
+                return -1;
+        }
+
+        cpus = cpu_map__new(NULL);
+        if (cpus == NULL) {
+                pr_debug("cpu_map__new\n");
+                goto out_free_threads;
+        }
+
+        CPU_ZERO(&cpu_set);
+        CPU_SET(cpus->map[0], &cpu_set);
+        sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
+        if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
+                pr_debug("sched_setaffinity() failed on CPU %d: %s ",
+                         cpus->map[0], strerror(errno));
+                goto out_free_cpus;
+        }
+
+        evlist = perf_evlist__new(cpus, threads);
+        if (evlist == NULL) {
+                pr_debug("perf_evlist__new\n");
+                goto out_free_cpus;
+        }
+
+        /* anonymous union fields, can't be initialized above */
+        attr.wakeup_events = 1;
+        attr.sample_period = 1;
+
+        for (i = 0; i < nsyscalls; ++i) {
+                attr.config = ids[i];
+                evsels[i] = perf_evsel__new(&attr, i);
+                if (evsels[i] == NULL) {
+                        pr_debug("perf_evsel__new\n");
+                        goto out_free_evlist;
+                }
+
+                perf_evlist__add(evlist, evsels[i]);
+
+                if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
+                        pr_debug("failed to open counter: %s, "
+                                 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
+                                 strerror(errno));
+                        goto out_close_fd;
+                }
+        }
+
+        if (perf_evlist__mmap(evlist, 128, true) < 0) {
+                pr_debug("failed to mmap events: %d (%s)\n", errno,
+                         strerror(errno));
+                goto out_close_fd;
+        }
+
+        for (i = 0; i < nsyscalls; ++i)
+                for (j = 0; j < expected_nr_events[i]; ++j) {
+                        int foo = syscalls[i]();
+                        ++foo;
+                }
+
+        while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+                struct perf_sample sample;
+
+                if (event->header.type != PERF_RECORD_SAMPLE) {
+                        pr_debug("unexpected %s event\n",
+                                 perf_event__name(event->header.type));
+                        goto out_munmap;
+                }
+
+                err = perf_event__parse_sample(event, attr.sample_type, sample_size,
+                                               false, &sample);
+                if (err) {
+                        pr_err("Can't parse sample, err = %d\n", err);
+                        goto out_munmap;
+                }
+
+                evsel = perf_evlist__id2evsel(evlist, sample.id);
+                if (evsel == NULL) {
+                        pr_debug("event with id %" PRIu64
+                                 " doesn't map to an evsel\n", sample.id);
+                        goto out_munmap;
+                }
+                nr_events[evsel->idx]++;
+        }
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
+                        pr_debug("expected %d %s events, got %d\n",
+                                 expected_nr_events[evsel->idx],
+                                 event_name(evsel), nr_events[evsel->idx]);
+                        goto out_munmap;
+                }
+        }
+
+        err = 0;
+out_munmap:
+        perf_evlist__munmap(evlist);
+out_close_fd:
+        for (i = 0; i < nsyscalls; ++i)
+                perf_evsel__close_fd(evsels[i], 1, threads->nr);
+out_free_evlist:
+        perf_evlist__delete(evlist);
+out_free_cpus:
+        cpu_map__delete(cpus);
+out_free_threads:
+        thread_map__delete(threads);
+        return err;
+#undef nsyscalls
+}
+
 static struct test {
         const char *desc;
         int (*func)(void);
@@ -228,6 +609,18 @@ static struct test {
                 .func = test__vmlinux_matches_kallsyms,
         },
         {
+                .desc = "detect open syscall event",
+                .func = test__open_syscall_event,
+        },
+        {
+                .desc = "detect open syscall event on all cpus",
+                .func = test__open_syscall_event_on_all_cpus,
+        },
+        {
+                .desc = "read samples using the mmap interface",
+                .func = test__basic_mmap,
+        },
+        {
                 .func = NULL,
         },
 };
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 9bcc38f0b706..aa26f4d66d10 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -32,6 +32,10 @@
 #include "util/session.h"
 #include "util/svghelper.h"
 
+#define SUPPORT_OLD_POWER_EVENTS 1
+#define PWR_EVENT_EXIT -1
+
+
 static char             const *input_name = "perf.data";
 static char             const *output_name = "output.svg";
 
@@ -260,9 +264,6 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
                 c->start_time = start;
         if (p->start_time == 0 || p->start_time > start)
                 p->start_time = start;
-
-        if (cpu > numcpus)
-                numcpus = cpu;
 }
 
 #define MAX_CPUS 4096
@@ -272,19 +273,25 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(event_t *event, struct perf_session *session __used)
+static int process_comm_event(union perf_event *event,
+                              struct perf_sample *sample __used,
+                              struct perf_session *session __used)
 {
         pid_set_comm(event->comm.tid, event->comm.comm);
         return 0;
 }
 
-static int process_fork_event(event_t *event, struct perf_session *session __used)
+static int process_fork_event(union perf_event *event,
+                              struct perf_sample *sample __used,
+                              struct perf_session *session __used)
 {
         pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
         return 0;
 }
 
-static int process_exit_event(event_t *event, struct perf_session *session __used)
+static int process_exit_event(union perf_event *event,
+                              struct perf_sample *sample __used,
+                              struct perf_session *session __used)
 {
         pid_exit(event->fork.pid, event->fork.time);
         return 0;
@@ -298,12 +305,21 @@ struct trace_entry {
         int                     lock_depth;
 };
 
-struct power_entry {
+#ifdef SUPPORT_OLD_POWER_EVENTS
+static int use_old_power_events;
+struct power_entry_old {
         struct trace_entry te;
         u64     type;
         u64     value;
         u64     cpu_id;
 };
+#endif
+
+struct power_processor_entry {
+        struct trace_entry te;
+        u32     state;
+        u32     cpu_id;
+};
 
 #define TASK_COMM_LEN 16
 struct wakeup_entry {
@@ -470,48 +486,79 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 }
 
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(union perf_event *event __used,
+                                struct perf_sample *sample,
+                                struct perf_evsel *evsel __used,
+                                struct perf_session *session)
 {
-        struct sample_data data;
         struct trace_entry *te;
 
-        memset(&data, 0, sizeof(data));
-
-        event__parse_sample(event, session->sample_type, &data);
-
         if (session->sample_type & PERF_SAMPLE_TIME) {
-                if (!first_time || first_time > data.time)
-                        first_time = data.time;
-                if (last_time < data.time)
-                        last_time = data.time;
+                if (!first_time || first_time > sample->time)
+                        first_time = sample->time;
+                if (last_time < sample->time)
+                        last_time = sample->time;
         }
 
-        te = (void *)data.raw_data;
-        if (session->sample_type & PERF_SAMPLE_RAW && data.raw_size > 0) {
+        te = (void *)sample->raw_data;
+        if (session->sample_type & PERF_SAMPLE_RAW && sample->raw_size > 0) {
                 char *event_str;
-                struct power_entry *pe;
-
-                pe = (void *)te;
-
+#ifdef SUPPORT_OLD_POWER_EVENTS
+                struct power_entry_old *peo;
+                peo = (void *)te;
+#endif
+                /*
+                 * FIXME: use evsel, its already mapped from id to perf_evsel,
+                 * remove perf_header__find_event infrastructure bits.
+                 * Mapping all these "power:cpu_idle" strings to the tracepoint
+                 * ID and then just comparing against evsel->attr.config.
+                 *
+                 * e.g.:
+                 *
+                 * if (evsel->attr.config == power_cpu_idle_id)
+                 */
                 event_str = perf_header__find_event(te->type);
 
                 if (!event_str)
                         return 0;
 
-                if (strcmp(event_str, "power:power_start") == 0)
-                        c_state_start(pe->cpu_id, data.time, pe->value);
+                if (sample->cpu > numcpus)
+                        numcpus = sample->cpu;
+
+                if (strcmp(event_str, "power:cpu_idle") == 0) {
+                        struct power_processor_entry *ppe = (void *)te;
+                        if (ppe->state == (u32)PWR_EVENT_EXIT)
+                                c_state_end(ppe->cpu_id, sample->time);
+                        else
+                                c_state_start(ppe->cpu_id, sample->time,
+                                              ppe->state);
+                }
+                else if (strcmp(event_str, "power:cpu_frequency") == 0) {
+                        struct power_processor_entry *ppe = (void *)te;
+                        p_state_change(ppe->cpu_id, sample->time, ppe->state);
+                }
+
+                else if (strcmp(event_str, "sched:sched_wakeup") == 0)
+                        sched_wakeup(sample->cpu, sample->time, sample->pid, te);
 
-                if (strcmp(event_str, "power:power_end") == 0)
-                        c_state_end(pe->cpu_id, data.time);
+                else if (strcmp(event_str, "sched:sched_switch") == 0)
+                        sched_switch(sample->cpu, sample->time, te);
 
-                if (strcmp(event_str, "power:power_frequency") == 0)
-                        p_state_change(pe->cpu_id, data.time, pe->value);
+#ifdef SUPPORT_OLD_POWER_EVENTS
+                if (use_old_power_events) {
+                        if (strcmp(event_str, "power:power_start") == 0)
+                                c_state_start(peo->cpu_id, sample->time,
+                                              peo->value);
 
-                if (strcmp(event_str, "sched:sched_wakeup") == 0)
-                        sched_wakeup(data.cpu, data.time, data.pid, te);
+                        else if (strcmp(event_str, "power:power_end") == 0)
+                                c_state_end(sample->cpu, sample->time);
 
-                if (strcmp(event_str, "sched:sched_switch") == 0)
-                        sched_switch(data.cpu, data.time, te);
+                        else if (strcmp(event_str,
+                                        "power:power_frequency") == 0)
+                                p_state_change(peo->cpu_id, sample->time,
+                                               peo->value);
+                }
+#endif
         }
         return 0;
 }
@@ -937,7 +984,8 @@ static struct perf_event_ops event_ops = {
 
 static int __cmd_timechart(void)
 {
-        struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+        struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+                                                         0, false, &event_ops);
         int ret = -EINVAL;
 
         if (session == NULL)
@@ -968,7 +1016,8 @@ static const char * const timechart_usage[] = {
         NULL
 };
 
-static const char *record_args[] = {
+#ifdef SUPPORT_OLD_POWER_EVENTS
+static const char * const record_old_args[] = {
         "record",
         "-a",
         "-R",
@@ -980,16 +1029,43 @@ static const char *record_args[] = {
         "-e", "sched:sched_wakeup",
         "-e", "sched:sched_switch",
 };
+#endif
+
+static const char * const record_new_args[] = {
+        "record",
+        "-a",
+        "-R",
+        "-f",
+        "-c", "1",
+        "-e", "power:cpu_frequency",
+        "-e", "power:cpu_idle",
+        "-e", "sched:sched_wakeup",
+        "-e", "sched:sched_switch",
+};
 
 static int __cmd_record(int argc, const char **argv)
 {
         unsigned int rec_argc, i, j;
         const char **rec_argv;
+        const char * const *record_args = record_new_args;
+        unsigned int record_elems = ARRAY_SIZE(record_new_args);
+
+#ifdef SUPPORT_OLD_POWER_EVENTS
+        if (!is_valid_tracepoint("power:cpu_idle") &&
+            is_valid_tracepoint("power:power_start")) {
+                use_old_power_events = 1;
+                record_args = record_old_args;
+                record_elems = ARRAY_SIZE(record_old_args);
+        }
+#endif
 
-        rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+        rec_argc = record_elems + argc - 1;
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
-        for (i = 0; i < ARRAY_SIZE(record_args); i++)
+        if (rec_argv == NULL)
+                return -ENOMEM;
+
+        for (i = 0; i < record_elems; i++)
                 rec_argv[i] = strdup(record_args[i]);
 
         for (j = 1; j < (unsigned int)argc; j++, i++)
@@ -1018,6 +1094,8 @@ static const struct option options[] = {
         OPT_CALLBACK('p', "process", NULL, "process",
                       "process selector. Pass a pid or process name.",
                        parse_process),
+        OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+                    "Look for files with symbols relative to this directory"),
         OPT_END()
 };
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b513e40974f4..f2f3f4937aa2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -20,15 +20,22 @@
 
 #include "perf.h"
 
+#include "util/annotate.h"
+#include "util/cache.h"
 #include "util/color.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/thread.h"
+#include "util/thread_map.h"
+#include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/cpumap.h"
+#include "util/xyarray.h"
 
 #include "util/debug.h"
 
@@ -38,11 +45,11 @@
 #include <stdio.h>
 #include <termios.h>
 #include <unistd.h>
+#include <inttypes.h>
 
 #include <errno.h>
 #include <time.h>
 #include <sched.h>
-#include <pthread.h>
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
@@ -55,88 +62,44 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
+static struct perf_top top = {
+        .count_filter           = 5,
+        .delay_secs             = 2,
+        .display_weighted       = -1,
+        .target_pid             = -1,
+        .target_tid             = -1,
+        .active_symbols         = LIST_HEAD_INIT(top.active_symbols),
+        .active_symbols_lock    = PTHREAD_MUTEX_INITIALIZER,
+        .active_symbols_cond    = PTHREAD_COND_INITIALIZER,
+        .freq                   = 1000, /* 1 KHz */
+};
 
 static bool                     system_wide                     =  false;
 
-static int                      default_interval                =      0;
+static bool                     use_tui, use_stdio;
 
-static int                      count_filter                    =      5;
-static int                      print_entries;
+static int                      default_interval                =      0;
 
-static int                      target_pid                      =     -1;
-static int                      target_tid                      =     -1;
-static pid_t                    *all_tids                       =      NULL;
-static int                      thread_num                      =      0;
+static bool                     kptr_restrict_warned;
+static bool                     vmlinux_warned;
 static bool                     inherit                         =  false;
-static int                      profile_cpu                     =     -1;
-static int                      nr_cpus                         =      0;
 static int                      realtime_prio                   =      0;
 static bool                     group                           =  false;
 static unsigned int             page_size;
-static unsigned int             mmap_pages                      =     16;
-static int                      freq                            =   1000; /* 1 KHz */
+static unsigned int             mmap_pages                      =    128;
 
-static int                      delay_secs                      =      2;
-static bool                     zero                            =  false;
 static bool                     dump_symtab                     =  false;
 
-static bool                     hide_kernel_symbols             =  false;
-static bool                     hide_user_symbols               =  false;
 static struct winsize           winsize;
 
-/*
- * Source
- */
-
-struct source_line {
-        u64                     eip;
-        unsigned long           count[MAX_COUNTERS];
-        char                    *line;
-        struct source_line      *next;
-};
-
 static const char               *sym_filter                     =   NULL;
-struct sym_entry                *sym_filter_entry               =   NULL;
 struct sym_entry                *sym_filter_entry_sched         =   NULL;
 static int                      sym_pcnt_filter                 =      5;
-static int                      sym_counter                     =      0;
-static int                      display_weighted                =     -1;
-static const char               *cpu_list;
-
-/*
- * Symbols
- */
-
-struct sym_entry_source {
-        struct source_line      *source;
-        struct source_line      *lines;
-        struct source_line      **lines_tail;
-        pthread_mutex_t         lock;
-};
-
-struct sym_entry {
-        struct rb_node          rb_node;
-        struct list_head        node;
-        unsigned long           snap_count;
-        double                  weight;
-        int                     skip;
-        u16                     name_len;
-        u8                      origin;
-        struct map              *map;
-        struct sym_entry_source *src;
-        unsigned long           count[0];
-};
 
 /*
  * Source functions
  */
 
-static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
-{
-       return ((void *)self) + symbol_conf.priv_size;
-}
-
 void get_term_dimensions(struct winsize *ws)
 {
         char *s = getenv("LINES");
@@ -161,10 +124,10 @@ void get_term_dimensions(struct winsize *ws)
 
 static void update_print_entries(struct winsize *ws)
 {
-        print_entries = ws->ws_row;
+        top.print_entries = ws->ws_row;
 
-        if (print_entries > 9)
-                print_entries -= 9;
+        if (top.print_entries > 9)
+                top.print_entries -= 9;
 }
 
 static void sig_winch_handler(int sig __used)
@@ -176,12 +139,9 @@ static void sig_winch_handler(int sig __used)
 static int parse_source(struct sym_entry *syme)
 {
         struct symbol *sym;
-        struct sym_entry_source *source;
+        struct annotation *notes;
         struct map *map;
-        FILE *file;
-        char command[PATH_MAX*2];
-        const char *path;
-        u64 len;
+        int err = -1;
 
         if (!syme)
                 return -1;
@@ -192,408 +152,137 @@ static int parse_source(struct sym_entry *syme)
         /*
          * We can't annotate with just /proc/kallsyms
          */
-        if (map->dso->origin == DSO__ORIG_KERNEL)
+        if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
+                pr_err("Can't annotate %s: No vmlinux file was found in the "
+                       "path\n", sym->name);
+                sleep(1);
                 return -1;
-
-        if (syme->src == NULL) {
-                syme->src = zalloc(sizeof(*source));
-                if (syme->src == NULL)
-                        return -1;
-                pthread_mutex_init(&syme->src->lock, NULL);
         }
 
-        source = syme->src;
-
-        if (source->lines) {
-                pthread_mutex_lock(&source->lock);
+        notes = symbol__annotation(sym);
+        if (notes->src != NULL) {
+                pthread_mutex_lock(&notes->lock);
                 goto out_assign;
         }
-        path = map->dso->long_name;
-
-        len = sym->end - sym->start;
-
-        sprintf(command,
-                "objdump --start-address=%#0*Lx --stop-address=%#0*Lx -dS %s",
-                BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
-                BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
-
-        file = popen(command, "r");
-        if (!file)
-                return -1;
-
-        pthread_mutex_lock(&source->lock);
-        source->lines_tail = &source->lines;
-        while (!feof(file)) {
-                struct source_line *src;
-                size_t dummy = 0;
-                char *c, *sep;
-
-                src = malloc(sizeof(struct source_line));
-                assert(src != NULL);
-                memset(src, 0, sizeof(struct source_line));
-
-                if (getline(&src->line, &dummy, file) < 0)
-                        break;
-                if (!src->line)
-                        break;
 
-                c = strchr(src->line, '\n');
-                if (c)
-                        *c = 0;
+        pthread_mutex_lock(&notes->lock);
 
-                src->next = NULL;
-                *source->lines_tail = src;
-                source->lines_tail = &src->next;
-
-                src->eip = strtoull(src->line, &sep, 16);
-                if (*sep == ':')
-                        src->eip = map__objdump_2ip(map, src->eip);
-                else /* this line has no ip info (e.g. source line) */
-                        src->eip = 0;
+        if (symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
+                pthread_mutex_unlock(&notes->lock);
+                pr_err("Not enough memory for annotating '%s' symbol!\n",
+                       sym->name);
+                sleep(1);
+                return err;
         }
-        pclose(file);
+
+        err = symbol__annotate(sym, syme->map, 0);
+        if (err == 0) {
 out_assign:
-        sym_filter_entry = syme;
-        pthread_mutex_unlock(&source->lock);
-        return 0;
+                top.sym_filter_entry = syme;
+        }
+
+        pthread_mutex_unlock(&notes->lock);
+        return err;
 }
 
 static void __zero_source_counters(struct sym_entry *syme)
 {
-        int i;
-        struct source_line *line;
-
-        line = syme->src->lines;
-        while (line) {
-                for (i = 0; i < nr_counters; i++)
-                        line->count[i] = 0;
-                line = line->next;
-        }
+        struct symbol *sym = sym_entry__symbol(syme);
+        symbol__annotate_zero_histograms(sym);
 }
 
 static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
 {
-        struct source_line *line;
-
-        if (syme != sym_filter_entry)
-                return;
+        struct annotation *notes;
+        struct symbol *sym;
 
-        if (pthread_mutex_trylock(&syme->src->lock))
+        if (syme != top.sym_filter_entry)
                 return;
 
-        if (syme->src == NULL || syme->src->source == NULL)
-                goto out_unlock;
-
-        for (line = syme->src->lines; line; line = line->next) {
-                /* skip lines without IP info */
-                if (line->eip == 0)
-                        continue;
-                if (line->eip == ip) {
-                        line->count[counter]++;
-                        break;
-                }
-                if (line->eip > ip)
-                        break;
-        }
-out_unlock:
-        pthread_mutex_unlock(&syme->src->lock);
-}
-
-#define PATTERN_LEN             (BITS_PER_LONG / 4 + 2)
-
-static void lookup_sym_source(struct sym_entry *syme)
-{
-        struct symbol *symbol = sym_entry__symbol(syme);
-        struct source_line *line;
-        char pattern[PATTERN_LEN + 1];
-
-        sprintf(pattern, "%0*Lx <", BITS_PER_LONG / 4,
-                map__rip_2objdump(syme->map, symbol->start));
-
-        pthread_mutex_lock(&syme->src->lock);
-        for (line = syme->src->lines; line; line = line->next) {
-                if (memcmp(line->line, pattern, PATTERN_LEN) == 0) {
-                        syme->src->source = line;
-                        break;
-                }
-        }
-        pthread_mutex_unlock(&syme->src->lock);
-}
+        sym = sym_entry__symbol(syme);
+        notes = symbol__annotation(sym);
 
-static void show_lines(struct source_line *queue, int count, int total)
-{
-        int i;
-        struct source_line *line;
+        if (pthread_mutex_trylock(&notes->lock))
+                return;
 
-        line = queue;
-        for (i = 0; i < count; i++) {
-                float pcnt = 100.0*(float)line->count[sym_counter]/(float)total;
+        ip = syme->map->map_ip(syme->map, ip);
+        symbol__inc_addr_samples(sym, syme->map, counter, ip);
 
-                printf("%8li %4.1f%%\t%s\n", line->count[sym_counter], pcnt, line->line);
-                line = line->next;
-        }
+        pthread_mutex_unlock(&notes->lock);
 }
 
-#define TRACE_COUNT     3
-
 static void show_details(struct sym_entry *syme)
 {
+        struct annotation *notes;
         struct symbol *symbol;
-        struct source_line *line;
-        struct source_line *line_queue = NULL;
-        int displayed = 0;
-        int line_queue_count = 0, total = 0, more = 0;
+        int more;
 
         if (!syme)
                 return;
 
-        if (!syme->src->source)
-                lookup_sym_source(syme);
-
-        if (!syme->src->source)
-                return;
-
         symbol = sym_entry__symbol(syme);
-        printf("Showing %s for %s\n", event_name(sym_counter), symbol->name);
-        printf("  Events  Pcnt (>=%d%%)\n", sym_pcnt_filter);
-
-        pthread_mutex_lock(&syme->src->lock);
-        line = syme->src->source;
-        while (line) {
-                total += line->count[sym_counter];
-                line = line->next;
-        }
-
-        line = syme->src->source;
-        while (line) {
-                float pcnt = 0.0;
-
-                if (!line_queue_count)
-                        line_queue = line;
-                line_queue_count++;
-
-                if (line->count[sym_counter])
-                        pcnt = 100.0 * line->count[sym_counter] / (float)total;
-                if (pcnt >= (float)sym_pcnt_filter) {
-                        if (displayed <= print_entries)
-                                show_lines(line_queue, line_queue_count, total);
-                        else more++;
-                        displayed += line_queue_count;
-                        line_queue_count = 0;
-                        line_queue = NULL;
-                } else if (line_queue_count > TRACE_COUNT) {
-                        line_queue = line_queue->next;
-                        line_queue_count--;
-                }
-
-                line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8;
-                line = line->next;
-        }
-        pthread_mutex_unlock(&syme->src->lock);
-        if (more)
-                printf("%d lines not displayed, maybe increase display entries [e]\n", more);
-}
-
-/*
- * Symbols will be added here in event__process_sample and will get out
- * after decayed.
- */
-static LIST_HEAD(active_symbols);
-static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER;
-
-/*
- * Ordering weight: count-1 * count-2 * ... / count-n
- */
-static double sym_weight(const struct sym_entry *sym)
-{
-        double weight = sym->snap_count;
-        int counter;
+        notes = symbol__annotation(symbol);
 
-        if (!display_weighted)
-                return weight;
+        pthread_mutex_lock(&notes->lock);
 
-        for (counter = 1; counter < nr_counters-1; counter++)
-                weight *= sym->count[counter];
+        if (notes->src == NULL)
+                goto out_unlock;
 
-        weight /= (sym->count[counter] + 1);
+        printf("Showing %s for %s\n", event_name(top.sym_evsel), symbol->name);
+        printf("  Events  Pcnt (>=%d%%)\n", sym_pcnt_filter);
 
-        return weight;
+        more = symbol__annotate_printf(symbol, syme->map, top.sym_evsel->idx,
+                                       0, sym_pcnt_filter, top.print_entries, 4);
+        if (top.zero)
+                symbol__annotate_zero_histogram(symbol, top.sym_evsel->idx);
+        else
+                symbol__annotate_decay_histogram(symbol, top.sym_evsel->idx);
+        if (more != 0)
+                printf("%d lines not displayed, maybe increase display entries [e]\n", more);
+out_unlock:
+        pthread_mutex_unlock(&notes->lock);
 }
 
-static long                     samples;
-static long                     kernel_samples, us_samples;
-static long                     exact_samples;
-static long                     guest_us_samples, guest_kernel_samples;
 static const char               CONSOLE_CLEAR[] = "";
 
 static void __list_insert_active_sym(struct sym_entry *syme)
 {
-        list_add(&syme->node, &active_symbols);
-}
-
-static void list_remove_active_sym(struct sym_entry *syme)
-{
-        pthread_mutex_lock(&active_symbols_lock);
-        list_del_init(&syme->node);
-        pthread_mutex_unlock(&active_symbols_lock);
-}
-
-static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
-{
-        struct rb_node **p = &tree->rb_node;
-        struct rb_node *parent = NULL;
-        struct sym_entry *iter;
-
-        while (*p != NULL) {
-                parent = *p;
-                iter = rb_entry(parent, struct sym_entry, rb_node);
-
-                if (se->weight > iter->weight)
-                        p = &(*p)->rb_left;
-                else
-                        p = &(*p)->rb_right;
-        }
-
-        rb_link_node(&se->rb_node, parent, p);
-        rb_insert_color(&se->rb_node, tree);
+        list_add(&syme->node, &top.active_symbols);
 }
 
-static void print_sym_table(void)
+static void print_sym_table(struct perf_session *session)
 {
-        int printed = 0, j;
-        int counter, snap = !display_weighted ? sym_counter : 0;
-        float samples_per_sec = samples/delay_secs;
-        float ksamples_per_sec = kernel_samples/delay_secs;
-        float us_samples_per_sec = (us_samples)/delay_secs;
-        float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs;
-        float guest_us_samples_per_sec = (guest_us_samples)/delay_secs;
-        float esamples_percent = (100.0*exact_samples)/samples;
-        float sum_ksamples = 0.0;
-        struct sym_entry *syme, *n;
-        struct rb_root tmp = RB_ROOT;
+        char bf[160];
+        int printed = 0;
         struct rb_node *nd;
-        int sym_width = 0, dso_width = 0, dso_short_width = 0;
+        struct sym_entry *syme;
+        struct rb_root tmp = RB_ROOT;
         const int win_width = winsize.ws_col - 1;
-
-        samples = us_samples = kernel_samples = exact_samples = 0;
-        guest_kernel_samples = guest_us_samples = 0;
-
-        /* Sort the active symbols */
-        pthread_mutex_lock(&active_symbols_lock);
-        syme = list_entry(active_symbols.next, struct sym_entry, node);
-        pthread_mutex_unlock(&active_symbols_lock);
-
-        list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
-                syme->snap_count = syme->count[snap];
-                if (syme->snap_count != 0) {
-
-                        if ((hide_user_symbols &&
-                             syme->origin == PERF_RECORD_MISC_USER) ||
-                            (hide_kernel_symbols &&
-                             syme->origin == PERF_RECORD_MISC_KERNEL)) {
-                                list_remove_active_sym(syme);
-                                continue;
-                        }
-                        syme->weight = sym_weight(syme);
-                        rb_insert_active_sym(&tmp, syme);
-                        sum_ksamples += syme->snap_count;
-
-                        for (j = 0; j < nr_counters; j++)
-                                syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8;
-                } else
-                        list_remove_active_sym(syme);
-        }
+        int sym_width, dso_width, dso_short_width;
+        float sum_ksamples = perf_top__decay_samples(&top, &tmp);
 
         puts(CONSOLE_CLEAR);
 
-        printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
-        if (!perf_guest) {
-                printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
-                        "  exact: %4.1f%% [",
-                        samples_per_sec,
-                        100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
-                                         samples_per_sec)),
-                        esamples_percent);
-        } else {
-                printf("   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
-                        " guest kernel:%4.1f%% guest us:%4.1f%%"
-                        " exact: %4.1f%% [",
-                        samples_per_sec,
-                        100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) /
-                                          samples_per_sec)),
-                        100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) /
-                                          samples_per_sec)),
-                        100.0 - (100.0 * ((samples_per_sec -
-                                                guest_kernel_samples_per_sec) /
-                                          samples_per_sec)),
-                        100.0 - (100.0 * ((samples_per_sec -
-                                           guest_us_samples_per_sec) /
-                                          samples_per_sec)),
-                        esamples_percent);
-        }
-
-        if (nr_counters == 1 || !display_weighted) {
-                printf("%Ld", (u64)attrs[0].sample_period);
-                if (freq)
-                        printf("Hz ");
-                else
-                        printf(" ");
-        }
-
-        if (!display_weighted)
-                printf("%s", event_name(sym_counter));
-        else for (counter = 0; counter < nr_counters; counter++) {
-                if (counter)
-                        printf("/");
-
-                printf("%s", event_name(counter));
-        }
+        perf_top__header_snprintf(&top, bf, sizeof(bf));
+        printf("%s\n", bf);
 
-        printf( "], ");
-
-        if (target_pid != -1)
-                printf(" (target_pid: %d", target_pid);
-        else if (target_tid != -1)
-                printf(" (target_tid: %d", target_tid);
-        else
-                printf(" (all");
-
-        if (profile_cpu != -1)
-                printf(", cpu: %d)\n", profile_cpu);
-        else {
-                if (target_tid != -1)
-                        printf(")\n");
-                else
-                        printf(", %d CPUs)\n", nr_cpus);
-        }
+        perf_top__reset_sample_counters(&top);
 
         printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-        if (sym_filter_entry) {
-                show_details(sym_filter_entry);
-                return;
+        if (session->hists.stats.total_lost != 0) {
+                color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
+                printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
+                       session->hists.stats.total_lost);
         }
 
-        /*
-         * Find the longest symbol name that will be displayed
-         */
-        for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) {
-                syme = rb_entry(nd, struct sym_entry, rb_node);
-                if (++printed > print_entries ||
-                    (int)syme->snap_count < count_filter)
-                        continue;
-
-                if (syme->map->dso->long_name_len > dso_width)
-                        dso_width = syme->map->dso->long_name_len;
-
-                if (syme->map->dso->short_name_len > dso_short_width)
-                        dso_short_width = syme->map->dso->short_name_len;
-
-                if (syme->name_len > sym_width)
-                        sym_width = syme->name_len;
+        if (top.sym_filter_entry) {
+                show_details(top.sym_filter_entry);
+                return;
         }
 
-        printed = 0;
+        perf_top__find_widths(&top, &tmp, &dso_width, &dso_short_width,
+                              &sym_width);
 
         if (sym_width + dso_width > winsize.ws_col - 29) {
                 dso_width = dso_short_width;
@@ -601,7 +290,7 @@ static void print_sym_table(void)
                         sym_width = winsize.ws_col - dso_width - 29;
         }
         putchar('\n');
-        if (nr_counters == 1)
+        if (top.evlist->nr_entries == 1)
                 printf("             samples  pcnt");
         else
                 printf("   weight    samples  pcnt");
@@ -610,7 +299,7 @@ static void print_sym_table(void)
                 printf("         RIP       ");
         printf(" %-*.*s DSO\n", sym_width, sym_width, "function");
         printf("   %s    _______ _____",
-               nr_counters == 1 ? "      " : "______");
+               top.evlist->nr_entries == 1 ? "      " : "______");
         if (verbose)
                 printf(" ________________");
         printf(" %-*.*s", sym_width, sym_width, graph_line);
@@ -623,20 +312,21 @@ static void print_sym_table(void)
 
                 syme = rb_entry(nd, struct sym_entry, rb_node);
                 sym = sym_entry__symbol(syme);
-                if (++printed > print_entries || (int)syme->snap_count < count_filter)
+                if (++printed > top.print_entries ||
+                    (int)syme->snap_count < top.count_filter)
                         continue;
 
                 pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) /
                                          sum_ksamples));
 
-                if (nr_counters == 1 || !display_weighted)
+                if (top.evlist->nr_entries == 1 || !top.display_weighted)
                         printf("%20.2f ", syme->weight);
                 else
                         printf("%9.1f %10ld ", syme->weight, syme->snap_count);
 
                 percent_color_fprintf(stdout, "%4.1f%%", pcnt);
                 if (verbose)
-                        printf(" %016llx", sym->start);
+                        printf(" %016" PRIx64, sym->start);
                 printf(" %-*.*s", sym_width, sym_width, sym->name);
                 printf(" %-*.*s\n", dso_width, dso_width,
                        dso_width >= syme->map->dso->long_name_len ?
@@ -688,10 +378,8 @@ static void prompt_symbol(struct sym_entry **target, const char *msg)
 
         /* zero counters of active symbol */
         if (syme) {
-                pthread_mutex_lock(&syme->src->lock);
                 __zero_source_counters(syme);
                 *target = NULL;
-                pthread_mutex_unlock(&syme->src->lock);
         }
 
         fprintf(stdout, "\n%s: ", msg);
@@ -702,11 +390,11 @@ static void prompt_symbol(struct sym_entry **target, const char *msg)
         if (p)
                 *p = 0;
 
-        pthread_mutex_lock(&active_symbols_lock);
-        syme = list_entry(active_symbols.next, struct sym_entry, node);
-        pthread_mutex_unlock(&active_symbols_lock);
+        pthread_mutex_lock(&top.active_symbols_lock);
+        syme = list_entry(top.active_symbols.next, struct sym_entry, node);
+        pthread_mutex_unlock(&top.active_symbols_lock);
 
-        list_for_each_entry_safe_from(syme, n, &active_symbols, node) {
+        list_for_each_entry_safe_from(syme, n, &top.active_symbols, node) {
                 struct symbol *sym = sym_entry__symbol(syme);
 
                 if (!strcmp(buf, sym->name)) {
@@ -730,34 +418,34 @@ static void print_mapped_keys(void)
 {
         char *name = NULL;
 
-        if (sym_filter_entry) {
-                struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+        if (top.sym_filter_entry) {
+                struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
                 name = sym->name;
         }
 
         fprintf(stdout, "\nMapped keys:\n");
-        fprintf(stdout, "\t[d]     display refresh delay.             \t(%d)\n", delay_secs);
-        fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", print_entries);
+        fprintf(stdout, "\t[d]     display refresh delay.             \t(%d)\n", top.delay_secs);
+        fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", top.print_entries);
 
-        if (nr_counters > 1)
-                fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(sym_counter));
+        if (top.evlist->nr_entries > 1)
+                fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(top.sym_evsel));
 
-        fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", count_filter);
+        fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", top.count_filter);
 
         fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
         fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
         fprintf(stdout, "\t[S]     stop annotation.\n");
 
-        if (nr_counters > 1)
-                fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0);
+        if (top.evlist->nr_entries > 1)
+                fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", top.display_weighted ? 1 : 0);
 
         fprintf(stdout,
                 "\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
-                hide_kernel_symbols ? "yes" : "no");
+                top.hide_kernel_symbols ? "yes" : "no");
         fprintf(stdout,
                 "\t[U]     hide user symbols.               \t(%s)\n",
-                hide_user_symbols ? "yes" : "no");
-        fprintf(stdout, "\t[z]     toggle sample zeroing.             \t(%d)\n", zero ? 1 : 0);
+                top.hide_user_symbols ? "yes" : "no");
+        fprintf(stdout, "\t[z]     toggle sample zeroing.             \t(%d)\n", top.zero ? 1 : 0);
         fprintf(stdout, "\t[qQ]    quit.\n");
 }
 
@@ -778,7 +466,7 @@ static int key_mapped(int c)
                         return 1;
                 case 'E':
                 case 'w':
-                        return nr_counters > 1 ? 1 : 0;
+                        return top.evlist->nr_entries > 1 ? 1 : 0;
                 default:
                         break;
         }
@@ -813,43 +501,50 @@ static void handle_keypress(struct perf_session *session, int c)
 
         switch (c) {
                 case 'd':
-                        prompt_integer(&delay_secs, "Enter display delay");
-                        if (delay_secs < 1)
-                                delay_secs = 1;
+                        prompt_integer(&top.delay_secs, "Enter display delay");
+                        if (top.delay_secs < 1)
+                                top.delay_secs = 1;
                         break;
                 case 'e':
-                        prompt_integer(&print_entries, "Enter display entries (lines)");
-                        if (print_entries == 0) {
+                        prompt_integer(&top.print_entries, "Enter display entries (lines)");
+                        if (top.print_entries == 0) {
                                 sig_winch_handler(SIGWINCH);
                                 signal(SIGWINCH, sig_winch_handler);
                         } else
                                 signal(SIGWINCH, SIG_DFL);
                         break;
                 case 'E':
-                        if (nr_counters > 1) {
-                                int i;
+                        if (top.evlist->nr_entries > 1) {
+                                /* Select 0 as the default event: */
+                                int counter = 0;
 
                                 fprintf(stderr, "\nAvailable events:");
-                                for (i = 0; i < nr_counters; i++)
-                                        fprintf(stderr, "\n\t%d %s", i, event_name(i));
 
-                                prompt_integer(&sym_counter, "Enter details event counter");
+                                list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
+                                        fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel));
+
+                                prompt_integer(&counter, "Enter details event counter");
 
-                                if (sym_counter >= nr_counters) {
-                                        fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(0));
-                                        sym_counter = 0;
+                                if (counter >= top.evlist->nr_entries) {
+                                        top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
+                                        fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel));
                                         sleep(1);
+                                        break;
                                 }
-                        } else sym_counter = 0;
+                                list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
+                                        if (top.sym_evsel->idx == counter)
+                                                break;
+                        } else
+                                top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
                         break;
                 case 'f':
-                        prompt_integer(&count_filter, "Enter display event count filter");
+                        prompt_integer(&top.count_filter, "Enter display event count filter");
                         break;
                 case 'F':
                         prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)");
                         break;
                 case 'K':
-                        hide_kernel_symbols = !hide_kernel_symbols;
+                        top.hide_kernel_symbols = !top.hide_kernel_symbols;
                         break;
                 case 'q':
                 case 'Q':
@@ -858,34 +553,50 @@ static void handle_keypress(struct perf_session *session, int c)
                                 perf_session__fprintf_dsos(session, stderr);
                         exit(0);
                 case 's':
-                        prompt_symbol(&sym_filter_entry, "Enter details symbol");
+                        prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
                         break;
                 case 'S':
-                        if (!sym_filter_entry)
+                        if (!top.sym_filter_entry)
                                 break;
                         else {
-                                struct sym_entry *syme = sym_filter_entry;
+                                struct sym_entry *syme = top.sym_filter_entry;
 
-                                pthread_mutex_lock(&syme->src->lock);
-                                sym_filter_entry = NULL;
+                                top.sym_filter_entry = NULL;
                                 __zero_source_counters(syme);
-                                pthread_mutex_unlock(&syme->src->lock);
                         }
                         break;
                 case 'U':
-                        hide_user_symbols = !hide_user_symbols;
+                        top.hide_user_symbols = !top.hide_user_symbols;
                         break;
                 case 'w':
-                        display_weighted = ~display_weighted;
+                        top.display_weighted = ~top.display_weighted;
                         break;
                 case 'z':
-                        zero = !zero;
+                        top.zero = !top.zero;
                         break;
                 default:
                         break;
         }
 }
 
+static void *display_thread_tui(void *arg __used)
+{
+        int err = 0;
+        pthread_mutex_lock(&top.active_symbols_lock);
+        while (list_empty(&top.active_symbols)) {
+                err = pthread_cond_wait(&top.active_symbols_cond,
+                                        &top.active_symbols_lock);
+                if (err)
+                        break;
+        }
+        pthread_mutex_unlock(&top.active_symbols_lock);
+        if (!err)
+                perf_top__tui_browser(&top);
+        exit_browser(0);
+        exit(0);
+        return NULL;
+}
+
 static void *display_thread(void *arg __used)
 {
         struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
@@ -900,13 +611,13 @@ static void *display_thread(void *arg __used)
         tc.c_cc[VTIME] = 0;
 
 repeat:
-        delay_msecs = delay_secs * 1000;
+        delay_msecs = top.delay_secs * 1000;
         tcsetattr(0, TCSANOW, &tc);
         /* trash return*/
         getc(stdin);
 
         do {
-                print_sym_table();
+                print_sym_table(session);
         } while (!poll(&stdin_poll, 1, delay_msecs) == 1);
 
         c = getc(stdin);
@@ -921,6 +632,7 @@ repeat:
 /* Tag samples to be skipped. */
 static const char *skip_symbols[] = {
         "default_idle",
+        "native_safe_halt",
         "cpu_idle",
         "enter_idle",
         "exit_idle",
@@ -956,9 +668,9 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 
         syme = symbol__priv(sym);
         syme->map = map;
-        syme->src = NULL;
+        symbol__annotate_init(map, sym);
 
-        if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
+        if (!top.sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
                 /* schedule initial sym_filter_entry setup */
                 sym_filter_entry_sched = syme;
                 sym_filter = NULL;
@@ -966,48 +678,45 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 
         for (i = 0; skip_symbols[i]; i++) {
                 if (!strcmp(skip_symbols[i], name)) {
-                        syme->skip = 1;
+                        sym->ignore = true;
                         break;
                 }
         }
 
-        if (!syme->skip)
-                syme->name_len = strlen(sym->name);
-
         return 0;
 }
 
-static void event__process_sample(const event_t *self,
-                                 struct perf_session *session, int counter)
+static void perf_event__process_sample(const union perf_event *event,
+                                       struct perf_sample *sample,
+                                       struct perf_session *session)
 {
-        u64 ip = self->ip.ip;
+        u64 ip = event->ip.ip;
         struct sym_entry *syme;
         struct addr_location al;
-        struct sample_data data;
         struct machine *machine;
-        u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        u8 origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-        ++samples;
+        ++top.samples;
 
         switch (origin) {
         case PERF_RECORD_MISC_USER:
-                ++us_samples;
-                if (hide_user_symbols)
+                ++top.us_samples;
+                if (top.hide_user_symbols)
                         return;
                 machine = perf_session__find_host_machine(session);
                 break;
         case PERF_RECORD_MISC_KERNEL:
-                ++kernel_samples;
-                if (hide_kernel_symbols)
+                ++top.kernel_samples;
+                if (top.hide_kernel_symbols)
                         return;
                 machine = perf_session__find_host_machine(session);
                 break;
         case PERF_RECORD_MISC_GUEST_KERNEL:
-                ++guest_kernel_samples;
-                machine = perf_session__find_machine(session, self->ip.pid);
+                ++top.guest_kernel_samples;
+                machine = perf_session__find_machine(session, event->ip.pid);
                 break;
         case PERF_RECORD_MISC_GUEST_USER:
-                ++guest_us_samples;
+                ++top.guest_us_samples;
                 /*
                  * TODO: we don't process guest user from host side
                  * except simple counting.
@@ -1019,19 +728,34 @@ static void event__process_sample(const event_t *self,
 
         if (!machine && perf_guest) {
                 pr_err("Can't find guest [%d]'s kernel information\n",
-                        self->ip.pid);
+                        event->ip.pid);
                 return;
         }
 
-        if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
-                exact_samples++;
+        if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
+                top.exact_samples++;
 
-        if (event__preprocess_sample(self, session, &al, &data,
-                                     symbol_filter) < 0 ||
+        if (perf_event__preprocess_sample(event, session, &al, sample,
+                                          symbol_filter) < 0 ||
             al.filtered)
                 return;
 
+        if (!kptr_restrict_warned &&
+            symbol_conf.kptr_restrict &&
+            al.cpumode == PERF_RECORD_MISC_KERNEL) {
+                ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Kernel%s samples will not be resolved.\n",
+                          !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+                          " modules" : "");
+                if (use_browser <= 0)
+                        sleep(5);
+                kptr_restrict_warned = true;
+        }
+
         if (al.sym == NULL) {
+                const char *msg = "Kernel samples will not be resolved.\n";
                 /*
                  * As we do lazy loading of symtabs we only will know if the
                  * specified vmlinux file is invalid when we actually have a
@@ -1043,11 +767,20 @@ static void event__process_sample(const event_t *self,
                  * --hide-kernel-symbols, even if the user specifies an
                  * invalid --vmlinux ;-)
                  */
-                if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
+                if (!kptr_restrict_warned && !vmlinux_warned &&
+                    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
                     RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-                        pr_err("The %s file can't be used\n",
-                               symbol_conf.vmlinux_name);
-                        exit(1);
+                        if (symbol_conf.vmlinux_name) {
+                                ui__warning("The %s file can't be used.\n%s",
+                                            symbol_conf.vmlinux_name, msg);
+                        } else {
+                                ui__warning("A vmlinux file was not found.\n%s",
+                                            msg);
+                        }
+
+                        if (use_browser <= 0)
+                                sleep(5);
+                        vmlinux_warned = true;
                 }
 
                 return;
@@ -1055,13 +788,13 @@ static void event__process_sample(const event_t *self,
 
         /* let's see, whether we need to install initial sym_filter_entry */
         if (sym_filter_entry_sched) {
-                sym_filter_entry = sym_filter_entry_sched;
+                top.sym_filter_entry = sym_filter_entry_sched;
                 sym_filter_entry_sched = NULL;
-                if (parse_source(sym_filter_entry) < 0) {
-                        struct symbol *sym = sym_entry__symbol(sym_filter_entry);
+                if (parse_source(top.sym_filter_entry) < 0) {
+                        struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
 
                         pr_err("Can't annotate %s", sym->name);
-                        if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
+                        if (top.sym_filter_entry->map->dso->symtab_type == SYMTAB__KALLSYMS) {
                                 pr_err(": No vmlinux file was found in the path:\n");
                                 machine__fprintf_vmlinux_path(machine, stderr);
                         } else
@@ -1071,226 +804,158 @@ static void event__process_sample(const event_t *self,
         }
 
         syme = symbol__priv(al.sym);
-        if (!syme->skip) {
-                syme->count[counter]++;
-                syme->origin = origin;
-                record_precise_ip(syme, counter, ip);
-                pthread_mutex_lock(&active_symbols_lock);
-                if (list_empty(&syme->node) || !syme->node.next)
+        if (!al.sym->ignore) {
+                struct perf_evsel *evsel;
+
+                evsel = perf_evlist__id2evsel(top.evlist, sample->id);
+                assert(evsel != NULL);
+                syme->count[evsel->idx]++;
+                record_precise_ip(syme, evsel->idx, ip);
+                pthread_mutex_lock(&top.active_symbols_lock);
+                if (list_empty(&syme->node) || !syme->node.next) {
+                        static bool first = true;
                         __list_insert_active_sym(syme);
-                pthread_mutex_unlock(&active_symbols_lock);
+                        if (first) {
+                                pthread_cond_broadcast(&top.active_symbols_cond);
+                                first = false;
+                        }
+                }
+                pthread_mutex_unlock(&top.active_symbols_lock);
         }
 }
 
-struct mmap_data {
-        int                     counter;
-        void                    *base;
-        int                     mask;
-        unsigned int            prev;
-};
-
-static unsigned int mmap_read_head(struct mmap_data *md)
-{
-        struct perf_event_mmap_page *pc = md->base;
-        int head;
-
-        head = pc->data_head;
-        rmb();
-
-        return head;
-}
-
-static void perf_session__mmap_read_counter(struct perf_session *self,
-                                            struct mmap_data *md)
+static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
-        unsigned int head = mmap_read_head(md);
-        unsigned int old = md->prev;
-        unsigned char *data = md->base + page_size;
-        int diff;
-
-        /*
-         * If we're further behind than half the buffer, there's a chance
-         * the writer will bite our tail and mess up the samples under us.
-         *
-         * If we somehow ended up ahead of the head, we got messed up.
-         *
-         * In either case, truncate and restart at head.
-         */
-        diff = head - old;
-        if (diff > md->mask / 2 || diff < 0) {
-                fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
-
-                /*
-                 * head points to a known good entry, start there.
-                 */
-                old = head;
-        }
-
-        for (; old != head;) {
-                event_t *event = (event_t *)&data[old & md->mask];
-
-                event_t event_copy;
-
-                size_t size = event->header.size;
+        struct perf_sample sample;
+        union perf_event *event;
+        int ret;
 
-                /*
-                 * Event straddles the mmap boundary -- header should always
-                 * be inside due to u64 alignment of output.
-                 */
-                if ((old & md->mask) + size != ((old + size) & md->mask)) {
-                        unsigned int offset = old;
-                        unsigned int len = min(sizeof(*event), size), cpy;
-                        void *dst = &event_copy;
-
-                        do {
-                                cpy = min(md->mask + 1 - (offset & md->mask), len);
-                                memcpy(dst, &data[offset & md->mask], cpy);
-                                offset += cpy;
-                                dst += cpy;
-                                len -= cpy;
-                        } while (len);
-
-                        event = &event_copy;
+        while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
+                ret = perf_session__parse_sample(self, event, &sample);
+                if (ret) {
+                        pr_err("Can't parse sample, err = %d\n", ret);
+                        continue;
                 }
 
                 if (event->header.type == PERF_RECORD_SAMPLE)
-                        event__process_sample(event, self, md->counter);
+                        perf_event__process_sample(event, &sample, self);
                 else
-                        event__process(event, self);
-                old += size;
+                        perf_event__process(event, &sample, self);
         }
-
-        md->prev = old;
 }
 
-static struct pollfd *event_array;
-static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
-
 static void perf_session__mmap_read(struct perf_session *self)
 {
-        int i, counter, thread_index;
-
-        for (i = 0; i < nr_cpus; i++) {
-                for (counter = 0; counter < nr_counters; counter++)
-                        for (thread_index = 0;
-                                thread_index < thread_num;
-                                thread_index++) {
-                                perf_session__mmap_read_counter(self,
-                                        &mmap_array[i][counter][thread_index]);
-                        }
-        }
-}
+        int i;
 
-int nr_poll;
-int group_fd;
+        for (i = 0; i < top.evlist->nr_mmaps; i++)
+                perf_session__mmap_read_idx(self, i);
+}
 
-static void start_counter(int i, int counter)
+static void start_counters(struct perf_evlist *evlist)
 {
-        struct perf_event_attr *attr;
-        int cpu;
-        int thread_index;
-
-        cpu = profile_cpu;
-        if (target_tid == -1 && profile_cpu == -1)
-                cpu = cpumap[i];
+        struct perf_evsel *counter;
 
-        attr = attrs + counter;
+        list_for_each_entry(counter, &evlist->entries, node) {
+                struct perf_event_attr *attr = &counter->attr;
 
-        attr->sample_type       = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+                attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
-        if (freq) {
-                attr->sample_type       |= PERF_SAMPLE_PERIOD;
-                attr->freq              = 1;
-                attr->sample_freq       = freq;
-        }
+                if (top.freq) {
+                        attr->sample_type |= PERF_SAMPLE_PERIOD;
+                        attr->freq        = 1;
+                        attr->sample_freq = top.freq;
+                }
 
-        attr->inherit           = (cpu < 0) && inherit;
-        attr->mmap              = 1;
+                if (evlist->nr_entries > 1) {
+                        attr->sample_type |= PERF_SAMPLE_ID;
+                        attr->read_format |= PERF_FORMAT_ID;
+                }
 
-        for (thread_index = 0; thread_index < thread_num; thread_index++) {
+                attr->mmap = 1;
+                attr->inherit = inherit;
 try_again:
-                fd[i][counter][thread_index] = sys_perf_event_open(attr,
-                                all_tids[thread_index], cpu, group_fd, 0);
-
-                if (fd[i][counter][thread_index] < 0) {
+                if (perf_evsel__open(counter, top.evlist->cpus,
+                                     top.evlist->threads, group) < 0) {
                         int err = errno;
 
-                        if (err == EPERM || err == EACCES)
-                                die("No permission - are you root?\n");
+                        if (err == EPERM || err == EACCES) {
+                                ui__warning_paranoid();
+                                goto out_err;
+                        }
                         /*
                          * If it's cycles then fall back to hrtimer
                          * based cpu-clock-tick sw counter, which
                          * is always available even if no PMU support:
                          */
-                        if (attr->type == PERF_TYPE_HARDWARE
-                                        && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
+                        if (attr->type == PERF_TYPE_HARDWARE &&
+                            attr->config == PERF_COUNT_HW_CPU_CYCLES) {
                                 if (verbose)
-                                        warning(" ... trying to fall back to cpu-clock-ticks\n");
+                                        ui__warning("Cycles event not supported,\n"
+                                                    "trying to fall back to cpu-clock-ticks\n");
 
                                 attr->type = PERF_TYPE_SOFTWARE;
                                 attr->config = PERF_COUNT_SW_CPU_CLOCK;
                                 goto try_again;
                         }
-                        printf("\n");
-                        error("perfcounter syscall returned with %d (%s)\n",
-                                        fd[i][counter][thread_index], strerror(err));
-                        die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-                        exit(-1);
+
+                        if (err == ENOENT) {
+                                ui__warning("The %s event is not supported.\n",
+                                            event_name(counter));
+                                goto out_err;
+                        }
+
+                        ui__warning("The sys_perf_event_open() syscall "
+                                    "returned with %d (%s).  /bin/dmesg "
+                                    "may provide additional information.\n"
+                                    "No CONFIG_PERF_EVENTS=y kernel support "
+                                    "configured?\n", err, strerror(err));
+                        goto out_err;
                 }
-                assert(fd[i][counter][thread_index] >= 0);
-                fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
+        }
 
-                /*
-                 * First counter acts as the group leader:
-                 */
-                if (group && group_fd == -1)
-                        group_fd = fd[i][counter][thread_index];
-
-                event_array[nr_poll].fd = fd[i][counter][thread_index];
-                event_array[nr_poll].events = POLLIN;
-                nr_poll++;
-
-                mmap_array[i][counter][thread_index].counter = counter;
-                mmap_array[i][counter][thread_index].prev = 0;
-                mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1;
-                mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
-                                PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0);
-                if (mmap_array[i][counter][thread_index].base == MAP_FAILED)
-                        die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+        if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) {
+                ui__warning("Failed to mmap with %d (%s)\n",
+                            errno, strerror(errno));
+                goto out_err;
         }
+
+        return;
+
+out_err:
+        exit_browser(0);
+        exit(0);
 }
 
 static int __cmd_top(void)
 {
         pthread_t thread;
-        int i, counter;
-        int ret;
+        int ret __used;
         /*
          * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
          * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
          */
-        struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false);
+        struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
         if (session == NULL)
                 return -ENOMEM;
 
-        if (target_tid != -1)
-                event__synthesize_thread(target_tid, event__process, session);
+        if (top.target_tid != -1)
+                perf_event__synthesize_thread_map(top.evlist->threads,
+                                                  perf_event__process, session);
         else
-                event__synthesize_threads(event__process, session);
+                perf_event__synthesize_threads(perf_event__process, session);
 
-        for (i = 0; i < nr_cpus; i++) {
-                group_fd = -1;
-                for (counter = 0; counter < nr_counters; counter++)
-                        start_counter(i, counter);
-        }
+        start_counters(top.evlist);
+        session->evlist = top.evlist;
+        perf_session__update_sample_type(session);
 
         /* Wait for a minimal set of events before starting the snapshot */
-        poll(&event_array[0], nr_poll, 100);
+        poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
 
         perf_session__mmap_read(session);
 
-        if (pthread_create(&thread, NULL, display_thread, session)) {
+        if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
+                                                             display_thread), session)) {
                 printf("Could not create display thread.\n");
                 exit(-1);
         }
@@ -1306,12 +971,12 @@ static int __cmd_top(void)
         }
 
         while (1) {
-                int hits = samples;
+                u64 hits = top.samples;
 
                 perf_session__mmap_read(session);
 
-                if (hits == samples)
-                        ret = poll(event_array, nr_poll, 100);
+                if (hits == top.samples)
+                        ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
         }
 
         return 0;
@@ -1323,31 +988,31 @@ static const char * const top_usage[] = {
 };
 
 static const struct option options[] = {
-        OPT_CALLBACK('e', "event", NULL, "event",
+        OPT_CALLBACK('e', "event", &top.evlist, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events),
         OPT_INTEGER('c', "count", &default_interval,
                     "event period to sample"),
-        OPT_INTEGER('p', "pid", &target_pid,
+        OPT_INTEGER('p', "pid", &top.target_pid,
                     "profile events on existing process id"),
-        OPT_INTEGER('t', "tid", &target_tid,
+        OPT_INTEGER('t', "tid", &top.target_tid,
                     "profile events on existing thread id"),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                             "system-wide collection from all CPUs"),
-        OPT_STRING('C', "cpu", &cpu_list, "cpu",
+        OPT_STRING('C', "cpu", &top.cpu_list, "cpu",
                     "list of cpus to monitor"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
-        OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols,
+        OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
                     "hide kernel symbols"),
         OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
         OPT_INTEGER('r', "realtime", &realtime_prio,
                     "collect data with this RT SCHED_FIFO priority"),
-        OPT_INTEGER('d', "delay", &delay_secs,
+        OPT_INTEGER('d', "delay", &top.delay_secs,
                     "number of seconds to delay between refreshes"),
         OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
                             "dump the symbol table used for profiling"),
-        OPT_INTEGER('f', "count-filter", &count_filter,
+        OPT_INTEGER('f', "count-filter", &top.count_filter,
                     "only display functions with more events than this"),
         OPT_BOOLEAN('g', "group", &group,
                             "put the counters into a counter group"),
@@ -1355,14 +1020,16 @@ static const struct option options[] = {
                     "child tasks inherit counters"),
         OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name",
                     "symbol to annotate"),
-        OPT_BOOLEAN('z', "zero", &zero,
+        OPT_BOOLEAN('z', "zero", &top.zero,
                     "zero history across updates"),
-        OPT_INTEGER('F', "freq", &freq,
+        OPT_INTEGER('F', "freq", &top.freq,
                     "profile at this frequency"),
-        OPT_INTEGER('E', "entries", &print_entries,
+        OPT_INTEGER('E', "entries", &top.print_entries,
                     "display this many functions"),
-        OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols,
+        OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
                     "hide user symbols"),
+        OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
+        OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show counter open errors, etc)"),
         OPT_END()
@@ -1370,8 +1037,12 @@ static const struct option options[] = {
 
 int cmd_top(int argc, const char **argv, const char *prefix __used)
 {
-        int counter;
-        int i,j;
+        struct perf_evsel *pos;
+        int status = -ENOMEM;
+
+        top.evlist = perf_evlist__new(NULL, NULL);
+        if (top.evlist == NULL)
+                return -ENOMEM;
 
         page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -1379,92 +1050,90 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
         if (argc)
                 usage_with_options(top_usage, options);
 
-        if (target_pid != -1) {
-                target_tid = target_pid;
-                thread_num = find_all_tid(target_pid, &all_tids);
-                if (thread_num <= 0) {
-                        fprintf(stderr, "Can't find all threads of pid %d\n",
-                                target_pid);
-                        usage_with_options(top_usage, options);
-                }
-        } else {
-                all_tids=malloc(sizeof(pid_t));
-                if (!all_tids)
-                        return -ENOMEM;
+        /*
+         * XXX For now start disabled, only using TUI if explicitely asked for.
+         * Change that when handle_keys equivalent gets written, live annotation
+         * done, etc.
+         */
+        use_browser = 0;
 
-                all_tids[0] = target_tid;
-                thread_num = 1;
-        }
+        if (use_stdio)
+                use_browser = 0;
+        else if (use_tui)
+                use_browser = 1;
 
-        for (i = 0; i < MAX_NR_CPUS; i++) {
-                for (j = 0; j < MAX_COUNTERS; j++) {
-                        fd[i][j] = malloc(sizeof(int)*thread_num);
-                        mmap_array[i][j] = zalloc(
-                                sizeof(struct mmap_data)*thread_num);
-                        if (!fd[i][j] || !mmap_array[i][j])
-                                return -ENOMEM;
-                }
-        }
-        event_array = malloc(
-                sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
-        if (!event_array)
-                return -ENOMEM;
+        setup_browser(false);
 
         /* CPU and PID are mutually exclusive */
-        if (target_tid > 0 && cpu_list) {
+        if (top.target_tid > 0 && top.cpu_list) {
                 printf("WARNING: PID switch overriding CPU\n");
                 sleep(1);
-                cpu_list = NULL;
+                top.cpu_list = NULL;
         }
 
-        if (!nr_counters)
-                nr_counters = 1;
+        if (top.target_pid != -1)
+                top.target_tid = top.target_pid;
 
-        symbol_conf.priv_size = (sizeof(struct sym_entry) +
-                                 (nr_counters + 1) * sizeof(unsigned long));
+        if (perf_evlist__create_maps(top.evlist, top.target_pid,
+                                     top.target_tid, top.cpu_list) < 0)
+                usage_with_options(top_usage, options);
 
-        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-        if (symbol__init() < 0)
-                return -1;
+        if (!top.evlist->nr_entries &&
+            perf_evlist__add_default(top.evlist) < 0) {
+                pr_err("Not enough memory for event selector list\n");
+                return -ENOMEM;
+        }
 
-        if (delay_secs < 1)
-                delay_secs = 1;
+        if (top.delay_secs < 1)
+                top.delay_secs = 1;
 
         /*
          * User specified count overrides default frequency.
          */
         if (default_interval)
-                freq = 0;
-        else if (freq) {
-                default_interval = freq;
+                top.freq = 0;
+        else if (top.freq) {
+                default_interval = top.freq;
         } else {
                 fprintf(stderr, "frequency and count are zero, aborting\n");
                 exit(EXIT_FAILURE);
         }
 
-        /*
-         * Fill in the ones not specifically initialized via -c:
-         */
-        for (counter = 0; counter < nr_counters; counter++) {
-                if (attrs[counter].sample_period)
+        list_for_each_entry(pos, &top.evlist->entries, node) {
+                if (perf_evsel__alloc_fd(pos, top.evlist->cpus->nr,
+                                         top.evlist->threads->nr) < 0)
+                        goto out_free_fd;
+                /*
+                 * Fill in the ones not specifically initialized via -c:
+                 */
+                if (pos->attr.sample_period)
                         continue;
 
-                attrs[counter].sample_period = default_interval;
+                pos->attr.sample_period = default_interval;
         }
 
-        if (target_tid != -1)
-                nr_cpus = 1;
-        else
-                nr_cpus = read_cpu_map(cpu_list);
+        if (perf_evlist__alloc_pollfd(top.evlist) < 0 ||
+            perf_evlist__alloc_mmap(top.evlist) < 0)
+                goto out_free_fd;
 
-        if (nr_cpus < 1)
-                usage_with_options(top_usage, options);
+        top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
+
+        symbol_conf.priv_size = (sizeof(struct sym_entry) + sizeof(struct annotation) +
+                                 (top.evlist->nr_entries + 1) * sizeof(unsigned long));
+
+        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+        if (symbol__init() < 0)
+                return -1;
 
         get_term_dimensions(&winsize);
-        if (print_entries == 0) {
+        if (top.print_entries == 0) {
                 update_print_entries(&winsize);
                 signal(SIGWINCH, sig_winch_handler);
         }
 
-        return __cmd_top();
+        status = __cmd_top();
+out_free_fd:
+        perf_evlist__delete(top.evlist);
+
+        return status;
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
deleted file mode 100644
index 40a6a2992d15..000000000000
--- a/tools/perf/builtin-trace.c
+++ /dev/null
@@ -1,734 +0,0 @@
-#include "builtin.h"
-
-#include "perf.h"
-#include "util/cache.h"
-#include "util/debug.h"
-#include "util/exec_cmd.h"
-#include "util/header.h"
-#include "util/parse-options.h"
-#include "util/session.h"
-#include "util/symbol.h"
-#include "util/thread.h"
-#include "util/trace-event.h"
-#include "util/util.h"
-
-static char const               *script_name;
-static char const               *generate_script_lang;
-static bool                     debug_mode;
-static u64                      last_timestamp;
-static u64                      nr_unordered;
-
-static int default_start_script(const char *script __unused,
-                                int argc __unused,
-                                const char **argv __unused)
-{
-        return 0;
-}
-
-static int default_stop_script(void)
-{
-        return 0;
-}
-
-static int default_generate_script(const char *outfile __unused)
-{
-        return 0;
-}
-
-static struct scripting_ops default_scripting_ops = {
-        .start_script           = default_start_script,
-        .stop_script            = default_stop_script,
-        .process_event          = print_event,
-        .generate_script        = default_generate_script,
-};
-
-static struct scripting_ops     *scripting_ops;
-
-static void setup_scripting(void)
-{
-        /* make sure PERF_EXEC_PATH is set for scripts */
-        perf_set_argv_exec_path(perf_exec_path());
-
-        setup_perl_scripting();
-        setup_python_scripting();
-
-        scripting_ops = &default_scripting_ops;
-}
-
-static int cleanup_scripting(void)
-{
-        pr_debug("\nperf trace script stopped\n");
-
-        return scripting_ops->stop_script();
-}
-
-static char const               *input_name = "perf.data";
-
-static int process_sample_event(event_t *event, struct perf_session *session)
-{
-        struct sample_data data;
-        struct thread *thread;
-
-        memset(&data, 0, sizeof(data));
-        data.time = -1;
-        data.cpu = -1;
-        data.period = 1;
-
-        event__parse_sample(event, session->sample_type, &data);
-
-        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
-                    data.pid, data.tid, data.ip, data.period);
-
-        thread = perf_session__findnew(session, event->ip.pid);
-        if (thread == NULL) {
-                pr_debug("problem processing %d event, skipping it.\n",
-                         event->header.type);
-                return -1;
-        }
-
-        if (session->sample_type & PERF_SAMPLE_RAW) {
-                if (debug_mode) {
-                        if (data.time < last_timestamp) {
-                                pr_err("Samples misordered, previous: %llu "
-                                        "this: %llu\n", last_timestamp,
-                                        data.time);
-                                nr_unordered++;
-                        }
-                        last_timestamp = data.time;
-                        return 0;
-                }
-                /*
-                 * FIXME: better resolve from pid from the struct trace_entry
-                 * field, although it should be the same than this perf
-                 * event pid
-                 */
-                scripting_ops->process_event(data.cpu, data.raw_data,
-                                             data.raw_size,
-                                             data.time, thread->comm);
-        }
-
-        session->hists.stats.total_period += data.period;
-        return 0;
-}
-
-static u64 nr_lost;
-
-static int process_lost_event(event_t *event, struct perf_session *session __used)
-{
-        nr_lost += event->lost.lost;
-
-        return 0;
-}
-
-static struct perf_event_ops event_ops = {
-        .sample = process_sample_event,
-        .comm   = event__process_comm,
-        .attr   = event__process_attr,
-        .event_type = event__process_event_type,
-        .tracing_data = event__process_tracing_data,
-        .build_id = event__process_build_id,
-        .lost = process_lost_event,
-        .ordered_samples = true,
-};
-
-extern volatile int session_done;
-
-static void sig_handler(int sig __unused)
-{
-        session_done = 1;
-}
-
-static int __cmd_trace(struct perf_session *session)
-{
-        int ret;
-
-        signal(SIGINT, sig_handler);
-
-        ret = perf_session__process_events(session, &event_ops);
-
-        if (debug_mode) {
-                pr_err("Misordered timestamps: %llu\n", nr_unordered);
-                pr_err("Lost events: %llu\n", nr_lost);
-        }
-
-        return ret;
-}
-
-struct script_spec {
-        struct list_head        node;
-        struct scripting_ops    *ops;
-        char                    spec[0];
-};
-
-LIST_HEAD(script_specs);
-
-static struct script_spec *script_spec__new(const char *spec,
-                                            struct scripting_ops *ops)
-{
-        struct script_spec *s = malloc(sizeof(*s) + strlen(spec) + 1);
-
-        if (s != NULL) {
-                strcpy(s->spec, spec);
-                s->ops = ops;
-        }
-
-        return s;
-}
-
-static void script_spec__delete(struct script_spec *s)
-{
-        free(s->spec);
-        free(s);
-}
-
-static void script_spec__add(struct script_spec *s)
-{
-        list_add_tail(&s->node, &script_specs);
-}
-
-static struct script_spec *script_spec__find(const char *spec)
-{
-        struct script_spec *s;
-
-        list_for_each_entry(s, &script_specs, node)
-                if (strcasecmp(s->spec, spec) == 0)
-                        return s;
-        return NULL;
-}
-
-static struct script_spec *script_spec__findnew(const char *spec,
-                                                struct scripting_ops *ops)
-{
-        struct script_spec *s = script_spec__find(spec);
-
-        if (s)
-                return s;
-
-        s = script_spec__new(spec, ops);
-        if (!s)
-                goto out_delete_spec;
-
-        script_spec__add(s);
-
-        return s;
-
-out_delete_spec:
-        script_spec__delete(s);
-
-        return NULL;
-}
-
-int script_spec_register(const char *spec, struct scripting_ops *ops)
-{
-        struct script_spec *s;
-
-        s = script_spec__find(spec);
-        if (s)
-                return -1;
-
-        s = script_spec__findnew(spec, ops);
-        if (!s)
-                return -1;
-
-        return 0;
-}
-
-static struct scripting_ops *script_spec__lookup(const char *spec)
-{
-        struct script_spec *s = script_spec__find(spec);
-        if (!s)
-                return NULL;
-
-        return s->ops;
-}
-
-static void list_available_languages(void)
-{
-        struct script_spec *s;
-
-        fprintf(stderr, "\n");
-        fprintf(stderr, "Scripting language extensions (used in "
-                "perf trace -s [spec:]script.[spec]):\n\n");
-
-        list_for_each_entry(s, &script_specs, node)
-                fprintf(stderr, "  %-42s [%s]\n", s->spec, s->ops->name);
-
-        fprintf(stderr, "\n");
-}
-
-static int parse_scriptname(const struct option *opt __used,
-                            const char *str, int unset __used)
-{
-        char spec[PATH_MAX];
-        const char *script, *ext;
-        int len;
-
-        if (strcmp(str, "lang") == 0) {
-                list_available_languages();
-                exit(0);
-        }
-
-        script = strchr(str, ':');
-        if (script) {
-                len = script - str;
-                if (len >= PATH_MAX) {
-                        fprintf(stderr, "invalid language specifier");
-                        return -1;
-                }
-                strncpy(spec, str, len);
-                spec[len] = '\0';
-                scripting_ops = script_spec__lookup(spec);
-                if (!scripting_ops) {
-                        fprintf(stderr, "invalid language specifier");
-                        return -1;
-                }
-                script++;
-        } else {
-                script = str;
-                ext = strchr(script, '.');
-                if (!ext) {
-                        fprintf(stderr, "invalid script extension");
-                        return -1;
-                }
-                scripting_ops = script_spec__lookup(++ext);
-                if (!scripting_ops) {
-                        fprintf(stderr, "invalid script extension");
-                        return -1;
-                }
-        }
-
-        script_name = strdup(script);
-
-        return 0;
-}
-
-#define for_each_lang(scripts_dir, lang_dirent, lang_next)              \
-        while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&     \
-               lang_next)                                               \
-                if (lang_dirent.d_type == DT_DIR &&                     \
-                    (strcmp(lang_dirent.d_name, ".")) &&                \
-                    (strcmp(lang_dirent.d_name, "..")))
-
-#define for_each_script(lang_dir, script_dirent, script_next)           \
-        while (!readdir_r(lang_dir, &script_dirent, &script_next) &&    \
-               script_next)                                             \
-                if (script_dirent.d_type != DT_DIR)
-
-
-#define RECORD_SUFFIX                   "-record"
-#define REPORT_SUFFIX                   "-report"
-
-struct script_desc {
-        struct list_head        node;
-        char                    *name;
-        char                    *half_liner;
-        char                    *args;
-};
-
-LIST_HEAD(script_descs);
-
-static struct script_desc *script_desc__new(const char *name)
-{
-        struct script_desc *s = zalloc(sizeof(*s));
-
-        if (s != NULL)
-                s->name = strdup(name);
-
-        return s;
-}
-
-static void script_desc__delete(struct script_desc *s)
-{
-        free(s->name);
-        free(s);
-}
-
-static void script_desc__add(struct script_desc *s)
-{
-        list_add_tail(&s->node, &script_descs);
-}
-
-static struct script_desc *script_desc__find(const char *name)
-{
-        struct script_desc *s;
-
-        list_for_each_entry(s, &script_descs, node)
-                if (strcasecmp(s->name, name) == 0)
-                        return s;
-        return NULL;
-}
-
-static struct script_desc *script_desc__findnew(const char *name)
-{
-        struct script_desc *s = script_desc__find(name);
-
-        if (s)
-                return s;
-
-        s = script_desc__new(name);
-        if (!s)
-                goto out_delete_desc;
-
-        script_desc__add(s);
-
-        return s;
-
-out_delete_desc:
-        script_desc__delete(s);
-
-        return NULL;
-}
-
-static char *ends_with(char *str, const char *suffix)
-{
-        size_t suffix_len = strlen(suffix);
-        char *p = str;
-
-        if (strlen(str) > suffix_len) {
-                p = str + strlen(str) - suffix_len;
-                if (!strncmp(p, suffix, suffix_len))
-                        return p;
-        }
-
-        return NULL;
-}
-
-static char *ltrim(char *str)
-{
-        int len = strlen(str);
-
-        while (len && isspace(*str)) {
-                len--;
-                str++;
-        }
-
-        return str;
-}
-
-static int read_script_info(struct script_desc *desc, const char *filename)
-{
-        char line[BUFSIZ], *p;
-        FILE *fp;
-
-        fp = fopen(filename, "r");
-        if (!fp)
-                return -1;
-
-        while (fgets(line, sizeof(line), fp)) {
-                p = ltrim(line);
-                if (strlen(p) == 0)
-                        continue;
-                if (*p != '#')
-                        continue;
-                p++;
-                if (strlen(p) && *p == '!')
-                        continue;
-
-                p = ltrim(p);
-                if (strlen(p) && p[strlen(p) - 1] == '\n')
-                        p[strlen(p) - 1] = '\0';
-
-                if (!strncmp(p, "description:", strlen("description:"))) {
-                        p += strlen("description:");
-                        desc->half_liner = strdup(ltrim(p));
-                        continue;
-                }
-
-                if (!strncmp(p, "args:", strlen("args:"))) {
-                        p += strlen("args:");
-                        desc->args = strdup(ltrim(p));
-                        continue;
-                }
-        }
-
-        fclose(fp);
-
-        return 0;
-}
-
-static int list_available_scripts(const struct option *opt __used,
-                                  const char *s __used, int unset __used)
-{
-        struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
-        char scripts_path[MAXPATHLEN];
-        DIR *scripts_dir, *lang_dir;
-        char script_path[MAXPATHLEN];
-        char lang_path[MAXPATHLEN];
-        struct script_desc *desc;
-        char first_half[BUFSIZ];
-        char *script_root;
-        char *str;
-
-        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
-
-        scripts_dir = opendir(scripts_path);
-        if (!scripts_dir)
-                return -1;
-
-        for_each_lang(scripts_dir, lang_dirent, lang_next) {
-                snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-                         lang_dirent.d_name);
-                lang_dir = opendir(lang_path);
-                if (!lang_dir)
-                        continue;
-
-                for_each_script(lang_dir, script_dirent, script_next) {
-                        script_root = strdup(script_dirent.d_name);
-                        str = ends_with(script_root, REPORT_SUFFIX);
-                        if (str) {
-                                *str = '\0';
-                                desc = script_desc__findnew(script_root);
-                                snprintf(script_path, MAXPATHLEN, "%s/%s",
-                                         lang_path, script_dirent.d_name);
-                                read_script_info(desc, script_path);
-                        }
-                        free(script_root);
-                }
-        }
-
-        fprintf(stdout, "List of available trace scripts:\n");
-        list_for_each_entry(desc, &script_descs, node) {
-                sprintf(first_half, "%s %s", desc->name,
-                        desc->args ? desc->args : "");
-                fprintf(stdout, "  %-36s %s\n", first_half,
-                        desc->half_liner ? desc->half_liner : "");
-        }
-
-        exit(0);
-}
-
-static char *get_script_path(const char *script_root, const char *suffix)
-{
-        struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
-        char scripts_path[MAXPATHLEN];
-        char script_path[MAXPATHLEN];
-        DIR *scripts_dir, *lang_dir;
-        char lang_path[MAXPATHLEN];
-        char *str, *__script_root;
-        char *path = NULL;
-
-        snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
-
-        scripts_dir = opendir(scripts_path);
-        if (!scripts_dir)
-                return NULL;
-
-        for_each_lang(scripts_dir, lang_dirent, lang_next) {
-                snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-                         lang_dirent.d_name);
-                lang_dir = opendir(lang_path);
-                if (!lang_dir)
-                        continue;
-
-                for_each_script(lang_dir, script_dirent, script_next) {
-                        __script_root = strdup(script_dirent.d_name);
-                        str = ends_with(__script_root, suffix);
-                        if (str) {
-                                *str = '\0';
-                                if (strcmp(__script_root, script_root))
-                                        continue;
-                                snprintf(script_path, MAXPATHLEN, "%s/%s",
-                                         lang_path, script_dirent.d_name);
-                                path = strdup(script_path);
-                                free(__script_root);
-                                break;
-                        }
-                        free(__script_root);
-                }
-        }
-
-        return path;
-}
-
-static const char * const trace_usage[] = {
-        "perf trace [<options>] <command>",
-        NULL
-};
-
-static const struct option options[] = {
-        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-                    "dump raw trace in ASCII"),
-        OPT_INCR('v', "verbose", &verbose,
-                    "be more verbose (show symbol address, etc)"),
-        OPT_BOOLEAN('L', "Latency", &latency_format,
-                    "show latency attributes (irqs/preemption disabled, etc)"),
-        OPT_CALLBACK_NOOPT('l', "list", NULL, NULL, "list available scripts",
-                           list_available_scripts),
-        OPT_CALLBACK('s', "script", NULL, "name",
-                     "script file name (lang:script name, script name, or *)",
-                     parse_scriptname),
-        OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
-                   "generate perf-trace.xx script in specified language"),
-        OPT_STRING('i', "input", &input_name, "file",
-                    "input file name"),
-        OPT_BOOLEAN('d', "debug-mode", &debug_mode,
-                   "do various checks like samples ordering and lost events"),
-
-        OPT_END()
-};
-
-int cmd_trace(int argc, const char **argv, const char *prefix __used)
-{
-        struct perf_session *session;
-        const char *suffix = NULL;
-        const char **__argv;
-        char *script_path;
-        int i, err;
-
-        if (argc >= 2 && strncmp(argv[1], "rec", strlen("rec")) == 0) {
-                if (argc < 3) {
-                        fprintf(stderr,
-                                "Please specify a record script\n");
-                        return -1;
-                }
-                suffix = RECORD_SUFFIX;
-        }
-
-        if (argc >= 2 && strncmp(argv[1], "rep", strlen("rep")) == 0) {
-                if (argc < 3) {
-                        fprintf(stderr,
-                                "Please specify a report script\n");
-                        return -1;
-                }
-                suffix = REPORT_SUFFIX;
-        }
-
-        if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
-                char *record_script_path, *report_script_path;
-                int live_pipe[2];
-                pid_t pid;
-
-                record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
-                if (!record_script_path) {
-                        fprintf(stderr, "record script not found\n");
-                        return -1;
-                }
-
-                report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
-                if (!report_script_path) {
-                        fprintf(stderr, "report script not found\n");
-                        return -1;
-                }
-
-                if (pipe(live_pipe) < 0) {
-                        perror("failed to create pipe");
-                        exit(-1);
-                }
-
-                pid = fork();
-                if (pid < 0) {
-                        perror("failed to fork");
-                        exit(-1);
-                }
-
-                if (!pid) {
-                        dup2(live_pipe[1], 1);
-                        close(live_pipe[0]);
-
-                        __argv = malloc(5 * sizeof(const char *));
-                        __argv[0] = "/bin/sh";
-                        __argv[1] = record_script_path;
-                        __argv[2] = "-o";
-                        __argv[3] = "-";
-                        __argv[4] = NULL;
-
-                        execvp("/bin/sh", (char **)__argv);
-                        exit(-1);
-                }
-
-                dup2(live_pipe[0], 0);
-                close(live_pipe[1]);
-
-                __argv = malloc((argc + 3) * sizeof(const char *));
-                __argv[0] = "/bin/sh";
-                __argv[1] = report_script_path;
-                for (i = 2; i < argc; i++)
-                        __argv[i] = argv[i];
-                __argv[i++] = "-i";
-                __argv[i++] = "-";
-                __argv[i++] = NULL;
-
-                execvp("/bin/sh", (char **)__argv);
-                exit(-1);
-        }
-
-        if (suffix) {
-                script_path = get_script_path(argv[2], suffix);
-                if (!script_path) {
-                        fprintf(stderr, "script not found\n");
-                        return -1;
-                }
-
-                __argv = malloc((argc + 1) * sizeof(const char *));
-                __argv[0] = "/bin/sh";
-                __argv[1] = script_path;
-                for (i = 3; i < argc; i++)
-                        __argv[i - 1] = argv[i];
-                __argv[argc - 1] = NULL;
-
-                execvp("/bin/sh", (char **)__argv);
-                exit(-1);
-        }
-
-        setup_scripting();
-
-        argc = parse_options(argc, argv, options, trace_usage,
-                             PARSE_OPT_STOP_AT_NON_OPTION);
-
-        if (symbol__init() < 0)
-                return -1;
-        if (!script_name)
-                setup_pager();
-
-        session = perf_session__new(input_name, O_RDONLY, 0, false);
-        if (session == NULL)
-                return -ENOMEM;
-
-        if (strcmp(input_name, "-") &&
-            !perf_session__has_traces(session, "record -R"))
-                return -EINVAL;
-
-        if (generate_script_lang) {
-                struct stat perf_stat;
-
-                int input = open(input_name, O_RDONLY);
-                if (input < 0) {
-                        perror("failed to open file");
-                        exit(-1);
-                }
-
-                err = fstat(input, &perf_stat);
-                if (err < 0) {
-                        perror("failed to stat file");
-                        exit(-1);
-                }
-
-                if (!perf_stat.st_size) {
-                        fprintf(stderr, "zero-sized file, nothing to do!\n");
-                        exit(0);
-                }
-
-                scripting_ops = script_spec__lookup(generate_script_lang);
-                if (!scripting_ops) {
-                        fprintf(stderr, "invalid language specifier");
-                        return -1;
-                }
-
-                err = scripting_ops->generate_script("perf-trace");
-                goto out;
-        }
-
-        if (script_name) {
-                err = scripting_ops->start_script(script_name, argc, argv);
-                if (err)
-                        goto out;
-                pr_debug("perf trace started with script %s\n\n", script_name);
-        }
-
-        err = __cmd_trace(session);
-
-        perf_session__delete(session);
-        cleanup_scripting();
-out:
-        return err;
-}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 921245b28583..4702e2443a8e 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -19,6 +19,7 @@ extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
+extern int cmd_evlist(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
 extern int cmd_sched(int argc, const char **argv, const char *prefix);
 extern int cmd_list(int argc, const char **argv, const char *prefix);
@@ -27,7 +28,7 @@ extern int cmd_report(int argc, const char **argv, const char *prefix);
 extern int cmd_stat(int argc, const char **argv, const char *prefix);
 extern int cmd_timechart(int argc, const char **argv, const char *prefix);
 extern int cmd_top(int argc, const char **argv, const char *prefix);
-extern int cmd_trace(int argc, const char **argv, const char *prefix);
+extern int cmd_script(int argc, const char **argv, const char *prefix);
 extern int cmd_version(int argc, const char **argv, const char *prefix);
 extern int cmd_probe(int argc, const char **argv, const char *prefix);
 extern int cmd_kmem(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 949d77fc0b97..d695fe40fbff 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -8,6 +8,7 @@ perf-bench			mainporcelain common
 perf-buildid-cache              mainporcelain common
 perf-buildid-list               mainporcelain common
 perf-diff                       mainporcelain common
+perf-evlist                     mainporcelain common
 perf-inject                     mainporcelain common
 perf-list                       mainporcelain common
 perf-sched                      mainporcelain common
@@ -16,7 +17,7 @@ perf-report			mainporcelain common
 perf-stat                       mainporcelain common
 perf-timechart                  mainporcelain common
 perf-top                        mainporcelain common
-perf-trace                      mainporcelain common
+perf-script                     mainporcelain common
 perf-probe                      mainporcelain common
 perf-kmem                       mainporcelain common
 perf-lock                       mainporcelain common
diff --git a/tools/perf/feature-tests.mak b/tools/perf/config/feature-tests.mak
index 7a7b60859053..6170fd2531b5 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -9,8 +9,8 @@ endef
 ifndef NO_DWARF
 define SOURCE_DWARF
 #include <dwarf.h>
-#include <libdw.h>
-#include <version.h>
+#include <elfutils/libdw.h>
+#include <elfutils/version.h>
 #ifndef _ELFUTILS_PREREQ
 #error
 #endif
@@ -79,9 +79,15 @@ endef
 endif
 
 ifndef NO_LIBPYTHON
+define SOURCE_PYTHON_VERSION
+#include <Python.h>
+#if PY_VERSION_HEX >= 0x03000000
+        #error
+#endif
+int main(void){}
+endef
 define SOURCE_PYTHON_EMBED
 #include <Python.h>
-
 int main(void)
 {
         Py_Initialize();
@@ -110,10 +116,13 @@ int main(void)
 }
 endef
 
-# try-cc
-# Usage: option = $(call try-cc, source-to-build, cc-options)
-try-cc = $(shell sh -c                                            \
-        'TMP="$(OUTPUT)$(TMPOUT).$$$$";                           \
-         echo "$(1)" |                                            \
-         $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
-         rm -f "$$TMP"')
+define SOURCE_STRLCPY
+#include <stdlib.h>
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+int main(void)
+{
+        strlcpy(NULL, NULL, 0);
+        return 0;
+}
+endef
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
new file mode 100644
index 000000000000..8046182a19eb
--- /dev/null
+++ b/tools/perf/config/utilities.mak
@@ -0,0 +1,188 @@
+# This allows us to work with the newline character:
+define newline
+
+
+endef
+newline := $(newline)
+
+# nl-escape
+#
+# Usage: escape = $(call nl-escape[,escape])
+#
+# This is used as the common way to specify
+# what should replace a newline when escaping
+# newlines; the default is a bizarre string.
+#
+nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+
+# escape-nl
+#
+# Usage: escaped-text = $(call escape-nl,text[,escape])
+#
+# GNU make's $(shell ...) function converts to a
+# single space each newline character in the output
+# produced during the expansion; this may not be
+# desirable.
+#
+# The only solution is to change each newline into
+# something that won't be converted, so that the
+# information can be recovered later with
+# $(call unescape-nl...)
+#
+escape-nl = $(subst $(newline),$(call nl-escape,$(2)),$(1))
+
+# unescape-nl
+#
+# Usage: text = $(call unescape-nl,escaped-text[,escape])
+#
+# See escape-nl.
+#
+unescape-nl = $(subst $(call nl-escape,$(2)),$(newline),$(1))
+
+# shell-escape-nl
+#
+# Usage: $(shell some-command | $(call shell-escape-nl[,escape]))
+#
+# Use this to escape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as a string constant
+#       in an `awk' program that is delimited by shell
+#       single-quotes, so be wary of the characters
+#       that are chosen.
+#
+define shell-escape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "$(nl-escape)" $$0} END {printf t}'
+endef
+
+# shell-unescape-nl
+#
+# Usage: $(shell some-command | $(call shell-unescape-nl[,escape]))
+#
+# Use this to unescape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as an extended regular
+#       expression constant in an `awk' program that is
+#       delimited by shell single-quotes, so be wary
+#       of the characters that are chosen.
+#
+# (The bash shell has a bug where `{gsub(...),...}' is
+#  misinterpreted as a brace expansion; this can be
+#  overcome by putting a space between `{' and `gsub').
+#
+define shell-unescape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "\n" $$0} END { gsub(/$(nl-escape)/,"\n",t); printf t }'
+endef
+
+# escape-for-shell-sq
+#
+# Usage: embeddable-text = $(call escape-for-shell-sq,text)
+#
+# This function produces text that is suitable for
+# embedding in a shell string that is delimited by
+# single-quotes.
+#
+escape-for-shell-sq =  $(subst ','\'',$(1))
+
+# shell-sq
+#
+# Usage: single-quoted-and-escaped-text = $(call shell-sq,text)
+#
+shell-sq = '$(escape-for-shell-sq)'
+
+# shell-wordify
+#
+# Usage: wordified-text = $(call shell-wordify,text)
+#
+# For instance:
+#
+#  |define text
+#  |hello
+#  |world
+#  |endef
+#  |
+#  |target:
+#  |    echo $(call shell-wordify,$(text))
+#
+# At least GNU make gets confused by expanding a newline
+# within the context of a command line of a makefile rule
+# (this is in constrast to a `$(shell ...)' function call,
+# which can handle it just fine).
+#
+# This function avoids the problem by producing a string
+# that works as a shell word, regardless of whether or
+# not it contains a newline.
+#
+# If the text to be wordified contains a newline, then
+# an intrictate shell command substitution is constructed
+# to render the text as a single line; when the shell
+# processes the resulting escaped text, it transforms
+# it into the original unescaped text.
+#
+# If the text does not contain a newline, then this function
+# produces the same results as the `$(shell-sq)' function.
+#
+shell-wordify = $(if $(findstring $(newline),$(1)),$(_sw-esc-nl),$(shell-sq))
+define _sw-esc-nl
+"$$(echo $(call escape-nl,$(shell-sq),$(2)) | $(call shell-unescape-nl,$(2)))"
+endef
+
+# is-absolute
+#
+# Usage: bool-value = $(call is-absolute,path)
+#
+is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+
+# lookup
+#
+# Usage: absolute-executable-path-or-empty = $(call lookup,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+lookup = $(call unescape-nl,$(shell sh -c $(_l-sh)))
+_l-sh = $(call shell-sq,command -v $(shell-sq) | $(call shell-escape-nl,))
+
+# is-executable
+#
+# Usage: bool-value = $(call is-executable,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+#  trying too hard and getting things wrong).
+#
+is-executable = $(call _is-executable-helper,$(shell-sq))
+_is-executable-helper = $(shell sh -c $(_is-executable-sh))
+_is-executable-sh = $(call shell-sq,test -f $(1) -a -x $(1) && echo y)
+
+# get-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable,path)
+#
+# The goal is to get an absolute path for an executable;
+# the `command -v' is defined by POSIX, but it's not
+# necessarily very portable, so it's only used if
+# relative path resolution is requested, as determined
+# by the presence of a leading `/'.
+#
+get-executable = $(if $(1),$(if $(is-absolute),$(_ge-abspath),$(lookup)))
+_ge-abspath = $(if $(is-executable),$(1))
+
+# get-supplied-or-default-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
+#
+define get-executable-or-default
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+endef
+_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2)))
+_gea_warn = $(warning The path '$(1)' is not executable.)
+_gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-cc
+# Usage: option = $(call try-cc, source-to-build, cc-options)
+try-cc = $(shell sh -c                                            \
+        'TMP="$(OUTPUT)$(TMPOUT).$$$$";                           \
+         echo "$(1)" |                                            \
+         $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+         rm -f "$$TMP"')
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index cdd6c03f1e14..ec635b7cc8ea 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -313,6 +313,7 @@ static void handle_internal_command(int argc, const char **argv)
                 { "buildid-cache", cmd_buildid_cache, 0 },
                 { "buildid-list", cmd_buildid_list, 0 },
                 { "diff",       cmd_diff,       0 },
+                { "evlist",     cmd_evlist,     0 },
                 { "help",       cmd_help,       0 },
                 { "list",       cmd_list,       0 },
                 { "record",     cmd_record,     0 },
@@ -323,7 +324,7 @@ static void handle_internal_command(int argc, const char **argv)
                 { "top",        cmd_top,        0 },
                 { "annotate",   cmd_annotate,   0 },
                 { "version",    cmd_version,    0 },
-                { "trace",      cmd_trace,      0 },
+                { "script",     cmd_script,     0 },
                 { "sched",      cmd_sched,      0 },
                 { "probe",      cmd_probe,      0 },
                 { "kmem",       cmd_kmem,       0 },
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 95aaf565c704..a5fc660c1f12 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -94,6 +94,32 @@ void get_term_dimensions(struct winsize *ws);
 #include "util/types.h"
 #include <stdbool.h>
 
+struct perf_mmap {
+        void                    *base;
+        int                     mask;
+        unsigned int            prev;
+};
+
+static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
+{
+        struct perf_event_mmap_page *pc = mm->base;
+        int head = pc->data_head;
+        rmb();
+        return head;
+}
+
+static inline void perf_mmap__write_tail(struct perf_mmap *md,
+                                         unsigned long tail)
+{
+        struct perf_event_mmap_page *pc = md->base;
+
+        /*
+         * ensure all reads are done before we write the tail out.
+         */
+        /* mb(); */
+        pc->data_tail = tail;
+}
+
 /*
  * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all
  * counters in the current task.
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
new file mode 100755
index 000000000000..df638c438a9f
--- /dev/null
+++ b/tools/perf/python/twatch.py
@@ -0,0 +1,41 @@
+#! /usr/bin/python
+# -*- python -*-
+# -*- coding: utf-8 -*-
+#   twatch - Experimental use of the perf python interface
+#   Copyright (C) 2011 Arnaldo Carvalho de Melo <acme@redhat.com>
+#
+#   This application is free software; you can redistribute it and/or
+#   modify it under the terms of the GNU General Public License
+#   as published by the Free Software Foundation; version 2.
+#
+#   This application is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#   General Public License for more details.
+
+import perf
+
+def main():
+        cpus = perf.cpu_map()
+        threads = perf.thread_map()
+        evsel = perf.evsel(task = 1, comm = 1, mmap = 0,
+                           wakeup_events = 1, sample_period = 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);
+        evlist = perf.evlist(cpus, threads)
+        evlist.add(evsel)
+        evlist.mmap()
+        while True:
+                evlist.poll(timeout = -1)
+                for cpu in cpus:
+                        event = evlist.read_on_cpu(cpu)
+                        if not event:
+                                continue
+                        print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu,
+                                                                event.sample_pid,
+                                                                event.sample_tid),
+                        print event
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 01a64ad693f2..790ceba6ad3f 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -8,7 +8,7 @@
 
 #line 1 "Context.xs"
 /*
- * Context.xs.  XS interfaces for perf trace.
+ * Context.xs.  XS interfaces for perf script.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
index 549cf0467d30..c1e2ed1ed34e 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
@@ -1,5 +1,5 @@
 /*
- * Context.xs.  XS interfaces for perf trace.
+ * Context.xs.  XS interfaces for perf script.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
@@ -23,7 +23,7 @@
 #include "perl.h"
 #include "XSUB.h"
 #include "../../../perf.h"
-#include "../../../util/trace-event.h"
+#include "../../../util/script-event.h"
 
 MODULE = Perf::Trace::Context           PACKAGE = Perf::Trace::Context
 PROTOTYPES: ENABLE
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/README b/tools/perf/scripts/perl/Perf-Trace-Util/README
index 9a9707630791..2f0c7f3043ee 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/README
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/README
@@ -1,7 +1,7 @@
 Perf-Trace-Util version 0.01
 ============================
 
-This module contains utility functions for use with perf trace.
+This module contains utility functions for use with perf script.
 
 Core.pm and Util.pm are pure Perl modules; Core.pm contains routines
 that the core perf support for Perl calls on and should always be
@@ -33,7 +33,7 @@ After you do that:
 
 INSTALLATION
 
-Building perf with perf trace Perl scripting should install this
+Building perf with perf script Perl scripting should install this
 module in the right place.
 
 You should make sure libperl and ExtUtils/Embed.pm are installed first
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
index 6c7f3659cb17..4e2f6039ac92 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Context.pm
@@ -34,7 +34,7 @@ Perf::Trace::Context - Perl extension for accessing functions in perf.
 
 =head1 SEE ALSO
 
-Perf (trace) documentation
+Perf (script) documentation
 
 =head1 AUTHOR
 
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
index 9df376a9f629..9158458d3eeb 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Core.pm
@@ -163,7 +163,7 @@ sub dump_symbolic_fields
 __END__
 =head1 NAME
 
-Perf::Trace::Core - Perl extension for perf trace
+Perf::Trace::Core - Perl extension for perf script
 
 =head1 SYNOPSIS
 
@@ -171,7 +171,7 @@ Perf::Trace::Core - Perl extension for perf trace
 
 =head1 SEE ALSO
 
-Perf (trace) documentation
+Perf (script) documentation
 
 =head1 AUTHOR
 
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
index d94b40c8ac85..053500114625 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
@@ -65,7 +65,7 @@ sub clear_term
 __END__
 =head1 NAME
 
-Perf::Trace::Util - Perl extension for perf trace
+Perf::Trace::Util - Perl extension for perf script
 
 =head1 SYNOPSIS
 
@@ -73,7 +73,7 @@ Perf::Trace::Util - Perl extension for perf trace
 
 =head1 SEE ALSO
 
-Perf (trace) documentation
+Perf (script) documentation
 
 =head1 AUTHOR
 
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index eb5846bcb565..8104895a7b67 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-report b/tools/perf/scripts/perl/bin/failed-syscalls-report
index e3a5e55d54ff..9f83cc1ad8ba 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-report
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
         shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/failed-syscalls.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record
index 5bfaae5a6cba..33efc8673aae 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-record
+++ b/tools/perf/scripts/perl/bin/rw-by-file-record
@@ -1,3 +1,3 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
 
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report
index d83070b7eeb5..77200b3f3100 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-report
+++ b/tools/perf/scripts/perl/bin/rw-by-file-report
@@ -7,7 +7,4 @@ if [ $# -lt 1 ] ; then
 fi
 comm=$1
 shift
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $comm
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-file.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record
index 6e0b2f7755ac..7cb9db230448 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-record
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report
index 7ef46983f62f..a27b9f311f95 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-report
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-report
@@ -1,6 +1,3 @@
 #!/bin/bash
 # description: system-wide r/w activity
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rw-by-pid.pl
diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
index 6e0b2f7755ac..7cb9db230448 100644
--- a/tools/perf/scripts/perl/bin/rwtop-record
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
+perf record -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report
index 93e698cd3f38..83e11ec2e190 100644
--- a/tools/perf/scripts/perl/bin/rwtop-report
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -17,7 +17,4 @@ if [ "$n_args" -gt 0 ] ; then
     interval=$1
     shift
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/rwtop.pl $interval
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/rwtop.pl $interval
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record
index 9f2acaaae9f0..464251a1bd7e 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-record
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-record
@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -a -e sched:sched_switch -e sched:sched_wakeup $@
+perf record -e sched:sched_switch -e sched:sched_wakeup $@
 
 
 
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report
index a0d898f9ca1d..889e8130cca5 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-report
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-report
@@ -1,6 +1,3 @@
 #!/bin/bash
 # description: system-wide min/max/avg wakeup latency
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/wakeup-latency.pl
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
index 85301f2471ff..8edda9078d5d 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
+perf record -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report
index 35081132ef97..6d91411d248c 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-report
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-report
@@ -1,7 +1,3 @@
 #!/bin/bash
 # description: workqueue stats (ins/exe/create/destroy)
-perf trace $@ -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
-
-
-
-
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/workqueue-stats.pl
diff --git a/tools/perf/scripts/perl/check-perf-trace.pl b/tools/perf/scripts/perl/check-perf-trace.pl
index 4e7dc0a407a5..4e7076c20616 100644
--- a/tools/perf/scripts/perl/check-perf-trace.pl
+++ b/tools/perf/scripts/perl/check-perf-trace.pl
@@ -1,4 +1,4 @@
-# perf trace event handlers, generated by perf trace -g perl
+# perf script event handlers, generated by perf script -g perl
 # (c) 2009, Tom Zanussi <tzanussi@gmail.com>
 # Licensed under the terms of the GNU GPL License version 2
 
diff --git a/tools/perf/scripts/perl/rw-by-file.pl b/tools/perf/scripts/perl/rw-by-file.pl
index 2a39097687b9..74844ee2be3e 100644
--- a/tools/perf/scripts/perl/rw-by-file.pl
+++ b/tools/perf/scripts/perl/rw-by-file.pl
@@ -18,7 +18,7 @@ use lib "./Perf-Trace-Util/lib";
 use Perf::Trace::Core;
 use Perf::Trace::Util;
 
-my $usage = "perf trace -s rw-by-file.pl <comm>\n";
+my $usage = "perf script -s rw-by-file.pl <comm>\n";
 
 my $for_comm = shift or die $usage;
 
diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl
index b84b12699b70..a8eaff5119e0 100644
--- a/tools/perf/scripts/perl/workqueue-stats.pl
+++ b/tools/perf/scripts/perl/workqueue-stats.pl
@@ -10,7 +10,7 @@
 #     workqueue:workqueue_destruction -e workqueue:workqueue_execution
 #     -e workqueue:workqueue_insertion
 #
-#   perf trace -p -s tools/perf/scripts/perl/workqueue-stats.pl
+#   perf script -p -s tools/perf/scripts/perl/workqueue-stats.pl
 
 use 5.010000;
 use strict;
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index 957085dd5d8d..315067b8f552 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -1,5 +1,5 @@
 /*
- * Context.c.  Python interfaces for perf trace.
+ * Context.c.  Python interfaces for perf script.
  *
  * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com>
  *
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index aad7525bca1d..de7211e4fa47 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -1,4 +1,4 @@
-# Core.py - Python extension for perf trace, core functions
+# Core.py - Python extension for perf script, core functions
 #
 # Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
 #
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index ae9a56e43e05..fdd92f699055 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -1,4 +1,4 @@
-# SchedGui.py - Python extension for perf trace, basic GUI code for
+# SchedGui.py - Python extension for perf script, basic GUI code for
 #               traces drawing and overview.
 #
 # Copyright (C) 2010 by Frederic Weisbecker <fweisbec@gmail.com>
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 9689bc0acd9f..15c8400240fd 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -1,4 +1,4 @@
-# Util.py - Python extension for perf trace, miscellaneous utility code
+# Util.py - Python extension for perf script, miscellaneous utility code
 #
 # Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
 #
@@ -6,6 +6,14 @@
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
 
+import errno, os
+
+FUTEX_WAIT = 0
+FUTEX_WAKE = 1
+FUTEX_PRIVATE_FLAG = 128
+FUTEX_CLOCK_REALTIME = 256
+FUTEX_CMD_MASK = ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
+
 NSECS_PER_SEC    = 1000000000
 
 def avg(total, n):
@@ -24,5 +32,55 @@ def nsecs_str(nsecs):
     str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
     return str
 
+def add_stats(dict, key, value):
+        if not dict.has_key(key):
+                dict[key] = (value, value, value, 1)
+        else:
+                min, max, avg, count = dict[key]
+                if value < min:
+                        min = value
+                if value > max:
+                        max = value
+                avg = (avg + value) / 2
+                dict[key] = (min, max, avg, count + 1)
+
 def clear_term():
     print("\x1b[H\x1b[2J")
+
+audit_package_warned = False
+
+try:
+        import audit
+        machine_to_id = {
+                'x86_64': audit.MACH_86_64,
+                'alpha' : audit.MACH_ALPHA,
+                'ia64'  : audit.MACH_IA64,
+                'ppc'   : audit.MACH_PPC,
+                'ppc64' : audit.MACH_PPC64,
+                's390'  : audit.MACH_S390,
+                's390x' : audit.MACH_S390X,
+                'i386'  : audit.MACH_X86,
+                'i586'  : audit.MACH_X86,
+                'i686'  : audit.MACH_X86,
+        }
+        try:
+                machine_to_id['armeb'] = audit.MACH_ARMEB
+        except:
+                pass
+        machine_id = machine_to_id[os.uname()[4]]
+except:
+        if not audit_package_warned:
+                audit_package_warned = True
+                print "Install the audit-libs-python package to get syscall names"
+
+def syscall_name(id):
+        try:
+                return audit.audit_syscall_to_name(id, machine_id)
+        except:
+                return str(id)
+
+def strerror(nr):
+        try:
+                return errno.errorcode[abs(nr)]
+        except:
+                return "Unknown %d errno" % nr
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index eb5846bcb565..8104895a7b67 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_exit $@
+perf record -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
index 30293545fcc2..fda5096d0cbf 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
         shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/failed-syscalls-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/futex-contention-record b/tools/perf/scripts/python/bin/futex-contention-record
new file mode 100644
index 000000000000..b1495c9a9b20
--- /dev/null
+++ b/tools/perf/scripts/python/bin/futex-contention-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
diff --git a/tools/perf/scripts/python/bin/futex-contention-report b/tools/perf/scripts/python/bin/futex-contention-report
new file mode 100644
index 000000000000..6c44271091ab
--- /dev/null
+++ b/tools/perf/scripts/python/bin/futex-contention-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: futext contention measurement
+
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py
diff --git a/tools/perf/scripts/python/bin/netdev-times-record b/tools/perf/scripts/python/bin/netdev-times-record
new file mode 100644
index 000000000000..558754b840a9
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+perf record -e net:net_dev_xmit -e net:net_dev_queue            \
+                -e net:netif_receive_skb -e net:netif_rx                \
+                -e skb:consume_skb -e skb:kfree_skb                     \
+                -e skb:skb_copy_datagram_iovec -e napi:napi_poll        \
+                -e irq:irq_handler_entry -e irq:irq_handler_exit        \
+                -e irq:softirq_entry -e irq:softirq_exit                \
+                -e irq:softirq_raise $@
diff --git a/tools/perf/scripts/python/bin/netdev-times-report b/tools/perf/scripts/python/bin/netdev-times-report
new file mode 100644
index 000000000000..8f759291da86
--- /dev/null
+++ b/tools/perf/scripts/python/bin/netdev-times-report
@@ -0,0 +1,5 @@
+#!/bin/bash
+# description: display a process of packet and processing time
+# args: [tx] [rx] [dev=] [debug]
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/netdev-times.py $@
diff --git a/tools/perf/scripts/python/bin/sched-migration-record b/tools/perf/scripts/python/bin/sched-migration-record
index 17a3e9bd9e8f..7493fddbe995 100644
--- a/tools/perf/scripts/python/bin/sched-migration-record
+++ b/tools/perf/scripts/python/bin/sched-migration-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -m 16384 -a -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
+perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@
diff --git a/tools/perf/scripts/python/bin/sched-migration-report b/tools/perf/scripts/python/bin/sched-migration-report
index 61d05f72e443..68b037a1849b 100644
--- a/tools/perf/scripts/python/bin/sched-migration-report
+++ b/tools/perf/scripts/python/bin/sched-migration-report
@@ -1,3 +1,3 @@
 #!/bin/bash
 # description: sched migration overview
-perf trace $@ -s ~/libexec/perf-core/scripts/python/sched-migration.py
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sched-migration.py
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
index 1fc5998b721d..4efbfaa7f6a5 100644
--- a/tools/perf/scripts/python/bin/sctop-record
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report
index b01c842ae7b4..c32db294124d 100644
--- a/tools/perf/scripts/python/bin/sctop-report
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -21,4 +21,4 @@ elif [ "$n_args" -gt 0 ] ; then
     interval=$1
     shift
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/sctop.py $comm $interval
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sctop.py $comm $interval
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 1fc5998b721d..4efbfaa7f6a5 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
index 9e9d8ddd72ce..16eb8d65c543 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
         shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 1fc5998b721d..4efbfaa7f6a5 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e raw_syscalls:sys_enter $@
+perf record -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report
index dc076b618796..0f0e9d453bb4 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-report
@@ -7,4 +7,4 @@ if [ $# -gt 0 ] ; then
         shift
     fi
 fi
-perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts.py $comm
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts.py $comm
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index d9f7893e315c..4647a7694cf6 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -1,4 +1,4 @@
-# perf trace event handlers, generated by perf trace -g python
+# perf script event handlers, generated by perf script -g python
 # (c) 2010, Tom Zanussi <tzanussi@gmail.com>
 # Licensed under the terms of the GNU GPL License version 2
 #
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
index 0ca02278fe69..85805fac4116 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -13,21 +13,26 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 
 from perf_trace_context import *
 from Core import *
+from Util import *
 
-usage = "perf trace -s syscall-counts-by-pid.py [comm]\n";
+usage = "perf script -s syscall-counts-by-pid.py [comm|pid]\n";
 
 for_comm = None
+for_pid = None
 
 if len(sys.argv) > 2:
         sys.exit(usage)
 
 if len(sys.argv) > 1:
-        for_comm = sys.argv[1]
+        try:
+                for_pid = int(sys.argv[1])
+        except:
+                for_comm = sys.argv[1]
 
 syscalls = autodict()
 
 def trace_begin():
-        pass
+        print "Press control+C to stop and show the summary"
 
 def trace_end():
         print_error_totals()
@@ -35,9 +40,9 @@ def trace_end():
 def raw_syscalls__sys_exit(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
         id, ret):
-        if for_comm is not None:
-                if common_comm != for_comm:
-                        return
+        if (for_comm and common_comm != for_comm) or \
+           (for_pid  and common_pid  != for_pid ):
+                return
 
         if ret < 0:
                 try:
@@ -62,7 +67,7 @@ def print_error_totals():
                     print "\n%s [%d]\n" % (comm, pid),
                     id_keys = syscalls[comm][pid].keys()
                     for id in id_keys:
-                            print "  syscall: %-16d\n" % (id),
+                            print "  syscall: %-16s\n" % syscall_name(id),
                             ret_keys = syscalls[comm][pid][id].keys()
                             for ret, val in sorted(syscalls[comm][pid][id].iteritems(), key = lambda(k, v): (v, k),  reverse = True):
-                                    print "    err = %-20d  %10d\n" % (ret, val),
+                                    print "    err = %-20s  %10d\n" % (strerror(ret), val),
diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py
new file mode 100644
index 000000000000..11e70a388d41
--- /dev/null
+++ b/tools/perf/scripts/python/futex-contention.py
@@ -0,0 +1,50 @@
+# futex contention
+# (c) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Translation of:
+#
+# http://sourceware.org/systemtap/wiki/WSFutexContention
+#
+# to perf python scripting.
+#
+# Measures futex contention
+
+import os, sys
+sys.path.append(os.environ['PERF_EXEC_PATH'] + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+from Util import *
+
+process_names = {}
+thread_thislock = {}
+thread_blocktime = {}
+
+lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time
+process_names = {} # long-lived pid-to-execname mapping
+
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
+                              nr, uaddr, op, val, utime, uaddr2, val3):
+        cmd = op & FUTEX_CMD_MASK
+        if cmd != FUTEX_WAIT:
+                return # we don't care about originators of WAKE events
+
+        process_names[tid] = comm
+        thread_thislock[tid] = uaddr
+        thread_blocktime[tid] = nsecs(s, ns)
+
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm,
+                             nr, ret):
+        if thread_blocktime.has_key(tid):
+                elapsed = nsecs(s, ns) - thread_blocktime[tid]
+                add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed)
+                del thread_blocktime[tid]
+                del thread_thislock[tid]
+
+def trace_begin():
+        print "Press control+C to stop and show the summary"
+
+def trace_end():
+        for (tid, lock) in lock_waits:
+                min, max, avg, count = lock_waits[tid, lock]
+                print "%s[%d] lock %x contended %d times, %d avg ns" % \
+                      (process_names[tid], tid, lock, count, avg)
+
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
new file mode 100644
index 000000000000..9aa0a32972e8
--- /dev/null
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -0,0 +1,464 @@
+# Display a process of packets and processed time.
+# It helps us to investigate networking or network device.
+#
+# options
+# tx: show only tx chart
+# rx: show only rx chart
+# dev=: show only thing related to specified device
+# debug: work with debug mode. It shows buffer status.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+all_event_list = []; # insert all tracepoint event related with this script
+irq_dic = {}; # key is cpu and value is a list which stacks irqs
+              # which raise NET_RX softirq
+net_rx_dic = {}; # key is cpu and value include time of NET_RX softirq-entry
+                 # and a list which stacks receive
+receive_hunk_list = []; # a list which include a sequence of receive events
+rx_skb_list = []; # received packet list for matching
+                       # skb_copy_datagram_iovec
+
+buffer_budget = 65536; # the budget of rx_skb_list, tx_queue_list and
+                       # tx_xmit_list
+of_count_rx_skb_list = 0; # overflow count
+
+tx_queue_list = []; # list of packets which pass through dev_queue_xmit
+of_count_tx_queue_list = 0; # overflow count
+
+tx_xmit_list = [];  # list of packets which pass through dev_hard_start_xmit
+of_count_tx_xmit_list = 0; # overflow count
+
+tx_free_list = [];  # list of packets which is freed
+
+# options
+show_tx = 0;
+show_rx = 0;
+dev = 0; # store a name of device specified by option "dev="
+debug = 0;
+
+# indices of event_info tuple
+EINFO_IDX_NAME=   0
+EINFO_IDX_CONTEXT=1
+EINFO_IDX_CPU=    2
+EINFO_IDX_TIME=   3
+EINFO_IDX_PID=    4
+EINFO_IDX_COMM=   5
+
+# Calculate a time interval(msec) from src(nsec) to dst(nsec)
+def diff_msec(src, dst):
+        return (dst - src) / 1000000.0
+
+# Display a process of transmitting a packet
+def print_transmit(hunk):
+        if dev != 0 and hunk['dev'].find(dev) < 0:
+                return
+        print "%7s %5d %6d.%06dsec %12.3fmsec      %12.3fmsec" % \
+                (hunk['dev'], hunk['len'],
+                nsecs_secs(hunk['queue_t']),
+                nsecs_nsecs(hunk['queue_t'])/1000,
+                diff_msec(hunk['queue_t'], hunk['xmit_t']),
+                diff_msec(hunk['xmit_t'], hunk['free_t']))
+
+# Format for displaying rx packet processing
+PF_IRQ_ENTRY= "  irq_entry(+%.3fmsec irq=%d:%s)"
+PF_SOFT_ENTRY="  softirq_entry(+%.3fmsec)"
+PF_NAPI_POLL= "  napi_poll_exit(+%.3fmsec %s)"
+PF_JOINT=     "         |"
+PF_WJOINT=    "         |            |"
+PF_NET_RECV=  "         |---netif_receive_skb(+%.3fmsec skb=%x len=%d)"
+PF_NET_RX=    "         |---netif_rx(+%.3fmsec skb=%x)"
+PF_CPY_DGRAM= "         |      skb_copy_datagram_iovec(+%.3fmsec %d:%s)"
+PF_KFREE_SKB= "         |      kfree_skb(+%.3fmsec location=%x)"
+PF_CONS_SKB=  "         |      consume_skb(+%.3fmsec)"
+
+# Display a process of received packets and interrputs associated with
+# a NET_RX softirq
+def print_receive(hunk):
+        show_hunk = 0
+        irq_list = hunk['irq_list']
+        cpu = irq_list[0]['cpu']
+        base_t = irq_list[0]['irq_ent_t']
+        # check if this hunk should be showed
+        if dev != 0:
+                for i in range(len(irq_list)):
+                        if irq_list[i]['name'].find(dev) >= 0:
+                                show_hunk = 1
+                                break
+        else:
+                show_hunk = 1
+        if show_hunk == 0:
+                return
+
+        print "%d.%06dsec cpu=%d" % \
+                (nsecs_secs(base_t), nsecs_nsecs(base_t)/1000, cpu)
+        for i in range(len(irq_list)):
+                print PF_IRQ_ENTRY % \
+                        (diff_msec(base_t, irq_list[i]['irq_ent_t']),
+                        irq_list[i]['irq'], irq_list[i]['name'])
+                print PF_JOINT
+                irq_event_list = irq_list[i]['event_list']
+                for j in range(len(irq_event_list)):
+                        irq_event = irq_event_list[j]
+                        if irq_event['event'] == 'netif_rx':
+                                print PF_NET_RX % \
+                                        (diff_msec(base_t, irq_event['time']),
+                                        irq_event['skbaddr'])
+                                print PF_JOINT
+        print PF_SOFT_ENTRY % \
+                diff_msec(base_t, hunk['sirq_ent_t'])
+        print PF_JOINT
+        event_list = hunk['event_list']
+        for i in range(len(event_list)):
+                event = event_list[i]
+                if event['event_name'] == 'napi_poll':
+                        print PF_NAPI_POLL % \
+                            (diff_msec(base_t, event['event_t']), event['dev'])
+                        if i == len(event_list) - 1:
+                                print ""
+                        else:
+                                print PF_JOINT
+                else:
+                        print PF_NET_RECV % \
+                            (diff_msec(base_t, event['event_t']), event['skbaddr'],
+                                event['len'])
+                        if 'comm' in event.keys():
+                                print PF_WJOINT
+                                print PF_CPY_DGRAM % \
+                                        (diff_msec(base_t, event['comm_t']),
+                                        event['pid'], event['comm'])
+                        elif 'handle' in event.keys():
+                                print PF_WJOINT
+                                if event['handle'] == "kfree_skb":
+                                        print PF_KFREE_SKB % \
+                                                (diff_msec(base_t,
+                                                event['comm_t']),
+                                                event['location'])
+                                elif event['handle'] == "consume_skb":
+                                        print PF_CONS_SKB % \
+                                                diff_msec(base_t,
+                                                        event['comm_t'])
+                        print PF_JOINT
+
+def trace_begin():
+        global show_tx
+        global show_rx
+        global dev
+        global debug
+
+        for i in range(len(sys.argv)):
+                if i == 0:
+                        continue
+                arg = sys.argv[i]
+                if arg == 'tx':
+                        show_tx = 1
+                elif arg =='rx':
+                        show_rx = 1
+                elif arg.find('dev=',0, 4) >= 0:
+                        dev = arg[4:]
+                elif arg == 'debug':
+                        debug = 1
+        if show_tx == 0  and show_rx == 0:
+                show_tx = 1
+                show_rx = 1
+
+def trace_end():
+        # order all events in time
+        all_event_list.sort(lambda a,b :cmp(a[EINFO_IDX_TIME],
+                                            b[EINFO_IDX_TIME]))
+        # process all events
+        for i in range(len(all_event_list)):
+                event_info = all_event_list[i]
+                name = event_info[EINFO_IDX_NAME]
+                if name == 'irq__softirq_exit':
+                        handle_irq_softirq_exit(event_info)
+                elif name == 'irq__softirq_entry':
+                        handle_irq_softirq_entry(event_info)
+                elif name == 'irq__softirq_raise':
+                        handle_irq_softirq_raise(event_info)
+                elif name == 'irq__irq_handler_entry':
+                        handle_irq_handler_entry(event_info)
+                elif name == 'irq__irq_handler_exit':
+                        handle_irq_handler_exit(event_info)
+                elif name == 'napi__napi_poll':
+                        handle_napi_poll(event_info)
+                elif name == 'net__netif_receive_skb':
+                        handle_netif_receive_skb(event_info)
+                elif name == 'net__netif_rx':
+                        handle_netif_rx(event_info)
+                elif name == 'skb__skb_copy_datagram_iovec':
+                        handle_skb_copy_datagram_iovec(event_info)
+                elif name == 'net__net_dev_queue':
+                        handle_net_dev_queue(event_info)
+                elif name == 'net__net_dev_xmit':
+                        handle_net_dev_xmit(event_info)
+                elif name == 'skb__kfree_skb':
+                        handle_kfree_skb(event_info)
+                elif name == 'skb__consume_skb':
+                        handle_consume_skb(event_info)
+        # display receive hunks
+        if show_rx:
+                for i in range(len(receive_hunk_list)):
+                        print_receive(receive_hunk_list[i])
+        # display transmit hunks
+        if show_tx:
+                print "   dev    len      Qdisc        " \
+                        "       netdevice             free"
+                for i in range(len(tx_free_list)):
+                        print_transmit(tx_free_list[i])
+        if debug:
+                print "debug buffer status"
+                print "----------------------------"
+                print "xmit Qdisc:remain:%d overflow:%d" % \
+                        (len(tx_queue_list), of_count_tx_queue_list)
+                print "xmit netdevice:remain:%d overflow:%d" % \
+                        (len(tx_xmit_list), of_count_tx_xmit_list)
+                print "receive:remain:%d overflow:%d" % \
+                        (len(rx_skb_list), of_count_rx_skb_list)
+
+# called from perf, when it finds a correspoinding event
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+        if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+                return
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+        all_event_list.append(event_info)
+
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+        if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+                return
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+        all_event_list.append(event_info)
+
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+        if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
+                return
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
+        all_event_list.append(event_info)
+
+def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
+                        irq, irq_name):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        irq, irq_name)
+        all_event_list.append(event_info)
+
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
+        all_event_list.append(event_info)
+
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        napi, dev_name)
+        all_event_list.append(event_info)
+
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+                        skblen, dev_name):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr, skblen, dev_name)
+        all_event_list.append(event_info)
+
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+                        skblen, dev_name):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr, skblen, dev_name)
+        all_event_list.append(event_info)
+
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+                        skbaddr, skblen, dev_name):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr, skblen, dev_name)
+        all_event_list.append(event_info)
+
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+                        skbaddr, skblen, rc, dev_name):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr, skblen, rc ,dev_name)
+        all_event_list.append(event_info)
+
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+                        skbaddr, protocol, location):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr, protocol, location)
+        all_event_list.append(event_info)
+
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr)
+        all_event_list.append(event_info)
+
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+        skbaddr, skblen):
+        event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
+                        skbaddr, skblen)
+        all_event_list.append(event_info)
+
+def handle_irq_handler_entry(event_info):
+        (name, context, cpu, time, pid, comm, irq, irq_name) = event_info
+        if cpu not in irq_dic.keys():
+                irq_dic[cpu] = []
+        irq_record = {'irq':irq, 'name':irq_name, 'cpu':cpu, 'irq_ent_t':time}
+        irq_dic[cpu].append(irq_record)
+
+def handle_irq_handler_exit(event_info):
+        (name, context, cpu, time, pid, comm, irq, ret) = event_info
+        if cpu not in irq_dic.keys():
+                return
+        irq_record = irq_dic[cpu].pop()
+        if irq != irq_record['irq']:
+                return
+        irq_record.update({'irq_ext_t':time})
+        # if an irq doesn't include NET_RX softirq, drop.
+        if 'event_list' in irq_record.keys():
+                irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_raise(event_info):
+        (name, context, cpu, time, pid, comm, vec) = event_info
+        if cpu not in irq_dic.keys() \
+        or len(irq_dic[cpu]) == 0:
+                return
+        irq_record = irq_dic[cpu].pop()
+        if 'event_list' in irq_record.keys():
+                irq_event_list = irq_record['event_list']
+        else:
+                irq_event_list = []
+        irq_event_list.append({'time':time, 'event':'sirq_raise'})
+        irq_record.update({'event_list':irq_event_list})
+        irq_dic[cpu].append(irq_record)
+
+def handle_irq_softirq_entry(event_info):
+        (name, context, cpu, time, pid, comm, vec) = event_info
+        net_rx_dic[cpu] = {'sirq_ent_t':time, 'event_list':[]}
+
+def handle_irq_softirq_exit(event_info):
+        (name, context, cpu, time, pid, comm, vec) = event_info
+        irq_list = []
+        event_list = 0
+        if cpu in irq_dic.keys():
+                irq_list = irq_dic[cpu]
+                del irq_dic[cpu]
+        if cpu in net_rx_dic.keys():
+                sirq_ent_t = net_rx_dic[cpu]['sirq_ent_t']
+                event_list = net_rx_dic[cpu]['event_list']
+                del net_rx_dic[cpu]
+        if irq_list == [] or event_list == 0:
+                return
+        rec_data = {'sirq_ent_t':sirq_ent_t, 'sirq_ext_t':time,
+                    'irq_list':irq_list, 'event_list':event_list}
+        # merge information realted to a NET_RX softirq
+        receive_hunk_list.append(rec_data)
+
+def handle_napi_poll(event_info):
+        (name, context, cpu, time, pid, comm, napi, dev_name) = event_info
+        if cpu in net_rx_dic.keys():
+                event_list = net_rx_dic[cpu]['event_list']
+                rec_data = {'event_name':'napi_poll',
+                                'dev':dev_name, 'event_t':time}
+                event_list.append(rec_data)
+
+def handle_netif_rx(event_info):
+        (name, context, cpu, time, pid, comm,
+                skbaddr, skblen, dev_name) = event_info
+        if cpu not in irq_dic.keys() \
+        or len(irq_dic[cpu]) == 0:
+                return
+        irq_record = irq_dic[cpu].pop()
+        if 'event_list' in irq_record.keys():
+                irq_event_list = irq_record['event_list']
+        else:
+                irq_event_list = []
+        irq_event_list.append({'time':time, 'event':'netif_rx',
+                'skbaddr':skbaddr, 'skblen':skblen, 'dev_name':dev_name})
+        irq_record.update({'event_list':irq_event_list})
+        irq_dic[cpu].append(irq_record)
+
+def handle_netif_receive_skb(event_info):
+        global of_count_rx_skb_list
+
+        (name, context, cpu, time, pid, comm,
+                skbaddr, skblen, dev_name) = event_info
+        if cpu in net_rx_dic.keys():
+                rec_data = {'event_name':'netif_receive_skb',
+                            'event_t':time, 'skbaddr':skbaddr, 'len':skblen}
+                event_list = net_rx_dic[cpu]['event_list']
+                event_list.append(rec_data)
+                rx_skb_list.insert(0, rec_data)
+                if len(rx_skb_list) > buffer_budget:
+                        rx_skb_list.pop()
+                        of_count_rx_skb_list += 1
+
+def handle_net_dev_queue(event_info):
+        global of_count_tx_queue_list
+
+        (name, context, cpu, time, pid, comm,
+                skbaddr, skblen, dev_name) = event_info
+        skb = {'dev':dev_name, 'skbaddr':skbaddr, 'len':skblen, 'queue_t':time}
+        tx_queue_list.insert(0, skb)
+        if len(tx_queue_list) > buffer_budget:
+                tx_queue_list.pop()
+                of_count_tx_queue_list += 1
+
+def handle_net_dev_xmit(event_info):
+        global of_count_tx_xmit_list
+
+        (name, context, cpu, time, pid, comm,
+                skbaddr, skblen, rc, dev_name) = event_info
+        if rc == 0: # NETDEV_TX_OK
+                for i in range(len(tx_queue_list)):
+                        skb = tx_queue_list[i]
+                        if skb['skbaddr'] == skbaddr:
+                                skb['xmit_t'] = time
+                                tx_xmit_list.insert(0, skb)
+                                del tx_queue_list[i]
+                                if len(tx_xmit_list) > buffer_budget:
+                                        tx_xmit_list.pop()
+                                        of_count_tx_xmit_list += 1
+                                return
+
+def handle_kfree_skb(event_info):
+        (name, context, cpu, time, pid, comm,
+                skbaddr, protocol, location) = event_info
+        for i in range(len(tx_queue_list)):
+                skb = tx_queue_list[i]
+                if skb['skbaddr'] == skbaddr:
+                        del tx_queue_list[i]
+                        return
+        for i in range(len(tx_xmit_list)):
+                skb = tx_xmit_list[i]
+                if skb['skbaddr'] == skbaddr:
+                        skb['free_t'] = time
+                        tx_free_list.append(skb)
+                        del tx_xmit_list[i]
+                        return
+        for i in range(len(rx_skb_list)):
+                rec_data = rx_skb_list[i]
+                if rec_data['skbaddr'] == skbaddr:
+                        rec_data.update({'handle':"kfree_skb",
+                                        'comm':comm, 'pid':pid, 'comm_t':time})
+                        del rx_skb_list[i]
+                        return
+
+def handle_consume_skb(event_info):
+        (name, context, cpu, time, pid, comm, skbaddr) = event_info
+        for i in range(len(tx_xmit_list)):
+                skb = tx_xmit_list[i]
+                if skb['skbaddr'] == skbaddr:
+                        skb['free_t'] = time
+                        tx_free_list.append(skb)
+                        del tx_xmit_list[i]
+                        return
+
+def handle_skb_copy_datagram_iovec(event_info):
+        (name, context, cpu, time, pid, comm, skbaddr, skblen) = event_info
+        for i in range(len(rx_skb_list)):
+                rec_data = rx_skb_list[i]
+                if skbaddr == rec_data['skbaddr']:
+                        rec_data.update({'handle':"skb_copy_datagram_iovec",
+                                        'comm':comm, 'pid':pid, 'comm_t':time})
+                        del rx_skb_list[i]
+                        return
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index b934383c3364..74d55ec08aed 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -4,7 +4,7 @@
 #
 # Copyright (C) 2010 Frederic Weisbecker <fweisbec@gmail.com>
 #
-# perf trace event handlers have been generated by perf trace -g python
+# perf script event handlers have been generated by perf script -g python
 #
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
index 6cafad40c296..42c267e292fa 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -8,10 +8,7 @@
 # will be refreshed every [interval] seconds.  The default interval is
 # 3 seconds.
 
-import thread
-import time
-import os
-import sys
+import os, sys, thread, time
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
         '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -20,7 +17,7 @@ from perf_trace_context import *
 from Core import *
 from Util import *
 
-usage = "perf trace -s syscall-counts.py [comm] [interval]\n";
+usage = "perf script -s sctop.py [comm] [interval]\n";
 
 for_comm = None
 default_interval = 3
@@ -71,7 +68,7 @@ def print_syscall_totals(interval):
                 for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
                                               reverse = True):
                         try:
-                                print "%-40d  %10d\n" % (id, val),
+                                print "%-40s  %10d\n" % (syscall_name(id), val),
                         except TypeError:
                                 pass
                 syscalls.clear()
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index af722d6a4b3f..c64d1c55d745 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -5,29 +5,33 @@
 # Displays system-wide system call totals, broken down by syscall.
 # If a [comm] arg is specified, only syscalls called by [comm] are displayed.
 
-import os
-import sys
+import os, sys
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
         '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
 
 from perf_trace_context import *
 from Core import *
+from Util import syscall_name
 
-usage = "perf trace -s syscall-counts-by-pid.py [comm]\n";
+usage = "perf script -s syscall-counts-by-pid.py [comm]\n";
 
 for_comm = None
+for_pid = None
 
 if len(sys.argv) > 2:
         sys.exit(usage)
 
 if len(sys.argv) > 1:
-        for_comm = sys.argv[1]
+        try:
+                for_pid = int(sys.argv[1])
+        except:
+                for_comm = sys.argv[1]
 
 syscalls = autodict()
 
 def trace_begin():
-        pass
+        print "Press control+C to stop and show the summary"
 
 def trace_end():
         print_syscall_totals()
@@ -35,9 +39,10 @@ def trace_end():
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
         common_secs, common_nsecs, common_pid, common_comm,
         id, args):
-        if for_comm is not None:
-                if common_comm != for_comm:
-                        return
+
+        if (for_comm and common_comm != for_comm) or \
+           (for_pid  and common_pid  != for_pid ):
+                return
         try:
                 syscalls[common_comm][common_pid][id] += 1
         except TypeError:
@@ -61,4 +66,4 @@ def print_syscall_totals():
                     id_keys = syscalls[comm][pid].keys()
                     for id, val in sorted(syscalls[comm][pid].iteritems(), \
                                   key = lambda(k, v): (v, k),  reverse = True):
-                            print "  %-38d  %10d\n" % (id, val),
+                            print "  %-38s  %10d\n" % (syscall_name(id), val),
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index f977e85ff049..b435d3f188e8 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -13,8 +13,9 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 
 from perf_trace_context import *
 from Core import *
+from Util import syscall_name
 
-usage = "perf trace -s syscall-counts.py [comm]\n";
+usage = "perf script -s syscall-counts.py [comm]\n";
 
 for_comm = None
 
@@ -27,7 +28,7 @@ if len(sys.argv) > 1:
 syscalls = autodict()
 
 def trace_begin():
-        pass
+        print "Press control+C to stop and show the summary"
 
 def trace_end():
         print_syscall_totals()
@@ -55,4 +56,4 @@ def print_syscall_totals():
 
     for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
                                   reverse = True):
-            print "%-40d  %10d\n" % (id, val),
+            print "%-40s  %10d\n" % (syscall_name(id), val),
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 97d76562a1a0..ad73300f7bac 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -23,12 +23,7 @@ if test -d ../../.git -o -f ../../.git &&
 then
         VN=$(echo "$VN" | sed -e 's/-/./g');
 else
-        eval `grep '^VERSION\s*=' ../../Makefile|tr -d ' '`
-        eval `grep '^PATCHLEVEL\s*=' ../../Makefile|tr -d ' '`
-        eval `grep '^SUBLEVEL\s*=' ../../Makefile|tr -d ' '`
-        eval `grep '^EXTRAVERSION\s*=' ../../Makefile|tr -d ' '`
-
-        VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}"
+        VN=$(MAKEFLAGS= make -sC ../.. kernelversion)
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
new file mode 100644
index 000000000000..e01af2b1a469
--- /dev/null
+++ b/tools/perf/util/annotate.c
@@ -0,0 +1,605 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-annotate.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "util.h"
+#include "build-id.h"
+#include "color.h"
+#include "cache.h"
+#include "symbol.h"
+#include "debug.h"
+#include "annotate.h"
+#include <pthread.h>
+
+int symbol__annotate_init(struct map *map __used, struct symbol *sym)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        pthread_mutex_init(&notes->lock, NULL);
+        return 0;
+}
+
+int symbol__alloc_hist(struct symbol *sym, int nevents)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        size_t sizeof_sym_hist = (sizeof(struct sym_hist) +
+                                  (sym->end - sym->start) * sizeof(u64));
+
+        notes->src = zalloc(sizeof(*notes->src) + nevents * sizeof_sym_hist);
+        if (notes->src == NULL)
+                return -1;
+        notes->src->sizeof_sym_hist = sizeof_sym_hist;
+        notes->src->nr_histograms   = nevents;
+        INIT_LIST_HEAD(&notes->src->source);
+        return 0;
+}
+
+void symbol__annotate_zero_histograms(struct symbol *sym)
+{
+        struct annotation *notes = symbol__annotation(sym);
+
+        pthread_mutex_lock(&notes->lock);
+        if (notes->src != NULL)
+                memset(notes->src->histograms, 0,
+                       notes->src->nr_histograms * notes->src->sizeof_sym_hist);
+        pthread_mutex_unlock(&notes->lock);
+}
+
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+                             int evidx, u64 addr)
+{
+        unsigned offset;
+        struct annotation *notes;
+        struct sym_hist *h;
+
+        notes = symbol__annotation(sym);
+        if (notes->src == NULL)
+                return -ENOMEM;
+
+        pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
+
+        if (addr >= sym->end)
+                return 0;
+
+        offset = addr - sym->start;
+        h = annotation__histogram(notes, evidx);
+        h->sum++;
+        h->addr[offset]++;
+
+        pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64
+                  ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name,
+                  addr, addr - sym->start, evidx, h->addr[offset]);
+        return 0;
+}
+
+static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize)
+{
+        struct objdump_line *self = malloc(sizeof(*self) + privsize);
+
+        if (self != NULL) {
+                self->offset = offset;
+                self->line = line;
+        }
+
+        return self;
+}
+
+void objdump_line__free(struct objdump_line *self)
+{
+        free(self->line);
+        free(self);
+}
+
+static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+{
+        list_add_tail(&line->node, head);
+}
+
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+                                               struct objdump_line *pos)
+{
+        list_for_each_entry_continue(pos, head, node)
+                if (pos->offset >= 0)
+                        return pos;
+
+        return NULL;
+}
+
+static int objdump_line__print(struct objdump_line *oline, struct symbol *sym,
+                               int evidx, u64 len, int min_pcnt,
+                               int printed, int max_lines,
+                               struct objdump_line *queue)
+{
+        static const char *prev_line;
+        static const char *prev_color;
+
+        if (oline->offset != -1) {
+                const char *path = NULL;
+                unsigned int hits = 0;
+                double percent = 0.0;
+                const char *color;
+                struct annotation *notes = symbol__annotation(sym);
+                struct source_line *src_line = notes->src->lines;
+                struct sym_hist *h = annotation__histogram(notes, evidx);
+                s64 offset = oline->offset;
+                struct objdump_line *next;
+
+                next = objdump__get_next_ip_line(&notes->src->source, oline);
+
+                while (offset < (s64)len &&
+                       (next == NULL || offset < next->offset)) {
+                        if (src_line) {
+                                if (path == NULL)
+                                        path = src_line[offset].path;
+                                percent += src_line[offset].percent;
+                        } else
+                                hits += h->addr[offset];
+
+                        ++offset;
+                }
+
+                if (src_line == NULL && h->sum)
+                        percent = 100.0 * hits / h->sum;
+
+                if (percent < min_pcnt)
+                        return -1;
+
+                if (max_lines && printed >= max_lines)
+                        return 1;
+
+                if (queue != NULL) {
+                        list_for_each_entry_from(queue, &notes->src->source, node) {
+                                if (queue == oline)
+                                        break;
+                                objdump_line__print(queue, sym, evidx, len,
+                                                    0, 0, 1, NULL);
+                        }
+                }
+
+                color = get_percent_color(percent);
+
+                /*
+                 * Also color the filename and line if needed, with
+                 * the same color than the percentage. Don't print it
+                 * twice for close colored addr with the same filename:line
+                 */
+                if (path) {
+                        if (!prev_line || strcmp(prev_line, path)
+                                       || color != prev_color) {
+                                color_fprintf(stdout, color, " %s", path);
+                                prev_line = path;
+                                prev_color = color;
+                        }
+                }
+
+                color_fprintf(stdout, color, " %7.2f", percent);
+                printf(" :      ");
+                color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", oline->line);
+        } else if (max_lines && printed >= max_lines)
+                return 1;
+        else {
+                if (queue)
+                        return -1;
+
+                if (!*oline->line)
+                        printf("         :\n");
+                else
+                        printf("         :      %s\n", oline->line);
+        }
+
+        return 0;
+}
+
+static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
+                                      FILE *file, size_t privsize)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct objdump_line *objdump_line;
+        char *line = NULL, *tmp, *tmp2, *c;
+        size_t line_len;
+        s64 line_ip, offset = -1;
+
+        if (getline(&line, &line_len, file) < 0)
+                return -1;
+
+        if (!line)
+                return -1;
+
+        while (line_len != 0 && isspace(line[line_len - 1]))
+                line[--line_len] = '\0';
+
+        c = strchr(line, '\n');
+        if (c)
+                *c = 0;
+
+        line_ip = -1;
+
+        /*
+         * Strip leading spaces:
+         */
+        tmp = line;
+        while (*tmp) {
+                if (*tmp != ' ')
+                        break;
+                tmp++;
+        }
+
+        if (*tmp) {
+                /*
+                 * Parse hexa addresses followed by ':'
+                 */
+                line_ip = strtoull(tmp, &tmp2, 16);
+                if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
+                        line_ip = -1;
+        }
+
+        if (line_ip != -1) {
+                u64 start = map__rip_2objdump(map, sym->start),
+                    end = map__rip_2objdump(map, sym->end);
+
+                offset = line_ip - start;
+                if (offset < 0 || (u64)line_ip > end)
+                        offset = -1;
+        }
+
+        objdump_line = objdump_line__new(offset, line, privsize);
+        if (objdump_line == NULL) {
+                free(line);
+                return -1;
+        }
+        objdump__add_line(&notes->src->source, objdump_line);
+
+        return 0;
+}
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+{
+        struct dso *dso = map->dso;
+        char *filename = dso__build_id_filename(dso, NULL, 0);
+        bool free_filename = true;
+        char command[PATH_MAX * 2];
+        FILE *file;
+        int err = 0;
+        char symfs_filename[PATH_MAX];
+
+        if (filename) {
+                snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+                         symbol_conf.symfs, filename);
+        }
+
+        if (filename == NULL) {
+                if (dso->has_build_id) {
+                        pr_err("Can't annotate %s: not enough memory\n",
+                               sym->name);
+                        return -ENOMEM;
+                }
+                goto fallback;
+        } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
+                   strstr(command, "[kernel.kallsyms]") ||
+                   access(symfs_filename, R_OK)) {
+                free(filename);
+fallback:
+                /*
+                 * If we don't have build-ids or the build-id file isn't in the
+                 * cache, or is just a kallsyms file, well, lets hope that this
+                 * DSO is the same as when 'perf record' ran.
+                 */
+                filename = dso->long_name;
+                snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
+                         symbol_conf.symfs, filename);
+                free_filename = false;
+        }
+
+        if (dso->symtab_type == SYMTAB__KALLSYMS) {
+                char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
+                char *build_id_msg = NULL;
+
+                if (dso->annotate_warned)
+                        goto out_free_filename;
+
+                if (dso->has_build_id) {
+                        build_id__sprintf(dso->build_id,
+                                          sizeof(dso->build_id), bf + 15);
+                        build_id_msg = bf;
+                }
+                err = -ENOENT;
+                dso->annotate_warned = 1;
+                pr_err("Can't annotate %s: No vmlinux file%s was found in the "
+                       "path.\nPlease use 'perf buildid-cache -av vmlinux' or "
+                       "--vmlinux vmlinux.\n",
+                       sym->name, build_id_msg ?: "");
+                goto out_free_filename;
+        }
+
+        pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+                 filename, sym->name, map->unmap_ip(map, sym->start),
+                 map->unmap_ip(map, sym->end));
+
+        pr_debug("annotating [%p] %30s : [%p] %30s\n",
+                 dso, dso->long_name, sym, sym->name);
+
+        snprintf(command, sizeof(command),
+                 "objdump --start-address=0x%016" PRIx64
+                 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand",
+                 map__rip_2objdump(map, sym->start),
+                 map__rip_2objdump(map, sym->end),
+                 symfs_filename, filename);
+
+        pr_debug("Executing: %s\n", command);
+
+        file = popen(command, "r");
+        if (!file)
+                goto out_free_filename;
+
+        while (!feof(file))
+                if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
+                        break;
+
+        pclose(file);
+out_free_filename:
+        if (free_filename)
+                free(filename);
+        return err;
+}
+
+static void insert_source_line(struct rb_root *root, struct source_line *src_line)
+{
+        struct source_line *iter;
+        struct rb_node **p = &root->rb_node;
+        struct rb_node *parent = NULL;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct source_line, node);
+
+                if (src_line->percent > iter->percent)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+
+        rb_link_node(&src_line->node, parent, p);
+        rb_insert_color(&src_line->node, root);
+}
+
+static void symbol__free_source_line(struct symbol *sym, int len)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct source_line *src_line = notes->src->lines;
+        int i;
+
+        for (i = 0; i < len; i++)
+                free(src_line[i].path);
+
+        free(src_line);
+        notes->src->lines = NULL;
+}
+
+/* Get the filename:line for the colored entries */
+static int symbol__get_source_line(struct symbol *sym, struct map *map,
+                                   int evidx, struct rb_root *root, int len,
+                                   const char *filename)
+{
+        u64 start;
+        int i;
+        char cmd[PATH_MAX * 2];
+        struct source_line *src_line;
+        struct annotation *notes = symbol__annotation(sym);
+        struct sym_hist *h = annotation__histogram(notes, evidx);
+
+        if (!h->sum)
+                return 0;
+
+        src_line = notes->src->lines = calloc(len, sizeof(struct source_line));
+        if (!notes->src->lines)
+                return -1;
+
+        start = map->unmap_ip(map, sym->start);
+
+        for (i = 0; i < len; i++) {
+                char *path = NULL;
+                size_t line_len;
+                u64 offset;
+                FILE *fp;
+
+                src_line[i].percent = 100.0 * h->addr[i] / h->sum;
+                if (src_line[i].percent <= 0.5)
+                        continue;
+
+                offset = start + i;
+                sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
+                fp = popen(cmd, "r");
+                if (!fp)
+                        continue;
+
+                if (getline(&path, &line_len, fp) < 0 || !line_len)
+                        goto next;
+
+                src_line[i].path = malloc(sizeof(char) * line_len + 1);
+                if (!src_line[i].path)
+                        goto next;
+
+                strcpy(src_line[i].path, path);
+                insert_source_line(root, &src_line[i]);
+
+        next:
+                pclose(fp);
+        }
+
+        return 0;
+}
+
+static void print_summary(struct rb_root *root, const char *filename)
+{
+        struct source_line *src_line;
+        struct rb_node *node;
+
+        printf("\nSorted summary for file %s\n", filename);
+        printf("----------------------------------------------\n\n");
+
+        if (RB_EMPTY_ROOT(root)) {
+                printf(" Nothing higher than %1.1f%%\n", MIN_GREEN);
+                return;
+        }
+
+        node = rb_first(root);
+        while (node) {
+                double percent;
+                const char *color;
+                char *path;
+
+                src_line = rb_entry(node, struct source_line, node);
+                percent = src_line->percent;
+                color = get_percent_color(percent);
+                path = src_line->path;
+
+                color_fprintf(stdout, color, " %7.2f %s", percent, path);
+                node = rb_next(node);
+        }
+}
+
+static void symbol__annotate_hits(struct symbol *sym, int evidx)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct sym_hist *h = annotation__histogram(notes, evidx);
+        u64 len = sym->end - sym->start, offset;
+
+        for (offset = 0; offset < len; ++offset)
+                if (h->addr[offset] != 0)
+                        printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
+                               sym->start + offset, h->addr[offset]);
+        printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+}
+
+int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
+                            bool full_paths, int min_pcnt, int max_lines,
+                            int context)
+{
+        struct dso *dso = map->dso;
+        const char *filename = dso->long_name, *d_filename;
+        struct annotation *notes = symbol__annotation(sym);
+        struct objdump_line *pos, *queue = NULL;
+        int printed = 2, queue_len = 0;
+        int more = 0;
+        u64 len;
+
+        if (full_paths)
+                d_filename = filename;
+        else
+                d_filename = basename(filename);
+
+        len = sym->end - sym->start;
+
+        printf(" Percent |      Source code & Disassembly of %s\n", d_filename);
+        printf("------------------------------------------------\n");
+
+        if (verbose)
+                symbol__annotate_hits(sym, evidx);
+
+        list_for_each_entry(pos, &notes->src->source, node) {
+                if (context && queue == NULL) {
+                        queue = pos;
+                        queue_len = 0;
+                }
+
+                switch (objdump_line__print(pos, sym, evidx, len, min_pcnt,
+                                            printed, max_lines, queue)) {
+                case 0:
+                        ++printed;
+                        if (context) {
+                                printed += queue_len;
+                                queue = NULL;
+                                queue_len = 0;
+                        }
+                        break;
+                case 1:
+                        /* filtered by max_lines */
+                        ++more;
+                        break;
+                case -1:
+                default:
+                        /*
+                         * Filtered by min_pcnt or non IP lines when
+                         * context != 0
+                         */
+                        if (!context)
+                                break;
+                        if (queue_len == context)
+                                queue = list_entry(queue->node.next, typeof(*queue), node);
+                        else
+                                ++queue_len;
+                        break;
+                }
+        }
+
+        return more;
+}
+
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct sym_hist *h = annotation__histogram(notes, evidx);
+
+        memset(h, 0, notes->src->sizeof_sym_hist);
+}
+
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
+{
+        struct annotation *notes = symbol__annotation(sym);
+        struct sym_hist *h = annotation__histogram(notes, evidx);
+        struct objdump_line *pos;
+        int len = sym->end - sym->start;
+
+        h->sum = 0;
+
+        list_for_each_entry(pos, &notes->src->source, node) {
+                if (pos->offset != -1 && pos->offset < len) {
+                        h->addr[pos->offset] = h->addr[pos->offset] * 7 / 8;
+                        h->sum += h->addr[pos->offset];
+                }
+        }
+}
+
+void objdump_line_list__purge(struct list_head *head)
+{
+        struct objdump_line *pos, *n;
+
+        list_for_each_entry_safe(pos, n, head, node) {
+                list_del(&pos->node);
+                objdump_line__free(pos);
+        }
+}
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
+                         bool print_lines, bool full_paths, int min_pcnt,
+                         int max_lines)
+{
+        struct dso *dso = map->dso;
+        const char *filename = dso->long_name;
+        struct rb_root source_line = RB_ROOT;
+        u64 len;
+
+        if (symbol__annotate(sym, map, 0) < 0)
+                return -1;
+
+        len = sym->end - sym->start;
+
+        if (print_lines) {
+                symbol__get_source_line(sym, map, evidx, &source_line,
+                                        len, filename);
+                print_summary(&source_line, filename);
+        }
+
+        symbol__annotate_printf(sym, map, evidx, full_paths,
+                                min_pcnt, max_lines, 0);
+        if (print_lines)
+                symbol__free_source_line(sym, len);
+
+        objdump_line_list__purge(&symbol__annotation(sym)->src->source);
+
+        return 0;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
new file mode 100644
index 000000000000..c2c286896801
--- /dev/null
+++ b/tools/perf/util/annotate.h
@@ -0,0 +1,103 @@
+#ifndef __PERF_ANNOTATE_H
+#define __PERF_ANNOTATE_H
+
+#include <stdbool.h>
+#include "types.h"
+#include "symbol.h"
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct objdump_line {
+        struct list_head node;
+        s64              offset;
+        char             *line;
+};
+
+void objdump_line__free(struct objdump_line *self);
+struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+                                               struct objdump_line *pos);
+
+struct sym_hist {
+        u64             sum;
+        u64             addr[0];
+};
+
+struct source_line {
+        struct rb_node  node;
+        double          percent;
+        char            *path;
+};
+
+/** struct annotated_source - symbols with hits have this attached as in sannotation
+ *
+ * @histogram: Array of addr hit histograms per event being monitored
+ * @lines: If 'print_lines' is specified, per source code line percentages
+ * @source: source parsed from objdump -dS
+ *
+ * lines is allocated, percentages calculated and all sorted by percentage
+ * when the annotation is about to be presented, so the percentages are for
+ * one of the entries in the histogram array, i.e. for the event/counter being
+ * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate
+ * returns.
+ */
+struct annotated_source {
+        struct list_head   source;
+        struct source_line *lines;
+        int                nr_histograms;
+        int                sizeof_sym_hist;
+        struct sym_hist    histograms[0];
+};
+
+struct annotation {
+        pthread_mutex_t         lock;
+        struct annotated_source *src;
+};
+
+struct sannotation {
+        struct annotation annotation;
+        struct symbol     symbol;
+};
+
+static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
+{
+        return (((void *)&notes->src->histograms) +
+                (notes->src->sizeof_sym_hist * idx));
+}
+
+static inline struct annotation *symbol__annotation(struct symbol *sym)
+{
+        struct sannotation *a = container_of(sym, struct sannotation, symbol);
+        return &a->annotation;
+}
+
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+                             int evidx, u64 addr);
+int symbol__alloc_hist(struct symbol *sym, int nevents);
+void symbol__annotate_zero_histograms(struct symbol *sym);
+
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__annotate_init(struct map *map __used, struct symbol *sym);
+int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx,
+                            bool full_paths, int min_pcnt, int max_lines,
+                            int context);
+void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
+void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
+void objdump_line_list__purge(struct list_head *head);
+
+int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
+                         bool print_lines, bool full_paths, int min_pcnt,
+                         int max_lines);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int symbol__tui_annotate(struct symbol *sym __used,
+                                       struct map *map __used,
+                                       int evidx __used, int refresh __used)
+{
+        return 0;
+}
+#else
+int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+                         int refresh);
+#endif
+
+#endif  /* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e437edb72417..a91cd99f26ea 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -14,7 +14,10 @@
 #include <linux/kernel.h>
 #include "debug.h"
 
-static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
+static int build_id__mark_dso_hit(union perf_event *event,
+                                  struct perf_sample *sample __used,
+                                  struct perf_evsel *evsel __used,
+                                  struct perf_session *session)
 {
         struct addr_location al;
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -35,12 +38,14 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
         return 0;
 }
 
-static int event__exit_del_thread(event_t *self, struct perf_session *session)
+static int perf_event__exit_del_thread(union perf_event *event,
+                                       struct perf_sample *sample __used,
+                                       struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, self->fork.tid);
+        struct thread *thread = perf_session__findnew(session, event->fork.tid);
 
-        dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
-                    self->fork.ppid, self->fork.ptid);
+        dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+                    event->fork.ppid, event->fork.ptid);
 
         if (thread) {
                 rb_erase(&thread->rb_node, &session->threads);
@@ -53,9 +58,9 @@ static int event__exit_del_thread(event_t *self, struct perf_session *session)
 
 struct perf_event_ops build_id__mark_dso_hit_ops = {
         .sample = build_id__mark_dso_hit,
-        .mmap   = event__process_mmap,
-        .fork   = event__process_task,
-        .exit   = event__exit_del_thread,
+        .mmap   = perf_event__process_mmap,
+        .fork   = perf_event__process_task,
+        .exit   = perf_event__exit_del_thread,
 };
 
 char *dso__build_id_filename(struct dso *self, char *bf, size_t size)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 27e9ebe4076e..fc5e5a09d5b9 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -34,13 +34,14 @@ extern int pager_use_color;
 extern int use_browser;
 
 #ifdef NO_NEWT_SUPPORT
-static inline void setup_browser(void)
+static inline void setup_browser(bool fallback_to_pager)
 {
-        setup_pager();
+        if (fallback_to_pager)
+                setup_pager();
 }
 static inline void exit_browser(bool wait_for_ok __used) {}
 #else
-void setup_browser(void);
+void setup_browser(bool fallback_to_pager);
 void exit_browser(bool wait_for_ok);
 #endif
 
@@ -82,6 +83,8 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
         __attribute__((format (printf, 1, 2)));
 
+#ifdef NO_STRLCPY
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index f231f43424d2..9f7106a8d9a4 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com>
  *
  * Handle the callchains from the stream in an ad-hoc radix tree and then
  * sort them in an rbtree.
@@ -18,7 +18,8 @@
 #include "util.h"
 #include "callchain.h"
 
-bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
+bool ip_callchain__valid(struct ip_callchain *chain,
+                         const union perf_event *event)
 {
         unsigned int chain_size = event->header.size;
         chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
@@ -26,7 +27,10 @@ bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event)
 }
 
 #define chain_for_each_child(child, parent)     \
-        list_for_each_entry(child, &parent->children, brothers)
+        list_for_each_entry(child, &parent->children, siblings)
+
+#define chain_for_each_child_safe(child, next, parent)  \
+        list_for_each_entry_safe(child, next, &parent->children, siblings)
 
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
@@ -35,14 +39,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
         struct callchain_node *rnode;
-        u64 chain_cumul = cumul_hits(chain);
+        u64 chain_cumul = callchain_cumul_hits(chain);
 
         while (*p) {
                 u64 rnode_cumul;
 
                 parent = *p;
                 rnode = rb_entry(parent, struct callchain_node, rb_node);
-                rnode_cumul = cumul_hits(rnode);
+                rnode_cumul = callchain_cumul_hits(rnode);
 
                 switch (mode) {
                 case CHAIN_FLAT:
@@ -86,10 +90,10 @@ __sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
  * sort them by hit
  */
 static void
-sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
+sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
                 u64 min_hit, struct callchain_param *param __used)
 {
-        __sort_chain_flat(rb_root, node, min_hit);
+        __sort_chain_flat(rb_root, &root->node, min_hit);
 }
 
 static void __sort_chain_graph_abs(struct callchain_node *node,
@@ -101,18 +105,18 @@ static void __sort_chain_graph_abs(struct callchain_node *node,
 
         chain_for_each_child(child, node) {
                 __sort_chain_graph_abs(child, min_hit);
-                if (cumul_hits(child) >= min_hit)
+                if (callchain_cumul_hits(child) >= min_hit)
                         rb_insert_callchain(&node->rb_root, child,
                                             CHAIN_GRAPH_ABS);
         }
 }
 
 static void
-sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_node *chain_root,
+sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root,
                      u64 min_hit, struct callchain_param *param __used)
 {
-        __sort_chain_graph_abs(chain_root, min_hit);
-        rb_root->rb_node = chain_root->rb_root.rb_node;
+        __sort_chain_graph_abs(&chain_root->node, min_hit);
+        rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
 static void __sort_chain_graph_rel(struct callchain_node *node,
@@ -126,21 +130,21 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 
         chain_for_each_child(child, node) {
                 __sort_chain_graph_rel(child, min_percent);
-                if (cumul_hits(child) >= min_hit)
+                if (callchain_cumul_hits(child) >= min_hit)
                         rb_insert_callchain(&node->rb_root, child,
                                             CHAIN_GRAPH_REL);
         }
 }
 
 static void
-sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
+sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
                      u64 min_hit __used, struct callchain_param *param)
 {
-        __sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
-        rb_root->rb_node = chain_root->rb_root.rb_node;
+        __sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0);
+        rb_root->rb_node = chain_root->node.rb_root.rb_node;
 }
 
-int register_callchain_param(struct callchain_param *param)
+int callchain_register_param(struct callchain_param *param)
 {
         switch (param->mode) {
         case CHAIN_GRAPH_ABS:
@@ -186,32 +190,27 @@ create_child(struct callchain_node *parent, bool inherit_children)
                 chain_for_each_child(next, new)
                         next->parent = new;
         }
-        list_add_tail(&new->brothers, &parent->children);
+        list_add_tail(&new->siblings, &parent->children);
 
         return new;
 }
 
 
-struct resolved_ip {
-        u64               ip;
-        struct map_symbol ms;
-};
-
-struct resolved_chain {
-        u64                     nr;
-        struct resolved_ip      ips[0];
-};
-
-
 /*
  * Fill the node with callchain values
  */
 static void
-fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
+fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
-        unsigned int i;
+        struct callchain_cursor_node *cursor_node;
 
-        for (i = start; i < chain->nr; i++) {
+        node->val_nr = cursor->nr - cursor->pos;
+        if (!node->val_nr)
+                pr_warning("Warning: empty node in callchain tree\n");
+
+        cursor_node = callchain_cursor_current(cursor);
+
+        while (cursor_node) {
                 struct callchain_list *call;
 
                 call = zalloc(sizeof(*call));
@@ -219,23 +218,25 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
                         perror("not enough memory for the code path tree");
                         return;
                 }
-                call->ip = chain->ips[i].ip;
-                call->ms = chain->ips[i].ms;
+                call->ip = cursor_node->ip;
+                call->ms.sym = cursor_node->sym;
+                call->ms.map = cursor_node->map;
                 list_add_tail(&call->list, &node->val);
+
+                callchain_cursor_advance(cursor);
+                cursor_node = callchain_cursor_current(cursor);
         }
-        node->val_nr = chain->nr - start;
-        if (!node->val_nr)
-                pr_warning("Warning: empty node in callchain tree\n");
 }
 
 static void
-add_child(struct callchain_node *parent, struct resolved_chain *chain,
-          int start, u64 period)
+add_child(struct callchain_node *parent,
+          struct callchain_cursor *cursor,
+          u64 period)
 {
         struct callchain_node *new;
 
         new = create_child(parent, false);
-        fill_node(new, chain, start);
+        fill_node(new, cursor);
 
         new->children_hit = 0;
         new->hit = period;
@@ -247,9 +248,10 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
  * Then create another child to host the given callchain of new branch
  */
 static void
-split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
-                struct callchain_list *to_split, int idx_parents, int idx_local,
-                u64 period)
+split_add_child(struct callchain_node *parent,
+                struct callchain_cursor *cursor,
+                struct callchain_list *to_split,
+                u64 idx_parents, u64 idx_local, u64 period)
 {
         struct callchain_node *new;
         struct list_head *old_tail;
@@ -269,14 +271,14 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
         /* split the hits */
         new->hit = parent->hit;
         new->children_hit = parent->children_hit;
-        parent->children_hit = cumul_hits(new);
+        parent->children_hit = callchain_cumul_hits(new);
         new->val_nr = parent->val_nr - idx_local;
         parent->val_nr = idx_local;
 
         /* create a new child for the new branch if any */
-        if (idx_total < chain->nr) {
+        if (idx_total < cursor->nr) {
                 parent->hit = 0;
-                add_child(parent, chain, idx_total, period);
+                add_child(parent, cursor, period);
                 parent->children_hit += period;
         } else {
                 parent->hit = period;
@@ -284,37 +286,41 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-               unsigned int start, u64 period);
+append_chain(struct callchain_node *root,
+             struct callchain_cursor *cursor,
+             u64 period);
 
 static void
-__append_chain_children(struct callchain_node *root,
-                        struct resolved_chain *chain,
-                        unsigned int start, u64 period)
+append_chain_children(struct callchain_node *root,
+                      struct callchain_cursor *cursor,
+                      u64 period)
 {
         struct callchain_node *rnode;
 
         /* lookup in childrens */
         chain_for_each_child(rnode, root) {
-                unsigned int ret = __append_chain(rnode, chain, start, period);
+                unsigned int ret = append_chain(rnode, cursor, period);
 
                 if (!ret)
                         goto inc_children_hit;
         }
         /* nothing in children, add to the current node */
-        add_child(root, chain, start, period);
+        add_child(root, cursor, period);
 
 inc_children_hit:
         root->children_hit += period;
 }
 
 static int
-__append_chain(struct callchain_node *root, struct resolved_chain *chain,
-               unsigned int start, u64 period)
+append_chain(struct callchain_node *root,
+             struct callchain_cursor *cursor,
+             u64 period)
 {
+        struct callchain_cursor_node *curr_snap = cursor->curr;
         struct callchain_list *cnode;
-        unsigned int i = start;
+        u64 start = cursor->pos;
         bool found = false;
+        u64 matches;
 
         /*
          * Lookup in the current node
@@ -322,85 +328,134 @@ __append_chain(struct callchain_node *root, struct resolved_chain *chain,
          * anywhere inside a function.
          */
         list_for_each_entry(cnode, &root->val, list) {
+                struct callchain_cursor_node *node;
                 struct symbol *sym;
 
-                if (i == chain->nr)
+                node = callchain_cursor_current(cursor);
+                if (!node)
                         break;
 
-                sym = chain->ips[i].ms.sym;
+                sym = node->sym;
 
                 if (cnode->ms.sym && sym) {
                         if (cnode->ms.sym->start != sym->start)
                                 break;
-                } else if (cnode->ip != chain->ips[i].ip)
+                } else if (cnode->ip != node->ip)
                         break;
 
                 if (!found)
                         found = true;
-                i++;
+
+                callchain_cursor_advance(cursor);
         }
 
         /* matches not, relay on the parent */
-        if (!found)
+        if (!found) {
+                cursor->curr = curr_snap;
+                cursor->pos = start;
                 return -1;
+        }
+
+        matches = cursor->pos - start;
 
         /* we match only a part of the node. Split it and add the new chain */
-        if (i - start < root->val_nr) {
-                split_add_child(root, chain, cnode, start, i - start, period);
+        if (matches < root->val_nr) {
+                split_add_child(root, cursor, cnode, start, matches, period);
                 return 0;
         }
 
         /* we match 100% of the path, increment the hit */
-        if (i - start == root->val_nr && i == chain->nr) {
+        if (matches == root->val_nr && cursor->pos == cursor->nr) {
                 root->hit += period;
                 return 0;
         }
 
         /* We match the node and still have a part remaining */
-        __append_chain_children(root, chain, i, period);
+        append_chain_children(root, cursor, period);
 
         return 0;
 }
 
-static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
-                           struct map_symbol *syms)
+int callchain_append(struct callchain_root *root,
+                     struct callchain_cursor *cursor,
+                     u64 period)
 {
-        int i, j = 0;
+        if (!cursor->nr)
+                return 0;
+
+        callchain_cursor_commit(cursor);
+
+        append_chain_children(&root->node, cursor, period);
 
-        for (i = 0; i < (int)old->nr; i++) {
-                if (old->ips[i] >= PERF_CONTEXT_MAX)
-                        continue;
+        if (cursor->nr > root->max_depth)
+                root->max_depth = cursor->nr;
 
-                new->ips[j].ip = old->ips[i];
-                new->ips[j].ms = syms[i];
-                j++;
+        return 0;
+}
+
+static int
+merge_chain_branch(struct callchain_cursor *cursor,
+                   struct callchain_node *dst, struct callchain_node *src)
+{
+        struct callchain_cursor_node **old_last = cursor->last;
+        struct callchain_node *child, *next_child;
+        struct callchain_list *list, *next_list;
+        int old_pos = cursor->nr;
+        int err = 0;
+
+        list_for_each_entry_safe(list, next_list, &src->val, list) {
+                callchain_cursor_append(cursor, list->ip,
+                                        list->ms.map, list->ms.sym);
+                list_del(&list->list);
+                free(list);
+        }
+
+        if (src->hit) {
+                callchain_cursor_commit(cursor);
+                append_chain_children(dst, cursor, src->hit);
+        }
+
+        chain_for_each_child_safe(child, next_child, src) {
+                err = merge_chain_branch(cursor, dst, child);
+                if (err)
+                        break;
+
+                list_del(&child->siblings);
+                free(child);
         }
 
-        new->nr = j;
+        cursor->nr = old_pos;
+        cursor->last = old_last;
+
+        return err;
 }
 
+int callchain_merge(struct callchain_cursor *cursor,
+                    struct callchain_root *dst, struct callchain_root *src)
+{
+        return merge_chain_branch(cursor, &dst->node, &src->node);
+}
 
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-                 struct map_symbol *syms, u64 period)
+int callchain_cursor_append(struct callchain_cursor *cursor,
+                            u64 ip, struct map *map, struct symbol *sym)
 {
-        struct resolved_chain *filtered;
+        struct callchain_cursor_node *node = *cursor->last;
 
-        if (!chain->nr)
-                return 0;
+        if (!node) {
+                node = calloc(sizeof(*node), 1);
+                if (!node)
+                        return -ENOMEM;
 
-        filtered = zalloc(sizeof(*filtered) +
-                          chain->nr * sizeof(struct resolved_ip));
-        if (!filtered)
-                return -ENOMEM;
+                *cursor->last = node;
+        }
 
-        filter_context(chain, filtered, syms);
+        node->ip = ip;
+        node->map = map;
+        node->sym = sym;
 
-        if (!filtered->nr)
-                goto end;
+        cursor->nr++;
 
-        __append_chain_children(root, filtered, 0, period);
-end:
-        free(filtered);
+        cursor->last = &node->next;
 
         return 0;
 }
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6de4313924fb..1a79df9f739f 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -16,7 +16,7 @@ enum chain_mode {
 
 struct callchain_node {
         struct callchain_node   *parent;
-        struct list_head        brothers;
+        struct list_head        siblings;
         struct list_head        children;
         struct list_head        val;
         struct rb_node          rb_node; /* to sort nodes in an rbtree */
@@ -26,9 +26,14 @@ struct callchain_node {
         u64                     children_hit;
 };
 
+struct callchain_root {
+        u64                     max_depth;
+        struct callchain_node   node;
+};
+
 struct callchain_param;
 
-typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_node *,
+typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
                                  u64, struct callchain_param *);
 
 struct callchain_param {
@@ -44,25 +49,87 @@ struct callchain_list {
         struct list_head        list;
 };
 
-static inline void callchain_init(struct callchain_node *node)
+/*
+ * A callchain cursor is a single linked list that
+ * let one feed a callchain progressively.
+ * It keeps persitent allocated entries to minimize
+ * allocations.
+ */
+struct callchain_cursor_node {
+        u64                             ip;
+        struct map                      *map;
+        struct symbol                   *sym;
+        struct callchain_cursor_node    *next;
+};
+
+struct callchain_cursor {
+        u64                             nr;
+        struct callchain_cursor_node    *first;
+        struct callchain_cursor_node    **last;
+        u64                             pos;
+        struct callchain_cursor_node    *curr;
+};
+
+static inline void callchain_init(struct callchain_root *root)
 {
-        INIT_LIST_HEAD(&node->brothers);
-        INIT_LIST_HEAD(&node->children);
-        INIT_LIST_HEAD(&node->val);
+        INIT_LIST_HEAD(&root->node.siblings);
+        INIT_LIST_HEAD(&root->node.children);
+        INIT_LIST_HEAD(&root->node.val);
 
-        node->children_hit = 0;
-        node->parent = NULL;
-        node->hit = 0;
+        root->node.parent = NULL;
+        root->node.hit = 0;
+        root->node.children_hit = 0;
+        root->max_depth = 0;
 }
 
-static inline u64 cumul_hits(struct callchain_node *node)
+static inline u64 callchain_cumul_hits(struct callchain_node *node)
 {
         return node->hit + node->children_hit;
 }
 
-int register_callchain_param(struct callchain_param *param);
-int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-                 struct map_symbol *syms, u64 period);
+int callchain_register_param(struct callchain_param *param);
+int callchain_append(struct callchain_root *root,
+                     struct callchain_cursor *cursor,
+                     u64 period);
+
+int callchain_merge(struct callchain_cursor *cursor,
+                    struct callchain_root *dst, struct callchain_root *src);
+
+bool ip_callchain__valid(struct ip_callchain *chain,
+                         const union perf_event *event);
+/*
+ * Initialize a cursor before adding entries inside, but keep
+ * the previously allocated entries as a cache.
+ */
+static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
+{
+        cursor->nr = 0;
+        cursor->last = &cursor->first;
+}
+
+int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
+                            struct map *map, struct symbol *sym);
+
+/* Close a cursor writing session. Initialize for the reader */
+static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
+{
+        cursor->curr = cursor->first;
+        cursor->pos = 0;
+}
+
+/* Cursor reading iteration helpers */
+static inline struct callchain_cursor_node *
+callchain_cursor_current(struct callchain_cursor *cursor)
+{
+        if (cursor->pos == cursor->nr)
+                return NULL;
+
+        return cursor->curr;
+}
 
-bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event);
+static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
+{
+        cursor->curr = cursor->curr->next;
+        cursor->pos++;
+}
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
new file mode 100644
index 000000000000..96bee5c46008
--- /dev/null
+++ b/tools/perf/util/cgroup.c
@@ -0,0 +1,178 @@
+#include "util.h"
+#include "../perf.h"
+#include "parse-options.h"
+#include "evsel.h"
+#include "cgroup.h"
+#include "debugfs.h" /* MAX_PATH, STR() */
+#include "evlist.h"
+
+int nr_cgroups;
+
+static int
+cgroupfs_find_mountpoint(char *buf, size_t maxlen)
+{
+        FILE *fp;
+        char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
+        char *token, *saved_ptr = NULL;
+        int found = 0;
+
+        fp = fopen("/proc/mounts", "r");
+        if (!fp)
+                return -1;
+
+        /*
+         * in order to handle split hierarchy, we need to scan /proc/mounts
+         * and inspect every cgroupfs mount point to find one that has
+         * perf_event subsystem
+         */
+        while (fscanf(fp, "%*s %"STR(MAX_PATH)"s %"STR(MAX_PATH)"s %"
+                                STR(MAX_PATH)"s %*d %*d\n",
+                                mountpoint, type, tokens) == 3) {
+
+                if (!strcmp(type, "cgroup")) {
+
+                        token = strtok_r(tokens, ",", &saved_ptr);
+
+                        while (token != NULL) {
+                                if (!strcmp(token, "perf_event")) {
+                                        found = 1;
+                                        break;
+                                }
+                                token = strtok_r(NULL, ",", &saved_ptr);
+                        }
+                }
+                if (found)
+                        break;
+        }
+        fclose(fp);
+        if (!found)
+                return -1;
+
+        if (strlen(mountpoint) < maxlen) {
+                strcpy(buf, mountpoint);
+                return 0;
+        }
+        return -1;
+}
+
+static int open_cgroup(char *name)
+{
+        char path[MAX_PATH+1];
+        char mnt[MAX_PATH+1];
+        int fd;
+
+
+        if (cgroupfs_find_mountpoint(mnt, MAX_PATH+1))
+                return -1;
+
+        snprintf(path, MAX_PATH, "%s/%s", mnt, name);
+
+        fd = open(path, O_RDONLY);
+        if (fd == -1)
+                fprintf(stderr, "no access to cgroup %s\n", path);
+
+        return fd;
+}
+
+static int add_cgroup(struct perf_evlist *evlist, char *str)
+{
+        struct perf_evsel *counter;
+        struct cgroup_sel *cgrp = NULL;
+        int n;
+        /*
+         * check if cgrp is already defined, if so we reuse it
+         */
+        list_for_each_entry(counter, &evlist->entries, node) {
+                cgrp = counter->cgrp;
+                if (!cgrp)
+                        continue;
+                if (!strcmp(cgrp->name, str))
+                        break;
+
+                cgrp = NULL;
+        }
+
+        if (!cgrp) {
+                cgrp = zalloc(sizeof(*cgrp));
+                if (!cgrp)
+                        return -1;
+
+                cgrp->name = str;
+
+                cgrp->fd = open_cgroup(str);
+                if (cgrp->fd == -1) {
+                        free(cgrp);
+                        return -1;
+                }
+        }
+
+        /*
+         * find corresponding event
+         * if add cgroup N, then need to find event N
+         */
+        n = 0;
+        list_for_each_entry(counter, &evlist->entries, node) {
+                if (n == nr_cgroups)
+                        goto found;
+                n++;
+        }
+        if (cgrp->refcnt == 0)
+                free(cgrp);
+
+        return -1;
+found:
+        cgrp->refcnt++;
+        counter->cgrp = cgrp;
+        return 0;
+}
+
+void close_cgroup(struct cgroup_sel *cgrp)
+{
+        if (!cgrp)
+                return;
+
+        /* XXX: not reentrant */
+        if (--cgrp->refcnt == 0) {
+                close(cgrp->fd);
+                free(cgrp->name);
+                free(cgrp);
+        }
+}
+
+int parse_cgroups(const struct option *opt __used, const char *str,
+                  int unset __used)
+{
+        struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+        const char *p, *e, *eos = str + strlen(str);
+        char *s;
+        int ret;
+
+        if (list_empty(&evlist->entries)) {
+                fprintf(stderr, "must define events before cgroups\n");
+                return -1;
+        }
+
+        for (;;) {
+                p = strchr(str, ',');
+                e = p ? p : eos;
+
+                /* allow empty cgroups, i.e., skip */
+                if (e - str) {
+                        /* termination added */
+                        s = strndup(str, e - str);
+                        if (!s)
+                                return -1;
+                        ret = add_cgroup(evlist, s);
+                        if (ret) {
+                                free(s);
+                                return -1;
+                        }
+                }
+                /* nr_cgroups is increased een for empty cgroups */
+                nr_cgroups++;
+                if (!p)
+                        break;
+                str = p+1;
+        }
+        return 0;
+}
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
new file mode 100644
index 000000000000..89acd6debdc5
--- /dev/null
+++ b/tools/perf/util/cgroup.h
@@ -0,0 +1,17 @@
+#ifndef __CGROUP_H__
+#define __CGROUP_H__
+
+struct option;
+
+struct cgroup_sel {
+        char *name;
+        int fd;
+        int refcnt;
+};
+
+
+extern int nr_cgroups; /* number of explicit cgroups defined */
+extern void close_cgroup(struct cgroup_sel *cgrp);
+extern int parse_cgroups(const struct option *opt, const char *str, int unset);
+
+#endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0f9b8d7a7d7e..6893eec693ab 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -4,32 +4,53 @@
 #include <assert.h>
 #include <stdio.h>
 
-int cpumap[MAX_NR_CPUS];
-
-static int default_cpu_map(void)
+static struct cpu_map *cpu_map__default_new(void)
 {
-        int nr_cpus, i;
+        struct cpu_map *cpus;
+        int nr_cpus;
 
         nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
-        assert(nr_cpus <= MAX_NR_CPUS);
-        assert((int)nr_cpus >= 0);
+        if (nr_cpus < 0)
+                return NULL;
+
+        cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+        if (cpus != NULL) {
+                int i;
+                for (i = 0; i < nr_cpus; ++i)
+                        cpus->map[i] = i;
 
-        for (i = 0; i < nr_cpus; ++i)
-                cpumap[i] = i;
+                cpus->nr = nr_cpus;
+        }
 
-        return nr_cpus;
+        return cpus;
 }
 
-static int read_all_cpu_map(void)
+static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 {
+        size_t payload_size = nr_cpus * sizeof(int);
+        struct cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+
+        if (cpus != NULL) {
+                cpus->nr = nr_cpus;
+                memcpy(cpus->map, tmp_cpus, payload_size);
+        }
+
+        return cpus;
+}
+
+static struct cpu_map *cpu_map__read_all_cpu_map(void)
+{
+        struct cpu_map *cpus = NULL;
         FILE *onlnf;
         int nr_cpus = 0;
+        int *tmp_cpus = NULL, *tmp;
+        int max_entries = 0;
         int n, cpu, prev;
         char sep;
 
         onlnf = fopen("/sys/devices/system/cpu/online", "r");
         if (!onlnf)
-                return default_cpu_map();
+                return cpu_map__default_new();
 
         sep = 0;
         prev = -1;
@@ -38,12 +59,28 @@ static int read_all_cpu_map(void)
                 if (n <= 0)
                         break;
                 if (prev >= 0) {
-                        assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+                        int new_max = nr_cpus + cpu - prev - 1;
+
+                        if (new_max >= max_entries) {
+                                max_entries = new_max + MAX_NR_CPUS / 2;
+                                tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+                                if (tmp == NULL)
+                                        goto out_free_tmp;
+                                tmp_cpus = tmp;
+                        }
+
                         while (++prev < cpu)
-                                cpumap[nr_cpus++] = prev;
+                                tmp_cpus[nr_cpus++] = prev;
+                }
+                if (nr_cpus == max_entries) {
+                        max_entries += MAX_NR_CPUS;
+                        tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+                        if (tmp == NULL)
+                                goto out_free_tmp;
+                        tmp_cpus = tmp;
                 }
-                assert (nr_cpus < MAX_NR_CPUS);
-                cpumap[nr_cpus++] = cpu;
+
+                tmp_cpus[nr_cpus++] = cpu;
                 if (n == 2 && sep == '-')
                         prev = cpu;
                 else
@@ -51,24 +88,31 @@ static int read_all_cpu_map(void)
                 if (n == 1 || sep == '\n')
                         break;
         }
-        fclose(onlnf);
-        if (nr_cpus > 0)
-                return nr_cpus;
 
-        return default_cpu_map();
+        if (nr_cpus > 0)
+                cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
+        else
+                cpus = cpu_map__default_new();
+out_free_tmp:
+        free(tmp_cpus);
+        fclose(onlnf);
+        return cpus;
 }
 
-int read_cpu_map(const char *cpu_list)
+struct cpu_map *cpu_map__new(const char *cpu_list)
 {
+        struct cpu_map *cpus = NULL;
         unsigned long start_cpu, end_cpu = 0;
         char *p = NULL;
         int i, nr_cpus = 0;
+        int *tmp_cpus = NULL, *tmp;
+        int max_entries = 0;
 
         if (!cpu_list)
-                return read_all_cpu_map();
+                return cpu_map__read_all_cpu_map();
 
         if (!isdigit(*cpu_list))
-                goto invalid;
+                goto out;
 
         while (isdigit(*cpu_list)) {
                 p = NULL;
@@ -94,21 +138,47 @@ int read_cpu_map(const char *cpu_list)
                 for (; start_cpu <= end_cpu; start_cpu++) {
                         /* check for duplicates */
                         for (i = 0; i < nr_cpus; i++)
-                                if (cpumap[i] == (int)start_cpu)
+                                if (tmp_cpus[i] == (int)start_cpu)
                                         goto invalid;
 
-                        assert(nr_cpus < MAX_NR_CPUS);
-                        cpumap[nr_cpus++] = (int)start_cpu;
+                        if (nr_cpus == max_entries) {
+                                max_entries += MAX_NR_CPUS;
+                                tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+                                if (tmp == NULL)
+                                        goto invalid;
+                                tmp_cpus = tmp;
+                        }
+                        tmp_cpus[nr_cpus++] = (int)start_cpu;
                 }
                 if (*p)
                         ++p;
 
                 cpu_list = p;
         }
-        if (nr_cpus > 0)
-                return nr_cpus;
 
-        return default_cpu_map();
+        if (nr_cpus > 0)
+                cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
+        else
+                cpus = cpu_map__default_new();
 invalid:
-        return -1;
+        free(tmp_cpus);
+out:
+        return cpus;
+}
+
+struct cpu_map *cpu_map__dummy_new(void)
+{
+        struct cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+
+        if (cpus != NULL) {
+                cpus->nr = 1;
+                cpus->map[0] = -1;
+        }
+
+        return cpus;
+}
+
+void cpu_map__delete(struct cpu_map *map)
+{
+        free(map);
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 3e60f56e490e..072c0a374794 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -1,7 +1,13 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
-extern int read_cpu_map(const char *cpu_list);
-extern int cpumap[];
+struct cpu_map {
+        int nr;
+        int map[];
+};
+
+struct cpu_map *cpu_map__new(const char *cpu_list);
+struct cpu_map *cpu_map__dummy_new(void);
+void cpu_map__delete(struct cpu_map *map);
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index f9c7e3ad1aa7..155749d74350 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -12,8 +12,8 @@
 #include "debug.h"
 #include "util.h"
 
-int verbose = 0;
-bool dump_trace = false;
+int verbose;
+bool dump_trace = false, quiet = false;
 
 int eprintf(int level, const char *fmt, ...)
 {
@@ -46,22 +46,28 @@ int dump_printf(const char *fmt, ...)
         return ret;
 }
 
-static int dump_printf_color(const char *fmt, const char *color, ...)
+#ifdef NO_NEWT_SUPPORT
+void ui__warning(const char *format, ...)
 {
         va_list args;
-        int ret = 0;
-
-        if (dump_trace) {
-                va_start(args, color);
-                ret = color_vfprintf(stdout, color, fmt, args);
-                va_end(args);
-        }
 
-        return ret;
+        va_start(args, format);
+        vfprintf(stderr, format, args);
+        va_end(args);
 }
+#endif
 
+void ui__warning_paranoid(void)
+{
+        ui__warning("Permission error - are you root?\n"
+                    "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
+                    " -1 - Not paranoid at all\n"
+                    "  0 - Disallow raw tracepoint access for unpriv\n"
+                    "  1 - Disallow cpu events for unpriv\n"
+                    "  2 - Disallow kernel profiling for unpriv\n");
+}
 
-void trace_event(event_t *event)
+void trace_event(union perf_event *event)
 {
         unsigned char *raw_event = (void *)event;
         const char *color = PERF_COLOR_BLUE;
@@ -70,29 +76,29 @@ void trace_event(event_t *event)
         if (!dump_trace)
                 return;
 
-        dump_printf(".");
-        dump_printf_color("\n. ... raw event: size %d bytes\n", color,
-                          event->header.size);
+        printf(".");
+        color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+                      event->header.size);
 
         for (i = 0; i < event->header.size; i++) {
                 if ((i & 15) == 0) {
-                        dump_printf(".");
-                        dump_printf_color("  %04x: ", color, i);
+                        printf(".");
+                        color_fprintf(stdout, color, "  %04x: ", i);
                 }
 
-                dump_printf_color(" %02x", color, raw_event[i]);
+                color_fprintf(stdout, color, " %02x", raw_event[i]);
 
                 if (((i & 15) == 15) || i == event->header.size-1) {
-                        dump_printf_color("  ", color);
+                        color_fprintf(stdout, color, "  ");
                         for (j = 0; j < 15-(i & 15); j++)
-                                dump_printf_color("   ", color);
+                                color_fprintf(stdout, color, "   ");
                         for (j = i & ~15; j <= i; j++) {
-                                dump_printf_color("%c", color,
-                                                isprint(raw_event[j]) ?
-                                                raw_event[j] : '.');
+                                color_fprintf(stdout, color, "%c",
+                                              isprint(raw_event[j]) ?
+                                              raw_event[j] : '.');
                         }
-                        dump_printf_color("\n", color);
+                        color_fprintf(stdout, color, "\n");
                 }
         }
-        dump_printf(".\n");
+        printf(".\n");
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 7a17ee061bcb..fd53db47e3de 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -6,10 +6,10 @@
 #include "event.h"
 
 extern int verbose;
-extern bool dump_trace;
+extern bool quiet, dump_trace;
 
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
-void trace_event(event_t *event);
+void trace_event(union perf_event *event);
 
 struct ui_progress;
 
@@ -35,4 +35,7 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #include "ui/progress.h"
 #endif
 
+void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
+void ui__warning_paranoid(void);
+
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dab9e754a281..3c1b8a632101 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -6,29 +6,48 @@
 #include "string.h"
 #include "strlist.h"
 #include "thread.h"
+#include "thread_map.h"
+
+static const char *perf_event__names[] = {
+        [0]                                     = "TOTAL",
+        [PERF_RECORD_MMAP]                      = "MMAP",
+        [PERF_RECORD_LOST]                      = "LOST",
+        [PERF_RECORD_COMM]                      = "COMM",
+        [PERF_RECORD_EXIT]                      = "EXIT",
+        [PERF_RECORD_THROTTLE]                  = "THROTTLE",
+        [PERF_RECORD_UNTHROTTLE]                = "UNTHROTTLE",
+        [PERF_RECORD_FORK]                      = "FORK",
+        [PERF_RECORD_READ]                      = "READ",
+        [PERF_RECORD_SAMPLE]                    = "SAMPLE",
+        [PERF_RECORD_HEADER_ATTR]               = "ATTR",
+        [PERF_RECORD_HEADER_EVENT_TYPE]         = "EVENT_TYPE",
+        [PERF_RECORD_HEADER_TRACING_DATA]       = "TRACING_DATA",
+        [PERF_RECORD_HEADER_BUILD_ID]           = "BUILD_ID",
+        [PERF_RECORD_FINISHED_ROUND]            = "FINISHED_ROUND",
+};
+
+const char *perf_event__name(unsigned int id)
+{
+        if (id >= ARRAY_SIZE(perf_event__names))
+                return "INVALID";
+        if (!perf_event__names[id])
+                return "UNKNOWN";
+        return perf_event__names[id];
+}
 
-const char *event__name[] = {
-        [0]                      = "TOTAL",
-        [PERF_RECORD_MMAP]       = "MMAP",
-        [PERF_RECORD_LOST]       = "LOST",
-        [PERF_RECORD_COMM]       = "COMM",
-        [PERF_RECORD_EXIT]       = "EXIT",
-        [PERF_RECORD_THROTTLE]   = "THROTTLE",
-        [PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-        [PERF_RECORD_FORK]       = "FORK",
-        [PERF_RECORD_READ]       = "READ",
-        [PERF_RECORD_SAMPLE]     = "SAMPLE",
-        [PERF_RECORD_HEADER_ATTR]        = "ATTR",
-        [PERF_RECORD_HEADER_EVENT_TYPE]  = "EVENT_TYPE",
-        [PERF_RECORD_HEADER_TRACING_DATA]        = "TRACING_DATA",
-        [PERF_RECORD_HEADER_BUILD_ID]    = "BUILD_ID",
+static struct perf_sample synth_sample = {
+        .pid       = -1,
+        .tid       = -1,
+        .time      = -1,
+        .stream_id = -1,
+        .cpu       = -1,
+        .period    = 1,
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
-                                    event__handler_t process,
-                                    struct perf_session *session)
+static pid_t perf_event__synthesize_comm(union perf_event *event, pid_t pid,
+                                         int full, perf_event__handler_t process,
+                                         struct perf_session *session)
 {
-        event_t ev;
         char filename[PATH_MAX];
         char bf[BUFSIZ];
         FILE *fp;
@@ -49,34 +68,39 @@ out_race:
                 return 0;
         }
 
-        memset(&ev.comm, 0, sizeof(ev.comm));
-        while (!ev.comm.comm[0] || !ev.comm.pid) {
-                if (fgets(bf, sizeof(bf), fp) == NULL)
-                        goto out_failure;
+        memset(&event->comm, 0, sizeof(event->comm));
+
+        while (!event->comm.comm[0] || !event->comm.pid) {
+                if (fgets(bf, sizeof(bf), fp) == NULL) {
+                        pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
+                        goto out;
+                }
 
                 if (memcmp(bf, "Name:", 5) == 0) {
                         char *name = bf + 5;
                         while (*name && isspace(*name))
                                 ++name;
                         size = strlen(name) - 1;
-                        memcpy(ev.comm.comm, name, size++);
+                        memcpy(event->comm.comm, name, size++);
                 } else if (memcmp(bf, "Tgid:", 5) == 0) {
                         char *tgids = bf + 5;
                         while (*tgids && isspace(*tgids))
                                 ++tgids;
-                        tgid = ev.comm.pid = atoi(tgids);
+                        tgid = event->comm.pid = atoi(tgids);
                 }
         }
 
-        ev.comm.header.type = PERF_RECORD_COMM;
+        event->comm.header.type = PERF_RECORD_COMM;
         size = ALIGN(size, sizeof(u64));
-        ev.comm.header.size = sizeof(ev.comm) - (sizeof(ev.comm.comm) - size);
-
+        memset(event->comm.comm + size, 0, session->id_hdr_size);
+        event->comm.header.size = (sizeof(event->comm) -
+                                (sizeof(event->comm.comm) - size) +
+                                session->id_hdr_size);
         if (!full) {
-                ev.comm.tid = pid;
+                event->comm.tid = pid;
 
-                process(&ev, session);
-                goto out_fclose;
+                process(event, &synth_sample, session);
+                goto out;
         }
 
         snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
@@ -91,24 +115,22 @@ out_race:
                 if (*end)
                         continue;
 
-                ev.comm.tid = pid;
+                event->comm.tid = pid;
 
-                process(&ev, session);
+                process(event, &synth_sample, session);
         }
-        closedir(tasks);
 
-out_fclose:
+        closedir(tasks);
+out:
         fclose(fp);
-        return tgid;
 
-out_failure:
-        pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
-        return -1;
+        return tgid;
 }
 
-static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
-                                         event__handler_t process,
-                                         struct perf_session *session)
+static int perf_event__synthesize_mmap_events(union perf_event *event,
+                                              pid_t pid, pid_t tgid,
+                                              perf_event__handler_t process,
+                                              struct perf_session *session)
 {
         char filename[PATH_MAX];
         FILE *fp;
@@ -124,29 +146,25 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
                 return -1;
         }
 
+        event->header.type = PERF_RECORD_MMAP;
+        /*
+         * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+         */
+        event->header.misc = PERF_RECORD_MISC_USER;
+
         while (1) {
                 char bf[BUFSIZ], *pbf = bf;
-                event_t ev = {
-                        .header = {
-                                .type = PERF_RECORD_MMAP,
-                                /*
-                                 * Just like the kernel, see __perf_event_mmap
-                                 * in kernel/perf_event.c
-                                 */
-                                .misc = PERF_RECORD_MISC_USER,
-                         },
-                };
                 int n;
                 size_t size;
                 if (fgets(bf, sizeof(bf), fp) == NULL)
                         break;
 
                 /* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-                n = hex2u64(pbf, &ev.mmap.start);
+                n = hex2u64(pbf, &event->mmap.start);
                 if (n < 0)
                         continue;
                 pbf += n + 1;
-                n = hex2u64(pbf, &ev.mmap.len);
+                n = hex2u64(pbf, &event->mmap.len);
                 if (n < 0)
                         continue;
                 pbf += n + 3;
@@ -161,19 +179,21 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
                                 continue;
 
                         pbf += 3;
-                        n = hex2u64(pbf, &ev.mmap.pgoff);
+                        n = hex2u64(pbf, &event->mmap.pgoff);
 
                         size = strlen(execname);
                         execname[size - 1] = '\0'; /* Remove \n */
-                        memcpy(ev.mmap.filename, execname, size);
+                        memcpy(event->mmap.filename, execname, size);
                         size = ALIGN(size, sizeof(u64));
-                        ev.mmap.len -= ev.mmap.start;
-                        ev.mmap.header.size = (sizeof(ev.mmap) -
-                                               (sizeof(ev.mmap.filename) - size));
-                        ev.mmap.pid = tgid;
-                        ev.mmap.tid = pid;
-
-                        process(&ev, session);
+                        event->mmap.len -= event->mmap.start;
+                        event->mmap.header.size = (sizeof(event->mmap) -
+                                                (sizeof(event->mmap.filename) - size));
+                        memset(event->mmap.filename + size, 0, session->id_hdr_size);
+                        event->mmap.header.size += session->id_hdr_size;
+                        event->mmap.pid = tgid;
+                        event->mmap.tid = pid;
+
+                        process(event, &synth_sample, session);
                 }
         }
 
@@ -181,26 +201,33 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
         return 0;
 }
 
-int event__synthesize_modules(event__handler_t process,
-                              struct perf_session *session,
-                              struct machine *machine)
+int perf_event__synthesize_modules(perf_event__handler_t process,
+                                   struct perf_session *session,
+                                   struct machine *machine)
 {
         struct rb_node *nd;
         struct map_groups *kmaps = &machine->kmaps;
-        u16 misc;
+        union perf_event *event = zalloc((sizeof(event->mmap) +
+                                          session->id_hdr_size));
+        if (event == NULL) {
+                pr_debug("Not enough memory synthesizing mmap event "
+                         "for kernel modules\n");
+                return -1;
+        }
+
+        event->header.type = PERF_RECORD_MMAP;
 
         /*
          * kernel uses 0 for user space maps, see kernel/perf_event.c
          * __perf_event_mmap
          */
         if (machine__is_host(machine))
-                misc = PERF_RECORD_MISC_KERNEL;
+                event->header.misc = PERF_RECORD_MISC_KERNEL;
         else
-                misc = PERF_RECORD_MISC_GUEST_KERNEL;
+                event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
         for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
              nd; nd = rb_next(nd)) {
-                event_t ev;
                 size_t size;
                 struct map *pos = rb_entry(nd, struct map, rb_node);
 
@@ -208,39 +235,87 @@ int event__synthesize_modules(event__handler_t process,
                         continue;
 
                 size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
-                memset(&ev, 0, sizeof(ev));
-                ev.mmap.header.misc = misc;
-                ev.mmap.header.type = PERF_RECORD_MMAP;
-                ev.mmap.header.size = (sizeof(ev.mmap) -
-                                        (sizeof(ev.mmap.filename) - size));
-                ev.mmap.start = pos->start;
-                ev.mmap.len   = pos->end - pos->start;
-                ev.mmap.pid   = machine->pid;
-
-                memcpy(ev.mmap.filename, pos->dso->long_name,
+                event->mmap.header.type = PERF_RECORD_MMAP;
+                event->mmap.header.size = (sizeof(event->mmap) -
+                                        (sizeof(event->mmap.filename) - size));
+                memset(event->mmap.filename + size, 0, session->id_hdr_size);
+                event->mmap.header.size += session->id_hdr_size;
+                event->mmap.start = pos->start;
+                event->mmap.len   = pos->end - pos->start;
+                event->mmap.pid   = machine->pid;
+
+                memcpy(event->mmap.filename, pos->dso->long_name,
                        pos->dso->long_name_len + 1);
-                process(&ev, session);
+                process(event, &synth_sample, session);
         }
 
+        free(event);
         return 0;
 }
 
-int event__synthesize_thread(pid_t pid, event__handler_t process,
-                             struct perf_session *session)
+static int __event__synthesize_thread(union perf_event *comm_event,
+                                      union perf_event *mmap_event,
+                                      pid_t pid, perf_event__handler_t process,
+                                      struct perf_session *session)
 {
-        pid_t tgid = event__synthesize_comm(pid, 1, process, session);
+        pid_t tgid = perf_event__synthesize_comm(comm_event, pid, 1, process,
+                                            session);
         if (tgid == -1)
                 return -1;
-        return event__synthesize_mmap_events(pid, tgid, process, session);
+        return perf_event__synthesize_mmap_events(mmap_event, pid, tgid,
+                                             process, session);
+}
+
+int perf_event__synthesize_thread_map(struct thread_map *threads,
+                                      perf_event__handler_t process,
+                                      struct perf_session *session)
+{
+        union perf_event *comm_event, *mmap_event;
+        int err = -1, thread;
+
+        comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+        if (comm_event == NULL)
+                goto out;
+
+        mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+        if (mmap_event == NULL)
+                goto out_free_comm;
+
+        err = 0;
+        for (thread = 0; thread < threads->nr; ++thread) {
+                if (__event__synthesize_thread(comm_event, mmap_event,
+                                               threads->map[thread],
+                                               process, session)) {
+                        err = -1;
+                        break;
+                }
+        }
+        free(mmap_event);
+out_free_comm:
+        free(comm_event);
+out:
+        return err;
 }
 
-void event__synthesize_threads(event__handler_t process,
-                               struct perf_session *session)
+int perf_event__synthesize_threads(perf_event__handler_t process,
+                                   struct perf_session *session)
 {
         DIR *proc;
         struct dirent dirent, *next;
+        union perf_event *comm_event, *mmap_event;
+        int err = -1;
+
+        comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+        if (comm_event == NULL)
+                goto out;
+
+        mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+        if (mmap_event == NULL)
+                goto out_free_comm;
 
         proc = opendir("/proc");
+        if (proc == NULL)
+                goto out_free_mmap;
 
         while (!readdir_r(proc, &dirent, &next) && next) {
                 char *end;
@@ -249,10 +324,18 @@ void event__synthesize_threads(event__handler_t process,
                 if (*end) /* only interested in proper numerical dirents */
                         continue;
 
-                event__synthesize_thread(pid, process, session);
+                __event__synthesize_thread(comm_event, mmap_event, pid,
+                                           process, session);
         }
 
         closedir(proc);
+        err = 0;
+out_free_mmap:
+        free(mmap_event);
+out_free_comm:
+        free(comm_event);
+out:
+        return err;
 }
 
 struct process_symbol_args {
@@ -260,7 +343,8 @@ struct process_symbol_args {
         u64        start;
 };
 
-static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
+static int find_symbol_cb(void *arg, const char *name, char type,
+                          u64 start, u64 end __used)
 {
         struct process_symbol_args *args = arg;
 
@@ -276,28 +360,30 @@ static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
         return 1;
 }
 
-int event__synthesize_kernel_mmap(event__handler_t process,
-                                  struct perf_session *session,
-                                  struct machine *machine,
-                                  const char *symbol_name)
+int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
+                                       struct perf_session *session,
+                                       struct machine *machine,
+                                       const char *symbol_name)
 {
         size_t size;
         const char *filename, *mmap_name;
         char path[PATH_MAX];
         char name_buff[PATH_MAX];
         struct map *map;
-
-        event_t ev = {
-                .header = {
-                        .type = PERF_RECORD_MMAP,
-                },
-        };
+        int err;
         /*
          * We should get this from /sys/kernel/sections/.text, but till that is
          * available use this, and after it is use this as a fallback for older
          * kernels.
          */
         struct process_symbol_args args = { .name = symbol_name, };
+        union perf_event *event = zalloc((sizeof(event->mmap) +
+                                          session->id_hdr_size));
+        if (event == NULL) {
+                pr_debug("Not enough memory synthesizing mmap event "
+                         "for kernel modules\n");
+                return -1;
+        }
 
         mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
         if (machine__is_host(machine)) {
@@ -305,10 +391,10 @@ int event__synthesize_kernel_mmap(event__handler_t process,
                  * kernel uses PERF_RECORD_MISC_USER for user space maps,
                  * see kernel/perf_event.c __perf_event_mmap
                  */
-                ev.header.misc = PERF_RECORD_MISC_KERNEL;
+                event->header.misc = PERF_RECORD_MISC_KERNEL;
                 filename = "/proc/kallsyms";
         } else {
-                ev.header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+                event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
                 if (machine__is_default_guest(machine))
                         filename = (char *) symbol_conf.default_guest_kallsyms;
                 else {
@@ -321,54 +407,32 @@ int event__synthesize_kernel_mmap(event__handler_t process,
                 return -ENOENT;
 
         map = machine->vmlinux_maps[MAP__FUNCTION];
-        size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
+        size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
                         "%s%s", mmap_name, symbol_name) + 1;
         size = ALIGN(size, sizeof(u64));
-        ev.mmap.header.size = (sizeof(ev.mmap) -
-                        (sizeof(ev.mmap.filename) - size));
-        ev.mmap.pgoff = args.start;
-        ev.mmap.start = map->start;
-        ev.mmap.len   = map->end - ev.mmap.start;
-        ev.mmap.pid   = machine->pid;
-
-        return process(&ev, session);
-}
-
-static void thread__comm_adjust(struct thread *self, struct hists *hists)
-{
-        char *comm = self->comm;
-
-        if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-            (!symbol_conf.comm_list ||
-             strlist__has_entry(symbol_conf.comm_list, comm))) {
-                u16 slen = strlen(comm);
-
-                if (hists__new_col_len(hists, HISTC_COMM, slen))
-                        hists__set_col_len(hists, HISTC_THREAD, slen + 6);
-        }
+        event->mmap.header.type = PERF_RECORD_MMAP;
+        event->mmap.header.size = (sizeof(event->mmap) -
+                        (sizeof(event->mmap.filename) - size) + session->id_hdr_size);
+        event->mmap.pgoff = args.start;
+        event->mmap.start = map->start;
+        event->mmap.len   = map->end - event->mmap.start;
+        event->mmap.pid   = machine->pid;
+
+        err = process(event, &synth_sample, session);
+        free(event);
+
+        return err;
 }
 
-static int thread__set_comm_adjust(struct thread *self, const char *comm,
-                                   struct hists *hists)
-{
-        int ret = thread__set_comm(self, comm);
-
-        if (ret)
-                return ret;
-
-        thread__comm_adjust(self, hists);
-
-        return 0;
-}
-
-int event__process_comm(event_t *self, struct perf_session *session)
+int perf_event__process_comm(union perf_event *event,
+                             struct perf_sample *sample __used,
+                             struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, self->comm.tid);
+        struct thread *thread = perf_session__findnew(session, event->comm.tid);
 
-        dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
+        dump_printf(": %s:%d\n", event->comm.comm, event->comm.tid);
 
-        if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm,
-                                                      &session->hists)) {
+        if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
                 dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
                 return -1;
         }
@@ -376,27 +440,31 @@ int event__process_comm(event_t *self, struct perf_session *session)
         return 0;
 }
 
-int event__process_lost(event_t *self, struct perf_session *session)
+int perf_event__process_lost(union perf_event *event,
+                             struct perf_sample *sample __used,
+                             struct perf_session *session)
 {
-        dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
-        session->hists.stats.total_lost += self->lost.lost;
+        dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+                    event->lost.id, event->lost.lost);
+        session->hists.stats.total_lost += event->lost.lost;
         return 0;
 }
 
-static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
+static void perf_event__set_kernel_mmap_len(union perf_event *event,
+                                            struct map **maps)
 {
-        maps[MAP__FUNCTION]->start = self->mmap.start;
-        maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
+        maps[MAP__FUNCTION]->start = event->mmap.start;
+        maps[MAP__FUNCTION]->end   = event->mmap.start + event->mmap.len;
         /*
          * Be a bit paranoid here, some perf.data file came with
          * a zero sized synthesized MMAP event for the kernel.
          */
         if (maps[MAP__FUNCTION]->end == 0)
-                maps[MAP__FUNCTION]->end = ~0UL;
+                maps[MAP__FUNCTION]->end = ~0ULL;
 }
 
-static int event__process_kernel_mmap(event_t *self,
-                        struct perf_session *session)
+static int perf_event__process_kernel_mmap(union perf_event *event,
+                                           struct perf_session *session)
 {
         struct map *map;
         char kmmap_prefix[PATH_MAX];
@@ -404,9 +472,9 @@ static int event__process_kernel_mmap(event_t *self,
         enum dso_kernel_type kernel_type;
         bool is_kernel_mmap;
 
-        machine = perf_session__findnew_machine(session, self->mmap.pid);
+        machine = perf_session__findnew_machine(session, event->mmap.pid);
         if (!machine) {
-                pr_err("Can't find id %d's machine\n", self->mmap.pid);
+                pr_err("Can't find id %d's machine\n", event->mmap.pid);
                 goto out_problem;
         }
 
@@ -416,17 +484,17 @@ static int event__process_kernel_mmap(event_t *self,
         else
                 kernel_type = DSO_TYPE_GUEST_KERNEL;
 
-        is_kernel_mmap = memcmp(self->mmap.filename,
+        is_kernel_mmap = memcmp(event->mmap.filename,
                                 kmmap_prefix,
                                 strlen(kmmap_prefix)) == 0;
-        if (self->mmap.filename[0] == '/' ||
-            (!is_kernel_mmap && self->mmap.filename[0] == '[')) {
+        if (event->mmap.filename[0] == '/' ||
+            (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
 
                 char short_module_name[1024];
                 char *name, *dot;
 
-                if (self->mmap.filename[0] == '/') {
-                        name = strrchr(self->mmap.filename, '/');
+                if (event->mmap.filename[0] == '/') {
+                        name = strrchr(event->mmap.filename, '/');
                         if (name == NULL)
                                 goto out_problem;
 
@@ -438,10 +506,10 @@ static int event__process_kernel_mmap(event_t *self,
                                         "[%.*s]", (int)(dot - name), name);
                         strxfrchar(short_module_name, '-', '_');
                 } else
-                        strcpy(short_module_name, self->mmap.filename);
+                        strcpy(short_module_name, event->mmap.filename);
 
-                map = machine__new_module(machine, self->mmap.start,
-                                          self->mmap.filename);
+                map = machine__new_module(machine, event->mmap.start,
+                                          event->mmap.filename);
                 if (map == NULL)
                         goto out_problem;
 
@@ -451,9 +519,9 @@ static int event__process_kernel_mmap(event_t *self,
 
                 map->dso->short_name = name;
                 map->dso->sname_alloc = 1;
-                map->end = map->start + self->mmap.len;
+                map->end = map->start + event->mmap.len;
         } else if (is_kernel_mmap) {
-                const char *symbol_name = (self->mmap.filename +
+                const char *symbol_name = (event->mmap.filename +
                                 strlen(kmmap_prefix));
                 /*
                  * Should be there already, from the build-id table in
@@ -468,10 +536,19 @@ static int event__process_kernel_mmap(event_t *self,
                 if (__machine__create_kernel_maps(machine, kernel) < 0)
                         goto out_problem;
 
-                event_set_kernel_mmap_len(machine->vmlinux_maps, self);
-                perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-                                                         symbol_name,
-                                                         self->mmap.pgoff);
+                perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
+
+                /*
+                 * Avoid using a zero address (kptr_restrict) for the ref reloc
+                 * symbol. Effectively having zero here means that at record
+                 * time /proc/sys/kernel/kptr_restrict was non zero.
+                 */
+                if (event->mmap.pgoff != 0) {
+                        perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+                                                                 symbol_name,
+                                                                 event->mmap.pgoff);
+                }
+
                 if (machine__is_default_guest(machine)) {
                         /*
                          * preload dso of guest kernel and modules
@@ -485,21 +562,23 @@ out_problem:
         return -1;
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+int perf_event__process_mmap(union perf_event *event,
+                             struct perf_sample *sample __used,
+                             struct perf_session *session)
 {
         struct machine *machine;
         struct thread *thread;
         struct map *map;
-        u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
         int ret = 0;
 
-        dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
-                        self->mmap.pid, self->mmap.tid, self->mmap.start,
-                        self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+        dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
+                        event->mmap.pid, event->mmap.tid, event->mmap.start,
+                        event->mmap.len, event->mmap.pgoff, event->mmap.filename);
 
         if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
             cpumode == PERF_RECORD_MISC_KERNEL) {
-                ret = event__process_kernel_mmap(self, session);
+                ret = perf_event__process_kernel_mmap(event, session);
                 if (ret < 0)
                         goto out_problem;
                 return 0;
@@ -508,12 +587,12 @@ int event__process_mmap(event_t *self, struct perf_session *session)
         machine = perf_session__find_host_machine(session);
         if (machine == NULL)
                 goto out_problem;
-        thread = perf_session__findnew(session, self->mmap.pid);
+        thread = perf_session__findnew(session, event->mmap.pid);
         if (thread == NULL)
                 goto out_problem;
-        map = map__new(&machine->user_dsos, self->mmap.start,
-                        self->mmap.len, self->mmap.pgoff,
-                        self->mmap.pid, self->mmap.filename,
+        map = map__new(&machine->user_dsos, event->mmap.start,
+                        event->mmap.len, event->mmap.pgoff,
+                        event->mmap.pid, event->mmap.filename,
                         MAP__FUNCTION);
         if (map == NULL)
                 goto out_problem;
@@ -526,15 +605,17 @@ out_problem:
         return 0;
 }
 
-int event__process_task(event_t *self, struct perf_session *session)
+int perf_event__process_task(union perf_event *event,
+                             struct perf_sample *sample __used,
+                             struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, self->fork.tid);
-        struct thread *parent = perf_session__findnew(session, self->fork.ptid);
+        struct thread *thread = perf_session__findnew(session, event->fork.tid);
+        struct thread *parent = perf_session__findnew(session, event->fork.ptid);
 
-        dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
-                    self->fork.ppid, self->fork.ptid);
+        dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+                    event->fork.ppid, event->fork.ptid);
 
-        if (self->header.type == PERF_RECORD_EXIT) {
+        if (event->header.type == PERF_RECORD_EXIT) {
                 perf_session__remove_thread(session, thread);
                 return 0;
         }
@@ -548,19 +629,22 @@ int event__process_task(event_t *self, struct perf_session *session)
         return 0;
 }
 
-int event__process(event_t *event, struct perf_session *session)
+int perf_event__process(union perf_event *event, struct perf_sample *sample,
+                        struct perf_session *session)
 {
         switch (event->header.type) {
         case PERF_RECORD_COMM:
-                event__process_comm(event, session);
+                perf_event__process_comm(event, sample, session);
                 break;
         case PERF_RECORD_MMAP:
-                event__process_mmap(event, session);
+                perf_event__process_mmap(event, sample, session);
                 break;
         case PERF_RECORD_FORK:
         case PERF_RECORD_EXIT:
-                event__process_task(event, session);
+                perf_event__process_task(event, sample, session);
                 break;
+        case PERF_RECORD_LOST:
+                perf_event__process_lost(event, sample, session);
         default:
                 break;
         }
@@ -635,7 +719,7 @@ try_again:
                  * in the whole kernel symbol list.
                  */
                 if ((long long)al->addr < 0 &&
-                    cpumode == PERF_RECORD_MISC_KERNEL &&
+                    cpumode == PERF_RECORD_MISC_USER &&
                     machine && mg != &machine->kmaps) {
                         mg = &machine->kmaps;
                         goto try_again;
@@ -657,49 +741,15 @@ void thread__find_addr_location(struct thread *self,
                 al->sym = NULL;
 }
 
-static void dso__calc_col_width(struct dso *self, struct hists *hists)
-{
-        if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-            (!symbol_conf.dso_list ||
-             strlist__has_entry(symbol_conf.dso_list, self->name))) {
-                u16 slen = dso__name_len(self);
-                hists__new_col_len(hists, HISTC_DSO, slen);
-        }
-
-        self->slen_calculated = 1;
-}
-
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
-                             struct addr_location *al, struct sample_data *data,
-                             symbol_filter_t filter)
+int perf_event__preprocess_sample(const union perf_event *event,
+                                  struct perf_session *session,
+                                  struct addr_location *al,
+                                  struct perf_sample *sample,
+                                  symbol_filter_t filter)
 {
-        u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-        struct thread *thread;
-
-        event__parse_sample(self, session->sample_type, data);
-
-        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n",
-                    self->header.misc, data->pid, data->tid, data->ip,
-                    data->period, data->cpu);
+        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        struct thread *thread = perf_session__findnew(session, event->ip.pid);
 
-        if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-                unsigned int i;
-
-                dump_printf("... chain: nr:%Lu\n", data->callchain->nr);
-
-                if (!ip_callchain__valid(data->callchain, self)) {
-                        pr_debug("call-chain problem with event, "
-                                 "skipping it.\n");
-                        goto out_filtered;
-                }
-
-                if (dump_trace) {
-                        for (i = 0; i < data->callchain->nr; i++)
-                                dump_printf("..... %2d: %016Lx\n",
-                                            i, data->callchain->ips[i]);
-                }
-        }
-        thread = perf_session__findnew(session, self->ip.pid);
         if (thread == NULL)
                 return -1;
 
@@ -720,12 +770,12 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
                 machine__create_kernel_maps(&session->host_machine);
 
         thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
-                              self->ip.pid, self->ip.ip, al);
+                              event->ip.pid, event->ip.ip, al);
         dump_printf(" ...... dso: %s\n",
                     al->map ? al->map->dso->long_name :
                         al->level == 'H' ? "[hypervisor]" : "<not found>");
         al->sym = NULL;
-        al->cpu = data->cpu;
+        al->cpu = sample->cpu;
 
         if (al->map) {
                 if (symbol_conf.dso_list &&
@@ -736,23 +786,8 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
                         strlist__has_entry(symbol_conf.dso_list,
                                            al->map->dso->long_name)))))
                         goto out_filtered;
-                /*
-                 * We have to do this here as we may have a dso with no symbol
-                 * hit that has a name longer than the ones with symbols
-                 * sampled.
-                 */
-                if (!sort_dso.elide && !al->map->dso->slen_calculated)
-                        dso__calc_col_width(al->map->dso, &session->hists);
 
                 al->sym = map__find_symbol(al->map, al->addr, filter);
-        } else {
-                const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
-
-                if (hists__col_len(&session->hists, HISTC_DSO) < unresolved_col_width &&
-                    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
-                    !symbol_conf.dso_list)
-                        hists__set_col_len(&session->hists, HISTC_DSO,
-                                           unresolved_col_width);
         }
 
         if (symbol_conf.sym_list && al->sym &&
@@ -765,72 +800,3 @@ out_filtered:
         al->filtered = true;
         return 0;
 }
-
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data)
-{
-        const u64 *array = event->sample.array;
-
-        if (type & PERF_SAMPLE_IP) {
-                data->ip = event->ip.ip;
-                array++;
-        }
-
-        if (type & PERF_SAMPLE_TID) {
-                u32 *p = (u32 *)array;
-                data->pid = p[0];
-                data->tid = p[1];
-                array++;
-        }
-
-        if (type & PERF_SAMPLE_TIME) {
-                data->time = *array;
-                array++;
-        }
-
-        if (type & PERF_SAMPLE_ADDR) {
-                data->addr = *array;
-                array++;
-        }
-
-        data->id = -1ULL;
-        if (type & PERF_SAMPLE_ID) {
-                data->id = *array;
-                array++;
-        }
-
-        if (type & PERF_SAMPLE_STREAM_ID) {
-                data->stream_id = *array;
-                array++;
-        }
-
-        if (type & PERF_SAMPLE_CPU) {
-                u32 *p = (u32 *)array;
-                data->cpu = *p;
-                array++;
-        } else
-                data->cpu = -1;
-
-        if (type & PERF_SAMPLE_PERIOD) {
-                data->period = *array;
-                array++;
-        }
-
-        if (type & PERF_SAMPLE_READ) {
-                pr_debug("PERF_SAMPLE_READ is unsuported for now\n");
-                return -1;
-        }
-
-        if (type & PERF_SAMPLE_CALLCHAIN) {
-                data->callchain = (struct ip_callchain *)array;
-                array += 1 + data->callchain->nr;
-        }
-
-        if (type & PERF_SAMPLE_RAW) {
-                u32 *p = (u32 *)array;
-                data->raw_size = *p;
-                p++;
-                data->raw_data = p;
-        }
-
-        return 0;
-}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8e790dae7026..1d7f66488a88 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -56,12 +56,19 @@ struct read_event {
         u64 id;
 };
 
+
+#define PERF_SAMPLE_MASK                                \
+        (PERF_SAMPLE_IP | PERF_SAMPLE_TID |             \
+         PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |          \
+        PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |        \
+         PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+
 struct sample_event {
         struct perf_event_header        header;
         u64 array[];
 };
 
-struct sample_data {
+struct perf_sample {
         u64 ip;
         u32 pid, tid;
         u64 time;
@@ -85,6 +92,7 @@ struct build_id_event {
 };
 
 enum perf_user_event_type { /* above any possible kernel type */
+        PERF_RECORD_USER_TYPE_START             = 64,
         PERF_RECORD_HEADER_ATTR                 = 64,
         PERF_RECORD_HEADER_EVENT_TYPE           = 65,
         PERF_RECORD_HEADER_TRACING_DATA         = 66,
@@ -116,7 +124,7 @@ struct tracing_data_event {
         u32 size;
 };
 
-typedef union event_union {
+union perf_event {
         struct perf_event_header        header;
         struct ip_event                 ip;
         struct mmap_event               mmap;
@@ -129,39 +137,55 @@ typedef union event_union {
         struct event_type_event         event_type;
         struct tracing_data_event       tracing_data;
         struct build_id_event           build_id;
-} event_t;
+};
 
-void event__print_totals(void);
+void perf_event__print_totals(void);
 
 struct perf_session;
-
-typedef int (*event__handler_t)(event_t *event, struct perf_session *session);
-
-int event__synthesize_thread(pid_t pid, event__handler_t process,
+struct thread_map;
+
+typedef int (*perf_event__handler_synth_t)(union perf_event *event, 
+                                           struct perf_session *session);
+typedef int (*perf_event__handler_t)(union perf_event *event,
+                                     struct perf_sample *sample,
+                                      struct perf_session *session);
+
+int perf_event__synthesize_thread_map(struct thread_map *threads,
+                                      perf_event__handler_t process,
+                                      struct perf_session *session);
+int perf_event__synthesize_threads(perf_event__handler_t process,
+                                   struct perf_session *session);
+int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
+                                       struct perf_session *session,
+                                       struct machine *machine,
+                                       const char *symbol_name);
+
+int perf_event__synthesize_modules(perf_event__handler_t process,
+                                   struct perf_session *session,
+                                   struct machine *machine);
+
+int perf_event__process_comm(union perf_event *event, struct perf_sample *sample,
                              struct perf_session *session);
-void event__synthesize_threads(event__handler_t process,
-                               struct perf_session *session);
-int event__synthesize_kernel_mmap(event__handler_t process,
-                                struct perf_session *session,
-                                struct machine *machine,
-                                const char *symbol_name);
-
-int event__synthesize_modules(event__handler_t process,
-                              struct perf_session *session,
-                              struct machine *machine);
-
-int event__process_comm(event_t *self, struct perf_session *session);
-int event__process_lost(event_t *self, struct perf_session *session);
-int event__process_mmap(event_t *self, struct perf_session *session);
-int event__process_task(event_t *self, struct perf_session *session);
-int event__process(event_t *event, struct perf_session *session);
+int perf_event__process_lost(union perf_event *event, struct perf_sample *sample,
+                             struct perf_session *session);
+int perf_event__process_mmap(union perf_event *event, struct perf_sample *sample,
+                             struct perf_session *session);
+int perf_event__process_task(union perf_event *event, struct perf_sample *sample,
+                             struct perf_session *session);
+int perf_event__process(union perf_event *event, struct perf_sample *sample,
+                        struct perf_session *session);
 
 struct addr_location;
-int event__preprocess_sample(const event_t *self, struct perf_session *session,
-                             struct addr_location *al, struct sample_data *data,
-                             symbol_filter_t filter);
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data);
+int perf_event__preprocess_sample(const union perf_event *self,
+                                  struct perf_session *session,
+                                  struct addr_location *al,
+                                  struct perf_sample *sample,
+                                  symbol_filter_t filter);
+
+const char *perf_event__name(unsigned int id);
 
-extern const char *event__name[];
+int perf_event__parse_sample(const union perf_event *event, u64 type,
+                             int sample_size, bool sample_id_all,
+                             struct perf_sample *sample);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
new file mode 100644
index 000000000000..b021ea9265c3
--- /dev/null
+++ b/tools/perf/util/evlist.c
@@ -0,0 +1,500 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include <poll.h>
+#include "cpumap.h"
+#include "thread_map.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "util.h"
+
+#include <sys/mman.h>
+
+#include <linux/bitops.h>
+#include <linux/hash.h>
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+                       struct thread_map *threads)
+{
+        int i;
+
+        for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+                INIT_HLIST_HEAD(&evlist->heads[i]);
+        INIT_LIST_HEAD(&evlist->entries);
+        perf_evlist__set_maps(evlist, cpus, threads);
+}
+
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+                                     struct thread_map *threads)
+{
+        struct perf_evlist *evlist = zalloc(sizeof(*evlist));
+
+        if (evlist != NULL)
+                perf_evlist__init(evlist, cpus, threads);
+
+        return evlist;
+}
+
+static void perf_evlist__purge(struct perf_evlist *evlist)
+{
+        struct perf_evsel *pos, *n;
+
+        list_for_each_entry_safe(pos, n, &evlist->entries, node) {
+                list_del_init(&pos->node);
+                perf_evsel__delete(pos);
+        }
+
+        evlist->nr_entries = 0;
+}
+
+void perf_evlist__exit(struct perf_evlist *evlist)
+{
+        free(evlist->mmap);
+        free(evlist->pollfd);
+        evlist->mmap = NULL;
+        evlist->pollfd = NULL;
+}
+
+void perf_evlist__delete(struct perf_evlist *evlist)
+{
+        perf_evlist__purge(evlist);
+        perf_evlist__exit(evlist);
+        free(evlist);
+}
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
+{
+        list_add_tail(&entry->node, &evlist->entries);
+        ++evlist->nr_entries;
+}
+
+int perf_evlist__add_default(struct perf_evlist *evlist)
+{
+        struct perf_event_attr attr = {
+                .type = PERF_TYPE_HARDWARE,
+                .config = PERF_COUNT_HW_CPU_CYCLES,
+        };
+        struct perf_evsel *evsel = perf_evsel__new(&attr, 0);
+
+        if (evsel == NULL)
+                return -ENOMEM;
+
+        perf_evlist__add(evlist, evsel);
+        return 0;
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+{
+        int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
+        evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
+        return evlist->pollfd != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+        fcntl(fd, F_SETFL, O_NONBLOCK);
+        evlist->pollfd[evlist->nr_fds].fd = fd;
+        evlist->pollfd[evlist->nr_fds].events = POLLIN;
+        evlist->nr_fds++;
+}
+
+static void perf_evlist__id_hash(struct perf_evlist *evlist,
+                                 struct perf_evsel *evsel,
+                                 int cpu, int thread, u64 id)
+{
+        int hash;
+        struct perf_sample_id *sid = SID(evsel, cpu, thread);
+
+        sid->id = id;
+        sid->evsel = evsel;
+        hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
+        hlist_add_head(&sid->node, &evlist->heads[hash]);
+}
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+                         int cpu, int thread, u64 id)
+{
+        perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+        evsel->id[evsel->ids++] = id;
+}
+
+static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+                                  struct perf_evsel *evsel,
+                                  int cpu, int thread, int fd)
+{
+        u64 read_data[4] = { 0, };
+        int id_idx = 1; /* The first entry is the counter value */
+
+        if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
+            read(fd, &read_data, sizeof(read_data)) == -1)
+                return -1;
+
+        if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                ++id_idx;
+        if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                ++id_idx;
+
+        perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]);
+        return 0;
+}
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
+{
+        struct hlist_head *head;
+        struct hlist_node *pos;
+        struct perf_sample_id *sid;
+        int hash;
+
+        if (evlist->nr_entries == 1)
+                return list_entry(evlist->entries.next, struct perf_evsel, node);
+
+        hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+        head = &evlist->heads[hash];
+
+        hlist_for_each_entry(sid, pos, head, node)
+                if (sid->id == id)
+                        return sid->evsel;
+        return NULL;
+}
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+        /* XXX Move this to perf.c, making it generally available */
+        unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+        struct perf_mmap *md = &evlist->mmap[idx];
+        unsigned int head = perf_mmap__read_head(md);
+        unsigned int old = md->prev;
+        unsigned char *data = md->base + page_size;
+        union perf_event *event = NULL;
+
+        if (evlist->overwrite) {
+                /*
+                 * If we're further behind than half the buffer, there's a chance
+                 * the writer will bite our tail and mess up the samples under us.
+                 *
+                 * If we somehow ended up ahead of the head, we got messed up.
+                 *
+                 * In either case, truncate and restart at head.
+                 */
+                int diff = head - old;
+                if (diff > md->mask / 2 || diff < 0) {
+                        fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
+
+                        /*
+                         * head points to a known good entry, start there.
+                         */
+                        old = head;
+                }
+        }
+
+        if (old != head) {
+                size_t size;
+
+                event = (union perf_event *)&data[old & md->mask];
+                size = event->header.size;
+
+                /*
+                 * Event straddles the mmap boundary -- header should always
+                 * be inside due to u64 alignment of output.
+                 */
+                if ((old & md->mask) + size != ((old + size) & md->mask)) {
+                        unsigned int offset = old;
+                        unsigned int len = min(sizeof(*event), size), cpy;
+                        void *dst = &evlist->event_copy;
+
+                        do {
+                                cpy = min(md->mask + 1 - (offset & md->mask), len);
+                                memcpy(dst, &data[offset & md->mask], cpy);
+                                offset += cpy;
+                                dst += cpy;
+                                len -= cpy;
+                        } while (len);
+
+                        event = &evlist->event_copy;
+                }
+
+                old += size;
+        }
+
+        md->prev = old;
+
+        if (!evlist->overwrite)
+                perf_mmap__write_tail(md, old);
+
+        return event;
+}
+
+void perf_evlist__munmap(struct perf_evlist *evlist)
+{
+        int i;
+
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                if (evlist->mmap[i].base != NULL) {
+                        munmap(evlist->mmap[i].base, evlist->mmap_len);
+                        evlist->mmap[i].base = NULL;
+                }
+        }
+
+        free(evlist->mmap);
+        evlist->mmap = NULL;
+}
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+{
+        evlist->nr_mmaps = evlist->cpus->nr;
+        if (evlist->cpus->map[0] == -1)
+                evlist->nr_mmaps = evlist->threads->nr;
+        evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
+        return evlist->mmap != NULL ? 0 : -ENOMEM;
+}
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
+                               int idx, int prot, int mask, int fd)
+{
+        evlist->mmap[idx].prev = 0;
+        evlist->mmap[idx].mask = mask;
+        evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
+                                      MAP_SHARED, fd, 0);
+        if (evlist->mmap[idx].base == MAP_FAILED)
+                return -1;
+
+        perf_evlist__add_pollfd(evlist, fd);
+        return 0;
+}
+
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+{
+        struct perf_evsel *evsel;
+        int cpu, thread;
+
+        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+                int output = -1;
+
+                for (thread = 0; thread < evlist->threads->nr; thread++) {
+                        list_for_each_entry(evsel, &evlist->entries, node) {
+                                int fd = FD(evsel, cpu, thread);
+
+                                if (output == -1) {
+                                        output = fd;
+                                        if (__perf_evlist__mmap(evlist, cpu,
+                                                                prot, mask, output) < 0)
+                                                goto out_unmap;
+                                } else {
+                                        if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+                                                goto out_unmap;
+                                }
+
+                                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+                                    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+                                        goto out_unmap;
+                        }
+                }
+        }
+
+        return 0;
+
+out_unmap:
+        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+                if (evlist->mmap[cpu].base != NULL) {
+                        munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+                        evlist->mmap[cpu].base = NULL;
+                }
+        }
+        return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+{
+        struct perf_evsel *evsel;
+        int thread;
+
+        for (thread = 0; thread < evlist->threads->nr; thread++) {
+                int output = -1;
+
+                list_for_each_entry(evsel, &evlist->entries, node) {
+                        int fd = FD(evsel, 0, thread);
+
+                        if (output == -1) {
+                                output = fd;
+                                if (__perf_evlist__mmap(evlist, thread,
+                                                        prot, mask, output) < 0)
+                                        goto out_unmap;
+                        } else {
+                                if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+                                        goto out_unmap;
+                        }
+
+                        if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+                            perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
+                                goto out_unmap;
+                }
+        }
+
+        return 0;
+
+out_unmap:
+        for (thread = 0; thread < evlist->threads->nr; thread++) {
+                if (evlist->mmap[thread].base != NULL) {
+                        munmap(evlist->mmap[thread].base, evlist->mmap_len);
+                        evlist->mmap[thread].base = NULL;
+                }
+        }
+        return -1;
+}
+
+/** perf_evlist__mmap - Create per cpu maps to receive events
+ *
+ * @evlist - list of events
+ * @pages - map length in pages
+ * @overwrite - overwrite older events?
+ *
+ * If overwrite is false the user needs to signal event consuption using:
+ *
+ *      struct perf_mmap *m = &evlist->mmap[cpu];
+ *      unsigned int head = perf_mmap__read_head(m);
+ *
+ *      perf_mmap__write_tail(m, head)
+ *
+ * Using perf_evlist__read_on_cpu does this automatically.
+ */
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
+{
+        unsigned int page_size = sysconf(_SC_PAGE_SIZE);
+        int mask = pages * page_size - 1;
+        struct perf_evsel *evsel;
+        const struct cpu_map *cpus = evlist->cpus;
+        const struct thread_map *threads = evlist->threads;
+        int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+
+        if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
+                return -ENOMEM;
+
+        if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+                return -ENOMEM;
+
+        evlist->overwrite = overwrite;
+        evlist->mmap_len = (pages + 1) * page_size;
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+                    evsel->sample_id == NULL &&
+                    perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
+                        return -ENOMEM;
+        }
+
+        if (evlist->cpus->map[0] == -1)
+                return perf_evlist__mmap_per_thread(evlist, prot, mask);
+
+        return perf_evlist__mmap_per_cpu(evlist, prot, mask);
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+                             pid_t target_tid, const char *cpu_list)
+{
+        evlist->threads = thread_map__new(target_pid, target_tid);
+
+        if (evlist->threads == NULL)
+                return -1;
+
+        if (cpu_list == NULL && target_tid != -1)
+                evlist->cpus = cpu_map__dummy_new();
+        else
+                evlist->cpus = cpu_map__new(cpu_list);
+
+        if (evlist->cpus == NULL)
+                goto out_delete_threads;
+
+        return 0;
+
+out_delete_threads:
+        thread_map__delete(evlist->threads);
+        return -1;
+}
+
+void perf_evlist__delete_maps(struct perf_evlist *evlist)
+{
+        cpu_map__delete(evlist->cpus);
+        thread_map__delete(evlist->threads);
+        evlist->cpus    = NULL;
+        evlist->threads = NULL;
+}
+
+int perf_evlist__set_filters(struct perf_evlist *evlist)
+{
+        const struct thread_map *threads = evlist->threads;
+        const struct cpu_map *cpus = evlist->cpus;
+        struct perf_evsel *evsel;
+        char *filter;
+        int thread;
+        int cpu;
+        int err;
+        int fd;
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                filter = evsel->filter;
+                if (!filter)
+                        continue;
+                for (cpu = 0; cpu < cpus->nr; cpu++) {
+                        for (thread = 0; thread < threads->nr; thread++) {
+                                fd = FD(evsel, cpu, thread);
+                                err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter);
+                                if (err)
+                                        return err;
+                        }
+                }
+        }
+
+        return 0;
+}
+
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
+{
+        struct perf_evsel *pos, *first;
+
+        pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+        list_for_each_entry_continue(pos, &evlist->entries, node) {
+                if (first->attr.sample_type != pos->attr.sample_type)
+                        return false;
+        }
+
+        return true;
+}
+
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+{
+        struct perf_evsel *first;
+
+        first = list_entry(evlist->entries.next, struct perf_evsel, node);
+        return first->attr.sample_type;
+}
+
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
+{
+        struct perf_evsel *pos, *first;
+
+        pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+        list_for_each_entry_continue(pos, &evlist->entries, node) {
+                if (first->attr.sample_id_all != pos->attr.sample_id_all)
+                        return false;
+        }
+
+        return true;
+}
+
+bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+{
+        struct perf_evsel *first;
+
+        first = list_entry(evlist->entries.next, struct perf_evsel, node);
+        return first->attr.sample_id_all;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
new file mode 100644
index 000000000000..b2b862374f37
--- /dev/null
+++ b/tools/perf/util/evlist.h
@@ -0,0 +1,74 @@
+#ifndef __PERF_EVLIST_H
+#define __PERF_EVLIST_H 1
+
+#include <linux/list.h>
+#include "../perf.h"
+#include "event.h"
+
+struct pollfd;
+struct thread_map;
+struct cpu_map;
+
+#define PERF_EVLIST__HLIST_BITS 8
+#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
+
+struct perf_evlist {
+        struct list_head entries;
+        struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
+        int              nr_entries;
+        int              nr_fds;
+        int              nr_mmaps;
+        int              mmap_len;
+        bool             overwrite;
+        union perf_event event_copy;
+        struct perf_mmap *mmap;
+        struct pollfd    *pollfd;
+        struct thread_map *threads;
+        struct cpu_map    *cpus;
+};
+
+struct perf_evsel;
+
+struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
+                                     struct thread_map *threads);
+void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
+                       struct thread_map *threads);
+void perf_evlist__exit(struct perf_evlist *evlist);
+void perf_evlist__delete(struct perf_evlist *evlist);
+
+void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
+int perf_evlist__add_default(struct perf_evlist *evlist);
+
+void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
+                         int cpu, int thread, u64 id);
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+
+struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
+
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
+
+int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
+int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
+void perf_evlist__munmap(struct perf_evlist *evlist);
+
+static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
+                                         struct cpu_map *cpus,
+                                         struct thread_map *threads)
+{
+        evlist->cpus    = cpus;
+        evlist->threads = threads;
+}
+
+int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
+                             pid_t target_tid, const char *cpu_list);
+void perf_evlist__delete_maps(struct perf_evlist *evlist);
+int perf_evlist__set_filters(struct perf_evlist *evlist);
+
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const 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);
+#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
new file mode 100644
index 000000000000..0239eb87b232
--- /dev/null
+++ b/tools/perf/util/evsel.c
@@ -0,0 +1,440 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "evsel.h"
+#include "evlist.h"
+#include "util.h"
+#include "cpumap.h"
+#include "thread_map.h"
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+int __perf_evsel__sample_size(u64 sample_type)
+{
+        u64 mask = sample_type & PERF_SAMPLE_MASK;
+        int size = 0;
+        int i;
+
+        for (i = 0; i < 64; i++) {
+                if (mask & (1ULL << i))
+                        size++;
+        }
+
+        size *= sizeof(u64);
+
+        return size;
+}
+
+void perf_evsel__init(struct perf_evsel *evsel,
+                      struct perf_event_attr *attr, int idx)
+{
+        evsel->idx         = idx;
+        evsel->attr        = *attr;
+        INIT_LIST_HEAD(&evsel->node);
+}
+
+struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
+{
+        struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+
+        if (evsel != NULL)
+                perf_evsel__init(evsel, attr, idx);
+
+        return evsel;
+}
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+        int cpu, thread;
+        evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+        if (evsel->fd) {
+                for (cpu = 0; cpu < ncpus; cpu++) {
+                        for (thread = 0; thread < nthreads; thread++) {
+                                FD(evsel, cpu, thread) = -1;
+                        }
+                }
+        }
+
+        return evsel->fd != NULL ? 0 : -ENOMEM;
+}
+
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+        evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
+        if (evsel->sample_id == NULL)
+                return -ENOMEM;
+
+        evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
+        if (evsel->id == NULL) {
+                xyarray__delete(evsel->sample_id);
+                evsel->sample_id = NULL;
+                return -ENOMEM;
+        }
+
+        return 0;
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+{
+        evsel->counts = zalloc((sizeof(*evsel->counts) +
+                                (ncpus * sizeof(struct perf_counts_values))));
+        return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_fd(struct perf_evsel *evsel)
+{
+        xyarray__delete(evsel->fd);
+        evsel->fd = NULL;
+}
+
+void perf_evsel__free_id(struct perf_evsel *evsel)
+{
+        xyarray__delete(evsel->sample_id);
+        evsel->sample_id = NULL;
+        free(evsel->id);
+        evsel->id = NULL;
+}
+
+void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+        int cpu, thread;
+
+        for (cpu = 0; cpu < ncpus; cpu++)
+                for (thread = 0; thread < nthreads; ++thread) {
+                        close(FD(evsel, cpu, thread));
+                        FD(evsel, cpu, thread) = -1;
+                }
+}
+
+void perf_evsel__exit(struct perf_evsel *evsel)
+{
+        assert(list_empty(&evsel->node));
+        xyarray__delete(evsel->fd);
+        xyarray__delete(evsel->sample_id);
+        free(evsel->id);
+}
+
+void perf_evsel__delete(struct perf_evsel *evsel)
+{
+        perf_evsel__exit(evsel);
+        close_cgroup(evsel->cgrp);
+        free(evsel->name);
+        free(evsel);
+}
+
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+                              int cpu, int thread, bool scale)
+{
+        struct perf_counts_values count;
+        size_t nv = scale ? 3 : 1;
+
+        if (FD(evsel, cpu, thread) < 0)
+                return -EINVAL;
+
+        if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+                return -ENOMEM;
+
+        if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
+                return -errno;
+
+        if (scale) {
+                if (count.run == 0)
+                        count.val = 0;
+                else if (count.run < count.ena)
+                        count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
+        } else
+                count.ena = count.run = 0;
+
+        evsel->counts->cpu[cpu] = count;
+        return 0;
+}
+
+int __perf_evsel__read(struct perf_evsel *evsel,
+                       int ncpus, int nthreads, bool scale)
+{
+        size_t nv = scale ? 3 : 1;
+        int cpu, thread;
+        struct perf_counts_values *aggr = &evsel->counts->aggr, count;
+
+        aggr->val = aggr->ena = aggr->run = 0;
+
+        for (cpu = 0; cpu < ncpus; cpu++) {
+                for (thread = 0; thread < nthreads; thread++) {
+                        if (FD(evsel, cpu, thread) < 0)
+                                continue;
+
+                        if (readn(FD(evsel, cpu, thread),
+                                  &count, nv * sizeof(u64)) < 0)
+                                return -errno;
+
+                        aggr->val += count.val;
+                        if (scale) {
+                                aggr->ena += count.ena;
+                                aggr->run += count.run;
+                        }
+                }
+        }
+
+        evsel->counts->scaled = 0;
+        if (scale) {
+                if (aggr->run == 0) {
+                        evsel->counts->scaled = -1;
+                        aggr->val = 0;
+                        return 0;
+                }
+
+                if (aggr->run < aggr->ena) {
+                        evsel->counts->scaled = 1;
+                        aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
+                }
+        } else
+                aggr->ena = aggr->run = 0;
+
+        return 0;
+}
+
+static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+                              struct thread_map *threads, bool group)
+{
+        int cpu, thread;
+        unsigned long flags = 0;
+        int pid = -1;
+
+        if (evsel->fd == NULL &&
+            perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+                return -1;
+
+        if (evsel->cgrp) {
+                flags = PERF_FLAG_PID_CGROUP;
+                pid = evsel->cgrp->fd;
+        }
+
+        for (cpu = 0; cpu < cpus->nr; cpu++) {
+                int group_fd = -1;
+
+                for (thread = 0; thread < threads->nr; thread++) {
+
+                        if (!evsel->cgrp)
+                                pid = threads->map[thread];
+
+                        FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
+                                                                     pid,
+                                                                     cpus->map[cpu],
+                                                                     group_fd, flags);
+                        if (FD(evsel, cpu, thread) < 0)
+                                goto out_close;
+
+                        if (group && group_fd == -1)
+                                group_fd = FD(evsel, cpu, thread);
+                }
+        }
+
+        return 0;
+
+out_close:
+        do {
+                while (--thread >= 0) {
+                        close(FD(evsel, cpu, thread));
+                        FD(evsel, cpu, thread) = -1;
+                }
+                thread = threads->nr;
+        } while (--cpu >= 0);
+        return -1;
+}
+
+static struct {
+        struct cpu_map map;
+        int cpus[1];
+} empty_cpu_map = {
+        .map.nr = 1,
+        .cpus   = { -1, },
+};
+
+static struct {
+        struct thread_map map;
+        int threads[1];
+} empty_thread_map = {
+        .map.nr  = 1,
+        .threads = { -1, },
+};
+
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+                     struct thread_map *threads, bool group)
+{
+        if (cpus == NULL) {
+                /* Work around old compiler warnings about strict aliasing */
+                cpus = &empty_cpu_map.map;
+        }
+
+        if (threads == NULL)
+                threads = &empty_thread_map.map;
+
+        return __perf_evsel__open(evsel, cpus, threads, group);
+}
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+                             struct cpu_map *cpus, bool group)
+{
+        return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
+}
+
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+                                struct thread_map *threads, bool group)
+{
+        return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
+}
+
+static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
+                                       struct perf_sample *sample)
+{
+        const u64 *array = event->sample.array;
+
+        array += ((event->header.size -
+                   sizeof(event->header)) / sizeof(u64)) - 1;
+
+        if (type & PERF_SAMPLE_CPU) {
+                u32 *p = (u32 *)array;
+                sample->cpu = *p;
+                array--;
+        }
+
+        if (type & PERF_SAMPLE_STREAM_ID) {
+                sample->stream_id = *array;
+                array--;
+        }
+
+        if (type & PERF_SAMPLE_ID) {
+                sample->id = *array;
+                array--;
+        }
+
+        if (type & PERF_SAMPLE_TIME) {
+                sample->time = *array;
+                array--;
+        }
+
+        if (type & PERF_SAMPLE_TID) {
+                u32 *p = (u32 *)array;
+                sample->pid = p[0];
+                sample->tid = p[1];
+        }
+
+        return 0;
+}
+
+static bool sample_overlap(const union perf_event *event,
+                           const void *offset, u64 size)
+{
+        const void *base = event;
+
+        if (offset + size > base + event->header.size)
+                return true;
+
+        return false;
+}
+
+int perf_event__parse_sample(const union perf_event *event, u64 type,
+                             int sample_size, bool sample_id_all,
+                             struct perf_sample *data)
+{
+        const u64 *array;
+
+        data->cpu = data->pid = data->tid = -1;
+        data->stream_id = data->id = data->time = -1ULL;
+
+        if (event->header.type != PERF_RECORD_SAMPLE) {
+                if (!sample_id_all)
+                        return 0;
+                return perf_event__parse_id_sample(event, type, data);
+        }
+
+        array = event->sample.array;
+
+        if (sample_size + sizeof(event->header) > event->header.size)
+                return -EFAULT;
+
+        if (type & PERF_SAMPLE_IP) {
+                data->ip = event->ip.ip;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_TID) {
+                u32 *p = (u32 *)array;
+                data->pid = p[0];
+                data->tid = p[1];
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_TIME) {
+                data->time = *array;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_ADDR) {
+                data->addr = *array;
+                array++;
+        }
+
+        data->id = -1ULL;
+        if (type & PERF_SAMPLE_ID) {
+                data->id = *array;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_STREAM_ID) {
+                data->stream_id = *array;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_CPU) {
+                u32 *p = (u32 *)array;
+                data->cpu = *p;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_PERIOD) {
+                data->period = *array;
+                array++;
+        }
+
+        if (type & PERF_SAMPLE_READ) {
+                fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n");
+                return -1;
+        }
+
+        if (type & PERF_SAMPLE_CALLCHAIN) {
+                if (sample_overlap(event, array, sizeof(data->callchain->nr)))
+                        return -EFAULT;
+
+                data->callchain = (struct ip_callchain *)array;
+
+                if (sample_overlap(event, array, data->callchain->nr))
+                        return -EFAULT;
+
+                array += 1 + data->callchain->nr;
+        }
+
+        if (type & PERF_SAMPLE_RAW) {
+                u32 *p = (u32 *)array;
+
+                if (sample_overlap(event, array, sizeof(u32)))
+                        return -EFAULT;
+
+                data->raw_size = *p;
+                p++;
+
+                if (sample_overlap(event, p, data->raw_size))
+                        return -EFAULT;
+
+                data->raw_data = p;
+        }
+
+        return 0;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
new file mode 100644
index 000000000000..7e9366e4490b
--- /dev/null
+++ b/tools/perf/util/evsel.h
@@ -0,0 +1,159 @@
+#ifndef __PERF_EVSEL_H
+#define __PERF_EVSEL_H 1
+
+#include <linux/list.h>
+#include <stdbool.h>
+#include "../../../include/linux/perf_event.h"
+#include "types.h"
+#include "xyarray.h"
+#include "cgroup.h"
+#include "hist.h"
+ 
+struct perf_counts_values {
+        union {
+                struct {
+                        u64 val;
+                        u64 ena;
+                        u64 run;
+                };
+                u64 values[3];
+        };
+};
+
+struct perf_counts {
+        s8                        scaled;
+        struct perf_counts_values aggr;
+        struct perf_counts_values cpu[];
+};
+
+struct perf_evsel;
+
+/*
+ * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
+ * more than one entry in the evlist.
+ */
+struct perf_sample_id {
+        struct hlist_node       node;
+        u64                     id;
+        struct perf_evsel       *evsel;
+};
+
+/** struct perf_evsel - event selector
+ *
+ * @name - Can be set to retain the original event name passed by the user,
+ *         so that when showing results in tools such as 'perf stat', we
+ *         show the name used, not some alias.
+ */
+struct perf_evsel {
+        struct list_head        node;
+        struct perf_event_attr  attr;
+        char                    *filter;
+        struct xyarray          *fd;
+        struct xyarray          *sample_id;
+        u64                     *id;
+        struct perf_counts      *counts;
+        int                     idx;
+        int                     ids;
+        struct hists            hists;
+        char                    *name;
+        union {
+                void            *priv;
+                off_t           id_offset;
+        };
+        struct cgroup_sel       *cgrp;
+};
+
+struct cpu_map;
+struct thread_map;
+struct perf_evlist;
+
+struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
+void perf_evsel__init(struct perf_evsel *evsel,
+                      struct perf_event_attr *attr, int idx);
+void perf_evsel__exit(struct perf_evsel *evsel);
+void perf_evsel__delete(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_fd(struct perf_evsel *evsel);
+void perf_evsel__free_id(struct perf_evsel *evsel);
+void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
+                             struct cpu_map *cpus, bool group);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel,
+                                struct thread_map *threads, bool group);
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+                     struct thread_map *threads, bool group);
+
+#define perf_evsel__match(evsel, t, c)          \
+        (evsel->attr.type == PERF_TYPE_##t &&   \
+         evsel->attr.config == PERF_COUNT_##c)
+
+int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+                              int cpu, int thread, bool scale);
+
+/**
+ * perf_evsel__read_on_cpu - Read out the results on a CPU and thread
+ *
+ * @evsel - event selector to read value
+ * @cpu - CPU of interest
+ * @thread - thread of interest
+ */
+static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
+                                          int cpu, int thread)
+{
+        return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
+}
+
+/**
+ * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
+ *
+ * @evsel - event selector to read value
+ * @cpu - CPU of interest
+ * @thread - thread of interest
+ */
+static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
+                                                 int cpu, int thread)
+{
+        return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
+}
+
+int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
+                       bool scale);
+
+/**
+ * perf_evsel__read - Read the aggregate results on all CPUs
+ *
+ * @evsel - event selector to read value
+ * @ncpus - Number of cpus affected, from zero
+ * @nthreads - Number of threads affected, from zero
+ */
+static inline int perf_evsel__read(struct perf_evsel *evsel,
+                                    int ncpus, int nthreads)
+{
+        return __perf_evsel__read(evsel, ncpus, nthreads, false);
+}
+
+/**
+ * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
+ *
+ * @evsel - event selector to read value
+ * @ncpus - Number of cpus affected, from zero
+ * @nthreads - Number of threads affected, from zero
+ */
+static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
+                                          int ncpus, int nthreads)
+{
+        return __perf_evsel__read(evsel, ncpus, nthreads, true);
+}
+
+int __perf_evsel__sample_size(u64 sample_type);
+
+static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
+{
+        return __perf_evsel__sample_size(evsel->attr.sample_type);
+}
+
+#endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c
index 67eeff571568..7adf4ad15d8f 100644
--- a/tools/perf/util/exec_cmd.c
+++ b/tools/perf/util/exec_cmd.c
@@ -11,31 +11,12 @@ static const char *argv0_path;
 
 const char *system_path(const char *path)
 {
-#ifdef RUNTIME_PREFIX
-        static const char *prefix;
-#else
         static const char *prefix = PREFIX;
-#endif
         struct strbuf d = STRBUF_INIT;
 
         if (is_absolute_path(path))
                 return path;
 
-#ifdef RUNTIME_PREFIX
-        assert(argv0_path);
-        assert(is_absolute_path(argv0_path));
-
-        if (!prefix &&
-            !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) &&
-            !(prefix = strip_path_suffix(argv0_path, BINDIR)) &&
-            !(prefix = strip_path_suffix(argv0_path, "perf"))) {
-                prefix = PREFIX;
-                fprintf(stderr, "RUNTIME_PREFIX requested, "
-                                "but prefix computation failed.  "
-                                "Using static fallback '%s'.\n", prefix);
-        }
-#endif
-
         strbuf_addf(&d, "%s/%s", prefix, path);
         path = strbuf_detach(&d, NULL);
         return path;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d7e67b167ea3..afb0849fe530 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -8,6 +8,8 @@
 #include <linux/list.h>
 #include <linux/kernel.h>
 
+#include "evlist.h"
+#include "evsel.h"
 #include "util.h"
 #include "header.h"
 #include "../perf.h"
@@ -18,89 +20,6 @@
 
 static bool no_buildid_cache = false;
 
-/*
- * Create new perf.data header attribute:
- */
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr)
-{
-        struct perf_header_attr *self = malloc(sizeof(*self));
-
-        if (self != NULL) {
-                self->attr = *attr;
-                self->ids  = 0;
-                self->size = 1;
-                self->id   = malloc(sizeof(u64));
-                if (self->id == NULL) {
-                        free(self);
-                        self = NULL;
-                }
-        }
-
-        return self;
-}
-
-void perf_header_attr__delete(struct perf_header_attr *self)
-{
-        free(self->id);
-        free(self);
-}
-
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id)
-{
-        int pos = self->ids;
-
-        self->ids++;
-        if (self->ids > self->size) {
-                int nsize = self->size * 2;
-                u64 *nid = realloc(self->id, nsize * sizeof(u64));
-
-                if (nid == NULL)
-                        return -1;
-
-                self->size = nsize;
-                self->id = nid;
-        }
-        self->id[pos] = id;
-        return 0;
-}
-
-int perf_header__init(struct perf_header *self)
-{
-        self->size = 1;
-        self->attr = malloc(sizeof(void *));
-        return self->attr == NULL ? -ENOMEM : 0;
-}
-
-void perf_header__exit(struct perf_header *self)
-{
-        int i;
-        for (i = 0; i < self->attrs; ++i)
-                perf_header_attr__delete(self->attr[i]);
-        free(self->attr);
-}
-
-int perf_header__add_attr(struct perf_header *self,
-                          struct perf_header_attr *attr)
-{
-        if (self->frozen)
-                return -1;
-
-        if (self->attrs == self->size) {
-                int nsize = self->size * 2;
-                struct perf_header_attr **nattr;
-
-                nattr = realloc(self->attr, nsize * sizeof(void *));
-                if (nattr == NULL)
-                        return -1;
-
-                self->size = nsize;
-                self->attr = nattr;
-        }
-
-        self->attr[self->attrs++] = attr;
-        return 0;
-}
-
 static int event_count;
 static struct perf_trace_event_type *events;
 
@@ -147,14 +66,19 @@ struct perf_file_attr {
         struct perf_file_section        ids;
 };
 
-void perf_header__set_feat(struct perf_header *self, int feat)
+void perf_header__set_feat(struct perf_header *header, int feat)
+{
+        set_bit(feat, header->adds_features);
+}
+
+void perf_header__clear_feat(struct perf_header *header, int feat)
 {
-        set_bit(feat, self->adds_features);
+        clear_bit(feat, header->adds_features);
 }
 
-bool perf_header__has_feat(const struct perf_header *self, int feat)
+bool perf_header__has_feat(const struct perf_header *header, int feat)
 {
-        return test_bit(feat, self->adds_features);
+        return test_bit(feat, header->adds_features);
 }
 
 static int do_write(int fd, const void *buf, size_t size)
@@ -223,22 +147,22 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
         return 0;
 }
 
-static int machine__write_buildid_table(struct machine *self, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
 {
         int err;
         u16 kmisc = PERF_RECORD_MISC_KERNEL,
             umisc = PERF_RECORD_MISC_USER;
 
-        if (!machine__is_host(self)) {
+        if (!machine__is_host(machine)) {
                 kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
                 umisc = PERF_RECORD_MISC_GUEST_USER;
         }
 
-        err = __dsos__write_buildid_table(&self->kernel_dsos, self->pid,
+        err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
                                           kmisc, fd);
         if (err == 0)
-                err = __dsos__write_buildid_table(&self->user_dsos,
-                                                  self->pid, umisc, fd);
+                err = __dsos__write_buildid_table(&machine->user_dsos,
+                                                  machine->pid, umisc, fd);
         return err;
 }
 
@@ -265,15 +189,24 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
                           const char *name, bool is_kallsyms)
 {
         const size_t size = PATH_MAX;
-        char *filename = malloc(size),
+        char *realname, *filename = malloc(size),
              *linkname = malloc(size), *targetname;
         int len, err = -1;
 
-        if (filename == NULL || linkname == NULL)
+        if (is_kallsyms) {
+                if (symbol_conf.kptr_restrict) {
+                        pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+                        return 0;
+                }
+                realname = (char *)name;
+        } else
+                realname = realpath(name, NULL);
+
+        if (realname == NULL || filename == NULL || linkname == NULL)
                 goto out_free;
 
         len = snprintf(filename, size, "%s%s%s",
-                       debugdir, is_kallsyms ? "/" : "", name);
+                       debugdir, is_kallsyms ? "/" : "", realname);
         if (mkdir_p(filename, 0755))
                 goto out_free;
 
@@ -283,7 +216,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
                 if (is_kallsyms) {
                          if (copyfile("/proc/kallsyms", filename))
                                 goto out_free;
-                } else if (link(name, filename) && copyfile(name, filename))
+                } else if (link(realname, filename) && copyfile(name, filename))
                         goto out_free;
         }
 
@@ -300,6 +233,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
         if (symlink(targetname, linkname) == 0)
                 err = 0;
 out_free:
+        if (!is_kallsyms)
+                free(realname);
         free(filename);
         free(linkname);
         return err;
@@ -354,12 +289,12 @@ out_free:
         return err;
 }
 
-static int dso__cache_build_id(struct dso *self, const char *debugdir)
+static int dso__cache_build_id(struct dso *dso, const char *debugdir)
 {
-        bool is_kallsyms = self->kernel && self->long_name[0] != '/';
+        bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
 
-        return build_id_cache__add_b(self->build_id, sizeof(self->build_id),
-                                     self->long_name, debugdir, is_kallsyms);
+        return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
+                                     dso->long_name, debugdir, is_kallsyms);
 }
 
 static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
@@ -374,14 +309,14 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
         return err;
 }
 
-static int machine__cache_build_ids(struct machine *self, const char *debugdir)
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-        int ret = __dsos__cache_build_ids(&self->kernel_dsos, debugdir);
-        ret |= __dsos__cache_build_ids(&self->user_dsos, debugdir);
+        int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
+        ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
         return ret;
 }
 
-static int perf_session__cache_build_ids(struct perf_session *self)
+static int perf_session__cache_build_ids(struct perf_session *session)
 {
         struct rb_node *nd;
         int ret;
@@ -392,28 +327,28 @@ static int perf_session__cache_build_ids(struct perf_session *self)
         if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
                 return -1;
 
-        ret = machine__cache_build_ids(&self->host_machine, debugdir);
+        ret = machine__cache_build_ids(&session->host_machine, debugdir);
 
-        for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
                 struct machine *pos = rb_entry(nd, struct machine, rb_node);
                 ret |= machine__cache_build_ids(pos, debugdir);
         }
         return ret ? -1 : 0;
 }
 
-static bool machine__read_build_ids(struct machine *self, bool with_hits)
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-        bool ret = __dsos__read_build_ids(&self->kernel_dsos, with_hits);
-        ret |= __dsos__read_build_ids(&self->user_dsos, with_hits);
+        bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
+        ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
         return ret;
 }
 
-static bool perf_session__read_build_ids(struct perf_session *self, bool with_hits)
+static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
 {
         struct rb_node *nd;
-        bool ret = machine__read_build_ids(&self->host_machine, with_hits);
+        bool ret = machine__read_build_ids(&session->host_machine, with_hits);
 
-        for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
                 struct machine *pos = rb_entry(nd, struct machine, rb_node);
                 ret |= machine__read_build_ids(pos, with_hits);
         }
@@ -421,7 +356,8 @@ static bool perf_session__read_build_ids(struct perf_session *self, bool with_hi
         return ret;
 }
 
-static int perf_header__adds_write(struct perf_header *self, int fd)
+static int perf_header__adds_write(struct perf_header *header,
+                                   struct perf_evlist *evlist, int fd)
 {
         int nr_sections;
         struct perf_session *session;
@@ -430,11 +366,13 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
         u64 sec_start;
         int idx = 0, err;
 
-        session = container_of(self, struct perf_session, header);
-        if (perf_session__read_build_ids(session, true))
-                perf_header__set_feat(self, HEADER_BUILD_ID);
+        session = container_of(header, struct perf_session, header);
 
-        nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
+        if (perf_header__has_feat(header, HEADER_BUILD_ID &&
+            !perf_session__read_build_ids(session, true)))
+                perf_header__clear_feat(header, HEADER_BUILD_ID);
+
+        nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
         if (!nr_sections)
                 return 0;
 
@@ -444,28 +382,28 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 
         sec_size = sizeof(*feat_sec) * nr_sections;
 
-        sec_start = self->data_offset + self->data_size;
+        sec_start = header->data_offset + header->data_size;
         lseek(fd, sec_start + sec_size, SEEK_SET);
 
-        if (perf_header__has_feat(self, HEADER_TRACE_INFO)) {
+        if (perf_header__has_feat(header, HEADER_TRACE_INFO)) {
                 struct perf_file_section *trace_sec;
 
                 trace_sec = &feat_sec[idx++];
 
                 /* Write trace info */
                 trace_sec->offset = lseek(fd, 0, SEEK_CUR);
-                read_tracing_data(fd, attrs, nr_counters);
+                read_tracing_data(fd, &evlist->entries);
                 trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
         }
 
-        if (perf_header__has_feat(self, HEADER_BUILD_ID)) {
+        if (perf_header__has_feat(header, HEADER_BUILD_ID)) {
                 struct perf_file_section *buildid_sec;
 
                 buildid_sec = &feat_sec[idx++];
 
                 /* Write build-ids */
                 buildid_sec->offset = lseek(fd, 0, SEEK_CUR);
-                err = dsos__write_buildid_table(self, fd);
+                err = dsos__write_buildid_table(header, fd);
                 if (err < 0) {
                         pr_debug("failed to write buildid table\n");
                         goto out_free;
@@ -504,32 +442,41 @@ int perf_header__write_pipe(int fd)
         return 0;
 }
 
-int perf_header__write(struct perf_header *self, int fd, bool at_exit)
+int perf_session__write_header(struct perf_session *session,
+                               struct perf_evlist *evlist,
+                               int fd, bool at_exit)
 {
         struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
-        struct perf_header_attr *attr;
-        int i, err;
+        struct perf_header *header = &session->header;
+        struct perf_evsel *attr, *pair = NULL;
+        int err;
 
         lseek(fd, sizeof(f_header), SEEK_SET);
 
-        for (i = 0; i < self->attrs; i++) {
-                attr = self->attr[i];
+        if (session->evlist != evlist)
+                pair = list_entry(session->evlist->entries.next, struct perf_evsel, node);
 
+        list_for_each_entry(attr, &evlist->entries, node) {
                 attr->id_offset = lseek(fd, 0, SEEK_CUR);
                 err = do_write(fd, attr->id, attr->ids * sizeof(u64));
                 if (err < 0) {
+out_err_write:
                         pr_debug("failed to write perf header\n");
                         return err;
                 }
+                if (session->evlist != evlist) {
+                        err = do_write(fd, pair->id, pair->ids * sizeof(u64));
+                        if (err < 0)
+                                goto out_err_write;
+                        attr->ids += pair->ids;
+                        pair = list_entry(pair->node.next, struct perf_evsel, node);
+                }
         }
 
+        header->attr_offset = lseek(fd, 0, SEEK_CUR);
 
-        self->attr_offset = lseek(fd, 0, SEEK_CUR);
-
-        for (i = 0; i < self->attrs; i++) {
-                attr = self->attr[i];
-
+        list_for_each_entry(attr, &evlist->entries, node) {
                 f_attr = (struct perf_file_attr){
                         .attr = attr->attr,
                         .ids  = {
@@ -544,20 +491,20 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
                 }
         }
 
-        self->event_offset = lseek(fd, 0, SEEK_CUR);
-        self->event_size = event_count * sizeof(struct perf_trace_event_type);
+        header->event_offset = lseek(fd, 0, SEEK_CUR);
+        header->event_size = event_count * sizeof(struct perf_trace_event_type);
         if (events) {
-                err = do_write(fd, events, self->event_size);
+                err = do_write(fd, events, header->event_size);
                 if (err < 0) {
                         pr_debug("failed to write perf header events\n");
                         return err;
                 }
         }
 
-        self->data_offset = lseek(fd, 0, SEEK_CUR);
+        header->data_offset = lseek(fd, 0, SEEK_CUR);
 
         if (at_exit) {
-                err = perf_header__adds_write(self, fd);
+                err = perf_header__adds_write(header, evlist, fd);
                 if (err < 0)
                         return err;
         }
@@ -567,20 +514,20 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
                 .size      = sizeof(f_header),
                 .attr_size = sizeof(f_attr),
                 .attrs = {
-                        .offset = self->attr_offset,
-                        .size   = self->attrs * sizeof(f_attr),
+                        .offset = header->attr_offset,
+                        .size   = evlist->nr_entries * sizeof(f_attr),
                 },
                 .data = {
-                        .offset = self->data_offset,
-                        .size   = self->data_size,
+                        .offset = header->data_offset,
+                        .size   = header->data_size,
                 },
                 .event_types = {
-                        .offset = self->event_offset,
-                        .size   = self->event_size,
+                        .offset = header->event_offset,
+                        .size   = header->event_size,
                 },
         };
 
-        memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features));
+        memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
 
         lseek(fd, 0, SEEK_SET);
         err = do_write(fd, &f_header, sizeof(f_header));
@@ -588,26 +535,26 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
                 pr_debug("failed to write perf header\n");
                 return err;
         }
-        lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+        lseek(fd, header->data_offset + header->data_size, SEEK_SET);
 
-        self->frozen = 1;
+        header->frozen = 1;
         return 0;
 }
 
-static int perf_header__getbuffer64(struct perf_header *self,
+static int perf_header__getbuffer64(struct perf_header *header,
                                     int fd, void *buf, size_t size)
 {
-        if (do_read(fd, buf, size) <= 0)
+        if (readn(fd, buf, size) <= 0)
                 return -1;
 
-        if (self->needs_swap)
+        if (header->needs_swap)
                 mem_bswap_64(buf, size);
 
         return 0;
 }
 
-int perf_header__process_sections(struct perf_header *self, int fd,
-                                  int (*process)(struct perf_file_section *self,
+int perf_header__process_sections(struct perf_header *header, int fd,
+                                  int (*process)(struct perf_file_section *section,
                                                  struct perf_header *ph,
                                                  int feat, int fd))
 {
@@ -617,7 +564,7 @@ int perf_header__process_sections(struct perf_header *self, int fd,
         int idx = 0;
         int err = -1, feat = 1;
 
-        nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
+        nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
         if (!nr_sections)
                 return 0;
 
@@ -627,17 +574,17 @@ int perf_header__process_sections(struct perf_header *self, int fd,
 
         sec_size = sizeof(*feat_sec) * nr_sections;
 
-        lseek(fd, self->data_offset + self->data_size, SEEK_SET);
+        lseek(fd, header->data_offset + header->data_size, SEEK_SET);
 
-        if (perf_header__getbuffer64(self, fd, feat_sec, sec_size))
+        if (perf_header__getbuffer64(header, fd, feat_sec, sec_size))
                 goto out_free;
 
         err = 0;
         while (idx < nr_sections && feat < HEADER_LAST_FEATURE) {
-                if (perf_header__has_feat(self, feat)) {
+                if (perf_header__has_feat(header, feat)) {
                         struct perf_file_section *sec = &feat_sec[idx++];
 
-                        err = process(sec, self, feat, fd);
+                        err = process(sec, header, feat, fd);
                         if (err < 0)
                                 break;
                 }
@@ -648,35 +595,35 @@ out_free:
         return err;
 }
 
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
                            struct perf_header *ph, int fd)
 {
         lseek(fd, 0, SEEK_SET);
 
-        if (do_read(fd, self, sizeof(*self)) <= 0 ||
-            memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+        if (readn(fd, header, sizeof(*header)) <= 0 ||
+            memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
                 return -1;
 
-        if (self->attr_size != sizeof(struct perf_file_attr)) {
-                u64 attr_size = bswap_64(self->attr_size);
+        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;
 
-                mem_bswap_64(self, offsetof(struct perf_file_header,
+                mem_bswap_64(header, offsetof(struct perf_file_header,
                                             adds_features));
                 ph->needs_swap = true;
         }
 
-        if (self->size != sizeof(*self)) {
+        if (header->size != sizeof(*header)) {
                 /* Support the previous format */
-                if (self->size == offsetof(typeof(*self), adds_features))
-                        bitmap_zero(self->adds_features, HEADER_FEAT_BITS);
+                if (header->size == offsetof(typeof(*header), adds_features))
+                        bitmap_zero(header->adds_features, HEADER_FEAT_BITS);
                 else
                         return -1;
         }
 
-        memcpy(&ph->adds_features, &self->adds_features,
+        memcpy(&ph->adds_features, &header->adds_features,
                sizeof(ph->adds_features));
         /*
          * FIXME: hack that assumes that if we need swap the perf.data file
@@ -690,10 +637,10 @@ int perf_file_header__read(struct perf_file_header *self,
                 perf_header__set_feat(ph, HEADER_BUILD_ID);
         }
 
-        ph->event_offset = self->event_types.offset;
-        ph->event_size   = self->event_types.size;
-        ph->data_offset  = self->data.offset;
-        ph->data_size    = self->data.size;
+        ph->event_offset = header->event_types.offset;
+        ph->event_size   = header->event_types.size;
+        ph->data_offset  = header->data.offset;
+        ph->data_size    = header->data.size;
         return 0;
 }
 
@@ -752,14 +699,50 @@ out:
         return err;
 }
 
-static int perf_header__read_build_ids(struct perf_header *self,
-                        int input, u64 offset, u64 size)
+static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
+                                                 int input, u64 offset, u64 size)
 {
-        struct perf_session *session = container_of(self,
-                        struct perf_session, header);
+        struct perf_session *session = container_of(header, struct perf_session, header);
+        struct {
+                struct perf_event_header   header;
+                u8                         build_id[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;
+                bev.pid    = 0;
+                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) {
@@ -768,12 +751,30 @@ static int perf_header__read_build_ids(struct perf_header *self,
                 if (read(input, &bev, sizeof(bev)) != sizeof(bev))
                         goto out;
 
-                if (self->needs_swap)
+                if (header->needs_swap)
                         perf_event_header__bswap(&bev.header);
 
                 len = bev.header.size - sizeof(bev);
                 if (read(input, filename, len) != len)
                         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);
 
@@ -784,13 +785,13 @@ out:
         return err;
 }
 
-static int perf_file_section__process(struct perf_file_section *self,
+static int perf_file_section__process(struct perf_file_section *section,
                                       struct perf_header *ph,
                                       int feat, int fd)
 {
-        if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) {
-                pr_debug("Failed to lseek to %Ld offset for feature %d, "
-                         "continuing...\n", self->offset, feat);
+        if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) {
+                pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
+                          "%d, continuing...\n", section->offset, feat);
                 return 0;
         }
 
@@ -800,7 +801,7 @@ static int perf_file_section__process(struct perf_file_section *self,
                 break;
 
         case HEADER_BUILD_ID:
-                if (perf_header__read_build_ids(ph, fd, self->offset, self->size))
+                if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
                         pr_debug("Failed to read buildids, continuing...\n");
                 break;
         default:
@@ -810,21 +811,21 @@ static int perf_file_section__process(struct perf_file_section *self,
         return 0;
 }
 
-static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
                                        struct perf_header *ph, int fd,
                                        bool repipe)
 {
-        if (do_read(fd, self, sizeof(*self)) <= 0 ||
-            memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+        if (readn(fd, header, sizeof(*header)) <= 0 ||
+            memcmp(&header->magic, __perf_magic, sizeof(header->magic)))
                 return -1;
 
-        if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0)
+        if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0)
                 return -1;
 
-        if (self->size != sizeof(*self)) {
-                u64 size = bswap_64(self->size);
+        if (header->size != sizeof(*header)) {
+                u64 size = bswap_64(header->size);
 
-                if (size != sizeof(*self))
+                if (size != sizeof(*header))
                         return -1;
 
                 ph->needs_swap = true;
@@ -835,10 +836,10 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
 
 static int perf_header__read_pipe(struct perf_session *session, int fd)
 {
-        struct perf_header *self = &session->header;
+        struct perf_header *header = &session->header;
         struct perf_pipe_file_header f_header;
 
-        if (perf_file_header__read_pipe(&f_header, self, fd,
+        if (perf_file_header__read_pipe(&f_header, header, fd,
                                         session->repipe) < 0) {
                 pr_debug("incompatible file format\n");
                 return -EINVAL;
@@ -849,18 +850,22 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
         return 0;
 }
 
-int perf_header__read(struct perf_session *session, int fd)
+int perf_session__read_header(struct perf_session *session, int fd)
 {
-        struct perf_header *self = &session->header;
+        struct perf_header *header = &session->header;
         struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
         u64                     f_id;
         int nr_attrs, nr_ids, i, j;
 
+        session->evlist = perf_evlist__new(NULL, NULL);
+        if (session->evlist == NULL)
+                return -ENOMEM;
+
         if (session->fd_pipe)
                 return perf_header__read_pipe(session, fd);
 
-        if (perf_file_header__read(&f_header, self, fd) < 0) {
+        if (perf_file_header__read(&f_header, header, fd) < 0) {
                 pr_debug("incompatible file format\n");
                 return -EINVAL;
         }
@@ -869,33 +874,39 @@ int perf_header__read(struct perf_session *session, int fd)
         lseek(fd, f_header.attrs.offset, SEEK_SET);
 
         for (i = 0; i < nr_attrs; i++) {
-                struct perf_header_attr *attr;
+                struct perf_evsel *evsel;
                 off_t tmp;
 
-                if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr)))
+                if (perf_header__getbuffer64(header, fd, &f_attr, sizeof(f_attr)))
                         goto out_errno;
 
                 tmp = lseek(fd, 0, SEEK_CUR);
+                evsel = perf_evsel__new(&f_attr.attr, i);
 
-                attr = perf_header_attr__new(&f_attr.attr);
-                if (attr == NULL)
-                         return -ENOMEM;
+                if (evsel == NULL)
+                        goto out_delete_evlist;
+                /*
+                 * Do it before so that if perf_evsel__alloc_id fails, this
+                 * entry gets purged too at perf_evlist__delete().
+                 */
+                perf_evlist__add(session->evlist, evsel);
 
                 nr_ids = f_attr.ids.size / sizeof(u64);
+                /*
+                 * We don't have the cpu and thread maps on the header, so
+                 * for allocating the perf_sample_id table we fake 1 cpu and
+                 * hattr->ids threads.
+                 */
+                if (perf_evsel__alloc_id(evsel, 1, nr_ids))
+                        goto out_delete_evlist;
+
                 lseek(fd, f_attr.ids.offset, SEEK_SET);
 
                 for (j = 0; j < nr_ids; j++) {
-                        if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id)))
+                        if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id)))
                                 goto out_errno;
 
-                        if (perf_header_attr__add_id(attr, f_id) < 0) {
-                                perf_header_attr__delete(attr);
-                                return -ENOMEM;
-                        }
-                }
-                if (perf_header__add_attr(self, attr) < 0) {
-                        perf_header_attr__delete(attr);
-                        return -ENOMEM;
+                        perf_evlist__id_add(session->evlist, evsel, 0, j, f_id);
                 }
 
                 lseek(fd, tmp, SEEK_SET);
@@ -906,70 +917,32 @@ int perf_header__read(struct perf_session *session, int fd)
                 events = malloc(f_header.event_types.size);
                 if (events == NULL)
                         return -ENOMEM;
-                if (perf_header__getbuffer64(self, fd, events,
+                if (perf_header__getbuffer64(header, fd, events,
                                              f_header.event_types.size))
                         goto out_errno;
                 event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
         }
 
-        perf_header__process_sections(self, fd, perf_file_section__process);
+        perf_header__process_sections(header, fd, perf_file_section__process);
 
-        lseek(fd, self->data_offset, SEEK_SET);
+        lseek(fd, header->data_offset, SEEK_SET);
 
-        self->frozen = 1;
+        header->frozen = 1;
         return 0;
 out_errno:
         return -errno;
-}
-
-u64 perf_header__sample_type(struct perf_header *header)
-{
-        u64 type = 0;
-        int i;
-
-        for (i = 0; i < header->attrs; i++) {
-                struct perf_header_attr *attr = header->attr[i];
-
-                if (!type)
-                        type = attr->attr.sample_type;
-                else if (type != attr->attr.sample_type)
-                        die("non matching sample_type");
-        }
-
-        return type;
-}
-
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header)
-{
-        int i;
-
-        /*
-         * We set id to -1 if the data file doesn't contain sample
-         * ids. Check for this and avoid walking through the entire
-         * list of ids which may be large.
-         */
-        if (id == -1ULL)
-                return NULL;
-
-        for (i = 0; i < header->attrs; i++) {
-                struct perf_header_attr *attr = header->attr[i];
-                int j;
-
-                for (j = 0; j < attr->ids; j++) {
-                        if (attr->id[j] == id)
-                                return &attr->attr;
-                }
-        }
 
-        return NULL;
+out_delete_evlist:
+        perf_evlist__delete(session->evlist);
+        session->evlist = NULL;
+        return -ENOMEM;
 }
 
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
-                           event__handler_t process,
-                           struct perf_session *session)
+int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+                                perf_event__handler_t process,
+                                struct perf_session *session)
 {
-        event_t *ev;
+        union perf_event *ev;
         size_t size;
         int err;
 
@@ -980,31 +953,31 @@ int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
 
         ev = malloc(size);
 
+        if (ev == NULL)
+                return -ENOMEM;
+
         ev->attr.attr = *attr;
         memcpy(ev->attr.id, id, ids * sizeof(u64));
 
         ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
         ev->attr.header.size = size;
 
-        err = process(ev, session);
+        err = process(ev, NULL, session);
 
         free(ev);
 
         return err;
 }
 
-int event__synthesize_attrs(struct perf_header *self,
-                            event__handler_t process,
-                            struct perf_session *session)
+int perf_session__synthesize_attrs(struct perf_session *session,
+                                   perf_event__handler_t process)
 {
-        struct perf_header_attr *attr;
-        int i, err = 0;
-
-        for (i = 0; i < self->attrs; i++) {
-                attr = self->attr[i];
+        struct perf_evsel *attr;
+        int err = 0;
 
-                err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
-                                             process, session);
+        list_for_each_entry(attr, &session->evlist->entries, node) {
+                err = perf_event__synthesize_attr(&attr->attr, attr->ids,
+                                                  attr->id, process, session);
                 if (err) {
                         pr_debug("failed to create perf header attribute\n");
                         return err;
@@ -1014,29 +987,39 @@ int event__synthesize_attrs(struct perf_header *self,
         return err;
 }
 
-int event__process_attr(event_t *self, struct perf_session *session)
+int perf_event__process_attr(union perf_event *event,
+                             struct perf_session *session)
 {
-        struct perf_header_attr *attr;
         unsigned int i, ids, n_ids;
+        struct perf_evsel *evsel;
+
+        if (session->evlist == NULL) {
+                session->evlist = perf_evlist__new(NULL, NULL);
+                if (session->evlist == NULL)
+                        return -ENOMEM;
+        }
 
-        attr = perf_header_attr__new(&self->attr.attr);
-        if (attr == NULL)
+        evsel = perf_evsel__new(&event->attr.attr,
+                                session->evlist->nr_entries);
+        if (evsel == NULL)
                 return -ENOMEM;
 
-        ids = self->header.size;
-        ids -= (void *)&self->attr.id - (void *)self;
+        perf_evlist__add(session->evlist, evsel);
+
+        ids = event->header.size;
+        ids -= (void *)&event->attr.id - (void *)event;
         n_ids = ids / sizeof(u64);
+        /*
+         * We don't have the cpu and thread maps on the header, so
+         * for allocating the perf_sample_id table we fake 1 cpu and
+         * hattr->ids threads.
+         */
+        if (perf_evsel__alloc_id(evsel, 1, n_ids))
+                return -ENOMEM;
 
         for (i = 0; i < n_ids; i++) {
-                if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
-                        perf_header_attr__delete(attr);
-                        return -ENOMEM;
-                }
-        }
-
-        if (perf_header__add_attr(&session->header, attr) < 0) {
-                perf_header_attr__delete(attr);
-                return -ENOMEM;
+                perf_evlist__id_add(session->evlist, evsel, 0, i,
+                                    event->attr.id[i]);
         }
 
         perf_session__update_sample_type(session);
@@ -1044,11 +1027,11 @@ int event__process_attr(event_t *self, struct perf_session *session)
         return 0;
 }
 
-int event__synthesize_event_type(u64 event_id, char *name,
-                                 event__handler_t process,
-                                 struct perf_session *session)
+int perf_event__synthesize_event_type(u64 event_id, char *name,
+                                      perf_event__handler_t process,
+                                      struct perf_session *session)
 {
-        event_t ev;
+        union perf_event ev;
         size_t size = 0;
         int err = 0;
 
@@ -1064,13 +1047,13 @@ int event__synthesize_event_type(u64 event_id, char *name,
         ev.event_type.header.size = sizeof(ev.event_type) -
                 (sizeof(ev.event_type.event_type.name) - size);
 
-        err = process(&ev, session);
+        err = process(&ev, NULL, session);
 
         return err;
 }
 
-int event__synthesize_event_types(event__handler_t process,
-                                  struct perf_session *session)
+int perf_event__synthesize_event_types(perf_event__handler_t process,
+                                       struct perf_session *session)
 {
         struct perf_trace_event_type *type;
         int i, err = 0;
@@ -1078,8 +1061,9 @@ int event__synthesize_event_types(event__handler_t process,
         for (i = 0; i < event_count; i++) {
                 type = &events[i];
 
-                err = event__synthesize_event_type(type->event_id, type->name,
-                                                   process, session);
+                err = perf_event__synthesize_event_type(type->event_id,
+                                                        type->name, process,
+                                                        session);
                 if (err) {
                         pr_debug("failed to create perf header event type\n");
                         return err;
@@ -1089,29 +1073,28 @@ int event__synthesize_event_types(event__handler_t process,
         return err;
 }
 
-int event__process_event_type(event_t *self,
-                              struct perf_session *session __unused)
+int perf_event__process_event_type(union perf_event *event,
+                                   struct perf_session *session __unused)
 {
-        if (perf_header__push_event(self->event_type.event_type.event_id,
-                                    self->event_type.event_type.name) < 0)
+        if (perf_header__push_event(event->event_type.event_type.event_id,
+                                    event->event_type.event_type.name) < 0)
                 return -ENOMEM;
 
         return 0;
 }
 
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-                                   int nb_events,
-                                   event__handler_t process,
+int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
+                                         perf_event__handler_t process,
                                    struct perf_session *session __unused)
 {
-        event_t ev;
+        union perf_event ev;
         ssize_t size = 0, aligned_size = 0, padding;
-        int err = 0;
+        int err __used = 0;
 
         memset(&ev, 0, sizeof(ev));
 
         ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
-        size = read_tracing_data_size(fd, pattrs, nb_events);
+        size = read_tracing_data_size(fd, &evlist->entries);
         if (size <= 0)
                 return size;
         aligned_size = ALIGN(size, sizeof(u64));
@@ -1119,18 +1102,18 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
         ev.tracing_data.header.size = sizeof(ev.tracing_data);
         ev.tracing_data.size = aligned_size;
 
-        process(&ev, session);
+        process(&ev, NULL, session);
 
-        err = read_tracing_data(fd, pattrs, nb_events);
+        err = read_tracing_data(fd, &evlist->entries);
         write_padded(fd, NULL, 0, padding);
 
         return aligned_size;
 }
 
-int event__process_tracing_data(event_t *self,
-                                struct perf_session *session)
+int perf_event__process_tracing_data(union perf_event *event,
+                                     struct perf_session *session)
 {
-        ssize_t size_read, padding, size = self->tracing_data.size;
+        ssize_t size_read, padding, size = event->tracing_data.size;
         off_t offset = lseek(session->fd, 0, SEEK_CUR);
         char buf[BUFSIZ];
 
@@ -1156,12 +1139,12 @@ int event__process_tracing_data(event_t *self,
         return size_read + padding;
 }
 
-int event__synthesize_build_id(struct dso *pos, u16 misc,
-                               event__handler_t process,
-                               struct machine *machine,
-                               struct perf_session *session)
+int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+                                    perf_event__handler_t process,
+                                    struct machine *machine,
+                                    struct perf_session *session)
 {
-        event_t ev;
+        union perf_event ev;
         size_t len;
         int err = 0;
 
@@ -1179,16 +1162,16 @@ int event__synthesize_build_id(struct dso *pos, u16 misc,
         ev.build_id.header.size = sizeof(ev.build_id) + len;
         memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
 
-        err = process(&ev, session);
+        err = process(&ev, NULL, session);
 
         return err;
 }
 
-int event__process_build_id(event_t *self,
-                            struct perf_session *session)
+int perf_event__process_build_id(union perf_event *event,
+                                 struct perf_session *session)
 {
-        __event_process_build_id(&self->build_id,
-                                 self->build_id.filename,
+        __event_process_build_id(&event->build_id,
+                                 event->build_id.filename,
                                  session);
         return 0;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 402ac2454cf8..1886256768a1 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -9,13 +9,6 @@
 
 #include <linux/bitmap.h>
 
-struct perf_header_attr {
-        struct perf_event_attr attr;
-        int ids, size;
-        u64 *id;
-        off_t id_offset;
-};
-
 enum {
         HEADER_TRACE_INFO = 1,
         HEADER_BUILD_ID,
@@ -46,14 +39,12 @@ struct perf_pipe_file_header {
 
 struct perf_header;
 
-int perf_file_header__read(struct perf_file_header *self,
+int perf_file_header__read(struct perf_file_header *header,
                            struct perf_header *ph, int fd);
 
 struct perf_header {
         int                     frozen;
-        int                     attrs, size;
         bool                    needs_swap;
-        struct perf_header_attr **attr;
         s64                     attr_offset;
         u64                     data_offset;
         u64                     data_size;
@@ -62,32 +53,23 @@ struct perf_header {
         DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
-int perf_header__init(struct perf_header *self);
-void perf_header__exit(struct perf_header *self);
+struct perf_evlist;
 
-int perf_header__read(struct perf_session *session, int fd);
-int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_session__read_header(struct perf_session *session, int fd);
+int perf_session__write_header(struct perf_session *session,
+                               struct perf_evlist *evlist,
+                               int fd, bool at_exit);
 int perf_header__write_pipe(int fd);
 
-int perf_header__add_attr(struct perf_header *self,
-                          struct perf_header_attr *attr);
-
 int perf_header__push_event(u64 id, const char *name);
 char *perf_header__find_event(u64 id);
 
-struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr);
-void perf_header_attr__delete(struct perf_header_attr *self);
+void perf_header__set_feat(struct perf_header *header, int feat);
+void perf_header__clear_feat(struct perf_header *header, int feat);
+bool perf_header__has_feat(const struct perf_header *header, int feat);
 
-int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
-
-u64 perf_header__sample_type(struct perf_header *header);
-struct perf_event_attr *
-perf_header__find_attr(u64 id, struct perf_header *header);
-void perf_header__set_feat(struct perf_header *self, int feat);
-bool perf_header__has_feat(const struct perf_header *self, int feat);
-
-int perf_header__process_sections(struct perf_header *self, int fd,
-                                  int (*process)(struct perf_file_section *self,
+int perf_header__process_sections(struct perf_header *header, int fd,
+                                  int (*process)(struct perf_file_section *section,
                                                  struct perf_header *ph,
                                                  int feat, int fd));
 
@@ -95,33 +77,31 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
                           const char *name, bool is_kallsyms);
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
 
-int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
-                           event__handler_t process,
-                           struct perf_session *session);
-int event__synthesize_attrs(struct perf_header *self,
-                            event__handler_t process,
-                            struct perf_session *session);
-int event__process_attr(event_t *self, struct perf_session *session);
-
-int event__synthesize_event_type(u64 event_id, char *name,
-                                 event__handler_t process,
-                                 struct perf_session *session);
-int event__synthesize_event_types(event__handler_t process,
-                                  struct perf_session *session);
-int event__process_event_type(event_t *self,
-                              struct perf_session *session);
-
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-                                   int nb_events,
-                                   event__handler_t process,
-                                   struct perf_session *session);
-int event__process_tracing_data(event_t *self,
+int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+                                perf_event__handler_t process,
                                 struct perf_session *session);
+int perf_session__synthesize_attrs(struct perf_session *session,
+                                   perf_event__handler_t process);
+int perf_event__process_attr(union perf_event *event, struct perf_session *session);
+
+int perf_event__synthesize_event_type(u64 event_id, char *name,
+                                      perf_event__handler_t process,
+                                      struct perf_session *session);
+int perf_event__synthesize_event_types(perf_event__handler_t process,
+                                       struct perf_session *session);
+int perf_event__process_event_type(union perf_event *event,
+                                   struct perf_session *session);
 
-int event__synthesize_build_id(struct dso *pos, u16 misc,
-                               event__handler_t process,
-                               struct machine *machine,
-                               struct perf_session *session);
-int event__process_build_id(event_t *self, struct perf_session *session);
-
+int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
+                                        perf_event__handler_t process,
+                                        struct perf_session *session);
+int perf_event__process_tracing_data(union perf_event *event,
+                                     struct perf_session *session);
+
+int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+                                    perf_event__handler_t process,
+                                    struct machine *machine,
+                                    struct perf_session *session);
+int perf_event__process_build_id(union perf_event *event,
+                                 struct perf_session *session);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index be22ae6ef055..627a02e03c57 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,3 +1,4 @@
+#include "annotate.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -49,6 +50,15 @@ static void hists__calc_col_len(struct hists *self, struct hist_entry *h)
 
         if (h->ms.sym)
                 hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen);
+        else {
+                const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+
+                if (hists__col_len(self, HISTC_DSO) < unresolved_col_width &&
+                    !symbol_conf.col_width_list_str && !symbol_conf.field_sep &&
+                    !symbol_conf.dso_list)
+                        hists__set_col_len(self, HISTC_DSO,
+                                           unresolved_col_width);
+        }
 
         len = thread__comm_len(h->thread);
         if (hists__new_col_len(self, HISTC_COMM, len))
@@ -87,7 +97,7 @@ static void hist_entry__add_cpumode_period(struct hist_entry *self,
 
 static struct hist_entry *hist_entry__new(struct hist_entry *template)
 {
-        size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
+        size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
         struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
 
         if (self != NULL) {
@@ -211,7 +221,9 @@ void hist_entry__free(struct hist_entry *he)
  * collapse the histogram
  */
 
-static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
+static bool hists__collapse_insert_entry(struct hists *self,
+                                         struct rb_root *root,
+                                         struct hist_entry *he)
 {
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
@@ -226,6 +238,11 @@ static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he)
 
                 if (!cmp) {
                         iter->period += he->period;
+                        if (symbol_conf.use_callchain) {
+                                callchain_cursor_reset(&self->callchain_cursor);
+                                callchain_merge(&self->callchain_cursor, iter->callchain,
+                                                he->callchain);
+                        }
                         hist_entry__free(he);
                         return false;
                 }
@@ -260,7 +277,7 @@ void hists__collapse_resort(struct hists *self)
                 next = rb_next(&n->rb_node);
 
                 rb_erase(&n->rb_node, &self->entries);
-                if (collapse__insert_entry(&tmp, n))
+                if (hists__collapse_insert_entry(self, &tmp, n))
                         hists__inc_nr_entries(self, n);
         }
 
@@ -354,7 +371,7 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 
 static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
                                      int depth, int depth_mask, int period,
-                                     u64 total_samples, int hits,
+                                     u64 total_samples, u64 hits,
                                      int left_margin)
 {
         int i;
@@ -423,7 +440,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
                 u64 cumul;
 
                 child = rb_entry(node, struct callchain_node, rb_node);
-                cumul = cumul_hits(child);
+                cumul = callchain_cumul_hits(child);
                 remaining -= cumul;
 
                 /*
@@ -583,6 +600,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 {
         struct sort_entry *se;
         u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
+        u64 nr_events;
         const char *sep = symbol_conf.field_sep;
         int ret;
 
@@ -591,6 +609,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
 
         if (pair_hists) {
                 period = self->pair ? self->pair->period : 0;
+                nr_events = self->pair ? self->pair->nr_events : 0;
                 total = pair_hists->stats.total_period;
                 period_sys = self->pair ? self->pair->period_sys : 0;
                 period_us = self->pair ? self->pair->period_us : 0;
@@ -598,6 +617,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
                 period_guest_us = self->pair ? self->pair->period_guest_us : 0;
         } else {
                 period = self->period;
+                nr_events = self->nr_events;
                 total = session_total;
                 period_sys = self->period_sys;
                 period_us = self->period_us;
@@ -634,13 +654,13 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size,
                         }
                 }
         } else
-                ret = snprintf(s, size, sep ? "%lld" : "%12lld ", period);
+                ret = snprintf(s, size, sep ? "%" PRIu64 : "%12" PRIu64 " ", period);
 
         if (symbol_conf.show_nr_samples) {
                 if (sep)
-                        ret += snprintf(s + ret, size - ret, "%c%lld", *sep, period);
+                        ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events);
                 else
-                        ret += snprintf(s + ret, size - ret, "%11lld", period);
+                        ret += snprintf(s + ret, size - ret, "%11" PRIu64, nr_events);
         }
 
         if (pair_hists) {
@@ -942,216 +962,14 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread)
         }
 }
 
-static int symbol__alloc_hist(struct symbol *self)
-{
-        struct sym_priv *priv = symbol__priv(self);
-        const int size = (sizeof(*priv->hist) +
-                          (self->end - self->start) * sizeof(u64));
-
-        priv->hist = zalloc(size);
-        return priv->hist == NULL ? -1 : 0;
-}
-
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
-{
-        unsigned int sym_size, offset;
-        struct symbol *sym = self->ms.sym;
-        struct sym_priv *priv;
-        struct sym_hist *h;
-
-        if (!sym || !self->ms.map)
-                return 0;
-
-        priv = symbol__priv(sym);
-        if (priv->hist == NULL && symbol__alloc_hist(sym) < 0)
-                return -ENOMEM;
-
-        sym_size = sym->end - sym->start;
-        offset = ip - sym->start;
-
-        pr_debug3("%s: ip=%#Lx\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
-
-        if (offset >= sym_size)
-                return 0;
-
-        h = priv->hist;
-        h->sum++;
-        h->ip[offset]++;
-
-        pr_debug3("%#Lx %s: period++ [ip: %#Lx, %#Lx] => %Ld\n", self->ms.sym->start,
-                  self->ms.sym->name, ip, ip - self->ms.sym->start, h->ip[offset]);
-        return 0;
-}
-
-static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize)
-{
-        struct objdump_line *self = malloc(sizeof(*self) + privsize);
-
-        if (self != NULL) {
-                self->offset = offset;
-                self->line = line;
-        }
-
-        return self;
-}
-
-void objdump_line__free(struct objdump_line *self)
-{
-        free(self->line);
-        free(self);
-}
-
-static void objdump__add_line(struct list_head *head, struct objdump_line *line)
-{
-        list_add_tail(&line->node, head);
-}
-
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-                                               struct objdump_line *pos)
-{
-        list_for_each_entry_continue(pos, head, node)
-                if (pos->offset >= 0)
-                        return pos;
-
-        return NULL;
-}
-
-static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
-                                          struct list_head *head, size_t privsize)
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 {
-        struct symbol *sym = self->ms.sym;
-        struct objdump_line *objdump_line;
-        char *line = NULL, *tmp, *tmp2, *c;
-        size_t line_len;
-        s64 line_ip, offset = -1;
-
-        if (getline(&line, &line_len, file) < 0)
-                return -1;
-
-        if (!line)
-                return -1;
-
-        while (line_len != 0 && isspace(line[line_len - 1]))
-                line[--line_len] = '\0';
-
-        c = strchr(line, '\n');
-        if (c)
-                *c = 0;
-
-        line_ip = -1;
-
-        /*
-         * Strip leading spaces:
-         */
-        tmp = line;
-        while (*tmp) {
-                if (*tmp != ' ')
-                        break;
-                tmp++;
-        }
-
-        if (*tmp) {
-                /*
-                 * Parse hexa addresses followed by ':'
-                 */
-                line_ip = strtoull(tmp, &tmp2, 16);
-                if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
-                        line_ip = -1;
-        }
-
-        if (line_ip != -1) {
-                u64 start = map__rip_2objdump(self->ms.map, sym->start),
-                    end = map__rip_2objdump(self->ms.map, sym->end);
-
-                offset = line_ip - start;
-                if (offset < 0 || (u64)line_ip > end)
-                        offset = -1;
-        }
-
-        objdump_line = objdump_line__new(offset, line, privsize);
-        if (objdump_line == NULL) {
-                free(line);
-                return -1;
-        }
-        objdump__add_line(head, objdump_line);
-
-        return 0;
+        return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
 }
 
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
-                         size_t privsize)
+int hist_entry__annotate(struct hist_entry *he, size_t privsize)
 {
-        struct symbol *sym = self->ms.sym;
-        struct map *map = self->ms.map;
-        struct dso *dso = map->dso;
-        char *filename = dso__build_id_filename(dso, NULL, 0);
-        bool free_filename = true;
-        char command[PATH_MAX * 2];
-        FILE *file;
-        int err = 0;
-        u64 len;
-
-        if (filename == NULL) {
-                if (dso->has_build_id) {
-                        pr_err("Can't annotate %s: not enough memory\n",
-                               sym->name);
-                        return -ENOMEM;
-                }
-                goto fallback;
-        } else if (readlink(filename, command, sizeof(command)) < 0 ||
-                   strstr(command, "[kernel.kallsyms]") ||
-                   access(filename, R_OK)) {
-                free(filename);
-fallback:
-                /*
-                 * If we don't have build-ids or the build-id file isn't in the
-                 * cache, or is just a kallsyms file, well, lets hope that this
-                 * DSO is the same as when 'perf record' ran.
-                 */
-                filename = dso->long_name;
-                free_filename = false;
-        }
-
-        if (dso->origin == DSO__ORIG_KERNEL) {
-                if (dso->annotate_warned)
-                        goto out_free_filename;
-                err = -ENOENT;
-                dso->annotate_warned = 1;
-                pr_err("Can't annotate %s: No vmlinux file was found in the "
-                       "path\n", sym->name);
-                goto out_free_filename;
-        }
-
-        pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
-                 filename, sym->name, map->unmap_ip(map, sym->start),
-                 map->unmap_ip(map, sym->end));
-
-        len = sym->end - sym->start;
-
-        pr_debug("annotating [%p] %30s : [%p] %30s\n",
-                 dso, dso->long_name, sym, sym->name);
-
-        snprintf(command, sizeof(command),
-                 "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand",
-                 map__rip_2objdump(map, sym->start),
-                 map__rip_2objdump(map, sym->end),
-                 filename, filename);
-
-        pr_debug("Executing: %s\n", command);
-
-        file = popen(command, "r");
-        if (!file)
-                goto out_free_filename;
-
-        while (!feof(file))
-                if (hist_entry__parse_objdump_line(self, file, head, privsize) < 0)
-                        break;
-
-        pclose(file);
-out_free_filename:
-        if (free_filename)
-                free(filename);
-        return err;
+        return symbol__annotate(he->ms.sym, he->ms.map, privsize);
 }
 
 void hists__inc_nr_events(struct hists *self, u32 type)
@@ -1166,10 +984,17 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp)
         size_t ret = 0;
 
         for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
-                if (!event__name[i])
+                const char *name;
+
+                if (self->stats.nr_events[i] == 0)
+                        continue;
+
+                name = perf_event__name(i);
+                if (!strcmp(name, "UNKNOWN"))
                         continue;
-                ret += fprintf(fp, "%10s events: %10d\n",
-                               event__name[i], self->stats.nr_events[i]);
+
+                ret += fprintf(fp, "%16s events: %10d\n", name,
+                               self->stats.nr_events[i]);
         }
 
         return ret;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 587d375d3430..3beb97c4d822 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -9,33 +9,6 @@ extern struct callchain_param callchain_param;
 struct hist_entry;
 struct addr_location;
 struct symbol;
-struct rb_root;
-
-struct objdump_line {
-        struct list_head node;
-        s64              offset;
-        char             *line;
-};
-
-void objdump_line__free(struct objdump_line *self);
-struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
-                                               struct objdump_line *pos);
-
-struct sym_hist {
-        u64             sum;
-        u64             ip[0];
-};
-
-struct sym_ext {
-        struct rb_node  node;
-        double          percent;
-        char            *path;
-};
-
-struct sym_priv {
-        struct sym_hist *hist;
-        struct sym_ext  *ext;
-};
 
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
@@ -52,8 +25,11 @@ struct sym_priv {
 struct events_stats {
         u64 total_period;
         u64 total_lost;
+        u64 total_invalid_chains;
         u32 nr_events[PERF_RECORD_HEADER_MAX];
         u32 nr_unknown_events;
+        u32 nr_invalid_chains;
+        u32 nr_unknown_id;
 };
 
 enum hist_column {
@@ -67,14 +43,13 @@ enum hist_column {
 };
 
 struct hists {
-        struct rb_node          rb_node;
         struct rb_root          entries;
         u64                     nr_entries;
         struct events_stats     stats;
-        u64                     config;
         u64                     event_stream;
-        u32                     type;
         u16                     col_len[HISTC_NR_COLS];
+        /* Best would be to reuse the session callchain cursor */
+        struct callchain_cursor callchain_cursor;
 };
 
 struct hist_entry *__hists__add_entry(struct hists *self,
@@ -100,9 +75,8 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp);
 size_t hists__fprintf(struct hists *self, struct hists *pair,
                       bool show_displacement, FILE *fp);
 
-int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip);
-int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
-                         size_t privsize);
+int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr);
+int hist_entry__annotate(struct hist_entry *self, size_t privsize);
 
 void hists__filter_by_dso(struct hists *self, const struct dso *dso);
 void hists__filter_by_thread(struct hists *self, const struct thread *thread);
@@ -111,21 +85,18 @@ u16 hists__col_len(struct hists *self, enum hist_column col);
 void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
 bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len);
 
-#ifdef NO_NEWT_SUPPORT
-static inline int hists__browse(struct hists *self __used,
-                                const char *helpline __used,
-                                const char *ev_name __used)
-{
-        return 0;
-}
+struct perf_evlist;
 
-static inline int hists__tui_browse_tree(struct rb_root *self __used,
-                                         const char *help __used)
+#ifdef NO_NEWT_SUPPORT
+static inline
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used,
+                                  const char *help __used)
 {
         return 0;
 }
 
-static inline int hist_entry__tui_annotate(struct hist_entry *self __used)
+static inline int hist_entry__tui_annotate(struct hist_entry *self __used,
+                                           int evidx __used)
 {
         return 0;
 }
@@ -133,14 +104,12 @@ static inline int hist_entry__tui_annotate(struct hist_entry *self __used)
 #define KEY_RIGHT -2
 #else
 #include <newt.h>
-int hists__browse(struct hists *self, const char *helpline,
-                  const char *ev_name);
-int hist_entry__tui_annotate(struct hist_entry *self);
+int hist_entry__tui_annotate(struct hist_entry *self, int evidx);
 
 #define KEY_LEFT NEWT_KEY_LEFT
 #define KEY_RIGHT NEWT_KEY_RIGHT
 
-int hists__tui_browse_tree(struct rb_root *self, const char *help);
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help);
 #endif
 
 unsigned int hists__sort_list_width(struct hists *self);
diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h
new file mode 100644
index 000000000000..6789d788d494
--- /dev/null
+++ b/tools/perf/util/include/asm/alternative-asm.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_ASM_ALTERNATIVE_ASM_H
+#define _PERF_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define altinstruction_entry #
+
+#endif
diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h
new file mode 100644
index 000000000000..acffd5e4d1d4
--- /dev/null
+++ b/tools/perf/util/include/asm/cpufeature.h
@@ -0,0 +1,9 @@
+
+#ifndef PERF_CPUFEATURE_H
+#define PERF_CPUFEATURE_H
+
+/* cpufeature.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define X86_FEATURE_REP_GOOD 0
+
+#endif  /* PERF_CPUFEATURE_H */
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
new file mode 100644
index 000000000000..bb4198e7837a
--- /dev/null
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -0,0 +1,11 @@
+
+#ifndef PERF_DWARF2_H
+#define PERF_DWARF2_H
+
+/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+
+#define CFI_STARTPROC
+#define CFI_ENDPROC
+
+#endif  /* PERF_DWARF2_H */
+
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index bb4ac2e05385..305c8484f200 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -2,6 +2,7 @@
 #define _PERF_LINUX_BITOPS_H_
 
 #include <linux/kernel.h>
+#include <linux/compiler.h>
 #include <asm/hweight.h>
 
 #define BITS_PER_LONG __WORDSIZE
@@ -13,6 +14,11 @@ static inline void set_bit(int nr, unsigned long *addr)
         addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
 }
 
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+        addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+}
+
 static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
 {
         return ((1UL << (nr % BITS_PER_LONG)) &
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 000000000000..1b476c9ae649
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
new file mode 100644
index 000000000000..06387cffe125
--- /dev/null
+++ b/tools/perf/util/include/linux/linkage.h
@@ -0,0 +1,13 @@
+
+#ifndef PERF_LINUX_LINKAGE_H_
+#define PERF_LINUX_LINKAGE_H_
+
+/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
+
+#define ENTRY(name)                             \
+        .globl name;                            \
+        name:
+
+#define ENDPROC(name)
+
+#endif  /* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index f5ca26e53fbb..1d928a0ce997 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,3 +1,6 @@
+#include <linux/kernel.h>
+#include <linux/prefetch.h>
+
 #include "../../../../include/linux/list.h"
 
 #ifndef PERF_LIST_H
@@ -22,5 +25,5 @@ static inline void list_del_range(struct list_head *begin,
  * @head: the head for your list.
  */
 #define list_for_each_from(pos, head) \
-        for (; prefetch(pos->next), pos != (head); pos = pos->next)
+        for (; pos != (head); pos = pos->next)
 #endif
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 3a7eb6ec0eec..a16ecab5229d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 #include "symbol.h"
 #include <errno.h>
+#include <inttypes.h>
 #include <limits.h>
 #include <stdlib.h>
 #include <string.h>
@@ -195,7 +196,7 @@ int map__overlap(struct map *l, struct map *r)
 
 size_t map__fprintf(struct map *self, FILE *fp)
 {
-        return fprintf(fp, " %Lx-%Lx %Lx %s\n",
+        return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
                        self->start, self->end, self->pgoff, self->dso->name);
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 78575796d5f3..b397c0383728 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -215,6 +215,16 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *self,
         return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
 }
 
+static inline
+struct symbol *machine__find_kernel_function_by_name(struct machine *self,
+                                                     const char *name,
+                                                     struct map **mapp,
+                                                     symbol_filter_t filter)
+{
+        return map_groups__find_function_by_name(&self->kmaps, name, mapp,
+                                                 filter);
+}
+
 int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
                                    int verbose, FILE *fp);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4af5bd59cfd1..41982c373faf 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,6 +1,8 @@
 #include "../../../include/linux/hw_breakpoint.h"
 #include "util.h"
 #include "../perf.h"
+#include "evlist.h"
+#include "evsel.h"
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
@@ -10,11 +12,6 @@
 #include "header.h"
 #include "debugfs.h"
 
-int                             nr_counters;
-
-struct perf_event_attr          attrs[MAX_COUNTERS];
-char                            *filters[MAX_COUNTERS];
-
 struct event_symbol {
         u8              type;
         u64             config;
@@ -34,34 +31,36 @@ char debugfs_path[MAXPATHLEN];
 #define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
 
 static struct event_symbol event_symbols[] = {
-  { CHW(CPU_CYCLES),            "cpu-cycles",           "cycles"        },
-  { CHW(INSTRUCTIONS),          "instructions",         ""              },
-  { CHW(CACHE_REFERENCES),      "cache-references",     ""              },
-  { CHW(CACHE_MISSES),          "cache-misses",         ""              },
-  { CHW(BRANCH_INSTRUCTIONS),   "branch-instructions",  "branches"      },
-  { CHW(BRANCH_MISSES),         "branch-misses",        ""              },
-  { CHW(BUS_CYCLES),            "bus-cycles",           ""              },
-
-  { CSW(CPU_CLOCK),             "cpu-clock",            ""              },
-  { CSW(TASK_CLOCK),            "task-clock",           ""              },
-  { CSW(PAGE_FAULTS),           "page-faults",          "faults"        },
-  { CSW(PAGE_FAULTS_MIN),       "minor-faults",         ""              },
-  { CSW(PAGE_FAULTS_MAJ),       "major-faults",         ""              },
-  { CSW(CONTEXT_SWITCHES),      "context-switches",     "cs"            },
-  { CSW(CPU_MIGRATIONS),        "cpu-migrations",       "migrations"    },
-  { CSW(ALIGNMENT_FAULTS),      "alignment-faults",     ""              },
-  { CSW(EMULATION_FAULTS),      "emulation-faults",     ""              },
+  { CHW(CPU_CYCLES),                    "cpu-cycles",                   "cycles"                },
+  { CHW(STALLED_CYCLES_FRONTEND),       "stalled-cycles-frontend",      "idle-cycles-frontend"  },
+  { CHW(STALLED_CYCLES_BACKEND),        "stalled-cycles-backend",       "idle-cycles-backend"   },
+  { CHW(INSTRUCTIONS),                  "instructions",                 ""                      },
+  { CHW(CACHE_REFERENCES),              "cache-references",             ""                      },
+  { CHW(CACHE_MISSES),                  "cache-misses",                 ""                      },
+  { CHW(BRANCH_INSTRUCTIONS),           "branch-instructions",          "branches"              },
+  { CHW(BRANCH_MISSES),                 "branch-misses",                ""                      },
+  { CHW(BUS_CYCLES),                    "bus-cycles",                   ""                      },
+
+  { CSW(CPU_CLOCK),                     "cpu-clock",                    ""                      },
+  { CSW(TASK_CLOCK),                    "task-clock",                   ""                      },
+  { CSW(PAGE_FAULTS),                   "page-faults",                  "faults"                },
+  { CSW(PAGE_FAULTS_MIN),               "minor-faults",                 ""                      },
+  { CSW(PAGE_FAULTS_MAJ),               "major-faults",                 ""                      },
+  { CSW(CONTEXT_SWITCHES),              "context-switches",             "cs"                    },
+  { CSW(CPU_MIGRATIONS),                "cpu-migrations",               "migrations"            },
+  { CSW(ALIGNMENT_FAULTS),              "alignment-faults",             ""                      },
+  { CSW(EMULATION_FAULTS),              "emulation-faults",             ""                      },
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
         ((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
 
-#define PERF_EVENT_RAW(config)  __PERF_EVENT_FIELD(config, RAW)
+#define PERF_EVENT_RAW(config)          __PERF_EVENT_FIELD(config, RAW)
 #define PERF_EVENT_CONFIG(config)       __PERF_EVENT_FIELD(config, CONFIG)
-#define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE)
+#define PERF_EVENT_TYPE(config)         __PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)           __PERF_EVENT_FIELD(config, EVENT)
 
-static const char *hw_event_names[] = {
+static const char *hw_event_names[PERF_COUNT_HW_MAX] = {
         "cycles",
         "instructions",
         "cache-references",
@@ -69,11 +68,13 @@ static const char *hw_event_names[] = {
         "branches",
         "branch-misses",
         "bus-cycles",
+        "stalled-cycles-frontend",
+        "stalled-cycles-backend",
 };
 
-static const char *sw_event_names[] = {
-        "cpu-clock-msecs",
-        "task-clock-msecs",
+static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
+        "cpu-clock",
+        "task-clock",
         "page-faults",
         "context-switches",
         "CPU-migrations",
@@ -266,10 +267,35 @@ static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
         return name;
 }
 
-const char *event_name(int counter)
+const char *event_type(int type)
 {
-        u64 config = attrs[counter].config;
-        int type = attrs[counter].type;
+        switch (type) {
+        case PERF_TYPE_HARDWARE:
+                return "hardware";
+
+        case PERF_TYPE_SOFTWARE:
+                return "software";
+
+        case PERF_TYPE_TRACEPOINT:
+                return "tracepoint";
+
+        case PERF_TYPE_HW_CACHE:
+                return "hardware-cache";
+
+        default:
+                break;
+        }
+
+        return "unknown";
+}
+
+const char *event_name(struct perf_evsel *evsel)
+{
+        u64 config = evsel->attr.config;
+        int type = evsel->attr.type;
+
+        if (evsel->name)
+                return evsel->name;
 
         return __event_name(type, config);
 }
@@ -279,13 +305,13 @@ const char *__event_name(int type, u64 config)
         static char buf[32];
 
         if (type == PERF_TYPE_RAW) {
-                sprintf(buf, "raw 0x%llx", config);
+                sprintf(buf, "raw 0x%" PRIx64, config);
                 return buf;
         }
 
         switch (type) {
         case PERF_TYPE_HARDWARE:
-                if (config < PERF_COUNT_HW_MAX)
+                if (config < PERF_COUNT_HW_MAX && hw_event_names[config])
                         return hw_event_names[config];
                 return "unknown-hardware";
 
@@ -311,7 +337,7 @@ const char *__event_name(int type, u64 config)
         }
 
         case PERF_TYPE_SOFTWARE:
-                if (config < PERF_COUNT_SW_MAX)
+                if (config < PERF_COUNT_SW_MAX && sw_event_names[config])
                         return sw_event_names[config];
                 return "unknown-software";
 
@@ -434,7 +460,7 @@ parse_single_tracepoint_event(char *sys_name,
         id = atoll(id_buf);
         attr->config = id;
         attr->type = PERF_TYPE_TRACEPOINT;
-        *strp = evt_name + evt_length;
+        *strp += strlen(sys_name) + evt_length + 1; /* + 1 for the ':' */
 
         attr->sample_type |= PERF_SAMPLE_RAW;
         attr->sample_type |= PERF_SAMPLE_TIME;
@@ -449,8 +475,8 @@ parse_single_tracepoint_event(char *sys_name,
 /* sys + ':' + event + ':' + flags*/
 #define MAX_EVOPT_LEN   (MAX_EVENT_LENGTH * 2 + 2 + 128)
 static enum event_result
-parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
-                                char *flags)
+parse_multiple_tracepoint_event(const struct option *opt, char *sys_name,
+                                const char *evt_exp, char *flags)
 {
         char evt_path[MAXPATHLEN];
         struct dirent *evt_ent;
@@ -483,19 +509,19 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
                 if (len < 0)
                         return EVT_FAILED;
 
-                if (parse_events(NULL, event_opt, 0))
+                if (parse_events(opt, event_opt, 0))
                         return EVT_FAILED;
         }
 
         return EVT_HANDLED_ALL;
 }
 
-
-static enum event_result parse_tracepoint_event(const char **strp,
-                                    struct perf_event_attr *attr)
+static enum event_result
+parse_tracepoint_event(const struct option *opt, const char **strp,
+                       struct perf_event_attr *attr)
 {
         const char *evt_name;
-        char *flags;
+        char *flags = NULL, *comma_loc;
         char sys_name[MAX_EVENT_LENGTH];
         unsigned int sys_length, evt_length;
 
@@ -514,6 +540,11 @@ static enum event_result parse_tracepoint_event(const char **strp,
         sys_name[sys_length] = '\0';
         evt_name = evt_name + 1;
 
+        comma_loc = strchr(evt_name, ',');
+        if (comma_loc) {
+                /* take the event name up to the comma */
+                evt_name = strndup(evt_name, comma_loc - evt_name);
+        }
         flags = strchr(evt_name, ':');
         if (flags) {
                 /* split it out: */
@@ -524,14 +555,14 @@ static enum event_result parse_tracepoint_event(const char **strp,
         evt_length = strlen(evt_name);
         if (evt_length >= MAX_EVENT_LENGTH)
                 return EVT_FAILED;
-
         if (strpbrk(evt_name, "*?")) {
-                *strp = evt_name + evt_length;
-                return parse_multiple_tracepoint_event(sys_name, evt_name,
+                *strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
+                return parse_multiple_tracepoint_event(opt, sys_name, evt_name,
                                                        flags);
-        } else
+        } else {
                 return parse_single_tracepoint_event(sys_name, evt_name,
                                                      evt_length, attr, strp);
+        }
 }
 
 static enum event_result
@@ -621,13 +652,15 @@ static int check_events(const char *str, unsigned int i)
         int n;
 
         n = strlen(event_symbols[i].symbol);
-        if (!strncmp(str, event_symbols[i].symbol, n))
+        if (!strncasecmp(str, event_symbols[i].symbol, n))
                 return n;
 
         n = strlen(event_symbols[i].alias);
-        if (n)
-                if (!strncmp(str, event_symbols[i].alias, n))
+        if (n) {
+                if (!strncasecmp(str, event_symbols[i].alias, n))
                         return n;
+        }
+
         return 0;
 }
 
@@ -691,15 +724,22 @@ parse_numeric_event(const char **strp, struct perf_event_attr *attr)
         return EVT_FAILED;
 }
 
-static enum event_result
+static int
 parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 {
         const char *str = *strp;
         int exclude = 0;
         int eu = 0, ek = 0, eh = 0, precise = 0;
 
-        if (*str++ != ':')
+        if (!*str)
                 return 0;
+
+        if (*str == ',')
+                return 0;
+
+        if (*str++ != ':')
+                return -1;
+
         while (*str) {
                 if (*str == 'u') {
                         if (!exclude)
@@ -720,14 +760,16 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
 
                 ++str;
         }
-        if (str >= *strp + 2) {
-                *strp = str;
-                attr->exclude_user   = eu;
-                attr->exclude_kernel = ek;
-                attr->exclude_hv     = eh;
-                attr->precise_ip     = precise;
-                return 1;
-        }
+        if (str < *strp + 2)
+                return -1;
+
+        *strp = str;
+
+        attr->exclude_user   = eu;
+        attr->exclude_kernel = ek;
+        attr->exclude_hv     = eh;
+        attr->precise_ip     = precise;
+
         return 0;
 }
 
@@ -736,11 +778,12 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr)
  * Symbolic names are (almost) exactly matched.
  */
 static enum event_result
-parse_event_symbols(const char **str, struct perf_event_attr *attr)
+parse_event_symbols(const struct option *opt, const char **str,
+                    struct perf_event_attr *attr)
 {
         enum event_result ret;
 
-        ret = parse_tracepoint_event(str, attr);
+        ret = parse_tracepoint_event(opt, str, attr);
         if (ret != EVT_FAILED)
                 goto modifier;
 
@@ -769,52 +812,27 @@ parse_event_symbols(const char **str, struct perf_event_attr *attr)
         return EVT_FAILED;
 
 modifier:
-        parse_event_modifier(str, attr);
-
-        return ret;
-}
-
-static int store_event_type(const char *orgname)
-{
-        char filename[PATH_MAX], *c;
-        FILE *file;
-        int id, n;
+        if (parse_event_modifier(str, attr) < 0) {
+                fprintf(stderr, "invalid event modifier: '%s'\n", *str);
+                fprintf(stderr, "Run 'perf list' for a list of valid events and modifiers\n");
 
-        sprintf(filename, "%s/", debugfs_path);
-        strncat(filename, orgname, strlen(orgname));
-        strcat(filename, "/id");
-
-        c = strchr(filename, ':');
-        if (c)
-                *c = '/';
-
-        file = fopen(filename, "r");
-        if (!file)
-                return 0;
-        n = fscanf(file, "%i", &id);
-        fclose(file);
-        if (n < 1) {
-                pr_err("cannot store event ID\n");
-                return -EINVAL;
+                return EVT_FAILED;
         }
-        return perf_header__push_event(id, orgname);
+
+        return ret;
 }
 
-int parse_events(const struct option *opt __used, const char *str, int unset __used)
+int parse_events(const struct option *opt, const char *str, int unset __used)
 {
+        struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
         struct perf_event_attr attr;
         enum event_result ret;
-
-        if (strchr(str, ':'))
-                if (store_event_type(str) < 0)
-                        return -1;
+        const char *ostr;
 
         for (;;) {
-                if (nr_counters == MAX_COUNTERS)
-                        return -1;
-
+                ostr = str;
                 memset(&attr, 0, sizeof(attr));
-                ret = parse_event_symbols(&str, &attr);
+                ret = parse_event_symbols(opt, &str, &attr);
                 if (ret == EVT_FAILED)
                         return -1;
 
@@ -822,8 +840,16 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
                         return -1;
 
                 if (ret != EVT_HANDLED_ALL) {
-                        attrs[nr_counters] = attr;
-                        nr_counters++;
+                        struct perf_evsel *evsel;
+                        evsel = perf_evsel__new(&attr, evlist->nr_entries);
+                        if (evsel == NULL)
+                                return -1;
+                        perf_evlist__add(evlist, evsel);
+
+                        evsel->name = calloc(str - ostr + 1, 1);
+                        if (!evsel->name)
+                                return -1;
+                        strncpy(evsel->name, ostr, str - ostr);
                 }
 
                 if (*str == 0)
@@ -837,24 +863,26 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
         return 0;
 }
 
-int parse_filter(const struct option *opt __used, const char *str,
+int parse_filter(const struct option *opt, const char *str,
                  int unset __used)
 {
-        int i = nr_counters - 1;
-        int len = strlen(str);
+        struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+        struct perf_evsel *last = NULL;
+
+        if (evlist->nr_entries > 0)
+                last = list_entry(evlist->entries.prev, struct perf_evsel, node);
 
-        if (i < 0 || attrs[i].type != PERF_TYPE_TRACEPOINT) {
+        if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
                 fprintf(stderr,
                         "-F option should follow a -e tracepoint option\n");
                 return -1;
         }
 
-        filters[i] = malloc(len + 1);
-        if (!filters[i]) {
+        last->filter = strdup(str);
+        if (last->filter == NULL) {
                 fprintf(stderr, "not enough memory to hold filter string\n");
                 return -1;
         }
-        strcpy(filters[i], str);
 
         return 0;
 }
@@ -872,7 +900,7 @@ static const char * const event_type_descriptors[] = {
  * Print the events from <debugfs_mount_point>/tracing/events
  */
 
-static void print_tracepoint_events(void)
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
 {
         DIR *sys_dir, *evt_dir;
         struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
@@ -887,6 +915,9 @@ static void print_tracepoint_events(void)
                 return;
 
         for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+                if (subsys_glob != NULL && 
+                    !strglobmatch(sys_dirent.d_name, subsys_glob))
+                        continue;
 
                 snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
                          sys_dirent.d_name);
@@ -895,9 +926,13 @@ static void print_tracepoint_events(void)
                         continue;
 
                 for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+                        if (event_glob != NULL && 
+                            !strglobmatch(evt_dirent.d_name, event_glob))
+                                continue;
+
                         snprintf(evt_path, MAXPATHLEN, "%s:%s",
                                  sys_dirent.d_name, evt_dirent.d_name);
-                        printf("  %-42s [%s]\n", evt_path,
+                        printf("  %-50s [%s]\n", evt_path,
                                 event_type_descriptors[PERF_TYPE_TRACEPOINT]);
                 }
                 closedir(evt_dir);
@@ -906,34 +941,71 @@ static void print_tracepoint_events(void)
 }
 
 /*
- * Print the help text for the event symbols:
+ * Check whether event is in <debugfs_mount_point>/tracing/events
  */
-void print_events(void)
+
+int is_valid_tracepoint(const char *event_string)
 {
-        struct event_symbol *syms = event_symbols;
-        unsigned int i, type, op, prev_type = -1;
-        char name[40];
+        DIR *sys_dir, *evt_dir;
+        struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+        char evt_path[MAXPATHLEN];
+        char dir_path[MAXPATHLEN];
 
-        printf("\n");
-        printf("List of pre-defined events (to be used in -e):\n");
+        if (debugfs_valid_mountpoint(debugfs_path))
+                return 0;
 
-        for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-                type = syms->type;
+        sys_dir = opendir(debugfs_path);
+        if (!sys_dir)
+                return 0;
 
-                if (type != prev_type)
-                        printf("\n");
+        for_each_subsystem(sys_dir, sys_dirent, sys_next) {
+
+                snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+                         sys_dirent.d_name);
+                evt_dir = opendir(dir_path);
+                if (!evt_dir)
+                        continue;
+
+                for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
+                        snprintf(evt_path, MAXPATHLEN, "%s:%s",
+                                 sys_dirent.d_name, evt_dirent.d_name);
+                        if (!strcmp(evt_path, event_string)) {
+                                closedir(evt_dir);
+                                closedir(sys_dir);
+                                return 1;
+                        }
+                }
+                closedir(evt_dir);
+        }
+        closedir(sys_dir);
+        return 0;
+}
+
+void print_events_type(u8 type)
+{
+        struct event_symbol *syms = event_symbols;
+        unsigned int i;
+        char name[64];
+
+        for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
+                if (type != syms->type)
+                        continue;
 
                 if (strlen(syms->alias))
-                        sprintf(name, "%s OR %s", syms->symbol, syms->alias);
+                        snprintf(name, sizeof(name),  "%s OR %s",
+                                 syms->symbol, syms->alias);
                 else
-                        strcpy(name, syms->symbol);
-                printf("  %-42s [%s]\n", name,
-                        event_type_descriptors[type]);
+                        snprintf(name, sizeof(name), "%s", syms->symbol);
 
-                prev_type = type;
+                printf("  %-50s [%s]\n", name,
+                        event_type_descriptors[type]);
         }
+}
+
+int print_hwcache_events(const char *event_glob)
+{
+        unsigned int type, op, i, printed = 0;
 
-        printf("\n");
         for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
                 for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
                         /* skip invalid cache type */
@@ -941,25 +1013,81 @@ void print_events(void)
                                 continue;
 
                         for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-                                printf("  %-42s [%s]\n",
-                                        event_cache_name(type, op, i),
+                                char *name = event_cache_name(type, op, i);
+
+                                if (event_glob != NULL && !strglobmatch(name, event_glob))
+                                        continue;
+
+                                printf("  %-50s [%s]\n", name,
                                         event_type_descriptors[PERF_TYPE_HW_CACHE]);
+                                ++printed;
                         }
                 }
         }
 
+        return printed;
+}
+
+#define MAX_NAME_LEN 100
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(const char *event_glob)
+{
+        unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0;
+        struct event_symbol *syms = event_symbols;
+        char name[MAX_NAME_LEN];
+
+        printf("\n");
+        printf("List of pre-defined events (to be used in -e):\n");
+
+        for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
+                type = syms->type;
+
+                if (type != prev_type && printed) {
+                        printf("\n");
+                        printed = 0;
+                        ntypes_printed++;
+                }
+
+                if (event_glob != NULL && 
+                    !(strglobmatch(syms->symbol, event_glob) ||
+                      (syms->alias && strglobmatch(syms->alias, event_glob))))
+                        continue;
+
+                if (strlen(syms->alias))
+                        snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
+                else
+                        strncpy(name, syms->symbol, MAX_NAME_LEN);
+                printf("  %-50s [%s]\n", name,
+                        event_type_descriptors[type]);
+
+                prev_type = type;
+                ++printed;
+        }
+
+        if (ntypes_printed) {
+                printed = 0;
+                printf("\n");
+        }
+        print_hwcache_events(event_glob);
+
+        if (event_glob != NULL)
+                return;
+
         printf("\n");
-        printf("  %-42s [%s]\n",
+        printf("  %-50s [%s]\n",
                 "rNNN (see 'perf list --help' on how to encode it)",
                event_type_descriptors[PERF_TYPE_RAW]);
         printf("\n");
 
-        printf("  %-42s [%s]\n",
+        printf("  %-50s [%s]\n",
                         "mem:<addr>[:access]",
                         event_type_descriptors[PERF_TYPE_BREAKPOINT]);
         printf("\n");
 
-        print_tracepoint_events();
+        print_tracepoint_events(NULL, NULL);
 
         exit(129);
 }
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index fc4ab3fe877a..746d3fcbfc2a 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -4,6 +4,11 @@
  * Parse symbolic events/counts passed in as options:
  */
 
+#include "../../../include/linux/perf_event.h"
+
+struct list_head;
+struct perf_evsel;
+
 struct option;
 
 struct tracepoint_path {
@@ -13,14 +18,10 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
-extern bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events);
-
-extern int                      nr_counters;
+extern bool have_tracepoints(struct list_head *evlist);
 
-extern struct perf_event_attr attrs[MAX_COUNTERS];
-extern char *filters[MAX_COUNTERS];
-
-extern const char *event_name(int ctr);
+const char *event_type(int type);
+const char *event_name(struct perf_evsel *event);
 extern const char *__event_name(int type, u64 config);
 
 extern int parse_events(const struct option *opt, const char *str, int unset);
@@ -28,10 +29,13 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
-extern void print_events(void);
+void print_events(const char *event_glob);
+void print_events_type(u8 type);
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
+int print_hwcache_events(const char *event_glob);
+extern int is_valid_tracepoint(const char *event_string);
 
 extern char debugfs_path[];
 extern int valid_debugfs_mount(const char *debugfs);
 
-
 #endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index c7d72dce54b2..abc31a1dac1a 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -119,6 +119,10 @@ struct option {
         { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
         { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
+        { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
+        .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+        .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
 
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c
index 58a470d036dd..bd7497711424 100644
--- a/tools/perf/util/path.c
+++ b/tools/perf/util/path.c
@@ -22,6 +22,7 @@ static const char *get_perf_dir(void)
         return ".";
 }
 
+#ifdef NO_STRLCPY
 size_t strlcpy(char *dest, const char *src, size_t size)
 {
         size_t ret = strlen(src);
@@ -33,7 +34,7 @@ size_t strlcpy(char *dest, const char *src, size_t size)
         }
         return ret;
 }
-
+#endif
 
 static char *get_pathname(void)
 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index fcc16e4349df..f0223166e761 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -31,6 +31,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <limits.h>
+#include <elf.h>
 
 #undef _GNU_SOURCE
 #include "util.h"
@@ -74,10 +75,9 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static struct machine machine;
 
-/* Initialize symbol maps and path of vmlinux */
+/* Initialize symbol maps and path of vmlinux/modules */
 static int init_vmlinux(void)
 {
-        struct dso *kernel;
         int ret;
 
         symbol_conf.sort_by_name = true;
@@ -91,33 +91,95 @@ static int init_vmlinux(void)
                 goto out;
         }
 
-        ret = machine__init(&machine, "/", 0);
+        ret = machine__init(&machine, "", HOST_KERNEL_ID);
         if (ret < 0)
                 goto out;
 
-        kernel = dso__new_kernel(symbol_conf.vmlinux_name);
-        if (kernel == NULL)
-                die("Failed to create kernel dso.");
-
-        ret = __machine__create_kernel_maps(&machine, kernel);
-        if (ret < 0)
-                pr_debug("Failed to create kernel maps.\n");
-
+        if (machine__create_kernel_maps(&machine) < 0) {
+                pr_debug("machine__create_kernel_maps() failed.\n");
+                goto out;
+        }
 out:
         if (ret < 0)
                 pr_warning("Failed to init vmlinux path.\n");
         return ret;
 }
 
+static struct symbol *__find_kernel_function_by_name(const char *name,
+                                                     struct map **mapp)
+{
+        return machine__find_kernel_function_by_name(&machine, name, mapp,
+                                                     NULL);
+}
+
+static struct map *kernel_get_module_map(const char *module)
+{
+        struct rb_node *nd;
+        struct map_groups *grp = &machine.kmaps;
+
+        if (!module)
+                module = "kernel";
+
+        for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
+                struct map *pos = rb_entry(nd, struct map, rb_node);
+                if (strncmp(pos->dso->short_name + 1, module,
+                            pos->dso->short_name_len - 2) == 0) {
+                        return pos;
+                }
+        }
+        return NULL;
+}
+
+static struct dso *kernel_get_module_dso(const char *module)
+{
+        struct dso *dso;
+        struct map *map;
+        const char *vmlinux_name;
+
+        if (module) {
+                list_for_each_entry(dso, &machine.kernel_dsos, node) {
+                        if (strncmp(dso->short_name + 1, module,
+                                    dso->short_name_len - 2) == 0)
+                                goto found;
+                }
+                pr_debug("Failed to find module %s.\n", module);
+                return NULL;
+        }
+
+        map = machine.vmlinux_maps[MAP__FUNCTION];
+        dso = map->dso;
+
+        vmlinux_name = symbol_conf.vmlinux_name;
+        if (vmlinux_name) {
+                if (dso__load_vmlinux(dso, map, vmlinux_name, NULL) <= 0)
+                        return NULL;
+        } else {
+                if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
+                        pr_debug("Failed to load kernel map.\n");
+                        return NULL;
+                }
+        }
+found:
+        return dso;
+}
+
+const char *kernel_get_module_path(const char *module)
+{
+        struct dso *dso = kernel_get_module_dso(module);
+        return (dso) ? dso->long_name : NULL;
+}
+
 #ifdef DWARF_SUPPORT
-static int open_vmlinux(void)
+static int open_vmlinux(const char *module)
 {
-        if (map__load(machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
-                pr_debug("Failed to load kernel map.\n");
-                return -EINVAL;
+        const char *path = kernel_get_module_path(module);
+        if (!path) {
+                pr_err("Failed to find path of %s module.\n",
+                       module ?: "kernel");
+                return -ENOENT;
         }
-        pr_debug("Try to open %s\n", machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name);
-        return open(machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
+        pr_debug("Try to open %s\n", path);
+        return open(path, O_RDONLY);
 }
 
 /*
@@ -125,20 +187,19 @@ static int open_vmlinux(void)
  * Currently only handles kprobes.
  */
 static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-                                       struct perf_probe_point *pp)
+                                        struct perf_probe_point *pp)
 {
         struct symbol *sym;
-        int fd, ret = -ENOENT;
+        struct map *map;
+        u64 addr;
+        int ret = -ENOENT;
 
-        sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
-                                       tp->symbol, NULL);
+        sym = __find_kernel_function_by_name(tp->symbol, &map);
         if (sym) {
-                fd = open_vmlinux();
-                if (fd >= 0) {
-                        ret = find_perf_probe_point(fd,
-                                                 sym->start + tp->offset, pp);
-                        close(fd);
-                }
+                addr = map->unmap_ip(map, sym->start + tp->offset);
+                pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol,
+                         tp->offset, addr);
+                ret = find_perf_probe_point((unsigned long)addr, pp);
         }
         if (ret <= 0) {
                 pr_debug("Failed to find corresponding probes from "
@@ -156,12 +217,12 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 /* 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)
+                                           int max_tevs, const char *module)
 {
         bool need_dwarf = perf_probe_event_need_dwarf(pev);
         int fd, ntevs;
 
-        fd = open_vmlinux();
+        fd = open_vmlinux(module);
         if (fd < 0) {
                 if (need_dwarf) {
                         pr_warning("Failed to open debuginfo file.\n");
@@ -173,7 +234,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
         /* Searching trace events corresponding to probe event */
         ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs);
-        close(fd);
 
         if (ntevs > 0) {        /* Succeeded to find trace events */
                 pr_debug("find %d probe_trace_events.\n", ntevs);
@@ -191,7 +251,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                 pr_warning("Warning: No dwarf info found in the vmlinux - "
                         "please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
                 if (!need_dwarf) {
-                        pr_debug("Trying to use symbols.\nn");
+                        pr_debug("Trying to use symbols.\n");
                         return 0;
                 }
         }
@@ -260,47 +320,54 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 #define LINEBUF_SIZE 256
 #define NR_ADDITIONAL_LINES 2
 
-static int show_one_line(FILE *fp, int l, bool skip, bool show_num)
+static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 {
         char buf[LINEBUF_SIZE];
-        const char *color = PERF_COLOR_BLUE;
-
-        if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
-                goto error;
-        if (!skip) {
-                if (show_num)
-                        fprintf(stdout, "%7d  %s", l, buf);
-                else
-                        color_fprintf(stdout, color, "         %s", buf);
-        }
+        const char *color = show_num ? "" : PERF_COLOR_BLUE;
+        const char *prefix = NULL;
 
-        while (strlen(buf) == LINEBUF_SIZE - 1 &&
-               buf[LINEBUF_SIZE - 2] != '\n') {
+        do {
                 if (fgets(buf, LINEBUF_SIZE, fp) == NULL)
                         goto error;
-                if (!skip) {
-                        if (show_num)
-                                fprintf(stdout, "%s", buf);
-                        else
-                                color_fprintf(stdout, color, "%s", buf);
+                if (skip)
+                        continue;
+                if (!prefix) {
+                        prefix = show_num ? "%7d  " : "         ";
+                        color_fprintf(stdout, color, prefix, l);
                 }
-        }
+                color_fprintf(stdout, color, "%s", buf);
 
-        return 0;
+        } while (strchr(buf, '\n') == NULL);
+
+        return 1;
 error:
-        if (feof(fp))
-                pr_warning("Source file is shorter than expected.\n");
-        else
+        if (ferror(fp)) {
                 pr_warning("File read error: %s\n", strerror(errno));
+                return -1;
+        }
+        return 0;
+}
 
-        return -1;
+static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
+{
+        int rv = __show_one_line(fp, l, skip, show_num);
+        if (rv == 0) {
+                pr_warning("Source file is shorter than expected.\n");
+                rv = -1;
+        }
+        return rv;
 }
 
+#define show_one_line_with_num(f,l)     _show_one_line(f,l,false,true)
+#define show_one_line(f,l)              _show_one_line(f,l,false,false)
+#define skip_one_line(f,l)              _show_one_line(f,l,true,false)
+#define show_one_line_or_eof(f,l)       __show_one_line(f,l,false,false)
+
 /*
  * Show line-range always requires debuginfo to find source file and
  * line number.
  */
-int show_line_range(struct line_range *lr)
+int show_line_range(struct line_range *lr, const char *module)
 {
         int l = 1;
         struct line_node *ln;
@@ -313,14 +380,13 @@ int show_line_range(struct line_range *lr)
         if (ret < 0)
                 return ret;
 
-        fd = open_vmlinux();
+        fd = open_vmlinux(module);
         if (fd < 0) {
                 pr_warning("Failed to open debuginfo file.\n");
                 return fd;
         }
 
         ret = find_line_range(fd, lr);
-        close(fd);
         if (ret == 0) {
                 pr_warning("Specified source line is not found.\n");
                 return -ENOENT;
@@ -341,10 +407,10 @@ int show_line_range(struct line_range *lr)
         setup_pager();
 
         if (lr->function)
-                fprintf(stdout, "<%s:%d>\n", lr->function,
+                fprintf(stdout, "<%s@%s:%d>\n", lr->function, lr->path,
                         lr->start - lr->offset);
         else
-                fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+                fprintf(stdout, "<%s:%d>\n", lr->path, lr->start);
 
         fp = fopen(lr->path, "r");
         if (fp == NULL) {
@@ -353,36 +419,124 @@ int show_line_range(struct line_range *lr)
                 return -errno;
         }
         /* Skip to starting line number */
-        while (l < lr->start && ret >= 0)
-                ret = show_one_line(fp, l++, true, false);
-        if (ret < 0)
-                goto end;
+        while (l < lr->start) {
+                ret = skip_one_line(fp, l++);
+                if (ret < 0)
+                        goto end;
+        }
 
         list_for_each_entry(ln, &lr->line_list, list) {
-                while (ln->line > l && ret >= 0)
-                        ret = show_one_line(fp, (l++) - lr->offset,
-                                            false, false);
-                if (ret >= 0)
-                        ret = show_one_line(fp, (l++) - lr->offset,
-                                            false, true);
+                for (; ln->line > l; l++) {
+                        ret = show_one_line(fp, l - lr->offset);
+                        if (ret < 0)
+                                goto end;
+                }
+                ret = show_one_line_with_num(fp, l++ - lr->offset);
                 if (ret < 0)
                         goto end;
         }
 
         if (lr->end == INT_MAX)
                 lr->end = l + NR_ADDITIONAL_LINES;
-        while (l <= lr->end && !feof(fp) && ret >= 0)
-                ret = show_one_line(fp, (l++) - lr->offset, false, false);
+        while (l <= lr->end) {
+                ret = show_one_line_or_eof(fp, l++ - lr->offset);
+                if (ret <= 0)
+                        break;
+        }
 end:
         fclose(fp);
         return ret;
 }
 
+static int show_available_vars_at(int fd, struct perf_probe_event *pev,
+                                  int max_vls, struct strfilter *_filter,
+                                  bool externs)
+{
+        char *buf;
+        int ret, i, nvars;
+        struct str_node *node;
+        struct variable_list *vls = NULL, *vl;
+        const char *var;
+
+        buf = synthesize_perf_probe_point(&pev->point);
+        if (!buf)
+                return -EINVAL;
+        pr_debug("Searching variables at %s\n", buf);
+
+        ret = find_available_vars_at(fd, pev, &vls, max_vls, externs);
+        if (ret <= 0) {
+                pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+                goto end;
+        }
+        /* Some variables are found */
+        fprintf(stdout, "Available variables at %s\n", buf);
+        for (i = 0; i < ret; i++) {
+                vl = &vls[i];
+                /*
+                 * A probe point might be converted to
+                 * several trace points.
+                 */
+                fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
+                        vl->point.offset);
+                free(vl->point.symbol);
+                nvars = 0;
+                if (vl->vars) {
+                        strlist__for_each(node, vl->vars) {
+                                var = strchr(node->s, '\t') + 1;
+                                if (strfilter__compare(_filter, var)) {
+                                        fprintf(stdout, "\t\t%s\n", node->s);
+                                        nvars++;
+                                }
+                        }
+                        strlist__delete(vl->vars);
+                }
+                if (nvars == 0)
+                        fprintf(stdout, "\t\t(No matched variables)\n");
+        }
+        free(vls);
+end:
+        free(buf);
+        return ret;
+}
+
+/* Show available variables on given probe point */
+int show_available_vars(struct perf_probe_event *pevs, int npevs,
+                        int max_vls, const char *module,
+                        struct strfilter *_filter, bool externs)
+{
+        int i, fd, ret = 0;
+
+        ret = init_vmlinux();
+        if (ret < 0)
+                return ret;
+
+        setup_pager();
+
+        for (i = 0; i < npevs && ret >= 0; i++) {
+                fd = open_vmlinux(module);
+                if (fd < 0) {
+                        pr_warning("Failed to open debug information file.\n");
+                        ret = fd;
+                        break;
+                }
+                ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter,
+                                             externs);
+        }
+        return ret;
+}
+
 #else   /* !DWARF_SUPPORT */
 
 static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-                                       struct perf_probe_point *pp)
+                                        struct perf_probe_point *pp)
 {
+        struct symbol *sym;
+
+        sym = __find_kernel_function_by_name(tp->symbol, NULL);
+        if (!sym) {
+                pr_err("Failed to find symbol %s in kernel.\n", tp->symbol);
+                return -ENOENT;
+        }
         pp->function = strdup(tp->symbol);
         if (pp->function == NULL)
                 return -ENOMEM;
@@ -394,7 +548,7 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                                 struct probe_trace_event **tevs __unused,
-                                int max_tevs __unused)
+                                int max_tevs __unused, const char *mod __unused)
 {
         if (perf_probe_event_need_dwarf(pev)) {
                 pr_warning("Debuginfo-analysis is not supported.\n");
@@ -403,64 +557,113 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         return 0;
 }
 
-int show_line_range(struct line_range *lr __unused)
+int show_line_range(struct line_range *lr __unused, const char *module __unused)
 {
         pr_warning("Debuginfo-analysis is not supported.\n");
         return -ENOSYS;
 }
 
+int show_available_vars(struct perf_probe_event *pevs __unused,
+                        int npevs __unused, int max_vls __unused,
+                        const char *module __unused,
+                        struct strfilter *filter __unused,
+                        bool externs __unused)
+{
+        pr_warning("Debuginfo-analysis is not supported.\n");
+        return -ENOSYS;
+}
 #endif
 
+static int parse_line_num(char **ptr, int *val, const char *what)
+{
+        const char *start = *ptr;
+
+        errno = 0;
+        *val = strtol(*ptr, ptr, 0);
+        if (errno || *ptr == start) {
+                semantic_error("'%s' is not a valid number.\n", what);
+                return -EINVAL;
+        }
+        return 0;
+}
+
+/*
+ * Stuff 'lr' according to the line range described by 'arg'.
+ * The line range syntax is described by:
+ *
+ *         SRC[:SLN[+NUM|-ELN]]
+ *         FNC[@SRC][:SLN[+NUM|-ELN]]
+ */
 int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
-        const char *ptr;
-        char *tmp;
-        /*
-         * <Syntax>
-         * SRC:SLN[+NUM|-ELN]
-         * FUNC[:SLN[+NUM|-ELN]]
-         */
-        ptr = strchr(arg, ':');
-        if (ptr) {
-                lr->start = (int)strtoul(ptr + 1, &tmp, 0);
-                if (*tmp == '+') {
-                        lr->end = lr->start + (int)strtoul(tmp + 1, &tmp, 0);
-                        lr->end--;      /*
-                                         * Adjust the number of lines here.
-                                         * If the number of lines == 1, the
-                                         * the end of line should be equal to
-                                         * the start of line.
-                                         */
-                } else if (*tmp == '-')
-                        lr->end = (int)strtoul(tmp + 1, &tmp, 0);
-                else
-                        lr->end = INT_MAX;
+        char *range, *file, *name = strdup(arg);
+        int err;
+
+        if (!name)
+                return -ENOMEM;
+
+        lr->start = 0;
+        lr->end = INT_MAX;
+
+        range = strchr(name, ':');
+        if (range) {
+                *range++ = '\0';
+
+                err = parse_line_num(&range, &lr->start, "start line");
+                if (err)
+                        goto err;
+
+                if (*range == '+' || *range == '-') {
+                        const char c = *range++;
+
+                        err = parse_line_num(&range, &lr->end, "end line");
+                        if (err)
+                                goto err;
+
+                        if (c == '+') {
+                                lr->end += lr->start;
+                                /*
+                                 * Adjust the number of lines here.
+                                 * If the number of lines == 1, the
+                                 * the end of line should be equal to
+                                 * the start of line.
+                                 */
+                                lr->end--;
+                        }
+                }
+
                 pr_debug("Line range is %d to %d\n", lr->start, lr->end);
+
+                err = -EINVAL;
                 if (lr->start > lr->end) {
                         semantic_error("Start line must be smaller"
                                        " than end line.\n");
-                        return -EINVAL;
+                        goto err;
                 }
-                if (*tmp != '\0') {
-                        semantic_error("Tailing with invalid character '%d'.\n",
-                                       *tmp);
-                        return -EINVAL;
+                if (*range != '\0') {
+                        semantic_error("Tailing with invalid str '%s'.\n", range);
+                        goto err;
                 }
-                tmp = strndup(arg, (ptr - arg));
-        } else {
-                tmp = strdup(arg);
-                lr->end = INT_MAX;
         }
 
-        if (tmp == NULL)
-                return -ENOMEM;
-
-        if (strchr(tmp, '.'))
-                lr->file = tmp;
+        file = strchr(name, '@');
+        if (file) {
+                *file = '\0';
+                lr->file = strdup(++file);
+                if (lr->file == NULL) {
+                        err = -ENOMEM;
+                        goto err;
+                }
+                lr->function = name;
+        } else if (strchr(name, '.'))
+                lr->file = name;
         else
-                lr->function = tmp;
+                lr->function = name;
 
         return 0;
+err:
+        free(name);
+        return err;
 }
 
 /* Check the name is good for event/group */
@@ -584,39 +787,40 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 
         /* Exclusion check */
         if (pp->lazy_line && pp->line) {
-                semantic_error("Lazy pattern can't be used with line number.");
+                semantic_error("Lazy pattern can't be used with"
+                               " line number.\n");
                 return -EINVAL;
         }
 
         if (pp->lazy_line && pp->offset) {
-                semantic_error("Lazy pattern can't be used with offset.");
+                semantic_error("Lazy pattern can't be used with offset.\n");
                 return -EINVAL;
         }
 
         if (pp->line && pp->offset) {
-                semantic_error("Offset can't be used with line number.");
+                semantic_error("Offset can't be used with line number.\n");
                 return -EINVAL;
         }
 
         if (!pp->line && !pp->lazy_line && pp->file && !pp->function) {
                 semantic_error("File always requires line number or "
-                               "lazy pattern.");
+                               "lazy pattern.\n");
                 return -EINVAL;
         }
 
         if (pp->offset && !pp->function) {
-                semantic_error("Offset requires an entry function.");
+                semantic_error("Offset requires an entry function.\n");
                 return -EINVAL;
         }
 
         if (pp->retprobe && !pp->function) {
-                semantic_error("Return probe requires an entry function.");
+                semantic_error("Return probe requires an entry function.\n");
                 return -EINVAL;
         }
 
         if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
                 semantic_error("Offset/Line/Lazy pattern can't be used with "
-                               "return probe.");
+                               "return probe.\n");
                 return -EINVAL;
         }
 
@@ -890,7 +1094,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 
         return tmp - buf;
 error:
-        pr_debug("Failed to synthesize perf probe argument: %s",
+        pr_debug("Failed to synthesize perf probe argument: %s\n",
                  strerror(-ret));
         return ret;
 }
@@ -918,13 +1122,13 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
                         goto error;
         }
         if (pp->file) {
-                len = strlen(pp->file) - 31;
-                if (len < 0)
-                        len = 0;
-                tmp = strchr(pp->file + len, '/');
-                if (!tmp)
-                        tmp = pp->file + len;
-                ret = e_snprintf(file, 32, "@%s", tmp + 1);
+                tmp = pp->file;
+                len = strlen(tmp);
+                if (len > 30) {
+                        tmp = strchr(pp->file + len - 30, '/');
+                        tmp = tmp ? tmp + 1 : pp->file + len - 30;
+                }
+                ret = e_snprintf(file, 32, "@%s", tmp);
                 if (ret <= 0)
                         goto error;
         }
@@ -940,7 +1144,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 
         return buf;
 error:
-        pr_debug("Failed to synthesize perf probe point: %s",
+        pr_debug("Failed to synthesize perf probe point: %s\n",
                  strerror(-ret));
         if (buf)
                 free(buf);
@@ -1087,7 +1291,7 @@ error:
 }
 
 static int convert_to_perf_probe_event(struct probe_trace_event *tev,
-                                struct perf_probe_event *pev)
+                                       struct perf_probe_event *pev)
 {
         char buf[64] = "";
         int i, ret;
@@ -1516,14 +1720,14 @@ 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)
+                                          int max_tevs, const char *module)
 {
         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);
+        ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, module);
         if (ret != 0)
                 return ret;
 
@@ -1572,8 +1776,7 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
         }
 
         /* Currently just checking function name from symbol map */
-        sym = map__find_symbol_by_name(machine.vmlinux_maps[MAP__FUNCTION],
-                                       tev->point.symbol, NULL);
+        sym = __find_kernel_function_by_name(tev->point.symbol, NULL);
         if (!sym) {
                 pr_warning("Kernel symbol \'%s\' not found.\n",
                            tev->point.symbol);
@@ -1596,7 +1799,7 @@ struct __event_package {
 };
 
 int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-                          bool force_add, int max_tevs)
+                          int max_tevs, const char *module, bool force_add)
 {
         int i, j, ret;
         struct __event_package *pkgs;
@@ -1617,16 +1820,21 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
                 pkgs[i].pev = &pevs[i];
                 /* Convert with or without debuginfo */
                 ret  = convert_to_probe_trace_events(pkgs[i].pev,
-                                                      &pkgs[i].tevs, max_tevs);
+                                                     &pkgs[i].tevs,
+                                                     max_tevs,
+                                                     module);
                 if (ret < 0)
                         goto end;
                 pkgs[i].ntevs = ret;
         }
 
         /* Loop 2: add all events */
-        for (i = 0; i < npevs && ret >= 0; i++)
+        for (i = 0; i < npevs; i++) {
                 ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
                                                 pkgs[i].ntevs, force_add);
+                if (ret < 0)
+                        break;
+        }
 end:
         /* Loop 3: cleanup and free trace events  */
         for (i = 0; i < npevs; i++) {
@@ -1680,7 +1888,7 @@ static int del_trace_probe_event(int fd, const char *group,
 
         ret = e_snprintf(buf, 128, "%s:%s", group, event);
         if (ret < 0) {
-                pr_err("Failed to copy event.");
+                pr_err("Failed to copy event.\n");
                 return ret;
         }
 
@@ -1752,4 +1960,46 @@ int del_perf_probe_events(struct strlist *dellist)
 
         return ret;
 }
+/* TODO: don't use a global variable for filter ... */
+static struct strfilter *available_func_filter;
+
+/*
+ * If a symbol corresponds to a function with global binding and
+ * matches filter return 0. For all others return 1.
+ */
+static int filter_available_functions(struct map *map __unused,
+                                      struct symbol *sym)
+{
+        if (sym->binding == STB_GLOBAL &&
+            strfilter__compare(available_func_filter, sym->name))
+                return 0;
+        return 1;
+}
 
+int show_available_funcs(const char *module, struct strfilter *_filter)
+{
+        struct map *map;
+        int ret;
+
+        setup_pager();
+
+        ret = init_vmlinux();
+        if (ret < 0)
+                return ret;
+
+        map = kernel_get_module_map(module);
+        if (!map) {
+                pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+                return -EINVAL;
+        }
+        available_func_filter = _filter;
+        if (map__load(map, filter_available_functions)) {
+                pr_err("Failed to load map.\n");
+                return -EINVAL;
+        }
+        if (!dso__sorted_by_name(map->dso, map->type))
+                dso__sort_by_name(map->dso, map->type);
+
+        dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+        return 0;
+}
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 5af39243a25b..3434fc9d79d5 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "strlist.h"
+#include "strfilter.h"
 
 extern bool probe_event_dry_run;
 
@@ -90,6 +91,12 @@ struct line_range {
         struct list_head        line_list;      /* Visible lines */
 };
 
+/* List of variables */
+struct variable_list {
+        struct probe_trace_point        point;  /* Actual probepoint */
+        struct strlist                  *vars;  /* Available variables */
+};
+
 /* Command string to events */
 extern int parse_perf_probe_command(const char *cmd,
                                     struct perf_probe_event *pev);
@@ -109,12 +116,19 @@ extern void clear_perf_probe_event(struct perf_probe_event *pev);
 /* Command string to line-range */
 extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
 
+/* Internal use: Return kernel/module path */
+extern const char *kernel_get_module_path(const char *module);
 
 extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-                                 bool force_add, int max_probe_points);
+                                 int max_probe_points, const char *module,
+                                 bool force_add);
 extern int del_perf_probe_events(struct strlist *dellist);
 extern int show_perf_probe_events(void);
-extern int show_line_range(struct line_range *lr);
+extern int show_line_range(struct line_range *lr, const char *module);
+extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
+                               int max_probe_points, const char *module,
+                               struct strfilter *filter, bool externs);
+extern int show_available_funcs(const char *module, struct strfilter *filter);
 
 
 /* Maximum index number of event-name postfix */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 32b81f707ff5..3b9d0b800d5c 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -33,6 +33,7 @@
 #include <ctype.h>
 #include <dwarf-regs.h>
 
+#include <linux/bitops.h>
 #include "event.h"
 #include "debug.h"
 #include "util.h"
@@ -116,6 +117,126 @@ static void line_list__free(struct list_head *head)
         }
 }
 
+/* Dwarf FL wrappers */
+static char *debuginfo_path;    /* Currently dummy */
+
+static const Dwfl_Callbacks offline_callbacks = {
+        .find_debuginfo = dwfl_standard_find_debuginfo,
+        .debuginfo_path = &debuginfo_path,
+
+        .section_address = dwfl_offline_section_address,
+
+        /* We use this table for core files too.  */
+        .find_elf = dwfl_build_id_find_elf,
+};
+
+/* Get a Dwarf from offline image */
+static Dwarf *dwfl_init_offline_dwarf(int fd, Dwfl **dwflp, Dwarf_Addr *bias)
+{
+        Dwfl_Module *mod;
+        Dwarf *dbg = NULL;
+
+        if (!dwflp)
+                return NULL;
+
+        *dwflp = dwfl_begin(&offline_callbacks);
+        if (!*dwflp)
+                return NULL;
+
+        mod = dwfl_report_offline(*dwflp, "", "", fd);
+        if (!mod)
+                goto error;
+
+        dbg = dwfl_module_getdwarf(mod, bias);
+        if (!dbg) {
+error:
+                dwfl_end(*dwflp);
+                *dwflp = NULL;
+        }
+        return dbg;
+}
+
+#if _ELFUTILS_PREREQ(0, 148)
+/* This method is buggy if elfutils is older than 0.148 */
+static int __linux_kernel_find_elf(Dwfl_Module *mod,
+                                   void **userdata,
+                                   const char *module_name,
+                                   Dwarf_Addr base,
+                                   char **file_name, Elf **elfp)
+{
+        int fd;
+        const char *path = kernel_get_module_path(module_name);
+
+        pr_debug2("Use file %s for %s\n", path, module_name);
+        if (path) {
+                fd = open(path, O_RDONLY);
+                if (fd >= 0) {
+                        *file_name = strdup(path);
+                        return fd;
+                }
+        }
+        /* If failed, try to call standard method */
+        return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
+                                          file_name, elfp);
+}
+
+static const Dwfl_Callbacks kernel_callbacks = {
+        .find_debuginfo = dwfl_standard_find_debuginfo,
+        .debuginfo_path = &debuginfo_path,
+
+        .find_elf = __linux_kernel_find_elf,
+        .section_address = dwfl_linux_kernel_module_section_address,
+};
+
+/* Get a Dwarf from live kernel image */
+static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **dwflp,
+                                          Dwarf_Addr *bias)
+{
+        Dwarf *dbg;
+
+        if (!dwflp)
+                return NULL;
+
+        *dwflp = dwfl_begin(&kernel_callbacks);
+        if (!*dwflp)
+                return NULL;
+
+        /* Load the kernel dwarves: Don't care the result here */
+        dwfl_linux_kernel_report_kernel(*dwflp);
+        dwfl_linux_kernel_report_modules(*dwflp);
+
+        dbg = dwfl_addrdwarf(*dwflp, addr, bias);
+        /* Here, check whether we could get a real dwarf */
+        if (!dbg) {
+                pr_debug("Failed to find kernel dwarf at %lx\n",
+                         (unsigned long)addr);
+                dwfl_end(*dwflp);
+                *dwflp = NULL;
+        }
+        return dbg;
+}
+#else
+/* With older elfutils, this just support kernel module... */
+static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr __used, Dwfl **dwflp,
+                                          Dwarf_Addr *bias)
+{
+        int fd;
+        const char *path = kernel_get_module_path("kernel");
+
+        if (!path) {
+                pr_err("Failed to find vmlinux path\n");
+                return NULL;
+        }
+
+        pr_debug2("Use file %s for debuginfo\n", path);
+        fd = open(path, O_RDONLY);
+        if (fd < 0)
+                return NULL;
+
+        return dwfl_init_offline_dwarf(fd, dwflp, bias);
+}
+#endif
+
 /* Dwarf wrappers */
 
 /* Find the realpath of the target file. */
@@ -152,6 +273,25 @@ static const char *cu_get_comp_dir(Dwarf_Die *cu_die)
         return dwarf_formstring(&attr);
 }
 
+/* Get a line number and file name for given address */
+static int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+                            const char **fname, int *lineno)
+{
+        Dwarf_Line *line;
+        Dwarf_Addr laddr;
+
+        line = dwarf_getsrc_die(cudie, (Dwarf_Addr)addr);
+        if (line && dwarf_lineaddr(line, &laddr) == 0 &&
+            addr == (unsigned long)laddr && dwarf_lineno(line, lineno) == 0) {
+                *fname = dwarf_linesrc(line, NULL, NULL);
+                if (!*fname)
+                        /* line number is useless without filename */
+                        *lineno = 0;
+        }
+
+        return *lineno ?: -ENOENT;
+}
+
 /* Compare diename and tname */
 static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
@@ -160,35 +300,76 @@ static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
         return name ? (strcmp(tname, name) == 0) : false;
 }
 
-/* Get type die, but skip qualifiers and typedef */
-static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+/* Get callsite line number of inline-function instance */
+static int die_get_call_lineno(Dwarf_Die *in_die)
 {
         Dwarf_Attribute attr;
+        Dwarf_Word ret;
+
+        if (!dwarf_attr(in_die, DW_AT_call_line, &attr))
+                return -ENOENT;
+
+        dwarf_formudata(&attr, &ret);
+        return (int)ret;
+}
+
+/* Get type die */
+static Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+        Dwarf_Attribute attr;
+
+        if (dwarf_attr_integrate(vr_die, DW_AT_type, &attr) &&
+            dwarf_formref_die(&attr, die_mem))
+                return die_mem;
+        else
+                return NULL;
+}
+
+/* Get a type die, but skip qualifiers */
+static Dwarf_Die *__die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
         int tag;
 
         do {
-                if (dwarf_attr(vr_die, DW_AT_type, &attr) == NULL ||
-                    dwarf_formref_die(&attr, die_mem) == NULL)
-                        return NULL;
-
-                tag = dwarf_tag(die_mem);
-                vr_die = die_mem;
+                vr_die = die_get_type(vr_die, die_mem);
+                if (!vr_die)
+                        break;
+                tag = dwarf_tag(vr_die);
         } while (tag == DW_TAG_const_type ||
                  tag == DW_TAG_restrict_type ||
                  tag == DW_TAG_volatile_type ||
-                 tag == DW_TAG_shared_type ||
-                 tag == DW_TAG_typedef);
+                 tag == DW_TAG_shared_type);
 
-        return die_mem;
+        return vr_die;
 }
 
-static bool die_is_signed_type(Dwarf_Die *tp_die)
+/* Get a type die, but skip qualifiers and typedef */
+static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem)
+{
+        do {
+                vr_die = __die_get_real_type(vr_die, die_mem);
+        } while (vr_die && dwarf_tag(vr_die) == DW_TAG_typedef);
+
+        return vr_die;
+}
+
+static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name,
+                              Dwarf_Word *result)
 {
         Dwarf_Attribute attr;
+
+        if (dwarf_attr(tp_die, attr_name, &attr) == NULL ||
+            dwarf_formudata(&attr, result) != 0)
+                return -ENOENT;
+
+        return 0;
+}
+
+static bool die_is_signed_type(Dwarf_Die *tp_die)
+{
         Dwarf_Word ret;
 
-        if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL ||
-            dwarf_formudata(&attr, &ret) != 0)
+        if (die_get_attr_udata(tp_die, DW_AT_encoding, &ret))
                 return false;
 
         return (ret == DW_ATE_signed_char || ret == DW_ATE_signed ||
@@ -197,11 +378,29 @@ static bool die_is_signed_type(Dwarf_Die *tp_die)
 
 static int die_get_byte_size(Dwarf_Die *tp_die)
 {
-        Dwarf_Attribute attr;
         Dwarf_Word ret;
 
-        if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL ||
-            dwarf_formudata(&attr, &ret) != 0)
+        if (die_get_attr_udata(tp_die, DW_AT_byte_size, &ret))
+                return 0;
+
+        return (int)ret;
+}
+
+static int die_get_bit_size(Dwarf_Die *tp_die)
+{
+        Dwarf_Word ret;
+
+        if (die_get_attr_udata(tp_die, DW_AT_bit_size, &ret))
+                return 0;
+
+        return (int)ret;
+}
+
+static int die_get_bit_offset(Dwarf_Die *tp_die)
+{
+        Dwarf_Word ret;
+
+        if (die_get_attr_udata(tp_die, DW_AT_bit_offset, &ret))
                 return 0;
 
         return (int)ret;
@@ -317,28 +516,196 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
                                       Dwarf_Die *die_mem)
 {
-        return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+        Dwarf_Die tmp_die;
+
+        sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr, &tmp_die);
+        if (!sp_die)
+                return NULL;
+
+        /* Inlined function could be recursive. Trace it until fail */
+        while (sp_die) {
+                memcpy(die_mem, sp_die, sizeof(Dwarf_Die));
+                sp_die = die_find_child(sp_die, __die_find_inline_cb, &addr,
+                                        &tmp_die);
+        }
+
+        return die_mem;
+}
+
+/* Walker on lines (Note: line number will not be sorted) */
+typedef int (* line_walk_handler_t) (const char *fname, int lineno,
+                                     Dwarf_Addr addr, void *data);
+
+struct __line_walk_param {
+        const char *fname;
+        line_walk_handler_t handler;
+        void *data;
+        int retval;
+};
+
+static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data)
+{
+        struct __line_walk_param *lw = data;
+        Dwarf_Addr addr;
+        int lineno;
+
+        if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) {
+                lineno = die_get_call_lineno(in_die);
+                if (lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) {
+                        lw->retval = lw->handler(lw->fname, lineno, addr,
+                                                 lw->data);
+                        if (lw->retval != 0)
+                                return DIE_FIND_CB_FOUND;
+                }
+        }
+        return DIE_FIND_CB_SIBLING;
+}
+
+/* Walk on lines of blocks included in given DIE */
+static int __die_walk_funclines(Dwarf_Die *sp_die,
+                                line_walk_handler_t handler, void *data)
+{
+        struct __line_walk_param lw = {
+                .handler = handler,
+                .data = data,
+                .retval = 0,
+        };
+        Dwarf_Die die_mem;
+        Dwarf_Addr addr;
+        int lineno;
+
+        /* Handle function declaration line */
+        lw.fname = dwarf_decl_file(sp_die);
+        if (lw.fname && dwarf_decl_line(sp_die, &lineno) == 0 &&
+            dwarf_entrypc(sp_die, &addr) == 0) {
+                lw.retval = handler(lw.fname, lineno, addr, data);
+                if (lw.retval != 0)
+                        goto done;
+        }
+        die_find_child(sp_die, __die_walk_funclines_cb, &lw, &die_mem);
+done:
+        return lw.retval;
+}
+
+static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data)
+{
+        struct __line_walk_param *lw = data;
+
+        lw->retval = __die_walk_funclines(sp_die, lw->handler, lw->data);
+        if (lw->retval != 0)
+                return DWARF_CB_ABORT;
+
+        return DWARF_CB_OK;
 }
 
+/*
+ * Walk on lines inside given PDIE. If the PDIE is subprogram, walk only on
+ * the lines inside the subprogram, otherwise PDIE must be a CU DIE.
+ */
+static int die_walk_lines(Dwarf_Die *pdie, line_walk_handler_t handler,
+                          void *data)
+{
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        Dwarf_Addr addr;
+        const char *fname;
+        int lineno, ret = 0;
+        Dwarf_Die die_mem, *cu_die;
+        size_t nlines, i;
+
+        /* Get the CU die */
+        if (dwarf_tag(pdie) == DW_TAG_subprogram)
+                cu_die = dwarf_diecu(pdie, &die_mem, NULL, NULL);
+        else
+                cu_die = pdie;
+        if (!cu_die) {
+                pr_debug2("Failed to get CU from subprogram\n");
+                return -EINVAL;
+        }
+
+        /* Get lines list in the CU */
+        if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0) {
+                pr_debug2("Failed to get source lines on this CU.\n");
+                return -ENOENT;
+        }
+        pr_debug2("Get %zd lines from this CU\n", nlines);
+
+        /* Walk on the lines on lines list */
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
+                if (line == NULL ||
+                    dwarf_lineno(line, &lineno) != 0 ||
+                    dwarf_lineaddr(line, &addr) != 0) {
+                        pr_debug2("Failed to get line info. "
+                                  "Possible error in debuginfo.\n");
+                        continue;
+                }
+                /* Filter lines based on address */
+                if (pdie != cu_die)
+                        /*
+                         * Address filtering
+                         * The line is included in given function, and
+                         * no inline block includes it.
+                         */
+                        if (!dwarf_haspc(pdie, addr) ||
+                            die_find_inlinefunc(pdie, addr, &die_mem))
+                                continue;
+                /* Get source line */
+                fname = dwarf_linesrc(line, NULL, NULL);
+
+                ret = handler(fname, lineno, addr, data);
+                if (ret != 0)
+                        return ret;
+        }
+
+        /*
+         * Dwarf lines doesn't include function declarations and inlined
+         * subroutines. We have to check functions list or given function.
+         */
+        if (pdie != cu_die)
+                ret = __die_walk_funclines(pdie, handler, data);
+        else {
+                struct __line_walk_param param = {
+                        .handler = handler,
+                        .data = data,
+                        .retval = 0,
+                };
+                dwarf_getfuncs(cu_die, __die_walk_culines_cb, &param, 0);
+                ret = param.retval;
+        }
+
+        return ret;
+}
+
+struct __find_variable_param {
+        const char *name;
+        Dwarf_Addr addr;
+};
+
 static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
 {
-        const char *name = data;
+        struct __find_variable_param *fvp = data;
         int tag;
 
         tag = dwarf_tag(die_mem);
         if ((tag == DW_TAG_formal_parameter ||
              tag == DW_TAG_variable) &&
-            die_compare_name(die_mem, name))
+            die_compare_name(die_mem, fvp->name))
                 return DIE_FIND_CB_FOUND;
 
-        return DIE_FIND_CB_CONTINUE;
+        if (dwarf_haspc(die_mem, fvp->addr))
+                return DIE_FIND_CB_CONTINUE;
+        else
+                return DIE_FIND_CB_SIBLING;
 }
 
-/* Find a variable called 'name' */
-static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
-                                    Dwarf_Die *die_mem)
+/* Find a variable called 'name' at given address */
+static Dwarf_Die *die_find_variable_at(Dwarf_Die *sp_die, const char *name,
+                                       Dwarf_Addr addr, Dwarf_Die *die_mem)
 {
-        return die_find_child(sp_die, __die_find_variable_cb, (void *)name,
+        struct __find_variable_param fvp = { .name = name, .addr = addr};
+
+        return die_find_child(sp_die, __die_find_variable_cb, (void *)&fvp,
                               die_mem);
 }
 
@@ -361,6 +728,60 @@ static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
                               die_mem);
 }
 
+/* Get the name of given variable DIE */
+static int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+{
+        Dwarf_Die type;
+        int tag, ret, ret2;
+        const char *tmp = "";
+
+        if (__die_get_real_type(vr_die, &type) == NULL)
+                return -ENOENT;
+
+        tag = dwarf_tag(&type);
+        if (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)
+                tmp = "*";
+        else if (tag == DW_TAG_subroutine_type) {
+                /* Function pointer */
+                ret = snprintf(buf, len, "(function_type)");
+                return (ret >= len) ? -E2BIG : ret;
+        } else {
+                if (!dwarf_diename(&type))
+                        return -ENOENT;
+                if (tag == DW_TAG_union_type)
+                        tmp = "union ";
+                else if (tag == DW_TAG_structure_type)
+                        tmp = "struct ";
+                /* Write a base name */
+                ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
+                return (ret >= len) ? -E2BIG : ret;
+        }
+        ret = die_get_typename(&type, buf, len);
+        if (ret > 0) {
+                ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
+                ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+        }
+        return ret;
+}
+
+/* Get the name and type of given variable DIE, stored as "type\tname" */
+static int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+{
+        int ret, ret2;
+
+        ret = die_get_typename(vr_die, buf, len);
+        if (ret < 0) {
+                pr_debug("Failed to get type, make it unknown.\n");
+                ret = snprintf(buf, len, "(unknown_type)");
+        }
+        if (ret > 0) {
+                ret2 = snprintf(buf + ret, len - ret, "\t%s",
+                                dwarf_diename(vr_die));
+                ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+        }
+        return ret;
+}
+
 /*
  * Probe finder related functions
  */
@@ -374,8 +795,13 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs)
         return ref;
 }
 
-/* Show a location */
-static int convert_variable_location(Dwarf_Die *vr_die, struct probe_finder *pf)
+/*
+ * Convert a location into trace_arg.
+ * If tvar == NULL, this just checks variable can be converted.
+ */
+static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
+                                     Dwarf_Op *fb_ops,
+                                     struct probe_trace_arg *tvar)
 {
         Dwarf_Attribute attr;
         Dwarf_Op *op;
@@ -384,20 +810,23 @@ static int convert_variable_location(Dwarf_Die *vr_die, struct probe_finder *pf)
         Dwarf_Word offs = 0;
         bool ref = false;
         const char *regs;
-        struct probe_trace_arg *tvar = pf->tvar;
         int ret;
 
+        if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
+                goto static_var;
+
         /* TODO: handle more than 1 exprs */
         if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL ||
-            dwarf_getlocation_addr(&attr, pf->addr, &op, &nops, 1) <= 0 ||
+            dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0 ||
             nops == 0) {
                 /* TODO: Support const_value */
-                pr_err("Failed to find the location of %s at this address.\n"
-                       " Perhaps, it has been optimized out.\n", pf->pvar->var);
                 return -ENOENT;
         }
 
         if (op->atom == DW_OP_addr) {
+static_var:
+                if (!tvar)
+                        return 0;
                 /* Static variables on memory (not stack), make @varname */
                 ret = strlen(dwarf_diename(vr_die));
                 tvar->value = zalloc(ret + 2);
@@ -412,14 +841,11 @@ static int convert_variable_location(Dwarf_Die *vr_die, struct probe_finder *pf)
 
         /* If this is based on frame buffer, set the offset */
         if (op->atom == DW_OP_fbreg) {
-                if (pf->fb_ops == NULL) {
-                        pr_warning("The attribute of frame base is not "
-                                   "supported.\n");
+                if (fb_ops == NULL)
                         return -ENOTSUP;
-                }
                 ref = true;
                 offs = op->number;
-                op = &pf->fb_ops[0];
+                op = &fb_ops[0];
         }
 
         if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
@@ -435,13 +861,18 @@ static int convert_variable_location(Dwarf_Die *vr_die, struct probe_finder *pf)
         } else if (op->atom == DW_OP_regx) {
                 regn = op->number;
         } else {
-                pr_warning("DW_OP %x is not supported.\n", op->atom);
+                pr_debug("DW_OP %x is not supported.\n", op->atom);
                 return -ENOTSUP;
         }
 
+        if (!tvar)
+                return 0;
+
         regs = get_arch_regstr(regn);
         if (!regs) {
-                pr_warning("Mapping for DWARF register number %u missing on this architecture.", regn);
+                /* This should be a bug in DWARF or this tool */
+                pr_warning("Mapping for the register number %u "
+                           "missing on this architecture.\n", regn);
                 return -ERANGE;
         }
 
@@ -457,6 +888,8 @@ static int convert_variable_location(Dwarf_Die *vr_die, struct probe_finder *pf)
         return 0;
 }
 
+#define BYTES_TO_BITS(nb)       ((nb) * BITS_PER_LONG / sizeof(long))
+
 static int convert_variable_type(Dwarf_Die *vr_die,
                                  struct probe_trace_arg *tvar,
                                  const char *cast)
@@ -473,6 +906,14 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                 return (tvar->type == NULL) ? -ENOMEM : 0;
         }
 
+        if (die_get_bit_size(vr_die) != 0) {
+                /* This is a bitfield */
+                ret = snprintf(buf, 16, "b%d@%d/%zd", die_get_bit_size(vr_die),
+                                die_get_bit_offset(vr_die),
+                                BYTES_TO_BITS(die_get_byte_size(vr_die)));
+                goto formatted;
+        }
+
         if (die_get_real_type(vr_die, &type) == NULL) {
                 pr_warning("Failed to get a type information of %s.\n",
                            dwarf_diename(vr_die));
@@ -487,13 +928,14 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                 if (ret != DW_TAG_pointer_type &&
                     ret != DW_TAG_array_type) {
                         pr_warning("Failed to cast into string: "
-                                   "%s(%s) is not a pointer nor array.",
+                                   "%s(%s) is not a pointer nor array.\n",
                                    dwarf_diename(vr_die), dwarf_diename(&type));
                         return -EINVAL;
                 }
                 if (ret == DW_TAG_pointer_type) {
                         if (die_get_real_type(&type, &type) == NULL) {
-                                pr_warning("Failed to get a type information.");
+                                pr_warning("Failed to get a type"
+                                           " information.\n");
                                 return -ENOENT;
                         }
                         while (*ref_ptr)
@@ -508,7 +950,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                 if (!die_compare_name(&type, "char") &&
                     !die_compare_name(&type, "unsigned char")) {
                         pr_warning("Failed to cast into string: "
-                                   "%s is not (unsigned) char *.",
+                                   "%s is not (unsigned) char *.\n",
                                    dwarf_diename(vr_die));
                         return -EINVAL;
                 }
@@ -516,29 +958,31 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                 return (tvar->type == NULL) ? -ENOMEM : 0;
         }
 
-        ret = die_get_byte_size(&type) * 8;
-        if (ret) {
-                /* Check the bitwidth */
-                if (ret > MAX_BASIC_TYPE_BITS) {
-                        pr_info("%s exceeds max-bitwidth."
-                                " Cut down to %d bits.\n",
-                                dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
-                        ret = MAX_BASIC_TYPE_BITS;
-                }
+        ret = BYTES_TO_BITS(die_get_byte_size(&type));
+        if (!ret)
+                /* No size ... try to use default type */
+                return 0;
 
-                ret = snprintf(buf, 16, "%c%d",
-                               die_is_signed_type(&type) ? 's' : 'u', ret);
-                if (ret < 0 || ret >= 16) {
-                        if (ret >= 16)
-                                ret = -E2BIG;
-                        pr_warning("Failed to convert variable type: %s\n",
-                                   strerror(-ret));
-                        return ret;
-                }
-                tvar->type = strdup(buf);
-                if (tvar->type == NULL)
-                        return -ENOMEM;
+        /* Check the bitwidth */
+        if (ret > MAX_BASIC_TYPE_BITS) {
+                pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n",
+                        dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
+                ret = MAX_BASIC_TYPE_BITS;
         }
+        ret = snprintf(buf, 16, "%c%d",
+                       die_is_signed_type(&type) ? 's' : 'u', ret);
+
+formatted:
+        if (ret < 0 || ret >= 16) {
+                if (ret >= 16)
+                        ret = -E2BIG;
+                pr_warning("Failed to convert variable type: %s\n",
+                           strerror(-ret));
+                return ret;
+        }
+        tvar->type = strdup(buf);
+        if (tvar->type == NULL)
+                return -ENOMEM;
         return 0;
 }
 
@@ -618,8 +1062,8 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
                         return -EINVAL;
                 }
                 if (field->name[0] == '[') {
-                        pr_err("Semantic error: %s is not a pointor nor array.",
-                               varname);
+                        pr_err("Semantic error: %s is not a pointor"
+                               " nor array.\n", varname);
                         return -EINVAL;
                 }
                 if (field->ref) {
@@ -666,8 +1110,14 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
         pr_debug("Converting variable %s into trace event.\n",
                  dwarf_diename(vr_die));
 
-        ret = convert_variable_location(vr_die, pf);
-        if (ret == 0 && pf->pvar->field) {
+        ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
+                                        pf->tvar);
+        if (ret == -ENOENT)
+                pr_err("Failed to find the location of %s at this address.\n"
+                       " Perhaps, it has been optimized out.\n", pf->pvar->var);
+        else if (ret == -ENOTSUP)
+                pr_err("Sorry, we don't support this variable location yet.\n");
+        else if (pf->pvar->field) {
                 ret = convert_variable_fields(vr_die, pf->pvar->var,
                                               pf->pvar->field, &pf->tvar->ref,
                                               &die_mem);
@@ -722,85 +1172,87 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
         pr_debug("Searching '%s' variable in context.\n",
                  pf->pvar->var);
         /* Search child die for local variables and parameters. */
-        if (die_find_variable(sp_die, pf->pvar->var, &vr_die))
+        if (die_find_variable_at(sp_die, pf->pvar->var, pf->addr, &vr_die))
                 ret = convert_variable(&vr_die, pf);
         else {
                 /* Search upper class */
                 nscopes = dwarf_getscopes_die(sp_die, &scopes);
-                if (nscopes > 0) {
-                        ret = dwarf_getscopevar(scopes, nscopes, pf->pvar->var,
-                                                0, NULL, 0, 0, &vr_die);
-                        if (ret >= 0)
+                while (nscopes-- > 1) {
+                        pr_debug("Searching variables in %s\n",
+                                 dwarf_diename(&scopes[nscopes]));
+                        /* We should check this scope, so give dummy address */
+                        if (die_find_variable_at(&scopes[nscopes],
+                                                 pf->pvar->var, 0,
+                                                 &vr_die)) {
                                 ret = convert_variable(&vr_die, pf);
-                        else
-                                ret = -ENOENT;
+                                goto found;
+                        }
+                }
+                if (scopes)
                         free(scopes);
-                } else
-                        ret = -ENOENT;
+                ret = -ENOENT;
         }
+found:
         if (ret < 0)
                 pr_warning("Failed to find '%s' in this function.\n",
                            pf->pvar->var);
         return ret;
 }
 
-/* Show a probe point to output buffer */
-static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
+/* Convert subprogram DIE to trace point */
+static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
+                                  bool retprobe, struct probe_trace_point *tp)
 {
-        struct probe_trace_event *tev;
         Dwarf_Addr eaddr;
-        Dwarf_Die die_mem;
         const char *name;
-        int ret, i;
-        Dwarf_Attribute fb_attr;
-        size_t nops;
-
-        if (pf->ntevs == pf->max_tevs) {
-                pr_warning("Too many( > %d) probe point found.\n",
-                           pf->max_tevs);
-                return -ERANGE;
-        }
-        tev = &pf->tevs[pf->ntevs++];
-
-        /* If no real subprogram, find a real one */
-        if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
-                sp_die = die_find_real_subprogram(&pf->cu_die,
-                                                 pf->addr, &die_mem);
-                if (!sp_die) {
-                        pr_warning("Failed to find probe point in any "
-                                   "functions.\n");
-                        return -ENOENT;
-                }
-        }
 
         /* Copy the name of probe point */
         name = dwarf_diename(sp_die);
         if (name) {
                 if (dwarf_entrypc(sp_die, &eaddr) != 0) {
-                        pr_warning("Failed to get entry pc of %s\n",
+                        pr_warning("Failed to get entry address of %s\n",
                                    dwarf_diename(sp_die));
                         return -ENOENT;
                 }
-                tev->point.symbol = strdup(name);
-                if (tev->point.symbol == NULL)
+                tp->symbol = strdup(name);
+                if (tp->symbol == NULL)
                         return -ENOMEM;
-                tev->point.offset = (unsigned long)(pf->addr - eaddr);
+                tp->offset = (unsigned long)(paddr - eaddr);
         } else
                 /* This function has no name. */
-                tev->point.offset = (unsigned long)pf->addr;
+                tp->offset = (unsigned long)paddr;
 
         /* Return probe must be on the head of a subprogram */
-        if (pf->pev->point.retprobe) {
-                if (tev->point.offset != 0) {
+        if (retprobe) {
+                if (eaddr != paddr) {
                         pr_warning("Return probe must be on the head of"
-                                   " a real function\n");
+                                   " a real function.\n");
                         return -EINVAL;
                 }
-                tev->point.retprobe = true;
+                tp->retprobe = true;
         }
 
-        pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
-                 tev->point.offset);
+        return 0;
+}
+
+/* Call probe_finder callback with real subprogram DIE */
+static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf)
+{
+        Dwarf_Die die_mem;
+        Dwarf_Attribute fb_attr;
+        size_t nops;
+        int ret;
+
+        /* If no real subprogram, find a real one */
+        if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
+                sp_die = die_find_real_subprogram(&pf->cu_die,
+                                                  pf->addr, &die_mem);
+                if (!sp_die) {
+                        pr_warning("Failed to find probe point in any "
+                                   "functions.\n");
+                        return -ENOENT;
+                }
+        }
 
         /* Get the frame base attribute/ops */
         dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
@@ -813,182 +1265,118 @@ static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
                 Dwarf_Frame *frame;
                 if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 ||
                     dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) {
-                        pr_warning("Failed to get CFA on 0x%jx\n",
+                        pr_warning("Failed to get call frame on 0x%jx\n",
                                    (uintmax_t)pf->addr);
                         return -ENOENT;
                 }
 #endif
         }
 
-        /* Find each argument */
-        tev->nargs = pf->pev->nargs;
-        tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
-        if (tev->args == NULL)
-                return -ENOMEM;
-        for (i = 0; i < pf->pev->nargs; i++) {
-                pf->pvar = &pf->pev->args[i];
-                pf->tvar = &tev->args[i];
-                ret = find_variable(sp_die, pf);
-                if (ret != 0)
-                        return ret;
-        }
+        /* Call finder's callback handler */
+        ret = pf->callback(sp_die, pf);
 
         /* *pf->fb_ops will be cached in libdw. Don't free it. */
         pf->fb_ops = NULL;
-        return 0;
+
+        return ret;
 }
 
-/* Find probe point from its line number */
-static int find_probe_point_by_line(struct probe_finder *pf)
+static int probe_point_line_walker(const char *fname, int lineno,
+                                   Dwarf_Addr addr, void *data)
 {
-        Dwarf_Lines *lines;
-        Dwarf_Line *line;
-        size_t nlines, i;
-        Dwarf_Addr addr;
-        int lineno;
-        int ret = 0;
-
-        if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-                pr_warning("No source lines found in this CU.\n");
-                return -ENOENT;
-        }
+        struct probe_finder *pf = data;
+        int ret;
 
-        for (i = 0; i < nlines && ret == 0; i++) {
-                line = dwarf_onesrcline(lines, i);
-                if (dwarf_lineno(line, &lineno) != 0 ||
-                    lineno != pf->lno)
-                        continue;
+        if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0)
+                return 0;
 
-                /* TODO: Get fileno from line, but how? */
-                if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
-                        continue;
+        pf->addr = addr;
+        ret = call_probe_finder(NULL, pf);
 
-                if (dwarf_lineaddr(line, &addr) != 0) {
-                        pr_warning("Failed to get the address of the line.\n");
-                        return -ENOENT;
-                }
-                pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
-                         (int)i, lineno, (uintmax_t)addr);
-                pf->addr = addr;
+        /* Continue if no error, because the line will be in inline function */
+        return ret < 0 ? ret : 0;
+}
 
-                ret = convert_probe_point(NULL, pf);
-                /* Continuing, because target line might be inlined. */
-        }
-        return ret;
+/* Find probe point from its line number */
+static int find_probe_point_by_line(struct probe_finder *pf)
+{
+        return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf);
 }
 
 /* Find lines which match lazy pattern */
 static int find_lazy_match_lines(struct list_head *head,
                                  const char *fname, const char *pat)
 {
-        char *fbuf, *p1, *p2;
-        int fd, line, nlines = -1;
-        struct stat st;
-
-        fd = open(fname, O_RDONLY);
-        if (fd < 0) {
-                pr_warning("Failed to open %s: %s\n", fname, strerror(-fd));
+        FILE *fp;
+        char *line = NULL;
+        size_t line_len;
+        ssize_t len;
+        int count = 0, linenum = 1;
+
+        fp = fopen(fname, "r");
+        if (!fp) {
+                pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
                 return -errno;
         }
 
-        if (fstat(fd, &st) < 0) {
-                pr_warning("Failed to get the size of %s: %s\n",
-                           fname, strerror(errno));
-                nlines = -errno;
-                goto out_close;
-        }
-
-        nlines = -ENOMEM;
-        fbuf = malloc(st.st_size + 2);
-        if (fbuf == NULL)
-                goto out_close;
-        if (read(fd, fbuf, st.st_size) < 0) {
-                pr_warning("Failed to read %s: %s\n", fname, strerror(errno));
-                nlines = -errno;
-                goto out_free_fbuf;
-        }
-        fbuf[st.st_size] = '\n';        /* Dummy line */
-        fbuf[st.st_size + 1] = '\0';
-        p1 = fbuf;
-        line = 1;
-        nlines = 0;
-        while ((p2 = strchr(p1, '\n')) != NULL) {
-                *p2 = '\0';
-                if (strlazymatch(p1, pat)) {
-                        line_list__add_line(head, line);
-                        nlines++;
+        while ((len = getline(&line, &line_len, fp)) > 0) {
+
+                if (line[len - 1] == '\n')
+                        line[len - 1] = '\0';
+
+                if (strlazymatch(line, pat)) {
+                        line_list__add_line(head, linenum);
+                        count++;
                 }
-                line++;
-                p1 = p2 + 1;
+                linenum++;
         }
-out_free_fbuf:
-        free(fbuf);
-out_close:
-        close(fd);
-        return nlines;
+
+        if (ferror(fp))
+                count = -errno;
+        free(line);
+        fclose(fp);
+
+        if (count == 0)
+                pr_debug("No matched lines found in %s.\n", fname);
+        return count;
+}
+
+static int probe_point_lazy_walker(const char *fname, int lineno,
+                                   Dwarf_Addr addr, void *data)
+{
+        struct probe_finder *pf = data;
+        int ret;
+
+        if (!line_list__has_line(&pf->lcache, lineno) ||
+            strtailcmp(fname, pf->fname) != 0)
+                return 0;
+
+        pr_debug("Probe line found: line:%d addr:0x%llx\n",
+                 lineno, (unsigned long long)addr);
+        pf->addr = addr;
+        ret = call_probe_finder(NULL, pf);
+
+        /*
+         * Continue if no error, because the lazy pattern will match
+         * to other lines
+         */
+        return ret < 0 ? ret : 0;
 }
 
 /* Find probe points from lazy pattern  */
 static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-        Dwarf_Lines *lines;
-        Dwarf_Line *line;
-        size_t nlines, i;
-        Dwarf_Addr addr;
-        Dwarf_Die die_mem;
-        int lineno;
         int ret = 0;
 
         if (list_empty(&pf->lcache)) {
                 /* Matching lazy line pattern */
                 ret = find_lazy_match_lines(&pf->lcache, pf->fname,
                                             pf->pev->point.lazy_line);
-                if (ret == 0) {
-                        pr_debug("No matched lines found in %s.\n", pf->fname);
-                        return 0;
-                } else if (ret < 0)
+                if (ret <= 0)
                         return ret;
         }
 
-        if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-                pr_warning("No source lines found in this CU.\n");
-                return -ENOENT;
-        }
-
-        for (i = 0; i < nlines && ret >= 0; i++) {
-                line = dwarf_onesrcline(lines, i);
-
-                if (dwarf_lineno(line, &lineno) != 0 ||
-                    !line_list__has_line(&pf->lcache, lineno))
-                        continue;
-
-                /* TODO: Get fileno from line, but how? */
-                if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
-                        continue;
-
-                if (dwarf_lineaddr(line, &addr) != 0) {
-                        pr_debug("Failed to get the address of line %d.\n",
-                                 lineno);
-                        continue;
-                }
-                if (sp_die) {
-                        /* Address filtering 1: does sp_die include addr? */
-                        if (!dwarf_haspc(sp_die, addr))
-                                continue;
-                        /* Address filtering 2: No child include addr? */
-                        if (die_find_inlinefunc(sp_die, addr, &die_mem))
-                                continue;
-                }
-
-                pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",
-                         (int)i, lineno, (unsigned long long)addr);
-                pf->addr = addr;
-
-                ret = convert_probe_point(sp_die, pf);
-                /* Continuing, because target line might be inlined. */
-        }
-        /* TODO: deallocate lines, but how? */
-        return ret;
+        return die_walk_lines(sp_die, probe_point_lazy_walker, pf);
 }
 
 /* Callback parameter with return value */
@@ -1009,7 +1397,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
         else {
                 /* Get probe address */
                 if (dwarf_entrypc(in_die, &addr) != 0) {
-                        pr_warning("Failed to get entry pc of %s.\n",
+                        pr_warning("Failed to get entry address of %s.\n",
                                    dwarf_diename(in_die));
                         param->retval = -ENOENT;
                         return DWARF_CB_ABORT;
@@ -1019,7 +1407,7 @@ static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
                 pr_debug("found inline addr: 0x%jx\n",
                          (uintmax_t)pf->addr);
 
-                param->retval = convert_probe_point(in_die, pf);
+                param->retval = call_probe_finder(in_die, pf);
                 if (param->retval < 0)
                         return DWARF_CB_ABORT;
         }
@@ -1039,6 +1427,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
             !die_compare_name(sp_die, pp->function))
                 return DWARF_CB_OK;
 
+        /* Check declared file */
+        if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
+                return DWARF_CB_OK;
+
         pf->fname = dwarf_decl_file(sp_die);
         if (pp->line) { /* Function relative line */
                 dwarf_decl_line(sp_die, &pf->lno);
@@ -1050,14 +1442,14 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
                         param->retval = find_probe_point_lazy(sp_die, pf);
                 else {
                         if (dwarf_entrypc(sp_die, &pf->addr) != 0) {
-                                pr_warning("Failed to get entry pc of %s.\n",
-                                           dwarf_diename(sp_die));
+                                pr_warning("Failed to get entry address of "
+                                           "%s.\n", dwarf_diename(sp_die));
                                 param->retval = -ENOENT;
                                 return DWARF_CB_ABORT;
                         }
                         pf->addr += pp->offset;
                         /* TODO: Check the address in this function */
-                        param->retval = convert_probe_point(sp_die, pf);
+                        param->retval = call_probe_finder(sp_die, pf);
                 }
         } else {
                 struct dwarf_callback_param _param = {.data = (void *)pf,
@@ -1079,155 +1471,410 @@ static int find_probe_point_by_func(struct probe_finder *pf)
         return _param.retval;
 }
 
-/* Find probe_trace_events specified by perf_probe_event from debuginfo */
-int find_probe_trace_events(int fd, struct perf_probe_event *pev,
-                             struct probe_trace_event **tevs, int max_tevs)
+struct pubname_callback_param {
+        char *function;
+        char *file;
+        Dwarf_Die *cu_die;
+        Dwarf_Die *sp_die;
+        int found;
+};
+
+static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
+{
+        struct pubname_callback_param *param = data;
+
+        if (dwarf_offdie(dbg, gl->die_offset, param->sp_die)) {
+                if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
+                        return DWARF_CB_OK;
+
+                if (die_compare_name(param->sp_die, param->function)) {
+                        if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
+                                return DWARF_CB_OK;
+
+                        if (param->file &&
+                            strtailcmp(param->file, dwarf_decl_file(param->sp_die)))
+                                return DWARF_CB_OK;
+
+                        param->found = 1;
+                        return DWARF_CB_ABORT;
+                }
+        }
+
+        return DWARF_CB_OK;
+}
+
+/* Find probe points from debuginfo */
+static int find_probes(int fd, struct probe_finder *pf)
 {
-        struct probe_finder pf = {.pev = pev, .max_tevs = max_tevs};
-        struct perf_probe_point *pp = &pev->point;
+        struct perf_probe_point *pp = &pf->pev->point;
         Dwarf_Off off, noff;
         size_t cuhl;
         Dwarf_Die *diep;
-        Dwarf *dbg;
+        Dwarf *dbg = NULL;
+        Dwfl *dwfl;
+        Dwarf_Addr bias;        /* Currently ignored */
         int ret = 0;
 
-        pf.tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
-        if (pf.tevs == NULL)
-                return -ENOMEM;
-        *tevs = pf.tevs;
-        pf.ntevs = 0;
-
-        dbg = dwarf_begin(fd, DWARF_C_READ);
+        dbg = dwfl_init_offline_dwarf(fd, &dwfl, &bias);
         if (!dbg) {
-                pr_warning("No dwarf info found in the vmlinux - "
+                pr_warning("No debug information found in the vmlinux - "
                         "please rebuild with CONFIG_DEBUG_INFO=y.\n");
-                free(pf.tevs);
-                *tevs = NULL;
+                close(fd);      /* Without dwfl_end(), fd isn't closed. */
                 return -EBADF;
         }
 
 #if _ELFUTILS_PREREQ(0, 142)
         /* Get the call frame information from this dwarf */
-        pf.cfi = dwarf_getcfi(dbg);
+        pf->cfi = dwarf_getcfi(dbg);
 #endif
 
         off = 0;
-        line_list__init(&pf.lcache);
+        line_list__init(&pf->lcache);
+
+        /* Fastpath: lookup by function name from .debug_pubnames section */
+        if (pp->function) {
+                struct pubname_callback_param pubname_param = {
+                        .function = pp->function,
+                        .file     = pp->file,
+                        .cu_die   = &pf->cu_die,
+                        .sp_die   = &pf->sp_die,
+                        .found    = 0,
+                };
+                struct dwarf_callback_param probe_param = {
+                        .data = pf,
+                };
+
+                dwarf_getpubnames(dbg, pubname_search_cb, &pubname_param, 0);
+                if (pubname_param.found) {
+                        ret = probe_point_search_cb(&pf->sp_die, &probe_param);
+                        if (ret)
+                                goto found;
+                }
+        }
+
         /* Loop on CUs (Compilation Unit) */
-        while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) &&
-               ret >= 0) {
+        while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
                 /* Get the DIE(Debugging Information Entry) of this CU */
-                diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die);
+                diep = dwarf_offdie(dbg, off + cuhl, &pf->cu_die);
                 if (!diep)
                         continue;
 
                 /* Check if target file is included. */
                 if (pp->file)
-                        pf.fname = cu_find_realpath(&pf.cu_die, pp->file);
+                        pf->fname = cu_find_realpath(&pf->cu_die, pp->file);
                 else
-                        pf.fname = NULL;
+                        pf->fname = NULL;
 
-                if (!pp->file || pf.fname) {
+                if (!pp->file || pf->fname) {
                         if (pp->function)
-                                ret = find_probe_point_by_func(&pf);
+                                ret = find_probe_point_by_func(pf);
                         else if (pp->lazy_line)
-                                ret = find_probe_point_lazy(NULL, &pf);
+                                ret = find_probe_point_lazy(NULL, pf);
                         else {
-                                pf.lno = pp->line;
-                                ret = find_probe_point_by_line(&pf);
+                                pf->lno = pp->line;
+                                ret = find_probe_point_by_line(pf);
                         }
+                        if (ret < 0)
+                                break;
                 }
                 off = noff;
         }
-        line_list__free(&pf.lcache);
-        dwarf_end(dbg);
 
-        return (ret < 0) ? ret : pf.ntevs;
+found:
+        line_list__free(&pf->lcache);
+        if (dwfl)
+                dwfl_end(dwfl);
+
+        return ret;
+}
+
+/* Add a found probe point into trace event list */
+static int add_probe_trace_event(Dwarf_Die *sp_die, struct probe_finder *pf)
+{
+        struct trace_event_finder *tf =
+                        container_of(pf, struct trace_event_finder, pf);
+        struct probe_trace_event *tev;
+        int ret, i;
+
+        /* Check number of tevs */
+        if (tf->ntevs == tf->max_tevs) {
+                pr_warning("Too many( > %d) probe point found.\n",
+                           tf->max_tevs);
+                return -ERANGE;
+        }
+        tev = &tf->tevs[tf->ntevs++];
+
+        ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe,
+                                     &tev->point);
+        if (ret < 0)
+                return ret;
+
+        pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
+                 tev->point.offset);
+
+        /* Find each argument */
+        tev->nargs = pf->pev->nargs;
+        tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
+        if (tev->args == NULL)
+                return -ENOMEM;
+        for (i = 0; i < pf->pev->nargs; i++) {
+                pf->pvar = &pf->pev->args[i];
+                pf->tvar = &tev->args[i];
+                ret = find_variable(sp_die, pf);
+                if (ret != 0)
+                        return ret;
+        }
+
+        return 0;
+}
+
+/* Find probe_trace_events specified by perf_probe_event from debuginfo */
+int find_probe_trace_events(int fd, struct perf_probe_event *pev,
+                            struct probe_trace_event **tevs, int max_tevs)
+{
+        struct trace_event_finder tf = {
+                        .pf = {.pev = pev, .callback = add_probe_trace_event},
+                        .max_tevs = max_tevs};
+        int ret;
+
+        /* Allocate result tevs array */
+        *tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+        if (*tevs == NULL)
+                return -ENOMEM;
+
+        tf.tevs = *tevs;
+        tf.ntevs = 0;
+
+        ret = find_probes(fd, &tf.pf);
+        if (ret < 0) {
+                free(*tevs);
+                *tevs = NULL;
+                return ret;
+        }
+
+        return (ret < 0) ? ret : tf.ntevs;
+}
+
+#define MAX_VAR_LEN 64
+
+/* Collect available variables in this scope */
+static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
+{
+        struct available_var_finder *af = data;
+        struct variable_list *vl;
+        char buf[MAX_VAR_LEN];
+        int tag, ret;
+
+        vl = &af->vls[af->nvls - 1];
+
+        tag = dwarf_tag(die_mem);
+        if (tag == DW_TAG_formal_parameter ||
+            tag == DW_TAG_variable) {
+                ret = convert_variable_location(die_mem, af->pf.addr,
+                                                af->pf.fb_ops, NULL);
+                if (ret == 0) {
+                        ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
+                        pr_debug2("Add new var: %s\n", buf);
+                        if (ret > 0)
+                                strlist__add(vl->vars, buf);
+                }
+        }
+
+        if (af->child && dwarf_haspc(die_mem, af->pf.addr))
+                return DIE_FIND_CB_CONTINUE;
+        else
+                return DIE_FIND_CB_SIBLING;
+}
+
+/* Add a found vars into available variables list */
+static int add_available_vars(Dwarf_Die *sp_die, struct probe_finder *pf)
+{
+        struct available_var_finder *af =
+                        container_of(pf, struct available_var_finder, pf);
+        struct variable_list *vl;
+        Dwarf_Die die_mem, *scopes = NULL;
+        int ret, nscopes;
+
+        /* Check number of tevs */
+        if (af->nvls == af->max_vls) {
+                pr_warning("Too many( > %d) probe point found.\n", af->max_vls);
+                return -ERANGE;
+        }
+        vl = &af->vls[af->nvls++];
+
+        ret = convert_to_trace_point(sp_die, pf->addr, pf->pev->point.retprobe,
+                                     &vl->point);
+        if (ret < 0)
+                return ret;
+
+        pr_debug("Probe point found: %s+%lu\n", vl->point.symbol,
+                 vl->point.offset);
+
+        /* Find local variables */
+        vl->vars = strlist__new(true, NULL);
+        if (vl->vars == NULL)
+                return -ENOMEM;
+        af->child = true;
+        die_find_child(sp_die, collect_variables_cb, (void *)af, &die_mem);
+
+        /* Find external variables */
+        if (!af->externs)
+                goto out;
+        /* Don't need to search child DIE for externs. */
+        af->child = false;
+        nscopes = dwarf_getscopes_die(sp_die, &scopes);
+        while (nscopes-- > 1)
+                die_find_child(&scopes[nscopes], collect_variables_cb,
+                               (void *)af, &die_mem);
+        if (scopes)
+                free(scopes);
+
+out:
+        if (strlist__empty(vl->vars)) {
+                strlist__delete(vl->vars);
+                vl->vars = NULL;
+        }
+
+        return ret;
+}
+
+/* Find available variables at given probe point */
+int find_available_vars_at(int fd, struct perf_probe_event *pev,
+                           struct variable_list **vls, int max_vls,
+                           bool externs)
+{
+        struct available_var_finder af = {
+                        .pf = {.pev = pev, .callback = add_available_vars},
+                        .max_vls = max_vls, .externs = externs};
+        int ret;
+
+        /* Allocate result vls array */
+        *vls = zalloc(sizeof(struct variable_list) * max_vls);
+        if (*vls == NULL)
+                return -ENOMEM;
+
+        af.vls = *vls;
+        af.nvls = 0;
+
+        ret = find_probes(fd, &af.pf);
+        if (ret < 0) {
+                /* Free vlist for error */
+                while (af.nvls--) {
+                        if (af.vls[af.nvls].point.symbol)
+                                free(af.vls[af.nvls].point.symbol);
+                        if (af.vls[af.nvls].vars)
+                                strlist__delete(af.vls[af.nvls].vars);
+                }
+                free(af.vls);
+                *vls = NULL;
+                return ret;
+        }
+
+        return (ret < 0) ? ret : af.nvls;
 }
 
 /* Reverse search */
-int find_perf_probe_point(int fd, unsigned long addr,
-                          struct perf_probe_point *ppt)
+int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
 {
         Dwarf_Die cudie, spdie, indie;
-        Dwarf *dbg;
-        Dwarf_Line *line;
-        Dwarf_Addr laddr, eaddr;
-        const char *tmp;
-        int lineno, ret = 0;
-        bool found = false;
-
-        dbg = dwarf_begin(fd, DWARF_C_READ);
-        if (!dbg)
-                return -EBADF;
+        Dwarf *dbg = NULL;
+        Dwfl *dwfl = NULL;
+        Dwarf_Addr _addr, baseaddr, bias = 0;
+        const char *fname = NULL, *func = NULL, *tmp;
+        int baseline = 0, lineno = 0, ret = 0;
+
+        /* Open the live linux kernel */
+        dbg = dwfl_init_live_kernel_dwarf(addr, &dwfl, &bias);
+        if (!dbg) {
+                pr_warning("No debug information found in the vmlinux - "
+                        "please rebuild with CONFIG_DEBUG_INFO=y.\n");
+                ret = -EINVAL;
+                goto end;
+        }
 
+        /* Adjust address with bias */
+        addr += bias;
         /* Find cu die */
-        if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr, &cudie)) {
+        if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr - bias, &cudie)) {
+                pr_warning("Failed to find debug information for address %lx\n",
+                           addr);
                 ret = -EINVAL;
                 goto end;
         }
 
-        /* Find a corresponding line */
-        line = dwarf_getsrc_die(&cudie, (Dwarf_Addr)addr);
-        if (line) {
-                if (dwarf_lineaddr(line, &laddr) == 0 &&
-                    (Dwarf_Addr)addr == laddr &&
-                    dwarf_lineno(line, &lineno) == 0) {
-                        tmp = dwarf_linesrc(line, NULL, NULL);
-                        if (tmp) {
-                                ppt->line = lineno;
-                                ppt->file = strdup(tmp);
-                                if (ppt->file == NULL) {
-                                        ret = -ENOMEM;
-                                        goto end;
-                                }
-                                found = true;
-                        }
-                }
-        }
+        /* Find a corresponding line (filename and lineno) */
+        cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+        /* Don't care whether it failed or not */
 
-        /* Find a corresponding function */
+        /* Find a corresponding function (name, baseline and baseaddr) */
         if (die_find_real_subprogram(&cudie, (Dwarf_Addr)addr, &spdie)) {
+                /* Get function entry information */
                 tmp = dwarf_diename(&spdie);
-                if (!tmp || dwarf_entrypc(&spdie, &eaddr) != 0)
-                        goto end;
-
-                if (ppt->line) {
-                        if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-                                                &indie)) {
-                                /* addr in an inline function */
+                if (!tmp ||
+                    dwarf_entrypc(&spdie, &baseaddr) != 0 ||
+                    dwarf_decl_line(&spdie, &baseline) != 0)
+                        goto post;
+                func = tmp;
+
+                if (addr == (unsigned long)baseaddr)
+                        /* Function entry - Relative line number is 0 */
+                        lineno = baseline;
+                else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
+                                             &indie)) {
+                        if (dwarf_entrypc(&indie, &_addr) == 0 &&
+                            _addr == addr)
+                                /*
+                                 * addr is at an inline function entry.
+                                 * In this case, lineno should be the call-site
+                                 * line number.
+                                 */
+                                lineno = die_get_call_lineno(&indie);
+                        else {
+                                /*
+                                 * addr is in an inline function body.
+                                 * Since lineno points one of the lines
+                                 * of the inline function, baseline should
+                                 * be the entry line of the inline function.
+                                 */
                                 tmp = dwarf_diename(&indie);
-                                if (!tmp)
-                                        goto end;
-                                ret = dwarf_decl_line(&indie, &lineno);
-                        } else {
-                                if (eaddr == addr) {    /* Function entry */
-                                        lineno = ppt->line;
-                                        ret = 0;
-                                } else
-                                        ret = dwarf_decl_line(&spdie, &lineno);
-                        }
-                        if (ret == 0) {
-                                /* Make a relative line number */
-                                ppt->line -= lineno;
-                                goto found;
+                                if (tmp &&
+                                    dwarf_decl_line(&spdie, &baseline) == 0)
+                                        func = tmp;
                         }
                 }
-                /* We don't have a line number, let's use offset */
-                ppt->offset = addr - (unsigned long)eaddr;
-found:
-                ppt->function = strdup(tmp);
+        }
+
+post:
+        /* Make a relative line number or an offset */
+        if (lineno)
+                ppt->line = lineno - baseline;
+        else if (func)
+                ppt->offset = addr - (unsigned long)baseaddr;
+
+        /* Duplicate strings */
+        if (func) {
+                ppt->function = strdup(func);
                 if (ppt->function == NULL) {
                         ret = -ENOMEM;
                         goto end;
                 }
-                found = true;
         }
-
+        if (fname) {
+                ppt->file = strdup(fname);
+                if (ppt->file == NULL) {
+                        if (ppt->function) {
+                                free(ppt->function);
+                                ppt->function = NULL;
+                        }
+                        ret = -ENOMEM;
+                        goto end;
+                }
+        }
 end:
-        dwarf_end(dbg);
-        if (ret >= 0)
-                ret = found ? 1 : 0;
+        if (dwfl)
+                dwfl_end(dwfl);
+        if (ret == 0 && (fname || func))
+                ret = 1;        /* Found a point */
         return ret;
 }
 
@@ -1244,91 +1891,28 @@ static int line_range_add_line(const char *src, unsigned int lineno,
         return line_list__add_line(&lr->line_list, lineno);
 }
 
-/* Search function declaration lines */
-static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data)
+static int line_range_walk_cb(const char *fname, int lineno,
+                              Dwarf_Addr addr __used,
+                              void *data)
 {
-        struct dwarf_callback_param *param = data;
-        struct line_finder *lf = param->data;
-        const char *src;
-        int lineno;
+        struct line_finder *lf = data;
 
-        src = dwarf_decl_file(sp_die);
-        if (src && strtailcmp(src, lf->fname) != 0)
-                return DWARF_CB_OK;
-
-        if (dwarf_decl_line(sp_die, &lineno) != 0 ||
+        if ((strtailcmp(fname, lf->fname) != 0) ||
             (lf->lno_s > lineno || lf->lno_e < lineno))
-                return DWARF_CB_OK;
+                return 0;
 
-        param->retval = line_range_add_line(src, lineno, lf->lr);
-        if (param->retval < 0)
-                return DWARF_CB_ABORT;
-        return DWARF_CB_OK;
-}
+        if (line_range_add_line(fname, lineno, lf->lr) < 0)
+                return -EINVAL;
 
-static int find_line_range_func_decl_lines(struct line_finder *lf)
-{
-        struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0};
-        dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, &param, 0);
-        return param.retval;
+        return 0;
 }
 
 /* Find line range from its line number */
 static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 {
-        Dwarf_Lines *lines;
-        Dwarf_Line *line;
-        size_t nlines, i;
-        Dwarf_Addr addr;
-        int lineno, ret = 0;
-        const char *src;
-        Dwarf_Die die_mem;
-
-        line_list__init(&lf->lr->line_list);
-        if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) {
-                pr_warning("No source lines found in this CU.\n");
-                return -ENOENT;
-        }
-
-        /* Search probable lines on lines list */
-        for (i = 0; i < nlines; i++) {
-                line = dwarf_onesrcline(lines, i);
-                if (dwarf_lineno(line, &lineno) != 0 ||
-                    (lf->lno_s > lineno || lf->lno_e < lineno))
-                        continue;
-
-                if (sp_die) {
-                        /* Address filtering 1: does sp_die include addr? */
-                        if (dwarf_lineaddr(line, &addr) != 0 ||
-                            !dwarf_haspc(sp_die, addr))
-                                continue;
-
-                        /* Address filtering 2: No child include addr? */
-                        if (die_find_inlinefunc(sp_die, addr, &die_mem))
-                                continue;
-                }
-
-                /* TODO: Get fileno from line, but how? */
-                src = dwarf_linesrc(line, NULL, NULL);
-                if (strtailcmp(src, lf->fname) != 0)
-                        continue;
+        int ret;
 
-                ret = line_range_add_line(src, lineno, lf->lr);
-                if (ret < 0)
-                        return ret;
-        }
-
-        /*
-         * Dwarf lines doesn't include function declarations. We have to
-         * check functions list or given function.
-         */
-        if (sp_die) {
-                src = dwarf_decl_file(sp_die);
-                if (src && dwarf_decl_line(sp_die, &lineno) == 0 &&
-                    (lf->lno_s <= lineno && lf->lno_e >= lineno))
-                        ret = line_range_add_line(src, lineno, lf->lr);
-        } else
-                ret = find_line_range_func_decl_lines(lf);
+        ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf);
 
         /* Update status */
         if (ret >= 0)
@@ -1358,6 +1942,10 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
         struct line_finder *lf = param->data;
         struct line_range *lr = lf->lr;
 
+        /* Check declared file */
+        if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
+                return DWARF_CB_OK;
+
         if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
             die_compare_name(sp_die, lr->function)) {
                 lf->fname = dwarf_decl_file(sp_die);
@@ -1401,16 +1989,35 @@ int find_line_range(int fd, struct line_range *lr)
         Dwarf_Off off = 0, noff;
         size_t cuhl;
         Dwarf_Die *diep;
-        Dwarf *dbg;
+        Dwarf *dbg = NULL;
+        Dwfl *dwfl;
+        Dwarf_Addr bias;        /* Currently ignored */
         const char *comp_dir;
 
-        dbg = dwarf_begin(fd, DWARF_C_READ);
+        dbg = dwfl_init_offline_dwarf(fd, &dwfl, &bias);
         if (!dbg) {
-                pr_warning("No dwarf info found in the vmlinux - "
+                pr_warning("No debug information found in the vmlinux - "
                         "please rebuild with CONFIG_DEBUG_INFO=y.\n");
+                close(fd);      /* Without dwfl_end(), fd isn't closed. */
                 return -EBADF;
         }
 
+        /* Fastpath: lookup by function name from .debug_pubnames section */
+        if (lr->function) {
+                struct pubname_callback_param pubname_param = {
+                        .function = lr->function, .file = lr->file,
+                        .cu_die = &lf.cu_die, .sp_die = &lf.sp_die, .found = 0};
+                struct dwarf_callback_param line_range_param = {
+                        .data = (void *)&lf, .retval = 0};
+
+                dwarf_getpubnames(dbg, pubname_search_cb, &pubname_param, 0);
+                if (pubname_param.found) {
+                        line_range_search_cb(&lf.sp_die, &line_range_param);
+                        if (lf.found)
+                                goto found;
+                }
+        }
+
         /* Loop on CUs (Compilation Unit) */
         while (!lf.found && ret >= 0) {
                 if (dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) != 0)
@@ -1439,6 +2046,7 @@ int find_line_range(int fd, struct line_range *lr)
                 off = noff;
         }
 
+found:
         /* Store comp_dir */
         if (lf.found) {
                 comp_dir = cu_get_comp_dir(&lf.cu_die);
@@ -1450,8 +2058,7 @@ int find_line_range(int fd, struct line_range *lr)
         }
 
         pr_debug("path: %s\n", lr->path);
-        dwarf_end(dbg);
-
+        dwfl_end(dwfl);
         return (ret < 0) ? ret : lf.found;
 }
 
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 4507d519f183..605730a366db 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -22,26 +22,34 @@ extern int find_probe_trace_events(int fd, struct perf_probe_event *pev,
                                     int max_tevs);
 
 /* Find a perf_probe_point from debuginfo */
-extern int find_perf_probe_point(int fd, unsigned long addr,
+extern int find_perf_probe_point(unsigned long addr,
                                  struct perf_probe_point *ppt);
 
+/* Find a line range */
 extern int find_line_range(int fd, struct line_range *lr);
 
+/* Find available variables */
+extern int find_available_vars_at(int fd, struct perf_probe_event *pev,
+                                  struct variable_list **vls, int max_points,
+                                  bool externs);
+
 #include <dwarf.h>
-#include <libdw.h>
-#include <version.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <elfutils/version.h>
 
 struct probe_finder {
         struct perf_probe_event *pev;           /* Target probe event */
-        struct probe_trace_event *tevs;         /* Result trace events */
-        int                     ntevs;          /* Number of trace events */
-        int                     max_tevs;       /* Max number of trace events */
+
+        /* Callback when a probe point is found */
+        int (*callback)(Dwarf_Die *sp_die, struct probe_finder *pf);
 
         /* For function searching */
         int                     lno;            /* Line number */
         Dwarf_Addr              addr;           /* Address */
         const char              *fname;         /* Real file name */
         Dwarf_Die               cu_die;         /* Current CU */
+        Dwarf_Die               sp_die;
         struct list_head        lcache;         /* Line cache for lazy match */
 
         /* For variable searching */
@@ -53,6 +61,22 @@ struct probe_finder {
         struct probe_trace_arg  *tvar;          /* Current result variable */
 };
 
+struct trace_event_finder {
+        struct probe_finder     pf;
+        struct probe_trace_event *tevs;         /* Found trace events */
+        int                     ntevs;          /* Number of trace events */
+        int                     max_tevs;       /* Max number of trace events */
+};
+
+struct available_var_finder {
+        struct probe_finder     pf;
+        struct variable_list    *vls;           /* Found variable lists */
+        int                     nvls;           /* Number of variable lists */
+        int                     max_vls;        /* Max no. of variable lists */
+        bool                    externs;        /* Find external vars too */
+        bool                    child;          /* Search child scopes */
+};
+
 struct line_finder {
         struct line_range       *lr;            /* Target line range */
 
@@ -60,6 +84,7 @@ struct line_finder {
         int                     lno_s;          /* Start line number */
         int                     lno_e;          /* End line number */
         Dwarf_Die               cu_die;         /* Current CU */
+        Dwarf_Die               sp_die;
         int                     found;
 };
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
new file mode 100644
index 000000000000..a9ac0504aabd
--- /dev/null
+++ b/tools/perf/util/python.c
@@ -0,0 +1,905 @@
+#include <Python.h>
+#include <structmember.h>
+#include <inttypes.h>
+#include <poll.h>
+#include "evlist.h"
+#include "evsel.h"
+#include "event.h"
+#include "cpumap.h"
+#include "thread_map.h"
+
+/* Define PyVarObject_HEAD_INIT for python 2.5 */
+#ifndef PyVarObject_HEAD_INIT
+# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
+#endif
+
+struct throttle_event {
+        struct perf_event_header header;
+        u64                      time;
+        u64                      id;
+        u64                      stream_id;
+};
+
+PyMODINIT_FUNC initperf(void);
+
+#define member_def(type, member, ptype, help) \
+        { #member, ptype, \
+          offsetof(struct pyrf_event, event) + offsetof(struct type, member), \
+          0, help }
+
+#define sample_member_def(name, member, ptype, help) \
+        { #name, ptype, \
+          offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \
+          0, help }
+
+struct pyrf_event {
+        PyObject_HEAD
+        struct perf_sample sample;
+        union perf_event   event;
+};
+
+#define sample_members \
+        sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"),                     \
+        sample_member_def(sample_pid, pid, T_INT, "event pid"),                  \
+        sample_member_def(sample_tid, tid, T_INT, "event tid"),                  \
+        sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"),            \
+        sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"),                 \
+        sample_member_def(sample_id, id, T_ULONGLONG, "event id"),                       \
+        sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \
+        sample_member_def(sample_period, period, T_ULONGLONG, "event period"),           \
+        sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"),
+
+static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object.");
+
+static PyMemberDef pyrf_mmap_event__members[] = {
+        sample_members
+        member_def(perf_event_header, type, T_UINT, "event type"),
+        member_def(mmap_event, pid, T_UINT, "event pid"),
+        member_def(mmap_event, tid, T_UINT, "event tid"),
+        member_def(mmap_event, start, T_ULONGLONG, "start of the map"),
+        member_def(mmap_event, len, T_ULONGLONG, "map length"),
+        member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"),
+        member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"),
+        { .name = NULL, },
+};
+
+static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
+{
+        PyObject *ret;
+        char *s;
+
+        if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", "
+                         "length: %#" PRIx64 ", offset: %#" PRIx64 ", "
+                         "filename: %s }",
+                     pevent->event.mmap.pid, pevent->event.mmap.tid,
+                     pevent->event.mmap.start, pevent->event.mmap.len,
+                     pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
+                ret = PyErr_NoMemory();
+        } else {
+                ret = PyString_FromString(s);
+                free(s);
+        }
+        return ret;
+}
+
+static PyTypeObject pyrf_mmap_event__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.mmap_event",
+        .tp_basicsize   = sizeof(struct pyrf_event),
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_mmap_event__doc,
+        .tp_members     = pyrf_mmap_event__members,
+        .tp_repr        = (reprfunc)pyrf_mmap_event__repr,
+};
+
+static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object.");
+
+static PyMemberDef pyrf_task_event__members[] = {
+        sample_members
+        member_def(perf_event_header, type, T_UINT, "event type"),
+        member_def(fork_event, pid, T_UINT, "event pid"),
+        member_def(fork_event, ppid, T_UINT, "event ppid"),
+        member_def(fork_event, tid, T_UINT, "event tid"),
+        member_def(fork_event, ptid, T_UINT, "event ptid"),
+        member_def(fork_event, time, T_ULONGLONG, "timestamp"),
+        { .name = NULL, },
+};
+
+static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
+{
+        return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
+                                   "ptid: %u, time: %" PRIu64 "}",
+                                   pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
+                                   pevent->event.fork.pid,
+                                   pevent->event.fork.ppid,
+                                   pevent->event.fork.tid,
+                                   pevent->event.fork.ptid,
+                                   pevent->event.fork.time);
+}
+
+static PyTypeObject pyrf_task_event__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.task_event",
+        .tp_basicsize   = sizeof(struct pyrf_event),
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_task_event__doc,
+        .tp_members     = pyrf_task_event__members,
+        .tp_repr        = (reprfunc)pyrf_task_event__repr,
+};
+
+static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object.");
+
+static PyMemberDef pyrf_comm_event__members[] = {
+        sample_members
+        member_def(perf_event_header, type, T_UINT, "event type"),
+        member_def(comm_event, pid, T_UINT, "event pid"),
+        member_def(comm_event, tid, T_UINT, "event tid"),
+        member_def(comm_event, comm, T_STRING_INPLACE, "process name"),
+        { .name = NULL, },
+};
+
+static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
+{
+        return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
+                                   pevent->event.comm.pid,
+                                   pevent->event.comm.tid,
+                                   pevent->event.comm.comm);
+}
+
+static PyTypeObject pyrf_comm_event__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.comm_event",
+        .tp_basicsize   = sizeof(struct pyrf_event),
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_comm_event__doc,
+        .tp_members     = pyrf_comm_event__members,
+        .tp_repr        = (reprfunc)pyrf_comm_event__repr,
+};
+
+static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object.");
+
+static PyMemberDef pyrf_throttle_event__members[] = {
+        sample_members
+        member_def(perf_event_header, type, T_UINT, "event type"),
+        member_def(throttle_event, time, T_ULONGLONG, "timestamp"),
+        member_def(throttle_event, id, T_ULONGLONG, "event id"),
+        member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"),
+        { .name = NULL, },
+};
+
+static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
+{
+        struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
+
+        return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
+                                   ", stream_id: %" PRIu64 " }",
+                                   pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
+                                   te->time, te->id, te->stream_id);
+}
+
+static PyTypeObject pyrf_throttle_event__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.throttle_event",
+        .tp_basicsize   = sizeof(struct pyrf_event),
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_throttle_event__doc,
+        .tp_members     = pyrf_throttle_event__members,
+        .tp_repr        = (reprfunc)pyrf_throttle_event__repr,
+};
+
+static int pyrf_event__setup_types(void)
+{
+        int err;
+        pyrf_mmap_event__type.tp_new =
+        pyrf_task_event__type.tp_new =
+        pyrf_comm_event__type.tp_new =
+        pyrf_throttle_event__type.tp_new = PyType_GenericNew;
+        err = PyType_Ready(&pyrf_mmap_event__type);
+        if (err < 0)
+                goto out;
+        err = PyType_Ready(&pyrf_task_event__type);
+        if (err < 0)
+                goto out;
+        err = PyType_Ready(&pyrf_comm_event__type);
+        if (err < 0)
+                goto out;
+        err = PyType_Ready(&pyrf_throttle_event__type);
+        if (err < 0)
+                goto out;
+out:
+        return err;
+}
+
+static PyTypeObject *pyrf_event__type[] = {
+        [PERF_RECORD_MMAP]       = &pyrf_mmap_event__type,
+        [PERF_RECORD_LOST]       = &pyrf_mmap_event__type,
+        [PERF_RECORD_COMM]       = &pyrf_comm_event__type,
+        [PERF_RECORD_EXIT]       = &pyrf_task_event__type,
+        [PERF_RECORD_THROTTLE]   = &pyrf_throttle_event__type,
+        [PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type,
+        [PERF_RECORD_FORK]       = &pyrf_task_event__type,
+        [PERF_RECORD_READ]       = &pyrf_mmap_event__type,
+        [PERF_RECORD_SAMPLE]     = &pyrf_mmap_event__type,
+};
+
+static PyObject *pyrf_event__new(union perf_event *event)
+{
+        struct pyrf_event *pevent;
+        PyTypeObject *ptype;
+
+        if (event->header.type < PERF_RECORD_MMAP ||
+            event->header.type > PERF_RECORD_SAMPLE)
+                return NULL;
+
+        ptype = pyrf_event__type[event->header.type];
+        pevent = PyObject_New(struct pyrf_event, ptype);
+        if (pevent != NULL)
+                memcpy(&pevent->event, event, event->header.size);
+        return (PyObject *)pevent;
+}
+
+struct pyrf_cpu_map {
+        PyObject_HEAD
+
+        struct cpu_map *cpus;
+};
+
+static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
+                              PyObject *args, PyObject *kwargs)
+{
+        static char *kwlist[] = { "cpustr", NULL, NULL, };
+        char *cpustr = NULL;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s",
+                                         kwlist, &cpustr))
+                return -1;
+
+        pcpus->cpus = cpu_map__new(cpustr);
+        if (pcpus->cpus == NULL)
+                return -1;
+        return 0;
+}
+
+static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
+{
+        cpu_map__delete(pcpus->cpus);
+        pcpus->ob_type->tp_free((PyObject*)pcpus);
+}
+
+static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
+{
+        struct pyrf_cpu_map *pcpus = (void *)obj;
+
+        return pcpus->cpus->nr;
+}
+
+static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i)
+{
+        struct pyrf_cpu_map *pcpus = (void *)obj;
+
+        if (i >= pcpus->cpus->nr)
+                return NULL;
+
+        return Py_BuildValue("i", pcpus->cpus->map[i]);
+}
+
+static PySequenceMethods pyrf_cpu_map__sequence_methods = {
+        .sq_length = pyrf_cpu_map__length,
+        .sq_item   = pyrf_cpu_map__item,
+};
+
+static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object.");
+
+static PyTypeObject pyrf_cpu_map__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.cpu_map",
+        .tp_basicsize   = sizeof(struct pyrf_cpu_map),
+        .tp_dealloc     = (destructor)pyrf_cpu_map__delete,
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_cpu_map__doc,
+        .tp_as_sequence = &pyrf_cpu_map__sequence_methods,
+        .tp_init        = (initproc)pyrf_cpu_map__init,
+};
+
+static int pyrf_cpu_map__setup_types(void)
+{
+        pyrf_cpu_map__type.tp_new = PyType_GenericNew;
+        return PyType_Ready(&pyrf_cpu_map__type);
+}
+
+struct pyrf_thread_map {
+        PyObject_HEAD
+
+        struct thread_map *threads;
+};
+
+static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
+                                 PyObject *args, PyObject *kwargs)
+{
+        static char *kwlist[] = { "pid", "tid", NULL, NULL, };
+        int pid = -1, tid = -1;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii",
+                                         kwlist, &pid, &tid))
+                return -1;
+
+        pthreads->threads = thread_map__new(pid, tid);
+        if (pthreads->threads == NULL)
+                return -1;
+        return 0;
+}
+
+static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
+{
+        thread_map__delete(pthreads->threads);
+        pthreads->ob_type->tp_free((PyObject*)pthreads);
+}
+
+static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
+{
+        struct pyrf_thread_map *pthreads = (void *)obj;
+
+        return pthreads->threads->nr;
+}
+
+static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i)
+{
+        struct pyrf_thread_map *pthreads = (void *)obj;
+
+        if (i >= pthreads->threads->nr)
+                return NULL;
+
+        return Py_BuildValue("i", pthreads->threads->map[i]);
+}
+
+static PySequenceMethods pyrf_thread_map__sequence_methods = {
+        .sq_length = pyrf_thread_map__length,
+        .sq_item   = pyrf_thread_map__item,
+};
+
+static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object.");
+
+static PyTypeObject pyrf_thread_map__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.thread_map",
+        .tp_basicsize   = sizeof(struct pyrf_thread_map),
+        .tp_dealloc     = (destructor)pyrf_thread_map__delete,
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_thread_map__doc,
+        .tp_as_sequence = &pyrf_thread_map__sequence_methods,
+        .tp_init        = (initproc)pyrf_thread_map__init,
+};
+
+static int pyrf_thread_map__setup_types(void)
+{
+        pyrf_thread_map__type.tp_new = PyType_GenericNew;
+        return PyType_Ready(&pyrf_thread_map__type);
+}
+
+struct pyrf_evsel {
+        PyObject_HEAD
+
+        struct perf_evsel evsel;
+};
+
+static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
+                            PyObject *args, PyObject *kwargs)
+{
+        struct perf_event_attr attr = {
+                .type = PERF_TYPE_HARDWARE,
+                .config = PERF_COUNT_HW_CPU_CYCLES,
+                .sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID,
+        };
+        static char *kwlist[] = {
+                "type",
+                "config",
+                "sample_freq",
+                "sample_period",
+                "sample_type",
+                "read_format",
+                "disabled",
+                "inherit",
+                "pinned",
+                "exclusive",
+                "exclude_user",
+                "exclude_kernel",
+                "exclude_hv",
+                "exclude_idle",
+                "mmap",
+                "comm",
+                "freq",
+                "inherit_stat",
+                "enable_on_exec",
+                "task",
+                "watermark",
+                "precise_ip",
+                "mmap_data",
+                "sample_id_all",
+                "wakeup_events",
+                "bp_type",
+                "bp_addr",
+                "bp_len", NULL, NULL, };
+        u64 sample_period = 0;
+        u32 disabled = 0,
+            inherit = 0,
+            pinned = 0,
+            exclusive = 0,
+            exclude_user = 0,
+            exclude_kernel = 0,
+            exclude_hv = 0,
+            exclude_idle = 0,
+            mmap = 0,
+            comm = 0,
+            freq = 1,
+            inherit_stat = 0,
+            enable_on_exec = 0,
+            task = 0,
+            watermark = 0,
+            precise_ip = 0,
+            mmap_data = 0,
+            sample_id_all = 1;
+        int idx = 0;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs,
+                                         "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist,
+                                         &attr.type, &attr.config, &attr.sample_freq,
+                                         &sample_period, &attr.sample_type,
+                                         &attr.read_format, &disabled, &inherit,
+                                         &pinned, &exclusive, &exclude_user,
+                                         &exclude_kernel, &exclude_hv, &exclude_idle,
+                                         &mmap, &comm, &freq, &inherit_stat,
+                                         &enable_on_exec, &task, &watermark,
+                                         &precise_ip, &mmap_data, &sample_id_all,
+                                         &attr.wakeup_events, &attr.bp_type,
+                                         &attr.bp_addr, &attr.bp_len, &idx))
+                return -1;
+
+        /* union... */
+        if (sample_period != 0) {
+                if (attr.sample_freq != 0)
+                        return -1; /* FIXME: throw right exception */
+                attr.sample_period = sample_period;
+        }
+
+        /* Bitfields */
+        attr.disabled       = disabled;
+        attr.inherit        = inherit;
+        attr.pinned         = pinned;
+        attr.exclusive      = exclusive;
+        attr.exclude_user   = exclude_user;
+        attr.exclude_kernel = exclude_kernel;
+        attr.exclude_hv     = exclude_hv;
+        attr.exclude_idle   = exclude_idle;
+        attr.mmap           = mmap;
+        attr.comm           = comm;
+        attr.freq           = freq;
+        attr.inherit_stat   = inherit_stat;
+        attr.enable_on_exec = enable_on_exec;
+        attr.task           = task;
+        attr.watermark      = watermark;
+        attr.precise_ip     = precise_ip;
+        attr.mmap_data      = mmap_data;
+        attr.sample_id_all  = sample_id_all;
+
+        perf_evsel__init(&pevsel->evsel, &attr, idx);
+        return 0;
+}
+
+static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
+{
+        perf_evsel__exit(&pevsel->evsel);
+        pevsel->ob_type->tp_free((PyObject*)pevsel);
+}
+
+static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
+                                  PyObject *args, PyObject *kwargs)
+{
+        struct perf_evsel *evsel = &pevsel->evsel;
+        struct cpu_map *cpus = NULL;
+        struct thread_map *threads = NULL;
+        PyObject *pcpus = NULL, *pthreads = NULL;
+        int group = 0, inherit = 0;
+        static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
+                                         &pcpus, &pthreads, &group, &inherit))
+                return NULL;
+
+        if (pthreads != NULL)
+                threads = ((struct pyrf_thread_map *)pthreads)->threads;
+
+        if (pcpus != NULL)
+                cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+
+        evsel->attr.inherit = inherit;
+        if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
+                PyErr_SetFromErrno(PyExc_OSError);
+                return NULL;
+        }
+
+        Py_INCREF(Py_None);
+        return Py_None;
+}
+
+static PyMethodDef pyrf_evsel__methods[] = {
+        {
+                .ml_name  = "open",
+                .ml_meth  = (PyCFunction)pyrf_evsel__open,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("open the event selector file descriptor table.")
+        },
+        { .ml_name = NULL, }
+};
+
+static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evsel__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.evsel",
+        .tp_basicsize   = sizeof(struct pyrf_evsel),
+        .tp_dealloc     = (destructor)pyrf_evsel__delete,
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_doc         = pyrf_evsel__doc,
+        .tp_methods     = pyrf_evsel__methods,
+        .tp_init        = (initproc)pyrf_evsel__init,
+};
+
+static int pyrf_evsel__setup_types(void)
+{
+        pyrf_evsel__type.tp_new = PyType_GenericNew;
+        return PyType_Ready(&pyrf_evsel__type);
+}
+
+struct pyrf_evlist {
+        PyObject_HEAD
+
+        struct perf_evlist evlist;
+};
+
+static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
+                             PyObject *args, PyObject *kwargs __used)
+{
+        PyObject *pcpus = NULL, *pthreads = NULL;
+        struct cpu_map *cpus;
+        struct thread_map *threads;
+
+        if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads))
+                return -1;
+
+        threads = ((struct pyrf_thread_map *)pthreads)->threads;
+        cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
+        perf_evlist__init(&pevlist->evlist, cpus, threads);
+        return 0;
+}
+
+static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
+{
+        perf_evlist__exit(&pevlist->evlist);
+        pevlist->ob_type->tp_free((PyObject*)pevlist);
+}
+
+static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
+                                   PyObject *args, PyObject *kwargs)
+{
+        struct perf_evlist *evlist = &pevlist->evlist;
+        static char *kwlist[] = {"pages", "overwrite",
+                                  NULL, NULL};
+        int pages = 128, overwrite = false;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist,
+                                         &pages, &overwrite))
+                return NULL;
+
+        if (perf_evlist__mmap(evlist, pages, overwrite) < 0) {
+                PyErr_SetFromErrno(PyExc_OSError);
+                return NULL;
+        }
+
+        Py_INCREF(Py_None);
+        return Py_None;
+}
+
+static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
+                                   PyObject *args, PyObject *kwargs)
+{
+        struct perf_evlist *evlist = &pevlist->evlist;
+        static char *kwlist[] = {"timeout", NULL, NULL};
+        int timeout = -1, n;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
+                return NULL;
+
+        n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+        if (n < 0) {
+                PyErr_SetFromErrno(PyExc_OSError);
+                return NULL;
+        }
+
+        return Py_BuildValue("i", n);
+}
+
+static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
+                                         PyObject *args __used, PyObject *kwargs __used)
+{
+        struct perf_evlist *evlist = &pevlist->evlist;
+        PyObject *list = PyList_New(0);
+        int i;
+
+        for (i = 0; i < evlist->nr_fds; ++i) {
+                PyObject *file;
+                FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+
+                if (fp == NULL)
+                        goto free_list;
+
+                file = PyFile_FromFile(fp, "perf", "r", NULL);
+                if (file == NULL)
+                        goto free_list;
+
+                if (PyList_Append(list, file) != 0) {
+                        Py_DECREF(file);
+                        goto free_list;
+                }
+                        
+                Py_DECREF(file);
+        }
+
+        return list;
+free_list:
+        return PyErr_NoMemory();
+}
+
+
+static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist,
+                                  PyObject *args, PyObject *kwargs __used)
+{
+        struct perf_evlist *evlist = &pevlist->evlist;
+        PyObject *pevsel;
+        struct perf_evsel *evsel;
+
+        if (!PyArg_ParseTuple(args, "O", &pevsel))
+                return NULL;
+
+        Py_INCREF(pevsel);
+        evsel = &((struct pyrf_evsel *)pevsel)->evsel;
+        evsel->idx = evlist->nr_entries;
+        perf_evlist__add(evlist, evsel);
+
+        return Py_BuildValue("i", evlist->nr_entries);
+}
+
+static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
+                                          PyObject *args, PyObject *kwargs)
+{
+        struct perf_evlist *evlist = &pevlist->evlist;
+        union perf_event *event;
+        int sample_id_all = 1, cpu;
+        static char *kwlist[] = {"cpu", "sample_id_all", NULL, NULL};
+        int err;
+
+        if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
+                                         &cpu, &sample_id_all))
+                return NULL;
+
+        event = perf_evlist__mmap_read(evlist, cpu);
+        if (event != NULL) {
+                struct perf_evsel *first;
+                PyObject *pyevent = pyrf_event__new(event);
+                struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
+
+                if (pyevent == NULL)
+                        return PyErr_NoMemory();
+
+                first = list_entry(evlist->entries.next, struct perf_evsel, node);
+                err = perf_event__parse_sample(event, first->attr.sample_type,
+                                               perf_evsel__sample_size(first),
+                                               sample_id_all, &pevent->sample);
+                if (err)
+                        return PyErr_Format(PyExc_OSError,
+                                            "perf: can't parse sample, err=%d", err);
+                return pyevent;
+        }
+
+        Py_INCREF(Py_None);
+        return Py_None;
+}
+
+static PyMethodDef pyrf_evlist__methods[] = {
+        {
+                .ml_name  = "mmap",
+                .ml_meth  = (PyCFunction)pyrf_evlist__mmap,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("mmap the file descriptor table.")
+        },
+        {
+                .ml_name  = "poll",
+                .ml_meth  = (PyCFunction)pyrf_evlist__poll,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("poll the file descriptor table.")
+        },
+        {
+                .ml_name  = "get_pollfd",
+                .ml_meth  = (PyCFunction)pyrf_evlist__get_pollfd,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("get the poll file descriptor table.")
+        },
+        {
+                .ml_name  = "add",
+                .ml_meth  = (PyCFunction)pyrf_evlist__add,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("adds an event selector to the list.")
+        },
+        {
+                .ml_name  = "read_on_cpu",
+                .ml_meth  = (PyCFunction)pyrf_evlist__read_on_cpu,
+                .ml_flags = METH_VARARGS | METH_KEYWORDS,
+                .ml_doc   = PyDoc_STR("reads an event.")
+        },
+        { .ml_name = NULL, }
+};
+
+static Py_ssize_t pyrf_evlist__length(PyObject *obj)
+{
+        struct pyrf_evlist *pevlist = (void *)obj;
+
+        return pevlist->evlist.nr_entries;
+}
+
+static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
+{
+        struct pyrf_evlist *pevlist = (void *)obj;
+        struct perf_evsel *pos;
+
+        if (i >= pevlist->evlist.nr_entries)
+                return NULL;
+
+        list_for_each_entry(pos, &pevlist->evlist.entries, node)
+                if (i-- == 0)
+                        break;
+
+        return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
+}
+
+static PySequenceMethods pyrf_evlist__sequence_methods = {
+        .sq_length = pyrf_evlist__length,
+        .sq_item   = pyrf_evlist__item,
+};
+
+static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object.");
+
+static PyTypeObject pyrf_evlist__type = {
+        PyVarObject_HEAD_INIT(NULL, 0)
+        .tp_name        = "perf.evlist",
+        .tp_basicsize   = sizeof(struct pyrf_evlist),
+        .tp_dealloc     = (destructor)pyrf_evlist__delete,
+        .tp_flags       = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE,
+        .tp_as_sequence = &pyrf_evlist__sequence_methods,
+        .tp_doc         = pyrf_evlist__doc,
+        .tp_methods     = pyrf_evlist__methods,
+        .tp_init        = (initproc)pyrf_evlist__init,
+};
+
+static int pyrf_evlist__setup_types(void)
+{
+        pyrf_evlist__type.tp_new = PyType_GenericNew;
+        return PyType_Ready(&pyrf_evlist__type);
+}
+
+static struct {
+        const char *name;
+        int         value;
+} perf__constants[] = {
+        { "TYPE_HARDWARE",   PERF_TYPE_HARDWARE },
+        { "TYPE_SOFTWARE",   PERF_TYPE_SOFTWARE },
+        { "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT },
+        { "TYPE_HW_CACHE",   PERF_TYPE_HW_CACHE },
+        { "TYPE_RAW",        PERF_TYPE_RAW },
+        { "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT },
+
+        { "COUNT_HW_CPU_CYCLES",          PERF_COUNT_HW_CPU_CYCLES },
+        { "COUNT_HW_INSTRUCTIONS",        PERF_COUNT_HW_INSTRUCTIONS },
+        { "COUNT_HW_CACHE_REFERENCES",    PERF_COUNT_HW_CACHE_REFERENCES },
+        { "COUNT_HW_CACHE_MISSES",        PERF_COUNT_HW_CACHE_MISSES },
+        { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+        { "COUNT_HW_BRANCH_MISSES",       PERF_COUNT_HW_BRANCH_MISSES },
+        { "COUNT_HW_BUS_CYCLES",          PERF_COUNT_HW_BUS_CYCLES },
+        { "COUNT_HW_CACHE_L1D",           PERF_COUNT_HW_CACHE_L1D },
+        { "COUNT_HW_CACHE_L1I",           PERF_COUNT_HW_CACHE_L1I },
+        { "COUNT_HW_CACHE_LL",            PERF_COUNT_HW_CACHE_LL },
+        { "COUNT_HW_CACHE_DTLB",          PERF_COUNT_HW_CACHE_DTLB },
+        { "COUNT_HW_CACHE_ITLB",          PERF_COUNT_HW_CACHE_ITLB },
+        { "COUNT_HW_CACHE_BPU",           PERF_COUNT_HW_CACHE_BPU },
+        { "COUNT_HW_CACHE_OP_READ",       PERF_COUNT_HW_CACHE_OP_READ },
+        { "COUNT_HW_CACHE_OP_WRITE",      PERF_COUNT_HW_CACHE_OP_WRITE },
+        { "COUNT_HW_CACHE_OP_PREFETCH",   PERF_COUNT_HW_CACHE_OP_PREFETCH },
+        { "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS },
+        { "COUNT_HW_CACHE_RESULT_MISS",   PERF_COUNT_HW_CACHE_RESULT_MISS },
+
+        { "COUNT_HW_STALLED_CYCLES_FRONTEND",     PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+        { "COUNT_HW_STALLED_CYCLES_BACKEND",      PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
+
+        { "COUNT_SW_CPU_CLOCK",        PERF_COUNT_SW_CPU_CLOCK },
+        { "COUNT_SW_TASK_CLOCK",       PERF_COUNT_SW_TASK_CLOCK },
+        { "COUNT_SW_PAGE_FAULTS",      PERF_COUNT_SW_PAGE_FAULTS },
+        { "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES },
+        { "COUNT_SW_CPU_MIGRATIONS",   PERF_COUNT_SW_CPU_MIGRATIONS },
+        { "COUNT_SW_PAGE_FAULTS_MIN",  PERF_COUNT_SW_PAGE_FAULTS_MIN },
+        { "COUNT_SW_PAGE_FAULTS_MAJ",  PERF_COUNT_SW_PAGE_FAULTS_MAJ },
+        { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS },
+        { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS },
+
+        { "SAMPLE_IP",        PERF_SAMPLE_IP },
+        { "SAMPLE_TID",       PERF_SAMPLE_TID },
+        { "SAMPLE_TIME",      PERF_SAMPLE_TIME },
+        { "SAMPLE_ADDR",      PERF_SAMPLE_ADDR },
+        { "SAMPLE_READ",      PERF_SAMPLE_READ },
+        { "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN },
+        { "SAMPLE_ID",        PERF_SAMPLE_ID },
+        { "SAMPLE_CPU",       PERF_SAMPLE_CPU },
+        { "SAMPLE_PERIOD",    PERF_SAMPLE_PERIOD },
+        { "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID },
+        { "SAMPLE_RAW",       PERF_SAMPLE_RAW },
+
+        { "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED },
+        { "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING },
+        { "FORMAT_ID",                 PERF_FORMAT_ID },
+        { "FORMAT_GROUP",              PERF_FORMAT_GROUP },
+
+        { "RECORD_MMAP",       PERF_RECORD_MMAP },
+        { "RECORD_LOST",       PERF_RECORD_LOST },
+        { "RECORD_COMM",       PERF_RECORD_COMM },
+        { "RECORD_EXIT",       PERF_RECORD_EXIT },
+        { "RECORD_THROTTLE",   PERF_RECORD_THROTTLE },
+        { "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE },
+        { "RECORD_FORK",       PERF_RECORD_FORK },
+        { "RECORD_READ",       PERF_RECORD_READ },
+        { "RECORD_SAMPLE",     PERF_RECORD_SAMPLE },
+        { .name = NULL, },
+};
+
+static PyMethodDef perf__methods[] = {
+        { .ml_name = NULL, }
+};
+
+PyMODINIT_FUNC initperf(void)
+{
+        PyObject *obj;
+        int i;
+        PyObject *dict, *module = Py_InitModule("perf", perf__methods);
+
+        if (module == NULL ||
+            pyrf_event__setup_types() < 0 ||
+            pyrf_evlist__setup_types() < 0 ||
+            pyrf_evsel__setup_types() < 0 ||
+            pyrf_thread_map__setup_types() < 0 ||
+            pyrf_cpu_map__setup_types() < 0)
+                return;
+
+        Py_INCREF(&pyrf_evlist__type);
+        PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type);
+
+        Py_INCREF(&pyrf_evsel__type);
+        PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type);
+
+        Py_INCREF(&pyrf_thread_map__type);
+        PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type);
+
+        Py_INCREF(&pyrf_cpu_map__type);
+        PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type);
+
+        dict = PyModule_GetDict(module);
+        if (dict == NULL)
+                goto error;
+
+        for (i = 0; perf__constants[i].name != NULL; i++) {
+                obj = PyInt_FromLong(perf__constants[i].value);
+                if (obj == NULL)
+                        goto error;
+                PyDict_SetItemString(dict, perf__constants[i].name, obj);
+                Py_DECREF(obj);
+        }
+
+error:
+        if (PyErr_Occurred())
+                PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b059dc50cc2d..74350ffb57fe 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -1,5 +1,5 @@
 /*
- * trace-event-perl.  Feed perf trace events to an embedded Perl interpreter.
+ * trace-event-perl.  Feed perf script events to an embedded Perl interpreter.
  *
  * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
  *
@@ -245,9 +245,11 @@ static inline struct event *find_cache_event(int type)
         return event;
 }
 
-static void perl_process_event(int cpu, void *data,
-                               int size __unused,
-                               unsigned long long nsecs, char *comm)
+static void perl_process_event(union perf_event *pevent __unused,
+                               struct perf_sample *sample,
+                               struct perf_evsel *evsel,
+                               struct perf_session *session __unused,
+                               struct thread *thread)
 {
         struct format_field *field;
         static char handler[256];
@@ -256,6 +258,10 @@ static void perl_process_event(int cpu, void *data,
         struct event *event;
         int type;
         int pid;
+        int cpu = sample->cpu;
+        void *data = sample->raw_data;
+        unsigned long long nsecs = sample->time;
+        char *comm = thread->comm;
 
         dSP;
 
@@ -411,8 +417,8 @@ static int perl_generate_script(const char *outfile)
                 return -1;
         }
 
-        fprintf(ofp, "# perf trace event handlers, "
-                "generated by perf trace -g perl\n");
+        fprintf(ofp, "# perf script event handlers, "
+                "generated by perf script -g perl\n");
 
         fprintf(ofp, "# Licensed under the terms of the GNU GPL"
                 " License version 2\n\n");
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 33a632523743..6ccf70e8d8f2 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -204,9 +204,11 @@ static inline struct event *find_cache_event(int type)
         return event;
 }
 
-static void python_process_event(int cpu, void *data,
-                                 int size __unused,
-                                 unsigned long long nsecs, char *comm)
+static void python_process_event(union perf_event *pevent __unused,
+                                 struct perf_sample *sample,
+                                 struct perf_evsel *evsel __unused,
+                                 struct perf_session *session __unused,
+                                 struct thread *thread)
 {
         PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
         static char handler_name[256];
@@ -217,6 +219,10 @@ static void python_process_event(int cpu, void *data,
         unsigned n = 0;
         int type;
         int pid;
+        int cpu = sample->cpu;
+        void *data = sample->raw_data;
+        unsigned long long nsecs = sample->time;
+        char *comm = thread->comm;
 
         t = PyTuple_New(MAX_FIELDS);
         if (!t)
@@ -248,8 +254,7 @@ static void python_process_event(int cpu, void *data,
         context = PyCObject_FromVoidPtr(scripting_context, NULL);
 
         PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
-        PyTuple_SetItem(t, n++,
-                        PyCObject_FromVoidPtr(scripting_context, NULL));
+        PyTuple_SetItem(t, n++, context);
 
         if (handler) {
                 PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
@@ -442,8 +447,8 @@ static int python_generate_script(const char *outfile)
                 fprintf(stderr, "couldn't open %s\n", fname);
                 return -1;
         }
-        fprintf(ofp, "# perf trace event handlers, "
-                "generated by perf trace -g python\n");
+        fprintf(ofp, "# perf script event handlers, "
+                "generated by perf script -g python\n");
 
         fprintf(ofp, "# Licensed under the terms of the GNU GPL"
                 " License version 2\n\n");
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fa9d652c2dc3..f5a8fbdd3f76 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -7,6 +7,8 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 
+#include "evlist.h"
+#include "evsel.h"
 #include "session.h"
 #include "sort.h"
 #include "util.h"
@@ -19,7 +21,7 @@ static int perf_session__open(struct perf_session *self, bool force)
                 self->fd_pipe = true;
                 self->fd = STDIN_FILENO;
 
-                if (perf_header__read(self, self->fd) < 0)
+                if (perf_session__read_header(self, self->fd) < 0)
                         pr_err("incompatible file format");
 
                 return 0;
@@ -51,11 +53,21 @@ static int perf_session__open(struct perf_session *self, bool force)
                 goto out_close;
         }
 
-        if (perf_header__read(self, self->fd) < 0) {
+        if (perf_session__read_header(self, self->fd) < 0) {
                 pr_err("incompatible file format");
                 goto out_close;
         }
 
+        if (!perf_evlist__valid_sample_type(self->evlist)) {
+                pr_err("non matching sample_type");
+                goto out_close;
+        }
+
+        if (!perf_evlist__valid_sample_id_all(self->evlist)) {
+                pr_err("non matching sample_id_all");
+                goto out_close;
+        }
+
         self->size = input_stat.st_size;
         return 0;
 
@@ -65,9 +77,39 @@ out_close:
         return -1;
 }
 
+static void perf_session__id_header_size(struct perf_session *session)
+{
+       struct perf_sample *data;
+       u64 sample_type = session->sample_type;
+       u16 size = 0;
+
+        if (!session->sample_id_all)
+                goto out;
+
+       if (sample_type & PERF_SAMPLE_TID)
+               size += sizeof(data->tid) * 2;
+
+       if (sample_type & PERF_SAMPLE_TIME)
+               size += sizeof(data->time);
+
+       if (sample_type & PERF_SAMPLE_ID)
+               size += sizeof(data->id);
+
+       if (sample_type & PERF_SAMPLE_STREAM_ID)
+               size += sizeof(data->stream_id);
+
+       if (sample_type & PERF_SAMPLE_CPU)
+               size += sizeof(data->cpu) * 2;
+out:
+       session->id_hdr_size = size;
+}
+
 void perf_session__update_sample_type(struct perf_session *self)
 {
-        self->sample_type = perf_header__sample_type(&self->header);
+        self->sample_type = perf_evlist__sample_type(self->evlist);
+        self->sample_size = __perf_evsel__sample_size(self->sample_type);
+        self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
+        perf_session__id_header_size(self);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -85,7 +127,9 @@ static void perf_session__destroy_kernel_maps(struct perf_session *self)
         machines__destroy_guest_kernel_maps(&self->machines);
 }
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe)
+struct perf_session *perf_session__new(const char *filename, int mode,
+                                       bool force, bool repipe,
+                                       struct perf_event_ops *ops)
 {
         size_t len = filename ? strlen(filename) + 1 : 0;
         struct perf_session *self = zalloc(sizeof(*self) + len);
@@ -93,38 +137,47 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
         if (self == NULL)
                 goto out;
 
-        if (perf_header__init(&self->header) < 0)
-                goto out_free;
-
         memcpy(self->filename, filename, len);
         self->threads = RB_ROOT;
         INIT_LIST_HEAD(&self->dead_threads);
-        self->hists_tree = RB_ROOT;
         self->last_match = NULL;
-        self->mmap_window = 32;
+        /*
+         * On 64bit we can mmap the data file in one go. No need for tiny mmap
+         * slices. On 32bit we use 32MB.
+         */
+#if BITS_PER_LONG == 64
+        self->mmap_window = ULLONG_MAX;
+#else
+        self->mmap_window = 32 * 1024 * 1024ULL;
+#endif
         self->machines = RB_ROOT;
         self->repipe = repipe;
-        INIT_LIST_HEAD(&self->ordered_samples.samples_head);
+        INIT_LIST_HEAD(&self->ordered_samples.samples);
+        INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
+        INIT_LIST_HEAD(&self->ordered_samples.to_free);
         machine__init(&self->host_machine, "", HOST_KERNEL_ID);
 
         if (mode == O_RDONLY) {
                 if (perf_session__open(self, force) < 0)
                         goto out_delete;
+                perf_session__update_sample_type(self);
         } else if (mode == O_WRONLY) {
                 /*
                  * In O_RDONLY mode this will be performed when reading the
-                 * kernel MMAP event, in event__process_mmap().
+                 * kernel MMAP event, in perf_event__process_mmap().
                  */
                 if (perf_session__create_kernel_maps(self) < 0)
                         goto out_delete;
         }
 
-        perf_session__update_sample_type(self);
+        if (ops && ops->ordering_requires_timestamps &&
+            ops->ordered_samples && !self->sample_id_all) {
+                dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
+                ops->ordered_samples = false;
+        }
+
 out:
         return self;
-out_free:
-        free(self);
-        return NULL;
 out_delete:
         perf_session__delete(self);
         return NULL;
@@ -155,7 +208,6 @@ static void perf_session__delete_threads(struct perf_session *self)
 
 void perf_session__delete(struct perf_session *self)
 {
-        perf_header__exit(&self->header);
         perf_session__destroy_kernel_maps(self);
         perf_session__delete_dead_threads(self);
         perf_session__delete_threads(self);
@@ -183,17 +235,16 @@ static bool symbol__match_parent_regex(struct symbol *sym)
         return 0;
 }
 
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
-                                                   struct thread *thread,
-                                                   struct ip_callchain *chain,
-                                                   struct symbol **parent)
+int perf_session__resolve_callchain(struct perf_session *self,
+                                    struct thread *thread,
+                                    struct ip_callchain *chain,
+                                    struct symbol **parent)
 {
         u8 cpumode = PERF_RECORD_MISC_USER;
         unsigned int i;
-        struct map_symbol *syms = calloc(chain->nr, sizeof(*syms));
+        int err;
 
-        if (!syms)
-                return NULL;
+        callchain_cursor_reset(&self->callchain_cursor);
 
         for (i = 0; i < chain->nr; i++) {
                 u64 ip = chain->ips[i];
@@ -222,22 +273,42 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
                                 *parent = al.sym;
                         if (!symbol_conf.use_callchain)
                                 break;
-                        syms[i].map = al.map;
-                        syms[i].sym = al.sym;
                 }
+
+                err = callchain_cursor_append(&self->callchain_cursor,
+                                              ip, al.map, al.sym);
+                if (err)
+                        return err;
         }
 
-        return syms;
+        return 0;
+}
+
+static int process_event_synth_stub(union perf_event *event __used,
+                                    struct perf_session *session __used)
+{
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
+static int process_event_sample_stub(union perf_event *event __used,
+                                     struct perf_sample *sample __used,
+                                     struct perf_evsel *evsel __used,
+                                     struct perf_session *session __used)
+{
+        dump_printf(": unhandled!\n");
+        return 0;
 }
 
-static int process_event_stub(event_t *event __used,
+static int process_event_stub(union perf_event *event __used,
+                              struct perf_sample *sample __used,
                               struct perf_session *session __used)
 {
         dump_printf(": unhandled!\n");
         return 0;
 }
 
-static int process_finished_round_stub(event_t *event __used,
+static int process_finished_round_stub(union perf_event *event __used,
                                        struct perf_session *session __used,
                                        struct perf_event_ops *ops __used)
 {
@@ -245,14 +316,14 @@ static int process_finished_round_stub(event_t *event __used,
         return 0;
 }
 
-static int process_finished_round(event_t *event,
+static int process_finished_round(union perf_event *event,
                                   struct perf_session *session,
                                   struct perf_event_ops *ops);
 
 static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
 {
         if (handler->sample == NULL)
-                handler->sample = process_event_stub;
+                handler->sample = process_event_sample_stub;
         if (handler->mmap == NULL)
                 handler->mmap = process_event_stub;
         if (handler->comm == NULL)
@@ -262,7 +333,7 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
         if (handler->exit == NULL)
                 handler->exit = process_event_stub;
         if (handler->lost == NULL)
-                handler->lost = process_event_stub;
+                handler->lost = perf_event__process_lost;
         if (handler->read == NULL)
                 handler->read = process_event_stub;
         if (handler->throttle == NULL)
@@ -270,13 +341,13 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
         if (handler->unthrottle == NULL)
                 handler->unthrottle = process_event_stub;
         if (handler->attr == NULL)
-                handler->attr = process_event_stub;
+                handler->attr = process_event_synth_stub;
         if (handler->event_type == NULL)
-                handler->event_type = process_event_stub;
+                handler->event_type = process_event_synth_stub;
         if (handler->tracing_data == NULL)
-                handler->tracing_data = process_event_stub;
+                handler->tracing_data = process_event_synth_stub;
         if (handler->build_id == NULL)
-                handler->build_id = process_event_stub;
+                handler->build_id = process_event_synth_stub;
         if (handler->finished_round == NULL) {
                 if (handler->ordered_samples)
                         handler->finished_round = process_finished_round;
@@ -296,123 +367,155 @@ void mem_bswap_64(void *src, int byte_size)
         }
 }
 
-static void event__all64_swap(event_t *self)
+static void perf_event__all64_swap(union perf_event *event)
 {
-        struct perf_event_header *hdr = &self->header;
-        mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr));
+        struct perf_event_header *hdr = &event->header;
+        mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
 }
 
-static void event__comm_swap(event_t *self)
+static void perf_event__comm_swap(union perf_event *event)
 {
-        self->comm.pid = bswap_32(self->comm.pid);
-        self->comm.tid = bswap_32(self->comm.tid);
+        event->comm.pid = bswap_32(event->comm.pid);
+        event->comm.tid = bswap_32(event->comm.tid);
 }
 
-static void event__mmap_swap(event_t *self)
+static void perf_event__mmap_swap(union perf_event *event)
 {
-        self->mmap.pid   = bswap_32(self->mmap.pid);
-        self->mmap.tid   = bswap_32(self->mmap.tid);
-        self->mmap.start = bswap_64(self->mmap.start);
-        self->mmap.len   = bswap_64(self->mmap.len);
-        self->mmap.pgoff = bswap_64(self->mmap.pgoff);
+        event->mmap.pid   = bswap_32(event->mmap.pid);
+        event->mmap.tid   = bswap_32(event->mmap.tid);
+        event->mmap.start = bswap_64(event->mmap.start);
+        event->mmap.len   = bswap_64(event->mmap.len);
+        event->mmap.pgoff = bswap_64(event->mmap.pgoff);
 }
 
-static void event__task_swap(event_t *self)
+static void perf_event__task_swap(union perf_event *event)
 {
-        self->fork.pid  = bswap_32(self->fork.pid);
-        self->fork.tid  = bswap_32(self->fork.tid);
-        self->fork.ppid = bswap_32(self->fork.ppid);
-        self->fork.ptid = bswap_32(self->fork.ptid);
-        self->fork.time = bswap_64(self->fork.time);
+        event->fork.pid  = bswap_32(event->fork.pid);
+        event->fork.tid  = bswap_32(event->fork.tid);
+        event->fork.ppid = bswap_32(event->fork.ppid);
+        event->fork.ptid = bswap_32(event->fork.ptid);
+        event->fork.time = bswap_64(event->fork.time);
 }
 
-static void event__read_swap(event_t *self)
+static void perf_event__read_swap(union perf_event *event)
 {
-        self->read.pid          = bswap_32(self->read.pid);
-        self->read.tid          = bswap_32(self->read.tid);
-        self->read.value        = bswap_64(self->read.value);
-        self->read.time_enabled = bswap_64(self->read.time_enabled);
-        self->read.time_running = bswap_64(self->read.time_running);
-        self->read.id           = bswap_64(self->read.id);
+        event->read.pid          = bswap_32(event->read.pid);
+        event->read.tid          = bswap_32(event->read.tid);
+        event->read.value        = bswap_64(event->read.value);
+        event->read.time_enabled = bswap_64(event->read.time_enabled);
+        event->read.time_running = bswap_64(event->read.time_running);
+        event->read.id           = bswap_64(event->read.id);
 }
 
-static void event__attr_swap(event_t *self)
+static void perf_event__attr_swap(union perf_event *event)
 {
         size_t size;
 
-        self->attr.attr.type            = bswap_32(self->attr.attr.type);
-        self->attr.attr.size            = bswap_32(self->attr.attr.size);
-        self->attr.attr.config          = bswap_64(self->attr.attr.config);
-        self->attr.attr.sample_period   = bswap_64(self->attr.attr.sample_period);
-        self->attr.attr.sample_type     = bswap_64(self->attr.attr.sample_type);
-        self->attr.attr.read_format     = bswap_64(self->attr.attr.read_format);
-        self->attr.attr.wakeup_events   = bswap_32(self->attr.attr.wakeup_events);
-        self->attr.attr.bp_type         = bswap_32(self->attr.attr.bp_type);
-        self->attr.attr.bp_addr         = bswap_64(self->attr.attr.bp_addr);
-        self->attr.attr.bp_len          = bswap_64(self->attr.attr.bp_len);
+        event->attr.attr.type           = bswap_32(event->attr.attr.type);
+        event->attr.attr.size           = bswap_32(event->attr.attr.size);
+        event->attr.attr.config         = bswap_64(event->attr.attr.config);
+        event->attr.attr.sample_period  = bswap_64(event->attr.attr.sample_period);
+        event->attr.attr.sample_type    = bswap_64(event->attr.attr.sample_type);
+        event->attr.attr.read_format    = bswap_64(event->attr.attr.read_format);
+        event->attr.attr.wakeup_events  = bswap_32(event->attr.attr.wakeup_events);
+        event->attr.attr.bp_type        = bswap_32(event->attr.attr.bp_type);
+        event->attr.attr.bp_addr        = bswap_64(event->attr.attr.bp_addr);
+        event->attr.attr.bp_len         = bswap_64(event->attr.attr.bp_len);
 
-        size = self->header.size;
-        size -= (void *)&self->attr.id - (void *)self;
-        mem_bswap_64(self->attr.id, size);
+        size = event->header.size;
+        size -= (void *)&event->attr.id - (void *)event;
+        mem_bswap_64(event->attr.id, size);
 }
 
-static void event__event_type_swap(event_t *self)
+static void perf_event__event_type_swap(union perf_event *event)
 {
-        self->event_type.event_type.event_id =
-                bswap_64(self->event_type.event_type.event_id);
+        event->event_type.event_type.event_id =
+                bswap_64(event->event_type.event_type.event_id);
 }
 
-static void event__tracing_data_swap(event_t *self)
+static void perf_event__tracing_data_swap(union perf_event *event)
 {
-        self->tracing_data.size = bswap_32(self->tracing_data.size);
+        event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
-typedef void (*event__swap_op)(event_t *self);
-
-static event__swap_op event__swap_ops[] = {
-        [PERF_RECORD_MMAP]   = event__mmap_swap,
-        [PERF_RECORD_COMM]   = event__comm_swap,
-        [PERF_RECORD_FORK]   = event__task_swap,
-        [PERF_RECORD_EXIT]   = event__task_swap,
-        [PERF_RECORD_LOST]   = event__all64_swap,
-        [PERF_RECORD_READ]   = event__read_swap,
-        [PERF_RECORD_SAMPLE] = event__all64_swap,
-        [PERF_RECORD_HEADER_ATTR]   = event__attr_swap,
-        [PERF_RECORD_HEADER_EVENT_TYPE]   = event__event_type_swap,
-        [PERF_RECORD_HEADER_TRACING_DATA]   = event__tracing_data_swap,
-        [PERF_RECORD_HEADER_BUILD_ID]   = NULL,
-        [PERF_RECORD_HEADER_MAX]    = NULL,
+typedef void (*perf_event__swap_op)(union perf_event *event);
+
+static perf_event__swap_op perf_event__swap_ops[] = {
+        [PERF_RECORD_MMAP]                = perf_event__mmap_swap,
+        [PERF_RECORD_COMM]                = perf_event__comm_swap,
+        [PERF_RECORD_FORK]                = perf_event__task_swap,
+        [PERF_RECORD_EXIT]                = perf_event__task_swap,
+        [PERF_RECORD_LOST]                = perf_event__all64_swap,
+        [PERF_RECORD_READ]                = perf_event__read_swap,
+        [PERF_RECORD_SAMPLE]              = perf_event__all64_swap,
+        [PERF_RECORD_HEADER_ATTR]         = perf_event__attr_swap,
+        [PERF_RECORD_HEADER_EVENT_TYPE]   = perf_event__event_type_swap,
+        [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
+        [PERF_RECORD_HEADER_BUILD_ID]     = NULL,
+        [PERF_RECORD_HEADER_MAX]          = NULL,
 };
 
 struct sample_queue {
         u64                     timestamp;
-        struct sample_event     *event;
+        u64                     file_offset;
+        union perf_event        *event;
         struct list_head        list;
 };
 
+static void perf_session_free_sample_buffers(struct perf_session *session)
+{
+        struct ordered_samples *os = &session->ordered_samples;
+
+        while (!list_empty(&os->to_free)) {
+                struct sample_queue *sq;
+
+                sq = list_entry(os->to_free.next, struct sample_queue, list);
+                list_del(&sq->list);
+                free(sq);
+        }
+}
+
+static int perf_session_deliver_event(struct perf_session *session,
+                                      union perf_event *event,
+                                      struct perf_sample *sample,
+                                      struct perf_event_ops *ops,
+                                      u64 file_offset);
+
 static void flush_sample_queue(struct perf_session *s,
                                struct perf_event_ops *ops)
 {
-        struct list_head *head = &s->ordered_samples.samples_head;
-        u64 limit = s->ordered_samples.next_flush;
+        struct ordered_samples *os = &s->ordered_samples;
+        struct list_head *head = &os->samples;
         struct sample_queue *tmp, *iter;
+        struct perf_sample sample;
+        u64 limit = os->next_flush;
+        u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
+        int ret;
 
         if (!ops->ordered_samples || !limit)
                 return;
 
         list_for_each_entry_safe(iter, tmp, head, list) {
                 if (iter->timestamp > limit)
-                        return;
-
-                if (iter == s->ordered_samples.last_inserted)
-                        s->ordered_samples.last_inserted = NULL;
+                        break;
 
-                ops->sample((event_t *)iter->event, s);
+                ret = perf_session__parse_sample(s, iter->event, &sample);
+                if (ret)
+                        pr_err("Can't parse sample, err = %d\n", ret);
+                else
+                        perf_session_deliver_event(s, iter->event, &sample, ops,
+                                                   iter->file_offset);
 
-                s->ordered_samples.last_flush = iter->timestamp;
+                os->last_flush = iter->timestamp;
                 list_del(&iter->list);
-                free(iter->event);
-                free(iter);
+                list_add(&iter->list, &os->sample_cache);
+        }
+
+        if (list_empty(head)) {
+                os->last_sample = NULL;
+        } else if (last_ts <= limit) {
+                os->last_sample =
+                        list_entry(head->prev, struct sample_queue, list);
         }
 }
 
@@ -455,7 +558,7 @@ static void flush_sample_queue(struct perf_session *s,
  *      Flush every events below timestamp 7
  *      etc...
  */
-static int process_finished_round(event_t *event __used,
+static int process_finished_round(union perf_event *event __used,
                                   struct perf_session *session,
                                   struct perf_event_ops *ops)
 {
@@ -465,178 +568,277 @@ static int process_finished_round(event_t *event __used,
         return 0;
 }
 
-static void __queue_sample_end(struct sample_queue *new, struct list_head *head)
-{
-        struct sample_queue *iter;
-
-        list_for_each_entry_reverse(iter, head, list) {
-                if (iter->timestamp < new->timestamp) {
-                        list_add(&new->list, &iter->list);
-                        return;
-                }
-        }
-
-        list_add(&new->list, head);
-}
-
-static void __queue_sample_before(struct sample_queue *new,
-                                  struct sample_queue *iter,
-                                  struct list_head *head)
-{
-        list_for_each_entry_continue_reverse(iter, head, list) {
-                if (iter->timestamp < new->timestamp) {
-                        list_add(&new->list, &iter->list);
-                        return;
-                }
-        }
-
-        list_add(&new->list, head);
-}
-
-static void __queue_sample_after(struct sample_queue *new,
-                                 struct sample_queue *iter,
-                                 struct list_head *head)
-{
-        list_for_each_entry_continue(iter, head, list) {
-                if (iter->timestamp > new->timestamp) {
-                        list_add_tail(&new->list, &iter->list);
-                        return;
-                }
-        }
-        list_add_tail(&new->list, head);
-}
-
 /* The queue is ordered by time */
-static void __queue_sample_event(struct sample_queue *new,
-                                 struct perf_session *s)
+static void __queue_event(struct sample_queue *new, struct perf_session *s)
 {
-        struct sample_queue *last_inserted = s->ordered_samples.last_inserted;
-        struct list_head *head = &s->ordered_samples.samples_head;
+        struct ordered_samples *os = &s->ordered_samples;
+        struct sample_queue *sample = os->last_sample;
+        u64 timestamp = new->timestamp;
+        struct list_head *p;
 
+        os->last_sample = new;
 
-        if (!last_inserted) {
-                __queue_sample_end(new, head);
+        if (!sample) {
+                list_add(&new->list, &os->samples);
+                os->max_timestamp = timestamp;
                 return;
         }
 
         /*
-         * Most of the time the current event has a timestamp
-         * very close to the last event inserted, unless we just switched
-         * to another event buffer. Having a sorting based on a list and
-         * on the last inserted event that is close to the current one is
-         * probably more efficient than an rbtree based sorting.
+         * last_sample might point to some random place in the list as it's
+         * the last queued event. We expect that the new event is close to
+         * this.
          */
-        if (last_inserted->timestamp >= new->timestamp)
-                __queue_sample_before(new, last_inserted, head);
-        else
-                __queue_sample_after(new, last_inserted, head);
+        if (sample->timestamp <= timestamp) {
+                while (sample->timestamp <= timestamp) {
+                        p = sample->list.next;
+                        if (p == &os->samples) {
+                                list_add_tail(&new->list, &os->samples);
+                                os->max_timestamp = timestamp;
+                                return;
+                        }
+                        sample = list_entry(p, struct sample_queue, list);
+                }
+                list_add_tail(&new->list, &sample->list);
+        } else {
+                while (sample->timestamp > timestamp) {
+                        p = sample->list.prev;
+                        if (p == &os->samples) {
+                                list_add(&new->list, &os->samples);
+                                return;
+                        }
+                        sample = list_entry(p, struct sample_queue, list);
+                }
+                list_add(&new->list, &sample->list);
+        }
 }
 
-static int queue_sample_event(event_t *event, struct sample_data *data,
-                              struct perf_session *s)
+#define MAX_SAMPLE_BUFFER       (64 * 1024 / sizeof(struct sample_queue))
+
+static int perf_session_queue_event(struct perf_session *s, union perf_event *event,
+                                    struct perf_sample *sample, u64 file_offset)
 {
-        u64 timestamp = data->time;
+        struct ordered_samples *os = &s->ordered_samples;
+        struct list_head *sc = &os->sample_cache;
+        u64 timestamp = sample->time;
         struct sample_queue *new;
 
+        if (!timestamp || timestamp == ~0ULL)
+                return -ETIME;
 
         if (timestamp < s->ordered_samples.last_flush) {
                 printf("Warning: Timestamp below last timeslice flush\n");
                 return -EINVAL;
         }
 
-        new = malloc(sizeof(*new));
-        if (!new)
-                return -ENOMEM;
+        if (!list_empty(sc)) {
+                new = list_entry(sc->next, struct sample_queue, list);
+                list_del(&new->list);
+        } else if (os->sample_buffer) {
+                new = os->sample_buffer + os->sample_buffer_idx;
+                if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
+                        os->sample_buffer = NULL;
+        } else {
+                os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
+                if (!os->sample_buffer)
+                        return -ENOMEM;
+                list_add(&os->sample_buffer->list, &os->to_free);
+                os->sample_buffer_idx = 2;
+                new = os->sample_buffer + 1;
+        }
 
         new->timestamp = timestamp;
+        new->file_offset = file_offset;
+        new->event = event;
 
-        new->event = malloc(event->header.size);
-        if (!new->event) {
-                free(new);
-                return -ENOMEM;
-        }
+        __queue_event(new, s);
 
-        memcpy(new->event, event, event->header.size);
+        return 0;
+}
 
-        __queue_sample_event(new, s);
-        s->ordered_samples.last_inserted = new;
+static void callchain__printf(struct perf_sample *sample)
+{
+        unsigned int i;
 
-        if (new->timestamp > s->ordered_samples.max_timestamp)
-                s->ordered_samples.max_timestamp = new->timestamp;
+        printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr);
 
-        return 0;
+        for (i = 0; i < sample->callchain->nr; i++)
+                printf("..... %2d: %016" PRIx64 "\n",
+                       i, sample->callchain->ips[i]);
 }
 
-static int perf_session__process_sample(event_t *event, struct perf_session *s,
-                                        struct perf_event_ops *ops)
+static void perf_session__print_tstamp(struct perf_session *session,
+                                       union perf_event *event,
+                                       struct perf_sample *sample)
 {
-        struct sample_data data;
+        if (event->header.type != PERF_RECORD_SAMPLE &&
+            !session->sample_id_all) {
+                fputs("-1 -1 ", stdout);
+                return;
+        }
 
-        if (!ops->ordered_samples)
-                return ops->sample(event, s);
+        if ((session->sample_type & PERF_SAMPLE_CPU))
+                printf("%u ", sample->cpu);
 
-        bzero(&data, sizeof(struct sample_data));
-        event__parse_sample(event, s->sample_type, &data);
+        if (session->sample_type & PERF_SAMPLE_TIME)
+                printf("%" PRIu64 " ", sample->time);
+}
 
-        queue_sample_event(event, &data, s);
+static void dump_event(struct perf_session *session, union perf_event *event,
+                       u64 file_offset, struct perf_sample *sample)
+{
+        if (!dump_trace)
+                return;
 
-        return 0;
+        printf("\n%#" PRIx64 " [%#x]: event: %d\n",
+               file_offset, event->header.size, event->header.type);
+
+        trace_event(event);
+
+        if (sample)
+                perf_session__print_tstamp(session, event, sample);
+
+        printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
+               event->header.size, perf_event__name(event->header.type));
 }
 
-static int perf_session__process_event(struct perf_session *self,
-                                       event_t *event,
-                                       struct perf_event_ops *ops,
-                                       u64 offset, u64 head)
+static void dump_sample(struct perf_session *session, union perf_event *event,
+                        struct perf_sample *sample)
 {
-        trace_event(event);
+        if (!dump_trace)
+                return;
 
-        if (event->header.type < PERF_RECORD_HEADER_MAX) {
-                dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
-                            offset + head, event->header.size,
-                            event__name[event->header.type]);
-                hists__inc_nr_events(&self->hists, event->header.type);
-        }
+        printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 "\n",
+               event->header.misc, sample->pid, sample->tid, sample->ip,
+               sample->period);
 
-        if (self->header.needs_swap && event__swap_ops[event->header.type])
-                event__swap_ops[event->header.type](event);
+        if (session->sample_type & PERF_SAMPLE_CALLCHAIN)
+                callchain__printf(sample);
+}
+
+static int perf_session_deliver_event(struct perf_session *session,
+                                      union perf_event *event,
+                                      struct perf_sample *sample,
+                                      struct perf_event_ops *ops,
+                                      u64 file_offset)
+{
+        struct perf_evsel *evsel;
+
+        dump_event(session, event, file_offset, sample);
 
         switch (event->header.type) {
         case PERF_RECORD_SAMPLE:
-                return perf_session__process_sample(event, self, ops);
+                dump_sample(session, event, sample);
+                evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+                if (evsel == NULL) {
+                        ++session->hists.stats.nr_unknown_id;
+                        return -1;
+                }
+                return ops->sample(event, sample, evsel, session);
         case PERF_RECORD_MMAP:
-                return ops->mmap(event, self);
+                return ops->mmap(event, sample, session);
         case PERF_RECORD_COMM:
-                return ops->comm(event, self);
+                return ops->comm(event, sample, session);
         case PERF_RECORD_FORK:
-                return ops->fork(event, self);
+                return ops->fork(event, sample, session);
         case PERF_RECORD_EXIT:
-                return ops->exit(event, self);
+                return ops->exit(event, sample, session);
         case PERF_RECORD_LOST:
-                return ops->lost(event, self);
+                return ops->lost(event, sample, session);
         case PERF_RECORD_READ:
-                return ops->read(event, self);
+                return ops->read(event, sample, session);
         case PERF_RECORD_THROTTLE:
-                return ops->throttle(event, self);
+                return ops->throttle(event, sample, session);
         case PERF_RECORD_UNTHROTTLE:
-                return ops->unthrottle(event, self);
+                return ops->unthrottle(event, sample, session);
+        default:
+                ++session->hists.stats.nr_unknown_events;
+                return -1;
+        }
+}
+
+static int perf_session__preprocess_sample(struct perf_session *session,
+                                           union perf_event *event, struct perf_sample *sample)
+{
+        if (event->header.type != PERF_RECORD_SAMPLE ||
+            !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+                return 0;
+
+        if (!ip_callchain__valid(sample->callchain, event)) {
+                pr_debug("call-chain problem with event, skipping it.\n");
+                ++session->hists.stats.nr_invalid_chains;
+                session->hists.stats.total_invalid_chains += sample->period;
+                return -EINVAL;
+        }
+        return 0;
+}
+
+static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
+                                            struct perf_event_ops *ops, u64 file_offset)
+{
+        dump_event(session, event, file_offset, NULL);
+
+        /* These events are processed right away */
+        switch (event->header.type) {
         case PERF_RECORD_HEADER_ATTR:
-                return ops->attr(event, self);
+                return ops->attr(event, session);
         case PERF_RECORD_HEADER_EVENT_TYPE:
-                return ops->event_type(event, self);
+                return ops->event_type(event, session);
         case PERF_RECORD_HEADER_TRACING_DATA:
                 /* setup for reading amidst mmap */
-                lseek(self->fd, offset + head, SEEK_SET);
-                return ops->tracing_data(event, self);
+                lseek(session->fd, file_offset, SEEK_SET);
+                return ops->tracing_data(event, session);
         case PERF_RECORD_HEADER_BUILD_ID:
-                return ops->build_id(event, self);
+                return ops->build_id(event, session);
         case PERF_RECORD_FINISHED_ROUND:
-                return ops->finished_round(event, self, ops);
+                return ops->finished_round(event, session, ops);
         default:
-                ++self->hists.stats.nr_unknown_events;
-                return -1;
+                return -EINVAL;
         }
 }
 
+static int perf_session__process_event(struct perf_session *session,
+                                       union perf_event *event,
+                                       struct perf_event_ops *ops,
+                                       u64 file_offset)
+{
+        struct perf_sample sample;
+        int ret;
+
+        if (session->header.needs_swap &&
+            perf_event__swap_ops[event->header.type])
+                perf_event__swap_ops[event->header.type](event);
+
+        if (event->header.type >= PERF_RECORD_HEADER_MAX)
+                return -EINVAL;
+
+        hists__inc_nr_events(&session->hists, event->header.type);
+
+        if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+                return perf_session__process_user_event(session, event, ops, file_offset);
+
+        /*
+         * For all kernel events we get the sample data
+         */
+        ret = perf_session__parse_sample(session, event, &sample);
+        if (ret)
+                return ret;
+
+        /* Preprocess sample records - precheck callchains */
+        if (perf_session__preprocess_sample(session, event, &sample))
+                return 0;
+
+        if (ops->ordered_samples) {
+                ret = perf_session_queue_event(session, event, &sample,
+                                               file_offset);
+                if (ret != -ETIME)
+                        return ret;
+        }
+
+        return perf_session_deliver_event(session, event, &sample, ops,
+                                          file_offset);
+}
+
 void perf_event_header__bswap(struct perf_event_header *self)
 {
         self->type = bswap_32(self->type);
@@ -656,21 +858,38 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
         return thread;
 }
 
-int do_read(int fd, void *buf, size_t size)
+static void perf_session__warn_about_errors(const struct perf_session *session,
+                                            const struct perf_event_ops *ops)
 {
-        void *buf_start = buf;
-
-        while (size) {
-                int ret = read(fd, buf, size);
+        if (ops->lost == perf_event__process_lost &&
+            session->hists.stats.total_lost != 0) {
+                ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64
+                            "!\n\nCheck IO/CPU overload!\n\n",
+                            session->hists.stats.total_period,
+                            session->hists.stats.total_lost);
+        }
 
-                if (ret <= 0)
-                        return ret;
+        if (session->hists.stats.nr_unknown_events != 0) {
+                ui__warning("Found %u unknown events!\n\n"
+                            "Is this an older tool processing a perf.data "
+                            "file generated by a more recent tool?\n\n"
+                            "If that is not the case, consider "
+                            "reporting to linux-kernel@vger.kernel.org.\n\n",
+                            session->hists.stats.nr_unknown_events);
+        }
 
-                size -= ret;
-                buf += ret;
+        if (session->hists.stats.nr_unknown_id != 0) {
+                ui__warning("%u samples with id not present in the header\n",
+                            session->hists.stats.nr_unknown_id);
         }
 
-        return buf - buf_start;
+        if (session->hists.stats.nr_invalid_chains != 0) {
+                ui__warning("Found invalid callchains!\n\n"
+                            "%u out of %u events were discarded for this reason.\n\n"
+                            "Consider reporting to linux-kernel@vger.kernel.org.\n\n",
+                            session->hists.stats.nr_invalid_chains,
+                            session->hists.stats.nr_events[PERF_RECORD_SAMPLE]);
+        }
 }
 
 #define session_done()  (*(volatile int *)(&session_done))
@@ -679,7 +898,7 @@ volatile int session_done;
 static int __perf_session__process_pipe_events(struct perf_session *self,
                                                struct perf_event_ops *ops)
 {
-        event_t event;
+        union perf_event event;
         uint32_t size;
         int skip = 0;
         u64 head;
@@ -690,7 +909,7 @@ static int __perf_session__process_pipe_events(struct perf_session *self,
 
         head = 0;
 more:
-        err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+        err = readn(self->fd, &event, sizeof(struct perf_event_header));
         if (err <= 0) {
                 if (err == 0)
                         goto done;
@@ -710,8 +929,7 @@ more:
         p += sizeof(struct perf_event_header);
 
         if (size - sizeof(struct perf_event_header)) {
-                err = do_read(self->fd, p,
-                              size - sizeof(struct perf_event_header));
+                err = readn(self->fd, p, size - sizeof(struct perf_event_header));
                 if (err <= 0) {
                         if (err == 0) {
                                 pr_err("unexpected end of event stream\n");
@@ -724,9 +942,8 @@ more:
         }
 
         if (size == 0 ||
-            (skip = perf_session__process_event(self, &event, ops,
-                                                0, head)) < 0) {
-                dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+            (skip = perf_session__process_event(self, &event, ops, head)) < 0) {
+                dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n",
                             head, event.header.size, event.header.type);
                 /*
                  * assume we lost track of the stream, check alignment, and
@@ -740,9 +957,6 @@ more:
 
         head += size;
 
-        dump_printf("\n%#Lx [%#x]: event: %d\n",
-                    head, event.header.size, event.header.type);
-
         if (skip > 0)
                 head += skip;
 
@@ -751,82 +965,108 @@ more:
 done:
         err = 0;
 out_err:
+        perf_session__warn_about_errors(self, ops);
+        perf_session_free_sample_buffers(self);
         return err;
 }
 
-int __perf_session__process_events(struct perf_session *self,
+static union perf_event *
+fetch_mmaped_event(struct perf_session *session,
+                   u64 head, size_t mmap_size, char *buf)
+{
+        union perf_event *event;
+
+        /*
+         * Ensure we have enough space remaining to read
+         * the size of the event in the headers.
+         */
+        if (head + sizeof(event->header) > mmap_size)
+                return NULL;
+
+        event = (union perf_event *)(buf + head);
+
+        if (session->header.needs_swap)
+                perf_event_header__bswap(&event->header);
+
+        if (head + event->header.size > mmap_size)
+                return NULL;
+
+        return event;
+}
+
+int __perf_session__process_events(struct perf_session *session,
                                    u64 data_offset, u64 data_size,
                                    u64 file_size, struct perf_event_ops *ops)
 {
-        int err, mmap_prot, mmap_flags;
-        u64 head, shift;
-        u64 offset = 0;
-        size_t  page_size;
-        event_t *event;
+        u64 head, page_offset, file_offset, file_pos, progress_next;
+        int err, mmap_prot, mmap_flags, map_idx = 0;
+        struct ui_progress *progress;
+        size_t  page_size, mmap_size;
+        char *buf, *mmaps[8];
+        union perf_event *event;
         uint32_t size;
-        char *buf;
-        struct ui_progress *progress = ui_progress__new("Processing events...",
-                                                        self->size);
-        if (progress == NULL)
-                return -1;
 
         perf_event_ops__fill_defaults(ops);
 
         page_size = sysconf(_SC_PAGESIZE);
 
-        head = data_offset;
-        shift = page_size * (head / page_size);
-        offset += shift;
-        head -= shift;
+        page_offset = page_size * (data_offset / page_size);
+        file_offset = page_offset;
+        head = data_offset - page_offset;
+
+        if (data_offset + data_size < file_size)
+                file_size = data_offset + data_size;
+
+        progress_next = file_size / 16;
+        progress = ui_progress__new("Processing events...", file_size);
+        if (progress == NULL)
+                return -1;
+
+        mmap_size = session->mmap_window;
+        if (mmap_size > file_size)
+                mmap_size = file_size;
+
+        memset(mmaps, 0, sizeof(mmaps));
 
         mmap_prot  = PROT_READ;
         mmap_flags = MAP_SHARED;
 
-        if (self->header.needs_swap) {
+        if (session->header.needs_swap) {
                 mmap_prot  |= PROT_WRITE;
                 mmap_flags = MAP_PRIVATE;
         }
 remap:
-        buf = mmap(NULL, page_size * self->mmap_window, mmap_prot,
-                   mmap_flags, self->fd, offset);
+        buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd,
+                   file_offset);
         if (buf == MAP_FAILED) {
                 pr_err("failed to mmap file\n");
                 err = -errno;
                 goto out_err;
         }
+        mmaps[map_idx] = buf;
+        map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
+        file_pos = file_offset + head;
 
 more:
-        event = (event_t *)(buf + head);
-        ui_progress__update(progress, offset);
-
-        if (self->header.needs_swap)
-                perf_event_header__bswap(&event->header);
-        size = event->header.size;
-        if (size == 0)
-                size = 8;
-
-        if (head + event->header.size >= page_size * self->mmap_window) {
-                int munmap_ret;
-
-                shift = page_size * (head / page_size);
-
-                munmap_ret = munmap(buf, page_size * self->mmap_window);
-                assert(munmap_ret == 0);
+        event = fetch_mmaped_event(session, head, mmap_size, buf);
+        if (!event) {
+                if (mmaps[map_idx]) {
+                        munmap(mmaps[map_idx], mmap_size);
+                        mmaps[map_idx] = NULL;
+                }
 
-                offset += shift;
-                head -= shift;
+                page_offset = page_size * (head / page_size);
+                file_offset += page_offset;
+                head -= page_offset;
                 goto remap;
         }
 
         size = event->header.size;
 
-        dump_printf("\n%#Lx [%#x]: event: %d\n",
-                    offset + head, event->header.size, event->header.type);
-
         if (size == 0 ||
-            perf_session__process_event(self, event, ops, offset, head) < 0) {
-                dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
-                            offset + head, event->header.size,
+            perf_session__process_event(session, event, ops, file_pos) < 0) {
+                dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n",
+                            file_offset + head, event->header.size,
                             event->header.type);
                 /*
                  * assume we lost track of the stream, check alignment, and
@@ -839,19 +1079,24 @@ more:
         }
 
         head += size;
+        file_pos += size;
 
-        if (offset + head >= data_offset + data_size)
-                goto done;
+        if (file_pos >= progress_next) {
+                progress_next += file_size / 16;
+                ui_progress__update(progress, file_pos);
+        }
 
-        if (offset + head < file_size)
+        if (file_pos < file_size)
                 goto more;
-done:
+
         err = 0;
         /* do the final flush for ordered samples */
-        self->ordered_samples.next_flush = ULLONG_MAX;
-        flush_sample_queue(self, ops);
+        session->ordered_samples.next_flush = ULLONG_MAX;
+        flush_sample_queue(session, ops);
 out_err:
         ui_progress__delete(progress);
+        perf_session__warn_about_errors(session, ops);
+        perf_session_free_sample_buffers(session);
         return err;
 }
 
@@ -929,3 +1174,91 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp,
         size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits);
         return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits);
 }
+
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
+{
+        struct perf_evsel *pos;
+        size_t ret = fprintf(fp, "Aggregated stats:\n");
+
+        ret += hists__fprintf_nr_events(&session->hists, fp);
+
+        list_for_each_entry(pos, &session->evlist->entries, node) {
+                ret += fprintf(fp, "%s stats:\n", event_name(pos));
+                ret += hists__fprintf_nr_events(&pos->hists, fp);
+        }
+
+        return ret;
+}
+
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+                                              unsigned int type)
+{
+        struct perf_evsel *pos;
+
+        list_for_each_entry(pos, &session->evlist->entries, node) {
+                if (pos->attr.type == type)
+                        return pos;
+        }
+        return NULL;
+}
+
+void perf_session__print_symbols(union perf_event *event,
+                                struct perf_sample *sample,
+                                struct perf_session *session)
+{
+        struct addr_location al;
+        const char *symname, *dsoname;
+        struct callchain_cursor *cursor = &session->callchain_cursor;
+        struct callchain_cursor_node *node;
+
+        if (perf_event__preprocess_sample(event, session, &al, sample,
+                                          NULL) < 0) {
+                error("problem processing %d event, skipping it.\n",
+                        event->header.type);
+                return;
+        }
+
+        if (symbol_conf.use_callchain && sample->callchain) {
+
+                if (perf_session__resolve_callchain(session, al.thread,
+                                                sample->callchain, NULL) != 0) {
+                        if (verbose)
+                                error("Failed to resolve callchain. Skipping\n");
+                        return;
+                }
+                callchain_cursor_commit(cursor);
+
+                while (1) {
+                        node = callchain_cursor_current(cursor);
+                        if (!node)
+                                break;
+
+                        if (node->sym && node->sym->name)
+                                symname = node->sym->name;
+                        else
+                                symname = "";
+
+                        if (node->map && node->map->dso && node->map->dso->name)
+                                dsoname = node->map->dso->name;
+                        else
+                                dsoname = "";
+
+                        printf("\t%16" PRIx64 " %s (%s)\n", node->ip, symname, dsoname);
+
+                        callchain_cursor_advance(cursor);
+                }
+
+        } else {
+                if (al.sym && al.sym->name)
+                        symname = al.sym->name;
+                else
+                        symname = "";
+
+                if (al.map && al.map->dso && al.map->dso->name)
+                        dsoname = al.map->dso->name;
+                else
+                        dsoname = "";
+
+                printf("%16" PRIx64 " %s (%s)", al.addr, symname, dsoname);
+        }
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9fa0fc2a863f..66d4e1490879 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -17,8 +17,12 @@ struct ordered_samples {
         u64                     last_flush;
         u64                     next_flush;
         u64                     max_timestamp;
-        struct list_head        samples_head;
-        struct sample_queue     *last_inserted;
+        struct list_head        samples;
+        struct list_head        sample_cache;
+        struct list_head        to_free;
+        struct sample_queue     *sample_buffer;
+        struct sample_queue     *last_sample;
+        int                     sample_buffer_idx;
 };
 
 struct perf_session {
@@ -30,49 +34,62 @@ struct perf_session {
         struct thread           *last_match;
         struct machine          host_machine;
         struct rb_root          machines;
-        struct rb_root          hists_tree;
+        struct perf_evlist      *evlist;
         /*
-         * FIXME: should point to the first entry in hists_tree and
-         *        be a hists instance. Right now its only 'report'
-         *        that is using ->hists_tree while all the rest use
-         *        ->hists.
+         * FIXME: Need to split this up further, we need global
+         *        stats + per event stats. 'perf diff' also needs
+         *        to properly support multiple events in a single
+         *        perf.data file.
          */
         struct hists            hists;
         u64                     sample_type;
+        int                     sample_size;
         int                     fd;
         bool                    fd_pipe;
         bool                    repipe;
+        bool                    sample_id_all;
+        u16                     id_hdr_size;
         int                     cwdlen;
         char                    *cwd;
         struct ordered_samples  ordered_samples;
-        char filename[0];
+        struct callchain_cursor callchain_cursor;
+        char                    filename[0];
 };
 
+struct perf_evsel;
 struct perf_event_ops;
 
-typedef int (*event_op)(event_t *self, struct perf_session *session);
-typedef int (*event_op2)(event_t *self, struct perf_session *session,
+typedef int (*event_sample)(union perf_event *event, struct perf_sample *sample,
+                            struct perf_evsel *evsel, struct perf_session *session);
+typedef int (*event_op)(union perf_event *self, struct perf_sample *sample,
+                        struct perf_session *session);
+typedef int (*event_synth_op)(union perf_event *self,
+                              struct perf_session *session);
+typedef int (*event_op2)(union perf_event *self, struct perf_session *session,
                          struct perf_event_ops *ops);
 
 struct perf_event_ops {
-        event_op        sample,
-                        mmap,
+        event_sample    sample;
+        event_op        mmap,
                         comm,
                         fork,
                         exit,
                         lost,
                         read,
                         throttle,
-                        unthrottle,
-                        attr,
+                        unthrottle;
+        event_synth_op  attr,
                         event_type,
                         tracing_data,
                         build_id;
         event_op2       finished_round;
         bool            ordered_samples;
+        bool            ordering_requires_timestamps;
 };
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe);
+struct perf_session *perf_session__new(const char *filename, int mode,
+                                       bool force, bool repipe,
+                                       struct perf_event_ops *ops);
 void perf_session__delete(struct perf_session *self);
 
 void perf_event_header__bswap(struct perf_event_header *self);
@@ -83,10 +100,10 @@ int __perf_session__process_events(struct perf_session *self,
 int perf_session__process_events(struct perf_session *self,
                                  struct perf_event_ops *event_ops);
 
-struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
-                                                   struct thread *thread,
-                                                   struct ip_callchain *chain,
-                                                   struct symbol **parent);
+int perf_session__resolve_callchain(struct perf_session *self,
+                                    struct thread *thread,
+                                    struct ip_callchain *chain,
+                                    struct symbol **parent);
 
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
@@ -98,7 +115,6 @@ void mem_bswap_64(void *src, int byte_size);
 
 int perf_session__create_kernel_maps(struct perf_session *self);
 
-int do_read(int fd, void *buf, size_t size);
 void perf_session__update_sample_type(struct perf_session *self);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
@@ -137,9 +153,22 @@ size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
 size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
                                           FILE *fp, bool with_hits);
 
-static inline
-size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp)
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
+
+static inline int perf_session__parse_sample(struct perf_session *session,
+                                             const union perf_event *event,
+                                             struct perf_sample *sample)
 {
-        return hists__fprintf_nr_events(&self->hists, fp);
+        return perf_event__parse_sample(event, session->sample_type,
+                                        session->sample_size,
+                                        session->sample_id_all, sample);
 }
+
+struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
+                                            unsigned int type);
+
+void perf_session__print_symbols(union perf_event *event,
+                                 struct perf_sample *sample,
+                                 struct perf_session *session);
+
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
new file mode 100644
index 000000000000..bbc982f5dd8b
--- /dev/null
+++ b/tools/perf/util/setup.py
@@ -0,0 +1,24 @@
+#!/usr/bin/python2
+
+from distutils.core import setup, Extension
+from os import getenv
+
+cflags = ['-fno-strict-aliasing', '-Wno-write-strings']
+cflags += getenv('CFLAGS', '').split()
+
+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'],
+                  include_dirs = ['util/include'],
+                  extra_compile_args = cflags,
+                 )
+
+setup(name='perf',
+      version='0.1',
+      description='Interface with the Linux profiling infrastructure',
+      author='Arnaldo Carvalho de Melo',
+      author_email='acme@redhat.com',
+      license='GPLv2',
+      url='http://perf.wiki.kernel.org',
+      ext_modules=[perf])
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b62a553cc67d..f44fa541d56e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -170,7 +170,7 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf,
                 return repsep_snprintf(bf, size, "%-*s", width, dso_name);
         }
 
-        return repsep_snprintf(bf, size, "%*Lx", width, self->ip);
+        return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
 }
 
 /* --sort symbol */
@@ -196,7 +196,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
 
         if (verbose) {
                 char o = self->ms.map ? dso__symtab_origin(self->ms.map->dso) : '!';
-                ret += repsep_snprintf(bf, size, "%*Lx %c ",
+                ret += repsep_snprintf(bf, size, "%-#*llx %c ",
                                        BITS_PER_LONG / 4, self->ip, o);
         }
 
@@ -205,7 +205,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf,
                 ret += repsep_snprintf(bf + ret, size - ret, "%s",
                                        self->ms.sym->name);
         else
-                ret += repsep_snprintf(bf + ret, size - ret, "%*Lx",
+                ret += repsep_snprintf(bf + ret, size - ret, "%-#*llx",
                                        BITS_PER_LONG / 4, self->ip);
 
         return ret;
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 46e531d09e8b..0b91053a7d11 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -70,7 +70,7 @@ struct hist_entry {
                 struct hist_entry *pair;
                 struct rb_root    sorted_chain;
         };
-        struct callchain_node   callchain[0];
+        struct callchain_root   callchain[0];
 };
 
 enum sort_type {
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
new file mode 100644
index 000000000000..834c8ebfe38e
--- /dev/null
+++ b/tools/perf/util/strfilter.c
@@ -0,0 +1,199 @@
+#include "util.h"
+#include "string.h"
+#include "strfilter.h"
+
+/* Operators */
+static const char *OP_and       = "&";  /* Logical AND */
+static const char *OP_or        = "|";  /* Logical OR */
+static const char *OP_not       = "!";  /* Logical NOT */
+
+#define is_operator(c)  ((c) == '|' || (c) == '&' || (c) == '!')
+#define is_separator(c) (is_operator(c) || (c) == '(' || (c) == ')')
+
+static void strfilter_node__delete(struct strfilter_node *self)
+{
+        if (self) {
+                if (self->p && !is_operator(*self->p))
+                        free((char *)self->p);
+                strfilter_node__delete(self->l);
+                strfilter_node__delete(self->r);
+                free(self);
+        }
+}
+
+void strfilter__delete(struct strfilter *self)
+{
+        if (self) {
+                strfilter_node__delete(self->root);
+                free(self);
+        }
+}
+
+static const char *get_token(const char *s, const char **e)
+{
+        const char *p;
+
+        while (isspace(*s))     /* Skip spaces */
+                s++;
+
+        if (*s == '\0') {
+                p = s;
+                goto end;
+        }
+
+        p = s + 1;
+        if (!is_separator(*s)) {
+                /* End search */
+retry:
+                while (*p && !is_separator(*p) && !isspace(*p))
+                        p++;
+                /* Escape and special case: '!' is also used in glob pattern */
+                if (*(p - 1) == '\\' || (*p == '!' && *(p - 1) == '[')) {
+                        p++;
+                        goto retry;
+                }
+        }
+end:
+        *e = p;
+        return s;
+}
+
+static struct strfilter_node *strfilter_node__alloc(const char *op,
+                                                    struct strfilter_node *l,
+                                                    struct strfilter_node *r)
+{
+        struct strfilter_node *ret = zalloc(sizeof(struct strfilter_node));
+
+        if (ret) {
+                ret->p = op;
+                ret->l = l;
+                ret->r = r;
+        }
+
+        return ret;
+}
+
+static struct strfilter_node *strfilter_node__new(const char *s,
+                                                  const char **ep)
+{
+        struct strfilter_node root, *cur, *last_op;
+        const char *e;
+
+        if (!s)
+                return NULL;
+
+        memset(&root, 0, sizeof(root));
+        last_op = cur = &root;
+
+        s = get_token(s, &e);
+        while (*s != '\0' && *s != ')') {
+                switch (*s) {
+                case '&':       /* Exchg last OP->r with AND */
+                        if (!cur->r || !last_op->r)
+                                goto error;
+                        cur = strfilter_node__alloc(OP_and, last_op->r, NULL);
+                        if (!cur)
+                                goto nomem;
+                        last_op->r = cur;
+                        last_op = cur;
+                        break;
+                case '|':       /* Exchg the root with OR */
+                        if (!cur->r || !root.r)
+                                goto error;
+                        cur = strfilter_node__alloc(OP_or, root.r, NULL);
+                        if (!cur)
+                                goto nomem;
+                        root.r = cur;
+                        last_op = cur;
+                        break;
+                case '!':       /* Add NOT as a leaf node */
+                        if (cur->r)
+                                goto error;
+                        cur->r = strfilter_node__alloc(OP_not, NULL, NULL);
+                        if (!cur->r)
+                                goto nomem;
+                        cur = cur->r;
+                        break;
+                case '(':       /* Recursively parses inside the parenthesis */
+                        if (cur->r)
+                                goto error;
+                        cur->r = strfilter_node__new(s + 1, &s);
+                        if (!s)
+                                goto nomem;
+                        if (!cur->r || *s != ')')
+                                goto error;
+                        e = s + 1;
+                        break;
+                default:
+                        if (cur->r)
+                                goto error;
+                        cur->r = strfilter_node__alloc(NULL, NULL, NULL);
+                        if (!cur->r)
+                                goto nomem;
+                        cur->r->p = strndup(s, e - s);
+                        if (!cur->r->p)
+                                goto nomem;
+                }
+                s = get_token(e, &e);
+        }
+        if (!cur->r)
+                goto error;
+        *ep = s;
+        return root.r;
+nomem:
+        s = NULL;
+error:
+        *ep = s;
+        strfilter_node__delete(root.r);
+        return NULL;
+}
+
+/*
+ * Parse filter rule and return new strfilter.
+ * Return NULL if fail, and *ep == NULL if memory allocation failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err)
+{
+        struct strfilter *ret = zalloc(sizeof(struct strfilter));
+        const char *ep = NULL;
+
+        if (ret)
+                ret->root = strfilter_node__new(rules, &ep);
+
+        if (!ret || !ret->root || *ep != '\0') {
+                if (err)
+                        *err = ep;
+                strfilter__delete(ret);
+                ret = NULL;
+        }
+
+        return ret;
+}
+
+static bool strfilter_node__compare(struct strfilter_node *self,
+                                    const char *str)
+{
+        if (!self || !self->p)
+                return false;
+
+        switch (*self->p) {
+        case '|':       /* OR */
+                return strfilter_node__compare(self->l, str) ||
+                        strfilter_node__compare(self->r, str);
+        case '&':       /* AND */
+                return strfilter_node__compare(self->l, str) &&
+                        strfilter_node__compare(self->r, str);
+        case '!':       /* NOT */
+                return !strfilter_node__compare(self->r, str);
+        default:
+                return strglobmatch(str, self->p);
+        }
+}
+
+/* Return true if STR matches the filter rules */
+bool strfilter__compare(struct strfilter *self, const char *str)
+{
+        if (!self)
+                return false;
+        return strfilter_node__compare(self->root, str);
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
new file mode 100644
index 000000000000..00f58a7506de
--- /dev/null
+++ b/tools/perf/util/strfilter.h
@@ -0,0 +1,48 @@
+#ifndef __PERF_STRFILTER_H
+#define __PERF_STRFILTER_H
+/* General purpose glob matching filter */
+
+#include <linux/list.h>
+#include <stdbool.h>
+
+/* A node of string filter */
+struct strfilter_node {
+        struct strfilter_node *l;       /* Tree left branche (for &,|) */
+        struct strfilter_node *r;       /* Tree right branche (for !,&,|) */
+        const char *p;          /* Operator or rule */
+};
+
+/* String filter */
+struct strfilter {
+        struct strfilter_node *root;
+};
+
+/**
+ * strfilter__new - Create a new string filter
+ * @rules: Filter rule, which is a combination of glob expressions.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and return new strfilter. Return NULL if an error detected.
+ * In that case, *@err will indicate where it is detected, and *@err is NULL
+ * if a memory allocation is failed.
+ */
+struct strfilter *strfilter__new(const char *rules, const char **err);
+
+/**
+ * strfilter__compare - compare given string and a string filter
+ * @self: String filter
+ * @str: target string
+ *
+ * Compare @str and @self. Return true if the str match the rule
+ */
+bool strfilter__compare(struct strfilter *self, const char *str);
+
+/**
+ * strfilter__delete - delete a string filter
+ * @self: String filter to delete
+ *
+ * Delete @self.
+ */
+void strfilter__delete(struct strfilter *self);
+
+#endif
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 0409fc7c0058..b9a985dadd08 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -85,7 +85,7 @@ out:
 
 /*
  * Helper function for splitting a string into an argv-like array.
- * originaly copied from lib/argv_split.c
+ * originally copied from lib/argv_split.c
  */
 static const char *skip_sep(const char *cp)
 {
@@ -259,7 +259,7 @@ static bool __match_glob(const char *str, const char *pat, bool ignore_space)
                 if (!*pat)      /* Tail wild card matches all */
                         return true;
                 while (*str)
-                        if (strglobmatch(str++, pat))
+                        if (__match_glob(str++, pat, ignore_space))
                                 return true;
         }
         return !*str && !*pat;
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index b3637db025a2..96c866045d60 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -12,6 +12,7 @@
  * of the License.
  */
 
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -43,11 +44,11 @@ static double cpu2y(int cpu)
         return cpu2slot(cpu) * SLOT_MULT;
 }
 
-static double time2pixels(u64 time)
+static double time2pixels(u64 __time)
 {
         double X;
 
-        X = 1.0 * svg_page_width * (time - first_time) / (last_time - first_time);
+        X = 1.0 * svg_page_width * (__time - first_time) / (last_time - first_time);
         return X;
 }
 
@@ -94,7 +95,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
         total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
         fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
-        fprintf(svgfile, "<svg width=\"%i\" height=\"%llu\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
+        fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
         fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
 
@@ -455,9 +456,9 @@ void svg_legenda(void)
                 return;
 
         svg_legenda_box(0,      "Running", "sample");
-        svg_legenda_box(100,    "Idle","rect.c1");
-        svg_legenda_box(200,    "Deeper Idle", "rect.c3");
-        svg_legenda_box(350,    "Deepest Idle", "rect.c6");
+        svg_legenda_box(100,    "Idle","c1");
+        svg_legenda_box(200,    "Deeper Idle", "c3");
+        svg_legenda_box(350,    "Deepest Idle", "c6");
         svg_legenda_box(550,    "Sleeping", "process2");
         svg_legenda_box(650,    "Waiting for cpu", "waiting");
         svg_legenda_box(800,    "Blocked on IO", "blocked");
@@ -483,7 +484,7 @@ void svg_time_grid(void)
                         color = 128;
                 }
 
-                fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%llu\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
+                fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
                         time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness);
 
                 i += 10000000;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b2f5ae97f33d..eec196329fd9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -11,6 +11,7 @@
 #include <sys/param.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <inttypes.h>
 #include "build-id.h"
 #include "debug.h"
 #include "symbol.h"
@@ -22,17 +23,21 @@
 #include <limits.h>
 #include <sys/utsname.h>
 
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 128
+#endif
+
 #ifndef NT_GNU_BUILD_ID
 #define NT_GNU_BUILD_ID 3
 #endif
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id);
+static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
 static int elf_read_build_id(Elf *elf, void *bf, size_t size);
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
                                 symbol_filter_t filter);
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
                         symbol_filter_t filter);
 static int vmlinux_path__nr_entries;
 static char **vmlinux_path;
@@ -41,29 +46,30 @@ struct symbol_conf symbol_conf = {
         .exclude_other    = true,
         .use_modules      = true,
         .try_vmlinux_path = true,
+        .symfs            = "",
 };
 
-int dso__name_len(const struct dso *self)
+int dso__name_len(const struct dso *dso)
 {
         if (verbose)
-                return self->long_name_len;
+                return dso->long_name_len;
 
-        return self->short_name_len;
+        return dso->short_name_len;
 }
 
-bool dso__loaded(const struct dso *self, enum map_type type)
+bool dso__loaded(const struct dso *dso, enum map_type type)
 {
-        return self->loaded & (1 << type);
+        return dso->loaded & (1 << type);
 }
 
-bool dso__sorted_by_name(const struct dso *self, enum map_type type)
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
 {
-        return self->sorted_by_name & (1 << type);
+        return dso->sorted_by_name & (1 << type);
 }
 
-static void dso__set_sorted_by_name(struct dso *self, enum map_type type)
+static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
 {
-        self->sorted_by_name |= (1 << type);
+        dso->sorted_by_name |= (1 << type);
 }
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
@@ -78,9 +84,9 @@ bool symbol_type__is_a(char symbol_type, enum map_type map_type)
         }
 }
 
-static void symbols__fixup_end(struct rb_root *self)
+static void symbols__fixup_end(struct rb_root *symbols)
 {
-        struct rb_node *nd, *prevnd = rb_first(self);
+        struct rb_node *nd, *prevnd = rb_first(symbols);
         struct symbol *curr, *prev;
 
         if (prevnd == NULL)
@@ -92,7 +98,7 @@ static void symbols__fixup_end(struct rb_root *self)
                 prev = curr;
                 curr = rb_entry(nd, struct symbol, rb_node);
 
-                if (prev->end == prev->start)
+                if (prev->end == prev->start && prev->end != curr->start)
                         prev->end = curr->start - 1;
         }
 
@@ -101,10 +107,10 @@ static void symbols__fixup_end(struct rb_root *self)
                 curr->end = roundup(curr->start, 4096);
 }
 
-static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
+static void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
         struct map *prev, *curr;
-        struct rb_node *nd, *prevnd = rb_first(&self->maps[type]);
+        struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
 
         if (prevnd == NULL)
                 return;
@@ -121,132 +127,131 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
          * We still haven't the actual symbols, so guess the
          * last map final address.
          */
-        curr->end = ~0UL;
+        curr->end = ~0ULL;
 }
 
-static void map_groups__fixup_end(struct map_groups *self)
+static void map_groups__fixup_end(struct map_groups *mg)
 {
         int i;
         for (i = 0; i < MAP__NR_TYPES; ++i)
-                __map_groups__fixup_end(self, i);
+                __map_groups__fixup_end(mg, i);
 }
 
 static struct symbol *symbol__new(u64 start, u64 len, u8 binding,
                                   const char *name)
 {
         size_t namelen = strlen(name) + 1;
-        struct symbol *self = calloc(1, (symbol_conf.priv_size +
-                                         sizeof(*self) + namelen));
-        if (self == NULL)
+        struct symbol *sym = calloc(1, (symbol_conf.priv_size +
+                                        sizeof(*sym) + namelen));
+        if (sym == NULL)
                 return NULL;
 
         if (symbol_conf.priv_size)
-                self = ((void *)self) + symbol_conf.priv_size;
-
-        self->start   = start;
-        self->end     = len ? start + len - 1 : start;
-        self->binding = binding;
-        self->namelen = namelen - 1;
+                sym = ((void *)sym) + symbol_conf.priv_size;
 
-        pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
+        sym->start   = start;
+        sym->end     = len ? start + len - 1 : start;
+        sym->binding = binding;
+        sym->namelen = namelen - 1;
 
-        memcpy(self->name, name, namelen);
+        pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n",
+                  __func__, name, start, sym->end);
+        memcpy(sym->name, name, namelen);
 
-        return self;
+        return sym;
 }
 
-void symbol__delete(struct symbol *self)
+void symbol__delete(struct symbol *sym)
 {
-        free(((void *)self) - symbol_conf.priv_size);
+        free(((void *)sym) - symbol_conf.priv_size);
 }
 
-static size_t symbol__fprintf(struct symbol *self, FILE *fp)
+static size_t symbol__fprintf(struct symbol *sym, FILE *fp)
 {
-        return fprintf(fp, " %llx-%llx %c %s\n",
-                       self->start, self->end,
-                       self->binding == STB_GLOBAL ? 'g' :
-                       self->binding == STB_LOCAL  ? 'l' : 'w',
-                       self->name);
+        return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
+                       sym->start, sym->end,
+                       sym->binding == STB_GLOBAL ? 'g' :
+                       sym->binding == STB_LOCAL  ? 'l' : 'w',
+                       sym->name);
 }
 
-void dso__set_long_name(struct dso *self, char *name)
+void dso__set_long_name(struct dso *dso, char *name)
 {
         if (name == NULL)
                 return;
-        self->long_name = name;
-        self->long_name_len = strlen(name);
+        dso->long_name = name;
+        dso->long_name_len = strlen(name);
 }
 
-static void dso__set_short_name(struct dso *self, const char *name)
+static void dso__set_short_name(struct dso *dso, const char *name)
 {
         if (name == NULL)
                 return;
-        self->short_name = name;
-        self->short_name_len = strlen(name);
+        dso->short_name = name;
+        dso->short_name_len = strlen(name);
 }
 
-static void dso__set_basename(struct dso *self)
+static void dso__set_basename(struct dso *dso)
 {
-        dso__set_short_name(self, basename(self->long_name));
+        dso__set_short_name(dso, basename(dso->long_name));
 }
 
 struct dso *dso__new(const char *name)
 {
-        struct dso *self = calloc(1, sizeof(*self) + strlen(name) + 1);
+        struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
 
-        if (self != NULL) {
+        if (dso != NULL) {
                 int i;
-                strcpy(self->name, name);
-                dso__set_long_name(self, self->name);
-                dso__set_short_name(self, self->name);
+                strcpy(dso->name, name);
+                dso__set_long_name(dso, dso->name);
+                dso__set_short_name(dso, dso->name);
                 for (i = 0; i < MAP__NR_TYPES; ++i)
-                        self->symbols[i] = self->symbol_names[i] = RB_ROOT;
-                self->slen_calculated = 0;
-                self->origin = DSO__ORIG_NOT_FOUND;
-                self->loaded = 0;
-                self->sorted_by_name = 0;
-                self->has_build_id = 0;
-                self->kernel = DSO_TYPE_USER;
-                INIT_LIST_HEAD(&self->node);
+                        dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+                dso->symtab_type = SYMTAB__NOT_FOUND;
+                dso->loaded = 0;
+                dso->sorted_by_name = 0;
+                dso->has_build_id = 0;
+                dso->kernel = DSO_TYPE_USER;
+                INIT_LIST_HEAD(&dso->node);
         }
 
-        return self;
+        return dso;
 }
 
-static void symbols__delete(struct rb_root *self)
+static void symbols__delete(struct rb_root *symbols)
 {
         struct symbol *pos;
-        struct rb_node *next = rb_first(self);
+        struct rb_node *next = rb_first(symbols);
 
         while (next) {
                 pos = rb_entry(next, struct symbol, rb_node);
                 next = rb_next(&pos->rb_node);
-                rb_erase(&pos->rb_node, self);
+                rb_erase(&pos->rb_node, symbols);
                 symbol__delete(pos);
         }
 }
 
-void dso__delete(struct dso *self)
+void dso__delete(struct dso *dso)
 {
         int i;
         for (i = 0; i < MAP__NR_TYPES; ++i)
-                symbols__delete(&self->symbols[i]);
-        if (self->sname_alloc)
-                free((char *)self->short_name);
-        if (self->lname_alloc)
-                free(self->long_name);
-        free(self);
+                symbols__delete(&dso->symbols[i]);
+        if (dso->sname_alloc)
+                free((char *)dso->short_name);
+        if (dso->lname_alloc)
+                free(dso->long_name);
+        free(dso);
 }
 
-void dso__set_build_id(struct dso *self, void *build_id)
+void dso__set_build_id(struct dso *dso, void *build_id)
 {
-        memcpy(self->build_id, build_id, sizeof(self->build_id));
-        self->has_build_id = 1;
+        memcpy(dso->build_id, build_id, sizeof(dso->build_id));
+        dso->has_build_id = 1;
 }
 
-static void symbols__insert(struct rb_root *self, struct symbol *sym)
+static void symbols__insert(struct rb_root *symbols, struct symbol *sym)
 {
-        struct rb_node **p = &self->rb_node;
+        struct rb_node **p = &symbols->rb_node;
         struct rb_node *parent = NULL;
         const u64 ip = sym->start;
         struct symbol *s;
@@ -260,17 +265,17 @@ static void symbols__insert(struct rb_root *self, struct symbol *sym)
                         p = &(*p)->rb_right;
         }
         rb_link_node(&sym->rb_node, parent, p);
-        rb_insert_color(&sym->rb_node, self);
+        rb_insert_color(&sym->rb_node, symbols);
 }
 
-static struct symbol *symbols__find(struct rb_root *self, u64 ip)
+static struct symbol *symbols__find(struct rb_root *symbols, u64 ip)
 {
         struct rb_node *n;
 
-        if (self == NULL)
+        if (symbols == NULL)
                 return NULL;
 
-        n = self->rb_node;
+        n = symbols->rb_node;
 
         while (n) {
                 struct symbol *s = rb_entry(n, struct symbol, rb_node);
@@ -291,11 +296,13 @@ struct symbol_name_rb_node {
         struct symbol   sym;
 };
 
-static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
+static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym)
 {
-        struct rb_node **p = &self->rb_node;
+        struct rb_node **p = &symbols->rb_node;
         struct rb_node *parent = NULL;
-        struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s;
+        struct symbol_name_rb_node *symn, *s;
+
+        symn = container_of(sym, struct symbol_name_rb_node, sym);
 
         while (*p != NULL) {
                 parent = *p;
@@ -306,27 +313,29 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
                         p = &(*p)->rb_right;
         }
         rb_link_node(&symn->rb_node, parent, p);
-        rb_insert_color(&symn->rb_node, self);
+        rb_insert_color(&symn->rb_node, symbols);
 }
 
-static void symbols__sort_by_name(struct rb_root *self, struct rb_root *source)
+static void symbols__sort_by_name(struct rb_root *symbols,
+                                  struct rb_root *source)
 {
         struct rb_node *nd;
 
         for (nd = rb_first(source); nd; nd = rb_next(nd)) {
                 struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
-                symbols__insert_by_name(self, pos);
+                symbols__insert_by_name(symbols, pos);
         }
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root *self, const char *name)
+static struct symbol *symbols__find_by_name(struct rb_root *symbols,
+                                            const char *name)
 {
         struct rb_node *n;
 
-        if (self == NULL)
+        if (symbols == NULL)
                 return NULL;
 
-        n = self->rb_node;
+        n = symbols->rb_node;
 
         while (n) {
                 struct symbol_name_rb_node *s;
@@ -346,29 +355,29 @@ static struct symbol *symbols__find_by_name(struct rb_root *self, const char *na
         return NULL;
 }
 
-struct symbol *dso__find_symbol(struct dso *self,
+struct symbol *dso__find_symbol(struct dso *dso,
                                 enum map_type type, u64 addr)
 {
-        return symbols__find(&self->symbols[type], addr);
+        return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name)
 {
-        return symbols__find_by_name(&self->symbol_names[type], name);
+        return symbols__find_by_name(&dso->symbol_names[type], name);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type)
+void dso__sort_by_name(struct dso *dso, enum map_type type)
 {
-        dso__set_sorted_by_name(self, type);
-        return symbols__sort_by_name(&self->symbol_names[type],
-                                     &self->symbols[type]);
+        dso__set_sorted_by_name(dso, type);
+        return symbols__sort_by_name(&dso->symbol_names[type],
+                                     &dso->symbols[type]);
 }
 
-int build_id__sprintf(const u8 *self, int len, char *bf)
+int build_id__sprintf(const u8 *build_id, int len, char *bf)
 {
         char *bid = bf;
-        const u8 *raw = self;
+        const u8 *raw = build_id;
         int i;
 
         for (i = 0; i < len; ++i) {
@@ -377,29 +386,44 @@ int build_id__sprintf(const u8 *self, int len, char *bf)
                 bid += 2;
         }
 
-        return raw - self;
+        return raw - build_id;
 }
 
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp)
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 {
         char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-        build_id__sprintf(self->build_id, sizeof(self->build_id), sbuild_id);
+        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
         return fprintf(fp, "%s", sbuild_id);
 }
 
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+                                    enum map_type type, FILE *fp)
+{
+        size_t ret = 0;
+        struct rb_node *nd;
+        struct symbol_name_rb_node *pos;
+
+        for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
+                pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+                fprintf(fp, "%s\n", pos->sym.name);
+        }
+
+        return ret;
+}
+
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 {
         struct rb_node *nd;
-        size_t ret = fprintf(fp, "dso: %s (", self->short_name);
+        size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
 
-        if (self->short_name != self->long_name)
-                ret += fprintf(fp, "%s, ", self->long_name);
+        if (dso->short_name != dso->long_name)
+                ret += fprintf(fp, "%s, ", dso->long_name);
         ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-                       self->loaded ? "" : "NOT ");
-        ret += dso__fprintf_buildid(self, fp);
+                       dso->loaded ? "" : "NOT ");
+        ret += dso__fprintf_buildid(dso, fp);
         ret += fprintf(fp, ")\n");
-        for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
                 struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
                 ret += symbol__fprintf(pos, fp);
         }
@@ -409,16 +433,25 @@ size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
 
 int kallsyms__parse(const char *filename, void *arg,
                     int (*process_symbol)(void *arg, const char *name,
-                                                     char type, u64 start))
+                                          char type, u64 start, u64 end))
 {
         char *line = NULL;
         size_t n;
-        int err = 0;
+        int err = -1;
+        u64 prev_start = 0;
+        char prev_symbol_type = 0;
+        char *prev_symbol_name;
         FILE *file = fopen(filename, "r");
 
         if (file == NULL)
                 goto out_failure;
 
+        prev_symbol_name = malloc(KSYM_NAME_LEN);
+        if (prev_symbol_name == NULL)
+                goto out_close;
+
+        err = 0;
+
         while (!feof(file)) {
                 u64 start;
                 int line_len, len;
@@ -438,14 +471,33 @@ int kallsyms__parse(const char *filename, void *arg,
                         continue;
 
                 symbol_type = toupper(line[len]);
-                symbol_name = line + len + 2;
+                len += 2;
+                symbol_name = line + len;
+                len = line_len - len;
 
-                err = process_symbol(arg, symbol_name, symbol_type, start);
-                if (err)
+                if (len >= KSYM_NAME_LEN) {
+                        err = -1;
                         break;
+                }
+
+                if (prev_symbol_type) {
+                        u64 end = start;
+                        if (end != prev_start)
+                                --end;
+                        err = process_symbol(arg, prev_symbol_name,
+                                             prev_symbol_type, prev_start, end);
+                        if (err)
+                                break;
+                }
+
+                memcpy(prev_symbol_name, symbol_name, len + 1);
+                prev_symbol_type = symbol_type;
+                prev_start = start;
         }
 
+        free(prev_symbol_name);
         free(line);
+out_close:
         fclose(file);
         return err;
 
@@ -467,7 +519,7 @@ static u8 kallsyms2elf_type(char type)
 }
 
 static int map__process_kallsym_symbol(void *arg, const char *name,
-                                       char type, u64 start)
+                                       char type, u64 start, u64 end)
 {
         struct symbol *sym;
         struct process_kallsyms_args *a = arg;
@@ -476,11 +528,8 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
         if (!symbol_type__is_a(type, a->map->type))
                 return 0;
 
-        /*
-         * Will fix up the end later, when we have all symbols sorted.
-         */
-        sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
-
+        sym = symbol__new(start, end - start + 1,
+                          kallsyms2elf_type(type), name);
         if (sym == NULL)
                 return -ENOMEM;
         /*
@@ -497,10 +546,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
  * so that we can in the next step set the symbol ->end address and then
  * call kernel_maps__split_kallsyms.
  */
-static int dso__load_all_kallsyms(struct dso *self, const char *filename,
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
                                   struct map *map)
 {
-        struct process_kallsyms_args args = { .map = map, .dso = self, };
+        struct process_kallsyms_args args = { .map = map, .dso = dso, };
         return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
 }
 
@@ -509,15 +558,15 @@ static int dso__load_all_kallsyms(struct dso *self, const char *filename,
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *self, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map,
                                symbol_filter_t filter)
 {
         struct map_groups *kmaps = map__kmap(map)->kmaps;
         struct machine *machine = kmaps->machine;
         struct map *curr_map = map;
         struct symbol *pos;
-        int count = 0;
-        struct rb_root *root = &self->symbols[map->type];
+        int count = 0, moved = 0;       
+        struct rb_root *root = &dso->symbols[map->type];
         struct rb_node *next = rb_first(root);
         int kernel_range = 0;
 
@@ -536,7 +585,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 
                         if (strcmp(curr_map->dso->short_name, module)) {
                                 if (curr_map != map &&
-                                    self->kernel == DSO_TYPE_GUEST_KERNEL &&
+                                    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
                                     machine__is_default_guest(machine)) {
                                         /*
                                          * We assume all symbols of a module are
@@ -572,9 +621,14 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
                         pos->end   = curr_map->map_ip(curr_map, pos->end);
                 } else if (curr_map != map) {
                         char dso_name[PATH_MAX];
-                        struct dso *dso;
+                        struct dso *ndso;
 
-                        if (self->kernel == DSO_TYPE_GUEST_KERNEL)
+                        if (count == 0) {
+                                curr_map = map;
+                                goto filter_symbol;
+                        }
+
+                        if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
                                 snprintf(dso_name, sizeof(dso_name),
                                         "[guest.kernel].%d",
                                         kernel_range++);
@@ -583,15 +637,15 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
                                         "[kernel].%d",
                                         kernel_range++);
 
-                        dso = dso__new(dso_name);
-                        if (dso == NULL)
+                        ndso = dso__new(dso_name);
+                        if (ndso == NULL)
                                 return -1;
 
-                        dso->kernel = self->kernel;
+                        ndso->kernel = dso->kernel;
 
-                        curr_map = map__new2(pos->start, dso, map->type);
+                        curr_map = map__new2(pos->start, ndso, map->type);
                         if (curr_map == NULL) {
-                                dso__delete(dso);
+                                dso__delete(ndso);
                                 return -1;
                         }
 
@@ -599,7 +653,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
                         map_groups__insert(kmaps, curr_map);
                         ++kernel_range;
                 }
-
+filter_symbol:
                 if (filter && filter(curr_map, pos)) {
 discard_symbol:         rb_erase(&pos->rb_node, root);
                         symbol__delete(pos);
@@ -607,36 +661,57 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
                         if (curr_map != map) {
                                 rb_erase(&pos->rb_node, root);
                                 symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
-                        }
-                        count++;
+                                ++moved;
+                        } else
+                                ++count;
                 }
         }
 
         if (curr_map != map &&
-            self->kernel == DSO_TYPE_GUEST_KERNEL &&
+            dso->kernel == DSO_TYPE_GUEST_KERNEL &&
             machine__is_default_guest(kmaps->machine)) {
                 dso__set_loaded(curr_map->dso, curr_map->type);
         }
 
-        return count;
+        return count + moved;
 }
 
-int dso__load_kallsyms(struct dso *self, const char *filename,
+static bool symbol__restricted_filename(const char *filename,
+                                        const char *restricted_filename)
+{
+        bool restricted = false;
+
+        if (symbol_conf.kptr_restrict) {
+                char *r = realpath(filename, NULL);
+
+                if (r != NULL) {
+                        restricted = strcmp(r, restricted_filename) == 0;
+                        free(r);
+                        return restricted;
+                }
+        }
+
+        return restricted;
+}
+
+int dso__load_kallsyms(struct dso *dso, const char *filename,
                        struct map *map, symbol_filter_t filter)
 {
-        if (dso__load_all_kallsyms(self, filename, map) < 0)
+        if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+                return -1;
+
+        if (dso__load_all_kallsyms(dso, filename, map) < 0)
                 return -1;
 
-        symbols__fixup_end(&self->symbols[map->type]);
-        if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-                self->origin = DSO__ORIG_GUEST_KERNEL;
+        if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+                dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
         else
-                self->origin = DSO__ORIG_KERNEL;
+                dso->symtab_type = SYMTAB__KALLSYMS;
 
-        return dso__split_kallsyms(self, map, filter);
+        return dso__split_kallsyms(dso, map, filter);
 }
 
-static int dso__load_perf_map(struct dso *self, struct map *map,
+static int dso__load_perf_map(struct dso *dso, struct map *map,
                               symbol_filter_t filter)
 {
         char *line = NULL;
@@ -644,7 +719,7 @@ static int dso__load_perf_map(struct dso *self, struct map *map,
         FILE *file;
         int nr_syms = 0;
 
-        file = fopen(self->long_name, "r");
+        file = fopen(dso->long_name, "r");
         if (file == NULL)
                 goto out_failure;
 
@@ -682,7 +757,7 @@ static int dso__load_perf_map(struct dso *self, struct map *map,
                 if (filter && filter(map, sym))
                         symbol__delete(sym);
                 else {
-                        symbols__insert(&self->symbols[map->type], sym);
+                        symbols__insert(&dso->symbols[map->type], sym);
                         nr_syms++;
                 }
         }
@@ -701,7 +776,7 @@ out_failure:
 /**
  * elf_symtab__for_each_symbol - iterate thru all the symbols
  *
- * @self: struct elf_symtab instance to iterate
+ * @syms: struct elf_symtab instance to iterate
  * @idx: uint32_t idx
  * @sym: GElf_Sym iterator
  */
@@ -801,7 +876,7 @@ static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
+static int dso__synthesize_plt_symbols(struct  dso *dso, struct map *map,
                                        symbol_filter_t filter)
 {
         uint32_t nr_rel_entries, idx;
@@ -817,8 +892,11 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
         char sympltname[1024];
         Elf *elf;
         int nr = 0, symidx, fd, err = 0;
+        char name[PATH_MAX];
 
-        fd = open(self->long_name, O_RDONLY);
+        snprintf(name, sizeof(name), "%s%s",
+                 symbol_conf.symfs, dso->long_name);
+        fd = open(name, O_RDONLY);
         if (fd < 0)
                 goto out;
 
@@ -893,7 +971,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
                         if (filter && filter(map, f))
                                 symbol__delete(f);
                         else {
-                                symbols__insert(&self->symbols[map->type], f);
+                                symbols__insert(&dso->symbols[map->type], f);
                                 ++nr;
                         }
                 }
@@ -915,7 +993,7 @@ static int dso__synthesize_plt_symbols(struct  dso *self, struct map *map,
                         if (filter && filter(map, f))
                                 symbol__delete(f);
                         else {
-                                symbols__insert(&self->symbols[map->type], f);
+                                symbols__insert(&dso->symbols[map->type], f);
                                 ++nr;
                         }
                 }
@@ -931,29 +1009,30 @@ out_close:
                 return nr;
 out:
         pr_debug("%s: problems reading %s PLT info.\n",
-                 __func__, self->long_name);
+                 __func__, dso->long_name);
         return 0;
 }
 
-static bool elf_sym__is_a(GElf_Sym *self, enum map_type type)
+static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
 {
         switch (type) {
         case MAP__FUNCTION:
-                return elf_sym__is_function(self);
+                return elf_sym__is_function(sym);
         case MAP__VARIABLE:
-                return elf_sym__is_object(self);
+                return elf_sym__is_object(sym);
         default:
                 return false;
         }
 }
 
-static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type)
+static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
+                          enum map_type type)
 {
         switch (type) {
         case MAP__FUNCTION:
-                return elf_sec__is_text(self, secstrs);
+                return elf_sec__is_text(shdr, secstrs);
         case MAP__VARIABLE:
-                return elf_sec__is_data(self, secstrs);
+                return elf_sec__is_data(shdr, secstrs);
         default:
                 return false;
         }
@@ -978,13 +1057,13 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
         return -1;
 }
 
-static int dso__load_sym(struct dso *self, struct map *map, const char *name,
+static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
                          int fd, symbol_filter_t filter, int kmodule,
                          int want_symtab)
 {
-        struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
+        struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
         struct map *curr_map = map;
-        struct dso *curr_dso = self;
+        struct dso *curr_dso = dso;
         Elf_Data *symstrs, *secstrs;
         uint32_t nr_syms;
         int err = -1;
@@ -1010,14 +1089,14 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
         }
 
         /* Always reject images with a mismatched build-id: */
-        if (self->has_build_id) {
+        if (dso->has_build_id) {
                 u8 build_id[BUILD_ID_SIZE];
 
                 if (elf_read_build_id(elf, build_id,
                                       BUILD_ID_SIZE) != BUILD_ID_SIZE)
                         goto out_elf_end;
 
-                if (!dso__build_id_equal(self, build_id))
+                if (!dso__build_id_equal(dso, build_id))
                         goto out_elf_end;
         }
 
@@ -1058,13 +1137,14 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
         nr_syms = shdr.sh_size / shdr.sh_entsize;
 
         memset(&sym, 0, sizeof(sym));
-        if (self->kernel == DSO_TYPE_USER) {
-                self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
+        if (dso->kernel == DSO_TYPE_USER) {
+                dso->adjust_symbols = (ehdr.e_type == ET_EXEC ||
                                 elf_section_by_name(elf, &ehdr, &shdr,
                                                      ".gnu.prelink_undo",
                                                      NULL) != NULL);
-        } else self->adjust_symbols = 0;
-
+        } else {
+                dso->adjust_symbols = 0;
+        }
         elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
                 struct symbol *f;
                 const char *elf_name = elf_sym__name(&sym, symstrs);
@@ -1107,22 +1187,29 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 
                 section_name = elf_sec__name(&shdr, secstrs);
 
-                if (self->kernel != DSO_TYPE_USER || kmodule) {
+                /* On ARM, symbols for thumb functions have 1 added to
+                 * the symbol address as a flag - remove it */
+                if ((ehdr.e_machine == EM_ARM) &&
+                    (map->type == MAP__FUNCTION) &&
+                    (sym.st_value & 1))
+                        --sym.st_value;
+
+                if (dso->kernel != DSO_TYPE_USER || kmodule) {
                         char dso_name[PATH_MAX];
 
                         if (strcmp(section_name,
                                    (curr_dso->short_name +
-                                    self->short_name_len)) == 0)
+                                    dso->short_name_len)) == 0)
                                 goto new_symbol;
 
                         if (strcmp(section_name, ".text") == 0) {
                                 curr_map = map;
-                                curr_dso = self;
+                                curr_dso = dso;
                                 goto new_symbol;
                         }
 
                         snprintf(dso_name, sizeof(dso_name),
-                                 "%s%s", self->short_name, section_name);
+                                 "%s%s", dso->short_name, section_name);
 
                         curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
                         if (curr_map == NULL) {
@@ -1134,7 +1221,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                                 curr_dso = dso__new(dso_name);
                                 if (curr_dso == NULL)
                                         goto out_elf_end;
-                                curr_dso->kernel = self->kernel;
+                                curr_dso->kernel = dso->kernel;
+                                curr_dso->long_name = dso->long_name;
+                                curr_dso->long_name_len = dso->long_name_len;
                                 curr_map = map__new2(start, curr_dso,
                                                      map->type);
                                 if (curr_map == NULL) {
@@ -1143,9 +1232,9 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                                 }
                                 curr_map->map_ip = identity__map_ip;
                                 curr_map->unmap_ip = identity__map_ip;
-                                curr_dso->origin = self->origin;
+                                curr_dso->symtab_type = dso->symtab_type;
                                 map_groups__insert(kmap->kmaps, curr_map);
-                                dsos__add(&self->node, curr_dso);
+                                dsos__add(&dso->node, curr_dso);
                                 dso__set_loaded(curr_dso, map->type);
                         } else
                                 curr_dso = curr_map->dso;
@@ -1154,8 +1243,8 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
                 }
 
                 if (curr_dso->adjust_symbols) {
-                        pr_debug4("%s: adjusting symbol: st_value: %#Lx "
-                                  "sh_addr: %#Lx sh_offset: %#Lx\n", __func__,
+                        pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+                                  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
                                   (u64)sym.st_value, (u64)shdr.sh_addr,
                                   (u64)shdr.sh_offset);
                         sym.st_value -= shdr.sh_addr - shdr.sh_offset;
@@ -1187,7 +1276,7 @@ new_symbol:
          * For misannotated, zeroed, ASM function sizes.
          */
         if (nr > 0) {
-                symbols__fixup_end(&self->symbols[map->type]);
+                symbols__fixup_end(&dso->symbols[map->type]);
                 if (kmap) {
                         /*
                          * We need to fixup this here too because we create new
@@ -1203,9 +1292,9 @@ out_close:
         return err;
 }
 
-static bool dso__build_id_equal(const struct dso *self, u8 *build_id)
+static bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
 {
-        return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
+        return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
 }
 
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
@@ -1366,27 +1455,27 @@ out:
         return err;
 }
 
-char dso__symtab_origin(const struct dso *self)
+char dso__symtab_origin(const struct dso *dso)
 {
         static const char origin[] = {
-                [DSO__ORIG_KERNEL] =   'k',
-                [DSO__ORIG_JAVA_JIT] = 'j',
-                [DSO__ORIG_BUILD_ID_CACHE] = 'B',
-                [DSO__ORIG_FEDORA] =   'f',
-                [DSO__ORIG_UBUNTU] =   'u',
-                [DSO__ORIG_BUILDID] =  'b',
-                [DSO__ORIG_DSO] =      'd',
-                [DSO__ORIG_KMODULE] =  'K',
-                [DSO__ORIG_GUEST_KERNEL] =  'g',
-                [DSO__ORIG_GUEST_KMODULE] =  'G',
+                [SYMTAB__KALLSYMS]            = 'k',
+                [SYMTAB__JAVA_JIT]            = 'j',
+                [SYMTAB__BUILD_ID_CACHE]      = 'B',
+                [SYMTAB__FEDORA_DEBUGINFO]    = 'f',
+                [SYMTAB__UBUNTU_DEBUGINFO]    = 'u',
+                [SYMTAB__BUILDID_DEBUGINFO]   = 'b',
+                [SYMTAB__SYSTEM_PATH_DSO]     = 'd',
+                [SYMTAB__SYSTEM_PATH_KMODULE] = 'K',
+                [SYMTAB__GUEST_KALLSYMS]      =  'g',
+                [SYMTAB__GUEST_KMODULE]       =  'G',
         };
 
-        if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
+        if (dso == NULL || dso->symtab_type == SYMTAB__NOT_FOUND)
                 return '!';
-        return origin[self->origin];
+        return origin[dso->symtab_type];
 }
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
         int size = PATH_MAX;
         char *name;
@@ -1396,12 +1485,12 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
         const char *root_dir;
         int want_symtab;
 
-        dso__set_loaded(self, map->type);
+        dso__set_loaded(dso, map->type);
 
-        if (self->kernel == DSO_TYPE_KERNEL)
-                return dso__load_kernel_sym(self, map, filter);
-        else if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-                return dso__load_guest_kernel_sym(self, map, filter);
+        if (dso->kernel == DSO_TYPE_KERNEL)
+                return dso__load_kernel_sym(dso, map, filter);
+        else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+                return dso__load_guest_kernel_sym(dso, map, filter);
 
         if (map->groups && map->groups->machine)
                 machine = map->groups->machine;
@@ -1412,12 +1501,12 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
         if (!name)
                 return -1;
 
-        self->adjust_symbols = 0;
+        dso->adjust_symbols = 0;
 
-        if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
-                ret = dso__load_perf_map(self, map, filter);
-                self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT :
-                                         DSO__ORIG_NOT_FOUND;
+        if (strncmp(dso->name, "/tmp/perf-", 10) == 0) {
+                ret = dso__load_perf_map(dso, map, filter);
+                dso->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
+                                              SYMTAB__NOT_FOUND;
                 return ret;
         }
 
@@ -1425,57 +1514,59 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
          * On the first pass, only load images if they have a full symtab.
          * Failing that, do a second pass where we accept .dynsym also
          */
-        for (self->origin = DSO__ORIG_BUILD_ID_CACHE, want_symtab = 1;
-             self->origin != DSO__ORIG_NOT_FOUND;
-             self->origin++) {
-                switch (self->origin) {
-                case DSO__ORIG_BUILD_ID_CACHE:
-                        if (dso__build_id_filename(self, name, size) == NULL)
+        want_symtab = 1;
+restart:
+        for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE;
+             dso->symtab_type != SYMTAB__NOT_FOUND;
+             dso->symtab_type++) {
+                switch (dso->symtab_type) {
+                case SYMTAB__BUILD_ID_CACHE:
+                        /* skip the locally configured cache if a symfs is given */
+                        if (symbol_conf.symfs[0] ||
+                            (dso__build_id_filename(dso, name, size) == NULL)) {
                                 continue;
+                        }
                         break;
-                case DSO__ORIG_FEDORA:
-                        snprintf(name, size, "/usr/lib/debug%s.debug",
-                                 self->long_name);
+                case SYMTAB__FEDORA_DEBUGINFO:
+                        snprintf(name, size, "%s/usr/lib/debug%s.debug",
+                                 symbol_conf.symfs, dso->long_name);
                         break;
-                case DSO__ORIG_UBUNTU:
-                        snprintf(name, size, "/usr/lib/debug%s",
-                                 self->long_name);
+                case SYMTAB__UBUNTU_DEBUGINFO:
+                        snprintf(name, size, "%s/usr/lib/debug%s",
+                                 symbol_conf.symfs, dso->long_name);
                         break;
-                case DSO__ORIG_BUILDID: {
+                case SYMTAB__BUILDID_DEBUGINFO: {
                         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
-                        if (!self->has_build_id)
+                        if (!dso->has_build_id)
                                 continue;
 
-                        build_id__sprintf(self->build_id,
-                                          sizeof(self->build_id),
+                        build_id__sprintf(dso->build_id,
+                                          sizeof(dso->build_id),
                                           build_id_hex);
                         snprintf(name, size,
-                                 "/usr/lib/debug/.build-id/%.2s/%s.debug",
-                                 build_id_hex, build_id_hex + 2);
+                                 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
+                                 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
                         }
                         break;
-                case DSO__ORIG_DSO:
-                        snprintf(name, size, "%s", self->long_name);
+                case SYMTAB__SYSTEM_PATH_DSO:
+                        snprintf(name, size, "%s%s",
+                             symbol_conf.symfs, dso->long_name);
                         break;
-                case DSO__ORIG_GUEST_KMODULE:
-                        if (map->groups && map->groups->machine)
-                                root_dir = map->groups->machine->root_dir;
+                case SYMTAB__GUEST_KMODULE:
+                        if (map->groups && machine)
+                                root_dir = machine->root_dir;
                         else
                                 root_dir = "";
-                        snprintf(name, size, "%s%s", root_dir, self->long_name);
+                        snprintf(name, size, "%s%s%s", symbol_conf.symfs,
+                                 root_dir, dso->long_name);
                         break;
 
-                default:
-                        /*
-                         * If we wanted a full symtab but no image had one,
-                         * relax our requirements and repeat the search.
-                         */
-                        if (want_symtab) {
-                                want_symtab = 0;
-                                self->origin = DSO__ORIG_BUILD_ID_CACHE;
-                        } else
-                                continue;
+                case SYMTAB__SYSTEM_PATH_KMODULE:
+                        snprintf(name, size, "%s%s", symbol_conf.symfs,
+                                 dso->long_name);
+                        break;
+                default:;
                 }
 
                 /* Name is now the name of the next image to try */
@@ -1483,7 +1574,7 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
                 if (fd < 0)
                         continue;
 
-                ret = dso__load_sym(self, map, name, fd, filter, 0,
+                ret = dso__load_sym(dso, map, name, fd, filter, 0,
                                     want_symtab);
                 close(fd);
 
@@ -1495,25 +1586,35 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
                         continue;
 
                 if (ret > 0) {
-                        int nr_plt = dso__synthesize_plt_symbols(self, map, filter);
+                        int nr_plt = dso__synthesize_plt_symbols(dso, map,
+                                                                 filter);
                         if (nr_plt > 0)
                                 ret += nr_plt;
                         break;
                 }
         }
 
+        /*
+         * If we wanted a full symtab but no image had one,
+         * relax our requirements and repeat the search.
+         */
+        if (ret <= 0 && want_symtab) {
+                want_symtab = 0;
+                goto restart;
+        }
+
         free(name);
-        if (ret < 0 && strstr(self->name, " (deleted)") != NULL)
+        if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
                 return 0;
         return ret;
 }
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
                                      enum map_type type, const char *name)
 {
         struct rb_node *nd;
 
-        for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
                 struct map *map = rb_entry(nd, struct map, rb_node);
 
                 if (map->dso && strcmp(map->dso->short_name, name) == 0)
@@ -1523,28 +1624,28 @@ struct map *map_groups__find_by_name(struct map_groups *self,
         return NULL;
 }
 
-static int dso__kernel_module_get_build_id(struct dso *self,
-                                const char *root_dir)
+static int dso__kernel_module_get_build_id(struct dso *dso,
+                                           const char *root_dir)
 {
         char filename[PATH_MAX];
         /*
          * kernel module short names are of the form "[module]" and
          * we need just "module" here.
          */
-        const char *name = self->short_name + 1;
+        const char *name = dso->short_name + 1;
 
         snprintf(filename, sizeof(filename),
                  "%s/sys/module/%.*s/notes/.note.gnu.build-id",
                  root_dir, (int)strlen(name) - 1, name);
 
-        if (sysfs__read_build_id(filename, self->build_id,
-                                 sizeof(self->build_id)) == 0)
-                self->has_build_id = true;
+        if (sysfs__read_build_id(filename, dso->build_id,
+                                 sizeof(dso->build_id)) == 0)
+                dso->has_build_id = true;
 
         return 0;
 }
 
-static int map_groups__set_modules_path_dir(struct map_groups *self,
+static int map_groups__set_modules_path_dir(struct map_groups *mg,
                                 const char *dir_name)
 {
         struct dirent *dent;
@@ -1572,7 +1673,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 
                         snprintf(path, sizeof(path), "%s/%s",
                                  dir_name, dent->d_name);
-                        ret = map_groups__set_modules_path_dir(self, path);
+                        ret = map_groups__set_modules_path_dir(mg, path);
                         if (ret < 0)
                                 goto out;
                 } else {
@@ -1587,7 +1688,8 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
                                  (int)(dot - dent->d_name), dent->d_name);
 
                         strxfrchar(dso_name, '-', '_');
-                        map = map_groups__find_by_name(self, MAP__FUNCTION, dso_name);
+                        map = map_groups__find_by_name(mg, MAP__FUNCTION,
+                                                       dso_name);
                         if (map == NULL)
                                 continue;
 
@@ -1637,20 +1739,20 @@ static char *get_kernel_version(const char *root_dir)
         return strdup(name);
 }
 
-static int machine__set_modules_path(struct machine *self)
+static int machine__set_modules_path(struct machine *machine)
 {
         char *version;
         char modules_path[PATH_MAX];
 
-        version = get_kernel_version(self->root_dir);
+        version = get_kernel_version(machine->root_dir);
         if (!version)
                 return -1;
 
         snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
-                 self->root_dir, version);
+                 machine->root_dir, version);
         free(version);
 
-        return map_groups__set_modules_path_dir(&self->kmaps, modules_path);
+        return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
 }
 
 /*
@@ -1660,23 +1762,23 @@ static int machine__set_modules_path(struct machine *self)
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-        struct map *self = calloc(1, (sizeof(*self) +
-                                      (dso->kernel ? sizeof(struct kmap) : 0)));
-        if (self != NULL) {
+        struct map *map = calloc(1, (sizeof(*map) +
+                                     (dso->kernel ? sizeof(struct kmap) : 0)));
+        if (map != NULL) {
                 /*
                  * ->end will be filled after we load all the symbols
                  */
-                map__init(self, type, start, 0, 0, dso);
+                map__init(map, type, start, 0, 0, dso);
         }
 
-        return self;
+        return map;
 }
 
-struct map *machine__new_module(struct machine *self, u64 start,
+struct map *machine__new_module(struct machine *machine, u64 start,
                                 const char *filename)
 {
         struct map *map;
-        struct dso *dso = __dsos__findnew(&self->kernel_dsos, filename);
+        struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
 
         if (dso == NULL)
                 return NULL;
@@ -1685,15 +1787,15 @@ struct map *machine__new_module(struct machine *self, u64 start,
         if (map == NULL)
                 return NULL;
 
-        if (machine__is_host(self))
-                dso->origin = DSO__ORIG_KMODULE;
+        if (machine__is_host(machine))
+                dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
         else
-                dso->origin = DSO__ORIG_GUEST_KMODULE;
-        map_groups__insert(&self->kmaps, map);
+                dso->symtab_type = SYMTAB__GUEST_KMODULE;
+        map_groups__insert(&machine->kmaps, map);
         return map;
 }
 
-static int machine__create_modules(struct machine *self)
+static int machine__create_modules(struct machine *machine)
 {
         char *line = NULL;
         size_t n;
@@ -1702,13 +1804,16 @@ static int machine__create_modules(struct machine *self)
         const char *modules;
         char path[PATH_MAX];
 
-        if (machine__is_default_guest(self))
+        if (machine__is_default_guest(machine))
                 modules = symbol_conf.default_guest_modules;
         else {
-                sprintf(path, "%s/proc/modules", self->root_dir);
+                sprintf(path, "%s/proc/modules", machine->root_dir);
                 modules = path;
         }
 
+        if (symbol__restricted_filename(path, "/proc/modules"))
+                return -1;
+
         file = fopen(modules, "r");
         if (file == NULL)
                 return -1;
@@ -1741,16 +1846,16 @@ static int machine__create_modules(struct machine *self)
                 *sep = '\0';
 
                 snprintf(name, sizeof(name), "[%s]", line);
-                map = machine__new_module(self, start, name);
+                map = machine__new_module(machine, start, name);
                 if (map == NULL)
                         goto out_delete_line;
-                dso__kernel_module_get_build_id(map->dso, self->root_dir);
+                dso__kernel_module_get_build_id(map->dso, machine->root_dir);
         }
 
         free(line);
         fclose(file);
 
-        return machine__set_modules_path(self);
+        return machine__set_modules_path(machine);
 
 out_delete_line:
         free(line);
@@ -1758,26 +1863,30 @@ out_failure:
         return -1;
 }
 
-static int dso__load_vmlinux(struct dso *self, struct map *map,
-                             const char *vmlinux, symbol_filter_t filter)
+int dso__load_vmlinux(struct dso *dso, struct map *map,
+                      const char *vmlinux, symbol_filter_t filter)
 {
         int err = -1, fd;
+        char symfs_vmlinux[PATH_MAX];
 
-        fd = open(vmlinux, O_RDONLY);
+        snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
+                 symbol_conf.symfs, vmlinux);
+        fd = open(symfs_vmlinux, O_RDONLY);
         if (fd < 0)
                 return -1;
 
-        dso__set_loaded(self, map->type);
-        err = dso__load_sym(self, map, vmlinux, fd, filter, 0, 0);
+        dso__set_long_name(dso, (char *)vmlinux);
+        dso__set_loaded(dso, map->type);
+        err = dso__load_sym(dso, map, symfs_vmlinux, fd, filter, 0, 0);
         close(fd);
 
         if (err > 0)
-                pr_debug("Using %s for symbols\n", vmlinux);
+                pr_debug("Using %s for symbols\n", symfs_vmlinux);
 
         return err;
 }
 
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
                            symbol_filter_t filter)
 {
         int i, err = 0;
@@ -1786,20 +1895,20 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
         pr_debug("Looking at the vmlinux_path (%d entries long)\n",
                  vmlinux_path__nr_entries + 1);
 
-        filename = dso__build_id_filename(self, NULL, 0);
+        filename = dso__build_id_filename(dso, NULL, 0);
         if (filename != NULL) {
-                err = dso__load_vmlinux(self, map, filename, filter);
+                err = dso__load_vmlinux(dso, map, filename, filter);
                 if (err > 0) {
-                        dso__set_long_name(self, filename);
+                        dso__set_long_name(dso, filename);
                         goto out;
                 }
                 free(filename);
         }
 
         for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-                err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
+                err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
                 if (err > 0) {
-                        dso__set_long_name(self, strdup(vmlinux_path[i]));
+                        dso__set_long_name(dso, strdup(vmlinux_path[i]));
                         break;
                 }
         }
@@ -1807,15 +1916,15 @@ out:
         return err;
 }
 
-static int dso__load_kernel_sym(struct dso *self, struct map *map,
+static int dso__load_kernel_sym(struct dso *dso, struct map *map,
                                 symbol_filter_t filter)
 {
         int err;
         const char *kallsyms_filename = NULL;
         char *kallsyms_allocated_filename = NULL;
         /*
-         * Step 1: if the user specified a vmlinux filename, use it and only
-         * it, reporting errors to the user if it cannot be used.
+         * Step 1: if the user specified a kallsyms or vmlinux filename, use
+         * it and only it, reporting errors to the user if it cannot be used.
          *
          * For instance, try to analyse an ARM perf.data file _without_ a
          * build-id, or if the user specifies the wrong path to the right
@@ -1828,11 +1937,16 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
          * validation in dso__load_vmlinux and will bail out if they don't
          * match.
          */
+        if (symbol_conf.kallsyms_name != NULL) {
+                kallsyms_filename = symbol_conf.kallsyms_name;
+                goto do_kallsyms;
+        }
+
         if (symbol_conf.vmlinux_name != NULL) {
-                err = dso__load_vmlinux(self, map,
+                err = dso__load_vmlinux(dso, map,
                                         symbol_conf.vmlinux_name, filter);
                 if (err > 0) {
-                        dso__set_long_name(self,
+                        dso__set_long_name(dso,
                                            strdup(symbol_conf.vmlinux_name));
                         goto out_fixup;
                 }
@@ -1840,23 +1954,27 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
         }
 
         if (vmlinux_path != NULL) {
-                err = dso__load_vmlinux_path(self, map, filter);
+                err = dso__load_vmlinux_path(dso, map, filter);
                 if (err > 0)
                         goto out_fixup;
         }
 
+        /* do not try local files if a symfs was given */
+        if (symbol_conf.symfs[0] != 0)
+                return -1;
+
         /*
          * Say the kernel DSO was created when processing the build-id header table,
          * we have a build-id, so check if it is the same as the running kernel,
          * using it if it is.
          */
-        if (self->has_build_id) {
+        if (dso->has_build_id) {
                 u8 kallsyms_build_id[BUILD_ID_SIZE];
                 char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
                 if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
                                          sizeof(kallsyms_build_id)) == 0) {
-                        if (dso__build_id_equal(self, kallsyms_build_id)) {
+                        if (dso__build_id_equal(dso, kallsyms_build_id)) {
                                 kallsyms_filename = "/proc/kallsyms";
                                 goto do_kallsyms;
                         }
@@ -1865,7 +1983,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
                  * Now look if we have it on the build-id cache in
                  * $HOME/.debug/[kernel.kallsyms].
                  */
-                build_id__sprintf(self->build_id, sizeof(self->build_id),
+                build_id__sprintf(dso->build_id, sizeof(dso->build_id),
                                   sbuild_id);
 
                 if (asprintf(&kallsyms_allocated_filename,
@@ -1892,7 +2010,7 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
         }
 
 do_kallsyms:
-        err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+        err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
         if (err > 0)
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
         free(kallsyms_allocated_filename);
@@ -1900,7 +2018,7 @@ do_kallsyms:
         if (err > 0) {
 out_fixup:
                 if (kallsyms_filename != NULL)
-                        dso__set_long_name(self, strdup("[kernel.kallsyms]"));
+                        dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
@@ -1908,8 +2026,8 @@ out_fixup:
         return err;
 }
 
-static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
-                                symbol_filter_t filter)
+static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
+                                      symbol_filter_t filter)
 {
         int err;
         const char *kallsyms_filename = NULL;
@@ -1929,7 +2047,7 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
                  * Or use file guest_kallsyms inputted by user on commandline
                  */
                 if (symbol_conf.default_guest_vmlinux_name != NULL) {
-                        err = dso__load_vmlinux(self, map,
+                        err = dso__load_vmlinux(dso, map,
                                 symbol_conf.default_guest_vmlinux_name, filter);
                         goto out_try_fixup;
                 }
@@ -1942,7 +2060,7 @@ static int dso__load_guest_kernel_sym(struct dso *self, struct map *map,
                 kallsyms_filename = path;
         }
 
-        err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+        err = dso__load_kallsyms(dso, kallsyms_filename, map, filter);
         if (err > 0)
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
 
@@ -1950,7 +2068,7 @@ out_try_fixup:
         if (err > 0) {
                 if (kallsyms_filename != NULL) {
                         machine__mmap_name(machine, path, sizeof(path));
-                        dso__set_long_name(self, strdup(path));
+                        dso__set_long_name(dso, strdup(path));
                 }
                 map__fixup_start(map);
                 map__fixup_end(map);
@@ -2003,12 +2121,12 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
         return ret;
 }
 
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp)
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp)
 {
         struct rb_node *nd;
         size_t ret = 0;
 
-        for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
                 struct machine *pos = rb_entry(nd, struct machine, rb_node);
                 ret += __dsos__fprintf(&pos->kernel_dsos, fp);
                 ret += __dsos__fprintf(&pos->user_dsos, fp);
@@ -2032,18 +2150,20 @@ static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
         return ret;
 }
 
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits)
+size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+                                     bool with_hits)
 {
-        return __dsos__fprintf_buildid(&self->kernel_dsos, fp, with_hits) +
-               __dsos__fprintf_buildid(&self->user_dsos, fp, with_hits);
+        return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) +
+               __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits);
 }
 
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits)
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+                                      FILE *fp, bool with_hits)
 {
         struct rb_node *nd;
         size_t ret = 0;
 
-        for (nd = rb_first(self); nd; nd = rb_next(nd)) {
+        for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
                 struct machine *pos = rb_entry(nd, struct machine, rb_node);
                 ret += machine__fprintf_dsos_buildid(pos, fp, with_hits);
         }
@@ -2052,97 +2172,143 @@ size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_
 
 struct dso *dso__new_kernel(const char *name)
 {
-        struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
+        struct dso *dso = dso__new(name ?: "[kernel.kallsyms]");
 
-        if (self != NULL) {
-                dso__set_short_name(self, "[kernel]");
-                self->kernel = DSO_TYPE_KERNEL;
+        if (dso != NULL) {
+                dso__set_short_name(dso, "[kernel]");
+                dso->kernel = DSO_TYPE_KERNEL;
         }
 
-        return self;
+        return dso;
 }
 
 static struct dso *dso__new_guest_kernel(struct machine *machine,
                                         const char *name)
 {
         char bf[PATH_MAX];
-        struct dso *self = dso__new(name ?: machine__mmap_name(machine, bf, sizeof(bf)));
-
-        if (self != NULL) {
-                dso__set_short_name(self, "[guest.kernel]");
-                self->kernel = DSO_TYPE_GUEST_KERNEL;
+        struct dso *dso = dso__new(name ?: machine__mmap_name(machine, bf,
+                                                              sizeof(bf)));
+        if (dso != NULL) {
+                dso__set_short_name(dso, "[guest.kernel]");
+                dso->kernel = DSO_TYPE_GUEST_KERNEL;
         }
 
-        return self;
+        return dso;
 }
 
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine)
+void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
 {
         char path[PATH_MAX];
 
         if (machine__is_default_guest(machine))
                 return;
         sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
-        if (sysfs__read_build_id(path, self->build_id,
-                                 sizeof(self->build_id)) == 0)
-                self->has_build_id = true;
+        if (sysfs__read_build_id(path, dso->build_id,
+                                 sizeof(dso->build_id)) == 0)
+                dso->has_build_id = true;
 }
 
-static struct dso *machine__create_kernel(struct machine *self)
+static struct dso *machine__create_kernel(struct machine *machine)
 {
         const char *vmlinux_name = NULL;
         struct dso *kernel;
 
-        if (machine__is_host(self)) {
+        if (machine__is_host(machine)) {
                 vmlinux_name = symbol_conf.vmlinux_name;
                 kernel = dso__new_kernel(vmlinux_name);
         } else {
-                if (machine__is_default_guest(self))
+                if (machine__is_default_guest(machine))
                         vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-                kernel = dso__new_guest_kernel(self, vmlinux_name);
+                kernel = dso__new_guest_kernel(machine, vmlinux_name);
         }
 
         if (kernel != NULL) {
-                dso__read_running_kernel_build_id(kernel, self);
-                dsos__add(&self->kernel_dsos, kernel);
+                dso__read_running_kernel_build_id(kernel, machine);
+                dsos__add(&machine->kernel_dsos, kernel);
         }
         return kernel;
 }
 
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
+struct process_args {
+        u64 start;
+};
+
+static int symbol__in_kernel(void *arg, const char *name,
+                             char type __used, u64 start, u64 end __used)
+{
+        struct process_args *args = arg;
+
+        if (strchr(name, '['))
+                return 0;
+
+        args->start = start;
+        return 1;
+}
+
+/* Figure out the start address of kernel map from /proc/kallsyms */
+static u64 machine__get_kernel_start_addr(struct machine *machine)
+{
+        const char *filename;
+        char path[PATH_MAX];
+        struct process_args args;
+
+        if (machine__is_host(machine)) {
+                filename = "/proc/kallsyms";
+        } else {
+                if (machine__is_default_guest(machine))
+                        filename = (char *)symbol_conf.default_guest_kallsyms;
+                else {
+                        sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+                        filename = path;
+                }
+        }
+
+        if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+                return 0;
+
+        if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
+                return 0;
+
+        return args.start;
+}
+
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
         enum map_type type;
+        u64 start = machine__get_kernel_start_addr(machine);
 
         for (type = 0; type < MAP__NR_TYPES; ++type) {
                 struct kmap *kmap;
 
-                self->vmlinux_maps[type] = map__new2(0, kernel, type);
-                if (self->vmlinux_maps[type] == NULL)
+                machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+                if (machine->vmlinux_maps[type] == NULL)
                         return -1;
 
-                self->vmlinux_maps[type]->map_ip =
-                        self->vmlinux_maps[type]->unmap_ip = identity__map_ip;
-
-                kmap = map__kmap(self->vmlinux_maps[type]);
-                kmap->kmaps = &self->kmaps;
-                map_groups__insert(&self->kmaps, self->vmlinux_maps[type]);
+                machine->vmlinux_maps[type]->map_ip =
+                        machine->vmlinux_maps[type]->unmap_ip =
+                                identity__map_ip;
+                kmap = map__kmap(machine->vmlinux_maps[type]);
+                kmap->kmaps = &machine->kmaps;
+                map_groups__insert(&machine->kmaps,
+                                   machine->vmlinux_maps[type]);
         }
 
         return 0;
 }
 
-void machine__destroy_kernel_maps(struct machine *self)
+void machine__destroy_kernel_maps(struct machine *machine)
 {
         enum map_type type;
 
         for (type = 0; type < MAP__NR_TYPES; ++type) {
                 struct kmap *kmap;
 
-                if (self->vmlinux_maps[type] == NULL)
+                if (machine->vmlinux_maps[type] == NULL)
                         continue;
 
-                kmap = map__kmap(self->vmlinux_maps[type]);
-                map_groups__remove(&self->kmaps, self->vmlinux_maps[type]);
+                kmap = map__kmap(machine->vmlinux_maps[type]);
+                map_groups__remove(&machine->kmaps,
+                                   machine->vmlinux_maps[type]);
                 if (kmap->ref_reloc_sym) {
                         /*
                          * ref_reloc_sym is shared among all maps, so free just
@@ -2156,25 +2322,25 @@ void machine__destroy_kernel_maps(struct machine *self)
                         kmap->ref_reloc_sym = NULL;
                 }
 
-                map__delete(self->vmlinux_maps[type]);
-                self->vmlinux_maps[type] = NULL;
+                map__delete(machine->vmlinux_maps[type]);
+                machine->vmlinux_maps[type] = NULL;
         }
 }
 
-int machine__create_kernel_maps(struct machine *self)
+int machine__create_kernel_maps(struct machine *machine)
 {
-        struct dso *kernel = machine__create_kernel(self);
+        struct dso *kernel = machine__create_kernel(machine);
 
         if (kernel == NULL ||
-            __machine__create_kernel_maps(self, kernel) < 0)
+            __machine__create_kernel_maps(machine, kernel) < 0)
                 return -1;
 
-        if (symbol_conf.use_modules && machine__create_modules(self) < 0)
+        if (symbol_conf.use_modules && machine__create_modules(machine) < 0)
                 pr_debug("Problems creating module maps, continuing anyway...\n");
         /*
          * Now that we have all the maps created, just set the ->end of them:
          */
-        map_groups__fixup_end(&self->kmaps);
+        map_groups__fixup_end(&machine->kmaps);
         return 0;
 }
 
@@ -2194,9 +2360,6 @@ static int vmlinux_path__init(void)
         struct utsname uts;
         char bf[PATH_MAX];
 
-        if (uname(&uts) < 0)
-                return -1;
-
         vmlinux_path = malloc(sizeof(char *) * 5);
         if (vmlinux_path == NULL)
                 return -1;
@@ -2209,6 +2372,14 @@ static int vmlinux_path__init(void)
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
                 goto out_fail;
         ++vmlinux_path__nr_entries;
+
+        /* only try running kernel version if no symfs was given */
+        if (symbol_conf.symfs[0] != 0)
+                return 0;
+
+        if (uname(&uts) < 0)
+                return -1;
+
         snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
         vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
         if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
@@ -2233,11 +2404,11 @@ out_fail:
         return -1;
 }
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp)
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp)
 {
         int i;
         size_t printed = 0;
-        struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso;
+        struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso;
 
         if (kdso->has_build_id) {
                 char filename[PATH_MAX];
@@ -2266,11 +2437,34 @@ static int setup_list(struct strlist **list, const char *list_str,
         return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+        bool value = false;
+
+        if (geteuid() != 0) {
+                FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+                if (fp != NULL) {
+                        char line[8];
+
+                        if (fgets(line, sizeof(line), fp) != NULL)
+                                value = atoi(line) != 0;
+
+                        fclose(fp);
+                }
+        }
+
+        return value;
+}
+
 int symbol__init(void)
 {
+        const char *symfs;
+
         if (symbol_conf.initialized)
                 return 0;
 
+        symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
+
         elf_version(EV_CURRENT);
         if (symbol_conf.sort_by_name)
                 symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
@@ -2296,6 +2490,20 @@ int symbol__init(void)
                        symbol_conf.sym_list_str, "symbol") < 0)
                 goto out_free_comm_list;
 
+        /*
+         * A path to symbols of "/" is identical to ""
+         * reset here for simplicity.
+         */
+        symfs = realpath(symbol_conf.symfs, NULL);
+        if (symfs == NULL)
+                symfs = symbol_conf.symfs;
+        if (strcmp(symfs, "/") == 0)
+                symbol_conf.symfs = "";
+        if (symfs != symbol_conf.symfs)
+                free((void *)symfs);
+
+        symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
         symbol_conf.initialized = true;
         return 0;
 
@@ -2318,9 +2526,9 @@ void symbol__exit(void)
         symbol_conf.initialized = false;
 }
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid)
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid)
 {
-        struct machine *machine = machines__findnew(self, pid);
+        struct machine *machine = machines__findnew(machines, pid);
 
         if (machine == NULL)
                 return -1;
@@ -2371,7 +2579,7 @@ char *strxfrchar(char *s, char from, char to)
         return s;
 }
 
-int machines__create_guest_kernel_maps(struct rb_root *self)
+int machines__create_guest_kernel_maps(struct rb_root *machines)
 {
         int ret = 0;
         struct dirent **namelist = NULL;
@@ -2382,7 +2590,7 @@ int machines__create_guest_kernel_maps(struct rb_root *self)
         if (symbol_conf.default_guest_vmlinux_name ||
             symbol_conf.default_guest_modules ||
             symbol_conf.default_guest_kallsyms) {
-                machines__create_kernel_maps(self, DEFAULT_GUEST_KERNEL_ID);
+                machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID);
         }
 
         if (symbol_conf.guestmount) {
@@ -2403,7 +2611,7 @@ int machines__create_guest_kernel_maps(struct rb_root *self)
                                 pr_debug("Can't access file %s\n", path);
                                 goto failure;
                         }
-                        machines__create_kernel_maps(self, pid);
+                        machines__create_kernel_maps(machines, pid);
                 }
 failure:
                 free(namelist);
@@ -2412,23 +2620,23 @@ failure:
         return ret;
 }
 
-void machines__destroy_guest_kernel_maps(struct rb_root *self)
+void machines__destroy_guest_kernel_maps(struct rb_root *machines)
 {
-        struct rb_node *next = rb_first(self);
+        struct rb_node *next = rb_first(machines);
 
         while (next) {
                 struct machine *pos = rb_entry(next, struct machine, rb_node);
 
                 next = rb_next(&pos->rb_node);
-                rb_erase(&pos->rb_node, self);
+                rb_erase(&pos->rb_node, machines);
                 machine__delete(pos);
         }
 }
 
-int machine__load_kallsyms(struct machine *self, const char *filename,
+int machine__load_kallsyms(struct machine *machine, const char *filename,
                            enum map_type type, symbol_filter_t filter)
 {
-        struct map *map = self->vmlinux_maps[type];
+        struct map *map = machine->vmlinux_maps[type];
         int ret = dso__load_kallsyms(map->dso, filename, map, filter);
 
         if (ret > 0) {
@@ -2438,16 +2646,16 @@ int machine__load_kallsyms(struct machine *self, const char *filename,
                  * kernel, with modules between them, fixup the end of all
                  * sections.
                  */
-                __map_groups__fixup_end(&self->kmaps, type);
+                __map_groups__fixup_end(&machine->kmaps, type);
         }
 
         return ret;
 }
 
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
                                symbol_filter_t filter)
 {
-        struct map *map = self->vmlinux_maps[type];
+        struct map *map = machine->vmlinux_maps[type];
         int ret = dso__load_vmlinux_path(map->dso, map, filter);
 
         if (ret > 0) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ea95c2756f05..325ee36a9d29 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -48,16 +48,21 @@ char *strxfrchar(char *s, char from, char to);
 
 #define BUILD_ID_SIZE 20
 
+/** struct symbol - symtab entry
+ *
+ * @ignore - resolvable but tools ignore it (e.g. idle routines)
+ */
 struct symbol {
         struct rb_node  rb_node;
         u64             start;
         u64             end;
         u16             namelen;
         u8              binding;
+        bool            ignore;
         char            name[0];
 };
 
-void symbol__delete(struct symbol *self);
+void symbol__delete(struct symbol *sym);
 
 struct strlist;
 
@@ -70,8 +75,10 @@ struct symbol_conf {
                         use_callchain,
                         exclude_other,
                         show_cpu_utilization,
-                        initialized;
+                        initialized,
+                        kptr_restrict;
         const char      *vmlinux_name,
+                        *kallsyms_name,
                         *source_prefix,
                         *field_sep;
         const char      *default_guest_vmlinux_name,
@@ -85,13 +92,14 @@ struct symbol_conf {
        struct strlist   *dso_list,
                         *comm_list,
                         *sym_list;
+        const char      *symfs;
 };
 
 extern struct symbol_conf symbol_conf;
 
-static inline void *symbol__priv(struct symbol *self)
+static inline void *symbol__priv(struct symbol *sym)
 {
-        return ((void *)self) - symbol_conf.priv_size;
+        return ((void *)sym) - symbol_conf.priv_size;
 }
 
 struct ref_reloc_sym {
@@ -130,13 +138,12 @@ struct dso {
         struct rb_root   symbol_names[MAP__NR_TYPES];
         enum dso_kernel_type    kernel;
         u8               adjust_symbols:1;
-        u8               slen_calculated:1;
         u8               has_build_id:1;
         u8               hit:1;
         u8               annotate_warned:1;
         u8               sname_alloc:1;
         u8               lname_alloc:1;
-        unsigned char    origin;
+        unsigned char    symtab_type;
         u8               sorted_by_name;
         u8               loaded;
         u8               build_id[BUILD_ID_SIZE];
@@ -149,83 +156,90 @@ struct dso {
 
 struct dso *dso__new(const char *name);
 struct dso *dso__new_kernel(const char *name);
-void dso__delete(struct dso *self);
+void dso__delete(struct dso *dso);
 
-int dso__name_len(const struct dso *self);
+int dso__name_len(const struct dso *dso);
 
-bool dso__loaded(const struct dso *self, enum map_type type);
-bool dso__sorted_by_name(const struct dso *self, enum map_type type);
+bool dso__loaded(const struct dso *dso, enum map_type type);
+bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
 
-static inline void dso__set_loaded(struct dso *self, enum map_type type)
+static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 {
-        self->loaded |= (1 << type);
+        dso->loaded |= (1 << type);
 }
 
-void dso__sort_by_name(struct dso *self, enum map_type type);
+void dso__sort_by_name(struct dso *dso, enum map_type type);
 
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 
-int dso__load(struct dso *self, struct map *map, symbol_filter_t filter);
-int dso__load_vmlinux_path(struct dso *self, struct map *map,
+int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
+int dso__load_vmlinux(struct dso *dso, struct map *map,
+                      const char *vmlinux, symbol_filter_t filter);
+int dso__load_vmlinux_path(struct dso *dso, struct map *map,
                            symbol_filter_t filter);
-int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
+int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
                        symbol_filter_t filter);
-int machine__load_kallsyms(struct machine *self, const char *filename,
+int machine__load_kallsyms(struct machine *machine, const char *filename,
                            enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *self, enum map_type type,
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
                                symbol_filter_t filter);
 
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
-size_t machine__fprintf_dsos_buildid(struct machine *self, FILE *fp, bool with_hits);
-size_t machines__fprintf_dsos(struct rb_root *self, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *self, FILE *fp, bool with_hits);
-
-size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
-size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
-
-enum dso_origin {
-        DSO__ORIG_KERNEL = 0,
-        DSO__ORIG_GUEST_KERNEL,
-        DSO__ORIG_JAVA_JIT,
-        DSO__ORIG_BUILD_ID_CACHE,
-        DSO__ORIG_FEDORA,
-        DSO__ORIG_UBUNTU,
-        DSO__ORIG_BUILDID,
-        DSO__ORIG_DSO,
-        DSO__ORIG_GUEST_KMODULE,
-        DSO__ORIG_KMODULE,
-        DSO__ORIG_NOT_FOUND,
+size_t machine__fprintf_dsos_buildid(struct machine *machine,
+                                     FILE *fp, bool with_hits);
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+                                      FILE *fp, bool with_hits);
+size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso,
+                                    enum map_type type, FILE *fp);
+size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
+
+enum symtab_type {
+        SYMTAB__KALLSYMS = 0,
+        SYMTAB__GUEST_KALLSYMS,
+        SYMTAB__JAVA_JIT,
+        SYMTAB__BUILD_ID_CACHE,
+        SYMTAB__FEDORA_DEBUGINFO,
+        SYMTAB__UBUNTU_DEBUGINFO,
+        SYMTAB__BUILDID_DEBUGINFO,
+        SYMTAB__SYSTEM_PATH_DSO,
+        SYMTAB__GUEST_KMODULE,
+        SYMTAB__SYSTEM_PATH_KMODULE,
+        SYMTAB__NOT_FOUND,
 };
 
-char dso__symtab_origin(const struct dso *self);
-void dso__set_long_name(struct dso *self, char *name);
-void dso__set_build_id(struct dso *self, void *build_id);
-void dso__read_running_kernel_build_id(struct dso *self, struct machine *machine);
-struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
+char dso__symtab_origin(const struct dso *dso);
+void dso__set_long_name(struct dso *dso, char *name);
+void dso__set_build_id(struct dso *dso, void *build_id);
+void dso__read_running_kernel_build_id(struct dso *dso,
+                                       struct machine *machine);
+struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
+                                u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-int build_id__sprintf(const u8 *self, int len, char *bf);
+int build_id__sprintf(const u8 *build_id, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
                     int (*process_symbol)(void *arg, const char *name,
-                                          char type, u64 start));
+                                          char type, u64 start, u64 end));
 
-void machine__destroy_kernel_maps(struct machine *self);
-int __machine__create_kernel_maps(struct machine *self, struct dso *kernel);
-int machine__create_kernel_maps(struct machine *self);
+void machine__destroy_kernel_maps(struct machine *machine);
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *machine);
 
-int machines__create_kernel_maps(struct rb_root *self, pid_t pid);
-int machines__create_guest_kernel_maps(struct rb_root *self);
-void machines__destroy_guest_kernel_maps(struct rb_root *self);
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid);
+int machines__create_guest_kernel_maps(struct rb_root *machines);
+void machines__destroy_guest_kernel_maps(struct rb_root *machines);
 
 int symbol__init(void);
 void symbol__exit(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp);
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 8c72d888e449..d5d3b22250f3 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,46 +7,6 @@
 #include "util.h"
 #include "debug.h"
 
-/* Skip "." and ".." directories */
-static int filter(const struct dirent *dir)
-{
-        if (dir->d_name[0] == '.')
-                return 0;
-        else
-                return 1;
-}
-
-int find_all_tid(int pid, pid_t ** all_tid)
-{
-        char name[256];
-        int items;
-        struct dirent **namelist = NULL;
-        int ret = 0;
-        int i;
-
-        sprintf(name, "/proc/%d/task", pid);
-        items = scandir(name, &namelist, filter, NULL);
-        if (items <= 0)
-                return -ENOENT;
-        *all_tid = malloc(sizeof(pid_t) * items);
-        if (!*all_tid) {
-                ret = -ENOMEM;
-                goto failure;
-        }
-
-        for (i = 0; i < items; i++)
-                (*all_tid)[i] = atoi(namelist[i]->d_name);
-
-        ret = items;
-
-failure:
-        for (i=0; i<items; i++)
-                free(namelist[i]);
-        free(namelist);
-
-        return ret;
-}
-
 static struct thread *thread__new(pid_t pid)
 {
         struct thread *self = zalloc(sizeof(*self));
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 688500ff826f..e5f2401c1b5e 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -22,7 +22,6 @@ struct perf_session;
 
 void thread__delete(struct thread *self);
 
-int find_all_tid(int pid, pid_t ** all_tid);
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);
 struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
new file mode 100644
index 000000000000..a5df131b77c3
--- /dev/null
+++ b/tools/perf/util/thread_map.c
@@ -0,0 +1,64 @@
+#include <dirent.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "thread_map.h"
+
+/* Skip "." and ".." directories */
+static int filter(const struct dirent *dir)
+{
+        if (dir->d_name[0] == '.')
+                return 0;
+        else
+                return 1;
+}
+
+struct thread_map *thread_map__new_by_pid(pid_t pid)
+{
+        struct thread_map *threads;
+        char name[256];
+        int items;
+        struct dirent **namelist = NULL;
+        int i;
+
+        sprintf(name, "/proc/%d/task", pid);
+        items = scandir(name, &namelist, filter, NULL);
+        if (items <= 0)
+                return NULL;
+
+        threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+        if (threads != NULL) {
+                for (i = 0; i < items; i++)
+                        threads->map[i] = atoi(namelist[i]->d_name);
+                threads->nr = items;
+        }
+
+        for (i=0; i<items; i++)
+                free(namelist[i]);
+        free(namelist);
+
+        return threads;
+}
+
+struct thread_map *thread_map__new_by_tid(pid_t tid)
+{
+        struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+
+        if (threads != NULL) {
+                threads->map[0] = tid;
+                threads->nr     = 1;
+        }
+
+        return threads;
+}
+
+struct thread_map *thread_map__new(pid_t pid, pid_t tid)
+{
+        if (pid != -1)
+                return thread_map__new_by_pid(pid);
+        return thread_map__new_by_tid(tid);
+}
+
+void thread_map__delete(struct thread_map *threads)
+{
+        free(threads);
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
new file mode 100644
index 000000000000..3cb907311409
--- /dev/null
+++ b/tools/perf/util/thread_map.h
@@ -0,0 +1,15 @@
+#ifndef __PERF_THREAD_MAP_H
+#define __PERF_THREAD_MAP_H
+
+#include <sys/types.h>
+
+struct thread_map {
+        int nr;
+        int 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);
+void thread_map__delete(struct thread_map *threads);
+#endif  /* __PERF_THREAD_MAP_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
new file mode 100644
index 000000000000..a11f60735a18
--- /dev/null
+++ b/tools/perf/util/top.c
@@ -0,0 +1,238 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Refactored from builtin-top.c, see that files for further copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "cpumap.h"
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "parse-events.h"
+#include "symbol.h"
+#include "top.h"
+#include <inttypes.h>
+
+/*
+ * Ordering weight: count-1 * count-2 * ... / count-n
+ */
+static double sym_weight(const struct sym_entry *sym, struct perf_top *top)
+{
+        double weight = sym->snap_count;
+        int counter;
+
+        if (!top->display_weighted)
+                return weight;
+
+        for (counter = 1; counter < top->evlist->nr_entries - 1; counter++)
+                weight *= sym->count[counter];
+
+        weight /= (sym->count[counter] + 1);
+
+        return weight;
+}
+
+static void perf_top__remove_active_sym(struct perf_top *top, struct sym_entry *syme)
+{
+        pthread_mutex_lock(&top->active_symbols_lock);
+        list_del_init(&syme->node);
+        pthread_mutex_unlock(&top->active_symbols_lock);
+}
+
+static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
+{
+        struct rb_node **p = &tree->rb_node;
+        struct rb_node *parent = NULL;
+        struct sym_entry *iter;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct sym_entry, rb_node);
+
+                if (se->weight > iter->weight)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+
+        rb_link_node(&se->rb_node, parent, p);
+        rb_insert_color(&se->rb_node, tree);
+}
+
+#define SNPRINTF(buf, size, fmt, args...) \
+({ \
+        size_t r = snprintf(buf, size, fmt, ## args); \
+        r > size ?  size : r; \
+})
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
+{
+        struct perf_evsel *counter;
+        float samples_per_sec = top->samples / top->delay_secs;
+        float ksamples_per_sec = top->kernel_samples / top->delay_secs;
+        float esamples_percent = (100.0 * top->exact_samples) / top->samples;
+        size_t ret = 0;
+
+        if (!perf_guest) {
+                ret = SNPRINTF(bf, size,
+                               "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%%"
+                               "  exact: %4.1f%% [", samples_per_sec,
+                               100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+                                        samples_per_sec)),
+                                esamples_percent);
+        } else {
+                float us_samples_per_sec = top->us_samples / top->delay_secs;
+                float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs;
+                float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs;
+
+                ret = SNPRINTF(bf, size,
+                               "   PerfTop:%8.0f irqs/sec  kernel:%4.1f%% us:%4.1f%%"
+                               " guest kernel:%4.1f%% guest us:%4.1f%%"
+                               " exact: %4.1f%% [", samples_per_sec,
+                               100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) /
+                                                 samples_per_sec)),
+                               100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) /
+                                                 samples_per_sec)),
+                               100.0 - (100.0 * ((samples_per_sec -
+                                                  guest_kernel_samples_per_sec) /
+                                                 samples_per_sec)),
+                               100.0 - (100.0 * ((samples_per_sec -
+                                                  guest_us_samples_per_sec) /
+                                                 samples_per_sec)),
+                               esamples_percent);
+        }
+
+        if (top->evlist->nr_entries == 1 || !top->display_weighted) {
+                struct perf_evsel *first;
+                first = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+                ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
+                                (uint64_t)first->attr.sample_period,
+                                top->freq ? "Hz" : "");
+        }
+
+        if (!top->display_weighted) {
+                ret += SNPRINTF(bf + ret, size - ret, "%s",
+                                event_name(top->sym_evsel));
+        } else {
+                /*
+                 * Don't let events eat all the space. Leaving 30 bytes
+                 * for the rest should be enough.
+                 */
+                size_t last_pos = size - 30;
+
+                list_for_each_entry(counter, &top->evlist->entries, node) {
+                        ret += SNPRINTF(bf + ret, size - ret, "%s%s",
+                                        counter->idx ? "/" : "",
+                                        event_name(counter));
+                        if (ret > last_pos) {
+                                sprintf(bf + last_pos - 3, "..");
+                                ret = last_pos - 1;
+                                break;
+                        }
+                }
+        }
+
+        ret += SNPRINTF(bf + ret, size - ret, "], ");
+
+        if (top->target_pid != -1)
+                ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d",
+                                top->target_pid);
+        else if (top->target_tid != -1)
+                ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d",
+                                top->target_tid);
+        else
+                ret += SNPRINTF(bf + ret, size - ret, " (all");
+
+        if (top->cpu_list)
+                ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)",
+                                top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list);
+        else {
+                if (top->target_tid != -1)
+                        ret += SNPRINTF(bf + ret, size - ret, ")");
+                else
+                        ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)",
+                                        top->evlist->cpus->nr,
+                                        top->evlist->cpus->nr > 1 ? "s" : "");
+        }
+
+        return ret;
+}
+
+void perf_top__reset_sample_counters(struct perf_top *top)
+{
+        top->samples = top->us_samples = top->kernel_samples =
+        top->exact_samples = top->guest_kernel_samples =
+        top->guest_us_samples = 0;
+}
+
+float perf_top__decay_samples(struct perf_top *top, struct rb_root *root)
+{
+        struct sym_entry *syme, *n;
+        float sum_ksamples = 0.0;
+        int snap = !top->display_weighted ? top->sym_evsel->idx : 0, j;
+
+        /* Sort the active symbols */
+        pthread_mutex_lock(&top->active_symbols_lock);
+        syme = list_entry(top->active_symbols.next, struct sym_entry, node);
+        pthread_mutex_unlock(&top->active_symbols_lock);
+
+        top->rb_entries = 0;
+        list_for_each_entry_safe_from(syme, n, &top->active_symbols, node) {
+                syme->snap_count = syme->count[snap];
+                if (syme->snap_count != 0) {
+
+                        if ((top->hide_user_symbols &&
+                             syme->map->dso->kernel == DSO_TYPE_USER) ||
+                            (top->hide_kernel_symbols &&
+                             syme->map->dso->kernel == DSO_TYPE_KERNEL)) {
+                                perf_top__remove_active_sym(top, syme);
+                                continue;
+                        }
+                        syme->weight = sym_weight(syme, top);
+
+                        if ((int)syme->snap_count >= top->count_filter) {
+                                rb_insert_active_sym(root, syme);
+                                ++top->rb_entries;
+                        }
+                        sum_ksamples += syme->snap_count;
+
+                        for (j = 0; j < top->evlist->nr_entries; j++)
+                                syme->count[j] = top->zero ? 0 : syme->count[j] * 7 / 8;
+                } else
+                        perf_top__remove_active_sym(top, syme);
+        }
+
+        return sum_ksamples;
+}
+
+/*
+ * Find the longest symbol name that will be displayed
+ */
+void perf_top__find_widths(struct perf_top *top, struct rb_root *root,
+                           int *dso_width, int *dso_short_width, int *sym_width)
+{
+        struct rb_node *nd;
+        int printed = 0;
+
+        *sym_width = *dso_width = *dso_short_width = 0;
+
+        for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+                struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node);
+                struct symbol *sym = sym_entry__symbol(syme);
+
+                if (++printed > top->print_entries ||
+                    (int)syme->snap_count < top->count_filter)
+                        continue;
+
+                if (syme->map->dso->long_name_len > *dso_width)
+                        *dso_width = syme->map->dso->long_name_len;
+
+                if (syme->map->dso->short_name_len > *dso_short_width)
+                        *dso_short_width = syme->map->dso->short_name_len;
+
+                if (sym->namelen > *sym_width)
+                        *sym_width = sym->namelen;
+        }
+}
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
new file mode 100644
index 000000000000..bfbf95bcc603
--- /dev/null
+++ b/tools/perf/util/top.h
@@ -0,0 +1,64 @@
+#ifndef __PERF_TOP_H
+#define __PERF_TOP_H 1
+
+#include "types.h"
+#include "../perf.h"
+#include <stddef.h>
+#include <pthread.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct perf_evlist;
+struct perf_evsel;
+
+struct sym_entry {
+        struct rb_node          rb_node;
+        struct list_head        node;
+        unsigned long           snap_count;
+        double                  weight;
+        struct map              *map;
+        unsigned long           count[0];
+};
+
+static inline struct symbol *sym_entry__symbol(struct sym_entry *self)
+{
+       return ((void *)self) + symbol_conf.priv_size;
+}
+
+struct perf_top {
+        struct perf_evlist *evlist;
+        /*
+         * Symbols will be added here in perf_event__process_sample and will
+         * get out after decayed.
+         */
+        struct list_head   active_symbols;
+        pthread_mutex_t    active_symbols_lock;
+        pthread_cond_t     active_symbols_cond;
+        u64                samples;
+        u64                kernel_samples, us_samples;
+        u64                exact_samples;
+        u64                guest_us_samples, guest_kernel_samples;
+        int                print_entries, count_filter, delay_secs;
+        int                display_weighted, freq, rb_entries;
+        pid_t              target_pid, target_tid;
+        bool               hide_kernel_symbols, hide_user_symbols, zero;
+        const char         *cpu_list;
+        struct sym_entry   *sym_filter_entry;
+        struct perf_evsel  *sym_evsel;
+};
+
+size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
+void perf_top__reset_sample_counters(struct perf_top *top);
+float perf_top__decay_samples(struct perf_top *top, struct rb_root *root);
+void perf_top__find_widths(struct perf_top *top, struct rb_root *root,
+                           int *dso_width, int *dso_short_width, int *sym_width);
+
+#ifdef NO_NEWT_SUPPORT
+static inline int perf_top__tui_browser(struct perf_top *top __used)
+{
+        return 0;
+}
+#else
+int perf_top__tui_browser(struct perf_top *top);
+#endif
+#endif /* __PERF_TOP_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index b1572601286c..35729f4c40cb 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -34,11 +34,13 @@
 #include <ctype.h>
 #include <errno.h>
 #include <stdbool.h>
+#include <linux/list.h>
 #include <linux/kernel.h>
 
 #include "../perf.h"
 #include "trace-event.h"
 #include "debugfs.h"
+#include "evsel.h"
 
 #define VERSION "0.5"
 
@@ -469,16 +471,17 @@ out:
 }
 
 static struct tracepoint_path *
-get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events)
+get_tracepoints_path(struct list_head *pattrs)
 {
         struct tracepoint_path path, *ppath = &path;
-        int i, nr_tracepoints = 0;
+        struct perf_evsel *pos;
+        int nr_tracepoints = 0;
 
-        for (i = 0; i < nb_events; i++) {
-                if (pattrs[i].type != PERF_TYPE_TRACEPOINT)
+        list_for_each_entry(pos, pattrs, node) {
+                if (pos->attr.type != PERF_TYPE_TRACEPOINT)
                         continue;
                 ++nr_tracepoints;
-                ppath->next = tracepoint_id_to_path(pattrs[i].config);
+                ppath->next = tracepoint_id_to_path(pos->attr.config);
                 if (!ppath->next)
                         die("%s\n", "No memory to alloc tracepoints list");
                 ppath = ppath->next;
@@ -487,21 +490,21 @@ get_tracepoints_path(struct perf_event_attr *pattrs, int nb_events)
         return nr_tracepoints > 0 ? path.next : NULL;
 }
 
-bool have_tracepoints(struct perf_event_attr *pattrs, int nb_events)
+bool have_tracepoints(struct list_head *pattrs)
 {
-        int i;
+        struct perf_evsel *pos;
 
-        for (i = 0; i < nb_events; i++)
-                if (pattrs[i].type == PERF_TYPE_TRACEPOINT)
+        list_for_each_entry(pos, pattrs, node)
+                if (pos->attr.type == PERF_TYPE_TRACEPOINT)
                         return true;
 
         return false;
 }
 
-int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
+int read_tracing_data(int fd, struct list_head *pattrs)
 {
         char buf[BUFSIZ];
-        struct tracepoint_path *tps = get_tracepoints_path(pattrs, nb_events);
+        struct tracepoint_path *tps = get_tracepoints_path(pattrs);
 
         /*
          * What? No tracepoints? No sense writing anything here, bail out.
@@ -545,14 +548,13 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
         return 0;
 }
 
-ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
-                               int nb_events)
+ssize_t read_tracing_data_size(int fd, struct list_head *pattrs)
 {
         ssize_t size;
         int err = 0;
 
         calc_data_size = 1;
-        err = read_tracing_data(fd, pattrs, nb_events);
+        err = read_tracing_data(fd, pattrs);
         size = calc_data_size - 1;
         calc_data_size = 0;
 
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 73a02223c629..0a7ed5b5e281 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -153,7 +153,7 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused)
         char *next = NULL;
         char *addr_str;
         char ch;
-        int ret;
+        int ret __used;
         int i;
 
         line = strtok_r(file, "\n", &next);
@@ -2643,68 +2643,13 @@ static void print_lat_fmt(void *data, int size __unused)
                 printf(".");
 
         if (lock_depth < 0)
-                printf(".");
+                printf(". ");
         else
-                printf("%d", lock_depth);
-}
-
-/* taken from Linux, written by Frederic Weisbecker */
-static void print_graph_cpu(int cpu)
-{
-        int i;
-        int log10_this = log10_cpu(cpu);
-        int log10_all = log10_cpu(cpus);
-
-
-        /*
-         * Start with a space character - to make it stand out
-         * to the right a bit when trace output is pasted into
-         * email:
-         */
-        printf(" ");
-
-        /*
-         * Tricky - we space the CPU field according to the max
-         * number of online CPUs. On a 2-cpu system it would take
-         * a maximum of 1 digit - on a 128 cpu system it would
-         * take up to 3 digits:
-         */
-        for (i = 0; i < log10_all - log10_this; i++)
-                printf(" ");
-
-        printf("%d) ", cpu);
+                printf("%d ", lock_depth);
 }
 
-#define TRACE_GRAPH_PROCINFO_LENGTH     14
 #define TRACE_GRAPH_INDENT      2
 
-static void print_graph_proc(int pid, const char *comm)
-{
-        /* sign + log10(MAX_INT) + '\0' */
-        char pid_str[11];
-        int spaces = 0;
-        int len;
-        int i;
-
-        sprintf(pid_str, "%d", pid);
-
-        /* 1 stands for the "-" character */
-        len = strlen(comm) + strlen(pid_str) + 1;
-
-        if (len < TRACE_GRAPH_PROCINFO_LENGTH)
-                spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;
-
-        /* First spaces to align center */
-        for (i = 0; i < spaces / 2; i++)
-                printf(" ");
-
-        printf("%s-%s", comm, pid_str);
-
-        /* Last spaces to align center */
-        for (i = 0; i < spaces - (spaces / 2); i++)
-                printf(" ");
-}
-
 static struct record *
 get_return_for_leaf(int cpu, int cur_pid, unsigned long long cur_func,
                     struct record *next)
@@ -2876,21 +2821,13 @@ static void print_graph_nested(struct event *event, void *data)
 
 static void
 pretty_print_func_ent(void *data, int size, struct event *event,
-                      int cpu, int pid, const char *comm,
-                      unsigned long secs, unsigned long usecs)
+                      int cpu, int pid)
 {
         struct format_field *field;
         struct record *rec;
         void *copy_data;
         unsigned long val;
 
-        printf("%5lu.%06lu |  ", secs, usecs);
-
-        print_graph_cpu(cpu);
-        print_graph_proc(pid, comm);
-
-        printf(" | ");
-
         if (latency_format) {
                 print_lat_fmt(data, size);
                 printf(" | ");
@@ -2923,22 +2860,13 @@ out_free:
 }
 
 static void
-pretty_print_func_ret(void *data, int size __unused, struct event *event,
-                      int cpu, int pid, const char *comm,
-                      unsigned long secs, unsigned long usecs)
+pretty_print_func_ret(void *data, int size __unused, struct event *event)
 {
         unsigned long long rettime, calltime;
         unsigned long long duration, depth;
         struct format_field *field;
         int i;
 
-        printf("%5lu.%06lu |  ", secs, usecs);
-
-        print_graph_cpu(cpu);
-        print_graph_proc(pid, comm);
-
-        printf(" | ");
-
         if (latency_format) {
                 print_lat_fmt(data, size);
                 printf(" | ");
@@ -2976,31 +2904,21 @@ pretty_print_func_ret(void *data, int size __unused, struct event *event,
 
 static void
 pretty_print_func_graph(void *data, int size, struct event *event,
-                        int cpu, int pid, const char *comm,
-                        unsigned long secs, unsigned long usecs)
+                        int cpu, int pid)
 {
         if (event->flags & EVENT_FL_ISFUNCENT)
-                pretty_print_func_ent(data, size, event,
-                                      cpu, pid, comm, secs, usecs);
+                pretty_print_func_ent(data, size, event, cpu, pid);
         else if (event->flags & EVENT_FL_ISFUNCRET)
-                pretty_print_func_ret(data, size, event,
-                                      cpu, pid, comm, secs, usecs);
+                pretty_print_func_ret(data, size, event);
         printf("\n");
 }
 
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-                  char *comm)
+void print_trace_event(int cpu, void *data, int size)
 {
         struct event *event;
-        unsigned long secs;
-        unsigned long usecs;
         int type;
         int pid;
 
-        secs = nsecs / NSECS_PER_SEC;
-        nsecs -= secs * NSECS_PER_SEC;
-        usecs = nsecs / NSECS_PER_USEC;
-
         type = trace_parse_common_type(data);
 
         event = trace_find_event(type);
@@ -3012,17 +2930,10 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs,
         pid = trace_parse_common_pid(data);
 
         if (event->flags & (EVENT_FL_ISFUNCENT | EVENT_FL_ISFUNCRET))
-                return pretty_print_func_graph(data, size, event, cpu,
-                                               pid, comm, secs, usecs);
+                return pretty_print_func_graph(data, size, event, cpu, pid);
 
-        if (latency_format) {
-                printf("%8.8s-%-5d %3d",
-                       comm, pid, cpu);
+        if (latency_format)
                 print_lat_fmt(data, size);
-        } else
-                printf("%16s-%-5d [%03d]", comm, pid,  cpu);
-
-        printf(" %5lu.%06lu: %s: ", secs, usecs, event->name);
 
         if (event->flags & EVENT_FL_FAILED) {
                 printf("EVENT '%s' FAILED TO PARSE\n",
@@ -3031,7 +2942,6 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs,
         }
 
         pretty_print(data, size, event);
-        printf("\n");
 }
 
 static void print_fields(struct print_flag_sym *field)
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index f7af2fca965d..c9dcbec7d800 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -36,11 +36,11 @@ static int stop_script_unsupported(void)
         return 0;
 }
 
-static void process_event_unsupported(int cpu __unused,
-                                      void *data __unused,
-                                      int size __unused,
-                                      unsigned long long nsecs __unused,
-                                      char *comm __unused)
+static void process_event_unsupported(union perf_event *event __unused,
+                                      struct perf_sample *sample __unused,
+                                      struct perf_evsel *evsel __unused,
+                                      struct perf_session *session __unused,
+                                      struct thread *thread __unused)
 {
 }
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b3e86b1e4444..f674dda3363b 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "parse-events.h"
+#include "session.h"
 
 #define __unused __attribute__((unused))
 
@@ -176,8 +177,7 @@ void print_printk(void);
 
 int parse_ftrace_file(char *buf, unsigned long size);
 int parse_event_file(char *buf, unsigned long size, char *sys);
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-                  char *comm);
+void print_trace_event(int cpu, void *data, int size);
 
 extern int file_bigendian;
 extern int host_bigendian;
@@ -262,9 +262,8 @@ raw_field_value(struct event *event, const char *name, void *data);
 void *raw_field_ptr(struct event *event, const char *name, void *data);
 unsigned long long eval_flag(const char *flag);
 
-int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
-ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
-                               int nb_events);
+int read_tracing_data(int fd, struct list_head *pattrs);
+ssize_t read_tracing_data_size(int fd, struct list_head *pattrs);
 
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {
@@ -279,8 +278,11 @@ struct scripting_ops {
         const char *name;
         int (*start_script) (const char *script, int argc, const char **argv);
         int (*stop_script) (void);
-        void (*process_event) (int cpu, void *data, int size,
-                               unsigned long long nsecs, char *comm);
+        void (*process_event) (union perf_event *event,
+                               struct perf_sample *sample,
+                               struct perf_evsel *evsel,
+                               struct perf_session *session,
+                               struct thread *thread);
         int (*generate_script) (const char *outfile);
 };
 
diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h
index 7d6b8331f898..5f3689a3d085 100644
--- a/tools/perf/util/types.h
+++ b/tools/perf/util/types.h
@@ -1,12 +1,14 @@
 #ifndef __PERF_TYPES_H
 #define __PERF_TYPES_H
 
+#include <stdint.h>
+
 /*
- * We define u64 as unsigned long long for every architecture
- * so that we can print it with %Lx without getting warnings.
+ * We define u64 as uint64_t for every architecture
+ * so that we can print it with "%"PRIx64 without getting warnings.
  */
-typedef unsigned long long u64;
-typedef signed long long   s64;
+typedef uint64_t           u64;
+typedef int64_t            s64;
 typedef unsigned int       u32;
 typedef signed int         s32;
 typedef unsigned short     u16;
diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c
index 66f2d583d8c4..611219f80680 100644
--- a/tools/perf/util/ui/browser.c
+++ b/tools/perf/util/ui/browser.c
@@ -1,16 +1,6 @@
-#define _GNU_SOURCE
-#include <stdio.h>
-#undef _GNU_SOURCE
-/*
- * slang versions <= 2.0.6 have a "#if HAVE_LONG_LONG" that breaks
- * the build if it isn't defined. Use the equivalent one that glibc
- * has on features.h.
- */
-#include <features.h>
-#ifndef HAVE_LONG_LONG
-#define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG
-#endif
-#include <slang.h>
+#include "libslang.h"
+#include "ui.h"
+#include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <stdlib.h>
@@ -19,17 +9,9 @@
 #include "helpline.h"
 #include "../color.h"
 #include "../util.h"
+#include <stdio.h>
 
-#if SLANG_VERSION < 20104
-#define sltt_set_color(obj, name, fg, bg) \
-        SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg)
-#else
-#define sltt_set_color SLtt_set_color
-#endif
-
-newtComponent newt_form__new(void);
-
-int ui_browser__percent_color(double percent, bool current)
+static int ui_browser__percent_color(double percent, bool current)
 {
         if (current)
                 return HE_COLORSET_SELECTED;
@@ -40,6 +22,23 @@ int ui_browser__percent_color(double percent, bool current)
         return HE_COLORSET_NORMAL;
 }
 
+void ui_browser__set_color(struct ui_browser *self __used, int color)
+{
+        SLsmg_set_color(color);
+}
+
+void ui_browser__set_percent_color(struct ui_browser *self,
+                                   double percent, bool current)
+{
+         int color = ui_browser__percent_color(percent, current);
+         ui_browser__set_color(self, color);
+}
+
+void ui_browser__gotorc(struct ui_browser *self, int y, int x)
+{
+        SLsmg_gotorc(self->y + y, self->x + x);
+}
+
 void ui_browser__list_head_seek(struct ui_browser *self, off_t offset, int whence)
 {
         struct list_head *head = self->entries;
@@ -111,7 +110,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self)
         nd = self->top;
 
         while (nd != NULL) {
-                SLsmg_gotorc(self->y + row, self->x);
+                ui_browser__gotorc(self, row, 0);
                 self->write(self, nd, row);
                 if (++row == self->height)
                         break;
@@ -131,13 +130,10 @@ void ui_browser__refresh_dimensions(struct ui_browser *self)
         int cols, rows;
         newtGetScreenSize(&cols, &rows);
 
-        if (self->width > cols - 4)
-                self->width = cols - 4;
-        self->height = rows - 5;
-        if (self->height > self->nr_entries)
-                self->height = self->nr_entries;
-        self->y  = (rows - self->height) / 2;
-        self->x = (cols - self->width) / 2;
+        self->width = cols - 1;
+        self->height = rows - 2;
+        self->y = 1;
+        self->x = 0;
 }
 
 void ui_browser__reset_index(struct ui_browser *self)
@@ -146,78 +142,109 @@ void ui_browser__reset_index(struct ui_browser *self)
         self->seek(self, 0, SEEK_SET);
 }
 
+void ui_browser__add_exit_key(struct ui_browser *self, int key)
+{
+        newtFormAddHotKey(self->form, key);
+}
+
+void ui_browser__add_exit_keys(struct ui_browser *self, int keys[])
+{
+        int i = 0;
+
+        while (keys[i] && i < 64) {
+                ui_browser__add_exit_key(self, keys[i]);
+                ++i;
+        }
+}
+
+void __ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+        SLsmg_gotorc(0, 0);
+        ui_browser__set_color(browser, NEWT_COLORSET_ROOT);
+        slsmg_write_nstring(title, browser->width);
+}
+
+void ui_browser__show_title(struct ui_browser *browser, const char *title)
+{
+        pthread_mutex_lock(&ui__lock);
+        __ui_browser__show_title(browser, title);
+        pthread_mutex_unlock(&ui__lock);
+}
+
 int ui_browser__show(struct ui_browser *self, const char *title,
                      const char *helpline, ...)
 {
         va_list ap;
+        int keys[] = { NEWT_KEY_UP, NEWT_KEY_DOWN, NEWT_KEY_PGUP,
+                       NEWT_KEY_PGDN, NEWT_KEY_HOME, NEWT_KEY_END, ' ',
+                       NEWT_KEY_LEFT, NEWT_KEY_ESCAPE, 'q', CTRL('c'), 0 };
 
-        if (self->form != NULL) {
+        if (self->form != NULL)
                 newtFormDestroy(self->form);
-                newtPopWindow();
-        }
+
         ui_browser__refresh_dimensions(self);
-        newtCenteredWindow(self->width, self->height, title);
-        self->form = newt_form__new();
+        self->form = newtForm(NULL, NULL, 0);
         if (self->form == NULL)
                 return -1;
 
-        self->sb = newtVerticalScrollbar(self->width, 0, self->height,
+        self->sb = newtVerticalScrollbar(self->width, 1, self->height,
                                          HE_COLORSET_NORMAL,
                                          HE_COLORSET_SELECTED);
         if (self->sb == NULL)
                 return -1;
 
-        newtFormAddHotKey(self->form, NEWT_KEY_UP);
-        newtFormAddHotKey(self->form, NEWT_KEY_DOWN);
-        newtFormAddHotKey(self->form, NEWT_KEY_PGUP);
-        newtFormAddHotKey(self->form, NEWT_KEY_PGDN);
-        newtFormAddHotKey(self->form, NEWT_KEY_HOME);
-        newtFormAddHotKey(self->form, NEWT_KEY_END);
-        newtFormAddHotKey(self->form, ' ');
+        pthread_mutex_lock(&ui__lock);
+        __ui_browser__show_title(self, title);
+
+        ui_browser__add_exit_keys(self, keys);
         newtFormAddComponent(self->form, self->sb);
 
         va_start(ap, helpline);
         ui_helpline__vpush(helpline, ap);
         va_end(ap);
+        pthread_mutex_unlock(&ui__lock);
         return 0;
 }
 
 void ui_browser__hide(struct ui_browser *self)
 {
+        pthread_mutex_lock(&ui__lock);
         newtFormDestroy(self->form);
-        newtPopWindow();
         self->form = NULL;
         ui_helpline__pop();
+        pthread_mutex_unlock(&ui__lock);
 }
 
 int ui_browser__refresh(struct ui_browser *self)
 {
         int row;
 
+        pthread_mutex_lock(&ui__lock);
         newtScrollbarSet(self->sb, self->index, self->nr_entries - 1);
         row = self->refresh(self);
-        SLsmg_set_color(HE_COLORSET_NORMAL);
+        ui_browser__set_color(self, HE_COLORSET_NORMAL);
         SLsmg_fill_region(self->y + row, self->x,
                           self->height - row, self->width, ' ');
+        pthread_mutex_unlock(&ui__lock);
 
         return 0;
 }
 
-int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es)
+int ui_browser__run(struct ui_browser *self)
 {
+        struct newtExitStruct es;
+
         if (ui_browser__refresh(self) < 0)
                 return -1;
 
         while (1) {
                 off_t offset;
 
-                newtFormRun(self->form, es);
+                newtFormRun(self->form, &es);
 
-                if (es->reason != NEWT_EXIT_HOTKEY)
+                if (es.reason != NEWT_EXIT_HOTKEY)
                         break;
-                if (is_exit_key(es->u.key))
-                        return es->u.key;
-                switch (es->u.key) {
+                switch (es.u.key) {
                 case NEWT_KEY_DOWN:
                         if (self->index == self->nr_entries - 1)
                                 break;
@@ -274,12 +301,12 @@ int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es)
                         self->seek(self, -offset, SEEK_END);
                         break;
                 default:
-                        return es->u.key;
+                        return es.u.key;
                 }
                 if (ui_browser__refresh(self) < 0)
                         return -1;
         }
-        return 0;
+        return -1;
 }
 
 unsigned int ui_browser__list_head_refresh(struct ui_browser *self)
@@ -294,7 +321,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *self)
         pos = self->top;
 
         list_for_each_from(pos, head) {
-                SLsmg_gotorc(self->y + row, self->x);
+                ui_browser__gotorc(self, row, 0);
                 self->write(self, pos, row);
                 if (++row == self->height)
                         break;
diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h
index 0b9f829214f7..fc63dda10910 100644
--- a/tools/perf/util/ui/browser.h
+++ b/tools/perf/util/ui/browser.h
@@ -24,17 +24,23 @@ struct ui_browser {
         u32           nr_entries;
 };
 
-
-int ui_browser__percent_color(double percent, bool current);
+void ui_browser__set_color(struct ui_browser *self, int color);
+void ui_browser__set_percent_color(struct ui_browser *self,
+                                   double percent, bool current);
 bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row);
 void ui_browser__refresh_dimensions(struct ui_browser *self);
 void ui_browser__reset_index(struct ui_browser *self);
 
+void ui_browser__gotorc(struct ui_browser *self, int y, int x);
+void ui_browser__add_exit_key(struct ui_browser *self, int key);
+void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]);
+void __ui_browser__show_title(struct ui_browser *browser, const char *title);
+void ui_browser__show_title(struct ui_browser *browser, const char *title);
 int ui_browser__show(struct ui_browser *self, const char *title,
                      const char *helpline, ...);
 void ui_browser__hide(struct ui_browser *self);
 int ui_browser__refresh(struct ui_browser *self);
-int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es);
+int ui_browser__run(struct ui_browser *self);
 
 void ui_browser__rb_tree_seek(struct ui_browser *self, off_t offset, int whence);
 unsigned int ui_browser__rb_tree_refresh(struct ui_browser *self);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index a90273e63f4f..0229723aceb3 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -1,9 +1,11 @@
 #include "../browser.h"
 #include "../helpline.h"
 #include "../libslang.h"
+#include "../../annotate.h"
 #include "../../hist.h"
 #include "../../sort.h"
 #include "../../symbol.h"
+#include <pthread.h>
 
 static void ui__error_window(const char *fmt, ...)
 {
@@ -40,14 +42,10 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
 
         if (ol->offset != -1) {
                 struct objdump_line_rb_node *olrb = objdump_line__rb(ol);
-                int color = ui_browser__percent_color(olrb->percent, current_entry);
-                SLsmg_set_color(color);
+                ui_browser__set_percent_color(self, olrb->percent, current_entry);
                 slsmg_printf(" %7.2f ", olrb->percent);
-                if (!current_entry)
-                        SLsmg_set_color(HE_COLORSET_CODE);
         } else {
-                int color = ui_browser__percent_color(0, current_entry);
-                SLsmg_set_color(color);
+                ui_browser__set_percent_color(self, 0, current_entry);
                 slsmg_write_nstring(" ", 9);
         }
 
@@ -57,35 +55,40 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro
                 slsmg_write_nstring(" ", width - 18);
         else
                 slsmg_write_nstring(ol->line, width - 18);
+
+        if (!current_entry)
+                ui_browser__set_color(self, HE_COLORSET_CODE);
 }
 
 static double objdump_line__calc_percent(struct objdump_line *self,
-                                         struct list_head *head,
-                                         struct symbol *sym)
+                                         struct symbol *sym, int evidx)
 {
         double percent = 0.0;
 
         if (self->offset != -1) {
                 int len = sym->end - sym->start;
                 unsigned int hits = 0;
-                struct sym_priv *priv = symbol__priv(sym);
-                struct sym_ext *sym_ext = priv->ext;
-                struct sym_hist *h = priv->hist;
+                struct annotation *notes = symbol__annotation(sym);
+                struct source_line *src_line = notes->src->lines;
+                struct sym_hist *h = annotation__histogram(notes, evidx);
                 s64 offset = self->offset;
-                struct objdump_line *next = objdump__get_next_ip_line(head, self);
-
+                struct objdump_line *next;
 
+                next = objdump__get_next_ip_line(&notes->src->source, self);
                 while (offset < (s64)len &&
                        (next == NULL || offset < next->offset)) {
-                        if (sym_ext) {
-                                percent += sym_ext[offset].percent;
+                        if (src_line) {
+                                percent += src_line[offset].percent;
                         } else
-                                hits += h->ip[offset];
+                                hits += h->addr[offset];
 
                         ++offset;
                 }
-
-                if (sym_ext == NULL && h->sum)
+                /*
+                 * If the percentage wasn't already calculated in
+                 * symbol__get_source_line, do it now:
+                 */
+                if (src_line == NULL && h->sum)
                         percent = 100.0 * hits / h->sum;
         }
 
@@ -135,105 +138,163 @@ static void annotate_browser__set_top(struct annotate_browser *self,
         self->curr_hot = nd;
 }
 
-static int annotate_browser__run(struct annotate_browser *self,
-                                 struct newtExitStruct *es)
+static void annotate_browser__calc_percent(struct annotate_browser *browser,
+                                           int evidx)
+{
+        struct symbol *sym = browser->b.priv;
+        struct annotation *notes = symbol__annotation(sym);
+        struct objdump_line *pos;
+
+        browser->entries = RB_ROOT;
+
+        pthread_mutex_lock(&notes->lock);
+
+        list_for_each_entry(pos, &notes->src->source, node) {
+                struct objdump_line_rb_node *rbpos = objdump_line__rb(pos);
+                rbpos->percent = objdump_line__calc_percent(pos, sym, evidx);
+                if (rbpos->percent < 0.01) {
+                        RB_CLEAR_NODE(&rbpos->rb_node);
+                        continue;
+                }
+                objdump__insert_line(&browser->entries, rbpos);
+        }
+        pthread_mutex_unlock(&notes->lock);
+
+        browser->curr_hot = rb_last(&browser->entries);
+}
+
+static int annotate_browser__run(struct annotate_browser *self, int evidx,
+                                 int refresh)
 {
-        struct rb_node *nd;
-        struct hist_entry *he = self->b.priv;
+        struct rb_node *nd = NULL;
+        struct symbol *sym = self->b.priv;
+        /*
+         * RIGHT To allow builtin-annotate to cycle thru multiple symbols by
+         * examining the exit key for this function.
+         */
+        int exit_keys[] = { 'H', NEWT_KEY_TAB, NEWT_KEY_UNTAB,
+                            NEWT_KEY_RIGHT, 0 };
+        int key;
 
-        if (ui_browser__show(&self->b, he->ms.sym->name,
-                             "<- or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0)
+        if (ui_browser__show(&self->b, sym->name,
+                             "<-, -> or ESC: exit, TAB/shift+TAB: "
+                             "cycle hottest lines, H: Hottest") < 0)
                 return -1;
 
-        newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-        newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
+        ui_browser__add_exit_keys(&self->b, exit_keys);
+        annotate_browser__calc_percent(self, evidx);
+
+        if (self->curr_hot)
+                annotate_browser__set_top(self, self->curr_hot);
 
         nd = self->curr_hot;
-        if (nd) {
-                newtFormAddHotKey(self->b.form, NEWT_KEY_TAB);
-                newtFormAddHotKey(self->b.form, NEWT_KEY_UNTAB);
-        }
 
-        while (1) {
-                ui_browser__run(&self->b, es);
+        if (refresh != 0)
+                newtFormSetTimer(self->b.form, refresh);
 
-                if (es->reason != NEWT_EXIT_HOTKEY)
-                        break;
+        while (1) {
+                key = ui_browser__run(&self->b);
+
+                if (refresh != 0) {
+                        annotate_browser__calc_percent(self, evidx);
+                        /*
+                         * Current line focus got out of the list of most active
+                         * lines, NULL it so that if TAB|UNTAB is pressed, we
+                         * move to curr_hot (current hottest line).
+                         */
+                        if (nd != NULL && RB_EMPTY_NODE(nd))
+                                nd = NULL;
+                }
 
-                switch (es->u.key) {
+                switch (key) {
+                case -1:
+                        /*
+                         * FIXME we need to check if it was
+                         * es.reason == NEWT_EXIT_TIMER
+                         */
+                        if (refresh != 0)
+                                symbol__annotate_decay_histogram(sym, evidx);
+                        continue;
                 case NEWT_KEY_TAB:
-                        nd = rb_prev(nd);
-                        if (nd == NULL)
-                                nd = rb_last(&self->entries);
-                        annotate_browser__set_top(self, nd);
+                        if (nd != NULL) {
+                                nd = rb_prev(nd);
+                                if (nd == NULL)
+                                        nd = rb_last(&self->entries);
+                        } else
+                                nd = self->curr_hot;
                         break;
                 case NEWT_KEY_UNTAB:
-                        nd = rb_next(nd);
-                        if (nd == NULL)
-                                nd = rb_first(&self->entries);
-                        annotate_browser__set_top(self, nd);
+                        if (nd != NULL)
+                                nd = rb_next(nd);
+                                if (nd == NULL)
+                                        nd = rb_first(&self->entries);
+                        else
+                                nd = self->curr_hot;
+                        break;
+                case 'H':
+                        nd = self->curr_hot;
                         break;
                 default:
                         goto out;
                 }
+
+                if (nd != NULL)
+                        annotate_browser__set_top(self, nd);
         }
 out:
         ui_browser__hide(&self->b);
-        return es->u.key;
+        return key;
 }
 
-int hist_entry__tui_annotate(struct hist_entry *self)
+int hist_entry__tui_annotate(struct hist_entry *he, int evidx)
+{
+        return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, 0);
+}
+
+int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
+                         int refresh)
 {
-        struct newtExitStruct es;
         struct objdump_line *pos, *n;
-        struct objdump_line_rb_node *rbpos;
-        LIST_HEAD(head);
+        struct annotation *notes;
         struct annotate_browser browser = {
                 .b = {
-                        .entries = &head,
                         .refresh = ui_browser__list_head_refresh,
                         .seek    = ui_browser__list_head_seek,
                         .write   = annotate_browser__write,
-                        .priv    = self,
+                        .priv    = sym,
                 },
         };
         int ret;
 
-        if (self->ms.sym == NULL)
+        if (sym == NULL)
                 return -1;
 
-        if (self->ms.map->dso->annotate_warned)
+        if (map->dso->annotate_warned)
                 return -1;
 
-        if (hist_entry__annotate(self, &head, sizeof(*rbpos)) < 0) {
+        if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) {
                 ui__error_window(ui_helpline__last_msg);
                 return -1;
         }
 
         ui_helpline__push("Press <- or ESC to exit");
 
-        list_for_each_entry(pos, &head, node) {
+        notes = symbol__annotation(sym);
+
+        list_for_each_entry(pos, &notes->src->source, node) {
+                struct objdump_line_rb_node *rbpos;
                 size_t line_len = strlen(pos->line);
+
                 if (browser.b.width < line_len)
                         browser.b.width = line_len;
                 rbpos = objdump_line__rb(pos);
                 rbpos->idx = browser.b.nr_entries++;
-                rbpos->percent = objdump_line__calc_percent(pos, &head, self->ms.sym);
-                if (rbpos->percent < 0.01)
-                        continue;
-                objdump__insert_line(&browser.entries, rbpos);
         }
 
-        /*
-         * Position the browser at the hottest line.
-         */
-        browser.curr_hot = rb_last(&browser.entries);
-        if (browser.curr_hot)
-                annotate_browser__set_top(&browser, browser.curr_hot);
-
+        browser.b.entries = &notes->src->source,
         browser.b.width += 18; /* Percentage */
-        ret = annotate_browser__run(&browser, &es);
-        list_for_each_entry_safe(pos, n, &head, node) {
+        ret = annotate_browser__run(&browser, evidx, refresh);
+        list_for_each_entry_safe(pos, n, &notes->src->source, node) {
                 list_del(&pos->node);
                 objdump_line__free(pos);
         }
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 6866aa4c41e0..5d767c622dfc 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -7,6 +7,8 @@
 #include <newt.h>
 #include <linux/rbtree.h>
 
+#include "../../evsel.h"
+#include "../../evlist.h"
 #include "../../hist.h"
 #include "../../pstack.h"
 #include "../../sort.h"
@@ -58,6 +60,11 @@ static char callchain_list__folded(const struct callchain_list *self)
         return map_symbol__folded(&self->ms);
 }
 
+static void map_symbol__set_folding(struct map_symbol *self, bool unfold)
+{
+        self->unfolded = unfold ? self->has_children : false;
+}
+
 static int callchain_node__count_rows_rb_tree(struct callchain_node *self)
 {
         int n = 0;
@@ -129,16 +136,16 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *se
         for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
                 struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
                 struct callchain_list *chain;
-                int first = true;
+                bool first = true;
 
                 list_for_each_entry(chain, &child->val, list) {
                         if (first) {
                                 first = false;
                                 chain->ms.has_children = chain->list.next != &child->val ||
-                                                         rb_first(&child->rb_root) != NULL;
+                                                         !RB_EMPTY_ROOT(&child->rb_root);
                         } else
                                 chain->ms.has_children = chain->list.next == &child->val &&
-                                                         rb_first(&child->rb_root) != NULL;
+                                                         !RB_EMPTY_ROOT(&child->rb_root);
                 }
 
                 callchain_node__init_have_children_rb_tree(child);
@@ -150,7 +157,7 @@ static void callchain_node__init_have_children(struct callchain_node *self)
         struct callchain_list *chain;
 
         list_for_each_entry(chain, &self->val, list)
-                chain->ms.has_children = rb_first(&self->rb_root) != NULL;
+                chain->ms.has_children = !RB_EMPTY_ROOT(&self->rb_root);
 
         callchain_node__init_have_children_rb_tree(self);
 }
@@ -168,6 +175,7 @@ static void callchain__init_have_children(struct rb_root *self)
 static void hist_entry__init_have_children(struct hist_entry *self)
 {
         if (!self->init_have_children) {
+                self->ms.has_children = !RB_EMPTY_ROOT(&self->sorted_chain);
                 callchain__init_have_children(&self->sorted_chain);
                 self->init_have_children = true;
         }
@@ -195,43 +203,115 @@ static bool hist_browser__toggle_fold(struct hist_browser *self)
         return false;
 }
 
-static int hist_browser__run(struct hist_browser *self, const char *title,
-                             struct newtExitStruct *es)
+static int callchain_node__set_folding_rb_tree(struct callchain_node *self, bool unfold)
 {
-        char str[256], unit;
-        unsigned long nr_events = self->hists->stats.nr_events[PERF_RECORD_SAMPLE];
+        int n = 0;
+        struct rb_node *nd;
+
+        for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) {
+                struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node);
+                struct callchain_list *chain;
+                bool has_children = false;
+
+                list_for_each_entry(chain, &child->val, list) {
+                        ++n;
+                        map_symbol__set_folding(&chain->ms, unfold);
+                        has_children = chain->ms.has_children;
+                }
+
+                if (has_children)
+                        n += callchain_node__set_folding_rb_tree(child, unfold);
+        }
+
+        return n;
+}
+
+static int callchain_node__set_folding(struct callchain_node *node, bool unfold)
+{
+        struct callchain_list *chain;
+        bool has_children = false;
+        int n = 0;
+
+        list_for_each_entry(chain, &node->val, list) {
+                ++n;
+                map_symbol__set_folding(&chain->ms, unfold);
+                has_children = chain->ms.has_children;
+        }
+
+        if (has_children)
+                n += callchain_node__set_folding_rb_tree(node, unfold);
+
+        return n;
+}
+
+static int callchain__set_folding(struct rb_root *chain, bool unfold)
+{
+        struct rb_node *nd;
+        int n = 0;
+
+        for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
+                struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+                n += callchain_node__set_folding(node, unfold);
+        }
+
+        return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *self, bool unfold)
+{
+        hist_entry__init_have_children(self);
+        map_symbol__set_folding(&self->ms, unfold);
+
+        if (self->ms.has_children) {
+                int n = callchain__set_folding(&self->sorted_chain, unfold);
+                self->nr_rows = unfold ? n : 0;
+        } else
+                self->nr_rows = 0;
+}
+
+static void hists__set_folding(struct hists *self, bool unfold)
+{
+        struct rb_node *nd;
+
+        self->nr_entries = 0;
+
+        for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
+                struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
+                hist_entry__set_folding(he, unfold);
+                self->nr_entries += 1 + he->nr_rows;
+        }
+}
+
+static void hist_browser__set_folding(struct hist_browser *self, bool unfold)
+{
+        hists__set_folding(self->hists, unfold);
+        self->b.nr_entries = self->hists->nr_entries;
+        /* Go to the start, we may be way after valid entries after a collapse */
+        ui_browser__reset_index(&self->b);
+}
+
+static int hist_browser__run(struct hist_browser *self, const char *title)
+{
+        int key;
+        int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't',
+                            NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT,
+                            NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0, };
 
         self->b.entries = &self->hists->entries;
         self->b.nr_entries = self->hists->nr_entries;
 
         hist_browser__refresh_dimensions(self);
 
-        nr_events = convert_unit(nr_events, &unit);
-        snprintf(str, sizeof(str), "Events: %lu%c                            ",
-                 nr_events, unit);
-        newtDrawRootText(0, 0, str);
-
         if (ui_browser__show(&self->b, title,
                              "Press '?' for help on key bindings") < 0)
                 return -1;
 
-        newtFormAddHotKey(self->b.form, 'a');
-        newtFormAddHotKey(self->b.form, '?');
-        newtFormAddHotKey(self->b.form, 'h');
-        newtFormAddHotKey(self->b.form, 'd');
-        newtFormAddHotKey(self->b.form, 'D');
-        newtFormAddHotKey(self->b.form, 't');
-
-        newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-        newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT);
-        newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER);
+        ui_browser__add_exit_keys(&self->b, exit_keys);
 
         while (1) {
-                ui_browser__run(&self->b, es);
+                key = ui_browser__run(&self->b);
 
-                if (es->reason != NEWT_EXIT_HOTKEY)
-                        break;
-                switch (es->u.key) {
+                switch (key) {
                 case 'D': { /* Debug */
                         static int seq;
                         struct hist_entry *h = rb_entry(self->b.top,
@@ -245,18 +325,26 @@ static int hist_browser__run(struct hist_browser *self, const char *title,
                                            self->b.top_idx,
                                            h->row_offset, h->nr_rows);
                 }
-                        continue;
+                        break;
+                case 'C':
+                        /* Collapse the whole world. */
+                        hist_browser__set_folding(self, false);
+                        break;
+                case 'E':
+                        /* Expand the whole world. */
+                        hist_browser__set_folding(self, true);
+                        break;
                 case NEWT_KEY_ENTER:
                         if (hist_browser__toggle_fold(self))
                                 break;
                         /* fall thru */
                 default:
-                        return 0;
+                        goto out;
                 }
         }
-
+out:
         ui_browser__hide(&self->b);
-        return 0;
+        return key;
 }
 
 static char *callchain_list__sym_name(struct callchain_list *self,
@@ -265,7 +353,7 @@ static char *callchain_list__sym_name(struct callchain_list *self,
         if (self->ms.sym)
                 return self->ms.sym->name;
 
-        snprintf(bf, bfsize, "%#Lx", self->ip);
+        snprintf(bf, bfsize, "%#" PRIx64, self->ip);
         return bf;
 }
 
@@ -292,7 +380,7 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
                 struct rb_node *next = rb_next(node);
-                u64 cumul = cumul_hits(child);
+                u64 cumul = callchain_cumul_hits(child);
                 struct callchain_list *chain;
                 char folded_sign = ' ';
                 int first = true;
@@ -306,15 +394,10 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
                         int color;
                         bool was_first = first;
 
-                        if (first) {
+                        if (first)
                                 first = false;
-                                chain->ms.has_children = chain->list.next != &child->val ||
-                                                         rb_first(&child->rb_root) != NULL;
-                        } else {
+                        else
                                 extra_offset = LEVEL_OFFSET_STEP;
-                                chain->ms.has_children = chain->list.next == &child->val &&
-                                                         rb_first(&child->rb_root) != NULL;
-                        }
 
                         folded_sign = callchain_list__folded(chain);
                         if (*row_offset != 0) {
@@ -341,8 +424,8 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self,
                                 *is_current_entry = true;
                         }
 
-                        SLsmg_set_color(color);
-                        SLsmg_gotorc(self->b.y + row, self->b.x);
+                        ui_browser__set_color(&self->b, color);
+                        ui_browser__gotorc(&self->b, row, 0);
                         slsmg_write_nstring(" ", offset + extra_offset);
                         slsmg_printf("%c ", folded_sign);
                         slsmg_write_nstring(str, width);
@@ -384,12 +467,7 @@ static int hist_browser__show_callchain_node(struct hist_browser *self,
         list_for_each_entry(chain, &node->val, list) {
                 char ipstr[BITS_PER_LONG / 4 + 1], *s;
                 int color;
-                /*
-                 * FIXME: This should be moved to somewhere else,
-                 * probably when the callchain is created, so as not to
-                 * traverse it all over again
-                 */
-                chain->ms.has_children = rb_first(&node->rb_root) != NULL;
+
                 folded_sign = callchain_list__folded(chain);
 
                 if (*row_offset != 0) {
@@ -405,8 +483,8 @@ static int hist_browser__show_callchain_node(struct hist_browser *self,
                 }
 
                 s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
-                SLsmg_gotorc(self->b.y + row, self->b.x);
-                SLsmg_set_color(color);
+                ui_browser__gotorc(&self->b, row, 0);
+                ui_browser__set_color(&self->b, color);
                 slsmg_write_nstring(" ", offset);
                 slsmg_printf("%c ", folded_sign);
                 slsmg_write_nstring(s, width - 2);
@@ -465,7 +543,7 @@ static int hist_browser__show_entry(struct hist_browser *self,
         }
 
         if (symbol_conf.use_callchain) {
-                entry->ms.has_children = !RB_EMPTY_ROOT(&entry->sorted_chain);
+                hist_entry__init_have_children(entry);
                 folded_sign = hist_entry__folded(entry);
         }
 
@@ -484,8 +562,8 @@ static int hist_browser__show_entry(struct hist_browser *self,
                                 color = HE_COLORSET_NORMAL;
                 }
 
-                SLsmg_set_color(color);
-                SLsmg_gotorc(self->b.y + row, self->b.x);
+                ui_browser__set_color(&self->b, color);
+                ui_browser__gotorc(&self->b, row, 0);
                 if (symbol_conf.use_callchain) {
                         slsmg_printf("%c ", folded_sign);
                         width -= 2;
@@ -563,6 +641,9 @@ static void ui_browser__hists_seek(struct ui_browser *self,
         struct rb_node *nd;
         bool first = true;
 
+        if (self->nr_entries == 0)
+                return;
+
         switch (whence) {
         case SEEK_SET:
                 nd = hists__filter_entries(rb_first(self->entries));
@@ -687,8 +768,6 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 
 static void hist_browser__delete(struct hist_browser *self)
 {
-        newtFormDestroy(self->b.form);
-        newtPopWindow();
         free(self);
 }
 
@@ -702,30 +781,37 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *self)
         return self->he_selection->thread;
 }
 
-static int hist_browser__title(char *bf, size_t size, const char *ev_name,
-                               const struct dso *dso, const struct thread *thread)
+static int hists__browser_title(struct hists *self, char *bf, size_t size,
+                                const char *ev_name, const struct dso *dso,
+                                const struct thread *thread)
 {
-        int printed = 0;
+        char unit;
+        int printed;
+        unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
+
+        nr_events = convert_unit(nr_events, &unit);
+        printed = snprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name);
 
         if (thread)
                 printed += snprintf(bf + printed, size - printed,
-                                    "Thread: %s(%d)",
-                                    (thread->comm_set ?  thread->comm : ""),
+                                    ", Thread: %s(%d)",
+                                    (thread->comm_set ? thread->comm : ""),
                                     thread->pid);
         if (dso)
                 printed += snprintf(bf + printed, size - printed,
-                                    "%sDSO: %s", thread ? " " : "",
-                                    dso->short_name);
-        return printed ?: snprintf(bf, size, "Event: %s", ev_name);
+                                    ", DSO: %s", dso->short_name);
+        return printed;
 }
 
-int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
+static int perf_evsel__hists_browse(struct perf_evsel *evsel,
+                                    const char *helpline, const char *ev_name,
+                                    bool left_exits)
 {
+        struct hists *self = &evsel->hists;
         struct hist_browser *browser = hist_browser__new(self);
         struct pstack *fstack;
         const struct thread *thread_filter = NULL;
         const struct dso *dso_filter = NULL;
-        struct newtExitStruct es;
         char msg[160];
         int key = -1;
 
@@ -738,84 +824,88 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name)
 
         ui_helpline__push(helpline);
 
-        hist_browser__title(msg, sizeof(msg), ev_name,
-                            dso_filter, thread_filter);
-
+        hists__browser_title(self, msg, sizeof(msg), ev_name,
+                             dso_filter, thread_filter);
         while (1) {
-                const struct thread *thread;
-                const struct dso *dso;
+                const struct thread *thread = NULL;
+                const struct dso *dso = NULL;
                 char *options[16];
                 int nr_options = 0, choice = 0, i,
                     annotate = -2, zoom_dso = -2, zoom_thread = -2,
                     browse_map = -2;
 
-                if (hist_browser__run(browser, msg, &es))
-                        break;
+                key = hist_browser__run(browser, msg);
 
-                thread = hist_browser__selected_thread(browser);
-                dso = browser->selection->map ? browser->selection->map->dso : NULL;
+                if (browser->he_selection != NULL) {
+                        thread = hist_browser__selected_thread(browser);
+                        dso = browser->selection->map ? browser->selection->map->dso : NULL;
+                }
 
-                if (es.reason == NEWT_EXIT_HOTKEY) {
-                        key = es.u.key;
+                switch (key) {
+                case NEWT_KEY_TAB:
+                case NEWT_KEY_UNTAB:
+                        /*
+                         * Exit the browser, let hists__browser_tree
+                         * go to the next or previous
+                         */
+                        goto out_free_stack;
+                case 'a':
+                        if (browser->selection == NULL ||
+                            browser->selection->sym == NULL ||
+                            browser->selection->map->dso->annotate_warned)
+                                continue;
+                        goto do_annotate;
+                case 'd':
+                        goto zoom_dso;
+                case 't':
+                        goto zoom_thread;
+                case NEWT_KEY_F1:
+                case 'h':
+                case '?':
+                        ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
+                                        "<-        Zoom out\n"
+                                        "a         Annotate current symbol\n"
+                                        "h/?/F1    Show this window\n"
+                                        "C         Collapse all callchains\n"
+                                        "E         Expand all callchains\n"
+                                        "d         Zoom into current DSO\n"
+                                        "t         Zoom into current Thread\n"
+                                        "TAB/UNTAB Switch events\n"
+                                        "q/CTRL+C  Exit browser");
+                        continue;
+                case NEWT_KEY_ENTER:
+                case NEWT_KEY_RIGHT:
+                        /* menu */
+                        break;
+                case NEWT_KEY_LEFT: {
+                        const void *top;
 
-                        switch (key) {
-                        case NEWT_KEY_F1:
-                                goto do_help;
-                        case NEWT_KEY_TAB:
-                        case NEWT_KEY_UNTAB:
+                        if (pstack__empty(fstack)) {
                                 /*
-                                 * Exit the browser, let hists__browser_tree
-                                 * go to the next or previous
+                                 * Go back to the perf_evsel_menu__run or other user
                                  */
-                                goto out_free_stack;
-                        default:;
-                        }
-
-                        switch (key) {
-                        case 'a':
-                                if (browser->selection->map == NULL ||
-                                    browser->selection->map->dso->annotate_warned)
-                                        continue;
-                                goto do_annotate;
-                        case 'd':
-                                goto zoom_dso;
-                        case 't':
-                                goto zoom_thread;
-                        case 'h':
-                        case '?':
-do_help:
-                                ui__help_window("->        Zoom into DSO/Threads & Annotate current symbol\n"
-                                                "<-        Zoom out\n"
-                                                "a         Annotate current symbol\n"
-                                                "h/?/F1    Show this window\n"
-                                                "d         Zoom into current DSO\n"
-                                                "t         Zoom into current Thread\n"
-                                                "q/CTRL+C  Exit browser");
+                                if (left_exits)
+                                        goto out_free_stack;
                                 continue;
-                        default:;
                         }
-                        if (is_exit_key(key)) {
-                                if (key == NEWT_KEY_ESCAPE &&
-                                    !ui__dialog_yesno("Do you really want to exit?"))
-                                        continue;
-                                break;
-                        }
-
-                        if (es.u.key == NEWT_KEY_LEFT) {
-                                const void *top;
-
-                                if (pstack__empty(fstack))
-                                        continue;
-                                top = pstack__pop(fstack);
-                                if (top == &dso_filter)
-                                        goto zoom_out_dso;
-                                if (top == &thread_filter)
-                                        goto zoom_out_thread;
+                        top = pstack__pop(fstack);
+                        if (top == &dso_filter)
+                                goto zoom_out_dso;
+                        if (top == &thread_filter)
+                                goto zoom_out_thread;
+                        continue;
+                }
+                case NEWT_KEY_ESCAPE:
+                        if (!left_exits &&
+                            !ui__dialog_yesno("Do you really want to exit?"))
                                 continue;
-                        }
+                        /* Fall thru */
+                default:
+                        goto out_free_stack;
                 }
 
-                if (browser->selection->sym != NULL &&
+                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)
@@ -834,7 +924,8 @@ do_help:
                              (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
                         zoom_dso = nr_options++;
 
-                if (browser->selection->map != NULL &&
+                if (browser->selection != NULL &&
+                    browser->selection->map != NULL &&
                     asprintf(&options[nr_options], "Browse map details") > 0)
                         browse_map = nr_options++;
 
@@ -854,19 +945,11 @@ do_help:
                 if (choice == annotate) {
                         struct hist_entry *he;
 do_annotate:
-                        if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) {
-                                browser->selection->map->dso->annotate_warned = 1;
-                                ui_helpline__puts("No vmlinux file found, can't "
-                                                 "annotate with just a "
-                                                 "kallsyms file");
-                                continue;
-                        }
-
                         he = hist_browser__selected_entry(browser);
                         if (he == NULL)
                                 continue;
 
-                        hist_entry__tui_annotate(he);
+                        hist_entry__tui_annotate(he, evsel->idx);
                 } else if (choice == browse_map)
                         map__browse(browser->selection->map);
                 else if (choice == zoom_dso) {
@@ -885,8 +968,8 @@ zoom_out_dso:
                                 pstack__push(fstack, &dso_filter);
                         }
                         hists__filter_by_dso(self, dso_filter);
-                        hist_browser__title(msg, sizeof(msg), ev_name,
-                                            dso_filter, thread_filter);
+                        hists__browser_title(self, msg, sizeof(msg), ev_name,
+                                             dso_filter, thread_filter);
                         hist_browser__reset(browser);
                 } else if (choice == zoom_thread) {
 zoom_thread:
@@ -903,8 +986,8 @@ zoom_out_thread:
                                 pstack__push(fstack, &thread_filter);
                         }
                         hists__filter_by_thread(self, thread_filter);
-                        hist_browser__title(msg, sizeof(msg), ev_name,
-                                            dso_filter, thread_filter);
+                        hists__browser_title(self, msg, sizeof(msg), ev_name,
+                                             dso_filter, thread_filter);
                         hist_browser__reset(browser);
                 }
         }
@@ -915,34 +998,141 @@ out:
         return key;
 }
 
-int hists__tui_browse_tree(struct rb_root *self, const char *help)
+struct perf_evsel_menu {
+        struct ui_browser b;
+        struct perf_evsel *selection;
+};
+
+static void perf_evsel_menu__write(struct ui_browser *browser,
+                                   void *entry, int row)
 {
-        struct rb_node *first = rb_first(self), *nd = first, *next;
-        int key = 0;
+        struct perf_evsel_menu *menu = container_of(browser,
+                                                    struct perf_evsel_menu, b);
+        struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node);
+        bool current_entry = ui_browser__is_current_entry(browser, row);
+        unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE];
+        const char *ev_name = event_name(evsel);
+        char bf[256], unit;
+
+        ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+                                                       HE_COLORSET_NORMAL);
+
+        nr_events = convert_unit(nr_events, &unit);
+        snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events,
+                 unit, unit == ' ' ? "" : " ", ev_name);
+        slsmg_write_nstring(bf, browser->width);
 
-        while (nd) {
-                struct hists *hists = rb_entry(nd, struct hists, rb_node);
-                const char *ev_name = __event_name(hists->type, hists->config);
+        if (current_entry)
+                menu->selection = evsel;
+}
 
-                key = hists__browse(hists, help, ev_name);
+static int perf_evsel_menu__run(struct perf_evsel_menu *menu, const char *help)
+{
+        int exit_keys[] = { NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, };
+        struct perf_evlist *evlist = menu->b.priv;
+        struct perf_evsel *pos;
+        const char *ev_name, *title = "Available samples";
+        int key;
+
+        if (ui_browser__show(&menu->b, title,
+                             "ESC: exit, ENTER|->: Browse histograms") < 0)
+                return -1;
 
-                if (is_exit_key(key))
+        ui_browser__add_exit_keys(&menu->b, exit_keys);
+
+        while (1) {
+                key = ui_browser__run(&menu->b);
+
+                switch (key) {
+                case NEWT_KEY_RIGHT:
+                case NEWT_KEY_ENTER:
+                        if (!menu->selection)
+                                continue;
+                        pos = menu->selection;
+browse_hists:
+                        ev_name = event_name(pos);
+                        key = perf_evsel__hists_browse(pos, help, ev_name, true);
+                        ui_browser__show_title(&menu->b, title);
                         break;
+                case NEWT_KEY_LEFT:
+                        continue;
+                case NEWT_KEY_ESCAPE:
+                        if (!ui__dialog_yesno("Do you really want to exit?"))
+                                continue;
+                        /* Fall thru */
+                default:
+                        goto out;
+                }
 
                 switch (key) {
                 case NEWT_KEY_TAB:
-                        next = rb_next(nd);
-                        if (next)
-                                nd = next;
-                        break;
+                        if (pos->node.next == &evlist->entries)
+                                pos = list_entry(evlist->entries.next, struct perf_evsel, node);
+                        else
+                                pos = list_entry(pos->node.next, struct perf_evsel, node);
+                        goto browse_hists;
                 case NEWT_KEY_UNTAB:
-                        if (nd == first)
-                                continue;
-                        nd = rb_prev(nd);
+                        if (pos->node.prev == &evlist->entries)
+                                pos = list_entry(evlist->entries.prev, struct perf_evsel, node);
+                        else
+                                pos = list_entry(pos->node.prev, struct perf_evsel, node);
+                        goto browse_hists;
+                case 'q':
+                case CTRL('c'):
+                        goto out;
                 default:
                         break;
                 }
         }
 
+out:
+        ui_browser__hide(&menu->b);
         return key;
 }
+
+static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
+                                           const char *help)
+{
+        struct perf_evsel *pos;
+        struct perf_evsel_menu menu = {
+                .b = {
+                        .entries    = &evlist->entries,
+                        .refresh    = ui_browser__list_head_refresh,
+                        .seek       = ui_browser__list_head_seek,
+                        .write      = perf_evsel_menu__write,
+                        .nr_entries = evlist->nr_entries,
+                        .priv       = evlist,
+                },
+        };
+
+        ui_helpline__push("Press ESC to exit");
+
+        list_for_each_entry(pos, &evlist->entries, node) {
+                const char *ev_name = event_name(pos);
+                size_t line_len = strlen(ev_name) + 7;
+
+                if (menu.b.width < line_len)
+                        menu.b.width = line_len;
+                /*
+                 * Cache the evsel name, tracepoints have a _high_ cost per
+                 * event_name() call.
+                 */
+                if (pos->name == NULL)
+                        pos->name = strdup(ev_name);
+        }
+
+        return perf_evsel_menu__run(&menu, help);
+}
+
+int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help)
+{
+
+        if (evlist->nr_entries == 1) {
+                struct perf_evsel *first = list_entry(evlist->entries.next,
+                                                      struct perf_evsel, node);
+                const char *ev_name = event_name(first);
+                return perf_evsel__hists_browse(first, help, ev_name, false);
+        }
+
+        return __perf_evlist__tui_browse_hists(evlist, help);
+}
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index 142b825b42bf..8462bffe20bc 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -1,6 +1,6 @@
 #include "../libslang.h"
 #include <elf.h>
-#include <newt.h>
+#include <inttypes.h>
 #include <sys/ttydefaults.h>
 #include <ctype.h>
 #include <string.h>
@@ -41,13 +41,12 @@ static int ui_entry__read(const char *title, char *bf, size_t size, int width)
 out_free_form:
         newtPopWindow();
         newtFormDestroy(form);
-        return 0;
+        return err;
 }
 
 struct map_browser {
         struct ui_browser b;
         struct map        *map;
-        u16               namelen;
         u8                addrlen;
 };
 
@@ -56,14 +55,16 @@ static void map_browser__write(struct ui_browser *self, void *nd, int row)
         struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
         struct map_browser *mb = container_of(self, struct map_browser, b);
         bool current_entry = ui_browser__is_current_entry(self, row);
-        int color = ui_browser__percent_color(0, current_entry);
+        int width;
 
-        SLsmg_set_color(color);
-        slsmg_printf("%*llx %*llx %c ",
+        ui_browser__set_percent_color(self, 0, current_entry);
+        slsmg_printf("%*" PRIx64 " %*" PRIx64 " %c ",
                      mb->addrlen, sym->start, mb->addrlen, sym->end,
                      sym->binding == STB_GLOBAL ? 'g' :
                      sym->binding == STB_LOCAL  ? 'l' : 'w');
-        slsmg_write_nstring(sym->name, mb->namelen);
+        width = self->width - ((mb->addrlen * 2) + 4);
+        if (width > 0)
+                slsmg_write_nstring(sym->name, width);
 }
 
 /* FIXME uber-kludgy, see comment on cmd_report... */
@@ -98,31 +99,29 @@ static int map_browser__search(struct map_browser *self)
         return 0;
 }
 
-static int map_browser__run(struct map_browser *self, struct newtExitStruct *es)
+static int map_browser__run(struct map_browser *self)
 {
+        int key;
+
         if (ui_browser__show(&self->b, self->map->dso->long_name,
                              "Press <- or ESC to exit, %s / to search",
                              verbose ? "" : "restart with -v to use") < 0)
                 return -1;
 
-        newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT);
-        newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER);
         if (verbose)
-                newtFormAddHotKey(self->b.form, '/');
+                ui_browser__add_exit_key(&self->b, '/');
 
         while (1) {
-                ui_browser__run(&self->b, es);
+                key = ui_browser__run(&self->b);
 
-                if (es->reason != NEWT_EXIT_HOTKEY)
-                        break;
-                if (verbose && es->u.key == '/')
+                if (verbose && key == '/')
                         map_browser__search(self);
                 else
                         break;
         }
 
         ui_browser__hide(&self->b);
-        return 0;
+        return key;
 }
 
 int map__browse(struct map *self)
@@ -136,7 +135,6 @@ int map__browse(struct map *self)
                 },
                 .map = self,
         };
-        struct newtExitStruct es;
         struct rb_node *nd;
         char tmp[BITS_PER_LONG / 4];
         u64 maxaddr = 0;
@@ -144,8 +142,6 @@ int map__browse(struct map *self)
         for (nd = rb_first(mb.b.entries); nd; nd = rb_next(nd)) {
                 struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 
-                if (mb.namelen < pos->namelen)
-                        mb.namelen = pos->namelen;
                 if (maxaddr < pos->end)
                         maxaddr = pos->end;
                 if (verbose) {
@@ -155,7 +151,6 @@ int map__browse(struct map *self)
                 ++mb.b.nr_entries;
         }
 
-        mb.addrlen = snprintf(tmp, sizeof(tmp), "%llx", maxaddr);
-        mb.b.width += mb.addrlen * 2 + 4 + mb.namelen;
-        return map_browser__run(&mb, &es);
+        mb.addrlen = snprintf(tmp, sizeof(tmp), "%" PRIx64, maxaddr);
+        return map_browser__run(&mb);
 }
diff --git a/tools/perf/util/ui/browsers/top.c b/tools/perf/util/ui/browsers/top.c
new file mode 100644
index 000000000000..5a06538532af
--- /dev/null
+++ b/tools/perf/util/ui/browsers/top.c
@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Parts came from builtin-{top,stat,record}.c, see those files for further
+ * copyright notes.
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "../browser.h"
+#include "../../annotate.h"
+#include "../helpline.h"
+#include "../libslang.h"
+#include "../util.h"
+#include "../../evlist.h"
+#include "../../hist.h"
+#include "../../sort.h"
+#include "../../symbol.h"
+#include "../../top.h"
+
+struct perf_top_browser {
+        struct ui_browser b;
+        struct rb_root    root;
+        struct sym_entry  *selection;
+        float             sum_ksamples;
+        int               dso_width;
+        int               dso_short_width;
+        int               sym_width;
+};
+
+static void perf_top_browser__write(struct ui_browser *browser, void *entry, int row)
+{
+        struct perf_top_browser *top_browser = container_of(browser, struct perf_top_browser, b);
+        struct sym_entry *syme = rb_entry(entry, struct sym_entry, rb_node);
+        bool current_entry = ui_browser__is_current_entry(browser, row);
+        struct symbol *symbol = sym_entry__symbol(syme);
+        struct perf_top *top = browser->priv;
+        int width = browser->width;
+        double pcnt;
+
+        pcnt = 100.0 - (100.0 * ((top_browser->sum_ksamples - syme->snap_count) /
+                                 top_browser->sum_ksamples));
+        ui_browser__set_percent_color(browser, pcnt, current_entry);
+
+        if (top->evlist->nr_entries == 1 || !top->display_weighted) {
+                slsmg_printf("%20.2f ", syme->weight);
+                width -= 24;
+        } else {
+                slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count);
+                width -= 23;
+        }
+
+        slsmg_printf("%4.1f%%", pcnt);
+        width -= 7;
+
+        if (verbose) {
+                slsmg_printf(" %016" PRIx64, symbol->start);
+                width -= 17;
+        }
+
+        slsmg_printf(" %-*.*s ", top_browser->sym_width, top_browser->sym_width,
+                     symbol->name);
+        width -= top_browser->sym_width;
+        slsmg_write_nstring(width >= syme->map->dso->long_name_len ?
+                                syme->map->dso->long_name :
+                                syme->map->dso->short_name, width);
+
+        if (current_entry)
+                top_browser->selection = syme;
+}
+
+static void perf_top_browser__update_rb_tree(struct perf_top_browser *browser)
+{
+        struct perf_top *top = browser->b.priv;
+        u64 top_idx = browser->b.top_idx;
+
+        browser->root = RB_ROOT;
+        browser->b.top = NULL;
+        browser->sum_ksamples = perf_top__decay_samples(top, &browser->root);
+        /*
+         * No active symbols
+         */
+        if (top->rb_entries == 0)
+                return;
+
+        perf_top__find_widths(top, &browser->root, &browser->dso_width,
+                              &browser->dso_short_width,
+                              &browser->sym_width);
+        if (browser->sym_width + browser->dso_width > browser->b.width - 29) {
+                browser->dso_width = browser->dso_short_width;
+                if (browser->sym_width + browser->dso_width > browser->b.width - 29)
+                        browser->sym_width = browser->b.width - browser->dso_width - 29;
+        }
+
+        /*
+         * Adjust the ui_browser indexes since the entries in the browser->root
+         * rb_tree may have changed, then seek it from start, so that we get a
+         * possible new top of the screen.
+         */
+        browser->b.nr_entries = top->rb_entries;
+
+        if (top_idx >= browser->b.nr_entries) {
+                if (browser->b.height >= browser->b.nr_entries)
+                        top_idx = browser->b.nr_entries - browser->b.height;
+                else
+                        top_idx = 0;
+        }
+
+        if (browser->b.index >= top_idx + browser->b.height)
+                browser->b.index = top_idx + browser->b.index - browser->b.top_idx;
+
+        if (browser->b.index >= browser->b.nr_entries)
+                browser->b.index = browser->b.nr_entries - 1;
+
+        browser->b.top_idx = top_idx;
+        browser->b.seek(&browser->b, top_idx, SEEK_SET);
+}
+
+static void perf_top_browser__annotate(struct perf_top_browser *browser)
+{
+        struct sym_entry *syme = browser->selection;
+        struct symbol *sym = sym_entry__symbol(syme);
+        struct annotation *notes = symbol__annotation(sym);
+        struct perf_top *top = browser->b.priv;
+
+        if (notes->src != NULL)
+                goto do_annotation;
+
+        pthread_mutex_lock(&notes->lock);
+
+        top->sym_filter_entry = NULL;
+
+        if (symbol__alloc_hist(sym, top->evlist->nr_entries) < 0) {
+                pr_err("Not enough memory for annotating '%s' symbol!\n",
+                       sym->name);
+                pthread_mutex_unlock(&notes->lock);
+                return;
+        }
+
+        top->sym_filter_entry = syme;
+
+        pthread_mutex_unlock(&notes->lock);
+do_annotation:
+        symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000);
+}
+
+static int perf_top_browser__run(struct perf_top_browser *browser)
+{
+        int key;
+        char title[160];
+        struct perf_top *top = browser->b.priv;
+        int delay_msecs = top->delay_secs * 1000;
+        int exit_keys[] = { 'a', NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, };
+
+        perf_top_browser__update_rb_tree(browser);
+        perf_top__header_snprintf(top, title, sizeof(title));
+        perf_top__reset_sample_counters(top);
+
+        if (ui_browser__show(&browser->b, title,
+                             "ESC: exit, ENTER|->|a: Live Annotate") < 0)
+                return -1;
+
+        newtFormSetTimer(browser->b.form, delay_msecs);
+        ui_browser__add_exit_keys(&browser->b, exit_keys);
+
+        while (1) {
+                key = ui_browser__run(&browser->b);
+
+                switch (key) {
+                case -1:
+                        /* FIXME we need to check if it was es.reason == NEWT_EXIT_TIMER */
+                        perf_top_browser__update_rb_tree(browser);
+                        perf_top__header_snprintf(top, title, sizeof(title));
+                        perf_top__reset_sample_counters(top);
+                        ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT);
+                        SLsmg_gotorc(0, 0);
+                        slsmg_write_nstring(title, browser->b.width);
+                        break;
+                case 'a':
+                case NEWT_KEY_RIGHT:
+                case NEWT_KEY_ENTER:
+                        if (browser->selection)
+                                perf_top_browser__annotate(browser);
+                        break;
+                case NEWT_KEY_LEFT:
+                        continue;
+                case NEWT_KEY_ESCAPE:
+                        if (!ui__dialog_yesno("Do you really want to exit?"))
+                                continue;
+                        /* Fall thru */
+                default:
+                        goto out;
+                }
+        }
+out:
+        ui_browser__hide(&browser->b);
+        return key;
+}
+
+int perf_top__tui_browser(struct perf_top *top)
+{
+        struct perf_top_browser browser = {
+                .b = {
+                        .entries = &browser.root,
+                        .refresh = ui_browser__rb_tree_refresh,
+                        .seek    = ui_browser__rb_tree_seek,
+                        .write   = perf_top_browser__write,
+                        .priv    = top,
+                },
+        };
+
+        ui_helpline__push("Press <- or ESC to exit");
+        return perf_top_browser__run(&browser);
+}
diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c
index 8d79daa4458a..f36d2ff509ed 100644
--- a/tools/perf/util/ui/helpline.c
+++ b/tools/perf/util/ui/helpline.c
@@ -5,6 +5,7 @@
 
 #include "../debug.h"
 #include "helpline.h"
+#include "ui.h"
 
 void ui_helpline__pop(void)
 {
@@ -55,7 +56,8 @@ int ui_helpline__show_help(const char *format, va_list ap)
         int ret;
         static int backlog;
 
-        ret = vsnprintf(ui_helpline__last_msg + backlog,
+        pthread_mutex_lock(&ui__lock);
+        ret = vsnprintf(ui_helpline__last_msg + backlog,
                         sizeof(ui_helpline__last_msg) - backlog, format, ap);
         backlog += ret;
 
@@ -64,6 +66,7 @@ int ui_helpline__show_help(const char *format, va_list ap)
                 newtRefresh();
                 backlog = 0;
         }
+        pthread_mutex_unlock(&ui__lock);
 
         return ret;
 }
diff --git a/tools/perf/util/ui/libslang.h b/tools/perf/util/ui/libslang.h
index 5623da8e8080..2b63e1c9b181 100644
--- a/tools/perf/util/ui/libslang.h
+++ b/tools/perf/util/ui/libslang.h
@@ -13,11 +13,11 @@
 
 #if SLANG_VERSION < 20104
 #define slsmg_printf(msg, args...) \
-        SLsmg_printf((char *)msg, ##args)
+        SLsmg_printf((char *)(msg), ##args)
 #define slsmg_write_nstring(msg, len) \
-        SLsmg_write_nstring((char *)msg, len)
+        SLsmg_write_nstring((char *)(msg), len)
 #define sltt_set_color(obj, name, fg, bg) \
-        SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg)
+        SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg))
 #else
 #define slsmg_printf SLsmg_printf
 #define slsmg_write_nstring SLsmg_write_nstring
diff --git a/tools/perf/util/ui/setup.c b/tools/perf/util/ui/setup.c
index 662085032eb7..ee46d671db59 100644
--- a/tools/perf/util/ui/setup.c
+++ b/tools/perf/util/ui/setup.c
@@ -6,6 +6,9 @@
 #include "../debug.h"
 #include "browser.h"
 #include "helpline.h"
+#include "ui.h"
+
+pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void newt_suspend(void *d __used)
 {
@@ -14,11 +17,12 @@ static void newt_suspend(void *d __used)
         newtResume();
 }
 
-void setup_browser(void)
+void setup_browser(bool fallback_to_pager)
 {
         if (!isatty(1) || !use_browser || dump_trace) {
                 use_browser = 0;
-                setup_pager();
+                if (fallback_to_pager)
+                        setup_pager();
                 return;
         }
 
diff --git a/tools/perf/util/ui/ui.h b/tools/perf/util/ui/ui.h
new file mode 100644
index 000000000000..d264e059c829
--- /dev/null
+++ b/tools/perf/util/ui/ui.h
@@ -0,0 +1,8 @@
+#ifndef _PERF_UI_H_
+#define _PERF_UI_H_ 1
+
+#include <pthread.h>
+
+extern pthread_mutex_t ui__lock;
+
+#endif /* _PERF_UI_H_ */
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 04600e26ceea..fdf1fc8f08bc 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -9,10 +9,9 @@
 #include "../debug.h"
 #include "browser.h"
 #include "helpline.h"
+#include "ui.h"
 #include "util.h"
 
-newtComponent newt_form__new(void);
-
 static void newt_form__set_exit_keys(newtComponent self)
 {
         newtFormAddHotKey(self, NEWT_KEY_LEFT);
@@ -22,7 +21,7 @@ static void newt_form__set_exit_keys(newtComponent self)
         newtFormAddHotKey(self, CTRL('c'));
 }
 
-newtComponent newt_form__new(void)
+static newtComponent newt_form__new(void)
 {
         newtComponent self = newtForm(NULL, NULL, 0);
         if (self)
@@ -106,9 +105,26 @@ out_destroy_form:
         return rc;
 }
 
+static const char yes[] = "Yes", no[] = "No",
+                  warning_str[] = "Warning!", ok[] = "Ok";
+
 bool ui__dialog_yesno(const char *msg)
 {
         /* newtWinChoice should really be accepting const char pointers... */
-        char yes[] = "Yes", no[] = "No";
-        return newtWinChoice(NULL, yes, no, (char *)msg) == 1;
+        return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1;
+}
+
+void ui__warning(const char *format, ...)
+{
+        va_list args;
+
+        va_start(args, format);
+        if (use_browser > 0) {
+                pthread_mutex_lock(&ui__lock);
+                newtWinMessagev((char *)warning_str, (char *)ok,
+                                (char *)format, args);
+                pthread_mutex_unlock(&ui__lock);
+        } else
+                vfprintf(stderr, format, args);
+        va_end(args);
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 214265674ddd..5b3ea49aa63e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -114,3 +114,20 @@ unsigned long convert_unit(unsigned long value, char *unit)
 
         return value;
 }
+
+int readn(int fd, void *buf, size_t n)
+{
+        void *buf_start = buf;
+
+        while (n) {
+                int ret = read(fd, buf, n);
+
+                if (ret <= 0)
+                        return ret;
+
+                n -= ret;
+                buf += ret;
+        }
+
+        return buf - buf_start;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index f380fed74359..fc784284ac8b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -70,9 +70,7 @@
 #include <sys/poll.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
-#ifndef NO_SYS_SELECT_H
 #include <sys/select.h>
-#endif
 #include <netinet/in.h>
 #include <netinet/tcp.h>
 #include <arpa/inet.h>
@@ -83,10 +81,6 @@
 #include "types.h"
 #include <sys/ttydefaults.h>
 
-#ifndef NO_ICONV
-#include <iconv.h>
-#endif
-
 extern const char *graph_line;
 extern const char *graph_dotted_line;
 extern char buildid_dir[];
@@ -236,26 +230,6 @@ static inline int sane_case(int x, int high)
         return x;
 }
 
-#ifndef DIR_HAS_BSD_GROUP_SEMANTICS
-# define FORCE_DIR_SET_GID S_ISGID
-#else
-# define FORCE_DIR_SET_GID 0
-#endif
-
-#ifdef NO_NSEC
-#undef USE_NSEC
-#define ST_CTIME_NSEC(st) 0
-#define ST_MTIME_NSEC(st) 0
-#else
-#ifdef USE_ST_TIMESPEC
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec))
-#else
-#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec))
-#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec))
-#endif
-#endif
-
 int mkdir_p(char *path, mode_t mode);
 int copyfile(const char *from, const char *to);
 
@@ -265,19 +239,7 @@ void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
 unsigned long convert_unit(unsigned long value, char *unit);
-
-#ifndef ESC
-#define ESC 27
-#endif
-
-static inline bool is_exit_key(int key)
-{
-        char up;
-        if (key == CTRL('c') || key == ESC)
-                return true;
-        up = toupper(key);
-        return up == 'Q';
-}
+int readn(int fd, void *buf, size_t size);
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index cfa55d686e3b..bdd33470b235 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -150,7 +150,7 @@ static void perf_read_values__display_pretty(FILE *fp,
                 if (width > tidwidth)
                         tidwidth = width;
                 for (j = 0; j < values->counters; j++) {
-                        width = snprintf(NULL, 0, "%Lu", values->value[i][j]);
+                        width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
                         if (width > counterwidth[j])
                                 counterwidth[j] = width;
                 }
@@ -165,7 +165,7 @@ static void perf_read_values__display_pretty(FILE *fp,
                 fprintf(fp, "  %*d  %*d", pidwidth, values->pid[i],
                         tidwidth, values->tid[i]);
                 for (j = 0; j < values->counters; j++)
-                        fprintf(fp, "  %*Lu",
+                        fprintf(fp, "  %*" PRIu64,
                                 counterwidth[j], values->value[i][j]);
                 fprintf(fp, "\n");
         }
@@ -196,13 +196,13 @@ static void perf_read_values__display_raw(FILE *fp,
                 width = strlen(values->countername[j]);
                 if (width > namewidth)
                         namewidth = width;
-                width = snprintf(NULL, 0, "%llx", values->counterrawid[j]);
+                width = snprintf(NULL, 0, "%" PRIx64, values->counterrawid[j]);
                 if (width > rawwidth)
                         rawwidth = width;
         }
         for (i = 0; i < values->threads; i++) {
                 for (j = 0; j < values->counters; j++) {
-                        width = snprintf(NULL, 0, "%Lu", values->value[i][j]);
+                        width = snprintf(NULL, 0, "%" PRIu64, values->value[i][j]);
                         if (width > countwidth)
                                 countwidth = width;
                 }
@@ -214,7 +214,7 @@ static void perf_read_values__display_raw(FILE *fp,
                 countwidth, "Count");
         for (i = 0; i < values->threads; i++)
                 for (j = 0; j < values->counters; j++)
-                        fprintf(fp, "  %*d  %*d  %*s  %*llx  %*Lu\n",
+                        fprintf(fp, "  %*d  %*d  %*s  %*" PRIx64 "  %*" PRIu64,
                                 pidwidth, values->pid[i],
                                 tidwidth, values->tid[i],
                                 namewidth, values->countername[j],
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
new file mode 100644
index 000000000000..22afbf6c536a
--- /dev/null
+++ b/tools/perf/util/xyarray.c
@@ -0,0 +1,20 @@
+#include "xyarray.h"
+#include "util.h"
+
+struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
+{
+        size_t row_size = ylen * entry_size;
+        struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size);
+
+        if (xy != NULL) {
+                xy->entry_size = entry_size;
+                xy->row_size   = row_size;
+        }
+
+        return xy;
+}
+
+void xyarray__delete(struct xyarray *xy)
+{
+        free(xy);
+}
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
new file mode 100644
index 000000000000..c488a07275dd
--- /dev/null
+++ b/tools/perf/util/xyarray.h
@@ -0,0 +1,20 @@
+#ifndef _PERF_XYARRAY_H_
+#define _PERF_XYARRAY_H_ 1
+
+#include <sys/types.h>
+
+struct xyarray {
+        size_t row_size;
+        size_t entry_size;
+        char contents[];
+};
+
+struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
+void xyarray__delete(struct xyarray *xy);
+
+static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
+{
+        return &xy->contents[x * xy->row_size + y * xy->entry_size];
+}
+
+#endif /* _PERF_XYARRAY_H_ */