Merge branch 'next' into for-linus

135 files changed, 3935 insertions, 1736 deletions

diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index b2c63309a651..6f5a498608b2 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -24,12 +24,47 @@ 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 thru the lines with more samples.
+        samples, TAB/UNTAB cycles through the lines with more samples.
 
 SEE ALSO
 --------
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-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-lock.txt b/tools/perf/Documentation/perf-lock.txt
index b317102138c8..921de259ea10 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -24,6 +24,21 @@ and statistics with this 'perf lock' command.
 
   'perf lock report' reports statistical data.
 
+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.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 62de1b7f4e76..86b797a35aa6 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -115,9 +115,9 @@ 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[: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
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index a91f9f9e6e5c..e032716c839b 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.
@@ -99,6 +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.
@@ -109,8 +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.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 12052c9ed0ba..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 +73,26 @@ 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
@@ -72,6 +100,25 @@ OPTIONS
         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..5bb41e55a3ac 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
@@ -112,13 +112,13 @@ 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 +162,7 @@ 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 +170,7 @@ 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 +204,7 @@ 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 +214,4 @@ 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..36b38277422c 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
@@ -510,7 +510,7 @@ 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 +519,7 @@ 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 +559,15 @@ 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 +610,7 @@ 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 +620,4 @@ 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..29ad94293cd2
--- /dev/null
+++ b/tools/perf/Documentation/perf-script.txt
@@ -0,0 +1,118 @@
+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.
+
+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..b6da7affbbee 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 +35,54 @@ 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.
+
 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 d1db0f676a4b..7141c42e1469 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -185,7 +185,10 @@ ifeq ($(ARCH),i386)
         ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
+        RAW_ARCH := x86_64
         ARCH := x86
+        ARCH_CFLAGS := -DARCH_X86_64
+        ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
 endif
 
 # CFLAGS and LDFLAGS are for the users to override from the command line.
@@ -201,13 +204,11 @@ 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 +225,7 @@ 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 = $(LDFLAGS)
@@ -291,6 +292,13 @@ ifeq ($(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 ---
 
@@ -375,6 +383,7 @@ 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
@@ -383,6 +392,8 @@ 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/cache.h
 LIB_H += util/callchain.h
@@ -390,6 +401,7 @@ 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/exec_cmd.h
 LIB_H += util/types.h
 LIB_H += util/levenshtein.h
@@ -398,6 +410,7 @@ 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
@@ -417,6 +430,7 @@ LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
+LIB_H += $(ARCH_INCLUDE)
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -426,6 +440,7 @@ 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/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
 LIB_OBJS += $(OUTPUT)util/help.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
@@ -463,6 +478,7 @@ 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
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
@@ -472,6 +488,9 @@ 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
@@ -485,7 +504,7 @@ 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
@@ -507,7 +526,7 @@ 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 := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
         NO_DWARF := 1
@@ -554,7 +573,7 @@ ifndef NO_DWARF
 ifeq ($(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
@@ -891,13 +910,14 @@ prefix_SQ = $(subst ','\'',$(prefix))
 SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
 PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH))
 
-LIBS = $(PERFLIBS) $(EXTLIBS)
+LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS)
 
 BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
         $(COMPAT_CFLAGS)
 LIB_OBJS += $(COMPAT_OBJS)
 
 ALL_CFLAGS += $(BASIC_CFLAGS)
+ALL_CFLAGS += $(ARCH_CFLAGS)
 ALL_LDFLAGS += $(BASIC_LDFLAGS)
 
 export TAR INSTALL DESTDIR SHELL_PATH
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/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6d5604d8df95..8879463807e4 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -58,12 +58,12 @@ static int hists__add_entry(struct hists *self, struct addr_location *al)
         return hist_entry__inc_addr_samples(he, al->addr);
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+                                struct perf_session *session)
 {
         struct addr_location al;
-        struct sample_data data;
 
-        if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) {
+        if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -212,7 +212,7 @@ get_source_line(struct hist_entry *he, int len, const char *filename)
                         continue;
 
                 offset = start + i;
-                sprintf(cmd, "addr2line -e %s %016llx", filename, offset);
+                sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset);
                 fp = popen(cmd, "r");
                 if (!fp)
                         continue;
@@ -270,9 +270,9 @@ static void hist_entry__print_hits(struct hist_entry *self)
 
         for (offset = 0; offset < len; ++offset)
                 if (h->ip[offset] != 0)
-                        printf("%*Lx: %Lu\n", BITS_PER_LONG / 2,
+                        printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2,
                                sym->start + offset, h->ip[offset]);
-        printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+        printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum);
 }
 
 static int hist_entry__tty_annotate(struct hist_entry *he)
@@ -375,6 +375,8 @@ static struct perf_event_ops event_ops = {
         .mmap   = event__process_mmap,
         .comm   = event__process_comm,
         .fork   = event__process_task,
+        .ordered_samples = true,
+        .ordering_requires_timestamps = true,
 };
 
 static int __cmd_annotate(void)
@@ -382,7 +384,7 @@ static int __cmd_annotate(void)
         int ret;
         struct perf_session *session;
 
-        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;
 
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..3153e492dbcc 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -30,12 +30,13 @@ 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(event_t *event,
+                                      struct sample_data *sample,
+                                      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 (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
                            event->header.type);
                 return -1;
@@ -44,12 +45,12 @@ 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;
 }
 
@@ -60,6 +61,8 @@ static struct perf_event_ops event_ops = {
         .exit   = event__process_task,
         .fork   = event__process_task,
         .lost   = 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 +144,8 @@ 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 +176,7 @@ 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 +194,8 @@ 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-inject.c b/tools/perf/builtin-inject.c
index 8e3e47b064ce..0c78ffa7bf67 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 event__repipe_synth(event_t *event,
+                               struct perf_session *session __used)
 {
         uint32_t size;
         void *buf = event;
@@ -36,22 +36,30 @@ static int event__repipe(event_t *event __used,
         return 0;
 }
 
-static int event__repipe_mmap(event_t *self, struct perf_session *session)
+static int event__repipe(event_t *event, struct sample_data *sample __used,
+                         struct perf_session *session)
+{
+        return event__repipe_synth(event, session);
+}
+
+static int event__repipe_mmap(event_t *self, struct sample_data *sample,
+                              struct perf_session *session)
 {
         int err;
 
-        err = event__process_mmap(self, session);
-        event__repipe(self, session);
+        err = event__process_mmap(self, sample, session);
+        event__repipe(self, sample, session);
 
         return err;
 }
 
-static int event__repipe_task(event_t *self, struct perf_session *session)
+static int event__repipe_task(event_t *self, struct sample_data *sample,
+                              struct perf_session *session)
 {
         int err;
 
-        err = event__process_task(self, session);
-        event__repipe(self, session);
+        err = event__process_task(self, sample, session);
+        event__repipe(self, sample, session);
 
         return err;
 }
@@ -61,7 +69,7 @@ static int event__repipe_tracing_data(event_t *self,
 {
         int err;
 
-        event__repipe(self, session);
+        event__repipe_synth(self, session);
         err = event__process_tracing_data(self, session);
 
         return err;
@@ -111,7 +119,8 @@ 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 event__inject_buildid(event_t *event, struct sample_data *sample,
+                                 struct perf_session *session)
 {
         struct addr_location al;
         struct thread *thread;
@@ -146,7 +155,7 @@ static int event__inject_buildid(event_t *event, struct perf_session *session)
         }
 
 repipe:
-        event__repipe(event, session);
+        event__repipe(event, sample, session);
         return 0;
 }
 
@@ -160,10 +169,10 @@ struct perf_event_ops inject_ops = {
         .read           = event__repipe,
         .throttle       = event__repipe,
         .unthrottle     = event__repipe,
-        .attr           = event__repipe,
-        .event_type     = event__repipe,
-        .tracing_data   = event__repipe,
-        .build_id       = event__repipe,
+        .attr           = event__repipe_synth,
+        .event_type     = event__repipe_synth,
+        .tracing_data   = event__repipe_synth,
+        .build_id       = event__repipe_synth,
 };
 
 extern volatile int session_done;
@@ -187,7 +196,7 @@ static int __cmd_inject(void)
                 inject_ops.tracing_data = 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..d97256d65980 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -304,22 +304,11 @@ 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(event_t *event, struct sample_data *sample,
+                                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);
@@ -328,8 +317,8 @@ 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;
 }
@@ -382,10 +371,10 @@ 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 +481,8 @@ 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 +737,9 @@ 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-lock.c b/tools/perf/builtin-lock.c
index 821c1586a22b..2b36defc5d73 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -782,9 +782,9 @@ 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");
         }
@@ -834,22 +834,18 @@ 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(event_t *self, struct sample_data *sample,
+                                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);
                 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;
 }
@@ -862,7 +858,7 @@ static struct perf_event_ops eops = {
 
 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");
 
@@ -947,6 +943,9 @@ 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 +981,9 @@ 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 2e000c068cc5..add163c9f0e7 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -249,6 +249,11 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
              !params.show_lines))
                 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.mod_events) {
                         pr_err("  Error: Don't use --list with --add/--del.\n");
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e75583ddd6d..b2f729fdb317 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -18,6 +18,7 @@
 
 #include "util/header.h"
 #include "util/event.h"
+#include "util/evsel.h"
 #include "util/debug.h"
 #include "util/session.h"
 #include "util/symbol.h"
@@ -27,17 +28,18 @@
 #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 u64                      sample_type;
 
-static int                      nr_cpus                         =      0;
+static struct cpu_map           *cpus;
 static unsigned int             page_size;
 static unsigned int             mmap_pages                      =    128;
 static unsigned int             user_freq                       = UINT_MAX;
@@ -47,12 +49,13 @@ static int			pipe_output			=      0;
 static const char               *output_name                    = "perf.data";
 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 struct thread_map        *threads;
 static pid_t                    child_pid                       =     -1;
 static bool                     no_inherit                      =  false;
 static enum write_mode_t        write_mode                      = WRITE_FORCE;
@@ -60,7 +63,9 @@ 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 long                     samples                         =      0;
 static u64                      bytes_written                   =      0;
@@ -77,7 +82,6 @@ static struct perf_session	*session;
 static const char               *cpu_list;
 
 struct mmap_data {
-        int                     counter;
         void                    *base;
         unsigned int            mask;
         unsigned int            prev;
@@ -128,6 +132,7 @@ static void write_output(void *buf, size_t size)
 }
 
 static int process_synthesized_event(event_t *event,
+                                     struct sample_data *sample __used,
                                      struct perf_session *self __used)
 {
         write_output(event, event->header.size);
@@ -197,7 +202,7 @@ 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);
@@ -224,12 +229,12 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n
         return h_attr;
 }
 
-static void create_counter(int counter, int cpu)
+static void create_counter(struct perf_evsel *evsel, int cpu)
 {
-        char *filter = filters[counter];
-        struct perf_event_attr *attr = attrs + counter;
+        char *filter = evsel->filter;
+        struct perf_event_attr *attr = &evsel->attr;
         struct perf_header_attr *h_attr;
-        int track = !counter; /* only the first counter needs these */
+        int track = !evsel->idx; /* only the first counter needs these */
         int thread_index;
         int ret;
         struct {
@@ -238,6 +243,19 @@ static void create_counter(int counter, int cpu)
                 u64 time_running;
                 u64 id;
         } read_data;
+        /*
+         * 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;
 
         attr->read_format       = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                   PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -280,12 +298,21 @@ 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;
@@ -293,13 +320,14 @@ static void create_counter(int counter, int cpu)
                 attr->disabled = 1;
                 attr->enable_on_exec = 1;
         }
+retry_sample_id:
+        attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 
-        for (thread_index = 0; thread_index < thread_num; thread_index++) {
+        for (thread_index = 0; thread_index < threads->nr; thread_index++) {
 try_again:
-                fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
-                                all_tids[thread_index], cpu, group_fd, 0);
+                FD(evsel, nr_cpu, thread_index) = sys_perf_event_open(attr, threads->map[thread_index], cpu, group_fd, 0);
 
-                if (fd[nr_cpu][counter][thread_index] < 0) {
+                if (FD(evsel, nr_cpu, thread_index) < 0) {
                         int err = errno;
 
                         if (err == EPERM || err == EACCES)
@@ -309,6 +337,15 @@ try_again:
                         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;
                         }
 
                         /*
@@ -326,8 +363,8 @@ try_again:
                                 goto try_again;
                         }
                         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",
+                              FD(evsel, nr_cpu, thread_index), strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)
                         if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
@@ -341,7 +378,7 @@ try_again:
                         exit(-1);
                 }
 
-                h_attr = get_header_attr(attr, counter);
+                h_attr = get_header_attr(attr, evsel->idx);
                 if (h_attr == NULL)
                         die("nomem\n");
 
@@ -352,7 +389,7 @@ try_again:
                         }
                 }
 
-                if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
+                if (read(FD(evsel, nr_cpu, thread_index), &read_data, sizeof(read_data)) == -1) {
                         perror("Unable to read perf file descriptor");
                         exit(-1);
                 }
@@ -362,43 +399,44 @@ try_again:
                         exit(-1);
                 }
 
-                assert(fd[nr_cpu][counter][thread_index] >= 0);
-                fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
+                assert(FD(evsel, nr_cpu, thread_index) >= 0);
+                fcntl(FD(evsel, nr_cpu, 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]);
+                        group_fd = FD(evsel, nr_cpu, thread_index);
+
+                if (evsel->idx || thread_index) {
+                        struct perf_evsel *first;
+                        first = list_entry(evsel_list.next, struct perf_evsel, node);
+                        ret = ioctl(FD(evsel, nr_cpu, thread_index),
+                                    PERF_EVENT_IOC_SET_OUTPUT,
+                                    FD(first, nr_cpu, 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);
+                                PROT_READ | PROT_WRITE, MAP_SHARED, FD(evsel, nr_cpu, 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].fd = FD(evsel, nr_cpu, 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);
+                        ret = ioctl(FD(evsel, nr_cpu, thread_index),
+                                    PERF_EVENT_IOC_SET_FILTER, filter);
                         if (ret) {
                                 error("failed to set filter with %d (%s)\n", errno,
                                                 strerror(errno));
@@ -406,15 +444,19 @@ try_again:
                         }
                 }
         }
+
+        if (!sample_type)
+                sample_type = attr->sample_type;
 }
 
 static void open_counters(int cpu)
 {
-        int counter;
+        struct perf_evsel *pos;
 
         group_fd = -1;
-        for (counter = 0; counter < nr_counters; counter++)
-                create_counter(counter, cpu);
+
+        list_for_each_entry(pos, &evsel_list, node)
+                create_counter(pos, cpu);
 
         nr_cpu++;
 }
@@ -437,9 +479,11 @@ static void atexit_header(void)
         if (!pipe_output) {
                 session->header.data_size += bytes_written;
 
-                process_buildids();
+                if (!no_buildid)
+                        process_buildids();
                 perf_header__write(&session->header, output, true);
                 perf_session__delete(session);
+                perf_evsel_list__delete();
                 symbol__exit();
         }
 }
@@ -500,7 +544,7 @@ 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;
@@ -515,6 +559,7 @@ 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");
@@ -551,19 +596,22 @@ 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);
                 if (err < 0)
                         goto out_delete_session;
         }
 
-        if (have_tracepoints(attrs, nr_counters))
+        if (have_tracepoints(&evsel_list))
                 perf_header__set_feat(&session->header, HEADER_TRACE_INFO);
 
         /*
@@ -606,11 +654,12 @@ 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;
+                        threads->map[0] = child_pid;
 
                 close(child_ready_pipe[1]);
                 close(go_pipe[0]);
@@ -624,19 +673,15 @@ 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");
-                return -1;
-        }
-
         if (!system_wide && no_inherit && !cpu_list) {
                 open_counters(-1);
         } else {
-                for (i = 0; i < nr_cpus; i++)
-                        open_counters(cpumap[i]);
+                for (i = 0; i < cpus->nr; i++)
+                        open_counters(cpus->map[i]);
         }
 
+        perf_session__set_sample_type(session, sample_type);
+
         if (pipe_output) {
                 err = perf_header__write_pipe(output);
                 if (err < 0)
@@ -649,6 +694,8 @@ static int __cmd_record(int argc, const char **argv)
 
         post_processing_offset = lseek(output, 0, SEEK_CUR);
 
+        perf_session__set_sample_id_all(session, sample_id_all_avail);
+
         if (pipe_output) {
                 err = event__synthesize_attrs(&session->header,
                                               process_synthesized_event,
@@ -665,7 +712,7 @@ static int __cmd_record(int argc, const char **argv)
                         return err;
                 }
 
-                if (have_tracepoints(attrs, nr_counters)) {
+                if (have_tracepoints(&evsel_list)) {
                         /*
                          * FIXME err <= 0 here actually means that
                          * there were no tracepoints so its not really
@@ -674,8 +721,7 @@ 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,
+                        err = event__synthesize_tracing_data(output, &evsel_list,
                                                              process_synthesized_event,
                                                              session);
                         if (err <= 0) {
@@ -697,17 +743,18 @@ static int __cmd_record(int argc, const char **argv)
         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;
-        }
+        if (err < 0)
+                pr_err("Couldn't record kernel reference relocation symbol\n"
+                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                       "Check /proc/kallsyms permission or run as root.\n");
 
         err = event__synthesize_modules(process_synthesized_event,
                                         session, machine);
-        if (err < 0) {
-                pr_err("Couldn't record kernel reference relocation symbol.\n");
-                return err;
-        }
+        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");
+
         if (perf_guest)
                 perf_session__process_machines(session, event__synthesize_guest_os);
 
@@ -748,20 +795,20 @@ static int __cmd_record(int argc, const char **argv)
 
                 if (done) {
                         for (i = 0; i < nr_cpu; i++) {
-                                for (counter = 0;
-                                        counter < nr_counters;
-                                        counter++) {
+                                struct perf_evsel *pos;
+
+                                list_for_each_entry(pos, &evsel_list, node) {
                                         for (thread = 0;
-                                                thread < thread_num;
+                                                thread < threads->nr;
                                                 thread++)
-                                                ioctl(fd[i][counter][thread],
+                                                ioctl(FD(pos, i, thread),
                                                         PERF_EVENT_IOC_DISABLE);
                                 }
                         }
                 }
         }
 
-        if (quiet)
+        if (quiet || signr == SIGUSR1)
                 return 0;
 
         fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
@@ -770,7 +817,7 @@ static int __cmd_record(int argc, const char **argv)
          * 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);
@@ -790,7 +837,7 @@ static const char * const record_usage[] = {
 
 static bool force, append_file;
 
-static const struct option options[] = {
+const struct option record_options[] = {
         OPT_CALLBACK('e', "event", NULL, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events),
@@ -802,6 +849,8 @@ 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,
@@ -828,27 +877,31 @@ static const struct option options[] = {
                     "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_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,
+        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 {
@@ -856,41 +909,38 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
         }
 
         symbol__init();
-        if (no_buildid)
+
+        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 (list_empty(&evsel_list) && perf_evsel_list__create_default() < 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;
+        threads = thread_map__new(target_pid, target_tid);
+        if (threads == NULL) {
+                pr_err("Problems finding threads of monitor\n");
+                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;
-                }
+        cpus = cpu_map__new(cpu_list);
+        if (cpus == NULL) {
+                perror("failed to parse CPUs map");
+                return -1;
         }
-        event_array = malloc(
-                sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+
+        list_for_each_entry(pos, &evsel_list, node) {
+                if (perf_evsel__alloc_fd(pos, cpus->nr, 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 * threads->nr));
         if (!event_array)
                 goto out_free_fd;
 
@@ -917,12 +967,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 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;
+        thread_map__delete(threads);
+        threads = NULL;
 out_symbol_exit:
         symbol__exit();
         return err;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5de405d45230..c27e31f289e6 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -150,13 +150,13 @@ static int add_event_total(struct perf_session *session,
         return 0;
 }
 
-static int process_sample_event(event_t *event, struct perf_session *session)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+                                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 (event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
                 fprintf(stderr, "problem processing %d event, skipping it.\n",
                         event->header.type);
                 return -1;
@@ -165,14 +165,14 @@ 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)) {
+        if (perf_session__add_hist_entry(session, &al, sample)) {
                 pr_debug("problem incrementing symbol period, skipping event\n");
                 return -1;
         }
 
-        attr = perf_header__find_attr(data.id, &session->header);
+        attr = perf_header__find_attr(sample->id, &session->header);
 
-        if (add_event_total(session, &data, attr)) {
+        if (add_event_total(session, sample, attr)) {
                 pr_debug("problem adding event period\n");
                 return -1;
         }
@@ -180,7 +180,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         return 0;
 }
 
-static int process_read_event(event_t *event, struct perf_session *session __used)
+static int process_read_event(event_t *event, struct sample_data *sample __used,
+                              struct perf_session *session __used)
 {
         struct perf_event_attr *attr;
 
@@ -196,7 +197,7 @@ 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,
+        dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
                     attr ? __event_name(attr->type, attr->config) : "FAIL",
                     event->read.value);
 
@@ -243,6 +244,8 @@ static struct perf_event_ops event_ops = {
         .event_type = event__process_event_type,
         .tracing_data = event__process_tracing_data,
         .build_id = event__process_build_id,
+        .ordered_samples = true,
+        .ordering_requires_timestamps = true,
 };
 
 extern volatile int session_done;
@@ -307,7 +310,7 @@ static int __cmd_report(void)
 
         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;
 
@@ -442,6 +445,8 @@ 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"),
@@ -478,6 +483,8 @@ 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()
 };
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 55f3b5dcc731..29acb894e035 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 *
@@ -489,7 +489,8 @@ 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);
@@ -616,13 +617,13 @@ 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)     \
@@ -815,10 +816,10 @@ 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 +1048,7 @@ 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 +1221,7 @@ 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,
@@ -1422,7 +1423,7 @@ 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);
@@ -1606,25 +1607,15 @@ 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(event_t *event, struct sample_data *sample,
+                                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);
@@ -1633,10 +1624,11 @@ 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;
 }
@@ -1652,7 +1644,8 @@ static struct perf_event_ops event_ops = {
 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 +1713,7 @@ 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 +1843,15 @@ 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 +1862,9 @@ 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 +1884,10 @@ 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-trace.c b/tools/perf/builtin-script.c
index 2f8df45c4dcb..b766c2a9ac97 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-script.c
@@ -10,6 +10,7 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
+#include "util/parse-options.h"
 #include "util/util.h"
 
 static char const               *script_name;
@@ -17,6 +18,7 @@ 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 int default_start_script(const char *script __unused,
                                 int argc __unused,
@@ -54,29 +56,18 @@ static void setup_scripting(void)
 
 static int cleanup_scripting(void)
 {
-        pr_debug("\nperf trace script stopped\n");
+        pr_debug("\nperf 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)
+static int process_sample_event(event_t *event, struct sample_data *sample,
+                                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);
+        struct thread *thread = perf_session__findnew(session, event->ip.pid);
 
-        thread = perf_session__findnew(session, event->ip.pid);
         if (thread == NULL) {
                 pr_debug("problem processing %d event, skipping it.\n",
                          event->header.type);
@@ -85,13 +76,13 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         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);
+                        if (sample->time < last_timestamp) {
+                                pr_err("Samples misordered, previous: %" PRIu64
+                                        " this: %" PRIu64 "\n", last_timestamp,
+                                        sample->time);
                                 nr_unordered++;
                         }
-                        last_timestamp = data.time;
+                        last_timestamp = sample->time;
                         return 0;
                 }
                 /*
@@ -99,21 +90,12 @@ static int process_sample_event(event_t *event, struct perf_session *session)
                  * 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);
+                scripting_ops->process_event(sample->cpu, sample->raw_data,
+                                             sample->raw_size,
+                                             sample->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;
-
+        session->hists.stats.total_period += sample->period;
         return 0;
 }
 
@@ -124,7 +106,7 @@ static struct perf_event_ops event_ops = {
         .event_type = event__process_event_type,
         .tracing_data = event__process_tracing_data,
         .build_id = event__process_build_id,
-        .lost = process_lost_event,
+        .ordering_requires_timestamps = true,
         .ordered_samples = true,
 };
 
@@ -135,7 +117,7 @@ static void sig_handler(int sig __unused)
         session_done = 1;
 }
 
-static int __cmd_trace(struct perf_session *session)
+static int __cmd_script(struct perf_session *session)
 {
         int ret;
 
@@ -143,10 +125,8 @@ static int __cmd_trace(struct perf_session *session)
 
         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);
-        }
+        if (debug_mode)
+                pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
 
         return ret;
 }
@@ -157,7 +137,7 @@ struct script_spec {
         char                    spec[0];
 };
 
-LIST_HEAD(script_specs);
+static LIST_HEAD(script_specs);
 
 static struct script_spec *script_spec__new(const char *spec,
                                             struct scripting_ops *ops)
@@ -245,7 +225,7 @@ static void list_available_languages(void)
 
         fprintf(stderr, "\n");
         fprintf(stderr, "Scripting language extensions (used in "
-                "perf trace -s [spec:]script.[spec]):\n\n");
+                "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);
@@ -299,17 +279,34 @@ static int parse_scriptname(const struct option *opt __used,
         return 0;
 }
 
-#define for_each_lang(scripts_dir, lang_dirent, lang_next)              \
+/* 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 &&                     \
+                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_dir, script_dirent, script_next)           \
+#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)
+                if (script_dirent.d_type != DT_DIR &&                   \
+                    (script_dirent.d_type != DT_UNKNOWN ||              \
+                     !is_directory(lang_path, &script_dirent)))
 
 
 #define RECORD_SUFFIX                   "-record"
@@ -322,13 +319,13 @@ struct script_desc {
         char                    *args;
 };
 
-LIST_HEAD(script_descs);
+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)
+        if (s != NULL && name)
                 s->name = strdup(name);
 
         return s;
@@ -337,6 +334,8 @@ static struct script_desc *script_desc__new(const char *name)
 static void script_desc__delete(struct script_desc *s)
 {
         free(s->name);
+        free(s->half_liner);
+        free(s->args);
         free(s);
 }
 
@@ -376,10 +375,10 @@ out_delete_desc:
         return NULL;
 }
 
-static char *ends_with(char *str, const char *suffix)
+static const char *ends_with(const char *str, const char *suffix)
 {
         size_t suffix_len = strlen(suffix);
-        char *p = str;
+        const char *p = str;
 
         if (strlen(str) > suffix_len) {
                 p = str + strlen(str) - suffix_len;
@@ -462,16 +461,16 @@ static int list_available_scripts(const struct option *opt __used,
         if (!scripts_dir)
                 return -1;
 
-        for_each_lang(scripts_dir, lang_dirent, lang_next) {
+        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_dir, script_dirent, script_next) {
+                for_each_script(lang_path, lang_dir, script_dirent, script_next) {
                         script_root = strdup(script_dirent.d_name);
-                        str = ends_with(script_root, REPORT_SUFFIX);
+                        str = (char *)ends_with(script_root, REPORT_SUFFIX);
                         if (str) {
                                 *str = '\0';
                                 desc = script_desc__findnew(script_root);
@@ -510,16 +509,16 @@ static char *get_script_path(const char *script_root, const char *suffix)
         if (!scripts_dir)
                 return NULL;
 
-        for_each_lang(scripts_dir, lang_dirent, lang_next) {
+        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_dir, script_dirent, script_next) {
+                for_each_script(lang_path, lang_dir, script_dirent, script_next) {
                         __script_root = strdup(script_dirent.d_name);
-                        str = ends_with(__script_root, suffix);
+                        str = (char *)ends_with(__script_root, suffix);
                         if (str) {
                                 *str = '\0';
                                 if (strcmp(__script_root, script_root))
@@ -537,8 +536,40 @@ static char *get_script_path(const char *script_root, const char *suffix)
         return path;
 }
 
-static const char * const trace_usage[] = {
-        "perf trace [<options>] <command>",
+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
 };
 
@@ -555,7 +586,7 @@ static const struct option options[] = {
                      "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"),
+                   "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,
@@ -564,50 +595,81 @@ static const struct option options[] = {
         OPT_END()
 };
 
-int cmd_trace(int argc, const char **argv, const char *prefix __used)
+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;
-        const char *suffix = NULL;
+        char *script_path = NULL;
         const char **__argv;
-        char *script_path;
-        int i, err;
+        bool system_wide;
+        int i, j, 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;
+        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 >= 2 && strncmp(argv[1], "rep", strlen("rep")) == 0) {
-                if (argc < 3) {
+        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 report script\n");
+                                "Please specify a valid report script"
+                                "(see 'perf script -l' for listing)\n");
                         return -1;
                 }
-                suffix = REPORT_SUFFIX;
         }
 
         /* make sure PERF_EXEC_PATH is set for scripts */
         perf_set_argv_exec_path(perf_exec_path());
 
-        if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
-                char *record_script_path, *report_script_path;
+        if (argc && !script_name && !rec_script_path && !rep_script_path) {
                 int live_pipe[2];
+                int rep_args;
                 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;
+                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);
                 }
 
-                report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
-                if (!report_script_path) {
-                        fprintf(stderr, "report script not found\n");
-                        return -1;
+                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) {
@@ -622,66 +684,90 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                 }
 
                 if (!pid) {
+                        system_wide = true;
+                        j = 0;
+
                         dup2(live_pipe[1], 1);
                         close(live_pipe[0]);
 
-                        __argv = malloc(6 * sizeof(const char *));
-                        __argv[0] = "/bin/sh";
-                        __argv[1] = record_script_path;
-                        __argv[2] = "-q";
-                        __argv[3] = "-o";
-                        __argv[4] = "-";
-                        __argv[5] = NULL;
+                        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 + 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;
+                __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 (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;
+        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);
         }
 
-        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);
+        session = perf_session__new(input_name, O_RDONLY, 0, false, &event_ops);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -715,7 +801,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                         return -1;
                 }
 
-                err = scripting_ops->generate_script("perf-trace");
+                err = scripting_ops->generate_script("perf-script");
                 goto out;
         }
 
@@ -723,10 +809,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                 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);
+                pr_debug("perf script started with script %s\n\n", script_name);
         }
 
-        err = __cmd_trace(session);
+        err = __cmd_script(session);
 
         perf_session__delete(session);
         cleanup_scripting();
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a6b4d44f9502..a482a191a0ca 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -43,6 +43,7 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/event.h"
+#include "util/evsel.h"
 #include "util/debug.h"
 #include "util/header.h"
 #include "util/cpumap.h"
@@ -52,6 +53,8 @@
 #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              },
@@ -69,25 +72,23 @@ static struct perf_event_attr default_attrs[] = {
 };
 
 static bool                     system_wide                     =  false;
-static int                      nr_cpus                         =  0;
+static struct cpu_map           *cpus;
 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 struct thread_map        *threads;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
-static bool                     big_num                         =  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 +97,22 @@ 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;
@@ -135,69 +152,38 @@ 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_branches_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;
-                }
+        if (system_wide)
+                return perf_evsel__open_per_cpu(evsel, cpus);
+
+        attr->inherit = !no_inherit;
+        if (target_pid == -1 && target_tid == -1) {
+                attr->disabled = 1;
+                attr->enable_on_exec = 1;
         }
 
-        return ncreated;
+        return perf_evsel__open_per_thread(evsel, threads);
 }
 
 /*
  * Does the counter have nsecs as a unit?
  */
-static inline int nsec_counter(int counter)
+static inline int nsec_counter(struct perf_evsel *evsel)
 {
-        if (MATCH_EVENT(SOFTWARE, SW_CPU_CLOCK, counter) ||
-            MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
+        if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+            perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
                 return 1;
 
         return 0;
@@ -205,84 +191,73 @@ static inline int nsec_counter(int counter)
 
 /*
  * 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, cpus->nr, 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:
+         */
+        if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+                update_stats(&runtime_nsecs_stats[0], count[0]);
+        if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+                update_stats(&runtime_cycles_stats[0], count[0]);
+        if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+                update_stats(&runtime_branches_stats[0], count[0]);
 
-                        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 < 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]);
+                if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+                        update_stats(&runtime_nsecs_stats[cpu], count[0]);
+                if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+                        update_stats(&runtime_cycles_stats[cpu], count[0]);
+                if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+                        update_stats(&runtime_branches_stats[cpu], count[0]);
         }
 
-        /*
-         * 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 +297,7 @@ 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;
+                        threads->map[0] = child_pid;
 
                 /*
                  * Wait for the child to be ready to exec.
@@ -334,16 +309,25 @@ 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);
-
-        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);
-                return -1;
+        list_for_each_entry(counter, &evsel_list, node) {
+                if (create_perf_stat_counter(counter) < 0) {
+                        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 if (errno == ENOENT) {
+                                error("%s event is not supported. ", event_name(counter));
+                        } 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;
+                }
         }
 
         /*
@@ -362,60 +346,97 @@ 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, node) {
+                        read_counter(counter);
+                        perf_evsel__close_fd(counter, cpus->nr, 1);
+                }
+        } else {
+                list_for_each_entry(counter, &evsel_list, node) {
+                        read_counter_aggr(counter);
+                        perf_evsel__close_fd(counter, cpus->nr, threads->nr);
+                }
+        }
 
         return WEXITSTATUS(status);
 }
 
-static void print_noise(int counter, double avg)
+static void print_noise(struct perf_evsel *evsel, double avg)
 {
+        struct perf_stat *ps;
+
         if (run_count == 1)
                 return;
 
+        ps = evsel->priv;
         fprintf(stderr, "   ( +- %7.3f%% )",
-                        100 * stddev_stats(&event_res_stats[counter][0]) / avg);
+                        100 * 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%-24s";
+
+        if (no_aggr)
+                sprintf(cpustr, "CPU%*d%s",
+                        csv_output ? 0 : -4,
+                        cpus->map[cpu], csv_sep);
 
-        fprintf(stderr, " %18.6f  %-24s", msecs, event_name(counter));
+        fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel));
 
-        if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) {
+        if (csv_output)
+                return;
+
+        if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
                 fprintf(stderr, " # %10.3f CPUs ",
                                 avg / avg_stats(&walltime_nsecs_stats));
-        }
 }
 
-static void abs_printout(int counter, double avg)
+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 (big_num)
-                fprintf(stderr, " %'18.0f  %-24s", avg, event_name(counter));
+        if (csv_output)
+                fmt = "%s%.0f%s%s";
+        else if (big_num)
+                fmt = "%s%'18.0f%s%-24s";
         else
-                fprintf(stderr, " %18.0f  %-24s", avg, event_name(counter));
+                fmt = "%s%18.0f%s%-24s";
 
-        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,
+                        cpus->map[cpu], csv_sep);
+        else
+                cpu = 0;
+
+        fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel));
+
+        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);
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+                        runtime_branches_stats[cpu].n != 0) {
+                total = avg_stats(&runtime_branches_stats[cpu]);
 
                 if (total)
                         ratio = avg * 100 / total;
 
                 fprintf(stderr, " # %10.3f %%    ", ratio);
 
-        } else if (runtime_nsecs_stats.n != 0) {
-                total = avg_stats(&runtime_nsecs_stats);
+        } else if (runtime_nsecs_stats[cpu].n != 0) {
+                total = avg_stats(&runtime_nsecs_stats[cpu]);
 
                 if (total)
                         ratio = 1000.0 * avg / total;
@@ -426,30 +447,38 @@ static void abs_printout(int counter, double avg)
 
 /*
  * 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%-24s\n",
+                        csv_output ? 0 : 18,
+                        "<not counted>", csv_sep, event_name(counter));
                 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);
@@ -458,40 +487,92 @@ static void print_counter(int counter)
         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 < 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%-24s",
+                                csv_output ? 0 : -4,
+                                cpus->map[cpu], csv_sep,
+                                csv_output ? 0 : 18,
+                                "<not counted>", csv_sep,
+                                event_name(counter));
+
+                        fprintf(stderr, "\n");
+                        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, "  (scaled from %.2f%%)",
+                                        100.0 * run / ena);
+                        }
+                }
+                fprintf(stderr, "\n");
+        }
+}
+
 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, node)
+                        print_counter(counter);
+        } else {
+                list_for_each_entry(counter, &evsel_list, 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%% )",
+        if (!csv_output) {
+                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));
+                }
+                fprintf(stderr, "\n\n");
         }
-        fprintf(stderr, "\n\n");
 }
 
 static volatile int signr = -1;
@@ -521,6 +602,13 @@ 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",
                      "event selector. use 'perf list' to list available events",
@@ -541,64 +629,95 @@ 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_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_END()
 };
 
 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, "");
 
         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);
 
+        /* no_aggr is for system-wide only */
+        if (no_aggr && !system_wide)
+                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));
+                size_t c;
+
                 nr_counters = ARRAY_SIZE(default_attrs);
+
+                for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) {
+                        pos = perf_evsel__new(&default_attrs[c],
+                                              nr_counters);
+                        if (pos == NULL)
+                                goto out;
+                        list_add(&pos->node, &evsel_list);
+                }
         }
 
-        if (system_wide)
-                nr_cpus = read_cpu_map(cpu_list);
-        else
-                nr_cpus = 1;
+        if (target_pid != -1)
+                target_tid = target_pid;
 
-        if (nr_cpus < 1)
+        threads = thread_map__new(target_pid, target_tid);
+        if (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)
+                cpus = cpu_map__new(cpu_list);
+        else
+                cpus = cpu_map__dummy_new();
 
-                all_tids[0] = target_tid;
-                thread_num = 1;
+        if (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, node) {
+                if (perf_evsel__alloc_stat_priv(pos) < 0 ||
+                    perf_evsel__alloc_counts(pos, cpus->nr) < 0 ||
+                    perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0)
+                        goto out_free_fd;
         }
 
         /*
@@ -621,6 +740,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 
         if (status != -1)
                 print_stat(argc, argv);
-
+out_free_fd:
+        list_for_each_entry(pos, &evsel_list, node)
+                perf_evsel__free_stat_priv(pos);
+        perf_evsel_list__delete();
+out:
+        thread_map__delete(threads);
+        threads = NULL;
         return status;
 }
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 035b9fa063a9..5dcdba653d70 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -119,10 +119,16 @@ 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 +146,13 @@ 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 +161,18 @@ 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 +211,10 @@ 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 +234,209 @@ out:
         return err;
 }
 
+#include "util/cpumap.h"
+#include "util/evsel.h"
+#include <sys/types.h>
+
+static int trace_event__id(const char *event_name)
+{
+        char *filename;
+        int err = -1, fd;
+
+        if (asprintf(&filename,
+                     "/sys/kernel/debug/tracing/events/syscalls/%s/id",
+                     event_name) < 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) < 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__open_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 (threads == NULL) {
+                pr_debug("thread_map__new\n");
+                return -1;
+        }
+
+
+        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) < 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;
+        }
+
+        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__open_read_on_cpu\n");
+                        goto out_close_fd;
+                }
+
+                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);
+                        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;
+}
+
 static struct test {
         const char *desc;
         int (*func)(void);
@@ -228,6 +446,14 @@ 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,
+        },
+        {
                 .func = NULL,
         },
 };
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 9bcc38f0b706..746cf03cb05d 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";
 
@@ -272,19 +276,22 @@ 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(event_t *event, struct sample_data *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(event_t *event, struct sample_data *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(event_t *event, struct sample_data *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 +486,65 @@ 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(event_t *event __used,
+                                struct sample_data *sample,
+                                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
                 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 (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 +970,8 @@ 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 +1002,8 @@ 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 +1015,43 @@ 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 +1080,8 @@ 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..b6998e055767 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -21,6 +21,7 @@
 #include "perf.h"
 
 #include "util/color.h"
+#include "util/evsel.h"
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/thread.h"
@@ -29,6 +30,7 @@
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/cpumap.h"
+#include "util/xyarray.h"
 
 #include "util/debug.h"
 
@@ -38,6 +40,7 @@
 #include <stdio.h>
 #include <termios.h>
 #include <unistd.h>
+#include <inttypes.h>
 
 #include <errno.h>
 #include <time.h>
@@ -55,7 +58,7 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
 static bool                     system_wide                     =  false;
 
@@ -66,11 +69,9 @@ static int			print_entries;
 
 static int                      target_pid                      =     -1;
 static int                      target_tid                      =     -1;
-static pid_t                    *all_tids                       =      NULL;
-static int                      thread_num                      =      0;
+static struct thread_map        *threads;
 static bool                     inherit                         =  false;
-static int                      profile_cpu                     =     -1;
-static int                      nr_cpus                         =      0;
+static struct cpu_map           *cpus;
 static int                      realtime_prio                   =      0;
 static bool                     group                           =  false;
 static unsigned int             page_size;
@@ -101,6 +102,7 @@ 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 struct perf_evsel        *sym_evsel                      =   NULL;
 static int                      display_weighted                =     -1;
 static const char               *cpu_list;
 
@@ -213,7 +215,7 @@ static int parse_source(struct sym_entry *syme)
         len = sym->end - sym->start;
 
         sprintf(command,
-                "objdump --start-address=%#0*Lx --stop-address=%#0*Lx -dS %s",
+                "objdump --start-address=%#0*" PRIx64 " --stop-address=%#0*" PRIx64 " -dS %s",
                 BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
                 BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
 
@@ -307,7 +309,7 @@ static void lookup_sym_source(struct sym_entry *syme)
         struct source_line *line;
         char pattern[PATTERN_LEN + 1];
 
-        sprintf(pattern, "%0*Lx <", BITS_PER_LONG / 4,
+        sprintf(pattern, "%0*" PRIx64 " <", BITS_PER_LONG / 4,
                 map__rip_2objdump(syme->map, symbol->start));
 
         pthread_mutex_lock(&syme->src->lock);
@@ -354,7 +356,7 @@ static void show_details(struct sym_entry *syme)
                 return;
 
         symbol = sym_entry__symbol(syme);
-        printf("Showing %s for %s\n", event_name(sym_counter), symbol->name);
+        printf("Showing %s for %s\n", event_name(sym_evsel), symbol->name);
         printf("  Events  Pcnt (>=%d%%)\n", sym_pcnt_filter);
 
         pthread_mutex_lock(&syme->src->lock);
@@ -461,7 +463,8 @@ static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se)
 static void print_sym_table(void)
 {
         int printed = 0, j;
-        int counter, snap = !display_weighted ? sym_counter : 0;
+        struct perf_evsel *counter;
+        int 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;
@@ -533,7 +536,9 @@ static void print_sym_table(void)
         }
 
         if (nr_counters == 1 || !display_weighted) {
-                printf("%Ld", (u64)attrs[0].sample_period);
+                struct perf_evsel *first;
+                first = list_entry(evsel_list.next, struct perf_evsel, node);
+                printf("%" PRIu64, (uint64_t)first->attr.sample_period);
                 if (freq)
                         printf("Hz ");
                 else
@@ -541,9 +546,9 @@ static void print_sym_table(void)
         }
 
         if (!display_weighted)
-                printf("%s", event_name(sym_counter));
-        else for (counter = 0; counter < nr_counters; counter++) {
-                if (counter)
+                printf("%s", event_name(sym_evsel));
+        else list_for_each_entry(counter, &evsel_list, node) {
+                if (counter->idx)
                         printf("/");
 
                 printf("%s", event_name(counter));
@@ -558,13 +563,13 @@ static void print_sym_table(void)
         else
                 printf(" (all");
 
-        if (profile_cpu != -1)
-                printf(", cpu: %d)\n", profile_cpu);
+        if (cpu_list)
+                printf(", CPU%s: %s)\n", cpus->nr > 1 ? "s" : "", cpu_list);
         else {
                 if (target_tid != -1)
                         printf(")\n");
                 else
-                        printf(", %d CPUs)\n", nr_cpus);
+                        printf(", %d CPU%s)\n", cpus->nr, cpus->nr > 1 ? "s" : "");
         }
 
         printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
@@ -636,7 +641,7 @@ static void print_sym_table(void)
 
                 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 ?
@@ -740,7 +745,7 @@ static void print_mapped_keys(void)
         fprintf(stdout, "\t[e]     display entries (lines).           \t(%d)\n", print_entries);
 
         if (nr_counters > 1)
-                fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(sym_counter));
+                fprintf(stdout, "\t[E]     active event counter.              \t(%s)\n", event_name(sym_evsel));
 
         fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", count_filter);
 
@@ -827,19 +832,23 @@ static void handle_keypress(struct perf_session *session, int c)
                         break;
                 case 'E':
                         if (nr_counters > 1) {
-                                int i;
-
                                 fprintf(stderr, "\nAvailable events:");
-                                for (i = 0; i < nr_counters; i++)
-                                        fprintf(stderr, "\n\t%d %s", i, event_name(i));
+
+                                list_for_each_entry(sym_evsel, &evsel_list, node)
+                                        fprintf(stderr, "\n\t%d %s", sym_evsel->idx, event_name(sym_evsel));
 
                                 prompt_integer(&sym_counter, "Enter details event counter");
 
                                 if (sym_counter >= nr_counters) {
-                                        fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(0));
+                                        sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
                                         sym_counter = 0;
+                                        fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(sym_evsel));
                                         sleep(1);
+                                        break;
                                 }
+                                list_for_each_entry(sym_evsel, &evsel_list, node)
+                                        if (sym_evsel->idx == sym_counter)
+                                                break;
                         } else sym_counter = 0;
                         break;
                 case 'f':
@@ -978,12 +987,13 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 }
 
 static void event__process_sample(const event_t *self,
-                                 struct perf_session *session, int counter)
+                                  struct sample_data *sample,
+                                  struct perf_session *session,
+                                  struct perf_evsel *evsel)
 {
         u64 ip = self->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;
 
@@ -1026,7 +1036,7 @@ static void event__process_sample(const event_t *self,
         if (self->header.misc & PERF_RECORD_MISC_EXACT_IP)
                 exact_samples++;
 
-        if (event__preprocess_sample(self, session, &al, &data,
+        if (event__preprocess_sample(self, session, &al, sample,
                                      symbol_filter) < 0 ||
             al.filtered)
                 return;
@@ -1072,9 +1082,9 @@ static void event__process_sample(const event_t *self,
 
         syme = symbol__priv(al.sym);
         if (!syme->skip) {
-                syme->count[counter]++;
+                syme->count[evsel->idx]++;
                 syme->origin = origin;
-                record_precise_ip(syme, counter, ip);
+                record_precise_ip(syme, evsel->idx, ip);
                 pthread_mutex_lock(&active_symbols_lock);
                 if (list_empty(&syme->node) || !syme->node.next)
                         __list_insert_active_sym(syme);
@@ -1083,12 +1093,24 @@ static void event__process_sample(const event_t *self,
 }
 
 struct mmap_data {
-        int                     counter;
         void                    *base;
         int                     mask;
         unsigned int            prev;
 };
 
+static int perf_evsel__alloc_mmap_per_thread(struct perf_evsel *evsel,
+                                             int ncpus, int nthreads)
+{
+        evsel->priv = xyarray__new(ncpus, nthreads, sizeof(struct mmap_data));
+        return evsel->priv != NULL ? 0 : -ENOMEM;
+}
+
+static void perf_evsel__free_mmap(struct perf_evsel *evsel)
+{
+        xyarray__delete(evsel->priv);
+        evsel->priv = NULL;
+}
+
 static unsigned int mmap_read_head(struct mmap_data *md)
 {
         struct perf_event_mmap_page *pc = md->base;
@@ -1101,11 +1123,15 @@ static unsigned int mmap_read_head(struct mmap_data *md)
 }
 
 static void perf_session__mmap_read_counter(struct perf_session *self,
-                                            struct mmap_data *md)
+                                            struct perf_evsel *evsel,
+                                            int cpu, int thread_idx)
 {
+        struct xyarray *mmap_array = evsel->priv;
+        struct mmap_data *md = xyarray__entry(mmap_array, cpu, thread_idx);
         unsigned int head = mmap_read_head(md);
         unsigned int old = md->prev;
         unsigned char *data = md->base + page_size;
+        struct sample_data sample;
         int diff;
 
         /*
@@ -1153,10 +1179,11 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
                         event = &event_copy;
                 }
 
+                event__parse_sample(event, self, &sample);
                 if (event->header.type == PERF_RECORD_SAMPLE)
-                        event__process_sample(event, self, md->counter);
+                        event__process_sample(event, &sample, self, evsel);
                 else
-                        event__process(event, self);
+                        event__process(event, &sample, self);
                 old += size;
         }
 
@@ -1164,37 +1191,39 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
 }
 
 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;
+        struct perf_evsel *counter;
+        int i, thread_index;
 
-        for (i = 0; i < nr_cpus; i++) {
-                for (counter = 0; counter < nr_counters; counter++)
+        for (i = 0; i < cpus->nr; i++) {
+                list_for_each_entry(counter, &evsel_list, node) {
                         for (thread_index = 0;
-                                thread_index < thread_num;
+                                thread_index < threads->nr;
                                 thread_index++) {
                                 perf_session__mmap_read_counter(self,
-                                        &mmap_array[i][counter][thread_index]);
+                                        counter, i, thread_index);
                         }
+                }
         }
 }
 
 int nr_poll;
 int group_fd;
 
-static void start_counter(int i, int counter)
+static void start_counter(int i, struct perf_evsel *evsel)
 {
+        struct xyarray *mmap_array = evsel->priv;
+        struct mmap_data *mm;
         struct perf_event_attr *attr;
-        int cpu;
+        int cpu = -1;
         int thread_index;
 
-        cpu = profile_cpu;
-        if (target_tid == -1 && profile_cpu == -1)
-                cpu = cpumap[i];
+        if (target_tid == -1)
+                cpu = cpus->map[i];
 
-        attr = attrs + counter;
+        attr = &evsel->attr;
 
         attr->sample_type       = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
 
@@ -1207,16 +1236,18 @@ static void start_counter(int i, int counter)
         attr->inherit           = (cpu < 0) && inherit;
         attr->mmap              = 1;
 
-        for (thread_index = 0; thread_index < thread_num; thread_index++) {
+        for (thread_index = 0; thread_index < threads->nr; thread_index++) {
 try_again:
-                fd[i][counter][thread_index] = sys_perf_event_open(attr,
-                                all_tids[thread_index], cpu, group_fd, 0);
+                FD(evsel, i, thread_index) = sys_perf_event_open(attr,
+                                threads->map[thread_index], cpu, group_fd, 0);
 
-                if (fd[i][counter][thread_index] < 0) {
+                if (FD(evsel, i, thread_index) < 0) {
                         int err = errno;
 
                         if (err == EPERM || err == EACCES)
-                                die("No permission - are you root?\n");
+                                die("Permission error - are you root?\n"
+                                        "\t Consider tweaking"
+                                        " /proc/sys/kernel/perf_event_paranoid.\n");
                         /*
                          * If it's cycles then fall back to hrtimer
                          * based cpu-clock-tick sw counter, which
@@ -1233,30 +1264,30 @@ try_again:
                                 goto try_again;
                         }
                         printf("\n");
-                        error("perfcounter syscall returned with %d (%s)\n",
-                                        fd[i][counter][thread_index], strerror(err));
+                        error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
+                                        FD(evsel, i, thread_index), strerror(err));
                         die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
                         exit(-1);
                 }
-                assert(fd[i][counter][thread_index] >= 0);
-                fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
+                assert(FD(evsel, i, thread_index) >= 0);
+                fcntl(FD(evsel, i, 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];
+                        group_fd = FD(evsel, i, thread_index);
 
-                event_array[nr_poll].fd = fd[i][counter][thread_index];
+                event_array[nr_poll].fd = FD(evsel, i, 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)
+                mm = xyarray__entry(mmap_array, i, thread_index);
+                mm->prev = 0;
+                mm->mask = mmap_pages*page_size - 1;
+                mm->base = mmap(NULL, (mmap_pages+1)*page_size,
+                                PROT_READ, MAP_SHARED, FD(evsel, i, thread_index), 0);
+                if (mm->base == MAP_FAILED)
                         die("failed to mmap with %d (%s)\n", errno, strerror(errno));
         }
 }
@@ -1264,13 +1295,13 @@ try_again:
 static int __cmd_top(void)
 {
         pthread_t thread;
-        int i, counter;
-        int ret;
+        struct perf_evsel *counter;
+        int i, ret;
         /*
          * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
          * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
          */
-        struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false);
+        struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
         if (session == NULL)
                 return -ENOMEM;
 
@@ -1279,9 +1310,9 @@ static int __cmd_top(void)
         else
                 event__synthesize_threads(event__process, session);
 
-        for (i = 0; i < nr_cpus; i++) {
+        for (i = 0; i < cpus->nr; i++) {
                 group_fd = -1;
-                for (counter = 0; counter < nr_counters; counter++)
+                list_for_each_entry(counter, &evsel_list, node)
                         start_counter(i, counter);
         }
 
@@ -1370,8 +1401,8 @@ 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;
 
         page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -1379,34 +1410,17 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
         if (argc)
                 usage_with_options(top_usage, options);
 
-        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(top_usage, options);
-                }
-        } else {
-                all_tids=malloc(sizeof(pid_t));
-                if (!all_tids)
-                        return -ENOMEM;
 
-                all_tids[0] = target_tid;
-                thread_num = 1;
+        threads = thread_map__new(target_pid, target_tid);
+        if (threads == NULL) {
+                pr_err("Problems finding threads of monitor\n");
+                usage_with_options(top_usage, options);
         }
 
-        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);
+        event_array = malloc((sizeof(struct pollfd) *
+                              MAX_NR_CPUS * MAX_COUNTERS * threads->nr));
         if (!event_array)
                 return -ENOMEM;
 
@@ -1417,15 +1431,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 cpu_list = NULL;
         }
 
-        if (!nr_counters)
-                nr_counters = 1;
-
-        symbol_conf.priv_size = (sizeof(struct sym_entry) +
-                                 (nr_counters + 1) * sizeof(unsigned long));
-
-        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-        if (symbol__init() < 0)
-                return -1;
+        if (!nr_counters && perf_evsel_list__create_default() < 0) {
+                pr_err("Not enough memory for event selector list\n");
+                return -ENOMEM;
+        }
 
         if (delay_secs < 1)
                 delay_secs = 1;
@@ -1442,23 +1451,35 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 exit(EXIT_FAILURE);
         }
 
-        /*
-         * Fill in the ones not specifically initialized via -c:
-         */
-        for (counter = 0; counter < nr_counters; counter++) {
-                if (attrs[counter].sample_period)
+        if (target_tid != -1)
+                cpus = cpu_map__dummy_new();
+        else
+                cpus = cpu_map__new(cpu_list);
+
+        if (cpus == NULL)
+                usage_with_options(top_usage, options);
+
+        list_for_each_entry(pos, &evsel_list, node) {
+                if (perf_evsel__alloc_mmap_per_thread(pos, cpus->nr, threads->nr) < 0 ||
+                    perf_evsel__alloc_fd(pos, cpus->nr, 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);
+        sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node);
 
-        if (nr_cpus < 1)
-                usage_with_options(top_usage, options);
+        symbol_conf.priv_size = (sizeof(struct sym_entry) +
+                                 (nr_counters + 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) {
@@ -1466,5 +1487,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 signal(SIGWINCH, sig_winch_handler);
         }
 
-        return __cmd_top();
+        status = __cmd_top();
+out_free_fd:
+        list_for_each_entry(pos, &evsel_list, node)
+                perf_evsel__free_mmap(pos);
+        perf_evsel_list__delete();
+
+        return status;
 }
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 921245b28583..c7798c7f24ed 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -27,7 +27,7 @@ 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..16b5088cf8f4 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -16,7 +16,7 @@ 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/feature-tests.mak
index b253db634f04..b041ca67a2cb 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/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
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index cdd6c03f1e14..595d0f4a7103 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -323,7 +323,7 @@ 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/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 4028d92dc4ae..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 $@ -s "$PERF_EXEC_PATH"/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 ba25f4d41fb0..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 $@ -s "$PERF_EXEC_PATH"/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 641a3f5d085c..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 $@ -s "$PERF_EXEC_PATH"/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 $@
diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report
index 4918dba77021..83e11ec2e190 100644
--- a/tools/perf/scripts/perl/bin/rwtop-report
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -17,7 +17,4 @@ if [ "$n_args" -gt 0 ] ; then
     interval=$1
     shift
 fi
-perf trace $@ -s "$PERF_EXEC_PATH"/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 49052ebcb632..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 $@ -s "$PERF_EXEC_PATH"/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 df0c65f4ca93..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 $@ -s "$PERF_EXEC_PATH"/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 13cc02b5893a..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>
 #
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 03587021463d..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 $@ -s "$PERF_EXEC_PATH"/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
index 5ecbb433caf4..b1495c9a9b20 100644
--- a/tools/perf/scripts/python/bin/futex-contention-record
+++ b/tools/perf/scripts/python/bin/futex-contention-record
@@ -1,2 +1,2 @@
 #!/bin/bash
-perf record -a -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@
+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
index c8268138fb7e..6c44271091ab 100644
--- a/tools/perf/scripts/python/bin/futex-contention-report
+++ b/tools/perf/scripts/python/bin/futex-contention-report
@@ -1,4 +1,4 @@
 #!/bin/bash
 # description: futext contention measurement
 
-perf trace $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py
+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
index d931a828126b..558754b840a9 100644
--- a/tools/perf/scripts/python/bin/netdev-times-record
+++ b/tools/perf/scripts/python/bin/netdev-times-record
@@ -1,5 +1,5 @@
 #!/bin/bash
-perf record -a -e net:net_dev_xmit -e net:net_dev_queue         \
+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        \
diff --git a/tools/perf/scripts/python/bin/netdev-times-report b/tools/perf/scripts/python/bin/netdev-times-report
index 4ad361b31249..8f759291da86 100644
--- a/tools/perf/scripts/python/bin/netdev-times-report
+++ b/tools/perf/scripts/python/bin/netdev-times-report
@@ -2,4 +2,4 @@
 # description: display a process of packet and processing time
 # args: [tx] [rx] [dev=] [debug]
 
-perf trace -s "$PERF_EXEC_PATH"/scripts/python/netdev-times.py $@
+perf script -s "$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 df1791f07c24..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 $@ -s "$PERF_EXEC_PATH"/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 $@
diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report
index 36b409c05e50..c32db294124d 100644
--- a/tools/perf/scripts/python/bin/sctop-report
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -21,4 +21,4 @@ elif [ "$n_args" -gt 0 ] ; then
     interval=$1
     shift
 fi
-perf trace $@ -s "$PERF_EXEC_PATH"/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 4eb88c9fc83c..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 $@ -s "$PERF_EXEC_PATH"/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 cb2f9c5cf17e..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 $@ -s "$PERF_EXEC_PATH"/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 acd7848717b3..85805fac4116 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -15,7 +15,7 @@ from perf_trace_context import *
 from Core import *
 from Util import *
 
-usage = "perf trace -s syscall-counts-by-pid.py [comm|pid]\n";
+usage = "perf script -s syscall-counts-by-pid.py [comm|pid]\n";
 
 for_comm = None
 for_pid = None
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 7a6ec2c7d8ab..42c267e292fa 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -17,7 +17,7 @@ from perf_trace_context import *
 from Core import *
 from Util import *
 
-usage = "perf trace -s sctop.py [comm] [interval]\n";
+usage = "perf script -s sctop.py [comm] [interval]\n";
 
 for_comm = None
 default_interval = 3
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index d1ee3ec10cf2..c64d1c55d745 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -14,7 +14,7 @@ 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
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index ea183dc82d29..b435d3f188e8 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -15,7 +15,7 @@ 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
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e437edb72417..deffb8c96071 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -14,7 +14,9 @@
 #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(event_t *event,
+                                  struct sample_data *sample __used,
+                                  struct perf_session *session)
 {
         struct addr_location al;
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
@@ -35,7 +37,8 @@ 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 event__exit_del_thread(event_t *self, struct sample_data *sample __used,
+                                  struct perf_session *session)
 {
         struct thread *thread = perf_session__findnew(session, self->fork.tid);
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0f9b8d7a7d7e..3ccaa1043383 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 +138,42 @@ 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;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 3e60f56e490e..f7a4f42f6307 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 c8d81b00089d..01bbe8ecec3f 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -46,20 +46,16 @@ 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 trace_event(event_t *event)
 {
@@ -70,29 +66,29 @@ 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 7b514082bbaf..ca35fd66b5df 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -35,4 +35,6 @@ 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)));
+
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dab9e754a281..1478ab4ee222 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,7 +7,7 @@
 #include "strlist.h"
 #include "thread.h"
 
-const char *event__name[] = {
+static const char *event__name[] = {
         [0]                      = "TOTAL",
         [PERF_RECORD_MMAP]       = "MMAP",
         [PERF_RECORD_LOST]       = "LOST",
@@ -22,13 +22,31 @@ const char *event__name[] = {
         [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",
 };
 
-static pid_t event__synthesize_comm(pid_t pid, int full,
+const char *event__get_event_name(unsigned int id)
+{
+        if (id >= ARRAY_SIZE(event__name))
+                return "INVALID";
+        if (!event__name[id])
+                return "UNKNOWN";
+        return event__name[id];
+}
+
+static struct sample_data synth_sample = {
+        .pid       = -1,
+        .tid       = -1,
+        .time      = -1,
+        .stream_id = -1,
+        .cpu       = -1,
+        .period    = 1,
+};
+
+static pid_t event__synthesize_comm(event_t *event, pid_t pid, int full,
                                     event__handler_t process,
                                     struct perf_session *session)
 {
-        event_t ev;
         char filename[PATH_MAX];
         char bf[BUFSIZ];
         FILE *fp;
@@ -49,34 +67,39 @@ 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);
@@ -91,22 +114,19 @@ 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,
+static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid,
                                          event__handler_t process,
                                          struct perf_session *session)
 {
@@ -124,29 +144,25 @@ 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 +177,21 @@ 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);
                 }
         }
 
@@ -187,20 +205,27 @@ int event__synthesize_modules(event__handler_t process,
 {
         struct rb_node *nd;
         struct map_groups *kmaps = &machine->kmaps;
-        u16 misc;
+        event_t *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 +233,78 @@ 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(event_t *comm_event, event_t *mmap_event,
+                                      pid_t pid, event__handler_t process,
+                                      struct perf_session *session)
 {
-        pid_t tgid = event__synthesize_comm(pid, 1, process, session);
+        pid_t tgid = event__synthesize_comm(comm_event, pid, 1, process,
+                                            session);
         if (tgid == -1)
                 return -1;
-        return event__synthesize_mmap_events(pid, tgid, process, session);
+        return event__synthesize_mmap_events(mmap_event, pid, tgid,
+                                             process, session);
+}
+
+int event__synthesize_thread(pid_t pid, event__handler_t process,
+                             struct perf_session *session)
+{
+        event_t *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;
+
+        err = __event__synthesize_thread(comm_event, mmap_event, pid,
+                                         process, session);
+        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 event__synthesize_threads(event__handler_t process,
+                              struct perf_session *session)
 {
         DIR *proc;
         struct dirent dirent, *next;
+        event_t *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 +313,18 @@ 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 +332,8 @@ 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;
 
@@ -286,18 +359,20 @@ int event__synthesize_kernel_mmap(event__handler_t process,
         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, };
+        event_t *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 +380,10 @@ 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 {
@@ -321,17 +396,21 @@ 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);
+        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 void thread__comm_adjust(struct thread *self, struct hists *hists)
@@ -361,7 +440,8 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm,
         return 0;
 }
 
-int event__process_comm(event_t *self, struct perf_session *session)
+int event__process_comm(event_t *self, struct sample_data *sample __used,
+                        struct perf_session *session)
 {
         struct thread *thread = perf_session__findnew(session, self->comm.tid);
 
@@ -376,9 +456,11 @@ 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 event__process_lost(event_t *self, struct sample_data *sample __used,
+                        struct perf_session *session)
 {
-        dump_printf(": id:%Ld: lost:%Ld\n", self->lost.id, self->lost.lost);
+        dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
+                    self->lost.id, self->lost.lost);
         session->hists.stats.total_lost += self->lost.lost;
         return 0;
 }
@@ -392,7 +474,7 @@ static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
          * 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,
@@ -485,7 +567,8 @@ out_problem:
         return -1;
 }
 
-int event__process_mmap(event_t *self, struct perf_session *session)
+int event__process_mmap(event_t *self, struct sample_data *sample __used,
+                        struct perf_session *session)
 {
         struct machine *machine;
         struct thread *thread;
@@ -493,7 +576,7 @@ int event__process_mmap(event_t *self, struct perf_session *session)
         u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
         int ret = 0;
 
-        dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
+        dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
                         self->mmap.pid, self->mmap.tid, self->mmap.start,
                         self->mmap.len, self->mmap.pgoff, self->mmap.filename);
 
@@ -526,7 +609,8 @@ out_problem:
         return 0;
 }
 
-int event__process_task(event_t *self, struct perf_session *session)
+int event__process_task(event_t *self, struct sample_data *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);
@@ -548,18 +632,19 @@ int event__process_task(event_t *self, struct perf_session *session)
         return 0;
 }
 
-int event__process(event_t *event, struct perf_session *session)
+int event__process(event_t *event, struct sample_data *sample,
+                   struct perf_session *session)
 {
         switch (event->header.type) {
         case PERF_RECORD_COMM:
-                event__process_comm(event, session);
+                event__process_comm(event, sample, session);
                 break;
         case PERF_RECORD_MMAP:
-                event__process_mmap(event, session);
+                event__process_mmap(event, sample, session);
                 break;
         case PERF_RECORD_FORK:
         case PERF_RECORD_EXIT:
-                event__process_task(event, session);
+                event__process_task(event, sample, session);
                 break;
         default:
                 break;
@@ -674,32 +759,8 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session,
                              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);
-
-        if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
-                unsigned int i;
-
-                dump_printf("... chain: nr:%Lu\n", data->callchain->nr);
+        struct thread *thread = perf_session__findnew(session, self->ip.pid);
 
-                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;
 
@@ -766,9 +827,65 @@ out_filtered:
         return 0;
 }
 
-int event__parse_sample(const event_t *event, u64 type, struct sample_data *data)
+static int event__parse_id_sample(const event_t *event,
+                                  struct perf_session *session,
+                                  struct sample_data *sample)
 {
-        const u64 *array = event->sample.array;
+        const u64 *array;
+        u64 type;
+
+        sample->cpu = sample->pid = sample->tid = -1;
+        sample->stream_id = sample->id = sample->time = -1ULL;
+
+        if (!session->sample_id_all)
+                return 0;
+
+        array = event->sample.array;
+        array += ((event->header.size -
+                   sizeof(event->header)) / sizeof(u64)) - 1;
+        type = session->sample_type;
+
+        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;
+}
+
+int event__parse_sample(const event_t *event, struct perf_session *session,
+                        struct sample_data *data)
+{
+        const u64 *array;
+        u64 type;
+
+        if (event->header.type != PERF_RECORD_SAMPLE)
+                return event__parse_id_sample(event, session, data);
+
+        array = event->sample.array;
+        type = session->sample_type;
 
         if (type & PERF_SAMPLE_IP) {
                 data->ip = event->ip.ip;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8e790dae7026..2b7e91902f10 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@ 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,
@@ -135,12 +136,15 @@ void event__print_totals(void);
 
 struct perf_session;
 
-typedef int (*event__handler_t)(event_t *event, struct perf_session *session);
+typedef int (*event__handler_synth_t)(event_t *event, 
+                                      struct perf_session *session);
+typedef int (*event__handler_t)(event_t *event, struct sample_data *sample,
+                                struct perf_session *session);
 
 int event__synthesize_thread(pid_t pid, event__handler_t process,
                              struct perf_session *session);
-void event__synthesize_threads(event__handler_t process,
-                               struct perf_session *session);
+int event__synthesize_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,
@@ -150,18 +154,24 @@ 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 event__process_comm(event_t *self, struct sample_data *sample,
+                        struct perf_session *session);
+int event__process_lost(event_t *self, struct sample_data *sample,
+                        struct perf_session *session);
+int event__process_mmap(event_t *self, struct sample_data *sample,
+                        struct perf_session *session);
+int event__process_task(event_t *self, struct sample_data *sample,
+                        struct perf_session *session);
+int event__process(event_t *event, struct sample_data *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 event__parse_sample(const event_t *event, struct perf_session *session,
+                        struct sample_data *sample);
 
-extern const char *event__name[];
+const char *event__get_event_name(unsigned int id);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
new file mode 100644
index 000000000000..f5cfed60af98
--- /dev/null
+++ b/tools/perf/util/evsel.c
@@ -0,0 +1,201 @@
+#include "evsel.h"
+#include "../perf.h"
+#include "util.h"
+#include "cpumap.h"
+#include "thread.h"
+
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
+{
+        struct perf_evsel *evsel = zalloc(sizeof(*evsel));
+
+        if (evsel != NULL) {
+                evsel->idx         = idx;
+                evsel->attr        = *attr;
+                INIT_LIST_HEAD(&evsel->node);
+        }
+
+        return evsel;
+}
+
+int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+        evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+        return evsel->fd != NULL ? 0 : -ENOMEM;
+}
+
+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__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__delete(struct perf_evsel *evsel)
+{
+        assert(list_empty(&evsel->node));
+        xyarray__delete(evsel->fd);
+        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 = 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)
+{
+        int cpu, thread;
+
+        if (evsel->fd == NULL &&
+            perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+                return -1;
+
+        for (cpu = 0; cpu < cpus->nr; cpu++) {
+                for (thread = 0; thread < threads->nr; thread++) {
+                        FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
+                                                                     threads->map[thread],
+                                                                     cpus->map[cpu], -1, 0);
+                        if (FD(evsel, cpu, thread) < 0)
+                                goto out_close;
+                }
+        }
+
+        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)
+{
+
+        if (cpus == NULL) {
+                /* Work around old compiler warnings about strict aliasing */
+                cpus = &empty_cpu_map.map;
+        }
+
+        if (threads == NULL)
+                threads = &empty_thread_map.map;
+
+        return __perf_evsel__open(evsel, cpus, threads);
+}
+
+int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus)
+{
+        return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+}
+
+int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads)
+{
+        return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
new file mode 100644
index 000000000000..b2d755fe88a5
--- /dev/null
+++ b/tools/perf/util/evsel.h
@@ -0,0 +1,115 @@
+#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"
+ 
+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 {
+        struct list_head        node;
+        struct perf_event_attr  attr;
+        char                    *filter;
+        struct xyarray          *fd;
+        struct perf_counts      *counts;
+        int                     idx;
+        void                    *priv;
+};
+
+struct cpu_map;
+struct thread_map;
+
+struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
+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_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_fd(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);
+int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads);
+int perf_evsel__open(struct perf_evsel *evsel, 
+                     struct cpu_map *cpus, struct thread_map *threads);
+
+#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);
+}
+
+#endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d7e67b167ea3..f6a929e74981 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -152,6 +152,11 @@ void perf_header__set_feat(struct perf_header *self, int feat)
         set_bit(feat, self->adds_features);
 }
 
+void perf_header__clear_feat(struct perf_header *self, int feat)
+{
+        clear_bit(feat, self->adds_features);
+}
+
 bool perf_header__has_feat(const struct perf_header *self, int feat)
 {
         return test_bit(feat, self->adds_features);
@@ -265,15 +270,16 @@ 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 = realpath(name, NULL),
+             *filename = malloc(size),
              *linkname = malloc(size), *targetname;
         int len, err = -1;
 
-        if (filename == NULL || linkname == 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 +289,7 @@ 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 +306,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
         if (symlink(targetname, linkname) == 0)
                 err = 0;
 out_free:
+        free(realname);
         free(filename);
         free(linkname);
         return err;
@@ -431,8 +438,10 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
         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);
+
+        if (perf_header__has_feat(self, HEADER_BUILD_ID &&
+            !perf_session__read_build_ids(session, true)))
+                perf_header__clear_feat(self, HEADER_BUILD_ID);
 
         nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
         if (!nr_sections)
@@ -454,7 +463,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
 
                 /* Write trace info */
                 trace_sec->offset = lseek(fd, 0, SEEK_CUR);
-                read_tracing_data(fd, attrs, nr_counters);
+                read_tracing_data(fd, &evsel_list);
                 trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset;
         }
 
@@ -597,7 +606,7 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
 static int perf_header__getbuffer64(struct perf_header *self,
                                     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)
@@ -653,7 +662,7 @@ int perf_file_header__read(struct perf_file_header *self,
 {
         lseek(fd, 0, SEEK_SET);
 
-        if (do_read(fd, self, sizeof(*self)) <= 0 ||
+        if (readn(fd, self, sizeof(*self)) <= 0 ||
             memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
                 return -1;
 
@@ -789,8 +798,8 @@ static int perf_file_section__process(struct perf_file_section *self,
                                       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);
+                pr_debug("Failed to lseek to %" PRIu64 " offset for feature "
+                          "%d, continuing...\n", self->offset, feat);
                 return 0;
         }
 
@@ -814,7 +823,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
                                        struct perf_header *ph, int fd,
                                        bool repipe)
 {
-        if (do_read(fd, self, sizeof(*self)) <= 0 ||
+        if (readn(fd, self, sizeof(*self)) <= 0 ||
             memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
                 return -1;
 
@@ -939,6 +948,24 @@ u64 perf_header__sample_type(struct perf_header *header)
         return type;
 }
 
+bool perf_header__sample_id_all(const struct perf_header *header)
+{
+        bool value = false, first = true;
+        int i;
+
+        for (i = 0; i < header->attrs; i++) {
+                struct perf_header_attr *attr = header->attr[i];
+
+                if (first) {
+                        value = attr->attr.sample_id_all;
+                        first = false;
+                } else if (value != attr->attr.sample_id_all)
+                        die("non matching sample_id_all");
+        }
+
+        return value;
+}
+
 struct perf_event_attr *
 perf_header__find_attr(u64 id, struct perf_header *header)
 {
@@ -946,11 +973,16 @@ perf_header__find_attr(u64 id, struct perf_header *header)
 
         /*
          * 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.
+         * ids. This can happen when the data file contains one type
+         * of event and in that case, the header can still store the
+         * event attribute information. Check for this and avoid
+         * walking through the entire list of ids which may be large.
          */
-        if (id == -1ULL)
+        if (id == -1ULL) {
+                if (header->attrs > 0)
+                        return &header->attr[0]->attr;
                 return NULL;
+        }
 
         for (i = 0; i < header->attrs; i++) {
                 struct perf_header_attr *attr = header->attr[i];
@@ -980,21 +1012,23 @@ 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,
+int event__synthesize_attrs(struct perf_header *self, event__handler_t process,
                             struct perf_session *session)
 {
         struct perf_header_attr *attr;
@@ -1064,7 +1098,7 @@ 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;
 }
@@ -1099,8 +1133,7 @@ int event__process_event_type(event_t *self,
         return 0;
 }
 
-int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
-                                   int nb_events,
+int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
                                    event__handler_t process,
                                    struct perf_session *session __unused)
 {
@@ -1111,7 +1144,7 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
         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, pattrs);
         if (size <= 0)
                 return size;
         aligned_size = ALIGN(size, sizeof(u64));
@@ -1119,9 +1152,9 @@ 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, pattrs);
         write_padded(fd, NULL, 0, padding);
 
         return aligned_size;
@@ -1179,7 +1212,7 @@ 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;
 }
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 402ac2454cf8..33f16be7b72f 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -81,9 +81,11 @@ void perf_header_attr__delete(struct perf_header_attr *self);
 int perf_header_attr__add_id(struct perf_header_attr *self, u64 id);
 
 u64 perf_header__sample_type(struct perf_header *header);
+bool perf_header__sample_id_all(const 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);
+void perf_header__clear_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,
@@ -111,8 +113,7 @@ int event__synthesize_event_types(event__handler_t process,
 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,
+int event__synthesize_tracing_data(int fd, struct list_head *pattrs,
                                    event__handler_t process,
                                    struct perf_session *session);
 int event__process_tracing_data(event_t *self,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 2022e8740994..32f4f1f2f6e4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -356,7 +356,7 @@ 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;
@@ -636,13 +636,13 @@ 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, period);
                 else
-                        ret += snprintf(s + ret, size - ret, "%11lld", period);
+                        ret += snprintf(s + ret, size - ret, "%11" PRIu64, period);
         }
 
         if (pair_hists) {
@@ -971,7 +971,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
         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));
+        pr_debug3("%s: ip=%#" PRIx64 "\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip));
 
         if (offset >= sym_size)
                 return 0;
@@ -980,8 +980,9 @@ int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip)
         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]);
+        pr_debug3("%#" PRIx64 " %s: period++ [ip: %#" PRIx64 ", %#" PRIx64
+                  "] => %" PRIu64 "\n", self->ms.sym->start, self->ms.sym->name,
+                  ip, ip - self->ms.sym->start, h->ip[offset]);
         return 0;
 }
 
@@ -1092,6 +1093,12 @@ int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
         FILE *file;
         int err = 0;
         u64 len;
+        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) {
@@ -1100,9 +1107,9 @@ int hist_entry__annotate(struct hist_entry *self, struct list_head *head,
                         return -ENOMEM;
                 }
                 goto fallback;
-        } else if (readlink(filename, command, sizeof(command)) < 0 ||
+        } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
                    strstr(command, "[kernel.kallsyms]") ||
-                   access(filename, R_OK)) {
+                   access(symfs_filename, R_OK)) {
                 free(filename);
 fallback:
                 /*
@@ -1111,6 +1118,8 @@ fallback:
                  * 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;
         }
 
@@ -1124,7 +1133,7 @@ fallback:
                 goto out_free_filename;
         }
 
-        pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
+        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));
 
@@ -1134,10 +1143,10 @@ fallback:
                  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",
+                 "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),
-                 filename, filename);
+                 symfs_filename, filename);
 
         pr_debug("Executing: %s\n", command);
 
@@ -1168,10 +1177,13 @@ 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 = event__get_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..ee789856a8c9 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -52,8 +52,10 @@ 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;
 };
 
 enum hist_column {
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/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/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/parse-events.c b/tools/perf/util/parse-events.c
index 4af5bd59cfd1..135f69baf966 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,6 +1,7 @@
 #include "../../../include/linux/hw_breakpoint.h"
 #include "util.h"
 #include "../perf.h"
+#include "evsel.h"
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
@@ -12,8 +13,7 @@
 
 int                             nr_counters;
 
-struct perf_event_attr          attrs[MAX_COUNTERS];
-char                            *filters[MAX_COUNTERS];
+LIST_HEAD(evsel_list);
 
 struct event_symbol {
         u8              type;
@@ -266,10 +266,10 @@ 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_name(struct perf_evsel *evsel)
 {
-        u64 config = attrs[counter].config;
-        int type = attrs[counter].type;
+        u64 config = evsel->attr.config;
+        int type = evsel->attr.type;
 
         return __event_name(type, config);
 }
@@ -279,7 +279,7 @@ 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;
         }
 
@@ -434,7 +434,7 @@ 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;
@@ -490,12 +490,11 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
         return EVT_HANDLED_ALL;
 }
 
-
 static enum event_result parse_tracepoint_event(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 +513,11 @@ 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 +528,14 @@ 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;
+                *strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */
                 return parse_multiple_tracepoint_event(sys_name, evt_name,
                                                        flags);
-        } else
+        } else {
                 return parse_single_tracepoint_event(sys_name, evt_name,
                                                      evt_length, attr, strp);
+        }
 }
 
 static enum event_result
@@ -774,45 +778,12 @@ modifier:
         return ret;
 }
 
-static int store_event_type(const char *orgname)
-{
-        char filename[PATH_MAX], *c;
-        FILE *file;
-        int id, 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 perf_header__push_event(id, orgname);
-}
-
 int parse_events(const struct option *opt __used, const char *str, int unset __used)
 {
         struct perf_event_attr attr;
         enum event_result ret;
 
-        if (strchr(str, ':'))
-                if (store_event_type(str) < 0)
-                        return -1;
-
         for (;;) {
-                if (nr_counters == MAX_COUNTERS)
-                        return -1;
-
                 memset(&attr, 0, sizeof(attr));
                 ret = parse_event_symbols(&str, &attr);
                 if (ret == EVT_FAILED)
@@ -822,8 +793,13 @@ 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,
+                                                nr_counters);
+                        if (evsel == NULL)
+                                return -1;
+                        list_add_tail(&evsel->node, &evsel_list);
+                        ++nr_counters;
                 }
 
                 if (*str == 0)
@@ -840,21 +816,22 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
 int parse_filter(const struct option *opt __used, const char *str,
                  int unset __used)
 {
-        int i = nr_counters - 1;
-        int len = strlen(str);
+        struct perf_evsel *last = NULL;
+
+        if (!list_empty(&evsel_list))
+                last = list_entry(evsel_list.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;
 }
@@ -906,6 +883,47 @@ static void print_tracepoint_events(void)
 }
 
 /*
+ * Check whether event is in <debugfs_mount_point>/tracing/events
+ */
+
+int is_valid_tracepoint(const char *event_string)
+{
+        DIR *sys_dir, *evt_dir;
+        struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
+        char evt_path[MAXPATHLEN];
+        char dir_path[MAXPATHLEN];
+
+        if (debugfs_valid_mountpoint(debugfs_path))
+                return 0;
+
+        sys_dir = opendir(debugfs_path);
+        if (!sys_dir)
+                return 0;
+
+        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;
+}
+
+/*
  * Print the help text for the event symbols:
  */
 void print_events(void)
@@ -963,3 +981,33 @@ void print_events(void)
 
         exit(129);
 }
+
+int perf_evsel_list__create_default(void)
+{
+        struct perf_evsel *evsel;
+        struct perf_event_attr attr;
+
+        memset(&attr, 0, sizeof(attr));
+        attr.type = PERF_TYPE_HARDWARE;
+        attr.config = PERF_COUNT_HW_CPU_CYCLES;
+
+        evsel = perf_evsel__new(&attr, 0);
+
+        if (evsel == NULL)
+                return -ENOMEM;
+
+        list_add(&evsel->node, &evsel_list);
+        ++nr_counters;
+        return 0;
+}
+
+void perf_evsel_list__delete(void)
+{
+        struct perf_evsel *pos, *n;
+
+        list_for_each_entry_safe(pos, n, &evsel_list, node) {
+                list_del_init(&pos->node);
+                perf_evsel__delete(pos);
+        }
+        nr_counters = 0;
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index fc4ab3fe877a..458e3ecf17af 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -4,6 +4,16 @@
  * Parse symbolic events/counts passed in as options:
  */
 
+#include "../../../include/linux/perf_event.h"
+
+struct list_head;
+struct perf_evsel;
+
+extern struct list_head evsel_list;
+
+int perf_evsel_list__create_default(void);
+void perf_evsel_list__delete(void);
+
 struct option;
 
 struct tracepoint_path {
@@ -13,14 +23,11 @@ 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 bool have_tracepoints(struct list_head *evlist);
 
 extern int                      nr_counters;
 
-extern struct perf_event_attr attrs[MAX_COUNTERS];
-extern char *filters[MAX_COUNTERS];
-
-extern const char *event_name(int ctr);
+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);
@@ -29,9 +36,9 @@ extern int parse_filter(const struct option *opt, const char *str, int unset);
 #define EVENTS_HELP_MAX (128*1024)
 
 extern void print_events(void);
+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/probe-event.c b/tools/perf/util/probe-event.c
index 3b6a5297bf16..6e29d9c9dccc 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -95,7 +95,7 @@ static int init_vmlinux(void)
                 goto out;
 
         if (machine__create_kernel_maps(&machine) < 0) {
-                pr_debug("machine__create_kernel_maps ");
+                pr_debug("machine__create_kernel_maps() failed.\n");
                 goto out;
         }
 out:
@@ -114,6 +114,8 @@ static struct symbol *__find_kernel_function_by_name(const char *name,
 const char *kernel_get_module_path(const char *module)
 {
         struct dso *dso;
+        struct map *map;
+        const char *vmlinux_name;
 
         if (module) {
                 list_for_each_entry(dso, &machine.kernel_dsos, node) {
@@ -123,10 +125,17 @@ const char *kernel_get_module_path(const char *module)
                 }
                 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 {
-                dso = machine.vmlinux_maps[MAP__FUNCTION]->dso;
-                if (dso__load_vmlinux_path(dso,
-                         machine.vmlinux_maps[MAP__FUNCTION], NULL) < 0) {
+                if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
                         pr_debug("Failed to load kernel map.\n");
                         return NULL;
                 }
@@ -140,7 +149,8 @@ static int open_vmlinux(const char *module)
 {
         const char *path = kernel_get_module_path(module);
         if (!path) {
-                pr_err("Failed to find path of %s module", module ?: "kernel");
+                pr_err("Failed to find path of %s module.\n",
+                       module ?: "kernel");
                 return -ENOENT;
         }
         pr_debug("Try to open %s\n", path);
@@ -162,7 +172,7 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
         sym = __find_kernel_function_by_name(tp->symbol, &map);
         if (sym) {
                 addr = map->unmap_ip(map, sym->start + tp->offset);
-                pr_debug("try to find %s+%ld@%llx\n", tp->symbol,
+                pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol,
                          tp->offset, addr);
                 ret = find_perf_probe_point((unsigned long)addr, pp);
         }
@@ -217,7 +227,7 @@ 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;
                 }
         }
@@ -286,42 +296,49 @@ 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.
@@ -370,7 +387,7 @@ int show_line_range(struct line_range *lr, const char *module)
                 fprintf(stdout, "<%s:%d>\n", lr->function,
                         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) {
@@ -379,26 +396,30 @@ int show_line_range(struct line_range *lr, const char *module)
                 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;
@@ -457,7 +478,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 
         fd = open_vmlinux(module);
         if (fd < 0) {
-                pr_warning("Failed to open debuginfo file.\n");
+                pr_warning("Failed to open debug information file.\n");
                 return fd;
         }
 
@@ -517,56 +538,87 @@ int show_available_vars(struct perf_probe_event *pevs __unused,
 }
 #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[: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, *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;
+        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 */
@@ -690,39 +742,40 @@ 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;
         }
 
@@ -996,7 +1049,7 @@ 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;
 }
@@ -1024,13 +1077,13 @@ 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;
         }
@@ -1046,7 +1099,7 @@ 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);
@@ -1787,7 +1840,7 @@ 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;
         }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 3991d73d1cff..ab83b6ac5d65 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -117,28 +117,6 @@ static void line_list__free(struct list_head *head)
 }
 
 /* Dwarf FL wrappers */
-
-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);
-
-        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 char *debuginfo_path;    /* Currently dummy */
 
 static const Dwfl_Callbacks offline_callbacks = {
@@ -151,14 +129,6 @@ static const Dwfl_Callbacks offline_callbacks = {
         .find_elf = dwfl_build_id_find_elf,
 };
 
-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 offline image */
 static Dwarf *dwfl_init_offline_dwarf(int fd, Dwfl **dwflp, Dwarf_Addr *bias)
 {
@@ -185,6 +155,38 @@ error:
         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)
@@ -205,11 +207,34 @@ static Dwarf *dwfl_init_live_kernel_dwarf(Dwarf_Addr addr, Dwfl **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 */
 
@@ -627,8 +652,8 @@ static_var:
         regs = get_arch_regstr(regn);
         if (!regs) {
                 /* This should be a bug in DWARF or this tool */
-                pr_warning("Mapping for DWARF register number %u "
-                           "missing on this architecture.", regn);
+                pr_warning("Mapping for the register number %u "
+                           "missing on this architecture.\n", regn);
                 return -ERANGE;
         }
 
@@ -674,13 +699,14 @@ 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)
@@ -695,7 +721,7 @@ 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;
                 }
@@ -805,8 +831,8 @@ 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) {
@@ -953,7 +979,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
         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;
                 }
@@ -969,7 +995,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr,
         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;
                 }
                 tp->retprobe = true;
@@ -1008,7 +1034,7 @@ static int call_probe_finder(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;
                 }
@@ -1035,7 +1061,7 @@ static int find_probe_point_by_line(struct probe_finder *pf)
         int ret = 0;
 
         if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-                pr_warning("No source lines found in this CU.\n");
+                pr_warning("No source lines found.\n");
                 return -ENOENT;
         }
 
@@ -1137,7 +1163,7 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
         }
 
         if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) {
-                pr_warning("No source lines found in this CU.\n");
+                pr_warning("No source lines found.\n");
                 return -ENOENT;
         }
 
@@ -1195,7 +1221,7 @@ 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;
@@ -1236,8 +1262,8 @@ 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;
                         }
@@ -1279,7 +1305,7 @@ static int find_probes(int fd, struct probe_finder *pf)
 
         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");
                 return -EBADF;
         }
@@ -1524,7 +1550,7 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
         /* Open the live linux kernel */
         dbg = dwfl_init_live_kernel_dwarf(addr, &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");
                 ret = -EINVAL;
                 goto end;
@@ -1534,7 +1560,8 @@ int find_perf_probe_point(unsigned long addr, struct perf_probe_point *ppt)
         addr += bias;
         /* Find cu die */
         if (!dwarf_addrdie(dbg, (Dwarf_Addr)addr - bias, &cudie)) {
-                pr_warning("No CU DIE is found at %lx\n", addr);
+                pr_warning("Failed to find debug information for address %lx\n",
+                           addr);
                 ret = -EINVAL;
                 goto end;
         }
@@ -1659,7 +1686,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
         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");
+                pr_warning("No source lines found.\n");
                 return -ENOENT;
         }
 
@@ -1784,7 +1811,7 @@ int find_line_range(int fd, struct line_range *lr)
 
         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");
                 return -EBADF;
         }
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bba69d455699..beaefc3c1223 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -34,9 +34,9 @@ extern int find_available_vars_at(int fd, struct perf_probe_event *pev,
                                   bool externs);
 
 #include <dwarf.h>
-#include <libdw.h>
-#include <libdwfl.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 */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b059dc50cc2d..93680818e244 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>
  *
@@ -411,8 +411,8 @@ 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..c6d99334bdfa 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -442,8 +442,8 @@ 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..105f00bfd555 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -65,9 +65,49 @@ out_close:
         return -1;
 }
 
+static void perf_session__id_header_size(struct perf_session *session)
+{
+       struct sample_data *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__set_sample_id_all(struct perf_session *session, bool value)
+{
+        session->sample_id_all = value;
+        perf_session__id_header_size(session);
+}
+
+void perf_session__set_sample_type(struct perf_session *session, u64 type)
+{
+        session->sample_type = type;
+}
+
 void perf_session__update_sample_type(struct perf_session *self)
 {
         self->sample_type = perf_header__sample_type(&self->header);
+        self->sample_id_all = perf_header__sample_id_all(&self->header);
+        perf_session__id_header_size(self);
 }
 
 int perf_session__create_kernel_maps(struct perf_session *self)
@@ -85,7 +125,9 @@ 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);
@@ -101,10 +143,20 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
         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) {
@@ -120,6 +172,13 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
         }
 
         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:
@@ -230,7 +289,15 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self,
         return syms;
 }
 
+static int process_event_synth_stub(event_t *event __used,
+                                    struct perf_session *session __used)
+{
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
 static int process_event_stub(event_t *event __used,
+                              struct sample_data *sample __used,
                               struct perf_session *session __used)
 {
         dump_printf(": unhandled!\n");
@@ -262,7 +329,7 @@ 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 = event__process_lost;
         if (handler->read == NULL)
                 handler->read = process_event_stub;
         if (handler->throttle == NULL)
@@ -270,13 +337,13 @@ 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;
@@ -386,33 +453,61 @@ static event__swap_op event__swap_ops[] = {
 
 struct sample_queue {
         u64                     timestamp;
-        struct sample_event     *event;
+        u64                     file_offset;
+        event_t                 *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,
+                                      event_t *event,
+                                      struct sample_data *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 sample_data sample;
+        u64 limit = os->next_flush;
+        u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
 
         if (!ops->ordered_samples || !limit)
                 return;
 
         list_for_each_entry_safe(iter, tmp, head, list) {
                 if (iter->timestamp > limit)
-                        return;
+                        break;
 
-                if (iter == s->ordered_samples.last_inserted)
-                        s->ordered_samples.last_inserted = NULL;
+                event__parse_sample(iter->event, s, &sample);
+                perf_session_deliver_event(s, iter->event, &sample, ops,
+                                           iter->file_offset);
 
-                ops->sample((event_t *)iter->event, s);
-
-                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);
         }
 }
 
@@ -465,178 +560,267 @@ 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, event_t *event,
+                                    struct sample_data *data, u64 file_offset)
 {
+        struct ordered_samples *os = &s->ordered_samples;
+        struct list_head *sc = &os->sample_cache;
         u64 timestamp = data->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 sample_data *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,
+                                       event_t *event,
+                                       struct sample_data *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, event_t *event,
+                       u64 file_offset, struct sample_data *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, event__get_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, event_t *event,
+                        struct sample_data *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,
+                                      event_t *event,
+                                      struct sample_data *sample,
+                                      struct perf_event_ops *ops,
+                                      u64 file_offset)
+{
+        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);
+                return ops->sample(event, sample, 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,
+                                           event_t *event, struct sample_data *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, event_t *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,
+                                       event_t *event,
+                                       struct perf_event_ops *ops,
+                                       u64 file_offset)
+{
+        struct sample_data sample;
+        int ret;
+
+        if (session->header.needs_swap && event__swap_ops[event->header.type])
+                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
+         */
+        event__parse_sample(event, session, &sample);
+
+        /* 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 +840,33 @@ 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 (ret <= 0)
-                        return ret;
+        if (ops->lost == 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);
+        }
 
-                size -= ret;
-                buf += 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);
         }
 
-        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))
@@ -690,7 +886,7 @@ 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 +906,7 @@ 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 +919,8 @@ 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 +934,6 @@ 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 +942,91 @@ 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,
+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;
+        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];
         event_t *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)
+        if (session->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);
+        if (head + event->header.size > mmap_size) {
+                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 +1039,24 @@ 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;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9fa0fc2a863f..decd83f274fd 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 {
@@ -42,6 +46,8 @@ struct perf_session {
         int                     fd;
         bool                    fd_pipe;
         bool                    repipe;
+        bool                    sample_id_all;
+        u16                     id_hdr_size;
         int                     cwdlen;
         char                    *cwd;
         struct ordered_samples  ordered_samples;
@@ -50,7 +56,9 @@ struct perf_session {
 
 struct perf_event_ops;
 
-typedef int (*event_op)(event_t *self, struct perf_session *session);
+typedef int (*event_op)(event_t *self, struct sample_data *sample,
+                        struct perf_session *session);
+typedef int (*event_synth_op)(event_t *self, struct perf_session *session);
 typedef int (*event_op2)(event_t *self, struct perf_session *session,
                          struct perf_event_ops *ops);
 
@@ -63,16 +71,19 @@ struct perf_event_ops {
                         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);
@@ -98,8 +109,9 @@ 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__set_sample_id_all(struct perf_session *session, bool value);
+void perf_session__set_sample_type(struct perf_session *session, u64 type);
 void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
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/string.c b/tools/perf/util/string.c
index 0409fc7c0058..8fc0bd3a3a4a 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -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..fb737fe9be91 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");
 
@@ -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 b39f499e575a..7821d0e6866f 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"
@@ -22,6 +23,10 @@
 #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
@@ -41,6 +46,7 @@ struct symbol_conf symbol_conf = {
         .exclude_other    = true,
         .use_modules      = true,
         .try_vmlinux_path = true,
+        .symfs            = "",
 };
 
 int dso__name_len(const struct dso *self)
@@ -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;
         }
 
@@ -121,7 +127,7 @@ 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)
@@ -148,7 +154,7 @@ static struct symbol *symbol__new(u64 start, u64 len, u8 binding,
         self->binding = binding;
         self->namelen = namelen - 1;
 
-        pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
+        pr_debug4("%s: %s %#" PRIx64 "-%#" PRIx64 "\n", __func__, name, start, self->end);
 
         memcpy(self->name, name, namelen);
 
@@ -162,7 +168,7 @@ void symbol__delete(struct symbol *self)
 
 static size_t symbol__fprintf(struct symbol *self, FILE *fp)
 {
-        return fprintf(fp, " %llx-%llx %c %s\n",
+        return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n",
                        self->start, self->end,
                        self->binding == STB_GLOBAL ? 'g' :
                        self->binding == STB_LOCAL  ? 'l' : 'w',
@@ -295,7 +301,9 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 {
         struct rb_node **p = &self->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;
@@ -423,16 +431,25 @@ 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;
@@ -452,14 +469,33 @@ 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;
 
@@ -481,7 +517,7 @@ 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;
@@ -490,11 +526,8 @@ 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;
         /*
@@ -530,7 +563,7 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
         struct machine *machine = kmaps->machine;
         struct map *curr_map = map;
         struct symbol *pos;
-        int count = 0;
+        int count = 0, moved = 0;       
         struct rb_root *root = &self->symbols[map->type];
         struct rb_node *next = rb_first(root);
         int kernel_range = 0;
@@ -588,6 +621,11 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
                         char dso_name[PATH_MAX];
                         struct dso *dso;
 
+                        if (count == 0) {
+                                curr_map = map;
+                                goto filter_symbol;
+                        }
+
                         if (self->kernel == DSO_TYPE_GUEST_KERNEL)
                                 snprintf(dso_name, sizeof(dso_name),
                                         "[guest.kernel].%d",
@@ -613,7 +651,7 @@ 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);
@@ -621,8 +659,9 @@ 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;
                 }
         }
 
@@ -632,7 +671,7 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
                 dso__set_loaded(curr_map->dso, curr_map->type);
         }
 
-        return count;
+        return count + moved;
 }
 
 int dso__load_kallsyms(struct dso *self, const char *filename,
@@ -641,7 +680,6 @@ int dso__load_kallsyms(struct dso *self, const char *filename,
         if (dso__load_all_kallsyms(self, 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;
         else
@@ -831,8 +869,11 @@ 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, self->long_name);
+        fd = open(name, O_RDONLY);
         if (fd < 0)
                 goto out;
 
@@ -1121,6 +1162,13 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 
                 section_name = elf_sec__name(&shdr, secstrs);
 
+                /* On ARM, symbols for thumb functions have 1 added to
+                 * the symbol address as a flag - remove it */
+                if ((ehdr.e_machine == EM_ARM) &&
+                    (map->type == MAP__FUNCTION) &&
+                    (sym.st_value & 1))
+                        --sym.st_value;
+
                 if (self->kernel != DSO_TYPE_USER || kmodule) {
                         char dso_name[PATH_MAX];
 
@@ -1168,8 +1216,8 @@ 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;
@@ -1444,16 +1492,19 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
              self->origin++) {
                 switch (self->origin) {
                 case DSO__ORIG_BUILD_ID_CACHE:
-                        if (dso__build_id_filename(self, name, size) == NULL)
+                        /* skip the locally configured cache if a symfs is given */
+                        if (symbol_conf.symfs[0] ||
+                            (dso__build_id_filename(self, name, size) == NULL)) {
                                 continue;
+                        }
                         break;
                 case DSO__ORIG_FEDORA:
-                        snprintf(name, size, "/usr/lib/debug%s.debug",
-                                 self->long_name);
+                        snprintf(name, size, "%s/usr/lib/debug%s.debug",
+                                 symbol_conf.symfs, self->long_name);
                         break;
                 case DSO__ORIG_UBUNTU:
-                        snprintf(name, size, "/usr/lib/debug%s",
-                                 self->long_name);
+                        snprintf(name, size, "%s/usr/lib/debug%s",
+                                 symbol_conf.symfs, self->long_name);
                         break;
                 case DSO__ORIG_BUILDID: {
                         char build_id_hex[BUILD_ID_SIZE * 2 + 1];
@@ -1465,19 +1516,26 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
                                           sizeof(self->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);
+                        snprintf(name, size, "%s%s",
+                             symbol_conf.symfs, self->long_name);
                         break;
                 case DSO__ORIG_GUEST_KMODULE:
                         if (map->groups && map->groups->machine)
                                 root_dir = map->groups->machine->root_dir;
                         else
                                 root_dir = "";
-                        snprintf(name, size, "%s%s", root_dir, self->long_name);
+                        snprintf(name, size, "%s%s%s", symbol_conf.symfs,
+                                 root_dir, self->long_name);
+                        break;
+
+                case DSO__ORIG_KMODULE:
+                        snprintf(name, size, "%s%s", symbol_conf.symfs,
+                                 self->long_name);
                         break;
 
                 default:
@@ -1772,21 +1830,24 @@ 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 *self, 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);
+        err = dso__load_sym(self, 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;
 }
@@ -1828,8 +1889,8 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
         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
@@ -1842,6 +1903,11 @@ 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,
                                         symbol_conf.vmlinux_name, filter);
@@ -1859,6 +1925,10 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
                         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,
@@ -2123,14 +2193,55 @@ static struct dso *machine__create_kernel(struct machine *self)
         return 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 (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
+                return 0;
+
+        return args.start;
+}
+
 int __machine__create_kernel_maps(struct machine *self, struct dso *kernel)
 {
         enum map_type type;
+        u64 start = machine__get_kernel_start_addr(self);
 
         for (type = 0; type < MAP__NR_TYPES; ++type) {
                 struct kmap *kmap;
 
-                self->vmlinux_maps[type] = map__new2(0, kernel, type);
+                self->vmlinux_maps[type] = map__new2(start, kernel, type);
                 if (self->vmlinux_maps[type] == NULL)
                         return -1;
 
@@ -2208,9 +2319,6 @@ 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;
@@ -2223,6 +2331,14 @@ 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)
@@ -2282,6 +2398,8 @@ static int setup_list(struct strlist **list, const char *list_str,
 
 int symbol__init(void)
 {
+        const char *symfs;
+
         if (symbol_conf.initialized)
                 return 0;
 
@@ -2310,6 +2428,18 @@ 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.initialized = true;
         return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 038f2201ee09..670cd1c88f54 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -72,6 +72,7 @@ struct symbol_conf {
                         show_cpu_utilization,
                         initialized;
         const char      *vmlinux_name,
+                        *kallsyms_name,
                         *source_prefix,
                         *field_sep;
         const char      *default_guest_vmlinux_name,
@@ -85,6 +86,7 @@ struct symbol_conf {
        struct strlist   *dso_list,
                         *comm_list,
                         *sym_list;
+        const char      *symfs;
 };
 
 extern struct symbol_conf symbol_conf;
@@ -166,6 +168,8 @@ void dso__sort_by_name(struct dso *self, 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(struct dso *self, struct map *map,
+                      const char *vmlinux, symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *self, struct map *map,
                            symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *self, const char *filename, struct map *map,
@@ -213,7 +217,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 int build_id__sprintf(const u8 *self, int len, char *bf);
 int kallsyms__parse(const char *filename, void *arg,
                     int (*process_symbol)(void *arg, const char *name,
-                                          char type, u64 start));
+                                          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);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 8c72d888e449..00f4eade2e3e 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -16,35 +16,50 @@ static int filter(const struct dirent *dir)
                 return 1;
 }
 
-int find_all_tid(int pid, pid_t ** all_tid)
+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 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);
+                return NULL;
 
-        ret = items;
+        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;
+        }
 
-failure:
         for (i=0; i<items; i++)
                 free(namelist[i]);
         free(namelist);
 
-        return ret;
+        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);
 }
 
 static struct thread *thread__new(pid_t pid)
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 688500ff826f..d7574101054a 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -18,11 +18,24 @@ struct thread {
         int                     comm_len;
 };
 
+struct thread_map {
+        int nr;
+        int map[];
+};
+
 struct perf_session;
 
 void thread__delete(struct thread *self);
 
-int find_all_tid(int pid, pid_t ** all_tid);
+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);
+
+static inline void thread_map__delete(struct thread_map *threads)
+{
+        free(threads);
+}
+
 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/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.h b/tools/perf/util/trace-event.h
index b3e86b1e4444..b5f12ca24d99 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -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 {
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/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index ebda8c3fde9e..60c463c16028 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -350,7 +350,7 @@ 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;
 }
 
diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c
index e35437dfa5b4..e5158369106e 100644
--- a/tools/perf/util/ui/browsers/map.c
+++ b/tools/perf/util/ui/browsers/map.c
@@ -1,5 +1,6 @@
 #include "../libslang.h"
 #include <elf.h>
+#include <inttypes.h>
 #include <sys/ttydefaults.h>
 #include <ctype.h>
 #include <string.h>
@@ -57,7 +58,7 @@ static void map_browser__write(struct ui_browser *self, void *nd, int row)
         int width;
 
         ui_browser__set_percent_color(self, 0, current_entry);
-        slsmg_printf("%*llx %*llx %c ",
+        slsmg_printf("%*" PRIx64 " %*" PRIx64 " %c ",
                      mb->addrlen, sym->start, mb->addrlen, sym->end,
                      sym->binding == STB_GLOBAL ? 'g' :
                      sym->binding == STB_LOCAL  ? 'l' : 'w');
@@ -150,6 +151,6 @@ int map__browse(struct map *self)
                 ++mb.b.nr_entries;
         }
 
-        mb.addrlen = snprintf(tmp, sizeof(tmp), "%llx", maxaddr);
+        mb.addrlen = snprintf(tmp, sizeof(tmp), "%" PRIx64, maxaddr);
         return map_browser__run(&mb);
 }
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 9706d9d40279..7b5a8926624e 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -104,9 +104,24 @@ 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)
+                newtWinMessagev((char *)warning_str, (char *)ok,
+                                (char *)format, args);
+        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 7562707ddd1c..e833f26f3bfc 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -265,6 +265,7 @@ 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);
+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_ */