92 files changed, 6294 insertions, 1841 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index fe08660ce0bd..e1d60d780784 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -13,6 +13,8 @@ perf*.xml
 perf*.html
 common-cmds.h
 perf.data
+perf.data.old
+perf-archive
 tags
 TAGS
 cscope*
diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
new file mode 100644
index 000000000000..fae174dc7d01
--- /dev/null
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -0,0 +1,22 @@
+perf-archive(1)
+===============
+
+NAME
+----
+perf-archive - Create archive with object files with build-ids found in perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf archive' [file]
+
+DESCRIPTION
+-----------
+This command runs runs perf-buildid-list --with-hits, and collects the files
+with the buildids found so that analisys of perf.data contents can be possible
+on another machine.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-buildid-list[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
new file mode 100644
index 000000000000..88bc3b519746
--- /dev/null
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -0,0 +1,33 @@
+perf-buildid-cache(1)
+=====================
+
+NAME
+----
+perf-buildid-cache - Manage build-id cache.
+
+SYNOPSIS
+--------
+[verse]
+'perf buildid-list <options>'
+
+DESCRIPTION
+-----------
+This command manages the build-id cache. It can add and remove files to the
+cache. In the future it should as well purge older entries, set upper limits
+for the space used by the cache, etc.
+
+OPTIONS
+-------
+-a::
+--add=::
+        Add specified file to the cache.
+-r::
+--remove=::
+        Remove specified file to the cache.
+-v::
+--verbose::
+        Be more verbose.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
new file mode 100644
index 000000000000..b317102138c8
--- /dev/null
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -0,0 +1,29 @@
+perf-lock(1)
+============
+
+NAME
+----
+perf-lock - Analyze lock events
+
+SYNOPSIS
+--------
+[verse]
+'perf lock' {record|report|trace}
+
+DESCRIPTION
+-----------
+You can analyze various lock behaviours
+and statistics with this 'perf lock' command.
+
+  'perf lock record <command>' records lock events
+  between start and end <command>. And this command
+  produces the file "perf.data" which contains tracing
+  results of lock events.
+
+  'perf lock trace' shows raw lock events.
+
+  'perf lock report' reports statistical data.
+
+SEE ALSO
+--------
+linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 250e391b4bc8..34202b1be0bb 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -15,6 +15,8 @@ or
 'perf probe' [options] --del='[GROUP:]EVENT' [...]
 or
 'perf probe' --list
+or
+'perf probe' --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]'
 
 DESCRIPTION
 -----------
@@ -39,23 +41,89 @@ OPTIONS
 
 -d::
 --del=::
-        Delete a probe event.
+        Delete probe events. This accepts glob wildcards('*', '?') and character
+        classes(e.g. [a-z], [!A-Z]).
 
 -l::
 --list::
         List up current probe events.
 
+-L::
+--line=::
+        Show source code lines which can be probed. This needs an argument
+        which specifies a range of the source code. (see LINE SYNTAX for detail)
+
+-f::
+--force::
+        Forcibly add events with existing name.
+
 PROBE SYNTAX
 ------------
 Probe points are defined by following syntax.
 
- "[EVENT=]FUNC[+OFFS|:RLN|%return][@SRC]|SRC:ALN [ARG ...]"
+    1) Define event based on function name
+     [EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
+
+    2) Define event based on source file with line number
+     [EVENT=]SRC:ALN [ARG ...]
+
+    3) Define event based on source file with lazy pattern
+     [EVENT=]SRC;PTN [ARG ...]
+
 
 'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
-'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, 'RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. In addition, 'SRC' specifies a source file which has that function.
-It is also possible to specify a probe point by the source line number by using 'SRC:ALN' syntax, where 'SRC' is the source file path and 'ALN' is the line number.
+'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition.  In addition, '@SRC' specifies a source file which has that function.
+It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
 'ARG' specifies the arguments of this probe point. You can use the name of local variable, or kprobe-tracer argument format (e.g. $retval, %ax, etc).
 
+LINE SYNTAX
+-----------
+Line range is descripted by following syntax.
+
+ "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
+probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
+and 'ALN2' is end line number in the file. It is also possible to specify how
+many lines to show by using 'NUM'.
+So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
+
+LAZY MATCHING
+-------------
+ The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).
+
+e.g.
+ 'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.
+
+This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
+
+
+EXAMPLES
+--------
+Display which lines in schedule() can be probed:
+
+ ./perf probe --line schedule
+
+Add a probe on schedule() function 12th line with recording cpu local variable:
+
+ ./perf probe schedule:12 cpu
+ or
+ ./perf probe --add='schedule:12 cpu'
+
+ this will add one or more probes which has the name start with "schedule".
+
+ Add probes on lines in schedule() function which calls update_rq_clock().
+
+ ./perf probe 'schedule;update_rq_clock*'
+ or
+ ./perf probe --add='schedule;update_rq_clock*'
+
+Delete all probes on schedule().
+
+ ./perf probe --del='schedule*'
+
+
 SEE ALSO
 --------
 linkperf:perf-trace[1], linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 4a7d558dc309..785b9fc32a46 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -74,7 +74,7 @@ OPTIONS
 
 -s <symbol>::
 --sym-annotate=<symbol>::
-        Annotate this symbol.  Requires -k option.
+        Annotate this symbol.
 
 -v::
 --verbose::
diff --git a/tools/perf/Documentation/perf-trace-perl.txt b/tools/perf/Documentation/perf-trace-perl.txt
index c5f55f439091..d729cee8d987 100644
--- a/tools/perf/Documentation/perf-trace-perl.txt
+++ b/tools/perf/Documentation/perf-trace-perl.txt
@@ -8,7 +8,7 @@ perf-trace-perl - Process trace data with a Perl script
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [lang]:script[.ext] ]
+'perf trace' [-s [Perl]:script[.pl] ]
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/Documentation/perf-trace-python.txt b/tools/perf/Documentation/perf-trace-python.txt
new file mode 100644
index 000000000000..a241aca77184
--- /dev/null
+++ b/tools/perf/Documentation/perf-trace-python.txt
@@ -0,0 +1,625 @@
+perf-trace-python(1)
+==================
+
+NAME
+----
+perf-trace-python - Process trace data with a Python script
+
+SYNOPSIS
+--------
+[verse]
+'perf trace' [-s [Python]:script[.py] ]
+
+DESCRIPTION
+-----------
+
+This perf trace option is used to process perf trace 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.
+
+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
+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'
+scripts listed by that command.
+
+The syscall-counts script is a simple script, but demonstrates all the
+basic ideas necessary to create a useful script.  Here's an example
+of its output (syscall names are not yet supported, they will appear
+as numbers):
+
+----
+syscall events:
+
+event                                          count
+----------------------------------------  -----------
+sys_write                                     455067
+sys_getdents                                    4072
+sys_close                                       3037
+sys_swapoff                                     1769
+sys_read                                         923
+sys_sched_setparam                               826
+sys_open                                         331
+sys_newfstat                                     326
+sys_mmap                                         217
+sys_munmap                                       216
+sys_futex                                        141
+sys_select                                       102
+sys_poll                                          84
+sys_setitimer                                     12
+sys_writev                                         8
+15                                                 8
+sys_lseek                                          7
+sys_rt_sigprocmask                                 6
+sys_wait4                                          3
+sys_ioctl                                          3
+sys_set_robust_list                                1
+sys_exit                                           1
+56                                                 1
+sys_access                                         1
+----
+
+Basically our task is to keep a per-syscall tally that gets updated
+every time a system call occurs in the system.  Our script will do
+that, but first we need to record the data that will be processed by
+that script.  Theoretically, there are a couple of ways we could do
+that:
+
+- we could enable every event under the tracing/events/syscalls
+  directory, but this is over 600 syscalls, well beyond the number
+  allowable by perf.  These individual syscall events will however be
+  useful if we want to later use the guidance we get from the
+  general-purpose scripts to drill down and get more detail about
+  individual syscalls of interest.
+
+- we can enable the sys_enter and/or sys_exit syscalls found under
+  tracing/events/raw_syscalls.  These are called for all syscalls; the
+  'id' field can be used to distinguish between individual syscall
+  numbers.
+
+For this script, we only need to know that a syscall was entered; we
+don't care how it exited, so we'll use 'perf record' to record only
+the sys_enter events:
+
+----
+# perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+
+^C[ perf record: Woken up 1 times to write data ]
+[ perf record: Captured and wrote 56.545 MB perf.data (~2470503 samples) ]
+----
+
+The options basically say to collect data for every syscall event
+system-wide and multiplex the per-cpu output into a single stream.
+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
+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
+
+The output file created also in the current directory is named
+perf-trace.py.  Here's the file in its entirety:
+
+# perf trace event handlers, generated by perf trace -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.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+def trace_begin():
+        print "in trace_begin"
+
+def trace_end():
+        print "in trace_end"
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        id, args):
+                print_header(event_name, common_cpu, common_secs, common_nsecs,
+                        common_pid, common_comm)
+
+                print "id=%d, args=%s\n" % \
+                (id, args),
+
+def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
+                common_pid, common_comm):
+                print_header(event_name, common_cpu, common_secs, common_nsecs,
+                common_pid, common_comm)
+
+def print_header(event_name, cpu, secs, nsecs, pid, comm):
+        print "%-20s %5u %05u.%09u %8u %-20s " % \
+        (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.
+
+Following that are a couple generated functions, trace_begin() and
+trace_end(), which are called at the beginning and the end of the
+script respectively (for more details, see the SCRIPT_LAYOUT section
+below).
+
+Following those are the 'event handler' functions generated one for
+every event in the 'perf record' output.  The handler functions take
+the form subsystem__event_name, and contain named parameters, one for
+each field in the event; in this case, there's only one event,
+raw_syscalls__sys_enter().  (see the EVENT HANDLERS section below for
+more info on event handlers).
+
+The final couple of functions are, like the begin and end functions,
+generated for every script.  The first, trace_unhandled(), is called
+every time the script finds an event in the perf.data file that
+doesn't correspond to any event handler in the script.  This could
+mean either that the record step recorded event types that it wasn't
+really interested in, or the script was run against a trace file that
+doesn't correspond to the script.
+
+The script generated by -g option option simply prints a line for each
+event found in the trace stream i.e. it basically just dumps the event
+and its parameter values to stdout.  The print_header() function is
+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
+
+raw_syscalls__sys_enter     1 00840.847582083     7506 perf                  id=1, args=
+raw_syscalls__sys_enter     1 00840.847595764     7506 perf                  id=1, args=
+raw_syscalls__sys_enter     1 00840.847620860     7506 perf                  id=1, args=
+raw_syscalls__sys_enter     1 00840.847710478     6533 npviewer.bin          id=78, args=
+raw_syscalls__sys_enter     1 00840.847719204     6533 npviewer.bin          id=142, args=
+raw_syscalls__sys_enter     1 00840.847755445     6533 npviewer.bin          id=3, args=
+raw_syscalls__sys_enter     1 00840.847775601     6533 npviewer.bin          id=3, args=
+raw_syscalls__sys_enter     1 00840.847781820     6533 npviewer.bin          id=3, args=
+.
+.
+.
+----
+
+Of course, for this script, we're not interested in printing every
+trace event, but rather aggregating it in a useful way.  So we'll get
+rid of everything to do with printing as well as the trace_begin() and
+trace_unhandled() functions, which we won't be using.  That leaves us
+with this minimalistic skeleton:
+
+----
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+def trace_end():
+        print "in trace_end"
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        id, args):
+----
+
+In trace_end(), we'll simply print the results, but first we need to
+generate some results to print.  To do that we need to have our
+sys_enter() handler do the necessary tallying until all events have
+been counted.  A hash table indexed by syscall id is a good way to
+store that information; every time the sys_enter() handler is called,
+we simply increment a count associated with that hash entry indexed by
+that syscall id:
+
+----
+  syscalls = autodict()
+
+  try:
+    syscalls[id] += 1
+  except TypeError:
+    syscalls[id] = 1
+----
+
+The syscalls 'autodict' object is a special kind of Python dictionary
+(implemented in Core.py) that implements Perl's 'autovivifying' hashes
+in Python i.e. with autovivifying hashes, you can assign nested hash
+values without having to go to the trouble of creating intermediate
+levels if they don't exist e.g syscalls[comm][pid][id] = 1 will create
+the intermediate hash levels and finally assign the value 1 to the
+hash entry for 'id' (because the value being assigned isn't a hash
+object itself, the initial value is assigned in the TypeError
+exception.  Well, there may be a better way to do this in Python but
+that's what works for now).
+
+Putting that code into the raw_syscalls__sys_enter() handler, we
+effectively end up with a single-level dictionary keyed on syscall id
+and having the counts we've tallied as values.
+
+The print_syscall_totals() function iterates over the entries in the
+dictionary and displays a line for each entry containing the syscall
+name (the dictonary keys contain the syscall ids, which are passed to
+the Util function syscall_name(), which translates the raw syscall
+numbers to the corresponding syscall name strings).  The output is
+displayed after all the events in the trace have been processed, by
+calling the print_syscall_totals() function from the trace_end()
+handler called at the end of script processing.
+
+The final script producing the output shown above is shown in its
+entirety below (syscall_name() helper is not yet available, you can
+only deal with id's for now):
+
+----
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+syscalls = autodict()
+
+def trace_end():
+        print_syscall_totals()
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        id, args):
+        try:
+                syscalls[id] += 1
+        except TypeError:
+                syscalls[id] = 1
+
+def print_syscall_totals():
+    if for_comm is not None:
+            print "\nsyscall events for %s:\n\n" % (for_comm),
+    else:
+            print "\nsyscall events:\n\n",
+
+    print "%-40s  %10s\n" % ("event", "count"),
+    print "%-40s  %10s\n" % ("----------------------------------------", \
+                                 "-----------"),
+
+    for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
+                                  reverse = True):
+            print "%-40s  %10d\n" % (syscall_name(id), val),
+----
+
+The script can be run just as before:
+
+  # perf trace -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
+you're interested in - basically find the tracepoint(s) you're
+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
+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.:
+
+----
+root@tropicana:~# perf trace -l
+List of available trace scripts:
+  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
+  wakeup-latency                       system-wide min/max/avg wakeup latency
+  rw-by-file <comm>                    r/w activity for a program, by file
+  rw-by-pid                            system-wide r/w activity
+----
+
+A nice side effect of doing this is that you also then capture the
+probably lengthy 'perf record' command needed to record the events for
+the script.
+
+To have the script appear as a 'built-in' script, you write two simple
+scripts, one for recording and one for 'reporting'.
+
+The 'record' script is a shell script with the same base name as your
+script, but with -record appended.  The shell script should be put
+into the perf/scripts/python/bin directory in the kernel source tree.
+In that script, you write the 'perf record' command-line needed for
+your script:
+
+----
+# cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-record
+
+#!/bin/bash
+perf record -c 1 -f -a -M -R -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:
+
+----
+# 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
+----
+
+Note that the location of the Python script given in the shell script
+is in the libexec/perf-core/scripts/python directory - this is where
+the script will be copied by 'make install' when you install perf.
+For the installation to install your script there, your script needs
+to be located in the perf/scripts/python directory in the kernel
+source tree:
+
+----
+# ls -al kernel-source/tools/perf/scripts/python
+
+root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
+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 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'
+should show a new entry for your script:
+
+----
+root@tropicana:~# perf trace -l
+List of available trace scripts:
+  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
+  wakeup-latency                       system-wide min/max/avg wakeup latency
+  rw-by-file <comm>                    r/w activity for a program, by file
+  rw-by-pid                            system-wide r/w activity
+  syscall-counts                       system-wide syscall counts
+----
+
+You can now perform the record step via 'perf trace record':
+
+  # perf trace record syscall-counts
+
+and display the output using 'perf trace report':
+
+  # perf trace 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
+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
+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,
+attempts to exercise all of the main scripting features.
+
+EVENT HANDLERS
+--------------
+
+When perf trace 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
+next event is processed.
+
+Most of the event's field values are passed as arguments to the
+handler function; some of the less common ones aren't - those are
+available as calls back into the perf executable (see below).
+
+As an example, the following perf record command can be used to record
+all sched_wakeup events in the system:
+
+ # perf record -c 1 -f -a -M -R -e sched:sched_wakeup
+
+Traces meant to be processed using a script should be recorded with
+the above options: -c 1 says to sample every event, -a to enable
+system-wide collection, -M to multiplex the output, and -R to collect
+raw samples.
+
+The format file for the sched_wakep event defines the following fields
+(see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
+
+----
+ format:
+        field:unsigned short common_type;
+        field:unsigned char common_flags;
+        field:unsigned char common_preempt_count;
+        field:int common_pid;
+        field:int common_lock_depth;
+
+        field:char comm[TASK_COMM_LEN];
+        field:pid_t pid;
+        field:int prio;
+        field:int success;
+        field:int target_cpu;
+----
+
+The handler function for this event would be defined as:
+
+----
+def sched__sched_wakeup(event_name, context, common_cpu, common_secs,
+       common_nsecs, common_pid, common_comm,
+       comm, pid, prio, success, target_cpu):
+       pass
+----
+
+The handler function takes the form subsystem__event_name.
+
+The common_* arguments in the handler's argument list are the set of
+arguments passed to all event handlers; some of the fields correspond
+to the common_* fields in the format file, but some are synthesized,
+and some of the common_* fields aren't common enough to to be passed
+to every event as arguments but are available as library functions.
+
+Here's a brief description of each of the invariant event args:
+
+ event_name                 the name of the event as text
+ context                    an opaque 'cookie' used in calls back into perf
+ common_cpu                 the cpu the event occurred on
+ common_secs                the secs portion of the event timestamp
+ common_nsecs               the nsecs portion of the event timestamp
+ common_pid                 the pid of the current task
+ common_comm                the name of the current process
+
+All of the remaining fields in the event's format file have
+counterparts as handler function arguments of the same name, as can be
+seen in the example above.
+
+The above provides the basics needed to directly access every field of
+every event in a trace, which covers 90% of what you need to know to
+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
+module search path and 'import'ing a few support modules (see module
+descriptions below):
+
+----
+ import os
+ import sys
+
+ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+              '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+ from perf_trace_context import *
+ from Core import *
+----
+
+The rest of the script can contain handler functions and support
+functions in any order.
+
+Aside from the event handler functions discussed above, every script
+can implement a set of optional functions:
+
+*trace_begin*, if defined, is called before any event is processed and
+gives scripts a chance to do setup tasks:
+
+----
+def trace_begin:
+    pass
+----
+
+*trace_end*, if defined, is called after all events have been
+ processed and gives scripts a chance to do end-of-script tasks, such
+ as display results:
+
+----
+def trace_end:
+    pass
+----
+
+*trace_unhandled*, if defined, is called after for any event that
+ doesn't have a handler explicitly defined for it.  The standard set
+ of common arguments are passed into it:
+
+----
+def trace_unhandled(event_name, context, common_cpu, common_secs,
+        common_nsecs, common_pid, common_comm):
+    pass
+----
+
+The remaining sections provide descriptions of each of the available
+built-in perf trace 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
+variables from the given module, add the corresponding 'from XXXX
+import' line to your perf trace script.
+
+Core.py Module
+~~~~~~~~~~~~~~
+
+These functions provide some essential functions to user scripts.
+
+The *flag_str* and *symbol_str* functions provide human-readable
+strings for flag and symbolic fields.  These correspond to the strings
+and values parsed from the 'print fmt' fields of the event format
+files:
+
+  flag_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the flag field field_name of event event_name
+  symbol_str(event_name, field_name, field_value) - returns the string represention corresponding to field_value for the symbolic field field_name of event event_name
+
+The *autodict* function returns a special special kind of Python
+dictionary that implements Perl's 'autovivifying' hashes in Python
+i.e. with autovivifying hashes, you can assign nested hash values
+without having to go to the trouble of creating intermediate levels if
+they don't exist.
+
+  autodict() - returns an autovivifying dictionary instance
+
+
+perf_trace_context Module
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Some of the 'common' fields in the event format file aren't all that
+common, but need to be made accessible to user scripts nonetheless.
+
+perf_trace_context defines a set of functions that can be used to
+access this data in the context of the current event.  Each of these
+functions expects a context variable, which is the same as the
+context variable passed into every event handler as the second
+argument.
+
+ common_pc(context) - returns common_preempt count for the current event
+ common_flags(context) - returns common_flags for the current event
+ common_lock_depth(context) - returns common_lock_depth for the current event
+
+Util.py Module
+~~~~~~~~~~~~~~
+
+Various utility functions for use with perf trace:
+
+  nsecs(secs, nsecs) - returns total nsecs given secs/nsecs pair
+  nsecs_secs(nsecs) - returns whole secs portion given nsecs
+  nsecs_nsecs(nsecs) - returns nsecs remainder given nsecs
+  nsecs_str(nsecs) - returns printable string in the form secs.nsecs
+  avg(total, n) - returns average given a sum and a total number of values
+
+SEE ALSO
+--------
+linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 60e5900da483..8879299cd9df 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -19,6 +19,11 @@ 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
@@ -31,6 +36,9 @@ There are several variants 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::
@@ -45,9 +53,11 @@ OPTIONS
 --list=::
         Display a list of available trace scripts.
 
--s::
+-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=::
@@ -56,4 +66,5 @@ OPTIONS
 
 SEE ALSO
 --------
-linkperf:perf-record[1], linkperf:perf-trace-perl[1]
+linkperf:perf-record[1], linkperf:perf-trace-perl[1],
+linkperf:perf-trace-python[1]
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index 69c832557199..0eeb247dc7d2 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-Performance counters for Linux are are a new kernel-based subsystem
+Performance counters for Linux are a new kernel-based subsystem
 that provide a framework for all things performance analysis. It
 covers hardware level (CPU/PMU, Performance Monitoring Unit) features
 and software features (software counters, tracepoints) as well.
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 652a470b5f74..2d537382c686 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -250,7 +250,19 @@ PTHREAD_LIBS = -lpthread
 # explicitly what architecture to check for. Fix this up for yours..
 SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 
-ifeq ($(shell sh -c "echo 'int foo(void) {char X[2]; return 3;}' | $(CC) -x c -c -Werror -fstack-protector-all - -o /dev/null "$(QUIET_STDERR)" && echo y"), y)
+ifeq ($(V), 2)
+        QUIET_STDERR = ">/dev/null"
+else
+        QUIET_STDERR = ">/dev/null 2>&1"
+endif
+
+BITBUCKET = "/dev/null"
+
+ifneq ($(shell sh -c "(echo '\#include <stdio.h>'; echo 'int main(void) { return puts(\"hi\"); }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y)
+        BITBUCKET = .perf.dev.null
+endif
+
+ifeq ($(shell sh -c "echo 'int foo(void) {char X[2]; return 3;}' | $(CC) -x c -c -Werror -fstack-protector-all - -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y)
   CFLAGS := $(CFLAGS) -fstack-protector-all
 endif
 
@@ -274,11 +286,7 @@ SCRIPT_PERL =
 SCRIPT_SH =
 TEST_PROGRAMS =
 
-#
-# No scripts right now:
-#
-
-# SCRIPT_SH += perf-am.sh
+SCRIPT_SH += perf-archive.sh
 
 #
 # No Perl scripts right now:
@@ -303,9 +311,6 @@ PROGRAMS += perf
 # List built-in command $C whose implementation cmd_$C() is not in
 # builtin-$C.o but is linked in as part of some other command.
 #
-# None right now:
-#
-# BUILT_INS += perf-init $X
 
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
@@ -328,6 +333,7 @@ LIB_FILE=libperf.a
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
@@ -351,12 +357,14 @@ LIB_H += util/include/asm/uaccess.h
 LIB_H += perf.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
+LIB_H += util/build-id.h
 LIB_H += util/debug.h
 LIB_H += util/debugfs.h
 LIB_H += util/event.h
 LIB_H += util/exec_cmd.h
 LIB_H += util/types.h
 LIB_H += util/levenshtein.h
+LIB_H += util/map.h
 LIB_H += util/parse-options.h
 LIB_H += util/parse-events.h
 LIB_H += util/quote.h
@@ -377,12 +385,12 @@ LIB_H += util/sort.h
 LIB_H += util/hist.h
 LIB_H += util/thread.h
 LIB_H += util/trace-event.h
-LIB_H += util/trace-event-perl.h
 LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 
 LIB_OBJS += util/abspath.o
 LIB_OBJS += util/alias.o
+LIB_OBJS += util/build-id.o
 LIB_OBJS += util/config.o
 LIB_OBJS += util/ctype.o
 LIB_OBJS += util/debugfs.o
@@ -419,12 +427,12 @@ LIB_OBJS += util/thread.o
 LIB_OBJS += util/trace-event-parse.o
 LIB_OBJS += util/trace-event-read.o
 LIB_OBJS += util/trace-event-info.o
-LIB_OBJS += util/trace-event-perl.o
+LIB_OBJS += util/trace-event-scripting.o
 LIB_OBJS += util/svghelper.o
 LIB_OBJS += util/sort.o
 LIB_OBJS += util/hist.o
-LIB_OBJS += util/data_map.o
 LIB_OBJS += util/probe-event.o
+LIB_OBJS += util/util.o
 
 BUILTIN_OBJS += builtin-annotate.o
 
@@ -439,6 +447,7 @@ BUILTIN_OBJS += builtin-diff.o
 BUILTIN_OBJS += builtin-help.o
 BUILTIN_OBJS += builtin-sched.o
 BUILTIN_OBJS += builtin-buildid-list.o
+BUILTIN_OBJS += builtin-buildid-cache.o
 BUILTIN_OBJS += builtin-list.o
 BUILTIN_OBJS += builtin-record.o
 BUILTIN_OBJS += builtin-report.o
@@ -448,14 +457,10 @@ BUILTIN_OBJS += builtin-top.o
 BUILTIN_OBJS += builtin-trace.o
 BUILTIN_OBJS += builtin-probe.o
 BUILTIN_OBJS += builtin-kmem.o
+BUILTIN_OBJS += builtin-lock.o
 
 PERFLIBS = $(LIB_FILE)
 
-ifeq ($(V), 2)
-        QUIET_STDERR = ">/dev/null"
-else
-        QUIET_STDERR = ">/dev/null 2>&1"
-endif
 #
 # Platform specific tweaks
 #
@@ -483,24 +488,24 @@ ifeq ($(uname_S),Darwin)
         PTHREAD_LIBS =
 endif
 
-ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
         msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
 endif
 
-        ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+        ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
                 BASIC_CFLAGS += -DLIBELF_NO_MMAP
         endif
 else
         msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]);
 endif
 
-ifneq ($(shell sh -c "(echo '\#ifndef _MIPS_SZLONG'; echo '\#define _MIPS_SZLONG 0'; echo '\#endif'; echo '\#include <dwarf.h>'; echo '\#include <libdwarf.h>'; echo 'int main(void) { Dwarf_Debug dbg; Dwarf_Error err; Dwarf_Ranges *rng; dwarf_init(0, DW_DLC_READ, 0, 0, &dbg, &err); dwarf_get_ranges(dbg, 0, &rng, 0, 0, &err); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/libdwarf -ldwarf -lelf -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
-        msg := $(warning No libdwarf.h found or old libdwarf.h found, disables dwarf support. Please install libdwarf-dev/libdwarf-devel >= 20081231);
-        BASIC_CFLAGS += -DNO_LIBDWARF
+ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y)
+        msg := $(warning No libdw.h found or old libdw.h found, disables dwarf support. Please install elfutils-devel/elfutils-dev);
+        BASIC_CFLAGS += -DNO_DWARF_SUPPORT
 else
-        BASIC_CFLAGS += -I/usr/include/libdwarf
-        EXTLIBS += -lelf -ldwarf
+        BASIC_CFLAGS += -I/usr/include/elfutils
+        EXTLIBS += -lelf -ldw
         LIB_OBJS += util/probe-finder.o
 endif
 
@@ -509,30 +514,44 @@ PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null`
 PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
 endif
 
-ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o /dev/null $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
+ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o $(BITBUCKET) $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
         BASIC_CFLAGS += -DNO_LIBPERL
 else
         ALL_LDFLAGS += $(PERL_EMBED_LDOPTS)
+        LIB_OBJS += util/scripting-engines/trace-event-perl.o
         LIB_OBJS += scripts/perl/Perf-Trace-Util/Context.o
 endif
 
+ifndef NO_LIBPYTHON
+PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null`
+PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null`
+endif
+
+ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o /dev/null $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y)
+        BASIC_CFLAGS += -DNO_LIBPYTHON
+else
+        ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS)
+        LIB_OBJS += util/scripting-engines/trace-event-python.o
+        LIB_OBJS += scripts/python/Perf-Trace-Util/Context.o
+endif
+
 ifdef NO_DEMANGLE
         BASIC_CFLAGS += -DNO_DEMANGLE
 else
-        has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
+        has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
 
         ifeq ($(has_bfd),y)
                 EXTLIBS += -lbfd
         else
-                has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
+                has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
                 ifeq ($(has_bfd_iberty),y)
                         EXTLIBS += -lbfd -liberty
                 else
-                        has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
+                        has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
                         ifeq ($(has_bfd_iberty_z),y)
                                 EXTLIBS += -lbfd -liberty -lz
                         else
-                                has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
+                                has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
                                 ifeq ($(has_cplus_demangle),y)
                                         EXTLIBS += -liberty
                                         BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
@@ -780,7 +799,7 @@ export TAR INSTALL DESTDIR SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
-all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS
+all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) PERF-BUILD-OPTIONS
 ifneq (,$X)
         $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';)
 endif
@@ -887,12 +906,18 @@ util/hweight.o: ../../lib/hweight.c PERF-CFLAGS
 util/find_next_bit.o: ../../lib/find_next_bit.c PERF-CFLAGS
         $(QUIET_CC)$(CC) -o util/find_next_bit.o -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
-util/trace-event-perl.o: util/trace-event-perl.c PERF-CFLAGS
-        $(QUIET_CC)$(CC) -o util/trace-event-perl.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+util/scripting-engines/trace-event-perl.o: util/scripting-engines/trace-event-perl.c PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-perl.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
 
 scripts/perl/Perf-Trace-Util/Context.o: scripts/perl/Perf-Trace-Util/Context.c PERF-CFLAGS
         $(QUIET_CC)$(CC) -o scripts/perl/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
 
+util/scripting-engines/trace-event-python.o: util/scripting-engines/trace-event-python.c PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o util/scripting-engines/trace-event-python.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow $<
+
+scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o scripts/python/Perf-Trace-Util/Context.o -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $<
+
 perf-%$X: %.o $(PERFLIBS)
         $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
@@ -1002,9 +1027,16 @@ install: all
         $(INSTALL) perf$X '$(DESTDIR_SQ)$(bindir_SQ)'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
+        $(INSTALL) perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(INSTALL) scripts/perl/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
         $(INSTALL) scripts/perl/*.pl -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl'
         $(INSTALL) scripts/perl/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin'
+        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
+        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
+        $(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
+        $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
+        $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
+
 ifdef BUILT_INS
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -1107,6 +1139,11 @@ clean:
 .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS
 .PHONY: .FORCE-PERF-BUILD-OPTIONS
 
+.perf.dev.null:
+                touch .perf.dev.null
+
+.INTERMEDIATE:  .perf.dev.null
+
 ### Make sure built-ins do not have dups and listed in perf.c
 #
 check-builtins::
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 593ff25006de..5ec5de995872 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -53,32 +53,20 @@ struct sym_priv {
 
 static const char *sym_hist_filter;
 
-static int symbol_filter(struct map *map __used, struct symbol *sym)
+static int sym__alloc_hist(struct symbol *self)
 {
-        if (sym_hist_filter == NULL ||
-            strcmp(sym->name, sym_hist_filter) == 0) {
-                struct sym_priv *priv = symbol__priv(sym);
-                const int size = (sizeof(*priv->hist) +
-                                  (sym->end - sym->start) * sizeof(u64));
+        struct sym_priv *priv = symbol__priv(self);
+        const int size = (sizeof(*priv->hist) +
+                          (self->end - self->start) * sizeof(u64));
 
-                priv->hist = malloc(size);
-                if (priv->hist)
-                        memset(priv->hist, 0, size);
-                return 0;
-        }
-        /*
-         * FIXME: We should really filter it out, as we don't want to go thru symbols
-         * we're not interested, and if a DSO ends up with no symbols, delete it too,
-         * but right now the kernel loading routines in symbol.c bail out if no symbols
-         * are found, fix it later.
-         */
-        return 0;
+        priv->hist = zalloc(size);
+        return priv->hist == NULL ? -1 : 0;
 }
 
 /*
  * collect histogram counts
  */
-static void hist_hit(struct hist_entry *he, u64 ip)
+static int annotate__hist_hit(struct hist_entry *he, u64 ip)
 {
         unsigned int sym_size, offset;
         struct symbol *sym = he->sym;
@@ -88,83 +76,127 @@ static void hist_hit(struct hist_entry *he, u64 ip)
         he->count++;
 
         if (!sym || !he->map)
-                return;
+                return 0;
 
         priv = symbol__priv(sym);
-        if (!priv->hist)
-                return;
+        if (priv->hist == NULL && sym__alloc_hist(sym) < 0)
+                return -ENOMEM;
 
         sym_size = sym->end - sym->start;
         offset = ip - sym->start;
 
-        if (verbose)
-                fprintf(stderr, "%s: ip=%Lx\n", __func__,
-                        he->map->unmap_ip(he->map, ip));
+        pr_debug3("%s: ip=%#Lx\n", __func__, he->map->unmap_ip(he->map, ip));
 
         if (offset >= sym_size)
-                return;
+                return 0;
 
         h = priv->hist;
         h->sum++;
         h->ip[offset]++;
 
-        if (verbose >= 3)
-                printf("%p %s: count++ [ip: %p, %08Lx] => %Ld\n",
-                        (void *)(unsigned long)he->sym->start,
-                        he->sym->name,
-                        (void *)(unsigned long)ip, ip - he->sym->start,
-                        h->ip[offset]);
+        pr_debug3("%#Lx %s: count++ [ip: %#Lx, %#Lx] => %Ld\n", he->sym->start,
+                  he->sym->name, ip, ip - he->sym->start, h->ip[offset]);
+        return 0;
 }
 
 static int perf_session__add_hist_entry(struct perf_session *self,
                                         struct addr_location *al, u64 count)
 {
         bool hit;
-        struct hist_entry *he = __perf_session__add_hist_entry(self, al, NULL,
-                                                               count, &hit);
+        struct hist_entry *he;
+
+        if (sym_hist_filter != NULL &&
+            (al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
+                /* We're only interested in a symbol named sym_hist_filter */
+                if (al->sym != NULL) {
+                        rb_erase(&al->sym->rb_node,
+                                 &al->map->dso->symbols[al->map->type]);
+                        symbol__delete(al->sym);
+                }
+                return 0;
+        }
+
+        he = __perf_session__add_hist_entry(self, al, NULL, count, &hit);
         if (he == NULL)
                 return -ENOMEM;
-        hist_hit(he, al->addr);
-        return 0;
+
+        return annotate__hist_hit(he, al->addr);
 }
 
 static int process_sample_event(event_t *event, struct perf_session *session)
 {
         struct addr_location al;
 
-        dump_printf("(IP, %d): %d: %p\n", event->header.misc,
-                    event->ip.pid, (void *)(long)event->ip.ip);
+        dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
+                    event->ip.pid, event->ip.ip);
 
-        if (event__preprocess_sample(event, session, &al, symbol_filter) < 0) {
-                fprintf(stderr, "problem processing %d event, skipping it.\n",
-                        event->header.type);
+        if (event__preprocess_sample(event, session, &al, NULL) < 0) {
+                pr_warning("problem processing %d event, skipping it.\n",
+                           event->header.type);
                 return -1;
         }
 
         if (!al.filtered && perf_session__add_hist_entry(session, &al, 1)) {
-                fprintf(stderr, "problem incrementing symbol count, "
-                                "skipping event\n");
+                pr_warning("problem incrementing symbol count, "
+                           "skipping event\n");
                 return -1;
         }
 
         return 0;
 }
 
-static int parse_line(FILE *file, struct hist_entry *he, u64 len)
+struct objdump_line {
+        struct list_head node;
+        s64              offset;
+        char             *line;
+};
+
+static struct objdump_line *objdump_line__new(s64 offset, char *line)
+{
+        struct objdump_line *self = malloc(sizeof(*self));
+
+        if (self != NULL) {
+                self->offset = offset;
+                self->line = line;
+        }
+
+        return self;
+}
+
+static void objdump_line__free(struct objdump_line *self)
+{
+        free(self->line);
+        free(self);
+}
+
+static void objdump__add_line(struct list_head *head, struct objdump_line *line)
+{
+        list_add_tail(&line->node, head);
+}
+
+static struct objdump_line *objdump__get_next_ip_line(struct list_head *head,
+                                                      struct objdump_line *pos)
+{
+        list_for_each_entry_continue(pos, head, node)
+                if (pos->offset >= 0)
+                        return pos;
+
+        return NULL;
+}
+
+static int parse_line(FILE *file, struct hist_entry *he,
+                      struct list_head *head)
 {
         struct symbol *sym = he->sym;
+        struct objdump_line *objdump_line;
         char *line = NULL, *tmp, *tmp2;
-        static const char *prev_line;
-        static const char *prev_color;
-        unsigned int offset;
         size_t line_len;
-        u64 start;
-        s64 line_ip;
-        int ret;
+        s64 line_ip, offset = -1;
         char *c;
 
         if (getline(&line, &line_len, file) < 0)
                 return -1;
+
         if (!line)
                 return -1;
 
@@ -173,8 +205,6 @@ static int parse_line(FILE *file, struct hist_entry *he, u64 len)
                 *c = 0;
 
         line_ip = -1;
-        offset = 0;
-        ret = -2;
 
         /*
          * Strip leading spaces:
@@ -195,9 +225,30 @@ static int parse_line(FILE *file, struct hist_entry *he, u64 len)
                         line_ip = -1;
         }
 
-        start = he->map->unmap_ip(he->map, sym->start);
-
         if (line_ip != -1) {
+                u64 start = map__rip_2objdump(he->map, sym->start);
+                offset = line_ip - start;
+        }
+
+        objdump_line = objdump_line__new(offset, line);
+        if (objdump_line == NULL) {
+                free(line);
+                return -1;
+        }
+        objdump__add_line(head, objdump_line);
+
+        return 0;
+}
+
+static int objdump_line__print(struct objdump_line *self,
+                               struct list_head *head,
+                               struct hist_entry *he, u64 len)
+{
+        struct symbol *sym = he->sym;
+        static const char *prev_line;
+        static const char *prev_color;
+
+        if (self->offset != -1) {
                 const char *path = NULL;
                 unsigned int hits = 0;
                 double percent = 0.0;
@@ -205,15 +256,22 @@ static int parse_line(FILE *file, struct hist_entry *he, u64 len)
                 struct sym_priv *priv = symbol__priv(sym);
                 struct sym_ext *sym_ext = priv->ext;
                 struct sym_hist *h = priv->hist;
+                s64 offset = self->offset;
+                struct objdump_line *next = objdump__get_next_ip_line(head, self);
+
+                while (offset < (s64)len &&
+                       (next == NULL || offset < next->offset)) {
+                        if (sym_ext) {
+                                if (path == NULL)
+                                        path = sym_ext[offset].path;
+                                percent += sym_ext[offset].percent;
+                        } else
+                                hits += h->ip[offset];
+
+                        ++offset;
+                }
 
-                offset = line_ip - start;
-                if (offset < len)
-                        hits = h->ip[offset];
-
-                if (offset < len && sym_ext) {
-                        path = sym_ext[offset].path;
-                        percent = sym_ext[offset].percent;
-                } else if (h->sum)
+                if (sym_ext == NULL && h->sum)
                         percent = 100.0 * hits / h->sum;
 
                 color = get_percent_color(percent);
@@ -234,12 +292,12 @@ static int parse_line(FILE *file, struct hist_entry *he, u64 len)
 
                 color_fprintf(stdout, color, " %7.2f", percent);
                 printf(" :      ");
-                color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", line);
+                color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line);
         } else {
-                if (!*line)
+                if (!*self->line)
                         printf("         :\n");
                 else
-                        printf("         :      %s\n", line);
+                        printf("         :      %s\n", self->line);
         }
 
         return 0;
@@ -365,6 +423,20 @@ static void print_summary(const char *filename)
         }
 }
 
+static void hist_entry__print_hits(struct hist_entry *self)
+{
+        struct symbol *sym = self->sym;
+        struct sym_priv *priv = symbol__priv(sym);
+        struct sym_hist *h = priv->hist;
+        u64 len = sym->end - sym->start, offset;
+
+        for (offset = 0; offset < len; ++offset)
+                if (h->ip[offset] != 0)
+                        printf("%*Lx: %Lu\n", BITS_PER_LONG / 2,
+                               sym->start + offset, h->ip[offset]);
+        printf("%*s: %Lu\n", BITS_PER_LONG / 2, "h->sum", h->sum);
+}
+
 static void annotate_sym(struct hist_entry *he)
 {
         struct map *map = he->map;
@@ -374,15 +446,15 @@ static void annotate_sym(struct hist_entry *he)
         u64 len;
         char command[PATH_MAX*2];
         FILE *file;
+        LIST_HEAD(head);
+        struct objdump_line *pos, *n;
 
         if (!filename)
                 return;
 
-        if (verbose)
-                fprintf(stderr, "%s: filename=%s, sym=%s, start=%Lx, end=%Lx\n",
-                        __func__, filename, sym->name,
-                        map->unmap_ip(map, sym->start),
-                        map->unmap_ip(map, sym->end));
+        pr_debug("%s: filename=%s, sym=%s, start=%#Lx, end=%#Lx\n", __func__,
+                 filename, sym->name, map->unmap_ip(map, sym->start),
+                 map->unmap_ip(map, sym->end));
 
         if (full_paths)
                 d_filename = filename;
@@ -405,7 +477,8 @@ static void annotate_sym(struct hist_entry *he)
                        dso, dso->long_name, sym, sym->name);
 
         sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s",
-                map->unmap_ip(map, sym->start), map->unmap_ip(map, sym->end),
+                map__rip_2objdump(map, sym->start),
+                map__rip_2objdump(map, sym->end),
                 filename, filename);
 
         if (verbose >= 3)
@@ -416,11 +489,21 @@ static void annotate_sym(struct hist_entry *he)
                 return;
 
         while (!feof(file)) {
-                if (parse_line(file, he, len) < 0)
+                if (parse_line(file, he, &head) < 0)
                         break;
         }
 
         pclose(file);
+
+        if (verbose)
+                hist_entry__print_hits(he);
+
+        list_for_each_entry_safe(pos, n, &head, node) {
+                objdump_line__print(pos, &head, he, len);
+                list_del(&pos->node);
+                objdump_line__free(pos);
+        }
+
         if (print_line)
                 free_source_line(he, len);
 }
@@ -451,10 +534,10 @@ static void perf_session__find_annotations(struct perf_session *self)
 }
 
 static struct perf_event_ops event_ops = {
-        .process_sample_event   = process_sample_event,
-        .process_mmap_event     = event__process_mmap,
-        .process_comm_event     = event__process_comm,
-        .process_fork_event     = event__process_task,
+        .sample = process_sample_event,
+        .mmap   = event__process_mmap,
+        .comm   = event__process_comm,
+        .fork   = event__process_task,
 };
 
 static int __cmd_annotate(void)
@@ -542,9 +625,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used)
         setup_pager();
 
         if (field_sep && *field_sep == '.') {
-                fputs("'.' is the only non valid --field-separator argument\n",
-                                stderr);
-                exit(129);
+                pr_err("'.' is the only non valid --field-separator argument\n");
+                return -1;
         }
 
         return __cmd_annotate();
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
new file mode 100644
index 000000000000..30a05f552c96
--- /dev/null
+++ b/tools/perf/builtin-buildid-cache.c
@@ -0,0 +1,133 @@
+/*
+ * builtin-buildid-cache.c
+ *
+ * Builtin buildid-cache command: Manages build-id cache
+ *
+ * Copyright (C) 2010, Red Hat Inc.
+ * Copyright (C) 2010, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "builtin.h"
+#include "perf.h"
+#include "util/cache.h"
+#include "util/debug.h"
+#include "util/header.h"
+#include "util/parse-options.h"
+#include "util/strlist.h"
+#include "util/symbol.h"
+
+static char const *add_name_list_str, *remove_name_list_str;
+
+static const char * const buildid_cache_usage[] = {
+        "perf buildid-cache [<options>]",
+        NULL
+};
+
+static const struct option buildid_cache_options[] = {
+        OPT_STRING('a', "add", &add_name_list_str,
+                   "file list", "file(s) to add"),
+        OPT_STRING('r', "remove", &remove_name_list_str, "file list",
+                    "file(s) to remove"),
+        OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose"),
+        OPT_END()
+};
+
+static int build_id_cache__add_file(const char *filename, const char *debugdir)
+{
+        char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+        u8 build_id[BUILD_ID_SIZE];
+        int err;
+
+        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+                pr_debug("Couldn't read a build-id in %s\n", filename);
+                return -1;
+        }
+
+        build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+        err = build_id_cache__add_s(sbuild_id, debugdir, filename, false);
+        if (verbose)
+                pr_info("Adding %s %s: %s\n", sbuild_id, filename,
+                        err ? "FAIL" : "Ok");
+        return err;
+}
+
+static int build_id_cache__remove_file(const char *filename __used,
+                                       const char *debugdir __used)
+{
+        u8 build_id[BUILD_ID_SIZE];
+        char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+        int err;
+
+        if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) {
+                pr_debug("Couldn't read a build-id in %s\n", filename);
+                return -1;
+        }
+
+        build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+        err = build_id_cache__remove_s(sbuild_id, debugdir);
+        if (verbose)
+                pr_info("Removing %s %s: %s\n", sbuild_id, filename,
+                        err ? "FAIL" : "Ok");
+
+        return err;
+}
+
+static int __cmd_buildid_cache(void)
+{
+        struct strlist *list;
+        struct str_node *pos;
+        char debugdir[PATH_MAX];
+
+        snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
+                 DEBUG_CACHE_DIR);
+
+        if (add_name_list_str) {
+                list = strlist__new(true, add_name_list_str);
+                if (list) {
+                        strlist__for_each(pos, list)
+                                if (build_id_cache__add_file(pos->s, debugdir)) {
+                                        if (errno == EEXIST) {
+                                                pr_debug("%s already in the cache\n",
+                                                         pos->s);
+                                                continue;
+                                        }
+                                        pr_warning("Couldn't add %s: %s\n",
+                                                   pos->s, strerror(errno));
+                                }
+
+                        strlist__delete(list);
+                }
+        }
+
+        if (remove_name_list_str) {
+                list = strlist__new(true, remove_name_list_str);
+                if (list) {
+                        strlist__for_each(pos, list)
+                                if (build_id_cache__remove_file(pos->s, debugdir)) {
+                                        if (errno == ENOENT) {
+                                                pr_debug("%s wasn't in the cache\n",
+                                                         pos->s);
+                                                continue;
+                                        }
+                                        pr_warning("Couldn't remove %s: %s\n",
+                                                   pos->s, strerror(errno));
+                                }
+
+                        strlist__delete(list);
+                }
+        }
+
+        return 0;
+}
+
+int cmd_buildid_cache(int argc, const char **argv, const char *prefix __used)
+{
+        argc = parse_options(argc, argv, buildid_cache_options,
+                             buildid_cache_usage, 0);
+
+        if (symbol__init() < 0)
+                return -1;
+
+        setup_pager();
+        return __cmd_buildid_cache();
+}
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 1e99ac806913..d0675c02f81e 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -8,6 +8,7 @@
  */
 #include "builtin.h"
 #include "perf.h"
+#include "util/build-id.h"
 #include "util/cache.h"
 #include "util/debug.h"
 #include "util/parse-options.h"
@@ -16,6 +17,7 @@
 
 static char const *input_name = "perf.data";
 static int force;
+static bool with_hits;
 
 static const char * const buildid_list_usage[] = {
         "perf buildid-list [<options>]",
@@ -23,6 +25,7 @@ static const char * const buildid_list_usage[] = {
 };
 
 static const struct option options[] = {
+        OPT_BOOLEAN('H', "with-hits", &with_hits, "Show only DSOs with hits"),
         OPT_STRING('i', "input", &input_name, "file",
                     "input file name"),
         OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -31,26 +34,6 @@ static const struct option options[] = {
         OPT_END()
 };
 
-static int perf_file_section__process_buildids(struct perf_file_section *self,
-                                               int feat, int fd)
-{
-        if (feat != HEADER_BUILD_ID)
-                return 0;
-
-        if (lseek(fd, self->offset, SEEK_SET) < 0) {
-                pr_warning("Failed to lseek to %Ld offset for buildids!\n",
-                           self->offset);
-                return -1;
-        }
-
-        if (perf_header__read_build_ids(fd, self->offset, self->size)) {
-                pr_warning("Failed to read buildids!\n");
-                return -1;
-        }
-
-        return 0;
-}
-
 static int __cmd_buildid_list(void)
 {
         int err = -1;
@@ -60,10 +43,10 @@ static int __cmd_buildid_list(void)
         if (session == NULL)
                 return -1;
 
-        err = perf_header__process_sections(&session->header, session->fd,
-                                         perf_file_section__process_buildids);
-        if (err >= 0)
-                dsos__fprintf_buildid(stdout);
+        if (with_hits)
+                perf_session__process_events(session, &build_id__mark_dso_hit_ops);
+
+        dsos__fprintf_buildid(stdout, with_hits);
 
         perf_session__delete(session);
         return err;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index bd71b8ceafb7..18b3f505f9db 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -42,8 +42,8 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
         struct addr_location al;
         struct sample_data data = { .period = 1, };
 
-        dump_printf("(IP, %d): %d: %p\n", event->header.misc,
-                    event->ip.pid, (void *)(long)event->ip.ip);
+        dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc,
+                    event->ip.pid, event->ip.ip);
 
         if (event__preprocess_sample(event, session, &al, NULL) < 0) {
                 pr_warning("problem processing %d event, skipping it.\n",
@@ -51,12 +51,12 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
                 return -1;
         }
 
-        if (al.filtered)
+        if (al.filtered || al.sym == NULL)
                 return 0;
 
         event__parse_sample(event, session->sample_type, &data);
 
-        if (al.sym && perf_session__add_hist_entry(session, &al, data.period)) {
+        if (perf_session__add_hist_entry(session, &al, data.period)) {
                 pr_warning("problem incrementing symbol count, skipping event\n");
                 return -1;
         }
@@ -66,12 +66,12 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi
 }
 
 static struct perf_event_ops event_ops = {
-        .process_sample_event = diff__process_sample_event,
-        .process_mmap_event   = event__process_mmap,
-        .process_comm_event   = event__process_comm,
-        .process_exit_event   = event__process_task,
-        .process_fork_event   = event__process_task,
-        .process_lost_event   = event__process_lost,
+        .sample = diff__process_sample_event,
+        .mmap   = event__process_mmap,
+        .comm   = event__process_comm,
+        .exit   = event__process_task,
+        .fork   = event__process_task,
+        .lost   = event__process_lost,
 };
 
 static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
@@ -82,29 +82,19 @@ static void perf_session__insert_hist_entry_by_name(struct rb_root *root,
         struct hist_entry *iter;
 
         while (*p != NULL) {
-                int cmp;
                 parent = *p;
                 iter = rb_entry(parent, struct hist_entry, rb_node);
-
-                cmp = strcmp(he->map->dso->name, iter->map->dso->name);
-                if (cmp > 0)
+                if (hist_entry__cmp(he, iter) < 0)
                         p = &(*p)->rb_left;
-                else if (cmp < 0)
+                else
                         p = &(*p)->rb_right;
-                else {
-                        cmp = strcmp(he->sym->name, iter->sym->name);
-                        if (cmp > 0)
-                                p = &(*p)->rb_left;
-                        else
-                                p = &(*p)->rb_right;
-                }
         }
 
         rb_link_node(&he->rb_node, parent, p);
         rb_insert_color(&he->rb_node, root);
 }
 
-static void perf_session__resort_by_name(struct perf_session *self)
+static void perf_session__resort_hist_entries(struct perf_session *self)
 {
         unsigned long position = 1;
         struct rb_root tmp = RB_ROOT;
@@ -122,29 +112,28 @@ static void perf_session__resort_by_name(struct perf_session *self)
         self->hists = tmp;
 }
 
+static void perf_session__set_hist_entries_positions(struct perf_session *self)
+{
+        perf_session__output_resort(self, self->events_stats.total);
+        perf_session__resort_hist_entries(self);
+}
+
 static struct hist_entry *
-perf_session__find_hist_entry_by_name(struct perf_session *self,
-                                      struct hist_entry *he)
+perf_session__find_hist_entry(struct perf_session *self,
+                              struct hist_entry *he)
 {
         struct rb_node *n = self->hists.rb_node;
 
         while (n) {
                 struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
-                int cmp = strcmp(he->map->dso->name, iter->map->dso->name);
+                int64_t cmp = hist_entry__cmp(he, iter);
 
-                if (cmp > 0)
+                if (cmp < 0)
                         n = n->rb_left;
-                else if (cmp < 0)
+                else if (cmp > 0)
                         n = n->rb_right;
-                else {
-                        cmp = strcmp(he->sym->name, iter->sym->name);
-                        if (cmp > 0)
-                                n = n->rb_left;
-                        else if (cmp < 0)
-                                n = n->rb_right;
-                        else
-                                return iter;
-                }
+                else 
+                        return iter;
         }
 
         return NULL;
@@ -155,11 +144,9 @@ static void perf_session__match_hists(struct perf_session *old_session,
 {
         struct rb_node *nd;
 
-        perf_session__resort_by_name(old_session);
-
         for (nd = rb_first(&new_session->hists); nd; nd = rb_next(nd)) {
                 struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node);
-                pos->pair = perf_session__find_hist_entry_by_name(old_session, pos);
+                pos->pair = perf_session__find_hist_entry(old_session, pos);
         }
 }
 
@@ -177,9 +164,12 @@ static int __cmd_diff(void)
                 ret = perf_session__process_events(session[i], &event_ops);
                 if (ret)
                         goto out_delete;
-                perf_session__output_resort(session[i], session[i]->events_stats.total);
         }
 
+        perf_session__output_resort(session[1], session[1]->events_stats.total);
+        if (show_displacement)
+                perf_session__set_hist_entries_positions(session[0]);
+
         perf_session__match_hists(session[0], session[1]);
         perf_session__fprintf_hists(session[1], session[0],
                                     show_displacement, stdout);
@@ -204,7 +194,7 @@ static const struct option options[] = {
         OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
         OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
                     "load module symbols - WARNING: use only with -k and LIVE kernel"),
-        OPT_BOOLEAN('P', "full-paths", &event_ops.full_paths,
+        OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
                     "Don't shorten the pathnames taking into account the cwd"),
         OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
                    "only consider symbols in these dsos"),
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 9f810b17c25c..215b584007b1 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -286,8 +286,7 @@ void list_common_cmds_help(void)
 
         puts(" The most commonly used perf commands are:");
         for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
-                printf("   %s   ", common_cmds[i].name);
-                mput_char(' ', longest - strlen(common_cmds[i].name));
+                printf("   %-*s   ", longest, common_cmds[i].name);
                 puts(common_cmds[i].help);
         }
 }
@@ -314,8 +313,6 @@ static const char *cmd_to_page(const char *perf_cmd)
                 return "perf";
         else if (!prefixcmp(perf_cmd, "perf"))
                 return perf_cmd;
-        else if (is_perf_command(perf_cmd))
-                return prepend("perf-", perf_cmd);
         else
                 return prepend("perf-", perf_cmd);
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 7ceb7416c316..924a9518931a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -92,23 +92,18 @@ static void setup_cpunode_map(void)
         if (!dir1)
                 return;
 
-        while (true) {
-                dent1 = readdir(dir1);
-                if (!dent1)
-                        break;
-
-                if (sscanf(dent1->d_name, "node%u", &mem) < 1)
+        while ((dent1 = readdir(dir1)) != NULL) {
+                if (dent1->d_type != DT_DIR ||
+                    sscanf(dent1->d_name, "node%u", &mem) < 1)
                         continue;
 
                 snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
                 dir2 = opendir(buf);
                 if (!dir2)
                         continue;
-                while (true) {
-                        dent2 = readdir(dir2);
-                        if (!dent2)
-                                break;
-                        if (sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
+                while ((dent2 = readdir(dir2)) != NULL) {
+                        if (dent2->d_type != DT_LNK ||
+                            sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
                                 continue;
                         cpunode_map[cpu] = mem;
                 }
@@ -321,11 +316,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         event__parse_sample(event, session->sample_type, &data);
 
-        dump_printf("(IP, %d): %d/%d: %p period: %Ld\n",
-                event->header.misc,
-                data.pid, data.tid,
-                (void *)(long)data.ip,
-                (long long)data.period);
+        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) {
@@ -342,22 +334,9 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         return 0;
 }
 
-static int sample_type_check(struct perf_session *session)
-{
-        if (!(session->sample_type & PERF_SAMPLE_RAW)) {
-                fprintf(stderr,
-                        "No trace sample to read. Did you call perf record "
-                        "without -R?");
-                return -1;
-        }
-
-        return 0;
-}
-
 static struct perf_event_ops event_ops = {
-        .process_sample_event   = process_sample_event,
-        .process_comm_event     = event__process_comm,
-        .sample_type_check      = sample_type_check,
+        .sample = process_sample_event,
+        .comm   = event__process_comm,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -375,7 +354,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
 
         printf("%.102s\n", graph_dotted_line);
         printf(" %-34s |",  is_caller ? "Callsite": "Alloc Ptr");
-        printf(" Total_alloc/Per | Total_req/Per   | Hit   | Ping-pong | Frag\n");
+        printf(" Total_alloc/Per | Total_req/Per   | Hit      | Ping-pong | Frag\n");
         printf("%.102s\n", graph_dotted_line);
 
         next = rb_first(root);
@@ -390,7 +369,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
                 if (is_caller) {
                         addr = data->call_site;
                         if (!raw_ip)
-                                sym = map_groups__find_function(&session->kmaps, session, addr, NULL);
+                                sym = map_groups__find_function(&session->kmaps, addr, NULL);
                 } else
                         addr = data->ptr;
 
@@ -401,7 +380,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
                         snprintf(buf, sizeof(buf), "%#Lx", addr);
                 printf(" %-34s |", buf);
 
-                printf(" %9llu/%-5lu | %9llu/%-5lu | %6lu | %8lu | %6.3f%%\n",
+                printf(" %9llu/%-5lu | %9llu/%-5lu | %8lu | %8lu | %6.3f%%\n",
                        (unsigned long long)data->bytes_alloc,
                        (unsigned long)data->bytes_alloc / data->hit,
                        (unsigned long long)data->bytes_req,
@@ -504,11 +483,14 @@ static void sort_result(void)
 
 static int __cmd_kmem(void)
 {
-        int err;
+        int err = -EINVAL;
         struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0);
         if (session == NULL)
                 return -ENOMEM;
 
+        if (!perf_session__has_traces(session, "kmem record"))
+                goto out_delete;
+
         setup_pager();
         err = perf_session__process_events(session, &event_ops);
         if (err != 0)
@@ -784,7 +766,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __used)
                         setup_sorting(&alloc_sort, default_sort_order);
 
                 return __cmd_kmem();
-        }
+        } else
+                usage_with_options(kmem_usage, kmem_options);
 
         return 0;
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
new file mode 100644
index 000000000000..e12c844df1e2
--- /dev/null
+++ b/tools/perf/builtin-lock.c
@@ -0,0 +1,822 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/util.h"
+#include "util/cache.h"
+#include "util/symbol.h"
+#include "util/thread.h"
+#include "util/header.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+
+#include "util/debug.h"
+#include "util/session.h"
+
+#include <sys/types.h>
+#include <sys/prctl.h>
+#include <semaphore.h>
+#include <pthread.h>
+#include <math.h>
+#include <limits.h>
+
+#include <linux/list.h>
+#include <linux/hash.h>
+
+/* based on kernel/lockdep.c */
+#define LOCKHASH_BITS           12
+#define LOCKHASH_SIZE           (1UL << LOCKHASH_BITS)
+
+static struct list_head lockhash_table[LOCKHASH_SIZE];
+
+#define __lockhashfn(key)       hash_long((unsigned long)key, LOCKHASH_BITS)
+#define lockhashentry(key)      (lockhash_table + __lockhashfn((key)))
+
+#define LOCK_STATE_UNLOCKED     0              /* initial state */
+#define LOCK_STATE_LOCKED       1
+
+struct lock_stat {
+        struct list_head        hash_entry;
+        struct rb_node          rb;             /* used for sorting */
+
+        /*
+         * FIXME: raw_field_value() returns unsigned long long,
+         * so address of lockdep_map should be dealed as 64bit.
+         * Is there more better solution?
+         */
+        void                    *addr;          /* address of lockdep_map, used as ID */
+        char                    *name;          /* for strcpy(), we cannot use const */
+
+        int                     state;
+        u64                     prev_event_time; /* timestamp of previous event */
+
+        unsigned int            nr_acquired;
+        unsigned int            nr_acquire;
+        unsigned int            nr_contended;
+        unsigned int            nr_release;
+
+        /* these times are in nano sec. */
+        u64                     wait_time_total;
+        u64                     wait_time_min;
+        u64                     wait_time_max;
+};
+
+/* build simple key function one is bigger than two */
+#define SINGLE_KEY(member)                                              \
+        static int lock_stat_key_ ## member(struct lock_stat *one,      \
+                                         struct lock_stat *two)         \
+        {                                                               \
+                return one->member > two->member;                       \
+        }
+
+SINGLE_KEY(nr_acquired)
+SINGLE_KEY(nr_contended)
+SINGLE_KEY(wait_time_total)
+SINGLE_KEY(wait_time_min)
+SINGLE_KEY(wait_time_max)
+
+struct lock_key {
+        /*
+         * name: the value for specify by user
+         * this should be simpler than raw name of member
+         * e.g. nr_acquired -> acquired, wait_time_total -> wait_total
+         */
+        const char              *name;
+        int                     (*key)(struct lock_stat*, struct lock_stat*);
+};
+
+static const char               *sort_key = "acquired";
+
+static int                      (*compare)(struct lock_stat *, struct lock_stat *);
+
+static struct rb_root           result; /* place to store sorted data */
+
+#define DEF_KEY_LOCK(name, fn_suffix)   \
+        { #name, lock_stat_key_ ## fn_suffix }
+struct lock_key keys[] = {
+        DEF_KEY_LOCK(acquired, nr_acquired),
+        DEF_KEY_LOCK(contended, nr_contended),
+        DEF_KEY_LOCK(wait_total, wait_time_total),
+        DEF_KEY_LOCK(wait_min, wait_time_min),
+        DEF_KEY_LOCK(wait_max, wait_time_max),
+
+        /* extra comparisons much complicated should be here */
+
+        { NULL, NULL }
+};
+
+static void select_key(void)
+{
+        int i;
+
+        for (i = 0; keys[i].name; i++) {
+                if (!strcmp(keys[i].name, sort_key)) {
+                        compare = keys[i].key;
+                        return;
+                }
+        }
+
+        die("Unknown compare key:%s\n", sort_key);
+}
+
+static void insert_to_result(struct lock_stat *st,
+                             int (*bigger)(struct lock_stat *, struct lock_stat *))
+{
+        struct rb_node **rb = &result.rb_node;
+        struct rb_node *parent = NULL;
+        struct lock_stat *p;
+
+        while (*rb) {
+                p = container_of(*rb, struct lock_stat, rb);
+                parent = *rb;
+
+                if (bigger(st, p))
+                        rb = &(*rb)->rb_left;
+                else
+                        rb = &(*rb)->rb_right;
+        }
+
+        rb_link_node(&st->rb, parent, rb);
+        rb_insert_color(&st->rb, &result);
+}
+
+/* returns left most element of result, and erase it */
+static struct lock_stat *pop_from_result(void)
+{
+        struct rb_node *node = result.rb_node;
+
+        if (!node)
+                return NULL;
+
+        while (node->rb_left)
+                node = node->rb_left;
+
+        rb_erase(node, &result);
+        return container_of(node, struct lock_stat, rb);
+}
+
+static struct lock_stat *lock_stat_findnew(void *addr, const char *name)
+{
+        struct list_head *entry = lockhashentry(addr);
+        struct lock_stat *ret, *new;
+
+        list_for_each_entry(ret, entry, hash_entry) {
+                if (ret->addr == addr)
+                        return ret;
+        }
+
+        new = zalloc(sizeof(struct lock_stat));
+        if (!new)
+                goto alloc_failed;
+
+        new->addr = addr;
+        new->name = zalloc(sizeof(char) * strlen(name) + 1);
+        if (!new->name)
+                goto alloc_failed;
+        strcpy(new->name, name);
+
+        /* LOCK_STATE_UNLOCKED == 0 isn't guaranteed forever */
+        new->state = LOCK_STATE_UNLOCKED;
+        new->wait_time_min = ULLONG_MAX;
+
+        list_add(&new->hash_entry, entry);
+        return new;
+
+alloc_failed:
+        die("memory allocation failed\n");
+}
+
+static char                     const *input_name = "perf.data";
+
+static int                      profile_cpu = -1;
+
+struct raw_event_sample {
+        u32                     size;
+        char                    data[0];
+};
+
+struct trace_acquire_event {
+        void                    *addr;
+        const char              *name;
+};
+
+struct trace_acquired_event {
+        void                    *addr;
+        const char              *name;
+};
+
+struct trace_contended_event {
+        void                    *addr;
+        const char              *name;
+};
+
+struct trace_release_event {
+        void                    *addr;
+        const char              *name;
+};
+
+struct trace_lock_handler {
+        void (*acquire_event)(struct trace_acquire_event *,
+                              struct event *,
+                              int cpu,
+                              u64 timestamp,
+                              struct thread *thread);
+
+        void (*acquired_event)(struct trace_acquired_event *,
+                               struct event *,
+                               int cpu,
+                               u64 timestamp,
+                               struct thread *thread);
+
+        void (*contended_event)(struct trace_contended_event *,
+                                struct event *,
+                                int cpu,
+                                u64 timestamp,
+                                struct thread *thread);
+
+        void (*release_event)(struct trace_release_event *,
+                              struct event *,
+                              int cpu,
+                              u64 timestamp,
+                              struct thread *thread);
+};
+
+static void
+report_lock_acquire_event(struct trace_acquire_event *acquire_event,
+                        struct event *__event __used,
+                        int cpu __used,
+                        u64 timestamp,
+                        struct thread *thread __used)
+{
+        struct lock_stat *st;
+
+        st = lock_stat_findnew(acquire_event->addr, acquire_event->name);
+
+        switch (st->state) {
+        case LOCK_STATE_UNLOCKED:
+                break;
+        case LOCK_STATE_LOCKED:
+                break;
+        default:
+                BUG_ON(1);
+                break;
+        }
+
+        st->prev_event_time = timestamp;
+}
+
+static void
+report_lock_acquired_event(struct trace_acquired_event *acquired_event,
+                         struct event *__event __used,
+                         int cpu __used,
+                         u64 timestamp,
+                         struct thread *thread __used)
+{
+        struct lock_stat *st;
+
+        st = lock_stat_findnew(acquired_event->addr, acquired_event->name);
+
+        switch (st->state) {
+        case LOCK_STATE_UNLOCKED:
+                st->state = LOCK_STATE_LOCKED;
+                st->nr_acquired++;
+                break;
+        case LOCK_STATE_LOCKED:
+                break;
+        default:
+                BUG_ON(1);
+                break;
+        }
+
+        st->prev_event_time = timestamp;
+}
+
+static void
+report_lock_contended_event(struct trace_contended_event *contended_event,
+                          struct event *__event __used,
+                          int cpu __used,
+                          u64 timestamp,
+                          struct thread *thread __used)
+{
+        struct lock_stat *st;
+
+        st = lock_stat_findnew(contended_event->addr, contended_event->name);
+
+        switch (st->state) {
+        case LOCK_STATE_UNLOCKED:
+                break;
+        case LOCK_STATE_LOCKED:
+                st->nr_contended++;
+                break;
+        default:
+                BUG_ON(1);
+                break;
+        }
+
+        st->prev_event_time = timestamp;
+}
+
+static void
+report_lock_release_event(struct trace_release_event *release_event,
+                        struct event *__event __used,
+                        int cpu __used,
+                        u64 timestamp,
+                        struct thread *thread __used)
+{
+        struct lock_stat *st;
+        u64 hold_time;
+
+        st = lock_stat_findnew(release_event->addr, release_event->name);
+
+        switch (st->state) {
+        case LOCK_STATE_UNLOCKED:
+                break;
+        case LOCK_STATE_LOCKED:
+                st->state = LOCK_STATE_UNLOCKED;
+                hold_time = timestamp - st->prev_event_time;
+
+                if (timestamp < st->prev_event_time) {
+                        /* terribly, this can happen... */
+                        goto end;
+                }
+
+                if (st->wait_time_min > hold_time)
+                        st->wait_time_min = hold_time;
+                if (st->wait_time_max < hold_time)
+                        st->wait_time_max = hold_time;
+                st->wait_time_total += hold_time;
+
+                st->nr_release++;
+                break;
+        default:
+                BUG_ON(1);
+                break;
+        }
+
+end:
+        st->prev_event_time = timestamp;
+}
+
+/* lock oriented handlers */
+/* TODO: handlers for CPU oriented, thread oriented */
+static struct trace_lock_handler report_lock_ops  = {
+        .acquire_event          = report_lock_acquire_event,
+        .acquired_event         = report_lock_acquired_event,
+        .contended_event        = report_lock_contended_event,
+        .release_event          = report_lock_release_event,
+};
+
+static struct trace_lock_handler *trace_handler;
+
+static void
+process_lock_acquire_event(void *data,
+                           struct event *event __used,
+                           int cpu __used,
+                           u64 timestamp __used,
+                           struct thread *thread __used)
+{
+        struct trace_acquire_event acquire_event;
+        u64 tmp;                /* this is required for casting... */
+
+        tmp = raw_field_value(event, "lockdep_addr", data);
+        memcpy(&acquire_event.addr, &tmp, sizeof(void *));
+        acquire_event.name = (char *)raw_field_ptr(event, "name", data);
+
+        if (trace_handler->acquire_event)
+                trace_handler->acquire_event(&acquire_event, event, cpu, timestamp, thread);
+}
+
+static void
+process_lock_acquired_event(void *data,
+                            struct event *event __used,
+                            int cpu __used,
+                            u64 timestamp __used,
+                            struct thread *thread __used)
+{
+        struct trace_acquired_event acquired_event;
+        u64 tmp;                /* this is required for casting... */
+
+        tmp = raw_field_value(event, "lockdep_addr", data);
+        memcpy(&acquired_event.addr, &tmp, sizeof(void *));
+        acquired_event.name = (char *)raw_field_ptr(event, "name", data);
+
+        if (trace_handler->acquire_event)
+                trace_handler->acquired_event(&acquired_event, event, cpu, timestamp, thread);
+}
+
+static void
+process_lock_contended_event(void *data,
+                             struct event *event __used,
+                             int cpu __used,
+                             u64 timestamp __used,
+                             struct thread *thread __used)
+{
+        struct trace_contended_event contended_event;
+        u64 tmp;                /* this is required for casting... */
+
+        tmp = raw_field_value(event, "lockdep_addr", data);
+        memcpy(&contended_event.addr, &tmp, sizeof(void *));
+        contended_event.name = (char *)raw_field_ptr(event, "name", data);
+
+        if (trace_handler->acquire_event)
+                trace_handler->contended_event(&contended_event, event, cpu, timestamp, thread);
+}
+
+static void
+process_lock_release_event(void *data,
+                           struct event *event __used,
+                           int cpu __used,
+                           u64 timestamp __used,
+                           struct thread *thread __used)
+{
+        struct trace_release_event release_event;
+        u64 tmp;                /* this is required for casting... */
+
+        tmp = raw_field_value(event, "lockdep_addr", data);
+        memcpy(&release_event.addr, &tmp, sizeof(void *));
+        release_event.name = (char *)raw_field_ptr(event, "name", data);
+
+        if (trace_handler->acquire_event)
+                trace_handler->release_event(&release_event, event, cpu, timestamp, thread);
+}
+
+static void
+process_raw_event(void *data, int cpu,
+                  u64 timestamp, struct thread *thread)
+{
+        struct event *event;
+        int type;
+
+        type = trace_parse_common_type(data);
+        event = trace_find_event(type);
+
+        if (!strcmp(event->name, "lock_acquire"))
+                process_lock_acquire_event(data, event, cpu, timestamp, thread);
+        if (!strcmp(event->name, "lock_acquired"))
+                process_lock_acquired_event(data, event, cpu, timestamp, thread);
+        if (!strcmp(event->name, "lock_contended"))
+                process_lock_contended_event(data, event, cpu, timestamp, thread);
+        if (!strcmp(event->name, "lock_release"))
+                process_lock_release_event(data, event, cpu, timestamp, thread);
+}
+
+struct raw_event_queue {
+        u64                     timestamp;
+        int                     cpu;
+        void                    *data;
+        struct thread           *thread;
+        struct list_head        list;
+};
+
+static LIST_HEAD(raw_event_head);
+
+#define FLUSH_PERIOD    (5 * NSEC_PER_SEC)
+
+static u64 flush_limit = ULLONG_MAX;
+static u64 last_flush = 0;
+struct raw_event_queue *last_inserted;
+
+static void flush_raw_event_queue(u64 limit)
+{
+        struct raw_event_queue *tmp, *iter;
+
+        list_for_each_entry_safe(iter, tmp, &raw_event_head, list) {
+                if (iter->timestamp > limit)
+                        return;
+
+                if (iter == last_inserted)
+                        last_inserted = NULL;
+
+                process_raw_event(iter->data, iter->cpu, iter->timestamp,
+                                  iter->thread);
+
+                last_flush = iter->timestamp;
+                list_del(&iter->list);
+                free(iter->data);
+                free(iter);
+        }
+}
+
+static void __queue_raw_event_end(struct raw_event_queue *new)
+{
+        struct raw_event_queue *iter;
+
+        list_for_each_entry_reverse(iter, &raw_event_head, list) {
+                if (iter->timestamp < new->timestamp) {
+                        list_add(&new->list, &iter->list);
+                        return;
+                }
+        }
+
+        list_add(&new->list, &raw_event_head);
+}
+
+static void __queue_raw_event_before(struct raw_event_queue *new,
+                                     struct raw_event_queue *iter)
+{
+        list_for_each_entry_continue_reverse(iter, &raw_event_head, list) {
+                if (iter->timestamp < new->timestamp) {
+                        list_add(&new->list, &iter->list);
+                        return;
+                }
+        }
+
+        list_add(&new->list, &raw_event_head);
+}
+
+static void __queue_raw_event_after(struct raw_event_queue *new,
+                                     struct raw_event_queue *iter)
+{
+        list_for_each_entry_continue(iter, &raw_event_head, list) {
+                if (iter->timestamp > new->timestamp) {
+                        list_add_tail(&new->list, &iter->list);
+                        return;
+                }
+        }
+        list_add_tail(&new->list, &raw_event_head);
+}
+
+/* The queue is ordered by time */
+static void __queue_raw_event(struct raw_event_queue *new)
+{
+        if (!last_inserted) {
+                __queue_raw_event_end(new);
+                return;
+        }
+
+        /*
+         * Most of the time the current event has a timestamp
+         * very close to the last event inserted, unless we just switched
+         * to another event buffer. Having a sorting based on a list and
+         * on the last inserted event that is close to the current one is
+         * probably more efficient than an rbtree based sorting.
+         */
+        if (last_inserted->timestamp >= new->timestamp)
+                __queue_raw_event_before(new, last_inserted);
+        else
+                __queue_raw_event_after(new, last_inserted);
+}
+
+static void queue_raw_event(void *data, int raw_size, int cpu,
+                            u64 timestamp, struct thread *thread)
+{
+        struct raw_event_queue *new;
+
+        if (flush_limit == ULLONG_MAX)
+                flush_limit = timestamp + FLUSH_PERIOD;
+
+        if (timestamp < last_flush) {
+                printf("Warning: Timestamp below last timeslice flush\n");
+                return;
+        }
+
+        new = malloc(sizeof(*new));
+        if (!new)
+                die("Not enough memory\n");
+
+        new->timestamp = timestamp;
+        new->cpu = cpu;
+        new->thread = thread;
+
+        new->data = malloc(raw_size);
+        if (!new->data)
+                die("Not enough memory\n");
+
+        memcpy(new->data, data, raw_size);
+
+        __queue_raw_event(new);
+        last_inserted = new;
+
+        /*
+         * We want to have a slice of events covering 2 * FLUSH_PERIOD
+         * If FLUSH_PERIOD is big enough, it ensures every events that occured
+         * in the first half of the timeslice have all been buffered and there
+         * are none remaining (we need that because of the weakly ordered
+         * event recording we have). Then once we reach the 2 * FLUSH_PERIOD
+         * timeslice, we flush the first half to be gentle with the memory
+         * (the second half can still get new events in the middle, so wait
+         * another period to flush it)
+         */
+        if (new->timestamp > flush_limit &&
+                new->timestamp - flush_limit > FLUSH_PERIOD) {
+                flush_limit += FLUSH_PERIOD;
+                flush_raw_event_queue(flush_limit);
+        }
+}
+
+static int process_sample_event(event_t *event, struct perf_session *session)
+{
+        struct thread *thread;
+        struct sample_data data;
+
+        bzero(&data, sizeof(struct sample_data));
+        event__parse_sample(event, session->sample_type, &data);
+        thread = perf_session__findnew(session, data.pid);
+
+        if (thread == NULL) {
+                pr_debug("problem processing %d event, skipping it.\n",
+                         event->header.type);
+                return -1;
+        }
+
+        dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+
+        if (profile_cpu != -1 && profile_cpu != (int) data.cpu)
+                return 0;
+
+        queue_raw_event(data.raw_data, data.raw_size, data.cpu, data.time, thread);
+
+        return 0;
+}
+
+/* TODO: various way to print, coloring, nano or milli sec */
+static void print_result(void)
+{
+        struct lock_stat *st;
+        char cut_name[20];
+
+        printf("%18s ", "ID");
+        printf("%20s ", "Name");
+        printf("%10s ", "acquired");
+        printf("%10s ", "contended");
+
+        printf("%15s ", "total wait (ns)");
+        printf("%15s ", "max wait (ns)");
+        printf("%15s ", "min wait (ns)");
+
+        printf("\n\n");
+
+        while ((st = pop_from_result())) {
+                bzero(cut_name, 20);
+
+                printf("%p ", st->addr);
+
+                if (strlen(st->name) < 16) {
+                        /* output raw name */
+                        printf("%20s ", st->name);
+                } else {
+                        strncpy(cut_name, st->name, 16);
+                        cut_name[16] = '.';
+                        cut_name[17] = '.';
+                        cut_name[18] = '.';
+                        cut_name[19] = '\0';
+                        /* cut off name for saving output style */
+                        printf("%20s ", cut_name);
+                }
+
+                printf("%10u ", st->nr_acquired);
+                printf("%10u ", st->nr_contended);
+
+                printf("%15llu ", st->wait_time_total);
+                printf("%15llu ", st->wait_time_max);
+                printf("%15llu ", st->wait_time_min == ULLONG_MAX ?
+                       0 : st->wait_time_min);
+                printf("\n");
+        }
+}
+
+static void dump_map(void)
+{
+        unsigned int i;
+        struct lock_stat *st;
+
+        for (i = 0; i < LOCKHASH_SIZE; i++) {
+                list_for_each_entry(st, &lockhash_table[i], hash_entry) {
+                        printf("%p: %s\n", st->addr, st->name);
+                }
+        }
+}
+
+static struct perf_event_ops eops = {
+        .sample                 = process_sample_event,
+        .comm                   = event__process_comm,
+};
+
+static struct perf_session *session;
+
+static int read_events(void)
+{
+        session = perf_session__new(input_name, O_RDONLY, 0);
+        if (!session)
+                die("Initializing perf session failed\n");
+
+        return perf_session__process_events(session, &eops);
+}
+
+static void sort_result(void)
+{
+        unsigned int i;
+        struct lock_stat *st;
+
+        for (i = 0; i < LOCKHASH_SIZE; i++) {
+                list_for_each_entry(st, &lockhash_table[i], hash_entry) {
+                        insert_to_result(st, compare);
+                }
+        }
+}
+
+static void __cmd_report(void)
+{
+        setup_pager();
+        select_key();
+        read_events();
+        flush_raw_event_queue(ULLONG_MAX);
+        sort_result();
+        print_result();
+}
+
+static const char * const report_usage[] = {
+        "perf lock report [<options>]",
+        NULL
+};
+
+static const struct option report_options[] = {
+        OPT_STRING('k', "key", &sort_key, "acquired",
+                    "key for sorting"),
+        /* TODO: type */
+        OPT_END()
+};
+
+static const char * const lock_usage[] = {
+        "perf lock [<options>] {record|trace|report}",
+        NULL
+};
+
+static const struct option lock_options[] = {
+        OPT_STRING('i', "input", &input_name, "file", "input file name"),
+        OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
+        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
+        OPT_END()
+};
+
+static const char *record_args[] = {
+        "record",
+        "-a",
+        "-R",
+        "-f",
+        "-m", "1024",
+        "-c", "1",
+        "-e", "lock:lock_acquire:r",
+        "-e", "lock:lock_acquired:r",
+        "-e", "lock:lock_contended:r",
+        "-e", "lock:lock_release:r",
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+        unsigned int rec_argc, i, j;
+        const char **rec_argv;
+
+        rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+        rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+        for (i = 0; i < ARRAY_SIZE(record_args); i++)
+                rec_argv[i] = strdup(record_args[i]);
+
+        for (j = 1; j < (unsigned int)argc; j++, i++)
+                rec_argv[i] = argv[j];
+
+        BUG_ON(i != rec_argc);
+
+        return cmd_record(i, rec_argv, NULL);
+}
+
+int cmd_lock(int argc, const char **argv, const char *prefix __used)
+{
+        unsigned int i;
+
+        symbol__init();
+        for (i = 0; i < LOCKHASH_SIZE; i++)
+                INIT_LIST_HEAD(lockhash_table + i);
+
+        argc = parse_options(argc, argv, lock_options, lock_usage,
+                             PARSE_OPT_STOP_AT_NON_OPTION);
+        if (!argc)
+                usage_with_options(lock_usage, lock_options);
+
+        if (!strncmp(argv[0], "rec", 3)) {
+                return __cmd_record(argc, argv);
+        } else if (!strncmp(argv[0], "report", 6)) {
+                trace_handler = &report_lock_ops;
+                if (argc) {
+                        argc = parse_options(argc, argv,
+                                             report_options, report_usage, 0);
+                        if (argc)
+                                usage_with_options(report_usage, report_options);
+                }
+                __cmd_report();
+        } else if (!strcmp(argv[0], "trace")) {
+                /* Aliased to 'perf trace' */
+                return cmd_trace(argc, argv, prefix);
+        } else if (!strcmp(argv[0], "map")) {
+                /* recycling report_lock_ops */
+                trace_handler = &report_lock_ops;
+                setup_pager();
+                read_events();
+                dump_map();
+        } else {
+                usage_with_options(lock_usage, lock_options);
+        }
+
+        return 0;
+}
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c1e6774fd3ed..c30a33592340 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -41,7 +41,6 @@
 #include "util/debugfs.h"
 #include "util/symbol.h"
 #include "util/thread.h"
-#include "util/session.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"  /* For debugfs_path */
 #include "util/probe-finder.h"
@@ -55,11 +54,13 @@ static struct {
         bool need_dwarf;
         bool list_events;
         bool force_add;
+        bool show_lines;
         int nr_probe;
         struct probe_point probes[MAX_PROBES];
         struct strlist *dellist;
-        struct perf_session *psession;
-        struct map *kmap;
+        struct map_groups kmap_groups;
+        struct map *kmaps[MAP__NR_TYPES];
+        struct line_range line_range;
 } session;
 
 
@@ -120,22 +121,33 @@ static int opt_del_probe_event(const struct option *opt __used,
 static void evaluate_probe_point(struct probe_point *pp)
 {
         struct symbol *sym;
-        sym = map__find_symbol_by_name(session.kmap, pp->function,
-                                       session.psession, NULL);
+        sym = map__find_symbol_by_name(session.kmaps[MAP__FUNCTION],
+                                       pp->function, NULL);
         if (!sym)
                 die("Kernel symbol \'%s\' not found - probe not added.",
                     pp->function);
 }
 
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
 static int open_vmlinux(void)
 {
-        if (map__load(session.kmap, session.psession, NULL) < 0) {
+        if (map__load(session.kmaps[MAP__FUNCTION], NULL) < 0) {
                 pr_debug("Failed to load kernel map.\n");
                 return -EINVAL;
         }
-        pr_debug("Try to open %s\n", session.kmap->dso->long_name);
-        return open(session.kmap->dso->long_name, O_RDONLY);
+        pr_debug("Try to open %s\n",
+                 session.kmaps[MAP__FUNCTION]->dso->long_name);
+        return open(session.kmaps[MAP__FUNCTION]->dso->long_name, O_RDONLY);
+}
+
+static int opt_show_lines(const struct option *opt __used,
+                          const char *str, int unset __used)
+{
+        if (str)
+                parse_line_range_desc(str, &session.line_range);
+        INIT_LIST_HEAD(&session.line_range.line_list);
+        session.show_lines = true;
+        return 0;
 }
 #endif
 
@@ -144,13 +156,16 @@ static const char * const probe_usage[] = {
         "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
         "perf probe [<options>] --del '[GROUP:]EVENT' ...",
         "perf probe --list",
+#ifndef NO_DWARF_SUPPORT
+        "perf probe --line 'LINEDESC'",
+#endif
         NULL
 };
 
 static const struct option options[] = {
         OPT_BOOLEAN('v', "verbose", &verbose,
                     "be more verbose (show parsed arguments, etc)"),
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
 #endif
@@ -159,36 +174,60 @@ static const struct option options[] = {
         OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
                 opt_del_probe_event),
         OPT_CALLBACK('a', "add", NULL,
-#ifdef NO_LIBDWARF
-                "[EVENT=]FUNC[+OFFS|%return] [ARG ...]",
+#ifdef NO_DWARF_SUPPORT
+                "[EVENT=]FUNC[+OFF|%return] [ARG ...]",
 #else
-                "[EVENT=]FUNC[+OFFS|%return|:RLN][@SRC]|SRC:ALN [ARG ...]",
+                "[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
+                " [ARG ...]",
 #endif
                 "probe point definition, where\n"
                 "\t\tGROUP:\tGroup name (optional)\n"
                 "\t\tEVENT:\tEvent name\n"
                 "\t\tFUNC:\tFunction name\n"
-                "\t\tOFFS:\tOffset from function entry (in byte)\n"
+                "\t\tOFF:\tOffset from function entry (in byte)\n"
                 "\t\t%return:\tPut the probe at function return\n"
-#ifdef NO_LIBDWARF
+#ifdef NO_DWARF_SUPPORT
                 "\t\tARG:\tProbe argument (only \n"
 #else
                 "\t\tSRC:\tSource code path\n"
-                "\t\tRLN:\tRelative line number from function entry.\n"
-                "\t\tALN:\tAbsolute line number in file.\n"
+                "\t\tRL:\tRelative line number from function entry.\n"
+                "\t\tAL:\tAbsolute line number in file.\n"
+                "\t\tPT:\tLazy expression of line code.\n"
                 "\t\tARG:\tProbe argument (local variable name or\n"
 #endif
                 "\t\t\tkprobe-tracer argument format.)\n",
                 opt_add_probe_event),
         OPT_BOOLEAN('f', "force", &session.force_add, "forcibly add events"
                     " with existing name"),
+#ifndef NO_DWARF_SUPPORT
+        OPT_CALLBACK('L', "line", NULL,
+                     "FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]",
+                     "Show source code lines.", opt_show_lines),
+#endif
         OPT_END()
 };
 
+/* Initialize symbol maps for vmlinux */
+static void init_vmlinux(void)
+{
+        symbol_conf.sort_by_name = true;
+        if (symbol_conf.vmlinux_name == NULL)
+                symbol_conf.try_vmlinux_path = true;
+        else
+                pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
+        if (symbol__init() < 0)
+                die("Failed to init symbol map.");
+
+        map_groups__init(&session.kmap_groups);
+        if (map_groups__create_kernel_maps(&session.kmap_groups,
+                                           session.kmaps) < 0)
+                die("Failed to create kernel maps.");
+}
+
 int cmd_probe(int argc, const char **argv, const char *prefix __used)
 {
         int i, ret;
-#ifndef NO_LIBDWARF
+#ifndef NO_DWARF_SUPPORT
         int fd;
 #endif
         struct probe_point *pp;
@@ -203,7 +242,8 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                 parse_probe_event_argv(argc, argv);
         }
 
-        if ((!session.nr_probe && !session.dellist && !session.list_events))
+        if ((!session.nr_probe && !session.dellist && !session.list_events &&
+             !session.show_lines))
                 usage_with_options(probe_usage, options);
 
         if (debugfs_valid_mountpoint(debugfs_path) < 0)
@@ -215,10 +255,34 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                                    " --add/--del.\n");
                         usage_with_options(probe_usage, options);
                 }
+                if (session.show_lines) {
+                        pr_warning("  Error: Don't use --list with --line.\n");
+                        usage_with_options(probe_usage, options);
+                }
                 show_perf_probe_events();
                 return 0;
         }
 
+#ifndef NO_DWARF_SUPPORT
+        if (session.show_lines) {
+                if (session.nr_probe != 0 || session.dellist) {
+                        pr_warning("  Error: Don't use --line with"
+                                   " --add/--del.\n");
+                        usage_with_options(probe_usage, options);
+                }
+                init_vmlinux();
+                fd = open_vmlinux();
+                if (fd < 0)
+                        die("Could not open debuginfo file.");
+                ret = find_line_range(fd, &session.line_range);
+                if (ret <= 0)
+                        die("Source line is not found.\n");
+                close(fd);
+                show_line_range(&session.line_range);
+                return 0;
+        }
+#endif
+
         if (session.dellist) {
                 del_trace_kprobe_events(session.dellist);
                 strlist__delete(session.dellist);
@@ -226,25 +290,13 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                         return 0;
         }
 
-        /* Initialize symbol maps for vmlinux */
-        symbol_conf.sort_by_name = true;
-        if (symbol_conf.vmlinux_name == NULL)
-                symbol_conf.try_vmlinux_path = true;
-        if (symbol__init() < 0)
-                die("Failed to init symbol map.");
-        session.psession = perf_session__new(NULL, O_WRONLY, false);
-        if (session.psession == NULL)
-                die("Failed to init perf_session.");
-        session.kmap = map_groups__find_by_name(&session.psession->kmaps,
-                                                MAP__FUNCTION,
-                                                "[kernel.kallsyms]");
-        if (!session.kmap)
-                die("Could not find kernel map.\n");
+        /* Add probes */
+        init_vmlinux();
 
         if (session.need_dwarf)
-#ifdef NO_LIBDWARF
+#ifdef NO_DWARF_SUPPORT
                 die("Debuginfo-analysis is not supported");
-#else   /* !NO_LIBDWARF */
+#else   /* !NO_DWARF_SUPPORT */
                 pr_debug("Some probes require debuginfo.\n");
 
         fd = open_vmlinux();
@@ -264,7 +316,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
                         continue;
 
                 lseek(fd, SEEK_SET, 0);
-                ret = find_probepoint(fd, pp);
+                ret = find_probe_point(fd, pp);
                 if (ret > 0)
                         continue;
                 if (ret == 0) { /* No error but failed to find probe point. */
@@ -285,7 +337,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used)
         close(fd);
 
 end_dwarf:
-#endif /* !NO_LIBDWARF */
+#endif /* !NO_DWARF_SUPPORT */
 
         /* Synthesize probes without dwarf */
         for (i = 0; i < session.nr_probe; i++) {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 265425322734..771533ced6a8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -5,10 +5,13 @@
  * (or a CPU, or a PID) into the perf.data output file - for
  * later analysis via perf report.
  */
+#define _FILE_OFFSET_BITS 64
+
 #include "builtin.h"
 
 #include "perf.h"
 
+#include "util/build-id.h"
 #include "util/util.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
@@ -62,6 +65,7 @@ static int			nr_poll				=      0;
 static int                      nr_cpu                          =      0;
 
 static int                      file_new                        =      1;
+static off_t                    post_processing_offset;
 
 static struct perf_session      *session;
 
@@ -111,22 +115,10 @@ static void write_output(void *buf, size_t size)
         }
 }
 
-static void write_event(event_t *buf, size_t size)
-{
-        /*
-        * Add it to the list of DSOs, so that when we finish this
-         * record session we can pick the available build-ids.
-         */
-        if (buf->header.type == PERF_RECORD_MMAP)
-                dsos__findnew(buf->mmap.filename);
-
-        write_output(buf, size);
-}
-
 static int process_synthesized_event(event_t *event,
                                      struct perf_session *self __used)
 {
-        write_event(event, event->header.size);
+        write_output(event, event->header.size);
         return 0;
 }
 
@@ -178,14 +170,14 @@ static void mmap_read(struct mmap_data *md)
                 size = md->mask + 1 - (old & md->mask);
                 old += size;
 
-                write_event(buf, size);
+                write_output(buf, size);
         }
 
         buf = &data[old & md->mask];
         size = head - old;
         old += size;
 
-        write_event(buf, size);
+        write_output(buf, size);
 
         md->prev = old;
         mmap_write_tail(md, old);
@@ -395,10 +387,21 @@ static void open_counters(int cpu, pid_t pid)
         nr_cpu++;
 }
 
+static int process_buildids(void)
+{
+        u64 size = lseek(output, 0, SEEK_CUR);
+
+        session->fd = output;
+        return __perf_session__process_events(session, post_processing_offset,
+                                              size - post_processing_offset,
+                                              size, &build_id__mark_dso_hit_ops);
+}
+
 static void atexit_header(void)
 {
         session->header.data_size += bytes_written;
 
+        process_buildids();
         perf_header__write(&session->header, output, true);
 }
 
@@ -551,8 +554,23 @@ static int __cmd_record(int argc, const char **argv)
                         return err;
         }
 
+        post_processing_offset = lseek(output, 0, SEEK_CUR);
+
+        err = event__synthesize_kernel_mmap(process_synthesized_event,
+                                            session, "_text");
+        if (err < 0) {
+                pr_err("Couldn't record kernel reference relocation symbol.\n");
+                return err;
+        }
+
+        err = event__synthesize_modules(process_synthesized_event, session);
+        if (err < 0) {
+                pr_err("Couldn't record kernel reference relocation symbol.\n");
+                return err;
+        }
+
         if (!system_wide && profile_cpu == -1)
-                event__synthesize_thread(pid, process_synthesized_event,
+                event__synthesize_thread(target_pid, process_synthesized_event,
                                          session);
         else
                 event__synthesize_threads(process_synthesized_event, session);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index db10c0e8ecae..cfc655d40bb7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -34,6 +34,8 @@
 static char             const *input_name = "perf.data";
 
 static int              force;
+static bool             hide_unresolved;
+static bool             dont_use_callchains;
 
 static int              show_threads;
 static struct perf_read_values  show_threads_values;
@@ -91,11 +93,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         event__parse_sample(event, session->sample_type, &data);
 
-        dump_printf("(IP, %d): %d/%d: %p period: %Ld\n",
-                event->header.misc,
-                data.pid, data.tid,
-                (void *)(long)data.ip,
-                (long long)data.period);
+        dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc,
+                    data.pid, data.tid, data.ip, data.period);
 
         if (session->sample_type & PERF_SAMPLE_CALLCHAIN) {
                 unsigned int i;
@@ -121,7 +120,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
                 return -1;
         }
 
-        if (al.filtered)
+        if (al.filtered || (hide_unresolved && al.sym == NULL))
                 return 0;
 
         if (perf_session__add_hist_entry(session, &al, data.callchain, data.period)) {
@@ -156,14 +155,14 @@ static int process_read_event(event_t *event, struct perf_session *session __use
         return 0;
 }
 
-static int sample_type_check(struct perf_session *session)
+static int perf_session__setup_sample_type(struct perf_session *self)
 {
-        if (!(session->sample_type & PERF_SAMPLE_CALLCHAIN)) {
+        if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
                 if (sort__has_parent) {
                         fprintf(stderr, "selected --sort parent, but no"
                                         " callchain data. Did you call"
                                         " perf record without -g?\n");
-                        return -1;
+                        return -EINVAL;
                 }
                 if (symbol_conf.use_callchain) {
                         fprintf(stderr, "selected -g but no callchain data."
@@ -171,12 +170,13 @@ static int sample_type_check(struct perf_session *session)
                                         " -g?\n");
                         return -1;
                 }
-        } else if (callchain_param.mode != CHAIN_NONE && !symbol_conf.use_callchain) {
+        } else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
+                   !symbol_conf.use_callchain) {
                         symbol_conf.use_callchain = true;
                         if (register_callchain_param(&callchain_param) < 0) {
                                 fprintf(stderr, "Can't register callchain"
                                                 " params\n");
-                                return -1;
+                                return -EINVAL;
                         }
         }
 
@@ -184,20 +184,18 @@ static int sample_type_check(struct perf_session *session)
 }
 
 static struct perf_event_ops event_ops = {
-        .process_sample_event   = process_sample_event,
-        .process_mmap_event     = event__process_mmap,
-        .process_comm_event     = event__process_comm,
-        .process_exit_event     = event__process_task,
-        .process_fork_event     = event__process_task,
-        .process_lost_event     = event__process_lost,
-        .process_read_event     = process_read_event,
-        .sample_type_check      = sample_type_check,
+        .sample = process_sample_event,
+        .mmap   = event__process_mmap,
+        .comm   = event__process_comm,
+        .exit   = event__process_task,
+        .fork   = event__process_task,
+        .lost   = event__process_lost,
+        .read   = process_read_event,
 };
 
-
 static int __cmd_report(void)
 {
-        int ret;
+        int ret = -EINVAL;
         struct perf_session *session;
 
         session = perf_session__new(input_name, O_RDONLY, force);
@@ -207,6 +205,10 @@ static int __cmd_report(void)
         if (show_threads)
                 perf_read_values_init(&show_threads_values);
 
+        ret = perf_session__setup_sample_type(session);
+        if (ret)
+                goto out_delete;
+
         ret = perf_session__process_events(session, &event_ops);
         if (ret)
                 goto out_delete;
@@ -243,11 +245,19 @@ out_delete:
 
 static int
 parse_callchain_opt(const struct option *opt __used, const char *arg,
-                    int unset __used)
+                    int unset)
 {
         char *tok;
         char *endptr;
 
+        /*
+         * --no-call-graph
+         */
+        if (unset) {
+                dont_use_callchains = true;
+                return 0;
+        }
+
         symbol_conf.use_callchain = true;
 
         if (!arg)
@@ -269,7 +279,7 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 
         else if (!strncmp(tok, "none", strlen(arg))) {
                 callchain_param.mode = CHAIN_NONE;
-                symbol_conf.use_callchain = true;
+                symbol_conf.use_callchain = false;
 
                 return 0;
         }
@@ -319,7 +329,7 @@ static const struct option options[] = {
                    "pretty printing style key: normal raw"),
         OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
                    "sort by key(s): pid, comm, dso, symbol, parent"),
-        OPT_BOOLEAN('P', "full-paths", &event_ops.full_paths,
+        OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths,
                     "Don't shorten the pathnames taking into account the cwd"),
         OPT_STRING('p', "parent", &parent_pattern, "regex",
                    "regex filter to identify parent, see: '--sort parent'"),
@@ -340,6 +350,8 @@ 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_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
+                    "Only display entries resolved to a symbol"),
         OPT_END()
 };
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 80209df6cfe8..4f5a03e43444 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1621,11 +1621,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         event__parse_sample(event, session->sample_type, &data);
 
-        dump_printf("(IP, %d): %d/%d: %p period: %Ld\n",
-                event->header.misc,
-                data.pid, data.tid,
-                (void *)(long)data.ip,
-                (long long)data.period);
+        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);
         if (thread == NULL) {
@@ -1653,33 +1650,22 @@ static int process_lost_event(event_t *event __used,
         return 0;
 }
 
-static int sample_type_check(struct perf_session *session __used)
-{
-        if (!(session->sample_type & PERF_SAMPLE_RAW)) {
-                fprintf(stderr,
-                        "No trace sample to read. Did you call perf record "
-                        "without -R?");
-                return -1;
-        }
-
-        return 0;
-}
-
 static struct perf_event_ops event_ops = {
-        .process_sample_event   = process_sample_event,
-        .process_comm_event     = event__process_comm,
-        .process_lost_event     = process_lost_event,
-        .sample_type_check      = sample_type_check,
+        .sample = process_sample_event,
+        .comm   = event__process_comm,
+        .lost   = process_lost_event,
 };
 
 static int read_events(void)
 {
-        int err;
+        int err = -EINVAL;
         struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0);
         if (session == NULL)
                 return -ENOMEM;
 
-        err = perf_session__process_events(session, &event_ops);
+        if (perf_session__has_traces(session, "record -R"))
+                err = perf_session__process_events(session, &event_ops);
+
         perf_session__delete(session);
         return err;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c70d72003557..e8c85d5aec41 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -44,6 +44,7 @@
 #include "util/parse-events.h"
 #include "util/event.h"
 #include "util/debug.h"
+#include "util/header.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -79,6 +80,8 @@ static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int                      event_scaled[MAX_COUNTERS];
 
+static volatile int done = 0;
+
 struct stats
 {
         double n, mean, M2;
@@ -247,61 +250,64 @@ static int run_perf_stat(int argc __used, const char **argv)
         unsigned long long t0, t1;
         int status = 0;
         int counter;
-        int pid;
+        int pid = target_pid;
         int child_ready_pipe[2], go_pipe[2];
+        const bool forks = (target_pid == -1 && argc > 0);
         char buf;
 
         if (!system_wide)
                 nr_cpus = 1;
 
-        if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
+        if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
                 perror("failed to create pipes");
                 exit(1);
         }
 
-        if ((pid = fork()) < 0)
-                perror("failed to fork");
+        if (forks) {
+                if ((pid = fork()) < 0)
+                        perror("failed to fork");
+
+                if (!pid) {
+                        close(child_ready_pipe[0]);
+                        close(go_pipe[1]);
+                        fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+
+                        /*
+                         * Do a dummy execvp to get the PLT entry resolved,
+                         * so we avoid the resolver overhead on the real
+                         * execvp call.
+                         */
+                        execvp("", (char **)argv);
+
+                        /*
+                         * Tell the parent we're ready to go
+                         */
+                        close(child_ready_pipe[1]);
+
+                        /*
+                         * Wait until the parent tells us to go.
+                         */
+                        if (read(go_pipe[0], &buf, 1) == -1)
+                                perror("unable to read pipe");
+
+                        execvp(argv[0], (char **)argv);
+
+                        perror(argv[0]);
+                        exit(-1);
+                }
 
-        if (!pid) {
-                close(child_ready_pipe[0]);
-                close(go_pipe[1]);
-                fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+                child_pid = pid;
 
                 /*
-                 * Do a dummy execvp to get the PLT entry resolved,
-                 * so we avoid the resolver overhead on the real
-                 * execvp call.
-                 */
-                execvp("", (char **)argv);
-
-                /*
-                 * Tell the parent we're ready to go
+                 * Wait for the child to be ready to exec.
                  */
                 close(child_ready_pipe[1]);
-
-                /*
-                 * Wait until the parent tells us to go.
-                 */
-                if (read(go_pipe[0], &buf, 1) == -1)
+                close(go_pipe[0]);
+                if (read(child_ready_pipe[0], &buf, 1) == -1)
                         perror("unable to read pipe");
-
-                execvp(argv[0], (char **)argv);
-
-                perror(argv[0]);
-                exit(-1);
+                close(child_ready_pipe[0]);
         }
 
-        child_pid = pid;
-
-        /*
-         * Wait for the child to be ready to exec.
-         */
-        close(child_ready_pipe[1]);
-        close(go_pipe[0]);
-        if (read(child_ready_pipe[0], &buf, 1) == -1)
-                perror("unable to read pipe");
-        close(child_ready_pipe[0]);
-
         for (counter = 0; counter < nr_counters; counter++)
                 create_perf_stat_counter(counter, pid);
 
@@ -310,8 +316,12 @@ static int run_perf_stat(int argc __used, const char **argv)
          */
         t0 = rdclock();
 
-        close(go_pipe[1]);
-        wait(&status);
+        if (forks) {
+                close(go_pipe[1]);
+                wait(&status);
+        } else {
+                while(!done);
+        }
 
         t1 = rdclock();
 
@@ -417,10 +427,13 @@ static void print_stat(int argc, const char **argv)
         fflush(stdout);
 
         fprintf(stderr, "\n");
-        fprintf(stderr, " Performance counter stats for \'%s", argv[0]);
-
-        for (i = 1; i < argc; i++)
-                fprintf(stderr, " %s", argv[i]);
+        fprintf(stderr, " Performance counter stats for ");
+        if(target_pid == -1) {
+                fprintf(stderr, "\'%s", argv[0]);
+                for (i = 1; i < argc; i++)
+                        fprintf(stderr, " %s", argv[i]);
+        }else
+                fprintf(stderr, "task pid \'%d", target_pid);
 
         fprintf(stderr, "\'");
         if (run_count > 1)
@@ -445,6 +458,9 @@ static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
+        if(target_pid != -1)
+                done = 1;
+
         signr = signo;
 }
 
@@ -461,7 +477,7 @@ static void sig_atexit(void)
 }
 
 static const char * const stat_usage[] = {
-        "perf stat [<options>] <command>",
+        "perf stat [<options>] [<command>]",
         NULL
 };
 
@@ -492,7 +508,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 
         argc = parse_options(argc, argv, options, stat_usage,
                 PARSE_OPT_STOP_AT_NON_OPTION);
-        if (!argc)
+        if (!argc && target_pid == -1)
                 usage_with_options(stat_usage, options);
         if (run_count <= 0)
                 usage_with_options(stat_usage, options);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index a589a43112d6..0d4d8ff7914b 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -280,7 +280,7 @@ static u64 cpus_pstate_state[MAX_CPUS];
 
 static int process_comm_event(event_t *event, struct perf_session *session __used)
 {
-        pid_set_comm(event->comm.pid, event->comm.comm);
+        pid_set_comm(event->comm.tid, event->comm.comm);
         return 0;
 }
 
@@ -1029,33 +1029,24 @@ static void process_samples(struct perf_session *session)
         }
 }
 
-static int sample_type_check(struct perf_session *session)
-{
-        if (!(session->sample_type & PERF_SAMPLE_RAW)) {
-                fprintf(stderr, "No trace samples found in the file.\n"
-                                "Have you used 'perf timechart record' to record it?\n");
-                return -1;
-        }
-
-        return 0;
-}
-
 static struct perf_event_ops event_ops = {
-        .process_comm_event     = process_comm_event,
-        .process_fork_event     = process_fork_event,
-        .process_exit_event     = process_exit_event,
-        .process_sample_event   = queue_sample_event,
-        .sample_type_check      = sample_type_check,
+        .comm   = process_comm_event,
+        .fork   = process_fork_event,
+        .exit   = process_exit_event,
+        .sample = queue_sample_event,
 };
 
 static int __cmd_timechart(void)
 {
         struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0);
-        int ret;
+        int ret = -EINVAL;
 
         if (session == NULL)
                 return -ENOMEM;
 
+        if (!perf_session__has_traces(session, "timechart record"))
+                goto out_delete;
+
         ret = perf_session__process_events(session, &event_ops);
         if (ret)
                 goto out_delete;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ddc584b64871..31f2e597800c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -94,6 +94,7 @@ struct source_line {
 
 static char                     *sym_filter                     =   NULL;
 struct sym_entry                *sym_filter_entry               =   NULL;
+struct sym_entry                *sym_filter_entry_sched         =   NULL;
 static int                      sym_pcnt_filter                 =      5;
 static int                      sym_counter                     =      0;
 static int                      display_weighted                =     -1;
@@ -201,10 +202,9 @@ static void parse_source(struct sym_entry *syme)
         len = sym->end - sym->start;
 
         sprintf(command,
-                "objdump --start-address=0x%016Lx "
-                         "--stop-address=0x%016Lx -dS %s",
-                map->unmap_ip(map, sym->start),
-                map->unmap_ip(map, sym->end), path);
+                "objdump --start-address=%#0*Lx --stop-address=%#0*Lx -dS %s",
+                BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start),
+                BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path);
 
         file = popen(command, "r");
         if (!file)
@@ -215,7 +215,7 @@ static void parse_source(struct sym_entry *syme)
         while (!feof(file)) {
                 struct source_line *src;
                 size_t dummy = 0;
-                char *c;
+                char *c, *sep;
 
                 src = malloc(sizeof(struct source_line));
                 assert(src != NULL);
@@ -234,14 +234,11 @@ static void parse_source(struct sym_entry *syme)
                 *source->lines_tail = src;
                 source->lines_tail = &src->next;
 
-                if (strlen(src->line)>8 && src->line[8] == ':') {
-                        src->eip = strtoull(src->line, NULL, 16);
-                        src->eip = map->unmap_ip(map, src->eip);
-                }
-                if (strlen(src->line)>8 && src->line[16] == ':') {
-                        src->eip = strtoull(src->line, NULL, 16);
-                        src->eip = map->unmap_ip(map, src->eip);
-                }
+                src->eip = strtoull(src->line, &sep, 16);
+                if (*sep == ':')
+                        src->eip = map__objdump_2ip(map, src->eip);
+                else /* this line has no ip info (e.g. source line) */
+                        src->eip = 0;
         }
         pclose(file);
 out_assign:
@@ -276,6 +273,9 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
                 goto out_unlock;
 
         for (line = syme->src->lines; line; line = line->next) {
+                /* skip lines without IP info */
+                if (line->eip == 0)
+                        continue;
                 if (line->eip == ip) {
                         line->count[counter]++;
                         break;
@@ -287,17 +287,20 @@ out_unlock:
         pthread_mutex_unlock(&syme->src->lock);
 }
 
+#define PATTERN_LEN             (BITS_PER_LONG / 4 + 2)
+
 static void lookup_sym_source(struct sym_entry *syme)
 {
         struct symbol *symbol = sym_entry__symbol(syme);
         struct source_line *line;
-        char pattern[PATH_MAX];
+        char pattern[PATTERN_LEN + 1];
 
-        sprintf(pattern, "<%s>:", symbol->name);
+        sprintf(pattern, "%0*Lx <", BITS_PER_LONG / 4,
+                map__rip_2objdump(syme->map, symbol->start));
 
         pthread_mutex_lock(&syme->src->lock);
         for (line = syme->src->lines; line; line = line->next) {
-                if (strstr(line->line, pattern)) {
+                if (memcmp(line->line, pattern, PATTERN_LEN) == 0) {
                         syme->src->source = line;
                         break;
                 }
@@ -667,7 +670,7 @@ static void prompt_symbol(struct sym_entry **target, const char *msg)
         }
 
         if (!found) {
-                fprintf(stderr, "Sorry, %s is not active.\n", sym_filter);
+                fprintf(stderr, "Sorry, %s is not active.\n", buf);
                 sleep(1);
                 return;
         } else
@@ -695,17 +698,15 @@ static void print_mapped_keys(void)
 
         fprintf(stdout, "\t[f]     profile display filter (count).    \t(%d)\n", count_filter);
 
-        if (symbol_conf.vmlinux_name) {
-                fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
-                fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
-                fprintf(stdout, "\t[S]     stop annotation.\n");
-        }
+        fprintf(stdout, "\t[F]     annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
+        fprintf(stdout, "\t[s]     annotate symbol.                   \t(%s)\n", name?: "NULL");
+        fprintf(stdout, "\t[S]     stop annotation.\n");
 
         if (nr_counters > 1)
                 fprintf(stdout, "\t[w]     toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0);
 
         fprintf(stdout,
-                "\t[K]     hide kernel_symbols symbols.             \t(%s)\n",
+                "\t[K]     hide kernel_symbols symbols.     \t(%s)\n",
                 hide_kernel_symbols ? "yes" : "no");
         fprintf(stdout,
                 "\t[U]     hide user symbols.               \t(%s)\n",
@@ -725,14 +726,13 @@ static int key_mapped(int c)
                 case 'Q':
                 case 'K':
                 case 'U':
+                case 'F':
+                case 's':
+                case 'S':
                         return 1;
                 case 'E':
                 case 'w':
                         return nr_counters > 1 ? 1 : 0;
-                case 'F':
-                case 's':
-                case 'S':
-                        return symbol_conf.vmlinux_name ? 1 : 0;
                 default:
                         break;
         }
@@ -910,8 +910,12 @@ static int symbol_filter(struct map *map, struct symbol *sym)
         syme = symbol__priv(sym);
         syme->map = map;
         syme->src = NULL;
-        if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter))
-                sym_filter_entry = syme;
+
+        if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) {
+                /* schedule initial sym_filter_entry setup */
+                sym_filter_entry_sched = syme;
+                sym_filter = NULL;
+        }
 
         for (i = 0; skip_symbols[i]; i++) {
                 if (!strcmp(skip_symbols[i], name)) {
@@ -934,8 +938,11 @@ static void event__process_sample(const event_t *self,
         struct addr_location al;
         u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
+        ++samples;
+
         switch (origin) {
         case PERF_RECORD_MISC_USER:
+                ++userspace_samples;
                 if (hide_user_symbols)
                         return;
                 break;
@@ -948,9 +955,38 @@ static void event__process_sample(const event_t *self,
         }
 
         if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 ||
-            al.sym == NULL || al.filtered)
+            al.filtered)
                 return;
 
+        if (al.sym == NULL) {
+                /*
+                 * As we do lazy loading of symtabs we only will know if the
+                 * specified vmlinux file is invalid when we actually have a
+                 * hit in kernel space and then try to load it. So if we get
+                 * here and there are _no_ symbols in the DSO backing the
+                 * kernel map, bail out.
+                 *
+                 * We may never get here, for instance, if we use -K/
+                 * --hide-kernel-symbols, even if the user specifies an
+                 * invalid --vmlinux ;-)
+                 */
+                if (al.map == session->vmlinux_maps[MAP__FUNCTION] &&
+                    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
+                        pr_err("The %s file can't be used\n",
+                               symbol_conf.vmlinux_name);
+                        exit(1);
+                }
+
+                return;
+        }
+
+        /* let's see, whether we need to install initial sym_filter_entry */
+        if (sym_filter_entry_sched) {
+                sym_filter_entry = sym_filter_entry_sched;
+                sym_filter_entry_sched = NULL;
+                parse_source(sym_filter_entry);
+        }
+
         syme = symbol__priv(al.sym);
         if (!syme->skip) {
                 syme->count[counter]++;
@@ -960,9 +996,6 @@ static void event__process_sample(const event_t *self,
                 if (list_empty(&syme->node) || !syme->node.next)
                         __list_insert_active_sym(syme);
                 pthread_mutex_unlock(&active_symbols_lock);
-                if (origin == PERF_RECORD_MISC_USER)
-                        ++userspace_samples;
-                ++samples;
         }
 }
 
@@ -975,6 +1008,10 @@ static int event__process(event_t *event, struct perf_session *session)
         case PERF_RECORD_MMAP:
                 event__process_mmap(event, session);
                 break;
+        case PERF_RECORD_FORK:
+        case PERF_RECORD_EXIT:
+                event__process_task(event, session);
+                break;
         default:
                 break;
         }
@@ -1244,7 +1281,7 @@ static const struct option options[] = {
         OPT_BOOLEAN('i', "inherit", &inherit,
                     "child tasks inherit counters"),
         OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name",
-                    "symbol to annotate - requires -k option"),
+                    "symbol to annotate"),
         OPT_BOOLEAN('z', "zero", &zero,
                     "zero history across updates"),
         OPT_INTEGER('F', "freq", &freq,
@@ -1280,16 +1317,14 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
 
         symbol_conf.priv_size = (sizeof(struct sym_entry) +
                                  (nr_counters + 1) * sizeof(unsigned long));
-        if (symbol_conf.vmlinux_name == NULL)
-                symbol_conf.try_vmlinux_path = true;
+
+        symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
         if (symbol__init() < 0)
                 return -1;
 
         if (delay_secs < 1)
                 delay_secs = 1;
 
-        parse_source(sym_filter_entry);
-
         /*
          * User specified count overrides default frequency.
          */
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 574a215e800b..407041d20de0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -44,6 +44,7 @@ static void setup_scripting(void)
         perf_set_argv_exec_path(perf_exec_path());
 
         setup_perl_scripting();
+        setup_python_scripting();
 
         scripting_ops = &default_scripting_ops;
 }
@@ -75,11 +76,8 @@ static int process_sample_event(event_t *event, struct perf_session *session)
 
         event__parse_sample(event, session->sample_type, &data);
 
-        dump_printf("(IP, %d): %d/%d: %p period: %Ld\n",
-                event->header.misc,
-                data.pid, data.tid,
-                (void *)(long)data.ip,
-                (long long)data.period);
+        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) {
@@ -103,22 +101,9 @@ static int process_sample_event(event_t *event, struct perf_session *session)
         return 0;
 }
 
-static int sample_type_check(struct perf_session *session)
-{
-        if (!(session->sample_type & PERF_SAMPLE_RAW)) {
-                fprintf(stderr,
-                        "No trace sample to read. Did you call perf record "
-                        "without -R?");
-                return -1;
-        }
-
-        return 0;
-}
-
 static struct perf_event_ops event_ops = {
-        .process_sample_event   = process_sample_event,
-        .process_comm_event     = event__process_comm,
-        .sample_type_check      = sample_type_check,
+        .sample = process_sample_event,
+        .comm   = event__process_comm,
 };
 
 static int __cmd_trace(struct perf_session *session)
@@ -235,9 +220,9 @@ static int parse_scriptname(const struct option *opt __used,
         const char *script, *ext;
         int len;
 
-        if (strcmp(str, "list") == 0) {
+        if (strcmp(str, "lang") == 0) {
                 list_available_languages();
-                return 0;
+                exit(0);
         }
 
         script = strchr(str, ':');
@@ -531,6 +516,8 @@ static const struct option options[] = {
                      parse_scriptname),
         OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
                    "generate perf-trace.xx script in specified language"),
+        OPT_STRING('i', "input", &input_name, "file",
+                    "input file name"),
 
         OPT_END()
 };
@@ -586,12 +573,16 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
 
         if (symbol__init() < 0)
                 return -1;
-        setup_pager();
+        if (!script_name)
+                setup_pager();
 
         session = perf_session__new(input_name, O_RDONLY, 0);
         if (session == NULL)
                 return -ENOMEM;
 
+        if (!perf_session__has_traces(session, "record -R"))
+                return -EINVAL;
+
         if (generate_script_lang) {
                 struct stat perf_stat;
 
@@ -618,7 +609,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                         return -1;
                 }
 
-                perf_header__read(&session->header, input);
                 err = scripting_ops->generate_script("perf-trace");
                 goto out;
         }
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 18035b1f16c7..10fe49e7048a 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -16,6 +16,7 @@ extern int check_pager_config(const char *cmd);
 
 extern int cmd_annotate(int argc, const char **argv, const char *prefix);
 extern int cmd_bench(int argc, const char **argv, const char *prefix);
+extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
@@ -30,5 +31,6 @@ extern int cmd_trace(int argc, const char **argv, const char *prefix);
 extern int cmd_version(int argc, const char **argv, const char *prefix);
 extern int cmd_probe(int argc, const char **argv, const char *prefix);
 extern int cmd_kmem(int argc, const char **argv, const char *prefix);
+extern int cmd_lock(int argc, const char **argv, const char *prefix);
 
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 71dc7c3fe7b2..db6ee94d4a8e 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -3,7 +3,9 @@
 # command name                  category [deprecated] [common]
 #
 perf-annotate                   mainporcelain common
+perf-archive                    mainporcelain common
 perf-bench                      mainporcelain common
+perf-buildid-cache              mainporcelain common
 perf-buildid-list               mainporcelain common
 perf-diff                       mainporcelain common
 perf-list                       mainporcelain common
@@ -16,3 +18,4 @@ perf-top			mainporcelain common
 perf-trace                      mainporcelain common
 perf-probe                      mainporcelain common
 perf-kmem                       mainporcelain common
+perf-lock                       mainporcelain common
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index 8d0de5130db3..bd0bb1b1279b 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -101,10 +101,10 @@ enum hw_event_ids {
          */
         PERF_COUNT_HW_CPU_CYCLES                = 0,
         PERF_COUNT_HW_INSTRUCTIONS              = 1,
-        PERF_COUNT_HW_CACHE_REFERENCES  = 2,
+        PERF_COUNT_HW_CACHE_REFERENCES          = 2,
         PERF_COUNT_HW_CACHE_MISSES              = 3,
         PERF_COUNT_HW_BRANCH_INSTRUCTIONS       = 4,
-        PERF_COUNT_HW_BRANCH_MISSES     = 5,
+        PERF_COUNT_HW_BRANCH_MISSES             = 5,
         PERF_COUNT_HW_BUS_CYCLES                = 6,
 };
 
@@ -131,8 +131,8 @@ software events, selected by 'event_id':
  */
 enum sw_event_ids {
         PERF_COUNT_SW_CPU_CLOCK         = 0,
-        PERF_COUNT_SW_TASK_CLOCK                = 1,
-        PERF_COUNT_SW_PAGE_FAULTS               = 2,
+        PERF_COUNT_SW_TASK_CLOCK        = 1,
+        PERF_COUNT_SW_PAGE_FAULTS       = 2,
         PERF_COUNT_SW_CONTEXT_SWITCHES  = 3,
         PERF_COUNT_SW_CPU_MIGRATIONS    = 4,
         PERF_COUNT_SW_PAGE_FAULTS_MIN   = 5,
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
new file mode 100644
index 000000000000..910468e6e01c
--- /dev/null
+++ b/tools/perf/perf-archive.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+# perf archive
+# Arnaldo Carvalho de Melo <acme@redhat.com>
+
+PERF_DATA=perf.data
+if [ $# -ne 0 ] ; then
+        PERF_DATA=$1
+fi
+
+DEBUGDIR=~/.debug/
+BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
+NOBUILDID=0000000000000000000000000000000000000000
+
+perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
+if [ ! -s $BUILDIDS ] ; then
+        echo "perf archive: no build-ids found"
+        rm -f $BUILDIDS
+        exit 1
+fi
+
+MANIFEST=$(mktemp /tmp/perf-archive-manifest.XXXXXX)
+
+cut -d ' ' -f 1 $BUILDIDS | \
+while read build_id ; do
+        linkname=$DEBUGDIR.build-id/${build_id:0:2}/${build_id:2}
+        filename=$(readlink -f $linkname)
+        echo ${linkname#$DEBUGDIR} >> $MANIFEST
+        echo ${filename#$DEBUGDIR} >> $MANIFEST
+done
+
+tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST
+rm -f $MANIFEST $BUILDIDS
+exit 0
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 873e55fab375..cd32c200cdb3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -48,7 +48,8 @@ int check_pager_config(const char *cmd)
         return c.val;
 }
 
-static void commit_pager_choice(void) {
+static void commit_pager_choice(void)
+{
         switch (use_pager) {
         case 0:
                 setenv("PERF_PAGER", "cat", 1);
@@ -70,7 +71,7 @@ static void set_debugfs_path(void)
                  "tracing/events");
 }
 
-static int handle_options(const char*** argv, int* argc, int* envchanged)
+static int handle_options(const char ***argv, int *argc, int *envchanged)
 {
         int handled = 0;
 
@@ -109,7 +110,7 @@ static int handle_options(const char*** argv, int* argc, int* envchanged)
                                 *envchanged = 1;
                 } else if (!strcmp(cmd, "--perf-dir")) {
                         if (*argc < 2) {
-                                fprintf(stderr, "No directory given for --perf-dir.\n" );
+                                fprintf(stderr, "No directory given for --perf-dir.\n");
                                 usage(perf_usage_string);
                         }
                         setenv(PERF_DIR_ENVIRONMENT, (*argv)[1], 1);
@@ -124,7 +125,7 @@ static int handle_options(const char*** argv, int* argc, int* envchanged)
                                 *envchanged = 1;
                 } else if (!strcmp(cmd, "--work-tree")) {
                         if (*argc < 2) {
-                                fprintf(stderr, "No directory given for --work-tree.\n" );
+                                fprintf(stderr, "No directory given for --work-tree.\n");
                                 usage(perf_usage_string);
                         }
                         setenv(PERF_WORK_TREE_ENVIRONMENT, (*argv)[1], 1);
@@ -168,7 +169,7 @@ static int handle_alias(int *argcp, const char ***argv)
 {
         int envchanged = 0, ret = 0, saved_errno = errno;
         int count, option_count;
-        const char** new_argv;
+        const char **new_argv;
         const char *alias_command;
         char *alias_string;
 
@@ -210,11 +211,11 @@ static int handle_alias(int *argcp, const char ***argv)
                 if (!strcmp(alias_command, new_argv[0]))
                         die("recursive alias: %s", alias_command);
 
-                new_argv = realloc(new_argv, sizeof(char*) *
+                new_argv = realloc(new_argv, sizeof(char *) *
                                     (count + *argcp + 1));
                 /* insert after command name */
-                memcpy(new_argv + count, *argv + 1, sizeof(char*) * *argcp);
-                new_argv[count+*argcp] = NULL;
+                memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp);
+                new_argv[count + *argcp] = NULL;
 
                 *argv = new_argv;
                 *argcp += count - 1;
@@ -285,6 +286,7 @@ static void handle_internal_command(int argc, const char **argv)
 {
         const char *cmd = argv[0];
         static struct cmd_struct commands[] = {
+                { "buildid-cache", cmd_buildid_cache, 0 },
                 { "buildid-list", cmd_buildid_list, 0 },
                 { "diff",       cmd_diff,       0 },
                 { "help",       cmd_help,       0 },
@@ -301,6 +303,7 @@ static void handle_internal_command(int argc, const char **argv)
                 { "sched",      cmd_sched,      0 },
                 { "probe",      cmd_probe,      0 },
                 { "kmem",       cmd_kmem,       0 },
+                { "lock",       cmd_lock,       0 },
         };
         unsigned int i;
         static const char ext[] = STRIP_EXTENSION;
@@ -388,7 +391,7 @@ static int run_argv(int *argcp, const char ***argv)
 /* mini /proc/mounts parser: searching for "^blah /mount/point debugfs" */
 static void get_debugfs_mntpt(void)
 {
-        const char *path = debugfs_find_mountpoint();
+        const char *path = debugfs_mount(NULL);
 
         if (path)
                 strncpy(debugfs_mntpt, path, sizeof(debugfs_mntpt));
@@ -442,15 +445,15 @@ int main(int argc, const char **argv)
 
         /*
          * We use PATH to find perf commands, but we prepend some higher
-         * precidence paths: the "--exec-path" option, the PERF_EXEC_PATH
+         * precedence paths: the "--exec-path" option, the PERF_EXEC_PATH
          * environment, and the $(perfexecdir) from the Makefile at build
          * time.
          */
         setup_path();
 
         while (1) {
-                static int done_help = 0;
-                static int was_alias = 0;
+                static int done_help;
+                static int was_alias;
 
                 was_alias = run_argv(&argc, &argv);
                 if (errno != ENOENT)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 75f941bfba9e..6fb379bc1d1f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -65,9 +65,7 @@
  * Use the __kuser_memory_barrier helper in the CPU helper page. See
  * arch/arm/kernel/entry-armv.S in the kernel source for details.
  */
-#define rmb()           asm volatile("mov r0, #0xffff0fff; mov lr, pc;" \
-                                     "sub pc, r0, #95" ::: "r0", "lr", "cc", \
-                                     "memory")
+#define rmb()           ((void(*)(void))0xffff0fa0)()
 #define cpu_relax()     asm volatile("":::"memory")
 #endif
 
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index af78d9a52a7d..01a64ad693f2 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -31,13 +31,14 @@
 #include "EXTERN.h"
 #include "perl.h"
 #include "XSUB.h"
-#include "../../../util/trace-event-perl.h"
+#include "../../../perf.h"
+#include "../../../util/trace-event.h"
 
 #ifndef PERL_UNUSED_VAR
 #  define PERL_UNUSED_VAR(var) if (0) var = var
 #endif
 
-#line 41 "Context.c"
+#line 42 "Context.c"
 
 XS(XS_Perf__Trace__Context_common_pc); /* prototype to pass -Wmissing-prototypes */
 XS(XS_Perf__Trace__Context_common_pc)
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
index fb78006c165e..549cf0467d30 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.xs
@@ -22,7 +22,8 @@
 #include "EXTERN.h"
 #include "perl.h"
 #include "XSUB.h"
-#include "../../../util/trace-event-perl.h"
+#include "../../../perf.h"
+#include "../../../util/trace-event.h"
 
 MODULE = Perf::Trace::Context           PACKAGE = Perf::Trace::Context
 PROTOTYPES: ENABLE
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 052f132ced24..f869c48dc9b0 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
@@ -44,7 +44,7 @@ sub nsecs_secs {
 sub nsecs_nsecs {
     my ($nsecs) = @_;
 
-    return $nsecs - nsecs_secs($nsecs);
+    return $nsecs % $NSECS_PER_SEC;
 }
 
 sub nsecs_str {
diff --git a/tools/perf/scripts/perl/bin/check-perf-trace-record b/tools/perf/scripts/perl/bin/check-perf-trace-record
index c7ec5de2f535..e6cb1474f8e8 100644
--- a/tools/perf/scripts/perl/bin/check-perf-trace-record
+++ b/tools/perf/scripts/perl/bin/check-perf-trace-record
@@ -1,7 +1,2 @@
 #!/bin/bash
-perf record -c 1 -f -a -M -R -e kmem:kmalloc -e irq:softirq_entry
-
-
-
-
-
+perf record -c 1 -f -a -M -R -e kmem:kmalloc -e irq:softirq_entry -e kmem:kfree
diff --git a/tools/perf/scripts/perl/bin/check-perf-trace-report b/tools/perf/scripts/perl/bin/check-perf-trace-report
deleted file mode 100644
index 7fc4a033dd49..000000000000
--- a/tools/perf/scripts/perl/bin/check-perf-trace-report
+++ /dev/null
@@ -1,6 +0,0 @@
-#!/bin/bash
-# description: useless but exhaustive test script
-perf trace -s ~/libexec/perf-core/scripts/perl/check-perf-trace.pl
-
-
-
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
new file mode 100644
index 000000000000..f8885d389e6f
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -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
new file mode 100644
index 000000000000..8bfc660e5056
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: system-wide failed syscalls
+# args: [comm]
+perf trace -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $1
diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
new file mode 100644
index 000000000000..c18e7e27a84b
--- /dev/null
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -0,0 +1,38 @@
+# failed system call counts
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide failed system call totals
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Context;
+use Perf::Trace::Util;
+
+my %failed_syscalls;
+
+sub raw_syscalls::sys_exit
+{
+        my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+            $common_pid, $common_comm,
+            $id, $ret) = @_;
+
+        if ($ret < 0) {
+            $failed_syscalls{$common_comm}++;
+        }
+}
+
+sub trace_end
+{
+    printf("\nfailed syscalls by comm:\n\n");
+
+    printf("%-20s  %10s\n", "comm", "# errors");
+    printf("%-20s  %6s  %10s\n", "--------------------", "----------");
+
+    foreach my $comm (sort {$failed_syscalls{$b} <=> $failed_syscalls{$a}}
+                      keys %failed_syscalls) {
+            printf("%-20s  %10s\n", $comm, $failed_syscalls{$comm});
+    }
+}
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
new file mode 100644
index 000000000000..957085dd5d8d
--- /dev/null
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -0,0 +1,88 @@
+/*
+ * Context.c.  Python interfaces for perf trace.
+ *
+ * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <Python.h>
+#include "../../../perf.h"
+#include "../../../util/trace-event.h"
+
+PyMODINIT_FUNC initperf_trace_context(void);
+
+static PyObject *perf_trace_context_common_pc(PyObject *self, PyObject *args)
+{
+        static struct scripting_context *scripting_context;
+        PyObject *context;
+        int retval;
+
+        if (!PyArg_ParseTuple(args, "O", &context))
+                return NULL;
+
+        scripting_context = PyCObject_AsVoidPtr(context);
+        retval = common_pc(scripting_context);
+
+        return Py_BuildValue("i", retval);
+}
+
+static PyObject *perf_trace_context_common_flags(PyObject *self,
+                                                 PyObject *args)
+{
+        static struct scripting_context *scripting_context;
+        PyObject *context;
+        int retval;
+
+        if (!PyArg_ParseTuple(args, "O", &context))
+                return NULL;
+
+        scripting_context = PyCObject_AsVoidPtr(context);
+        retval = common_flags(scripting_context);
+
+        return Py_BuildValue("i", retval);
+}
+
+static PyObject *perf_trace_context_common_lock_depth(PyObject *self,
+                                                      PyObject *args)
+{
+        static struct scripting_context *scripting_context;
+        PyObject *context;
+        int retval;
+
+        if (!PyArg_ParseTuple(args, "O", &context))
+                return NULL;
+
+        scripting_context = PyCObject_AsVoidPtr(context);
+        retval = common_lock_depth(scripting_context);
+
+        return Py_BuildValue("i", retval);
+}
+
+static PyMethodDef ContextMethods[] = {
+        { "common_pc", perf_trace_context_common_pc, METH_VARARGS,
+          "Get the common preempt count event field value."},
+        { "common_flags", perf_trace_context_common_flags, METH_VARARGS,
+          "Get the common flags event field value."},
+        { "common_lock_depth", perf_trace_context_common_lock_depth,
+          METH_VARARGS, "Get the common lock depth event field value."},
+        { NULL, NULL, 0, NULL}
+};
+
+PyMODINIT_FUNC initperf_trace_context(void)
+{
+        (void) Py_InitModule("perf_trace_context", ContextMethods);
+}
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
new file mode 100644
index 000000000000..1dc464ee2ca8
--- /dev/null
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -0,0 +1,91 @@
+# Core.py - Python extension for perf trace, core functions
+#
+# Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
+#
+# This software may be distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+
+from collections import defaultdict
+
+def autodict():
+    return defaultdict(autodict)
+
+flag_fields = autodict()
+symbolic_fields = autodict()
+
+def define_flag_field(event_name, field_name, delim):
+    flag_fields[event_name][field_name]['delim'] = delim
+
+def define_flag_value(event_name, field_name, value, field_str):
+    flag_fields[event_name][field_name]['values'][value] = field_str
+
+def define_symbolic_field(event_name, field_name):
+    # nothing to do, really
+    pass
+
+def define_symbolic_value(event_name, field_name, value, field_str):
+    symbolic_fields[event_name][field_name]['values'][value] = field_str
+
+def flag_str(event_name, field_name, value):
+    string = ""
+
+    if flag_fields[event_name][field_name]:
+        print_delim = 0
+        keys = flag_fields[event_name][field_name]['values'].keys()
+        keys.sort()
+        for idx in keys:
+            if not value and not idx:
+                string += flag_fields[event_name][field_name]['values'][idx]
+                break
+            if idx and (value & idx) == idx:
+                if print_delim and flag_fields[event_name][field_name]['delim']:
+                    string += " " + flag_fields[event_name][field_name]['delim'] + " "
+                string += flag_fields[event_name][field_name]['values'][idx]
+                print_delim = 1
+                value &= ~idx
+
+    return string
+
+def symbol_str(event_name, field_name, value):
+    string = ""
+
+    if symbolic_fields[event_name][field_name]:
+        keys = symbolic_fields[event_name][field_name]['values'].keys()
+        keys.sort()
+        for idx in keys:
+            if not value and not idx:
+                string = symbolic_fields[event_name][field_name]['values'][idx]
+                break
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
+                break
+
+    return string
+
+trace_flags = { 0x00: "NONE", \
+                    0x01: "IRQS_OFF", \
+                    0x02: "IRQS_NOSUPPORT", \
+                    0x04: "NEED_RESCHED", \
+                    0x08: "HARDIRQ", \
+                    0x10: "SOFTIRQ" }
+
+def trace_flag_str(value):
+    string = ""
+    print_delim = 0
+
+    keys = trace_flags.keys()
+
+    for idx in keys:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
+
+    return string
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
new file mode 100644
index 000000000000..83e91435ed09
--- /dev/null
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -0,0 +1,25 @@
+# Util.py - Python extension for perf trace, miscellaneous utility code
+#
+# Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com>
+#
+# This software may be distributed under the terms of the GNU General
+# Public License ("GPL") version 2 as published by the Free Software
+# Foundation.
+
+NSECS_PER_SEC    = 1000000000
+
+def avg(total, n):
+    return total / n
+
+def nsecs(secs, nsecs):
+    return secs * NSECS_PER_SEC + nsecs
+
+def nsecs_secs(nsecs):
+    return nsecs / NSECS_PER_SEC
+
+def nsecs_nsecs(nsecs):
+    return nsecs % NSECS_PER_SEC
+
+def nsecs_str(nsecs):
+    str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
+    return str
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
new file mode 100644
index 000000000000..f8885d389e6f
--- /dev/null
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -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
new file mode 100644
index 000000000000..1e0c0a860c87
--- /dev/null
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: system-wide failed syscalls, by pid
+# args: [comm]
+perf trace -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $1
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
new file mode 100644
index 000000000000..45a8c50359da
--- /dev/null
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -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
new file mode 100644
index 000000000000..f8044d192271
--- /dev/null
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: system-wide syscall counts, by pid
+# args: [comm]
+perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $1
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
new file mode 100644
index 000000000000..45a8c50359da
--- /dev/null
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -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
new file mode 100644
index 000000000000..a366aa61612f
--- /dev/null
+++ b/tools/perf/scripts/python/bin/syscall-counts-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: system-wide syscall counts
+# args: [comm]
+perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py $1
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
new file mode 100644
index 000000000000..964d934395ff
--- /dev/null
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -0,0 +1,83 @@
+# perf trace event handlers, generated by perf trace -g python
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# This script tests basic functionality such as flag and symbol
+# strings, common_xxx() calls back into perf, begin, end, unhandled
+# events, etc.  Basically, if this script runs successfully and
+# displays expected results, Python scripting support should be ok.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from Core import *
+from perf_trace_context import *
+
+unhandled = autodict()
+
+def trace_begin():
+        print "trace_begin"
+        pass
+
+def trace_end():
+        print_unhandled()
+
+def irq__softirq_entry(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        vec):
+                print_header(event_name, common_cpu, common_secs, common_nsecs,
+                        common_pid, common_comm)
+
+                print_uncommon(context)
+
+                print "vec=%s\n" % \
+                (symbol_str("irq__softirq_entry", "vec", vec)),
+
+def kmem__kmalloc(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        call_site, ptr, bytes_req, bytes_alloc,
+        gfp_flags):
+                print_header(event_name, common_cpu, common_secs, common_nsecs,
+                        common_pid, common_comm)
+
+                print_uncommon(context)
+
+                print "call_site=%u, ptr=%u, bytes_req=%u, " \
+                "bytes_alloc=%u, gfp_flags=%s\n" % \
+                (call_site, ptr, bytes_req, bytes_alloc,
+
+                flag_str("kmem__kmalloc", "gfp_flags", gfp_flags)),
+
+def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
+                common_pid, common_comm):
+    try:
+        unhandled[event_name] += 1
+    except TypeError:
+        unhandled[event_name] = 1
+
+def print_header(event_name, cpu, secs, nsecs, pid, comm):
+        print "%-20s %5u %05u.%09u %8u %-20s " % \
+        (event_name, cpu, secs, nsecs, pid, comm),
+
+# print trace fields not included in handler args
+def print_uncommon(context):
+    print "common_preempt_count=%d, common_flags=%s, common_lock_depth=%d, " \
+        % (common_pc(context), trace_flag_str(common_flags(context)), \
+               common_lock_depth(context))
+
+def print_unhandled():
+    keys = unhandled.keys()
+    if not keys:
+        return
+
+    print "\nunhandled events:\n\n",
+
+    print "%-40s  %10s\n" % ("event", "count"),
+    print "%-40s  %10s\n" % ("----------------------------------------", \
+                                 "-----------"),
+
+    for event_name in keys:
+        print "%-40s  %10d\n" % (event_name, unhandled[event_name])
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
new file mode 100644
index 000000000000..0ca02278fe69
--- /dev/null
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -0,0 +1,68 @@
+# failed system call counts, by pid
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide failed system call totals, broken down by pid.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+usage = "perf trace -s syscall-counts-by-pid.py [comm]\n";
+
+for_comm = None
+
+if len(sys.argv) > 2:
+        sys.exit(usage)
+
+if len(sys.argv) > 1:
+        for_comm = sys.argv[1]
+
+syscalls = autodict()
+
+def trace_begin():
+        pass
+
+def trace_end():
+        print_error_totals()
+
+def raw_syscalls__sys_exit(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        id, ret):
+        if for_comm is not None:
+                if common_comm != for_comm:
+                        return
+
+        if ret < 0:
+                try:
+                        syscalls[common_comm][common_pid][id][ret] += 1
+                except TypeError:
+                        syscalls[common_comm][common_pid][id][ret] = 1
+
+def print_error_totals():
+    if for_comm is not None:
+            print "\nsyscall errors for %s:\n\n" % (for_comm),
+    else:
+            print "\nsyscall errors:\n\n",
+
+    print "%-30s  %10s\n" % ("comm [pid]", "count"),
+    print "%-30s  %10s\n" % ("------------------------------", \
+                                 "----------"),
+
+    comm_keys = syscalls.keys()
+    for comm in comm_keys:
+            pid_keys = syscalls[comm].keys()
+            for pid in pid_keys:
+                    print "\n%s [%d]\n" % (comm, pid),
+                    id_keys = syscalls[comm][pid].keys()
+                    for id in id_keys:
+                            print "  syscall: %-16d\n" % (id),
+                            ret_keys = syscalls[comm][pid][id].keys()
+                            for ret, val in sorted(syscalls[comm][pid][id].iteritems(), key = lambda(k, v): (v, k),  reverse = True):
+                                    print "    err = %-20d  %10d\n" % (ret, val),
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
new file mode 100644
index 000000000000..af722d6a4b3f
--- /dev/null
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -0,0 +1,64 @@
+# system call counts, by pid
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide system call totals, broken down by syscall.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+usage = "perf trace -s syscall-counts-by-pid.py [comm]\n";
+
+for_comm = None
+
+if len(sys.argv) > 2:
+        sys.exit(usage)
+
+if len(sys.argv) > 1:
+        for_comm = sys.argv[1]
+
+syscalls = autodict()
+
+def trace_begin():
+        pass
+
+def trace_end():
+        print_syscall_totals()
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        id, args):
+        if for_comm is not None:
+                if common_comm != for_comm:
+                        return
+        try:
+                syscalls[common_comm][common_pid][id] += 1
+        except TypeError:
+                syscalls[common_comm][common_pid][id] = 1
+
+def print_syscall_totals():
+    if for_comm is not None:
+            print "\nsyscall events for %s:\n\n" % (for_comm),
+    else:
+            print "\nsyscall events by comm/pid:\n\n",
+
+    print "%-40s  %10s\n" % ("comm [pid]/syscalls", "count"),
+    print "%-40s  %10s\n" % ("----------------------------------------", \
+                                 "----------"),
+
+    comm_keys = syscalls.keys()
+    for comm in comm_keys:
+            pid_keys = syscalls[comm].keys()
+            for pid in pid_keys:
+                    print "\n%s [%d]\n" % (comm, pid),
+                    id_keys = syscalls[comm][pid].keys()
+                    for id, val in sorted(syscalls[comm][pid].iteritems(), \
+                                  key = lambda(k, v): (v, k),  reverse = True):
+                            print "  %-38d  %10d\n" % (id, val),
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
new file mode 100644
index 000000000000..f977e85ff049
--- /dev/null
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -0,0 +1,58 @@
+# system call counts
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Displays system-wide system call totals, broken down by syscall.
+# If a [comm] arg is specified, only syscalls called by [comm] are displayed.
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+
+usage = "perf trace -s syscall-counts.py [comm]\n";
+
+for_comm = None
+
+if len(sys.argv) > 2:
+        sys.exit(usage)
+
+if len(sys.argv) > 1:
+        for_comm = sys.argv[1]
+
+syscalls = autodict()
+
+def trace_begin():
+        pass
+
+def trace_end():
+        print_syscall_totals()
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+        common_secs, common_nsecs, common_pid, common_comm,
+        id, args):
+        if for_comm is not None:
+                if common_comm != for_comm:
+                        return
+        try:
+                syscalls[id] += 1
+        except TypeError:
+                syscalls[id] = 1
+
+def print_syscall_totals():
+    if for_comm is not None:
+            print "\nsyscall events for %s:\n\n" % (for_comm),
+    else:
+            print "\nsyscall events:\n\n",
+
+    print "%-40s  %10s\n" % ("event", "count"),
+    print "%-40s  %10s\n" % ("----------------------------------------", \
+                                 "-----------"),
+
+    for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
+                                  reverse = True):
+            print "%-40d  %10d\n" % (id, val),
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
new file mode 100644
index 000000000000..04904b35ba81
--- /dev/null
+++ b/tools/perf/util/build-id.c
@@ -0,0 +1,39 @@
+/*
+ * build-id.c
+ *
+ * build-id support
+ *
+ * Copyright (C) 2009, 2010 Red Hat Inc.
+ * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "build-id.h"
+#include "event.h"
+#include "symbol.h"
+#include <linux/kernel.h>
+
+static int build_id__mark_dso_hit(event_t *event, struct perf_session *session)
+{
+        struct addr_location al;
+        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+        struct thread *thread = perf_session__findnew(session, event->ip.pid);
+
+        if (thread == NULL) {
+                pr_err("problem processing %d event, skipping it.\n",
+                        event->header.type);
+                return -1;
+        }
+
+        thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
+                              event->ip.ip, &al);
+
+        if (al.map != NULL)
+                al.map->dso->hit = 1;
+
+        return 0;
+}
+
+struct perf_event_ops build_id__mark_dso_hit_ops = {
+        .sample = build_id__mark_dso_hit,
+        .mmap   = event__process_mmap,
+        .fork   = event__process_task,
+};
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
new file mode 100644
index 000000000000..1d981d63cf9a
--- /dev/null
+++ b/tools/perf/util/build-id.h
@@ -0,0 +1,8 @@
+#ifndef PERF_BUILD_ID_H_
+#define PERF_BUILD_ID_H_ 1
+
+#include "session.h"
+
+extern struct perf_event_ops build_id__mark_dso_hit_ops;
+
+#endif
diff --git a/tools/perf/util/data_map.c b/tools/perf/util/data_map.c
deleted file mode 100644
index b557b836de3d..000000000000
--- a/tools/perf/util/data_map.c
+++ /dev/null
@@ -1,252 +0,0 @@
-#include "symbol.h"
-#include "util.h"
-#include "debug.h"
-#include "thread.h"
-#include "session.h"
-
-static int process_event_stub(event_t *event __used,
-                              struct perf_session *session __used)
-{
-        dump_printf(": unhandled!\n");
-        return 0;
-}
-
-static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
-{
-        if (!handler->process_sample_event)
-                handler->process_sample_event = process_event_stub;
-        if (!handler->process_mmap_event)
-                handler->process_mmap_event = process_event_stub;
-        if (!handler->process_comm_event)
-                handler->process_comm_event = process_event_stub;
-        if (!handler->process_fork_event)
-                handler->process_fork_event = process_event_stub;
-        if (!handler->process_exit_event)
-                handler->process_exit_event = process_event_stub;
-        if (!handler->process_lost_event)
-                handler->process_lost_event = process_event_stub;
-        if (!handler->process_read_event)
-                handler->process_read_event = process_event_stub;
-        if (!handler->process_throttle_event)
-                handler->process_throttle_event = process_event_stub;
-        if (!handler->process_unthrottle_event)
-                handler->process_unthrottle_event = process_event_stub;
-}
-
-static const char *event__name[] = {
-        [0]                      = "TOTAL",
-        [PERF_RECORD_MMAP]       = "MMAP",
-        [PERF_RECORD_LOST]       = "LOST",
-        [PERF_RECORD_COMM]       = "COMM",
-        [PERF_RECORD_EXIT]       = "EXIT",
-        [PERF_RECORD_THROTTLE]   = "THROTTLE",
-        [PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
-        [PERF_RECORD_FORK]       = "FORK",
-        [PERF_RECORD_READ]       = "READ",
-        [PERF_RECORD_SAMPLE]     = "SAMPLE",
-};
-
-unsigned long event__total[PERF_RECORD_MAX];
-
-void event__print_totals(void)
-{
-        int i;
-        for (i = 0; i < PERF_RECORD_MAX; ++i)
-                pr_info("%10s events: %10ld\n",
-                        event__name[i], event__total[i]);
-}
-
-static int process_event(event_t *event, struct perf_session *session,
-                         struct perf_event_ops *ops,
-                         unsigned long offset, unsigned long head)
-{
-        trace_event(event);
-
-        if (event->header.type < PERF_RECORD_MAX) {
-                dump_printf("%p [%p]: PERF_RECORD_%s",
-                            (void *)(offset + head),
-                            (void *)(long)(event->header.size),
-                            event__name[event->header.type]);
-                ++event__total[0];
-                ++event__total[event->header.type];
-        }
-
-        switch (event->header.type) {
-        case PERF_RECORD_SAMPLE:
-                return ops->process_sample_event(event, session);
-        case PERF_RECORD_MMAP:
-                return ops->process_mmap_event(event, session);
-        case PERF_RECORD_COMM:
-                return ops->process_comm_event(event, session);
-        case PERF_RECORD_FORK:
-                return ops->process_fork_event(event, session);
-        case PERF_RECORD_EXIT:
-                return ops->process_exit_event(event, session);
-        case PERF_RECORD_LOST:
-                return ops->process_lost_event(event, session);
-        case PERF_RECORD_READ:
-                return ops->process_read_event(event, session);
-        case PERF_RECORD_THROTTLE:
-                return ops->process_throttle_event(event, session);
-        case PERF_RECORD_UNTHROTTLE:
-                return ops->process_unthrottle_event(event, session);
-        default:
-                ops->total_unknown++;
-                return -1;
-        }
-}
-
-int perf_header__read_build_ids(int input, u64 offset, u64 size)
-{
-        struct build_id_event bev;
-        char filename[PATH_MAX];
-        u64 limit = offset + size;
-        int err = -1;
-
-        while (offset < limit) {
-                struct dso *dso;
-                ssize_t len;
-
-                if (read(input, &bev, sizeof(bev)) != sizeof(bev))
-                        goto out;
-
-                len = bev.header.size - sizeof(bev);
-                if (read(input, filename, len) != len)
-                        goto out;
-
-                dso = dsos__findnew(filename);
-                if (dso != NULL)
-                        dso__set_build_id(dso, &bev.build_id);
-
-                offset += bev.header.size;
-        }
-        err = 0;
-out:
-        return err;
-}
-
-static struct thread *perf_session__register_idle_thread(struct perf_session *self)
-{
-        struct thread *thread = perf_session__findnew(self, 0);
-
-        if (!thread || thread__set_comm(thread, "swapper")) {
-                pr_err("problem inserting idle task.\n");
-                thread = NULL;
-        }
-
-        return thread;
-}
-
-int perf_session__process_events(struct perf_session *self,
-                                 struct perf_event_ops *ops)
-{
-        int err;
-        unsigned long head, shift;
-        unsigned long offset = 0;
-        size_t  page_size;
-        event_t *event;
-        uint32_t size;
-        char *buf;
-
-        if (perf_session__register_idle_thread(self) == NULL)
-                return -ENOMEM;
-
-        perf_event_ops__fill_defaults(ops);
-
-        page_size = getpagesize();
-
-        head = self->header.data_offset;
-        self->sample_type = perf_header__sample_type(&self->header);
-
-        err = -EINVAL;
-        if (ops->sample_type_check && ops->sample_type_check(self) < 0)
-                goto out_err;
-
-        if (!ops->full_paths) {
-                char bf[PATH_MAX];
-
-                if (getcwd(bf, sizeof(bf)) == NULL) {
-                        err = -errno;
-out_getcwd_err:
-                        pr_err("failed to get the current directory\n");
-                        goto out_err;
-                }
-                self->cwd = strdup(bf);
-                if (self->cwd == NULL) {
-                        err = -ENOMEM;
-                        goto out_getcwd_err;
-                }
-                self->cwdlen = strlen(self->cwd);
-        }
-
-        shift = page_size * (head / page_size);
-        offset += shift;
-        head -= shift;
-
-remap:
-        buf = mmap(NULL, page_size * self->mmap_window, PROT_READ,
-                   MAP_SHARED, self->fd, offset);
-        if (buf == MAP_FAILED) {
-                pr_err("failed to mmap file\n");
-                err = -errno;
-                goto out_err;
-        }
-
-more:
-        event = (event_t *)(buf + head);
-
-        size = event->header.size;
-        if (!size)
-                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);
-
-                offset += shift;
-                head -= shift;
-                goto remap;
-        }
-
-        size = event->header.size;
-
-        dump_printf("\n%p [%p]: event: %d\n",
-                        (void *)(offset + head),
-                        (void *)(long)event->header.size,
-                        event->header.type);
-
-        if (!size || process_event(event, self, ops, offset, head) < 0) {
-
-                dump_printf("%p [%p]: skipping unknown header type: %d\n",
-                        (void *)(offset + head),
-                        (void *)(long)(event->header.size),
-                        event->header.type);
-
-                /*
-                 * assume we lost track of the stream, check alignment, and
-                 * increment a single u64 in the hope to catch on again 'soon'.
-                 */
-
-                if (unlikely(head & 7))
-                        head &= ~7ULL;
-
-                size = 8;
-        }
-
-        head += size;
-
-        if (offset + head >= self->header.data_offset + self->header.data_size)
-                goto done;
-
-        if (offset + head < self->size)
-                goto more;
-
-done:
-        err = 0;
-out_err:
-        return err;
-}
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 28d520d5a1fb..0905600c3851 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -9,6 +9,7 @@
 #include "color.h"
 #include "event.h"
 #include "debug.h"
+#include "util.h"
 
 int verbose = 0;
 int dump_trace = 0;
diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c
index 06b73ee02c49..a88fefc0cc0a 100644
--- a/tools/perf/util/debugfs.c
+++ b/tools/perf/util/debugfs.c
@@ -106,16 +106,14 @@ int debugfs_valid_entry(const char *path)
         return 0;
 }
 
-/* mount the debugfs somewhere */
+/* mount the debugfs somewhere if it's not mounted */
 
-int debugfs_mount(const char *mountpoint)
+char *debugfs_mount(const char *mountpoint)
 {
-        char mountcmd[128];
-
         /* see if it's already mounted */
         if (debugfs_find_mountpoint()) {
                 debugfs_premounted = 1;
-                return 0;
+                return debugfs_mountpoint;
         }
 
         /* if not mounted and no argument */
@@ -127,13 +125,14 @@ int debugfs_mount(const char *mountpoint)
                         mountpoint = "/sys/kernel/debug";
         }
 
+        if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
+                return NULL;
+
         /* save the mountpoint */
         strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
+        debugfs_found = 1;
 
-        /* mount it */
-        snprintf(mountcmd, sizeof(mountcmd),
-                 "/bin/mount -t debugfs debugfs %s", mountpoint);
-        return system(mountcmd);
+        return debugfs_mountpoint;
 }
 
 /* umount the debugfs */
diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h
index 3cd14f9ae784..83a02879745f 100644
--- a/tools/perf/util/debugfs.h
+++ b/tools/perf/util/debugfs.h
@@ -15,7 +15,7 @@
 extern const char *debugfs_find_mountpoint(void);
 extern int debugfs_valid_mountpoint(const char *debugfs);
 extern int debugfs_valid_entry(const char *path);
-extern int debugfs_mount(const char *mountpoint);
+extern char *debugfs_mount(const char *mountpoint);
 extern int debugfs_umount(void);
 extern int debugfs_write(const char *entry, const char *value);
 extern int debugfs_read(const char *entry, char *buffer, size_t size);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bb0fd6da2d56..705ec63548b4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -8,8 +8,7 @@
 #include "thread.h"
 
 static pid_t event__synthesize_comm(pid_t pid, int full,
-                                    int (*process)(event_t *event,
-                                                   struct perf_session *session),
+                                    event__handler_t process,
                                     struct perf_session *session)
 {
         event_t ev;
@@ -91,8 +90,7 @@ out_failure:
 }
 
 static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
-                                         int (*process)(event_t *event,
-                                                        struct perf_session *session),
+                                         event__handler_t process,
                                          struct perf_session *session)
 {
         char filename[PATH_MAX];
@@ -112,7 +110,10 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
         while (1) {
                 char bf[BUFSIZ], *pbf = bf;
                 event_t ev = {
-                        .header = { .type = PERF_RECORD_MMAP },
+                        .header = {
+                                .type = PERF_RECORD_MMAP,
+                                .misc = 0, /* Just like the kernel, see kernel/perf_event.c __perf_event_mmap */
+                         },
                 };
                 int n;
                 size_t size;
@@ -156,9 +157,38 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid,
         return 0;
 }
 
-int event__synthesize_thread(pid_t pid,
-                             int (*process)(event_t *event,
-                                            struct perf_session *session),
+int event__synthesize_modules(event__handler_t process,
+                              struct perf_session *session)
+{
+        struct rb_node *nd;
+
+        for (nd = rb_first(&session->kmaps.maps[MAP__FUNCTION]);
+             nd; nd = rb_next(nd)) {
+                event_t ev;
+                size_t size;
+                struct map *pos = rb_entry(nd, struct map, rb_node);
+
+                if (pos->dso->kernel)
+                        continue;
+
+                size = ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
+                memset(&ev, 0, sizeof(ev));
+                ev.mmap.header.misc = 1; /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
+                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;
+
+                memcpy(ev.mmap.filename, pos->dso->long_name,
+                       pos->dso->long_name_len + 1);
+                process(&ev, session);
+        }
+
+        return 0;
+}
+
+int event__synthesize_thread(pid_t pid, event__handler_t process,
                              struct perf_session *session)
 {
         pid_t tgid = event__synthesize_comm(pid, 1, process, session);
@@ -167,8 +197,7 @@ int event__synthesize_thread(pid_t pid,
         return event__synthesize_mmap_events(pid, tgid, process, session);
 }
 
-void event__synthesize_threads(int (*process)(event_t *event,
-                                              struct perf_session *session),
+void event__synthesize_threads(event__handler_t process,
                                struct perf_session *session)
 {
         DIR *proc;
@@ -189,6 +218,59 @@ void event__synthesize_threads(int (*process)(event_t *event,
         closedir(proc);
 }
 
+struct process_symbol_args {
+        const char *name;
+        u64        start;
+};
+
+static int find_symbol_cb(void *arg, const char *name, char type, u64 start)
+{
+        struct process_symbol_args *args = arg;
+
+        /*
+         * Must be a function or at least an alias, as in PARISC64, where "_text" is
+         * an 'A' to the same address as "_stext".
+         */
+        if (!(symbol_type__is_a(type, MAP__FUNCTION) ||
+              type == 'A') || strcmp(name, args->name))
+                return 0;
+
+        args->start = start;
+        return 1;
+}
+
+int event__synthesize_kernel_mmap(event__handler_t process,
+                                  struct perf_session *session,
+                                  const char *symbol_name)
+{
+        size_t size;
+        event_t ev = {
+                .header = {
+                        .type = PERF_RECORD_MMAP,
+                        .misc = 1, /* kernel uses 0 for user space maps, see kernel/perf_event.c __perf_event_mmap */
+                },
+        };
+        /*
+         * 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, };
+
+        if (kallsyms__parse("/proc/kallsyms", &args, find_symbol_cb) <= 0)
+                return -ENOENT;
+
+        size = snprintf(ev.mmap.filename, sizeof(ev.mmap.filename),
+                        "[kernel.kallsyms.%s]", 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 = session->vmlinux_maps[MAP__FUNCTION]->start;
+        ev.mmap.len   = session->vmlinux_maps[MAP__FUNCTION]->end - ev.mmap.start ;
+
+        return process(&ev, session);
+}
+
 static void thread__comm_adjust(struct thread *self)
 {
         char *comm = self->comm;
@@ -240,22 +322,88 @@ int event__process_lost(event_t *self, struct perf_session *session)
 
 int event__process_mmap(event_t *self, struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, self->mmap.pid);
-        struct map *map = map__new(&self->mmap, MAP__FUNCTION,
-                                   session->cwd, session->cwdlen);
+        struct thread *thread;
+        struct map *map;
+
+        dump_printf(" %d/%d: [%#Lx(%#Lx) @ %#Lx]: %s\n",
+                    self->mmap.pid, self->mmap.tid, self->mmap.start,
+                    self->mmap.len, self->mmap.pgoff, self->mmap.filename);
+
+        if (self->mmap.pid == 0) {
+                static const char kmmap_prefix[] = "[kernel.kallsyms.";
+
+                if (self->mmap.filename[0] == '/') {
+                        char short_module_name[1024];
+                        char *name = strrchr(self->mmap.filename, '/'), *dot;
+
+                        if (name == NULL)
+                                goto out_problem;
+
+                        ++name; /* skip / */
+                        dot = strrchr(name, '.');
+                        if (dot == NULL)
+                                goto out_problem;
+
+                        snprintf(short_module_name, sizeof(short_module_name),
+                                 "[%.*s]", (int)(dot - name), name);
+                        strxfrchar(short_module_name, '-', '_');
+
+                        map = perf_session__new_module_map(session,
+                                                           self->mmap.start,
+                                                           self->mmap.filename);
+                        if (map == NULL)
+                                goto out_problem;
+
+                        name = strdup(short_module_name);
+                        if (name == NULL)
+                                goto out_problem;
+
+                        map->dso->short_name = name;
+                        map->end = map->start + self->mmap.len;
+                } else if (memcmp(self->mmap.filename, kmmap_prefix,
+                                sizeof(kmmap_prefix) - 1) == 0) {
+                        const char *symbol_name = (self->mmap.filename +
+                                                   sizeof(kmmap_prefix) - 1);
+                        /*
+                         * Should be there already, from the build-id table in
+                         * the header.
+                         */
+                        struct dso *kernel = __dsos__findnew(&dsos__kernel,
+                                                             "[kernel.kallsyms]");
+                        if (kernel == NULL)
+                                goto out_problem;
+
+                        kernel->kernel = 1;
+                        if (__perf_session__create_kernel_maps(session, kernel) < 0)
+                                goto out_problem;
+
+                        session->vmlinux_maps[MAP__FUNCTION]->start = self->mmap.start;
+                        session->vmlinux_maps[MAP__FUNCTION]->end   = self->mmap.start + self->mmap.len;
+                        /*
+                         * Be a bit paranoid here, some perf.data file came with
+                         * a zero sized synthesized MMAP event for the kernel.
+                         */
+                        if (session->vmlinux_maps[MAP__FUNCTION]->end == 0)
+                                session->vmlinux_maps[MAP__FUNCTION]->end = ~0UL;
+
+                        perf_session__set_kallsyms_ref_reloc_sym(session, symbol_name,
+                                                                 self->mmap.pgoff);
+                }
+                return 0;
+        }
 
-        dump_printf(" %d/%d: [%p(%p) @ %p]: %s\n",
-                    self->mmap.pid, self->mmap.tid,
-                    (void *)(long)self->mmap.start,
-                    (void *)(long)self->mmap.len,
-                    (void *)(long)self->mmap.pgoff,
-                    self->mmap.filename);
+        thread = perf_session__findnew(session, self->mmap.pid);
+        map = map__new(&self->mmap, MAP__FUNCTION,
+                       session->cwd, session->cwdlen);
 
         if (thread == NULL || map == NULL)
-                dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
-        else
-                thread__insert_map(thread, map);
+                goto out_problem;
 
+        thread__insert_map(thread, map);
+        return 0;
+
+out_problem:
+        dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
         return 0;
 }
 
@@ -284,26 +432,24 @@ int event__process_task(event_t *self, struct perf_session *session)
         return 0;
 }
 
-void thread__find_addr_location(struct thread *self,
-                                struct perf_session *session, u8 cpumode,
-                                enum map_type type, u64 addr,
-                                struct addr_location *al,
-                                symbol_filter_t filter)
+void thread__find_addr_map(struct thread *self,
+                           struct perf_session *session, u8 cpumode,
+                           enum map_type type, u64 addr,
+                           struct addr_location *al)
 {
         struct map_groups *mg = &self->mg;
 
         al->thread = self;
         al->addr = addr;
 
-        if (cpumode & PERF_RECORD_MISC_KERNEL) {
+        if (cpumode == PERF_RECORD_MISC_KERNEL) {
                 al->level = 'k';
                 mg = &session->kmaps;
-        } else if (cpumode & PERF_RECORD_MISC_USER)
+        } else if (cpumode == PERF_RECORD_MISC_USER)
                 al->level = '.';
         else {
                 al->level = 'H';
                 al->map = NULL;
-                al->sym = NULL;
                 return;
         }
 try_again:
@@ -322,11 +468,21 @@ try_again:
                         mg = &session->kmaps;
                         goto try_again;
                 }
-                al->sym = NULL;
-        } else {
+        } else
                 al->addr = al->map->map_ip(al->map, al->addr);
-                al->sym = map__find_symbol(al->map, session, al->addr, filter);
-        }
+}
+
+void thread__find_addr_location(struct thread *self,
+                                struct perf_session *session, u8 cpumode,
+                                enum map_type type, u64 addr,
+                                struct addr_location *al,
+                                symbol_filter_t filter)
+{
+        thread__find_addr_map(self, session, cpumode, type, addr, al);
+        if (al->map != NULL)
+                al->sym = map__find_symbol(al->map, al->addr, filter);
+        else
+                al->sym = NULL;
 }
 
 static void dso__calc_col_width(struct dso *self)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 690a96d0467c..50a7132887f5 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -1,10 +1,10 @@
 #ifndef __PERF_RECORD_H
 #define __PERF_RECORD_H
 
+#include <limits.h>
+
 #include "../perf.h"
-#include "util.h"
-#include <linux/list.h>
-#include <linux/rbtree.h>
+#include "map.h"
 
 /*
  * PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
@@ -101,74 +101,19 @@ struct events_stats {
 
 void event__print_totals(void);
 
-enum map_type {
-        MAP__FUNCTION = 0,
-        MAP__VARIABLE,
-};
-
-#define MAP__NR_TYPES (MAP__VARIABLE + 1)
-
-struct map {
-        union {
-                struct rb_node  rb_node;
-                struct list_head node;
-        };
-        u64                     start;
-        u64                     end;
-        enum map_type           type;
-        u64                     pgoff;
-        u64                     (*map_ip)(struct map *, u64);
-        u64                     (*unmap_ip)(struct map *, u64);
-        struct dso              *dso;
-};
-
-static inline u64 map__map_ip(struct map *map, u64 ip)
-{
-        return ip - map->start + map->pgoff;
-}
-
-static inline u64 map__unmap_ip(struct map *map, u64 ip)
-{
-        return ip + map->start - map->pgoff;
-}
-
-static inline u64 identity__map_ip(struct map *map __used, u64 ip)
-{
-        return ip;
-}
-
-struct symbol;
-
-typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
-
-void map__init(struct map *self, enum map_type type,
-               u64 start, u64 end, u64 pgoff, struct dso *dso);
-struct map *map__new(struct mmap_event *event, enum map_type,
-                     char *cwd, int cwdlen);
-void map__delete(struct map *self);
-struct map *map__clone(struct map *self);
-int map__overlap(struct map *l, struct map *r);
-size_t map__fprintf(struct map *self, FILE *fp);
-
 struct perf_session;
 
-int map__load(struct map *self, struct perf_session *session,
-              symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *self, struct perf_session *session,
-                                u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
-                                        struct perf_session *session,
-                                        symbol_filter_t filter);
-void map__fixup_start(struct map *self);
-void map__fixup_end(struct map *self);
-
-int event__synthesize_thread(pid_t pid,
-                             int (*process)(event_t *event,
-                                            struct perf_session *session),
+typedef int (*event__handler_t)(event_t *event, struct perf_session *session);
+
+int event__synthesize_thread(pid_t pid, event__handler_t process,
                              struct perf_session *session);
-void event__synthesize_threads(int (*process)(event_t *event,
-                                              struct perf_session *session),
+void event__synthesize_threads(event__handler_t process,
                                struct perf_session *session);
+int event__synthesize_kernel_mmap(event__handler_t process,
+                                  struct perf_session *session,
+                                  const char *symbol_name);
+int event__synthesize_modules(event__handler_t process,
+                              struct perf_session *session);
 
 int event__process_comm(event_t *self, struct perf_session *session);
 int event__process_lost(event_t *self, struct perf_session *session);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8a0bca55106f..6c9aa16ee51f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,8 +1,12 @@
+#define _FILE_OFFSET_BITS 64
+
 #include <sys/types.h>
+#include <byteswap.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <linux/list.h>
+#include <linux/kernel.h>
 
 #include "util.h"
 #include "header.h"
@@ -105,24 +109,28 @@ struct perf_trace_event_type {
 static int event_count;
 static struct perf_trace_event_type *events;
 
-void perf_header__push_event(u64 id, const char *name)
+int perf_header__push_event(u64 id, const char *name)
 {
         if (strlen(name) > MAX_EVENT_NAME)
                 pr_warning("Event %s will be truncated\n", name);
 
         if (!events) {
                 events = malloc(sizeof(struct perf_trace_event_type));
-                if (!events)
-                        die("nomem");
+                if (events == NULL)
+                        return -ENOMEM;
         } else {
-                events = realloc(events, (event_count + 1) * sizeof(struct perf_trace_event_type));
-                if (!events)
-                        die("nomem");
+                struct perf_trace_event_type *nevents;
+
+                nevents = realloc(events, (event_count + 1) * sizeof(*events));
+                if (nevents == NULL)
+                        return -ENOMEM;
+                events = nevents;
         }
         memset(&events[event_count], 0, sizeof(struct perf_trace_event_type));
         events[event_count].event_id = id;
         strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1);
         event_count++;
+        return 0;
 }
 
 char *perf_header__find_event(u64 id)
@@ -169,31 +177,48 @@ static int do_write(int fd, const void *buf, size_t size)
         return 0;
 }
 
-static int __dsos__write_buildid_table(struct list_head *head, int fd)
+#define NAME_ALIGN 64
+
+static int write_padded(int fd, const void *bf, size_t count,
+                        size_t count_aligned)
 {
-#define NAME_ALIGN      64
-        struct dso *pos;
         static const char zero_buf[NAME_ALIGN];
+        int err = do_write(fd, bf, count);
+
+        if (!err)
+                err = do_write(fd, zero_buf, count_aligned - count);
+
+        return err;
+}
 
-        list_for_each_entry(pos, head, node) {
+#define dsos__for_each_with_build_id(pos, head) \
+        list_for_each_entry(pos, head, node)    \
+                if (!pos->has_build_id)         \
+                        continue;               \
+                else
+
+static int __dsos__write_buildid_table(struct list_head *head, u16 misc, int fd)
+{
+        struct dso *pos;
+
+        dsos__for_each_with_build_id(pos, head) {
                 int err;
                 struct build_id_event b;
                 size_t len;
 
-                if (!pos->has_build_id)
+                if (!pos->hit)
                         continue;
                 len = pos->long_name_len + 1;
                 len = ALIGN(len, NAME_ALIGN);
                 memset(&b, 0, sizeof(b));
                 memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
+                b.header.misc = misc;
                 b.header.size = sizeof(b) + len;
                 err = do_write(fd, &b, sizeof(b));
                 if (err < 0)
                         return err;
-                err = do_write(fd, pos->long_name, pos->long_name_len + 1);
-                if (err < 0)
-                        return err;
-                err = do_write(fd, zero_buf, len - pos->long_name_len - 1);
+                err = write_padded(fd, pos->long_name,
+                                   pos->long_name_len + 1, len);
                 if (err < 0)
                         return err;
         }
@@ -203,12 +228,143 @@ static int __dsos__write_buildid_table(struct list_head *head, int fd)
 
 static int dsos__write_buildid_table(int fd)
 {
-        int err = __dsos__write_buildid_table(&dsos__kernel, fd);
+        int err = __dsos__write_buildid_table(&dsos__kernel,
+                                              PERF_RECORD_MISC_KERNEL, fd);
         if (err == 0)
-                err = __dsos__write_buildid_table(&dsos__user, fd);
+                err = __dsos__write_buildid_table(&dsos__user,
+                                                  PERF_RECORD_MISC_USER, fd);
         return err;
 }
 
+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),
+             *linkname = malloc(size), *targetname;
+        int len, err = -1;
+
+        if (filename == NULL || linkname == NULL)
+                goto out_free;
+
+        len = snprintf(filename, size, "%s%s%s",
+                       debugdir, is_kallsyms ? "/" : "", name);
+        if (mkdir_p(filename, 0755))
+                goto out_free;
+
+        snprintf(filename + len, sizeof(filename) - len, "/%s", sbuild_id);
+
+        if (access(filename, F_OK)) {
+                if (is_kallsyms) {
+                         if (copyfile("/proc/kallsyms", filename))
+                                goto out_free;
+                } else if (link(name, filename) && copyfile(name, filename))
+                        goto out_free;
+        }
+
+        len = snprintf(linkname, size, "%s/.build-id/%.2s",
+                       debugdir, sbuild_id);
+
+        if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+                goto out_free;
+
+        snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+        targetname = filename + strlen(debugdir) - 5;
+        memcpy(targetname, "../..", 5);
+
+        if (symlink(targetname, linkname) == 0)
+                err = 0;
+out_free:
+        free(filename);
+        free(linkname);
+        return err;
+}
+
+static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+                                 const char *name, const char *debugdir,
+                                 bool is_kallsyms)
+{
+        char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+        build_id__sprintf(build_id, build_id_size, sbuild_id);
+
+        return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
+}
+
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
+{
+        const size_t size = PATH_MAX;
+        char *filename = malloc(size),
+             *linkname = malloc(size);
+        int err = -1;
+
+        if (filename == NULL || linkname == NULL)
+                goto out_free;
+
+        snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+                 debugdir, sbuild_id, sbuild_id + 2);
+
+        if (access(linkname, F_OK))
+                goto out_free;
+
+        if (readlink(linkname, filename, size) < 0)
+                goto out_free;
+
+        if (unlink(linkname))
+                goto out_free;
+
+        /*
+         * Since the link is relative, we must make it absolute:
+         */
+        snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+                 debugdir, sbuild_id, filename);
+
+        if (unlink(linkname))
+                goto out_free;
+
+        err = 0;
+out_free:
+        free(filename);
+        free(linkname);
+        return err;
+}
+
+static int dso__cache_build_id(struct dso *self, const char *debugdir)
+{
+        bool is_kallsyms = self->kernel && self->long_name[0] != '/';
+
+        return build_id_cache__add_b(self->build_id, sizeof(self->build_id),
+                                     self->long_name, debugdir, is_kallsyms);
+}
+
+static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+{
+        struct dso *pos;
+        int err = 0;
+
+        dsos__for_each_with_build_id(pos, head)
+                if (dso__cache_build_id(pos, debugdir))
+                        err = -1;
+
+        return err;
+}
+
+static int dsos__cache_build_ids(void)
+{
+        int err_kernel, err_user;
+        char debugdir[PATH_MAX];
+
+        snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"),
+                 DEBUG_CACHE_DIR);
+
+        if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+                return -1;
+
+        err_kernel = __dsos__cache_build_ids(&dsos__kernel, debugdir);
+        err_user   = __dsos__cache_build_ids(&dsos__user, debugdir);
+        return err_kernel || err_user ? -1 : 0;
+}
+
 static int perf_header__adds_write(struct perf_header *self, int fd)
 {
         int nr_sections;
@@ -217,7 +373,7 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
         u64 sec_start;
         int idx = 0, err;
 
-        if (dsos__read_build_ids())
+        if (dsos__read_build_ids(true))
                 perf_header__set_feat(self, HEADER_BUILD_ID);
 
         nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
@@ -257,7 +413,9 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
                         pr_debug("failed to write buildid table\n");
                         goto out_free;
                 }
-                buildid_sec->size = lseek(fd, 0, SEEK_CUR) - buildid_sec->offset;
+                buildid_sec->size = lseek(fd, 0, SEEK_CUR) -
+                                          buildid_sec->offset;
+                dsos__cache_build_ids();
         }
 
         lseek(fd, sec_start, SEEK_SET);
@@ -360,30 +518,43 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
         return 0;
 }
 
-static void do_read(int fd, void *buf, size_t size)
+static int do_read(int fd, void *buf, size_t size)
 {
         while (size) {
                 int ret = read(fd, buf, size);
 
-                if (ret < 0)
-                        die("failed to read");
-                if (ret == 0)
-                        die("failed to read: missing data");
+                if (ret <= 0)
+                        return -1;
 
                 size -= ret;
                 buf += ret;
         }
+
+        return 0;
+}
+
+static int perf_header__getbuffer64(struct perf_header *self,
+                                    int fd, void *buf, size_t size)
+{
+        if (do_read(fd, buf, size))
+                return -1;
+
+        if (self->needs_swap)
+                mem_bswap_64(buf, size);
+
+        return 0;
 }
 
 int perf_header__process_sections(struct perf_header *self, int fd,
                                   int (*process)(struct perf_file_section *self,
+                                                 struct perf_header *ph,
                                                  int feat, int fd))
 {
         struct perf_file_section *feat_sec;
         int nr_sections;
         int sec_size;
         int idx = 0;
-        int err = 0, feat = 1;
+        int err = -1, feat = 1;
 
         nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
         if (!nr_sections)
@@ -397,33 +568,45 @@ int perf_header__process_sections(struct perf_header *self, int fd,
 
         lseek(fd, self->data_offset + self->data_size, SEEK_SET);
 
-        do_read(fd, feat_sec, sec_size);
+        if (perf_header__getbuffer64(self, fd, feat_sec, sec_size))
+                goto out_free;
 
+        err = 0;
         while (idx < nr_sections && feat < HEADER_LAST_FEATURE) {
                 if (perf_header__has_feat(self, feat)) {
                         struct perf_file_section *sec = &feat_sec[idx++];
 
-                        err = process(sec, feat, fd);
+                        err = process(sec, self, feat, fd);
                         if (err < 0)
                                 break;
                 }
                 ++feat;
         }
-
+out_free:
         free(feat_sec);
         return err;
-};
+}
 
 int perf_file_header__read(struct perf_file_header *self,
                            struct perf_header *ph, int fd)
 {
         lseek(fd, 0, SEEK_SET);
-        do_read(fd, self, sizeof(*self));
 
-        if (self->magic     != PERF_MAGIC ||
-            self->attr_size != sizeof(struct perf_file_attr))
+        if (do_read(fd, self, sizeof(*self)) ||
+            memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
                 return -1;
 
+        if (self->attr_size != sizeof(struct perf_file_attr)) {
+                u64 attr_size = bswap_64(self->attr_size);
+
+                if (attr_size != sizeof(struct perf_file_attr))
+                        return -1;
+
+                mem_bswap_64(self, offsetof(struct perf_file_header,
+                                            adds_features));
+                ph->needs_swap = true;
+        }
+
         if (self->size != sizeof(*self)) {
                 /* Support the previous format */
                 if (self->size == offsetof(typeof(*self), adds_features))
@@ -433,19 +616,31 @@ int perf_file_header__read(struct perf_file_header *self,
         }
 
         memcpy(&ph->adds_features, &self->adds_features,
-               sizeof(self->adds_features));
+               sizeof(ph->adds_features));
+        /*
+         * FIXME: hack that assumes that if we need swap the perf.data file
+         * may be coming from an arch with a different word-size, ergo different
+         * DEFINE_BITMAP format, investigate more later, but for now its mostly
+         * safe to assume that we have a build-id section. Trace files probably
+         * have several other issues in this realm anyway...
+         */
+        if (ph->needs_swap) {
+                memset(&ph->adds_features, 0, sizeof(ph->adds_features));
+                perf_header__set_feat(ph, HEADER_BUILD_ID);
+        }
 
         ph->event_offset = self->event_types.offset;
-        ph->event_size   = self->event_types.size;
-        ph->data_offset  = self->data.offset;
+        ph->event_size   = self->event_types.size;
+        ph->data_offset  = self->data.offset;
         ph->data_size    = self->data.size;
         return 0;
 }
 
 static int perf_file_section__process(struct perf_file_section *self,
+                                      struct perf_header *ph,
                                       int feat, int fd)
 {
-        if (lseek(fd, self->offset, SEEK_SET) < 0) {
+        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);
                 return 0;
@@ -457,7 +652,7 @@ static int perf_file_section__process(struct perf_file_section *self,
                 break;
 
         case HEADER_BUILD_ID:
-                if (perf_header__read_build_ids(fd, self->offset, self->size))
+                if (perf_header__read_build_ids(ph, fd, self->offset, self->size))
                         pr_debug("Failed to read buildids, continuing...\n");
                 break;
         default:
@@ -469,7 +664,7 @@ static int perf_file_section__process(struct perf_file_section *self,
 
 int perf_header__read(struct perf_header *self, int fd)
 {
-        struct perf_file_header f_header;
+        struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
         u64                     f_id;
         int nr_attrs, nr_ids, i, j;
@@ -486,7 +681,9 @@ int perf_header__read(struct perf_header *self, int fd)
                 struct perf_header_attr *attr;
                 off_t tmp;
 
-                do_read(fd, &f_attr, sizeof(f_attr));
+                if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr)))
+                        goto out_errno;
+
                 tmp = lseek(fd, 0, SEEK_CUR);
 
                 attr = perf_header_attr__new(&f_attr.attr);
@@ -497,7 +694,8 @@ int perf_header__read(struct perf_header *self, int fd)
                 lseek(fd, f_attr.ids.offset, SEEK_SET);
 
                 for (j = 0; j < nr_ids; j++) {
-                        do_read(fd, &f_id, sizeof(f_id));
+                        if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id)))
+                                goto out_errno;
 
                         if (perf_header_attr__add_id(attr, f_id) < 0) {
                                 perf_header_attr__delete(attr);
@@ -517,7 +715,9 @@ int perf_header__read(struct perf_header *self, int fd)
                 events = malloc(f_header.event_types.size);
                 if (events == NULL)
                         return -ENOMEM;
-                do_read(fd, events, f_header.event_types.size);
+                if (perf_header__getbuffer64(self, fd, events,
+                                             f_header.event_types.size))
+                        goto out_errno;
                 event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
         }
 
@@ -527,6 +727,8 @@ int perf_header__read(struct perf_header *self, int fd)
 
         self->frozen = 1;
         return 0;
+out_errno:
+        return -errno;
 }
 
 u64 perf_header__sample_type(struct perf_header *header)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d118d05d3abe..82a6af72d4cc 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -5,6 +5,7 @@
 #include <sys/types.h>
 #include <stdbool.h>
 #include "types.h"
+#include "event.h"
 
 #include <linux/bitmap.h>
 
@@ -52,6 +53,7 @@ struct perf_header {
         u64                     data_size;
         u64                     event_offset;
         u64                     event_size;
+        bool                    needs_swap;
         DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
 
@@ -64,7 +66,7 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit);
 int perf_header__add_attr(struct perf_header *self,
                           struct perf_header_attr *attr);
 
-void perf_header__push_event(u64 id, const char *name);
+int perf_header__push_event(u64 id, const char *name);
 char *perf_header__find_event(u64 id);
 
 struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr);
@@ -80,6 +82,11 @@ bool perf_header__has_feat(const struct perf_header *self, int feat);
 
 int perf_header__process_sections(struct perf_header *self, int fd,
                                   int (*process)(struct perf_file_section *self,
+                                                 struct perf_header *ph,
                                                  int feat, int fd));
 
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+                          const char *name, bool is_kallsyms);
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e8daf5ca6fd2..44408c2621cf 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -321,7 +321,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
                         new_depth_mask &= ~(1 << (depth - 1));
 
                 /*
-                 * But we keep the older depth mask for the line seperator
+                 * But we keep the older depth mask for the line separator
                  * to keep the level link until we reach the last child
                  */
                 ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h
new file mode 100644
index 000000000000..201f57397997
--- /dev/null
+++ b/tools/perf/util/include/linux/hash.h
@@ -0,0 +1,5 @@
+#include "../../../../include/linux/hash.h"
+
+#ifndef PERF_HASH_H
+#define PERF_HASH_H
+#endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 21c0274c02fa..f2611655ab51 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -101,5 +101,6 @@ simple_strtoul(const char *nptr, char **endptr, int base)
         eprintf(n, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
 #endif
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index c4d55a0da2ea..e509cd59c67d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -5,6 +5,11 @@
 #include <stdio.h>
 #include "debug.h"
 
+const char *map_type__name[MAP__NR_TYPES] = {
+        [MAP__FUNCTION] = "Functions",
+        [MAP__VARIABLE] = "Variables",
+};
+
 static inline int is_anon_memory(const char *filename)
 {
         return strcmp(filename, "//anon") == 0;
@@ -68,8 +73,13 @@ struct map *map__new(struct mmap_event *event, enum map_type type,
                 map__init(self, type, event->start, event->start + event->len,
                           event->pgoff, dso);
 
-                if (self->dso == vdso || anon)
+                if (anon) {
+set_identity:
                         self->map_ip = self->unmap_ip = identity__map_ip;
+                } else if (strcmp(filename, "[vdso]") == 0) {
+                        dso__set_loaded(dso, self->type);
+                        goto set_identity;
+                }
         }
         return self;
 out_delete:
@@ -104,8 +114,7 @@ void map__fixup_end(struct map *self)
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *self, struct perf_session *session,
-              symbol_filter_t filter)
+int map__load(struct map *self, symbol_filter_t filter)
 {
         const char *name = self->dso->long_name;
         int nr;
@@ -113,7 +122,7 @@ int map__load(struct map *self, struct perf_session *session,
         if (dso__loaded(self->dso, self->type))
                 return 0;
 
-        nr = dso__load(self->dso, self, session, filter);
+        nr = dso__load(self->dso, self, filter);
         if (nr < 0) {
                 if (self->dso->has_build_id) {
                         char sbuild_id[BUILD_ID_SIZE * 2 + 1];
@@ -144,24 +153,29 @@ int map__load(struct map *self, struct perf_session *session,
 
                 return -1;
         }
+        /*
+         * Only applies to the kernel, as its symtabs aren't relative like the
+         * module ones.
+         */
+        if (self->dso->kernel)
+                map__reloc_vmlinux(self);
 
         return 0;
 }
 
-struct symbol *map__find_symbol(struct map *self, struct perf_session *session,
-                                u64 addr, symbol_filter_t filter)
+struct symbol *map__find_symbol(struct map *self, u64 addr,
+                                symbol_filter_t filter)
 {
-        if (map__load(self, session, filter) < 0)
+        if (map__load(self, filter) < 0)
                 return NULL;
 
         return dso__find_symbol(self->dso, self->type, addr);
 }
 
 struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
-                                        struct perf_session *session,
                                         symbol_filter_t filter)
 {
-        if (map__load(self, session, filter) < 0)
+        if (map__load(self, filter) < 0)
                 return NULL;
 
         if (!dso__sorted_by_name(self->dso, self->type))
@@ -201,3 +215,23 @@ size_t map__fprintf(struct map *self, FILE *fp)
         return fprintf(fp, " %Lx-%Lx %Lx %s\n",
                        self->start, self->end, self->pgoff, self->dso->name);
 }
+
+/*
+ * objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
+ * map->dso->adjust_symbols==1 for ET_EXEC-like cases.
+ */
+u64 map__rip_2objdump(struct map *map, u64 rip)
+{
+        u64 addr = map->dso->adjust_symbols ?
+                        map->unmap_ip(map, rip) :       /* RIP -> IP */
+                        rip;
+        return addr;
+}
+
+u64 map__objdump_2ip(struct map *map, u64 addr)
+{
+        u64 ip = map->dso->adjust_symbols ?
+                        addr :
+                        map->unmap_ip(map, addr);       /* RIP -> IP */
+        return ip;
+}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
new file mode 100644
index 000000000000..b756368076c6
--- /dev/null
+++ b/tools/perf/util/map.h
@@ -0,0 +1,94 @@
+#ifndef __PERF_MAP_H
+#define __PERF_MAP_H
+
+#include <linux/compiler.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+enum map_type {
+        MAP__FUNCTION = 0,
+        MAP__VARIABLE,
+};
+
+#define MAP__NR_TYPES (MAP__VARIABLE + 1)
+
+extern const char *map_type__name[MAP__NR_TYPES];
+
+struct dso;
+struct ref_reloc_sym;
+struct map_groups;
+
+struct map {
+        union {
+                struct rb_node  rb_node;
+                struct list_head node;
+        };
+        u64                     start;
+        u64                     end;
+        enum map_type           type;
+        u64                     pgoff;
+
+        /* ip -> dso rip */
+        u64                     (*map_ip)(struct map *, u64);
+        /* dso rip -> ip */
+        u64                     (*unmap_ip)(struct map *, u64);
+
+        struct dso              *dso;
+};
+
+struct kmap {
+        struct ref_reloc_sym    *ref_reloc_sym;
+        struct map_groups       *kmaps;
+};
+
+static inline struct kmap *map__kmap(struct map *self)
+{
+        return (struct kmap *)(self + 1);
+}
+
+static inline u64 map__map_ip(struct map *map, u64 ip)
+{
+        return ip - map->start + map->pgoff;
+}
+
+static inline u64 map__unmap_ip(struct map *map, u64 ip)
+{
+        return ip + map->start - map->pgoff;
+}
+
+static inline u64 identity__map_ip(struct map *map __used, u64 ip)
+{
+        return ip;
+}
+
+
+/* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
+u64 map__rip_2objdump(struct map *map, u64 rip);
+u64 map__objdump_2ip(struct map *map, u64 addr);
+
+struct symbol;
+struct mmap_event;
+
+typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
+
+void map__init(struct map *self, enum map_type type,
+               u64 start, u64 end, u64 pgoff, struct dso *dso);
+struct map *map__new(struct mmap_event *event, enum map_type,
+                     char *cwd, int cwdlen);
+void map__delete(struct map *self);
+struct map *map__clone(struct map *self);
+int map__overlap(struct map *l, struct map *r);
+size_t map__fprintf(struct map *self, FILE *fp);
+
+int map__load(struct map *self, symbol_filter_t filter);
+struct symbol *map__find_symbol(struct map *self,
+                                u64 addr, symbol_filter_t filter);
+struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+                                        symbol_filter_t filter);
+void map__fixup_start(struct map *self);
+void map__fixup_end(struct map *self);
+
+void map__reloc_vmlinux(struct map *self);
+
+#endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index e5bc0fb016b2..05d0c5c2030c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -450,7 +450,8 @@ parse_single_tracepoint_event(char *sys_name,
 /* sys + ':' + event + ':' + flags*/
 #define MAX_EVOPT_LEN   (MAX_EVENT_LENGTH * 2 + 2 + 128)
 static enum event_result
-parse_subsystem_tracepoint_event(char *sys_name, char *flags)
+parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp,
+                                char *flags)
 {
         char evt_path[MAXPATHLEN];
         struct dirent *evt_ent;
@@ -474,6 +475,9 @@ parse_subsystem_tracepoint_event(char *sys_name, char *flags)
                     || !strcmp(evt_ent->d_name, "filter"))
                         continue;
 
+                if (!strglobmatch(evt_ent->d_name, evt_exp))
+                        continue;
+
                 len = snprintf(event_opt, MAX_EVOPT_LEN, "%s:%s%s%s", sys_name,
                                evt_ent->d_name, flags ? ":" : "",
                                flags ?: "");
@@ -522,9 +526,10 @@ static enum event_result parse_tracepoint_event(const char **strp,
         if (evt_length >= MAX_EVENT_LENGTH)
                 return EVT_FAILED;
 
-        if (!strcmp(evt_name, "*")) {
+        if (strpbrk(evt_name, "*?")) {
                 *strp = evt_name + evt_length;
-                return parse_subsystem_tracepoint_event(sys_name, flags);
+                return parse_multiple_tracepoint_event(sys_name, evt_name,
+                                                       flags);
         } else
                 return parse_single_tracepoint_event(sys_name, evt_name,
                                                      evt_length, flags,
@@ -753,11 +758,11 @@ modifier:
         return ret;
 }
 
-static void store_event_type(const char *orgname)
+static int store_event_type(const char *orgname)
 {
         char filename[PATH_MAX], *c;
         FILE *file;
-        int id;
+        int id, n;
 
         sprintf(filename, "%s/", debugfs_path);
         strncat(filename, orgname, strlen(orgname));
@@ -769,11 +774,14 @@ static void store_event_type(const char *orgname)
 
         file = fopen(filename, "r");
         if (!file)
-                return;
-        if (fscanf(file, "%i", &id) < 1)
-                die("cannot store event ID");
+                return 0;
+        n = fscanf(file, "%i", &id);
         fclose(file);
-        perf_header__push_event(id, orgname);
+        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)
@@ -782,7 +790,8 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u
         enum event_result ret;
 
         if (strchr(str, ':'))
-                store_event_type(str);
+                if (store_event_type(str) < 0)
+                        return -1;
 
         for (;;) {
                 if (nr_counters == MAX_COUNTERS)
@@ -835,11 +844,12 @@ int parse_filter(const struct option *opt __used, const char *str,
 }
 
 static const char * const event_type_descriptors[] = {
-        "",
         "Hardware event",
         "Software event",
         "Tracepoint event",
         "Hardware cache event",
+        "Raw hardware event descriptor",
+        "Hardware breakpoint",
 };
 
 /*
@@ -872,7 +882,7 @@ static void print_tracepoint_events(void)
                         snprintf(evt_path, MAXPATHLEN, "%s:%s",
                                  sys_dirent.d_name, evt_dirent.d_name);
                         printf("  %-42s [%s]\n", evt_path,
-                                event_type_descriptors[PERF_TYPE_TRACEPOINT+1]);
+                                event_type_descriptors[PERF_TYPE_TRACEPOINT]);
                 }
                 closedir(evt_dir);
         }
@@ -892,9 +902,7 @@ void print_events(void)
         printf("List of pre-defined events (to be used in -e):\n");
 
         for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) {
-                type = syms->type + 1;
-                if (type >= ARRAY_SIZE(event_type_descriptors))
-                        type = 0;
+                type = syms->type;
 
                 if (type != prev_type)
                         printf("\n");
@@ -919,17 +927,19 @@ void print_events(void)
                         for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
                                 printf("  %-42s [%s]\n",
                                         event_cache_name(type, op, i),
-                                        event_type_descriptors[4]);
+                                        event_type_descriptors[PERF_TYPE_HW_CACHE]);
                         }
                 }
         }
 
         printf("\n");
-        printf("  %-42s [raw hardware event descriptor]\n",
-                "rNNN");
+        printf("  %-42s [%s]\n",
+                "rNNN", event_type_descriptors[PERF_TYPE_RAW]);
         printf("\n");
 
-        printf("  %-42s [hardware breakpoint]\n", "mem:<addr>[:access]");
+        printf("  %-42s [%s]\n",
+                        "mem:<addr>[:access]",
+                        event_type_descriptors[PERF_TYPE_BREAKPOINT]);
         printf("\n");
 
         print_tracepoint_events();
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 29465d440043..53181dbfe4a8 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -37,6 +37,8 @@
 #include "string.h"
 #include "strlist.h"
 #include "debug.h"
+#include "cache.h"
+#include "color.h"
 #include "parse-events.h"  /* For debugfs_path */
 #include "probe-event.h"
 
@@ -62,6 +64,42 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
         return ret;
 }
 
+void 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 = (unsigned int)strtoul(ptr + 1, &tmp, 0);
+                if (*tmp == '+')
+                        lr->end = lr->start + (unsigned int)strtoul(tmp + 1,
+                                                                    &tmp, 0);
+                else if (*tmp == '-')
+                        lr->end = (unsigned int)strtoul(tmp + 1, &tmp, 0);
+                else
+                        lr->end = 0;
+                pr_debug("Line range is %u to %u\n", lr->start, lr->end);
+                if (lr->end && lr->start > lr->end)
+                        semantic_error("Start line must be smaller"
+                                       " than end line.");
+                if (*tmp != '\0')
+                        semantic_error("Tailing with invalid character '%d'.",
+                                       *tmp);
+                tmp = strndup(arg, (ptr - arg));
+        } else
+                tmp = strdup(arg);
+
+        if (strchr(tmp, '.'))
+                lr->file = tmp;
+        else
+                lr->function = tmp;
+}
+
 /* Check the name is good for event/group */
 static bool check_event_name(const char *name)
 {
@@ -81,14 +119,14 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         char c, nc = 0;
         /*
          * <Syntax>
-         * perf probe [EVENT=]SRC:LN
-         * perf probe [EVENT=]FUNC[+OFFS|%return][@SRC]
+         * perf probe [EVENT=]SRC[:LN|;PTN]
+         * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT]
          *
          * TODO:Group name support
          */
 
-        ptr = strchr(arg, '=');
-        if (ptr) {      /* Event name */
+        ptr = strpbrk(arg, ";=@+%");
+        if (ptr && *ptr == '=') {       /* Event name */
                 *ptr = '\0';
                 tmp = ptr + 1;
                 ptr = strchr(arg, ':');
@@ -101,7 +139,7 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
                 arg = tmp;
         }
 
-        ptr = strpbrk(arg, ":+@%");
+        ptr = strpbrk(arg, ";:+@%");
         if (ptr) {
                 nc = *ptr;
                 *ptr++ = '\0';
@@ -118,7 +156,11 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         while (ptr) {
                 arg = ptr;
                 c = nc;
-                ptr = strpbrk(arg, ":+@%");
+                if (c == ';') { /* Lazy pattern must be the last part */
+                        pp->lazy_line = strdup(arg);
+                        break;
+                }
+                ptr = strpbrk(arg, ";:+@%");
                 if (ptr) {
                         nc = *ptr;
                         *ptr++ = '\0';
@@ -127,13 +169,13 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
                 case ':':       /* Line number */
                         pp->line = strtoul(arg, &tmp, 0);
                         if (*tmp != '\0')
-                                semantic_error("There is non-digit charactor"
-                                                " in line number.");
+                                semantic_error("There is non-digit char"
+                                               " in line number.");
                         break;
                 case '+':       /* Byte offset from a symbol */
                         pp->offset = strtoul(arg, &tmp, 0);
                         if (*tmp != '\0')
-                                semantic_error("There is non-digit charactor"
+                                semantic_error("There is non-digit character"
                                                 " in offset.");
                         break;
                 case '@':       /* File name */
@@ -141,9 +183,6 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
                                 semantic_error("SRC@SRC is not allowed.");
                         pp->file = strdup(arg);
                         DIE_IF(pp->file == NULL);
-                        if (ptr)
-                                semantic_error("@SRC must be the last "
-                                               "option.");
                         break;
                 case '%':       /* Probe places */
                         if (strcmp(arg, "return") == 0) {
@@ -158,11 +197,18 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         }
 
         /* Exclusion check */
+        if (pp->lazy_line && pp->line)
+                semantic_error("Lazy pattern can't be used with line number.");
+
+        if (pp->lazy_line && pp->offset)
+                semantic_error("Lazy pattern can't be used with offset.");
+
         if (pp->line && pp->offset)
                 semantic_error("Offset can't be used with line number.");
 
-        if (!pp->line && pp->file && !pp->function)
-                semantic_error("File always requires line number.");
+        if (!pp->line && !pp->lazy_line && pp->file && !pp->function)
+                semantic_error("File always requires line number or "
+                               "lazy pattern.");
 
         if (pp->offset && !pp->function)
                 semantic_error("Offset requires an entry function.");
@@ -170,11 +216,13 @@ static void parse_perf_probe_probepoint(char *arg, struct probe_point *pp)
         if (pp->retprobe && !pp->function)
                 semantic_error("Return probe requires an entry function.");
 
-        if ((pp->offset || pp->line) && pp->retprobe)
-                semantic_error("Offset/Line can't be used with return probe.");
+        if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe)
+                semantic_error("Offset/Line/Lazy pattern can't be used with "
+                               "return probe.");
 
-        pr_debug("symbol:%s file:%s line:%d offset:%d, return:%d\n",
-                 pp->function, pp->file, pp->line, pp->offset, pp->retprobe);
+        pr_debug("symbol:%s file:%s line:%d offset:%d return:%d lazy:%s\n",
+                 pp->function, pp->file, pp->line, pp->offset, pp->retprobe,
+                 pp->lazy_line);
 }
 
 /* Parse perf-probe event definition */
@@ -272,6 +320,7 @@ int synthesize_perf_probe_point(struct probe_point *pp)
         int ret;
 
         pp->probes[0] = buf = zalloc(MAX_CMDLEN);
+        pp->found = 1;
         if (!buf)
                 die("Failed to allocate memory by zalloc.");
         if (pp->offset) {
@@ -294,6 +343,7 @@ int synthesize_perf_probe_point(struct probe_point *pp)
 error:
                 free(pp->probes[0]);
                 pp->probes[0] = NULL;
+                pp->found = 0;
         }
         return ret;
 }
@@ -368,7 +418,7 @@ static int open_kprobe_events(int flags, int mode)
         if (ret < 0) {
                 if (errno == ENOENT)
                         die("kprobe_events file does not exist -"
-                            " please rebuild with CONFIG_KPROBE_TRACER.");
+                            " please rebuild with CONFIG_KPROBE_EVENT.");
                 else
                         die("Could not open kprobe_events file: %s",
                             strerror(errno));
@@ -418,6 +468,8 @@ static void clear_probe_point(struct probe_point *pp)
                 free(pp->function);
         if (pp->file)
                 free(pp->file);
+        if (pp->lazy_line)
+                free(pp->lazy_line);
         for (i = 0; i < pp->nr_args; i++)
                 free(pp->args[i]);
         if (pp->args)
@@ -455,6 +507,9 @@ void show_perf_probe_events(void)
         struct strlist *rawlist;
         struct str_node *ent;
 
+        setup_pager();
+        memset(&pp, 0, sizeof(pp));
+
         fd = open_kprobe_events(O_RDONLY, 0);
         rawlist = get_trace_kprobe_event_rawlist(fd);
         close(fd);
@@ -675,3 +730,73 @@ void del_trace_kprobe_events(struct strlist *dellist)
         close(fd);
 }
 
+#define LINEBUF_SIZE 256
+#define NR_ADDITIONAL_LINES 2
+
+static void show_one_line(FILE *fp, unsigned 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, "%7u  %s", l, buf);
+                else
+                        color_fprintf(stdout, color, "         %s", buf);
+        }
+
+        while (strlen(buf) == LINEBUF_SIZE - 1 &&
+               buf[LINEBUF_SIZE - 2] != '\n') {
+                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);
+                }
+        }
+        return;
+error:
+        if (feof(fp))
+                die("Source file is shorter than expected.");
+        else
+                die("File read error: %s", strerror(errno));
+}
+
+void show_line_range(struct line_range *lr)
+{
+        unsigned int l = 1;
+        struct line_node *ln;
+        FILE *fp;
+
+        setup_pager();
+
+        if (lr->function)
+                fprintf(stdout, "<%s:%d>\n", lr->function,
+                        lr->start - lr->offset);
+        else
+                fprintf(stdout, "<%s:%d>\n", lr->file, lr->start);
+
+        fp = fopen(lr->path, "r");
+        if (fp == NULL)
+                die("Failed to open %s: %s", lr->path, strerror(errno));
+        /* Skip to starting line number */
+        while (l < lr->start)
+                show_one_line(fp, l++, true, false);
+
+        list_for_each_entry(ln, &lr->line_list, list) {
+                while (ln->line > l)
+                        show_one_line(fp, (l++) - lr->offset, false, false);
+                show_one_line(fp, (l++) - lr->offset, false, true);
+        }
+
+        if (lr->end == INT_MAX)
+                lr->end = l + NR_ADDITIONAL_LINES;
+        while (l < lr->end && !feof(fp))
+                show_one_line(fp, (l++) - lr->offset, false, false);
+
+        fclose(fp);
+}
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 7f1d499118c0..711287d4baea 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -5,6 +5,7 @@
 #include "probe-finder.h"
 #include "strlist.h"
 
+extern void parse_line_range_desc(const char *arg, struct line_range *lr);
 extern void parse_perf_probe_event(const char *str, struct probe_point *pp,
                                    bool *need_dwarf);
 extern int synthesize_perf_probe_point(struct probe_point *pp);
@@ -15,6 +16,7 @@ extern void add_trace_kprobe_events(struct probe_point *probes, int nr_probes,
                                     bool force_add);
 extern void del_trace_kprobe_events(struct strlist *dellist);
 extern void show_perf_probe_events(void);
+extern void show_line_range(struct line_range *lr);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX 1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 4b852c0d16a5..e77dc886760e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -32,21 +32,13 @@
 #include <stdarg.h>
 #include <ctype.h>
 
+#include "string.h"
 #include "event.h"
 #include "debug.h"
 #include "util.h"
 #include "probe-finder.h"
 
 
-/* Dwarf_Die Linkage to parent Die */
-struct die_link {
-        struct die_link *parent;        /* Parent die */
-        Dwarf_Die die;                  /* Current die */
-};
-
-static Dwarf_Debug __dw_debug;
-static Dwarf_Error __dw_error;
-
 /*
  * Generic dwarf analysis helpers
  */
@@ -113,256 +105,190 @@ static int strtailcmp(const char *s1, const char *s2)
         return 0;
 }
 
-/* Find the fileno of the target file. */
-static Dwarf_Unsigned cu_find_fileno(Dwarf_Die cu_die, const char *fname)
-{
-        Dwarf_Signed cnt, i;
-        Dwarf_Unsigned found = 0;
-        char **srcs;
-        int ret;
-
-        if (!fname)
-                return 0;
+/* Line number list operations */
 
-        ret = dwarf_srcfiles(cu_die, &srcs, &cnt, &__dw_error);
-        if (ret == DW_DLV_OK) {
-                for (i = 0; i < cnt && !found; i++) {
-                        if (strtailcmp(srcs[i], fname) == 0)
-                                found = i + 1;
-                        dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING);
-                }
-                for (; i < cnt; i++)
-                        dwarf_dealloc(__dw_debug, srcs[i], DW_DLA_STRING);
-                dwarf_dealloc(__dw_debug, srcs, DW_DLA_LIST);
+/* Add a line to line number list */
+static void line_list__add_line(struct list_head *head, unsigned int line)
+{
+        struct line_node *ln;
+        struct list_head *p;
+
+        /* Reverse search, because new line will be the last one */
+        list_for_each_entry_reverse(ln, head, list) {
+                if (ln->line < line) {
+                        p = &ln->list;
+                        goto found;
+                } else if (ln->line == line)    /* Already exist */
+                        return ;
         }
-        if (found)
-                pr_debug("found fno: %d\n", (int)found);
-        return found;
+        /* List is empty, or the smallest entry */
+        p = head;
+found:
+        pr_debug("line list: add a line %u\n", line);
+        ln = zalloc(sizeof(struct line_node));
+        DIE_IF(ln == NULL);
+        ln->line = line;
+        INIT_LIST_HEAD(&ln->list);
+        list_add(&ln->list, p);
 }
 
-/* Compare diename and tname */
-static int die_compare_name(Dwarf_Die dw_die, const char *tname)
+/* Check if the line in line number list */
+static int line_list__has_line(struct list_head *head, unsigned int line)
 {
-        char *name;
-        int ret;
-        ret = dwarf_diename(dw_die, &name, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK) {
-                ret = strcmp(tname, name);
-                dwarf_dealloc(__dw_debug, name, DW_DLA_STRING);
-        } else
-                ret = -1;
-        return ret;
-}
+        struct line_node *ln;
 
-/* Check the address is in the subprogram(function). */
-static int die_within_subprogram(Dwarf_Die sp_die, Dwarf_Addr addr,
-                                 Dwarf_Signed *offs)
-{
-        Dwarf_Addr lopc, hipc;
-        int ret;
+        /* Reverse search, because new line will be the last one */
+        list_for_each_entry(ln, head, list)
+                if (ln->line == line)
+                        return 1;
 
-        /* TODO: check ranges */
-        ret = dwarf_lowpc(sp_die, &lopc, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_NO_ENTRY)
-                return 0;
-        ret = dwarf_highpc(sp_die, &hipc, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        if (lopc <= addr && addr < hipc) {
-                *offs = addr - lopc;
-                return 1;
-        } else
-                return 0;
+        return 0;
 }
 
-/* Check the die is inlined function */
-static Dwarf_Bool die_inlined_subprogram(Dwarf_Die dw_die)
+/* Init line number list */
+static void line_list__init(struct list_head *head)
 {
-        /* TODO: check strictly */
-        Dwarf_Bool inl;
-        int ret;
+        INIT_LIST_HEAD(head);
+}
 
-        ret = dwarf_hasattr(dw_die, DW_AT_inline, &inl, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        return inl;
+/* Free line number list */
+static void line_list__free(struct list_head *head)
+{
+        struct line_node *ln;
+        while (!list_empty(head)) {
+                ln = list_first_entry(head, struct line_node, list);
+                list_del(&ln->list);
+                free(ln);
+        }
 }
 
-/* Get the offset of abstruct_origin */
-static Dwarf_Off die_get_abstract_origin(Dwarf_Die dw_die)
+/* Dwarf wrappers */
+
+/* Find the realpath of the target file. */
+static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Off cu_offs;
+        Dwarf_Files *files;
+        size_t nfiles, i;
+        const char *src;
         int ret;
 
-        ret = dwarf_attr(dw_die, DW_AT_abstract_origin, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = dwarf_formref(attr, &cu_offs, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-        return cu_offs;
+        if (!fname)
+                return NULL;
+
+        ret = dwarf_getsrcfiles(cu_die, &files, &nfiles);
+        if (ret != 0)
+                return NULL;
+
+        for (i = 0; i < nfiles; i++) {
+                src = dwarf_filesrc(files, i, NULL, NULL);
+                if (strtailcmp(src, fname) == 0)
+                        break;
+        }
+        return src;
 }
 
-/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
-static Dwarf_Addr die_get_entrypc(Dwarf_Die dw_die)
+struct __addr_die_search_param {
+        Dwarf_Addr      addr;
+        Dwarf_Die       *die_mem;
+};
+
+static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Addr addr;
-        Dwarf_Off offs;
-        Dwarf_Ranges *ranges;
-        Dwarf_Signed cnt;
-        int ret;
+        struct __addr_die_search_param *ad = data;
 
-        /* Try to get entry pc */
-        ret = dwarf_attr(dw_die, DW_AT_entry_pc, &attr, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK) {
-                ret = dwarf_formaddr(attr, &addr, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-                return addr;
+        if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+            dwarf_haspc(fn_die, ad->addr)) {
+                memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+                return DWARF_CB_ABORT;
         }
+        return DWARF_CB_OK;
+}
 
-        /* Try to get low pc */
-        ret = dwarf_lowpc(dw_die, &addr, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK)
-                return addr;
-
-        /* Try to get ranges */
-        ret = dwarf_attr(dw_die, DW_AT_ranges, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = dwarf_formref(attr, &offs, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = dwarf_get_ranges(__dw_debug, offs, &ranges, &cnt, NULL,
-                                &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        addr = ranges[0].dwr_addr1;
-        dwarf_ranges_dealloc(__dw_debug, ranges, cnt);
-        return addr;
+/* Search a real subprogram including this line, */
+static Dwarf_Die *die_get_real_subprogram(Dwarf_Die *cu_die, Dwarf_Addr addr,
+                                          Dwarf_Die *die_mem)
+{
+        struct __addr_die_search_param ad;
+        ad.addr = addr;
+        ad.die_mem = die_mem;
+        /* dwarf_getscopes can't find subprogram. */
+        if (!dwarf_getfuncs(cu_die, __die_search_func_cb, &ad, 0))
+                return NULL;
+        else
+                return die_mem;
 }
 
-/*
- * Search a Die from Die tree.
- * Note: cur_link->die should be deallocated in this function.
- */
-static int __search_die_tree(struct die_link *cur_link,
-                             int (*die_cb)(struct die_link *, void *),
-                             void *data)
+/* Similar to dwarf_getfuncs, but returns inlined_subroutine if exists. */
+static Dwarf_Die *die_get_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+                                     Dwarf_Die *die_mem)
 {
-        Dwarf_Die new_die;
-        struct die_link new_link;
+        Dwarf_Die child_die;
         int ret;
 
-        if (!die_cb)
-                return 0;
-
-        /* Check current die */
-        while (!(ret = die_cb(cur_link, data))) {
-                /* Check child die */
-                ret = dwarf_child(cur_link->die, &new_die, &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                if (ret == DW_DLV_OK) {
-                        new_link.parent = cur_link;
-                        new_link.die = new_die;
-                        ret = __search_die_tree(&new_link, die_cb, data);
-                        if (ret)
-                                break;
-                }
+        ret = dwarf_child(sp_die, die_mem);
+        if (ret != 0)
+                return NULL;
 
-                /* Move to next sibling */
-                ret = dwarf_siblingof(__dw_debug, cur_link->die, &new_die,
-                                      &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                dwarf_dealloc(__dw_debug, cur_link->die, DW_DLA_DIE);
-                cur_link->die = new_die;
-                if (ret == DW_DLV_NO_ENTRY)
-                        return 0;
-        }
-        dwarf_dealloc(__dw_debug, cur_link->die, DW_DLA_DIE);
-        return ret;
-}
+        do {
+                if (dwarf_tag(die_mem) == DW_TAG_inlined_subroutine &&
+                    dwarf_haspc(die_mem, addr))
+                        return die_mem;
 
-/* Search a die in its children's die tree */
-static int search_die_from_children(Dwarf_Die parent_die,
-                                    int (*die_cb)(struct die_link *, void *),
-                                    void *data)
-{
-        struct die_link new_link;
-        int ret;
+                if (die_get_inlinefunc(die_mem, addr, &child_die)) {
+                        memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+                        return die_mem;
+                }
+        } while (dwarf_siblingof(die_mem, die_mem) == 0);
 
-        new_link.parent = NULL;
-        ret = dwarf_child(parent_die, &new_link.die, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK)
-                return __search_die_tree(&new_link, die_cb, data);
-        else
-                return 0;
+        return NULL;
 }
 
-/* Find a locdesc corresponding to the address */
-static int attr_get_locdesc(Dwarf_Attribute attr, Dwarf_Locdesc *desc,
-                            Dwarf_Addr addr)
+/* Compare diename and tname */
+static bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
-        Dwarf_Signed lcnt;
-        Dwarf_Locdesc **llbuf;
-        int ret, i;
-
-        ret = dwarf_loclist_n(attr, &llbuf, &lcnt, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = DW_DLV_NO_ENTRY;
-        for (i = 0; i < lcnt; ++i) {
-                if (llbuf[i]->ld_lopc <= addr &&
-                    llbuf[i]->ld_hipc > addr) {
-                        memcpy(desc, llbuf[i], sizeof(Dwarf_Locdesc));
-                        desc->ld_s =
-                                malloc(sizeof(Dwarf_Loc) * llbuf[i]->ld_cents);
-                        DIE_IF(desc->ld_s == NULL);
-                        memcpy(desc->ld_s, llbuf[i]->ld_s,
-                                sizeof(Dwarf_Loc) * llbuf[i]->ld_cents);
-                        ret = DW_DLV_OK;
-                        break;
-                }
-                dwarf_dealloc(__dw_debug, llbuf[i]->ld_s, DW_DLA_LOC_BLOCK);
-                dwarf_dealloc(__dw_debug, llbuf[i], DW_DLA_LOCDESC);
-        }
-        /* Releasing loop */
-        for (; i < lcnt; ++i) {
-                dwarf_dealloc(__dw_debug, llbuf[i]->ld_s, DW_DLA_LOC_BLOCK);
-                dwarf_dealloc(__dw_debug, llbuf[i], DW_DLA_LOCDESC);
-        }
-        dwarf_dealloc(__dw_debug, llbuf, DW_DLA_LIST);
-        return ret;
+        const char *name;
+        name = dwarf_diename(dw_die);
+        DIE_IF(name == NULL);
+        return strcmp(tname, name);
 }
 
-/* Get decl_file attribute value (file number) */
-static Dwarf_Unsigned die_get_decl_file(Dwarf_Die sp_die)
+/* Get entry pc(or low pc, 1st entry of ranges)  of the die */
+static Dwarf_Addr die_get_entrypc(Dwarf_Die *dw_die)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Unsigned fno;
+        Dwarf_Addr epc;
         int ret;
 
-        ret = dwarf_attr(sp_die, DW_AT_decl_file, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_formudata(attr, &fno, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-        return fno;
+        ret = dwarf_entrypc(dw_die, &epc);
+        DIE_IF(ret == -1);
+        return epc;
 }
 
-/* Get decl_line attribute value (line number) */
-static Dwarf_Unsigned die_get_decl_line(Dwarf_Die sp_die)
+/* Get a variable die */
+static Dwarf_Die *die_find_variable(Dwarf_Die *sp_die, const char *name,
+                                    Dwarf_Die *die_mem)
 {
-        Dwarf_Attribute attr;
-        Dwarf_Unsigned lno;
+        Dwarf_Die child_die;
+        int tag;
         int ret;
 
-        ret = dwarf_attr(sp_die, DW_AT_decl_line, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_formudata(attr, &lno, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-        return lno;
+        ret = dwarf_child(sp_die, die_mem);
+        if (ret != 0)
+                return NULL;
+
+        do {
+                tag = dwarf_tag(die_mem);
+                if ((tag == DW_TAG_formal_parameter ||
+                     tag == DW_TAG_variable) &&
+                    (die_compare_name(die_mem, name) == 0))
+                        return die_mem;
+
+                if (die_find_variable(die_mem, name, &child_die)) {
+                        memcpy(die_mem, &child_die, sizeof(Dwarf_Die));
+                        return die_mem;
+                }
+        } while (dwarf_siblingof(die_mem, die_mem) == 0);
+
+        return NULL;
 }
 
 /*
@@ -370,47 +296,45 @@ static Dwarf_Unsigned die_get_decl_line(Dwarf_Die sp_die)
  */
 
 /* Show a location */
-static void show_location(Dwarf_Loc *loc, struct probe_finder *pf)
+static void show_location(Dwarf_Op *op, struct probe_finder *pf)
 {
-        Dwarf_Small op;
-        Dwarf_Unsigned regn;
-        Dwarf_Signed offs;
+        unsigned int regn;
+        Dwarf_Word offs = 0;
         int deref = 0, ret;
         const char *regs;
 
-        op = loc->lr_atom;
-
+        /* TODO: support CFA */
         /* If this is based on frame buffer, set the offset */
-        if (op == DW_OP_fbreg) {
+        if (op->atom == DW_OP_fbreg) {
+                if (pf->fb_ops == NULL)
+                        die("The attribute of frame base is not supported.\n");
                 deref = 1;
-                offs = (Dwarf_Signed)loc->lr_number;
-                op = pf->fbloc.ld_s[0].lr_atom;
-                loc = &pf->fbloc.ld_s[0];
-        } else
-                offs = 0;
+                offs = op->number;
+                op = &pf->fb_ops[0];
+        }
 
-        if (op >= DW_OP_breg0 && op <= DW_OP_breg31) {
-                regn = op - DW_OP_breg0;
-                offs += (Dwarf_Signed)loc->lr_number;
+        if (op->atom >= DW_OP_breg0 && op->atom <= DW_OP_breg31) {
+                regn = op->atom - DW_OP_breg0;
+                offs += op->number;
                 deref = 1;
-        } else if (op >= DW_OP_reg0 && op <= DW_OP_reg31) {
-                regn = op - DW_OP_reg0;
-        } else if (op == DW_OP_bregx) {
-                regn = loc->lr_number;
-                offs += (Dwarf_Signed)loc->lr_number2;
+        } else if (op->atom >= DW_OP_reg0 && op->atom <= DW_OP_reg31) {
+                regn = op->atom - DW_OP_reg0;
+        } else if (op->atom == DW_OP_bregx) {
+                regn = op->number;
+                offs += op->number2;
                 deref = 1;
-        } else if (op == DW_OP_regx) {
-                regn = loc->lr_number;
+        } else if (op->atom == DW_OP_regx) {
+                regn = op->number;
         } else
-                die("Dwarf_OP %d is not supported.\n", op);
+                die("DW_OP %d is not supported.", op->atom);
 
         regs = get_arch_regstr(regn);
         if (!regs)
-                die("%lld exceeds max register number.\n", regn);
+                die("%u exceeds max register number.", regn);
 
         if (deref)
-                ret = snprintf(pf->buf, pf->len,
-                                 " %s=%+lld(%s)", pf->var, offs, regs);
+                ret = snprintf(pf->buf, pf->len, " %s=+%ju(%s)",
+                               pf->var, (uintmax_t)offs, regs);
         else
                 ret = snprintf(pf->buf, pf->len, " %s=%s", pf->var, regs);
         DIE_IF(ret < 0);
@@ -418,52 +342,37 @@ static void show_location(Dwarf_Loc *loc, struct probe_finder *pf)
 }
 
 /* Show a variables in kprobe event format */
-static void show_variable(Dwarf_Die vr_die, struct probe_finder *pf)
+static void show_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 {
         Dwarf_Attribute attr;
-        Dwarf_Locdesc ld;
+        Dwarf_Op *expr;
+        size_t nexpr;
         int ret;
 
-        ret = dwarf_attr(vr_die, DW_AT_location, &attr, &__dw_error);
-        if (ret != DW_DLV_OK)
+        if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
                 goto error;
-        ret = attr_get_locdesc(attr, &ld, (pf->addr - pf->cu_base));
-        if (ret != DW_DLV_OK)
+        /* TODO: handle more than 1 exprs */
+        ret = dwarf_getlocation_addr(&attr, (pf->addr - pf->cu_base),
+                                     &expr, &nexpr, 1);
+        if (ret <= 0 || nexpr == 0)
                 goto error;
-        /* TODO? */
-        DIE_IF(ld.ld_cents != 1);
-        show_location(&ld.ld_s[0], pf);
-        free(ld.ld_s);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
+
+        show_location(expr, pf);
+        /* *expr will be cached in libdw. Don't free it. */
         return ;
 error:
+        /* TODO: Support const_value */
         die("Failed to find the location of %s at this address.\n"
-            " Perhaps, it has been optimized out.\n", pf->var);
-}
-
-static int variable_callback(struct die_link *dlink, void *data)
-{
-        struct probe_finder *pf = (struct probe_finder *)data;
-        Dwarf_Half tag;
-        int ret;
-
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if ((tag == DW_TAG_formal_parameter ||
-             tag == DW_TAG_variable) &&
-            (die_compare_name(dlink->die, pf->var) == 0)) {
-                show_variable(dlink->die, pf);
-                return 1;
-        }
-        /* TODO: Support struct members and arrays */
-        return 0;
+            " Perhaps, it has been optimized out.", pf->var);
 }
 
 /* Find a variable in a subprogram die */
-static void find_variable(Dwarf_Die sp_die, struct probe_finder *pf)
+static void find_variable(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
         int ret;
+        Dwarf_Die vr_die;
 
+        /* TODO: Support struct members and arrays */
         if (!is_c_varname(pf->var)) {
                 /* Output raw parameters */
                 ret = snprintf(pf->buf, pf->len, " %s", pf->var);
@@ -474,58 +383,51 @@ static void find_variable(Dwarf_Die sp_die, struct probe_finder *pf)
 
         pr_debug("Searching '%s' variable in context.\n", pf->var);
         /* Search child die for local variables and parameters. */
-        ret = search_die_from_children(sp_die, variable_callback, pf);
-        if (!ret)
-                die("Failed to find '%s' in this function.\n", pf->var);
-}
+        if (!die_find_variable(sp_die, pf->var, &vr_die))
+                die("Failed to find '%s' in this function.", pf->var);
 
-/* Get a frame base on the address */
-static void get_current_frame_base(Dwarf_Die sp_die, struct probe_finder *pf)
-{
-        Dwarf_Attribute attr;
-        int ret;
-
-        ret = dwarf_attr(sp_die, DW_AT_frame_base, &attr, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
-        ret = attr_get_locdesc(attr, &pf->fbloc, (pf->addr - pf->cu_base));
-        DIE_IF(ret != DW_DLV_OK);
-        dwarf_dealloc(__dw_debug, attr, DW_DLA_ATTR);
-}
-
-static void free_current_frame_base(struct probe_finder *pf)
-{
-        free(pf->fbloc.ld_s);
-        memset(&pf->fbloc, 0, sizeof(Dwarf_Locdesc));
+        show_variable(&vr_die, pf);
 }
 
 /* Show a probe point to output buffer */
-static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs,
-                            struct probe_finder *pf)
+static void show_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
         struct probe_point *pp = pf->pp;
-        char *name;
+        Dwarf_Addr eaddr;
+        Dwarf_Die die_mem;
+        const char *name;
         char tmp[MAX_PROBE_BUFFER];
         int ret, i, len;
+        Dwarf_Attribute fb_attr;
+        size_t nops;
+
+        /* If no real subprogram, find a real one */
+        if (!sp_die || dwarf_tag(sp_die) != DW_TAG_subprogram) {
+                sp_die = die_get_real_subprogram(&pf->cu_die,
+                                                 pf->addr, &die_mem);
+                if (!sp_die)
+                        die("Probe point is not found in subprograms.");
+        }
 
         /* Output name of probe point */
-        ret = dwarf_diename(sp_die, &name, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (ret == DW_DLV_OK) {
-                ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%u", name,
-                                (unsigned int)offs);
+        name = dwarf_diename(sp_die);
+        if (name) {
+                dwarf_entrypc(sp_die, &eaddr);
+                ret = snprintf(tmp, MAX_PROBE_BUFFER, "%s+%lu", name,
+                                (unsigned long)(pf->addr - eaddr));
                 /* Copy the function name if possible */
                 if (!pp->function) {
                         pp->function = strdup(name);
-                        pp->offset = offs;
+                        pp->offset = (size_t)(pf->addr - eaddr);
                 }
-                dwarf_dealloc(__dw_debug, name, DW_DLA_STRING);
         } else {
                 /* This function has no name. */
-                ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%llx", pf->addr);
+                ret = snprintf(tmp, MAX_PROBE_BUFFER, "0x%jx",
+                               (uintmax_t)pf->addr);
                 if (!pp->function) {
                         /* TODO: Use _stext */
                         pp->function = strdup("");
-                        pp->offset = (int)pf->addr;
+                        pp->offset = (size_t)pf->addr;
                 }
         }
         DIE_IF(ret < 0);
@@ -533,8 +435,15 @@ static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs,
         len = ret;
         pr_debug("Probe point found: %s\n", tmp);
 
+        /* Get the frame base attribute/ops */
+        dwarf_attr(sp_die, DW_AT_frame_base, &fb_attr);
+        ret = dwarf_getlocation_addr(&fb_attr, (pf->addr - pf->cu_base),
+                                     &pf->fb_ops, &nops, 1);
+        if (ret <= 0 || nops == 0)
+                pf->fb_ops = NULL;
+
         /* Find each argument */
-        get_current_frame_base(sp_die, pf);
+        /* TODO: use dwarf_cfi_addrframe */
         for (i = 0; i < pp->nr_args; i++) {
                 pf->var = pp->args[i];
                 pf->buf = &tmp[len];
@@ -542,189 +451,383 @@ static void show_probepoint(Dwarf_Die sp_die, Dwarf_Signed offs,
                 find_variable(sp_die, pf);
                 len += strlen(pf->buf);
         }
-        free_current_frame_base(pf);
+
+        /* *pf->fb_ops will be cached in libdw. Don't free it. */
+        pf->fb_ops = NULL;
 
         pp->probes[pp->found] = strdup(tmp);
         pp->found++;
 }
 
-static int probeaddr_callback(struct die_link *dlink, void *data)
+/* Find probe point from its line number */
+static void find_probe_point_by_line(struct probe_finder *pf)
 {
-        struct probe_finder *pf = (struct probe_finder *)data;
-        Dwarf_Half tag;
-        Dwarf_Signed offs;
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        size_t nlines, i;
+        Dwarf_Addr addr;
+        int lineno;
         int ret;
 
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        /* Check the address is in this subprogram */
-        if (tag == DW_TAG_subprogram &&
-            die_within_subprogram(dlink->die, pf->addr, &offs)) {
-                show_probepoint(dlink->die, offs, pf);
-                return 1;
+        ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
+        DIE_IF(ret != 0);
+
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
+                dwarf_lineno(line, &lineno);
+                if (lineno != pf->lno)
+                        continue;
+
+                /* TODO: Get fileno from line, but how? */
+                if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
+                        continue;
+
+                ret = dwarf_lineaddr(line, &addr);
+                DIE_IF(ret != 0);
+                pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n",
+                         (int)i, lineno, (uintmax_t)addr);
+                pf->addr = addr;
+
+                show_probe_point(NULL, pf);
+                /* Continuing, because target line might be inlined. */
         }
-        return 0;
 }
 
-/* Find probe point from its line number */
-static void find_by_line(struct probe_finder *pf)
+/* Find lines which match lazy pattern */
+static int find_lazy_match_lines(struct list_head *head,
+                                 const char *fname, const char *pat)
+{
+        char *fbuf, *p1, *p2;
+        int fd, line, nlines = 0;
+        struct stat st;
+
+        fd = open(fname, O_RDONLY);
+        if (fd < 0)
+                die("failed to open %s", fname);
+        DIE_IF(fstat(fd, &st) < 0);
+        fbuf = malloc(st.st_size + 2);
+        DIE_IF(fbuf == NULL);
+        DIE_IF(read(fd, fbuf, st.st_size) < 0);
+        close(fd);
+        fbuf[st.st_size] = '\n';        /* Dummy line */
+        fbuf[st.st_size + 1] = '\0';
+        p1 = fbuf;
+        line = 1;
+        while ((p2 = strchr(p1, '\n')) != NULL) {
+                *p2 = '\0';
+                if (strlazymatch(p1, pat)) {
+                        line_list__add_line(head, line);
+                        nlines++;
+                }
+                line++;
+                p1 = p2 + 1;
+        }
+        free(fbuf);
+        return nlines;
+}
+
+/* Find probe points from lazy pattern  */
+static void find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
-        Dwarf_Signed cnt, i, clm;
-        Dwarf_Line *lines;
-        Dwarf_Unsigned lineno = 0;
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        size_t nlines, i;
         Dwarf_Addr addr;
-        Dwarf_Unsigned fno;
+        Dwarf_Die die_mem;
+        int lineno;
         int ret;
 
-        ret = dwarf_srclines(pf->cu_die, &lines, &cnt, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
+        if (list_empty(&pf->lcache)) {
+                /* Matching lazy line pattern */
+                ret = find_lazy_match_lines(&pf->lcache, pf->fname,
+                                            pf->pp->lazy_line);
+                if (ret <= 0)
+                        die("No matched lines found in %s.", pf->fname);
+        }
+
+        ret = dwarf_getsrclines(&pf->cu_die, &lines, &nlines);
+        DIE_IF(ret != 0);
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
 
-        for (i = 0; i < cnt; i++) {
-                ret = dwarf_line_srcfileno(lines[i], &fno, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                if (fno != pf->fno)
+                dwarf_lineno(line, &lineno);
+                if (!line_list__has_line(&pf->lcache, lineno))
                         continue;
 
-                ret = dwarf_lineno(lines[i], &lineno, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                if (lineno != pf->lno)
+                /* TODO: Get fileno from line, but how? */
+                if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0)
                         continue;
 
-                ret = dwarf_lineoff(lines[i], &clm, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
+                ret = dwarf_lineaddr(line, &addr);
+                DIE_IF(ret != 0);
+                if (sp_die) {
+                        /* Address filtering 1: does sp_die include addr? */
+                        if (!dwarf_haspc(sp_die, addr))
+                                continue;
+                        /* Address filtering 2: No child include addr? */
+                        if (die_get_inlinefunc(sp_die, addr, &die_mem))
+                                continue;
+                }
 
-                ret = dwarf_lineaddr(lines[i], &addr, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
-                pr_debug("Probe line found: line[%d]:%u,%d addr:0x%llx\n",
-                         (int)i, (unsigned)lineno, (int)clm, addr);
+                pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n",
+                         (int)i, lineno, (unsigned long long)addr);
                 pf->addr = addr;
-                /* Search a real subprogram including this line, */
-                ret = search_die_from_children(pf->cu_die,
-                                               probeaddr_callback, pf);
-                if (ret == 0)
-                        die("Probe point is not found in subprograms.\n");
+
+                show_probe_point(sp_die, pf);
                 /* Continuing, because target line might be inlined. */
         }
-        dwarf_srclines_dealloc(__dw_debug, lines, cnt);
+        /* TODO: deallocate lines, but how? */
+}
+
+static int probe_point_inline_cb(Dwarf_Die *in_die, void *data)
+{
+        struct probe_finder *pf = (struct probe_finder *)data;
+        struct probe_point *pp = pf->pp;
+
+        if (pp->lazy_line)
+                find_probe_point_lazy(in_die, pf);
+        else {
+                /* Get probe address */
+                pf->addr = die_get_entrypc(in_die);
+                pf->addr += pp->offset;
+                pr_debug("found inline addr: 0x%jx\n",
+                         (uintmax_t)pf->addr);
+
+                show_probe_point(in_die, pf);
+        }
+
+        return DWARF_CB_OK;
 }
 
 /* Search function from function name */
-static int probefunc_callback(struct die_link *dlink, void *data)
+static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 {
         struct probe_finder *pf = (struct probe_finder *)data;
         struct probe_point *pp = pf->pp;
-        struct die_link *lk;
-        Dwarf_Signed offs;
-        Dwarf_Half tag;
-        int ret;
 
-        ret = dwarf_tag(dlink->die, &tag, &__dw_error);
-        DIE_IF(ret == DW_DLV_ERROR);
-        if (tag == DW_TAG_subprogram) {
-                if (die_compare_name(dlink->die, pp->function) == 0) {
-                        if (pp->line) { /* Function relative line */
-                                pf->fno = die_get_decl_file(dlink->die);
-                                pf->lno = die_get_decl_line(dlink->die)
-                                         + pp->line;
-                                find_by_line(pf);
-                                return 1;
-                        }
-                        if (die_inlined_subprogram(dlink->die)) {
-                                /* Inlined function, save it. */
-                                ret = dwarf_die_CU_offset(dlink->die,
-                                                          &pf->inl_offs,
-                                                          &__dw_error);
-                                DIE_IF(ret != DW_DLV_OK);
-                                pr_debug("inline definition offset %lld\n",
-                                         pf->inl_offs);
-                                return 0;       /* Continue to search */
-                        }
-                        /* Get probe address */
-                        pf->addr = die_get_entrypc(dlink->die);
+        /* Check tag and diename */
+        if (dwarf_tag(sp_die) != DW_TAG_subprogram ||
+            die_compare_name(sp_die, pp->function) != 0)
+                return 0;
+
+        pf->fname = dwarf_decl_file(sp_die);
+        if (pp->line) { /* Function relative line */
+                dwarf_decl_line(sp_die, &pf->lno);
+                pf->lno += pp->line;
+                find_probe_point_by_line(pf);
+        } else if (!dwarf_func_inline(sp_die)) {
+                /* Real function */
+                if (pp->lazy_line)
+                        find_probe_point_lazy(sp_die, pf);
+                else {
+                        pf->addr = die_get_entrypc(sp_die);
                         pf->addr += pp->offset;
                         /* TODO: Check the address in this function */
-                        show_probepoint(dlink->die, pp->offset, pf);
-                        return 1; /* Exit; no same symbol in this CU. */
-                }
-        } else if (tag == DW_TAG_inlined_subroutine && pf->inl_offs) {
-                if (die_get_abstract_origin(dlink->die) == pf->inl_offs) {
-                        /* Get probe address */
-                        pf->addr = die_get_entrypc(dlink->die);
-                        pf->addr += pp->offset;
-                        pr_debug("found inline addr: 0x%llx\n", pf->addr);
-                        /* Inlined function. Get a real subprogram */
-                        for (lk = dlink->parent; lk != NULL; lk = lk->parent) {
-                                tag = 0;
-                                dwarf_tag(lk->die, &tag, &__dw_error);
-                                DIE_IF(ret == DW_DLV_ERROR);
-                                if (tag == DW_TAG_subprogram &&
-                                    !die_inlined_subprogram(lk->die))
-                                        goto found;
-                        }
-                        die("Failed to find real subprogram.\n");
-found:
-                        /* Get offset from subprogram */
-                        ret = die_within_subprogram(lk->die, pf->addr, &offs);
-                        DIE_IF(!ret);
-                        show_probepoint(lk->die, offs, pf);
-                        /* Continue to search */
+                        show_probe_point(sp_die, pf);
                 }
-        }
-        return 0;
+        } else
+                /* Inlined function: search instances */
+                dwarf_func_inline_instances(sp_die, probe_point_inline_cb, pf);
+
+        return 1; /* Exit; no same symbol in this CU. */
 }
 
-static void find_by_func(struct probe_finder *pf)
+static void find_probe_point_by_func(struct probe_finder *pf)
 {
-        search_die_from_children(pf->cu_die, probefunc_callback, pf);
+        dwarf_getfuncs(&pf->cu_die, probe_point_search_cb, pf, 0);
 }
 
 /* Find a probe point */
-int find_probepoint(int fd, struct probe_point *pp)
+int find_probe_point(int fd, struct probe_point *pp)
 {
-        Dwarf_Half addr_size = 0;
-        Dwarf_Unsigned next_cuh = 0;
-        int cu_number = 0, ret;
         struct probe_finder pf = {.pp = pp};
+        int ret;
+        Dwarf_Off off, noff;
+        size_t cuhl;
+        Dwarf_Die *diep;
+        Dwarf *dbg;
 
-        ret = dwarf_init(fd, DW_DLC_READ, 0, 0, &__dw_debug, &__dw_error);
-        if (ret != DW_DLV_OK)
+        dbg = dwarf_begin(fd, DWARF_C_READ);
+        if (!dbg)
                 return -ENOENT;
 
         pp->found = 0;
-        while (++cu_number) {
-                /* Search CU (Compilation Unit) */
-                ret = dwarf_next_cu_header(__dw_debug, NULL, NULL, NULL,
-                        &addr_size, &next_cuh, &__dw_error);
-                DIE_IF(ret == DW_DLV_ERROR);
-                if (ret == DW_DLV_NO_ENTRY)
-                        break;
-
+        off = 0;
+        line_list__init(&pf.lcache);
+        /* Loop on CUs (Compilation Unit) */
+        while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) {
                 /* Get the DIE(Debugging Information Entry) of this CU */
-                ret = dwarf_siblingof(__dw_debug, 0, &pf.cu_die, &__dw_error);
-                DIE_IF(ret != DW_DLV_OK);
+                diep = dwarf_offdie(dbg, off + cuhl, &pf.cu_die);
+                if (!diep)
+                        continue;
 
                 /* Check if target file is included. */
                 if (pp->file)
-                        pf.fno = cu_find_fileno(pf.cu_die, pp->file);
+                        pf.fname = cu_find_realpath(&pf.cu_die, pp->file);
+                else
+                        pf.fname = NULL;
 
-                if (!pp->file || pf.fno) {
+                if (!pp->file || pf.fname) {
                         /* Save CU base address (for frame_base) */
-                        ret = dwarf_lowpc(pf.cu_die, &pf.cu_base, &__dw_error);
-                        DIE_IF(ret == DW_DLV_ERROR);
-                        if (ret == DW_DLV_NO_ENTRY)
+                        ret = dwarf_lowpc(&pf.cu_die, &pf.cu_base);
+                        if (ret != 0)
                                 pf.cu_base = 0;
                         if (pp->function)
-                                find_by_func(&pf);
+                                find_probe_point_by_func(&pf);
+                        else if (pp->lazy_line)
+                                find_probe_point_lazy(NULL, &pf);
                         else {
                                 pf.lno = pp->line;
-                                find_by_line(&pf);
+                                find_probe_point_by_line(&pf);
                         }
                 }
-                dwarf_dealloc(__dw_debug, pf.cu_die, DW_DLA_DIE);
+                off = noff;
         }
-        ret = dwarf_finish(__dw_debug, &__dw_error);
-        DIE_IF(ret != DW_DLV_OK);
+        line_list__free(&pf.lcache);
+        dwarf_end(dbg);
 
         return pp->found;
 }
 
+/* Find line range from its line number */
+static void find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
+{
+        Dwarf_Lines *lines;
+        Dwarf_Line *line;
+        size_t nlines, i;
+        Dwarf_Addr addr;
+        int lineno;
+        int ret;
+        const char *src;
+        Dwarf_Die die_mem;
+
+        line_list__init(&lf->lr->line_list);
+        ret = dwarf_getsrclines(&lf->cu_die, &lines, &nlines);
+        DIE_IF(ret != 0);
+
+        for (i = 0; i < nlines; i++) {
+                line = dwarf_onesrcline(lines, i);
+                ret = dwarf_lineno(line, &lineno);
+                DIE_IF(ret != 0);
+                if (lf->lno_s > lineno || lf->lno_e < lineno)
+                        continue;
+
+                if (sp_die) {
+                        /* Address filtering 1: does sp_die include addr? */
+                        ret = dwarf_lineaddr(line, &addr);
+                        DIE_IF(ret != 0);
+                        if (!dwarf_haspc(sp_die, addr))
+                                continue;
+
+                        /* Address filtering 2: No child include addr? */
+                        if (die_get_inlinefunc(sp_die, addr, &die_mem))
+                                continue;
+                }
+
+                /* TODO: Get fileno from line, but how? */
+                src = dwarf_linesrc(line, NULL, NULL);
+                if (strtailcmp(src, lf->fname) != 0)
+                        continue;
+
+                /* Copy real path */
+                if (!lf->lr->path)
+                        lf->lr->path = strdup(src);
+                line_list__add_line(&lf->lr->line_list, (unsigned int)lineno);
+        }
+        /* Update status */
+        if (!list_empty(&lf->lr->line_list))
+                lf->found = 1;
+        else {
+                free(lf->lr->path);
+                lf->lr->path = NULL;
+        }
+}
+
+static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
+{
+        find_line_range_by_line(in_die, (struct line_finder *)data);
+        return DWARF_CB_ABORT;  /* No need to find other instances */
+}
+
+/* Search function from function name */
+static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
+{
+        struct line_finder *lf = (struct line_finder *)data;
+        struct line_range *lr = lf->lr;
+
+        if (dwarf_tag(sp_die) == DW_TAG_subprogram &&
+            die_compare_name(sp_die, lr->function) == 0) {
+                lf->fname = dwarf_decl_file(sp_die);
+                dwarf_decl_line(sp_die, &lr->offset);
+                pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
+                lf->lno_s = lr->offset + lr->start;
+                if (!lr->end)
+                        lf->lno_e = INT_MAX;
+                else
+                        lf->lno_e = lr->offset + lr->end;
+                lr->start = lf->lno_s;
+                lr->end = lf->lno_e;
+                if (dwarf_func_inline(sp_die))
+                        dwarf_func_inline_instances(sp_die,
+                                                    line_range_inline_cb, lf);
+                else
+                        find_line_range_by_line(sp_die, lf);
+                return 1;
+        }
+        return 0;
+}
+
+static void find_line_range_by_func(struct line_finder *lf)
+{
+        dwarf_getfuncs(&lf->cu_die, line_range_search_cb, lf, 0);
+}
+
+int find_line_range(int fd, struct line_range *lr)
+{
+        struct line_finder lf = {.lr = lr, .found = 0};
+        int ret;
+        Dwarf_Off off = 0, noff;
+        size_t cuhl;
+        Dwarf_Die *diep;
+        Dwarf *dbg;
+
+        dbg = dwarf_begin(fd, DWARF_C_READ);
+        if (!dbg)
+                return -ENOENT;
+
+        /* Loop on CUs (Compilation Unit) */
+        while (!lf.found) {
+                ret = dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL);
+                if (ret != 0)
+                        break;
+
+                /* Get the DIE(Debugging Information Entry) of this CU */
+                diep = dwarf_offdie(dbg, off + cuhl, &lf.cu_die);
+                if (!diep)
+                        continue;
+
+                /* Check if target file is included. */
+                if (lr->file)
+                        lf.fname = cu_find_realpath(&lf.cu_die, lr->file);
+                else
+                        lf.fname = 0;
+
+                if (!lr->file || lf.fname) {
+                        if (lr->function)
+                                find_line_range_by_func(&lf);
+                        else {
+                                lf.lno_s = lr->start;
+                                if (!lr->end)
+                                        lf.lno_e = INT_MAX;
+                                else
+                                        lf.lno_e = lr->end;
+                                find_line_range_by_line(NULL, &lf);
+                        }
+                }
+                off = noff;
+        }
+        pr_debug("path: %lx\n", (unsigned long)lr->path);
+        dwarf_end(dbg);
+        return lf.found;
+}
+
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index a4086aaddb73..d1a651793ba6 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -1,6 +1,9 @@
 #ifndef _PROBE_FINDER_H
 #define _PROBE_FINDER_H
 
+#include <stdbool.h>
+#include "util.h"
+
 #define MAX_PATH_LEN             256
 #define MAX_PROBE_BUFFER        1024
 #define MAX_PROBES               128
@@ -18,6 +21,7 @@ struct probe_point {
         /* Inputs */
         char                    *file;                  /* File name */
         int                     line;                   /* Line number */
+        char                    *lazy_line;             /* Lazy line pattern */
 
         char                    *function;              /* Function name */
         int                     offset;                 /* Offset bytes */
@@ -32,34 +36,58 @@ struct probe_point {
         char                    *probes[MAX_PROBES];    /* Output buffers (will be allocated)*/
 };
 
-#ifndef NO_LIBDWARF
-extern int find_probepoint(int fd, struct probe_point *pp);
+/* Line number container */
+struct line_node {
+        struct list_head        list;
+        unsigned int            line;
+};
+
+/* Line range */
+struct line_range {
+        char                    *file;                  /* File name */
+        char                    *function;              /* Function name */
+        unsigned int            start;                  /* Start line number */
+        unsigned int            end;                    /* End line number */
+        int                     offset;                 /* Start line offset */
+        char                    *path;                  /* Real path name */
+        struct list_head        line_list;              /* Visible lines */
+};
 
-/* Workaround for undefined _MIPS_SZLONG bug in libdwarf.h: */
-#ifndef _MIPS_SZLONG
-# define _MIPS_SZLONG           0
-#endif
+#ifndef NO_DWARF_SUPPORT
+extern int find_probe_point(int fd, struct probe_point *pp);
+extern int find_line_range(int fd, struct line_range *lr);
 
 #include <dwarf.h>
-#include <libdwarf.h>
+#include <libdw.h>
 
 struct probe_finder {
-        struct probe_point      *pp;                    /* Target probe point */
+        struct probe_point      *pp;            /* Target probe point */
 
         /* For function searching */
-        Dwarf_Addr              addr;                   /* Address */
-        Dwarf_Unsigned          fno;                    /* File number */
-        Dwarf_Unsigned          lno;                    /* Line number */
-        Dwarf_Off               inl_offs;               /* Inline offset */
-        Dwarf_Die               cu_die;                 /* Current CU */
+        Dwarf_Addr              addr;           /* Address */
+        const char              *fname;         /* File name */
+        int                     lno;            /* Line number */
+        Dwarf_Die               cu_die;         /* Current CU */
 
         /* For variable searching */
-        Dwarf_Addr              cu_base;                /* Current CU base address */
-        Dwarf_Locdesc           fbloc;                  /* Location of Current Frame Base */
-        const char              *var;                   /* Current variable name */
-        char                    *buf;                   /* Current output buffer */
-        int                     len;                    /* Length of output buffer */
+        Dwarf_Op                *fb_ops;        /* Frame base attribute */
+        Dwarf_Addr              cu_base;        /* Current CU base address */
+        const char              *var;           /* Current variable name */
+        char                    *buf;           /* Current output buffer */
+        int                     len;            /* Length of output buffer */
+        struct list_head        lcache;         /* Line cache for lazy match */
 };
-#endif /* NO_LIBDWARF */
+
+struct line_finder {
+        struct line_range       *lr;            /* Target line range */
+
+        const char              *fname;         /* File name */
+        int                     lno_s;          /* Start line number */
+        int                     lno_e;          /* End line number */
+        Dwarf_Die               cu_die;         /* Current CU */
+        int                     found;
+};
+
+#endif /* NO_DWARF_SUPPORT */
 
 #endif /*_PROBE_FINDER_H */
diff --git a/tools/perf/util/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 6d6d76b8a21e..5376378e0cfc 100644
--- a/tools/perf/util/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -25,10 +25,16 @@
 #include <ctype.h>
 #include <errno.h>
 
-#include "../perf.h"
-#include "util.h"
-#include "trace-event.h"
-#include "trace-event-perl.h"
+#include "../../perf.h"
+#include "../util.h"
+#include "../trace-event.h"
+
+#include <EXTERN.h>
+#include <perl.h>
+
+void boot_Perf__Trace__Context(pTHX_ CV *cv);
+void boot_DynaLoader(pTHX_ CV *cv);
+typedef PerlInterpreter * INTERP;
 
 void xs_init(pTHX);
 
@@ -49,7 +55,7 @@ INTERP my_perl;
 
 struct event *events[FTRACE_MAX_EVENT];
 
-static struct scripting_context *scripting_context;
+extern struct scripting_context *scripting_context;
 
 static char *cur_field_name;
 static int zero_flag_atom;
@@ -239,33 +245,6 @@ static inline struct event *find_cache_event(int type)
         return event;
 }
 
-int common_pc(struct scripting_context *context)
-{
-        int pc;
-
-        pc = parse_common_pc(context->event_data);
-
-        return pc;
-}
-
-int common_flags(struct scripting_context *context)
-{
-        int flags;
-
-        flags = parse_common_flags(context->event_data);
-
-        return flags;
-}
-
-int common_lock_depth(struct scripting_context *context)
-{
-        int lock_depth;
-
-        lock_depth = parse_common_lock_depth(context->event_data);
-
-        return lock_depth;
-}
-
 static void perl_process_event(int cpu, void *data,
                                int size __unused,
                                unsigned long long nsecs, char *comm)
@@ -587,75 +566,3 @@ struct scripting_ops perl_scripting_ops = {
         .process_event = perl_process_event,
         .generate_script = perl_generate_script,
 };
-
-static void print_unsupported_msg(void)
-{
-        fprintf(stderr, "Perl scripting not supported."
-                "  Install libperl and rebuild perf to enable it.\n"
-                "For example:\n  # apt-get install libperl-dev (ubuntu)"
-                "\n  # yum install perl-ExtUtils-Embed (Fedora)"
-                "\n  etc.\n");
-}
-
-static int perl_start_script_unsupported(const char *script __unused,
-                                         int argc __unused,
-                                         const char **argv __unused)
-{
-        print_unsupported_msg();
-
-        return -1;
-}
-
-static int perl_stop_script_unsupported(void)
-{
-        return 0;
-}
-
-static void perl_process_event_unsupported(int cpu __unused,
-                                           void *data __unused,
-                                           int size __unused,
-                                           unsigned long long nsecs __unused,
-                                           char *comm __unused)
-{
-}
-
-static int perl_generate_script_unsupported(const char *outfile __unused)
-{
-        print_unsupported_msg();
-
-        return -1;
-}
-
-struct scripting_ops perl_scripting_unsupported_ops = {
-        .name = "Perl",
-        .start_script = perl_start_script_unsupported,
-        .stop_script = perl_stop_script_unsupported,
-        .process_event = perl_process_event_unsupported,
-        .generate_script = perl_generate_script_unsupported,
-};
-
-static void register_perl_scripting(struct scripting_ops *scripting_ops)
-{
-        int err;
-        err = script_spec_register("Perl", scripting_ops);
-        if (err)
-                die("error registering Perl script extension");
-
-        err = script_spec_register("pl", scripting_ops);
-        if (err)
-                die("error registering pl script extension");
-
-        scripting_context = malloc(sizeof(struct scripting_context));
-}
-
-#ifdef NO_LIBPERL
-void setup_perl_scripting(void)
-{
-        register_perl_scripting(&perl_scripting_unsupported_ops);
-}
-#else
-void setup_perl_scripting(void)
-{
-        register_perl_scripting(&perl_scripting_ops);
-}
-#endif
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
new file mode 100644
index 000000000000..33a414bbba3e
--- /dev/null
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -0,0 +1,573 @@
+/*
+ * trace-event-python.  Feed trace events to an embedded Python interpreter.
+ *
+ * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <Python.h>
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+#include <errno.h>
+
+#include "../../perf.h"
+#include "../util.h"
+#include "../trace-event.h"
+
+PyMODINIT_FUNC initperf_trace_context(void);
+
+#define FTRACE_MAX_EVENT                                \
+        ((1 << (sizeof(unsigned short) * 8)) - 1)
+
+struct event *events[FTRACE_MAX_EVENT];
+
+#define MAX_FIELDS      64
+#define N_COMMON_FIELDS 7
+
+extern struct scripting_context *scripting_context;
+
+static char *cur_field_name;
+static int zero_flag_atom;
+
+static PyObject *main_module, *main_dict;
+
+static void handler_call_die(const char *handler_name)
+{
+        PyErr_Print();
+        Py_FatalError("problem in Python trace event handler");
+}
+
+static void define_value(enum print_arg_type field_type,
+                         const char *ev_name,
+                         const char *field_name,
+                         const char *field_value,
+                         const char *field_str)
+{
+        const char *handler_name = "define_flag_value";
+        PyObject *handler, *t, *retval;
+        unsigned long long value;
+        unsigned n = 0;
+
+        if (field_type == PRINT_SYMBOL)
+                handler_name = "define_symbolic_value";
+
+        t = PyTuple_New(4);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        value = eval_flag(field_value);
+
+        PyTuple_SetItem(t, n++, PyString_FromString(ev_name));
+        PyTuple_SetItem(t, n++, PyString_FromString(field_name));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(value));
+        PyTuple_SetItem(t, n++, PyString_FromString(field_str));
+
+        handler = PyDict_GetItemString(main_dict, handler_name);
+        if (handler && PyCallable_Check(handler)) {
+                retval = PyObject_CallObject(handler, t);
+                if (retval == NULL)
+                        handler_call_die(handler_name);
+        }
+
+        Py_DECREF(t);
+}
+
+static void define_values(enum print_arg_type field_type,
+                          struct print_flag_sym *field,
+                          const char *ev_name,
+                          const char *field_name)
+{
+        define_value(field_type, ev_name, field_name, field->value,
+                     field->str);
+
+        if (field->next)
+                define_values(field_type, field->next, ev_name, field_name);
+}
+
+static void define_field(enum print_arg_type field_type,
+                         const char *ev_name,
+                         const char *field_name,
+                         const char *delim)
+{
+        const char *handler_name = "define_flag_field";
+        PyObject *handler, *t, *retval;
+        unsigned n = 0;
+
+        if (field_type == PRINT_SYMBOL)
+                handler_name = "define_symbolic_field";
+
+        if (field_type == PRINT_FLAGS)
+                t = PyTuple_New(3);
+        else
+                t = PyTuple_New(2);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        PyTuple_SetItem(t, n++, PyString_FromString(ev_name));
+        PyTuple_SetItem(t, n++, PyString_FromString(field_name));
+        if (field_type == PRINT_FLAGS)
+                PyTuple_SetItem(t, n++, PyString_FromString(delim));
+
+        handler = PyDict_GetItemString(main_dict, handler_name);
+        if (handler && PyCallable_Check(handler)) {
+                retval = PyObject_CallObject(handler, t);
+                if (retval == NULL)
+                        handler_call_die(handler_name);
+        }
+
+        Py_DECREF(t);
+}
+
+static void define_event_symbols(struct event *event,
+                                 const char *ev_name,
+                                 struct print_arg *args)
+{
+        switch (args->type) {
+        case PRINT_NULL:
+                break;
+        case PRINT_ATOM:
+                define_value(PRINT_FLAGS, ev_name, cur_field_name, "0",
+                             args->atom.atom);
+                zero_flag_atom = 0;
+                break;
+        case PRINT_FIELD:
+                if (cur_field_name)
+                        free(cur_field_name);
+                cur_field_name = strdup(args->field.name);
+                break;
+        case PRINT_FLAGS:
+                define_event_symbols(event, ev_name, args->flags.field);
+                define_field(PRINT_FLAGS, ev_name, cur_field_name,
+                             args->flags.delim);
+                define_values(PRINT_FLAGS, args->flags.flags, ev_name,
+                              cur_field_name);
+                break;
+        case PRINT_SYMBOL:
+                define_event_symbols(event, ev_name, args->symbol.field);
+                define_field(PRINT_SYMBOL, ev_name, cur_field_name, NULL);
+                define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name,
+                              cur_field_name);
+                break;
+        case PRINT_STRING:
+                break;
+        case PRINT_TYPE:
+                define_event_symbols(event, ev_name, args->typecast.item);
+                break;
+        case PRINT_OP:
+                if (strcmp(args->op.op, ":") == 0)
+                        zero_flag_atom = 1;
+                define_event_symbols(event, ev_name, args->op.left);
+                define_event_symbols(event, ev_name, args->op.right);
+                break;
+        default:
+                /* we should warn... */
+                return;
+        }
+
+        if (args->next)
+                define_event_symbols(event, ev_name, args->next);
+}
+
+static inline struct event *find_cache_event(int type)
+{
+        static char ev_name[256];
+        struct event *event;
+
+        if (events[type])
+                return events[type];
+
+        events[type] = event = trace_find_event(type);
+        if (!event)
+                return NULL;
+
+        sprintf(ev_name, "%s__%s", event->system, event->name);
+
+        define_event_symbols(event, ev_name, event->print_fmt.args);
+
+        return event;
+}
+
+static void python_process_event(int cpu, void *data,
+                                 int size __unused,
+                                 unsigned long long nsecs, char *comm)
+{
+        PyObject *handler, *retval, *context, *t;
+        static char handler_name[256];
+        struct format_field *field;
+        unsigned long long val;
+        unsigned long s, ns;
+        struct event *event;
+        unsigned n = 0;
+        int type;
+        int pid;
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        type = trace_parse_common_type(data);
+
+        event = find_cache_event(type);
+        if (!event)
+                die("ug! no event found for type %d", type);
+
+        pid = trace_parse_common_pid(data);
+
+        sprintf(handler_name, "%s__%s", event->system, event->name);
+
+        s = nsecs / NSECS_PER_SEC;
+        ns = nsecs - s * NSECS_PER_SEC;
+
+        scripting_context->event_data = data;
+
+        context = PyCObject_FromVoidPtr(scripting_context, NULL);
+
+        PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
+        PyTuple_SetItem(t, n++,
+                        PyCObject_FromVoidPtr(scripting_context, NULL));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(s));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
+        PyTuple_SetItem(t, n++, PyString_FromString(comm));
+
+        for (field = event->format.fields; field; field = field->next) {
+                if (field->flags & FIELD_IS_STRING) {
+                        int offset;
+                        if (field->flags & FIELD_IS_DYNAMIC) {
+                                offset = *(int *)(data + field->offset);
+                                offset &= 0xffff;
+                        } else
+                                offset = field->offset;
+                        PyTuple_SetItem(t, n++,
+                                PyString_FromString((char *)data + offset));
+                } else { /* FIELD_IS_NUMERIC */
+                        val = read_size(data + field->offset, field->size);
+                        if (field->flags & FIELD_IS_SIGNED) {
+                                PyTuple_SetItem(t, n++, PyInt_FromLong(val));
+                        } else {
+                                PyTuple_SetItem(t, n++, PyInt_FromLong(val));
+                        }
+                }
+        }
+
+        if (_PyTuple_Resize(&t, n) == -1)
+                Py_FatalError("error resizing Python tuple");
+
+        handler = PyDict_GetItemString(main_dict, handler_name);
+        if (handler && PyCallable_Check(handler)) {
+                retval = PyObject_CallObject(handler, t);
+                if (retval == NULL)
+                        handler_call_die(handler_name);
+        } else {
+                handler = PyDict_GetItemString(main_dict, "trace_unhandled");
+                if (handler && PyCallable_Check(handler)) {
+                        if (_PyTuple_Resize(&t, N_COMMON_FIELDS) == -1)
+                                Py_FatalError("error resizing Python tuple");
+
+                        retval = PyObject_CallObject(handler, t);
+                        if (retval == NULL)
+                                handler_call_die("trace_unhandled");
+                }
+        }
+
+        Py_DECREF(t);
+}
+
+static int run_start_sub(void)
+{
+        PyObject *handler, *retval;
+        int err = 0;
+
+        main_module = PyImport_AddModule("__main__");
+        if (main_module == NULL)
+                return -1;
+        Py_INCREF(main_module);
+
+        main_dict = PyModule_GetDict(main_module);
+        if (main_dict == NULL) {
+                err = -1;
+                goto error;
+        }
+        Py_INCREF(main_dict);
+
+        handler = PyDict_GetItemString(main_dict, "trace_begin");
+        if (handler == NULL || !PyCallable_Check(handler))
+                goto out;
+
+        retval = PyObject_CallObject(handler, NULL);
+        if (retval == NULL)
+                handler_call_die("trace_begin");
+
+        Py_DECREF(retval);
+        return err;
+error:
+        Py_XDECREF(main_dict);
+        Py_XDECREF(main_module);
+out:
+        return err;
+}
+
+/*
+ * Start trace script
+ */
+static int python_start_script(const char *script, int argc, const char **argv)
+{
+        const char **command_line;
+        char buf[PATH_MAX];
+        int i, err = 0;
+        FILE *fp;
+
+        command_line = malloc((argc + 1) * sizeof(const char *));
+        command_line[0] = script;
+        for (i = 1; i < argc + 1; i++)
+                command_line[i] = argv[i - 1];
+
+        Py_Initialize();
+
+        initperf_trace_context();
+
+        PySys_SetArgv(argc + 1, (char **)command_line);
+
+        fp = fopen(script, "r");
+        if (!fp) {
+                sprintf(buf, "Can't open python script \"%s\"", script);
+                perror(buf);
+                err = -1;
+                goto error;
+        }
+
+        err = PyRun_SimpleFile(fp, script);
+        if (err) {
+                fprintf(stderr, "Error running python script %s\n", script);
+                goto error;
+        }
+
+        err = run_start_sub();
+        if (err) {
+                fprintf(stderr, "Error starting python script %s\n", script);
+                goto error;
+        }
+
+        free(command_line);
+        fprintf(stderr, "perf trace started with Python script %s\n\n",
+                script);
+
+        return err;
+error:
+        Py_Finalize();
+        free(command_line);
+
+        return err;
+}
+
+/*
+ * Stop trace script
+ */
+static int python_stop_script(void)
+{
+        PyObject *handler, *retval;
+        int err = 0;
+
+        handler = PyDict_GetItemString(main_dict, "trace_end");
+        if (handler == NULL || !PyCallable_Check(handler))
+                goto out;
+
+        retval = PyObject_CallObject(handler, NULL);
+        if (retval == NULL)
+                handler_call_die("trace_end");
+        else
+                Py_DECREF(retval);
+out:
+        Py_XDECREF(main_dict);
+        Py_XDECREF(main_module);
+        Py_Finalize();
+
+        fprintf(stderr, "\nperf trace Python script stopped\n");
+
+        return err;
+}
+
+static int python_generate_script(const char *outfile)
+{
+        struct event *event = NULL;
+        struct format_field *f;
+        char fname[PATH_MAX];
+        int not_first, count;
+        FILE *ofp;
+
+        sprintf(fname, "%s.py", outfile);
+        ofp = fopen(fname, "w");
+        if (ofp == NULL) {
+                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, "# Licensed under the terms of the GNU GPL"
+                " License version 2\n\n");
+
+        fprintf(ofp, "# The common_* event handler fields are the most useful "
+                "fields common to\n");
+
+        fprintf(ofp, "# all events.  They don't necessarily correspond to "
+                "the 'common_*' fields\n");
+
+        fprintf(ofp, "# in the format files.  Those fields not available as "
+                "handler params can\n");
+
+        fprintf(ofp, "# be retrieved using Python functions of the form "
+                "common_*(context).\n");
+
+        fprintf(ofp, "# See the perf-trace-python Documentation for the list "
+                "of available functions.\n\n");
+
+        fprintf(ofp, "import os\n");
+        fprintf(ofp, "import sys\n\n");
+
+        fprintf(ofp, "sys.path.append(os.environ['PERF_EXEC_PATH'] + \\\n");
+        fprintf(ofp, "\t'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')\n");
+        fprintf(ofp, "\nfrom perf_trace_context import *\n");
+        fprintf(ofp, "from Core import *\n\n\n");
+
+        fprintf(ofp, "def trace_begin():\n");
+        fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+
+        fprintf(ofp, "def trace_end():\n");
+        fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+
+        while ((event = trace_find_next_event(event))) {
+                fprintf(ofp, "def %s__%s(", event->system, event->name);
+                fprintf(ofp, "event_name, ");
+                fprintf(ofp, "context, ");
+                fprintf(ofp, "common_cpu,\n");
+                fprintf(ofp, "\tcommon_secs, ");
+                fprintf(ofp, "common_nsecs, ");
+                fprintf(ofp, "common_pid, ");
+                fprintf(ofp, "common_comm,\n\t");
+
+                not_first = 0;
+                count = 0;
+
+                for (f = event->format.fields; f; f = f->next) {
+                        if (not_first++)
+                                fprintf(ofp, ", ");
+                        if (++count % 5 == 0)
+                                fprintf(ofp, "\n\t");
+
+                        fprintf(ofp, "%s", f->name);
+                }
+                fprintf(ofp, "):\n");
+
+                fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
+                        "common_secs, common_nsecs,\n\t\t\t"
+                        "common_pid, common_comm)\n\n");
+
+                fprintf(ofp, "\t\tprint \"");
+
+                not_first = 0;
+                count = 0;
+
+                for (f = event->format.fields; f; f = f->next) {
+                        if (not_first++)
+                                fprintf(ofp, ", ");
+                        if (count && count % 3 == 0) {
+                                fprintf(ofp, "\" \\\n\t\t\"");
+                        }
+                        count++;
+
+                        fprintf(ofp, "%s=", f->name);
+                        if (f->flags & FIELD_IS_STRING ||
+                            f->flags & FIELD_IS_FLAG ||
+                            f->flags & FIELD_IS_SYMBOLIC)
+                                fprintf(ofp, "%%s");
+                        else if (f->flags & FIELD_IS_SIGNED)
+                                fprintf(ofp, "%%d");
+                        else
+                                fprintf(ofp, "%%u");
+                }
+
+                fprintf(ofp, "\\n\" %% \\\n\t\t(");
+
+                not_first = 0;
+                count = 0;
+
+                for (f = event->format.fields; f; f = f->next) {
+                        if (not_first++)
+                                fprintf(ofp, ", ");
+
+                        if (++count % 5 == 0)
+                                fprintf(ofp, "\n\t\t");
+
+                        if (f->flags & FIELD_IS_FLAG) {
+                                if ((count - 1) % 5 != 0) {
+                                        fprintf(ofp, "\n\t\t");
+                                        count = 4;
+                                }
+                                fprintf(ofp, "flag_str(\"");
+                                fprintf(ofp, "%s__%s\", ", event->system,
+                                        event->name);
+                                fprintf(ofp, "\"%s\", %s)", f->name,
+                                        f->name);
+                        } else if (f->flags & FIELD_IS_SYMBOLIC) {
+                                if ((count - 1) % 5 != 0) {
+                                        fprintf(ofp, "\n\t\t");
+                                        count = 4;
+                                }
+                                fprintf(ofp, "symbol_str(\"");
+                                fprintf(ofp, "%s__%s\", ", event->system,
+                                        event->name);
+                                fprintf(ofp, "\"%s\", %s)", f->name,
+                                        f->name);
+                        } else
+                                fprintf(ofp, "%s", f->name);
+                }
+
+                fprintf(ofp, "),\n\n");
+        }
+
+        fprintf(ofp, "def trace_unhandled(event_name, context, "
+                "common_cpu, common_secs, common_nsecs,\n\t\t"
+                "common_pid, common_comm):\n");
+
+        fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
+                "common_secs, common_nsecs,\n\t\tcommon_pid, "
+                "common_comm)\n\n");
+
+        fprintf(ofp, "def print_header("
+                "event_name, cpu, secs, nsecs, pid, comm):\n"
+                "\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+                "(event_name, cpu, secs, nsecs, pid, comm),\n");
+
+        fclose(ofp);
+
+        fprintf(stderr, "generated Python script: %s\n", fname);
+
+        return 0;
+}
+
+struct scripting_ops python_scripting_ops = {
+        .name = "Python",
+        .start_script = python_start_script,
+        .stop_script = python_stop_script,
+        .process_event = python_process_event,
+        .generate_script = python_generate_script,
+};
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ce3a6c8abe76..0de7258e70a5 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,8 @@
+#define _FILE_OFFSET_BITS 64
+
 #include <linux/kernel.h>
 
+#include <byteswap.h>
 #include <unistd.h>
 #include <sys/types.h>
 
@@ -49,6 +52,11 @@ out_close:
         return -1;
 }
 
+static inline int perf_session__create_kernel_maps(struct perf_session *self)
+{
+        return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
+}
+
 struct perf_session *perf_session__new(const char *filename, int mode, bool force)
 {
         size_t len = filename ? strlen(filename) + 1 : 0;
@@ -66,13 +74,22 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
         self->mmap_window = 32;
         self->cwd = NULL;
         self->cwdlen = 0;
+        self->unknown_events = 0;
         map_groups__init(&self->kmaps);
 
-        if (perf_session__create_kernel_maps(self) < 0)
-                goto out_delete;
+        if (mode == O_RDONLY) {
+                if (perf_session__open(self, force) < 0)
+                        goto out_delete;
+        } else if (mode == O_WRONLY) {
+                /*
+                 * In O_RDONLY mode this will be performed when reading the
+                 * kernel MMAP event, in event__process_mmap().
+                 */
+                if (perf_session__create_kernel_maps(self) < 0)
+                        goto out_delete;
+        }
 
-        if (mode == O_RDONLY && perf_session__open(self, force) < 0)
-                goto out_delete;
+        self->sample_type = perf_header__sample_type(&self->header);
 out:
         return self;
 out_free:
@@ -148,3 +165,409 @@ struct symbol **perf_session__resolve_callchain(struct perf_session *self,
 
         return syms;
 }
+
+static int process_event_stub(event_t *event __used,
+                              struct perf_session *session __used)
+{
+        dump_printf(": unhandled!\n");
+        return 0;
+}
+
+static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
+{
+        if (handler->sample == NULL)
+                handler->sample = process_event_stub;
+        if (handler->mmap == NULL)
+                handler->mmap = process_event_stub;
+        if (handler->comm == NULL)
+                handler->comm = process_event_stub;
+        if (handler->fork == NULL)
+                handler->fork = process_event_stub;
+        if (handler->exit == NULL)
+                handler->exit = process_event_stub;
+        if (handler->lost == NULL)
+                handler->lost = process_event_stub;
+        if (handler->read == NULL)
+                handler->read = process_event_stub;
+        if (handler->throttle == NULL)
+                handler->throttle = process_event_stub;
+        if (handler->unthrottle == NULL)
+                handler->unthrottle = process_event_stub;
+}
+
+static const char *event__name[] = {
+        [0]                      = "TOTAL",
+        [PERF_RECORD_MMAP]       = "MMAP",
+        [PERF_RECORD_LOST]       = "LOST",
+        [PERF_RECORD_COMM]       = "COMM",
+        [PERF_RECORD_EXIT]       = "EXIT",
+        [PERF_RECORD_THROTTLE]   = "THROTTLE",
+        [PERF_RECORD_UNTHROTTLE] = "UNTHROTTLE",
+        [PERF_RECORD_FORK]       = "FORK",
+        [PERF_RECORD_READ]       = "READ",
+        [PERF_RECORD_SAMPLE]     = "SAMPLE",
+};
+
+unsigned long event__total[PERF_RECORD_MAX];
+
+void event__print_totals(void)
+{
+        int i;
+        for (i = 0; i < PERF_RECORD_MAX; ++i)
+                pr_info("%10s events: %10ld\n",
+                        event__name[i], event__total[i]);
+}
+
+void mem_bswap_64(void *src, int byte_size)
+{
+        u64 *m = src;
+
+        while (byte_size > 0) {
+                *m = bswap_64(*m);
+                byte_size -= sizeof(u64);
+                ++m;
+        }
+}
+
+static void event__all64_swap(event_t *self)
+{
+        struct perf_event_header *hdr = &self->header;
+        mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr));
+}
+
+static void event__comm_swap(event_t *self)
+{
+        self->comm.pid = bswap_32(self->comm.pid);
+        self->comm.tid = bswap_32(self->comm.tid);
+}
+
+static void event__mmap_swap(event_t *self)
+{
+        self->mmap.pid   = bswap_32(self->mmap.pid);
+        self->mmap.tid   = bswap_32(self->mmap.tid);
+        self->mmap.start = bswap_64(self->mmap.start);
+        self->mmap.len   = bswap_64(self->mmap.len);
+        self->mmap.pgoff = bswap_64(self->mmap.pgoff);
+}
+
+static void event__task_swap(event_t *self)
+{
+        self->fork.pid  = bswap_32(self->fork.pid);
+        self->fork.tid  = bswap_32(self->fork.tid);
+        self->fork.ppid = bswap_32(self->fork.ppid);
+        self->fork.ptid = bswap_32(self->fork.ptid);
+        self->fork.time = bswap_64(self->fork.time);
+}
+
+static void event__read_swap(event_t *self)
+{
+        self->read.pid          = bswap_32(self->read.pid);
+        self->read.tid          = bswap_32(self->read.tid);
+        self->read.value        = bswap_64(self->read.value);
+        self->read.time_enabled = bswap_64(self->read.time_enabled);
+        self->read.time_running = bswap_64(self->read.time_running);
+        self->read.id           = bswap_64(self->read.id);
+}
+
+typedef void (*event__swap_op)(event_t *self);
+
+static event__swap_op event__swap_ops[] = {
+        [PERF_RECORD_MMAP]   = event__mmap_swap,
+        [PERF_RECORD_COMM]   = event__comm_swap,
+        [PERF_RECORD_FORK]   = event__task_swap,
+        [PERF_RECORD_EXIT]   = event__task_swap,
+        [PERF_RECORD_LOST]   = event__all64_swap,
+        [PERF_RECORD_READ]   = event__read_swap,
+        [PERF_RECORD_SAMPLE] = event__all64_swap,
+        [PERF_RECORD_MAX]    = NULL,
+};
+
+static int perf_session__process_event(struct perf_session *self,
+                                       event_t *event,
+                                       struct perf_event_ops *ops,
+                                       u64 offset, u64 head)
+{
+        trace_event(event);
+
+        if (event->header.type < PERF_RECORD_MAX) {
+                dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
+                            offset + head, event->header.size,
+                            event__name[event->header.type]);
+                ++event__total[0];
+                ++event__total[event->header.type];
+        }
+
+        if (self->header.needs_swap && event__swap_ops[event->header.type])
+                event__swap_ops[event->header.type](event);
+
+        switch (event->header.type) {
+        case PERF_RECORD_SAMPLE:
+                return ops->sample(event, self);
+        case PERF_RECORD_MMAP:
+                return ops->mmap(event, self);
+        case PERF_RECORD_COMM:
+                return ops->comm(event, self);
+        case PERF_RECORD_FORK:
+                return ops->fork(event, self);
+        case PERF_RECORD_EXIT:
+                return ops->exit(event, self);
+        case PERF_RECORD_LOST:
+                return ops->lost(event, self);
+        case PERF_RECORD_READ:
+                return ops->read(event, self);
+        case PERF_RECORD_THROTTLE:
+                return ops->throttle(event, self);
+        case PERF_RECORD_UNTHROTTLE:
+                return ops->unthrottle(event, self);
+        default:
+                self->unknown_events++;
+                return -1;
+        }
+}
+
+void perf_event_header__bswap(struct perf_event_header *self)
+{
+        self->type = bswap_32(self->type);
+        self->misc = bswap_16(self->misc);
+        self->size = bswap_16(self->size);
+}
+
+int perf_header__read_build_ids(struct perf_header *self,
+                                int input, u64 offset, u64 size)
+{
+        struct build_id_event bev;
+        char filename[PATH_MAX];
+        u64 limit = offset + size;
+        int err = -1;
+
+        while (offset < limit) {
+                struct dso *dso;
+                ssize_t len;
+                struct list_head *head = &dsos__user;
+
+                if (read(input, &bev, sizeof(bev)) != sizeof(bev))
+                        goto out;
+
+                if (self->needs_swap)
+                        perf_event_header__bswap(&bev.header);
+
+                len = bev.header.size - sizeof(bev);
+                if (read(input, filename, len) != len)
+                        goto out;
+
+                if (bev.header.misc & PERF_RECORD_MISC_KERNEL)
+                        head = &dsos__kernel;
+
+                dso = __dsos__findnew(head, filename);
+                if (dso != NULL) {
+                        dso__set_build_id(dso, &bev.build_id);
+                        if (head == &dsos__kernel && filename[0] == '[')
+                                dso->kernel = 1;
+                }
+
+                offset += bev.header.size;
+        }
+        err = 0;
+out:
+        return err;
+}
+
+static struct thread *perf_session__register_idle_thread(struct perf_session *self)
+{
+        struct thread *thread = perf_session__findnew(self, 0);
+
+        if (thread == NULL || thread__set_comm(thread, "swapper")) {
+                pr_err("problem inserting idle task.\n");
+                thread = NULL;
+        }
+
+        return thread;
+}
+
+int __perf_session__process_events(struct perf_session *self,
+                                   u64 data_offset, u64 data_size,
+                                   u64 file_size, struct perf_event_ops *ops)
+{
+        int err, mmap_prot, mmap_flags;
+        u64 head, shift;
+        u64 offset = 0;
+        size_t  page_size;
+        event_t *event;
+        uint32_t size;
+        char *buf;
+
+        perf_event_ops__fill_defaults(ops);
+
+        page_size = sysconf(_SC_PAGESIZE);
+
+        head = data_offset;
+        shift = page_size * (head / page_size);
+        offset += shift;
+        head -= shift;
+
+        mmap_prot  = PROT_READ;
+        mmap_flags = MAP_SHARED;
+
+        if (self->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);
+        if (buf == MAP_FAILED) {
+                pr_err("failed to mmap file\n");
+                err = -errno;
+                goto out_err;
+        }
+
+more:
+        event = (event_t *)(buf + head);
+
+        if (self->header.needs_swap)
+                perf_event_header__bswap(&event->header);
+        size = event->header.size;
+        if (size == 0)
+                size = 8;
+
+        if (head + event->header.size >= page_size * self->mmap_window) {
+                int munmap_ret;
+
+                shift = page_size * (head / page_size);
+
+                munmap_ret = munmap(buf, page_size * self->mmap_window);
+                assert(munmap_ret == 0);
+
+                offset += shift;
+                head -= shift;
+                goto remap;
+        }
+
+        size = event->header.size;
+
+        dump_printf("\n%#Lx [%#x]: event: %d\n",
+                    offset + head, event->header.size, event->header.type);
+
+        if (size == 0 ||
+            perf_session__process_event(self, event, ops, offset, head) < 0) {
+                dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+                            offset + head, event->header.size,
+                            event->header.type);
+                /*
+                 * assume we lost track of the stream, check alignment, and
+                 * increment a single u64 in the hope to catch on again 'soon'.
+                 */
+                if (unlikely(head & 7))
+                        head &= ~7ULL;
+
+                size = 8;
+        }
+
+        head += size;
+
+        if (offset + head >= data_offset + data_size)
+                goto done;
+
+        if (offset + head < file_size)
+                goto more;
+done:
+        err = 0;
+out_err:
+        return err;
+}
+
+int perf_session__process_events(struct perf_session *self,
+                                 struct perf_event_ops *ops)
+{
+        int err;
+
+        if (perf_session__register_idle_thread(self) == NULL)
+                return -ENOMEM;
+
+        if (!symbol_conf.full_paths) {
+                char bf[PATH_MAX];
+
+                if (getcwd(bf, sizeof(bf)) == NULL) {
+                        err = -errno;
+out_getcwd_err:
+                        pr_err("failed to get the current directory\n");
+                        goto out_err;
+                }
+                self->cwd = strdup(bf);
+                if (self->cwd == NULL) {
+                        err = -ENOMEM;
+                        goto out_getcwd_err;
+                }
+                self->cwdlen = strlen(self->cwd);
+        }
+
+        err = __perf_session__process_events(self, self->header.data_offset,
+                                             self->header.data_size,
+                                             self->size, ops);
+out_err:
+        return err;
+}
+
+bool perf_session__has_traces(struct perf_session *self, const char *msg)
+{
+        if (!(self->sample_type & PERF_SAMPLE_RAW)) {
+                pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
+                return false;
+        }
+
+        return true;
+}
+
+int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
+                                             const char *symbol_name,
+                                             u64 addr)
+{
+        char *bracket;
+        enum map_type i;
+
+        self->ref_reloc_sym.name = strdup(symbol_name);
+        if (self->ref_reloc_sym.name == NULL)
+                return -ENOMEM;
+
+        bracket = strchr(self->ref_reloc_sym.name, ']');
+        if (bracket)
+                *bracket = '\0';
+
+        self->ref_reloc_sym.addr = addr;
+
+        for (i = 0; i < MAP__NR_TYPES; ++i) {
+                struct kmap *kmap = map__kmap(self->vmlinux_maps[i]);
+                kmap->ref_reloc_sym = &self->ref_reloc_sym;
+        }
+
+        return 0;
+}
+
+static u64 map__reloc_map_ip(struct map *map, u64 ip)
+{
+        return ip + (s64)map->pgoff;
+}
+
+static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
+{
+        return ip - (s64)map->pgoff;
+}
+
+void map__reloc_vmlinux(struct map *self)
+{
+        struct kmap *kmap = map__kmap(self);
+        s64 reloc;
+
+        if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
+                return;
+
+        reloc = (kmap->ref_reloc_sym->unrelocated_addr -
+                 kmap->ref_reloc_sym->addr);
+
+        if (!reloc)
+                return;
+
+        self->map_ip   = map__reloc_map_ip;
+        self->unmap_ip = map__reloc_unmap_ip;
+        self->pgoff    = reloc;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 32eaa1bada06..31950fcd8a4d 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -3,13 +3,13 @@
 
 #include "event.h"
 #include "header.h"
+#include "symbol.h"
 #include "thread.h"
 #include <linux/rbtree.h>
 #include "../../../include/linux/perf_event.h"
 
 struct ip_callchain;
 struct thread;
-struct symbol;
 
 struct perf_session {
         struct perf_header      header;
@@ -18,10 +18,13 @@ struct perf_session {
         struct map_groups       kmaps;
         struct rb_root          threads;
         struct thread           *last_match;
+        struct map              *vmlinux_maps[MAP__NR_TYPES];
         struct events_stats     events_stats;
         unsigned long           event_total[PERF_RECORD_MAX];
+        unsigned long           unknown_events;
         struct rb_root          hists;
         u64                     sample_type;
+        struct ref_reloc_sym    ref_reloc_sym;
         int                     fd;
         int                     cwdlen;
         char                    *cwd;
@@ -31,23 +34,25 @@ struct perf_session {
 typedef int (*event_op)(event_t *self, struct perf_session *session);
 
 struct perf_event_ops {
-        event_op        process_sample_event;
-        event_op        process_mmap_event;
-        event_op        process_comm_event;
-        event_op        process_fork_event;
-        event_op        process_exit_event;
-        event_op        process_lost_event;
-        event_op        process_read_event;
-        event_op        process_throttle_event;
-        event_op        process_unthrottle_event;
-        int             (*sample_type_check)(struct perf_session *session);
-        unsigned long   total_unknown;
-        bool            full_paths;
+        event_op sample,
+                 mmap,
+                 comm,
+                 fork,
+                 exit,
+                 lost,
+                 read,
+                 throttle,
+                 unthrottle;
 };
 
 struct perf_session *perf_session__new(const char *filename, int mode, bool force);
 void perf_session__delete(struct perf_session *self);
 
+void perf_event_header__bswap(struct perf_event_header *self);
+
+int __perf_session__process_events(struct perf_session *self,
+                                   u64 data_offset, u64 data_size, u64 size,
+                                   struct perf_event_ops *ops);
 int perf_session__process_events(struct perf_session *self,
                                  struct perf_event_ops *event_ops);
 
@@ -56,6 +61,28 @@ struct symbol **perf_session__resolve_callchain(struct perf_session *self,
                                                 struct ip_callchain *chain,
                                                 struct symbol **parent);
 
-int perf_header__read_build_ids(int input, u64 offset, u64 file_size);
+bool perf_session__has_traces(struct perf_session *self, const char *msg);
+
+int perf_header__read_build_ids(struct perf_header *self, int input,
+                                u64 offset, u64 file_size);
+
+int perf_session__set_kallsyms_ref_reloc_sym(struct perf_session *self,
+                                             const char *symbol_name,
+                                             u64 addr);
+
+void mem_bswap_64(void *src, int byte_size);
+
+static inline int __perf_session__create_kernel_maps(struct perf_session *self,
+                                                struct dso *kernel)
+{
+        return __map_groups__create_kernel_maps(&self->kmaps,
+                                                self->vmlinux_maps, kernel);
+}
 
+static inline struct map *
+        perf_session__new_module_map(struct perf_session *self,
+                                     u64 start, const char *filename)
+{
+        return map_groups__new_module(&self->kmaps, start, filename);
+}
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 5352d7dccc61..a175949ed216 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -227,16 +227,73 @@ fail:
         return NULL;
 }
 
-/* Glob expression pattern matching */
-bool strglobmatch(const char *str, const char *pat)
+/* Character class matching */
+static bool __match_charclass(const char *pat, char c, const char **npat)
+{
+        bool complement = false, ret = true;
+
+        if (*pat == '!') {
+                complement = true;
+                pat++;
+        }
+        if (*pat++ == c)        /* First character is special */
+                goto end;
+
+        while (*pat && *pat != ']') {   /* Matching */
+                if (*pat == '-' && *(pat + 1) != ']') { /* Range */
+                        if (*(pat - 1) <= c && c <= *(pat + 1))
+                                goto end;
+                        if (*(pat - 1) > *(pat + 1))
+                                goto error;
+                        pat += 2;
+                } else if (*pat++ == c)
+                        goto end;
+        }
+        if (!*pat)
+                goto error;
+        ret = false;
+
+end:
+        while (*pat && *pat != ']')     /* Searching closing */
+                pat++;
+        if (!*pat)
+                goto error;
+        *npat = pat + 1;
+        return complement ? !ret : ret;
+
+error:
+        return false;
+}
+
+/* Glob/lazy pattern matching */
+static bool __match_glob(const char *str, const char *pat, bool ignore_space)
 {
         while (*str && *pat && *pat != '*') {
-                if (*pat == '?') {
+                if (ignore_space) {
+                        /* Ignore spaces for lazy matching */
+                        if (isspace(*str)) {
+                                str++;
+                                continue;
+                        }
+                        if (isspace(*pat)) {
+                                pat++;
+                                continue;
+                        }
+                }
+                if (*pat == '?') {      /* Matches any single character */
                         str++;
                         pat++;
-                } else
-                        if (*str++ != *pat++)
+                        continue;
+                } else if (*pat == '[') /* Character classes/Ranges */
+                        if (__match_charclass(pat + 1, *str, &pat)) {
+                                str++;
+                                continue;
+                        } else
                                 return false;
+                else if (*pat == '\\') /* Escaped char match as normal char */
+                        pat++;
+                if (*str++ != *pat++)
+                        return false;
         }
         /* Check wild card */
         if (*pat == '*') {
@@ -251,3 +308,32 @@ bool strglobmatch(const char *str, const char *pat)
         return !*str && !*pat;
 }
 
+/**
+ * strglobmatch - glob expression pattern matching
+ * @str: the target string to match
+ * @pat: the pattern string to match
+ *
+ * This returns true if the @str matches @pat. @pat can includes wildcards
+ * ('*','?') and character classes ([CHARS], complementation and ranges are
+ * also supported). Also, this supports escape character ('\') to use special
+ * characters as normal character.
+ *
+ * Note: if @pat syntax is broken, this always returns false.
+ */
+bool strglobmatch(const char *str, const char *pat)
+{
+        return __match_glob(str, pat, false);
+}
+
+/**
+ * strlazymatch - matching pattern strings lazily with glob pattern
+ * @str: the target string to match
+ * @pat: the pattern string to match
+ *
+ * This is similar to strglobmatch, except this ignores spaces in
+ * the target string.
+ */
+bool strlazymatch(const char *str, const char *pat)
+{
+        return __match_glob(str, pat, true);
+}
diff --git a/tools/perf/util/string.h b/tools/perf/util/string.h
index 02ede58c54b4..542e44de3719 100644
--- a/tools/perf/util/string.h
+++ b/tools/perf/util/string.h
@@ -10,6 +10,7 @@ s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ab92763edb03..323c0aea0a91 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1,6 +1,5 @@
 #include "util.h"
 #include "../perf.h"
-#include "session.h"
 #include "sort.h"
 #include "string.h"
 #include "symbol.h"
@@ -22,6 +21,7 @@
 enum dso_origin {
         DSO__ORIG_KERNEL = 0,
         DSO__ORIG_JAVA_JIT,
+        DSO__ORIG_BUILD_ID_CACHE,
         DSO__ORIG_FEDORA,
         DSO__ORIG_UBUNTU,
         DSO__ORIG_BUILDID,
@@ -33,7 +33,7 @@ enum dso_origin {
 static void dsos__add(struct list_head *head, struct dso *dso);
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 static int dso__load_kernel_sym(struct dso *self, struct map *map,
-                                struct perf_session *session, symbol_filter_t filter);
+                                symbol_filter_t filter);
 static int vmlinux_path__nr_entries;
 static char **vmlinux_path;
 
@@ -53,17 +53,12 @@ bool dso__sorted_by_name(const struct dso *self, enum map_type type)
         return self->sorted_by_name & (1 << type);
 }
 
-static void dso__set_loaded(struct dso *self, enum map_type type)
-{
-        self->loaded |= (1 << type);
-}
-
 static void dso__set_sorted_by_name(struct dso *self, enum map_type type)
 {
         self->sorted_by_name |= (1 << type);
 }
 
-static bool symbol_type__is_a(char symbol_type, enum map_type map_type)
+bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 {
         switch (map_type) {
         case MAP__FUNCTION:
@@ -142,14 +137,14 @@ static struct symbol *symbol__new(u64 start, u64 len, const char *name)
         self->start = start;
         self->end   = len ? start + len - 1 : start;
 
-        pr_debug3("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
+        pr_debug4("%s: %s %#Lx-%#Lx\n", __func__, name, start, self->end);
 
         memcpy(self->name, name, namelen);
 
         return self;
 }
 
-static void symbol__delete(struct symbol *self)
+void symbol__delete(struct symbol *self)
 {
         free(((void *)self) - symbol_conf.priv_size);
 }
@@ -160,7 +155,7 @@ static size_t symbol__fprintf(struct symbol *self, FILE *fp)
                        self->start, self->end, self->name);
 }
 
-static void dso__set_long_name(struct dso *self, char *name)
+void dso__set_long_name(struct dso *self, char *name)
 {
         if (name == NULL)
                 return;
@@ -175,7 +170,7 @@ static void dso__set_basename(struct dso *self)
 
 struct dso *dso__new(const char *name)
 {
-        struct dso *self = malloc(sizeof(*self) + strlen(name) + 1);
+        struct dso *self = zalloc(sizeof(*self) + strlen(name) + 1);
 
         if (self != NULL) {
                 int i;
@@ -344,10 +339,10 @@ void dso__sort_by_name(struct dso *self, enum map_type type)
                                      &self->symbols[type]);
 }
 
-int build_id__sprintf(u8 *self, int len, char *bf)
+int build_id__sprintf(const u8 *self, int len, char *bf)
 {
         char *bid = bf;
-        u8 *raw = self;
+        const u8 *raw = self;
         int i;
 
         for (i = 0; i < len; ++i) {
@@ -372,6 +367,10 @@ size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
         struct rb_node *nd;
         size_t ret = fprintf(fp, "dso: %s (", self->short_name);
 
+        if (self->short_name != self->long_name)
+                ret += fprintf(fp, "%s, ", self->long_name);
+        ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
+                       self->loaded ? "" : "NOT ");
         ret += dso__fprintf_buildid(self, fp);
         ret += fprintf(fp, ")\n");
         for (nd = rb_first(&self->symbols[type]); nd; nd = rb_next(nd)) {
@@ -382,24 +381,20 @@ size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp)
         return ret;
 }
 
-/*
- * Loads the function entries in /proc/kallsyms into kernel_map->dso,
- * so that we can in the next step set the symbol ->end address and then
- * call kernel_maps__split_kallsyms.
- */
-static int dso__load_all_kallsyms(struct dso *self, struct map *map)
+int kallsyms__parse(const char *filename, void *arg,
+                    int (*process_symbol)(void *arg, const char *name,
+                                                     char type, u64 start))
 {
         char *line = NULL;
         size_t n;
-        struct rb_root *root = &self->symbols[map->type];
-        FILE *file = fopen("/proc/kallsyms", "r");
+        int err = 0;
+        FILE *file = fopen(filename, "r");
 
         if (file == NULL)
                 goto out_failure;
 
         while (!feof(file)) {
                 u64 start;
-                struct symbol *sym;
                 int line_len, len;
                 char symbol_type;
                 char *symbol_name;
@@ -420,43 +415,72 @@ static int dso__load_all_kallsyms(struct dso *self, struct map *map)
                         continue;
 
                 symbol_type = toupper(line[len]);
-                if (!symbol_type__is_a(symbol_type, map->type))
-                        continue;
-
                 symbol_name = line + len + 2;
-                /*
-                 * Will fix up the end later, when we have all symbols sorted.
-                 */
-                sym = symbol__new(start, 0, symbol_name);
 
-                if (sym == NULL)
-                        goto out_delete_line;
-                /*
-                 * We will pass the symbols to the filter later, in
-                 * map__split_kallsyms, when we have split the maps per module
-                 */
-                symbols__insert(root, sym);
+                err = process_symbol(arg, symbol_name, symbol_type, start);
+                if (err)
+                        break;
         }
 
         free(line);
         fclose(file);
+        return err;
 
-        return 0;
-
-out_delete_line:
-        free(line);
 out_failure:
         return -1;
 }
 
+struct process_kallsyms_args {
+        struct map *map;
+        struct dso *dso;
+};
+
+static int map__process_kallsym_symbol(void *arg, const char *name,
+                                       char type, u64 start)
+{
+        struct symbol *sym;
+        struct process_kallsyms_args *a = arg;
+        struct rb_root *root = &a->dso->symbols[a->map->type];
+
+        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, name);
+
+        if (sym == NULL)
+                return -ENOMEM;
+        /*
+         * We will pass the symbols to the filter later, in
+         * map__split_kallsyms, when we have split the maps per module
+         */
+        symbols__insert(root, sym);
+        return 0;
+}
+
+/*
+ * Loads the function entries in /proc/kallsyms into kernel_map->dso,
+ * so that we can in the next step set the symbol ->end address and then
+ * call kernel_maps__split_kallsyms.
+ */
+static int dso__load_all_kallsyms(struct dso *self, const char *filename,
+                                  struct map *map)
+{
+        struct process_kallsyms_args args = { .map = map, .dso = self, };
+        return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
+}
+
 /*
  * Split the symbols into maps, making sure there are no overlaps, i.e. the
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
 static int dso__split_kallsyms(struct dso *self, struct map *map,
-                               struct perf_session *session, symbol_filter_t filter)
+                               symbol_filter_t filter)
 {
+        struct map_groups *kmaps = map__kmap(map)->kmaps;
         struct map *curr_map = map;
         struct symbol *pos;
         int count = 0;
@@ -477,13 +501,17 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
 
                         *module++ = '\0';
 
-                        if (strcmp(self->name, module)) {
-                                curr_map = map_groups__find_by_name(&session->kmaps, map->type, module);
+                        if (strcmp(curr_map->dso->short_name, module)) {
+                                curr_map = map_groups__find_by_name(kmaps, map->type, module);
                                 if (curr_map == NULL) {
                                         pr_debug("/proc/{kallsyms,modules} "
-                                                 "inconsistency!\n");
+                                                 "inconsistency while looking "
+                                                 "for \"%s\" module!\n", module);
                                         return -1;
                                 }
+
+                                if (curr_map->dso->loaded)
+                                        goto discard_symbol;
                         }
                         /*
                          * So that we look just like we get from .ko files,
@@ -503,13 +531,13 @@ static int dso__split_kallsyms(struct dso *self, struct map *map,
                                 return -1;
 
                         curr_map = map__new2(pos->start, dso, map->type);
-                        if (map == NULL) {
+                        if (curr_map == NULL) {
                                 dso__delete(dso);
                                 return -1;
                         }
 
                         curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
-                        map_groups__insert(&session->kmaps, curr_map);
+                        map_groups__insert(kmaps, curr_map);
                         ++kernel_range;
                 }
 
@@ -528,17 +556,16 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
         return count;
 }
 
-
-static int dso__load_kallsyms(struct dso *self, struct map *map,
-                              struct perf_session *session, symbol_filter_t filter)
+int dso__load_kallsyms(struct dso *self, const char *filename,
+                       struct map *map, symbol_filter_t filter)
 {
-        if (dso__load_all_kallsyms(self, map) < 0)
+        if (dso__load_all_kallsyms(self, filename, map) < 0)
                 return -1;
 
         symbols__fixup_end(&self->symbols[map->type]);
         self->origin = DSO__ORIG_KERNEL;
 
-        return dso__split_kallsyms(self, map, session, filter);
+        return dso__split_kallsyms(self, map, filter);
 }
 
 static int dso__load_perf_map(struct dso *self, struct map *map,
@@ -864,10 +891,10 @@ static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type
         }
 }
 
-static int dso__load_sym(struct dso *self, struct map *map,
-                         struct perf_session *session, const char *name, int fd,
-                         symbol_filter_t filter, int kernel, int kmodule)
+static int dso__load_sym(struct dso *self, struct map *map, const char *name,
+                         int fd, symbol_filter_t filter, int kmodule)
 {
+        struct kmap *kmap = self->kernel ? map__kmap(map) : NULL;
         struct map *curr_map = map;
         struct dso *curr_dso = self;
         size_t dso_name_len = strlen(self->short_name);
@@ -924,7 +951,7 @@ static int dso__load_sym(struct dso *self, struct map *map,
         nr_syms = shdr.sh_size / shdr.sh_entsize;
 
         memset(&sym, 0, sizeof(sym));
-        if (!kernel) {
+        if (!self->kernel) {
                 self->adjust_symbols = (ehdr.e_type == ET_EXEC ||
                                 elf_section_by_name(elf, &ehdr, &shdr,
                                                      ".gnu.prelink_undo",
@@ -933,11 +960,15 @@ static int dso__load_sym(struct dso *self, struct map *map,
 
         elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
                 struct symbol *f;
-                const char *elf_name;
+                const char *elf_name = elf_sym__name(&sym, symstrs);
                 char *demangled = NULL;
                 int is_label = elf_sym__is_label(&sym);
                 const char *section_name;
 
+                if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
+                    strcmp(elf_name, kmap->ref_reloc_sym->name) == 0)
+                        kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+
                 if (!is_label && !elf_sym__is_a(&sym, map->type))
                         continue;
 
@@ -950,10 +981,9 @@ static int dso__load_sym(struct dso *self, struct map *map,
                 if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
                         continue;
 
-                elf_name = elf_sym__name(&sym, symstrs);
                 section_name = elf_sec__name(&shdr, secstrs);
 
-                if (kernel || kmodule) {
+                if (self->kernel || kmodule) {
                         char dso_name[PATH_MAX];
 
                         if (strcmp(section_name,
@@ -969,7 +999,7 @@ static int dso__load_sym(struct dso *self, struct map *map,
                         snprintf(dso_name, sizeof(dso_name),
                                  "%s%s", self->short_name, section_name);
 
-                        curr_map = map_groups__find_by_name(&session->kmaps, map->type, dso_name);
+                        curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
                         if (curr_map == NULL) {
                                 u64 start = sym.st_value;
 
@@ -980,7 +1010,7 @@ static int dso__load_sym(struct dso *self, struct map *map,
                                 if (curr_dso == NULL)
                                         goto out_elf_end;
                                 curr_map = map__new2(start, curr_dso,
-                                                     MAP__FUNCTION);
+                                                     map->type);
                                 if (curr_map == NULL) {
                                         dso__delete(curr_dso);
                                         goto out_elf_end;
@@ -988,8 +1018,9 @@ static int dso__load_sym(struct dso *self, struct map *map,
                                 curr_map->map_ip = identity__map_ip;
                                 curr_map->unmap_ip = identity__map_ip;
                                 curr_dso->origin = DSO__ORIG_KERNEL;
-                                map_groups__insert(&session->kmaps, curr_map);
+                                map_groups__insert(kmap->kmaps, curr_map);
                                 dsos__add(&dsos__kernel, curr_dso);
+                                dso__set_loaded(curr_dso, map->type);
                         } else
                                 curr_dso = curr_map->dso;
 
@@ -997,9 +1028,10 @@ static int dso__load_sym(struct dso *self, struct map *map,
                 }
 
                 if (curr_dso->adjust_symbols) {
-                        pr_debug2("adjusting symbol: st_value: %Lx sh_addr: "
-                                  "%Lx sh_offset: %Lx\n", (u64)sym.st_value,
-                                  (u64)shdr.sh_addr, (u64)shdr.sh_offset);
+                        pr_debug4("%s: adjusting symbol: st_value: %#Lx "
+                                  "sh_addr: %#Lx sh_offset: %#Lx\n", __func__,
+                                  (u64)sym.st_value, (u64)shdr.sh_addr,
+                                  (u64)shdr.sh_offset);
                         sym.st_value -= shdr.sh_addr - shdr.sh_offset;
                 }
                 /*
@@ -1027,8 +1059,16 @@ new_symbol:
         /*
          * For misannotated, zeroed, ASM function sizes.
          */
-        if (nr > 0)
+        if (nr > 0) {
                 symbols__fixup_end(&self->symbols[map->type]);
+                if (kmap) {
+                        /*
+                         * We need to fixup this here too because we create new
+                         * maps here, for things like vsyscall sections.
+                         */
+                        __map_groups__fixup_end(kmap->kmaps, map->type);
+                }
+        }
         err = nr;
 out_elf_end:
         elf_end(elf);
@@ -1041,25 +1081,28 @@ static bool dso__build_id_equal(const struct dso *self, u8 *build_id)
         return memcmp(self->build_id, build_id, sizeof(self->build_id)) == 0;
 }
 
-static bool __dsos__read_build_ids(struct list_head *head)
+static bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 {
         bool have_build_id = false;
         struct dso *pos;
 
-        list_for_each_entry(pos, head, node)
+        list_for_each_entry(pos, head, node) {
+                if (with_hits && !pos->hit)
+                        continue;
                 if (filename__read_build_id(pos->long_name, pos->build_id,
                                             sizeof(pos->build_id)) > 0) {
                         have_build_id     = true;
                         pos->has_build_id = true;
                 }
+        }
 
         return have_build_id;
 }
 
-bool dsos__read_build_ids(void)
+bool dsos__read_build_ids(bool with_hits)
 {
-        bool kbuildids = __dsos__read_build_ids(&dsos__kernel),
-             ubuildids = __dsos__read_build_ids(&dsos__user);
+        bool kbuildids = __dsos__read_build_ids(&dsos__kernel, with_hits),
+             ubuildids = __dsos__read_build_ids(&dsos__user, with_hits);
         return kbuildids || ubuildids;
 }
 
@@ -1191,6 +1234,7 @@ char dso__symtab_origin(const struct dso *self)
         static const char origin[] = {
                 [DSO__ORIG_KERNEL] =   'k',
                 [DSO__ORIG_JAVA_JIT] = 'j',
+                [DSO__ORIG_BUILD_ID_CACHE] = 'B',
                 [DSO__ORIG_FEDORA] =   'f',
                 [DSO__ORIG_UBUNTU] =   'u',
                 [DSO__ORIG_BUILDID] =  'b',
@@ -1203,19 +1247,19 @@ char dso__symtab_origin(const struct dso *self)
         return origin[self->origin];
 }
 
-int dso__load(struct dso *self, struct map *map, struct perf_session *session,
-              symbol_filter_t filter)
+int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 {
         int size = PATH_MAX;
         char *name;
         u8 build_id[BUILD_ID_SIZE];
+        char build_id_hex[BUILD_ID_SIZE * 2 + 1];
         int ret = -1;
         int fd;
 
         dso__set_loaded(self, map->type);
 
         if (self->kernel)
-                return dso__load_kernel_sym(self, map, session, filter);
+                return dso__load_kernel_sym(self, map, filter);
 
         name = malloc(size);
         if (!name)
@@ -1230,8 +1274,16 @@ int dso__load(struct dso *self, struct map *map, struct perf_session *session,
                 return ret;
         }
 
-        self->origin = DSO__ORIG_FEDORA - 1;
+        self->origin = DSO__ORIG_BUILD_ID_CACHE;
 
+        if (self->has_build_id) {
+                build_id__sprintf(self->build_id, sizeof(self->build_id),
+                                  build_id_hex);
+                snprintf(name, size, "%s/%s/.build-id/%.2s/%s",
+                         getenv("HOME"), DEBUG_CACHE_DIR,
+                         build_id_hex, build_id_hex + 2);
+                goto open_file;
+        }
 more:
         do {
                 self->origin++;
@@ -1247,8 +1299,6 @@ more:
                 case DSO__ORIG_BUILDID:
                         if (filename__read_build_id(self->long_name, build_id,
                                                     sizeof(build_id))) {
-                                char build_id_hex[BUILD_ID_SIZE * 2 + 1];
-
                                 build_id__sprintf(build_id, sizeof(build_id),
                                                   build_id_hex);
                                 snprintf(name, size,
@@ -1276,11 +1326,11 @@ compare_build_id:
                         if (!dso__build_id_equal(self, build_id))
                                 goto more;
                 }
-
+open_file:
                 fd = open(name, O_RDONLY);
         } while (fd < 0);
 
-        ret = dso__load_sym(self, map, NULL, name, fd, filter, 0, 0);
+        ret = dso__load_sym(self, map, name, fd, filter, 0);
         close(fd);
 
         /*
@@ -1309,14 +1359,34 @@ struct map *map_groups__find_by_name(struct map_groups *self,
         for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
                 struct map *map = rb_entry(nd, struct map, rb_node);
 
-                if (map->dso && strcmp(map->dso->name, name) == 0)
+                if (map->dso && strcmp(map->dso->short_name, name) == 0)
                         return map;
         }
 
         return NULL;
 }
 
-static int perf_session__set_modules_path_dir(struct perf_session *self, char *dirname)
+static int dso__kernel_module_get_build_id(struct dso *self)
+{
+        char filename[PATH_MAX];
+        /*
+         * kernel module short names are of the form "[module]" and
+         * we need just "module" here.
+         */
+        const char *name = self->short_name + 1;
+
+        snprintf(filename, sizeof(filename),
+                 "/sys/module/%.*s/notes/.note.gnu.build-id",
+                 (int)strlen(name - 1), name);
+
+        if (sysfs__read_build_id(filename, self->build_id,
+                                 sizeof(self->build_id)) == 0)
+                self->has_build_id = true;
+
+        return 0;
+}
+
+static int map_groups__set_modules_path_dir(struct map_groups *self, char *dirname)
 {
         struct dirent *dent;
         DIR *dir = opendir(dirname);
@@ -1336,7 +1406,7 @@ static int perf_session__set_modules_path_dir(struct perf_session *self, char *d
 
                         snprintf(path, sizeof(path), "%s/%s",
                                  dirname, dent->d_name);
-                        if (perf_session__set_modules_path_dir(self, path) < 0)
+                        if (map_groups__set_modules_path_dir(self, path) < 0)
                                 goto failure;
                 } else {
                         char *dot = strrchr(dent->d_name, '.'),
@@ -1350,7 +1420,7 @@ static int perf_session__set_modules_path_dir(struct perf_session *self, char *d
                                  (int)(dot - dent->d_name), dent->d_name);
 
                         strxfrchar(dso_name, '-', '_');
-                        map = map_groups__find_by_name(&self->kmaps, MAP__FUNCTION, dso_name);
+                        map = map_groups__find_by_name(self, MAP__FUNCTION, dso_name);
                         if (map == NULL)
                                 continue;
 
@@ -1361,6 +1431,7 @@ static int perf_session__set_modules_path_dir(struct perf_session *self, char *d
                         if (long_name == NULL)
                                 goto failure;
                         dso__set_long_name(map->dso, long_name);
+                        dso__kernel_module_get_build_id(map->dso);
                 }
         }
 
@@ -1370,7 +1441,7 @@ failure:
         return -1;
 }
 
-static int perf_session__set_modules_path(struct perf_session *self)
+static int map_groups__set_modules_path(struct map_groups *self)
 {
         struct utsname uts;
         char modules_path[PATH_MAX];
@@ -1381,7 +1452,7 @@ static int perf_session__set_modules_path(struct perf_session *self)
         snprintf(modules_path, sizeof(modules_path), "/lib/modules/%s/kernel",
                  uts.release);
 
-        return perf_session__set_modules_path_dir(self, modules_path);
+        return map_groups__set_modules_path_dir(self, modules_path);
 }
 
 /*
@@ -1391,8 +1462,8 @@ static int perf_session__set_modules_path(struct perf_session *self)
  */
 static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 {
-        struct map *self = malloc(sizeof(*self));
-
+        struct map *self = zalloc(sizeof(*self) +
+                                  (dso->kernel ? sizeof(struct kmap) : 0));
         if (self != NULL) {
                 /*
                  * ->end will be filled after we load all the symbols
@@ -1403,7 +1474,25 @@ static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
         return self;
 }
 
-static int perf_session__create_module_maps(struct perf_session *self)
+struct map *map_groups__new_module(struct map_groups *self, u64 start,
+                                   const char *filename)
+{
+        struct map *map;
+        struct dso *dso = __dsos__findnew(&dsos__kernel, filename);
+
+        if (dso == NULL)
+                return NULL;
+
+        map = map__new2(start, dso, MAP__FUNCTION);
+        if (map == NULL)
+                return NULL;
+
+        dso->origin = DSO__ORIG_KMODULE;
+        map_groups__insert(self, map);
+        return map;
+}
+
+static int map_groups__create_modules(struct map_groups *self)
 {
         char *line = NULL;
         size_t n;
@@ -1416,7 +1505,6 @@ static int perf_session__create_module_maps(struct perf_session *self)
         while (!feof(file)) {
                 char name[PATH_MAX];
                 u64 start;
-                struct dso *dso;
                 char *sep;
                 int line_len;
 
@@ -1442,32 +1530,16 @@ static int perf_session__create_module_maps(struct perf_session *self)
                 *sep = '\0';
 
                 snprintf(name, sizeof(name), "[%s]", line);
-                dso = dso__new(name);
-
-                if (dso == NULL)
-                        goto out_delete_line;
-
-                map = map__new2(start, dso, MAP__FUNCTION);
-                if (map == NULL) {
-                        dso__delete(dso);
+                map = map_groups__new_module(self, start, name);
+                if (map == NULL)
                         goto out_delete_line;
-                }
-
-                snprintf(name, sizeof(name),
-                         "/sys/module/%s/notes/.note.gnu.build-id", line);
-                if (sysfs__read_build_id(name, dso->build_id,
-                                         sizeof(dso->build_id)) == 0)
-                        dso->has_build_id = true;
-
-                dso->origin = DSO__ORIG_KMODULE;
-                map_groups__insert(&self->kmaps, map);
-                dsos__add(&dsos__kernel, dso);
+                dso__kernel_module_get_build_id(map->dso);
         }
 
         free(line);
         fclose(file);
 
-        return perf_session__set_modules_path(self);
+        return map_groups__set_modules_path(self);
 
 out_delete_line:
         free(line);
@@ -1476,7 +1548,6 @@ out_failure:
 }
 
 static int dso__load_vmlinux(struct dso *self, struct map *map,
-                             struct perf_session *session,
                              const char *vmlinux, symbol_filter_t filter)
 {
         int err = -1, fd;
@@ -1510,51 +1581,124 @@ static int dso__load_vmlinux(struct dso *self, struct map *map,
                 return -1;
 
         dso__set_loaded(self, map->type);
-        err = dso__load_sym(self, map, session, self->long_name, fd, filter, 1, 0);
+        err = dso__load_sym(self, map, vmlinux, fd, filter, 0);
         close(fd);
 
+        if (err > 0)
+                pr_debug("Using %s for symbols\n", vmlinux);
+
+        return err;
+}
+
+int dso__load_vmlinux_path(struct dso *self, struct map *map,
+                           symbol_filter_t filter)
+{
+        int i, err = 0;
+
+        pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+                 vmlinux_path__nr_entries);
+
+        for (i = 0; i < vmlinux_path__nr_entries; ++i) {
+                err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
+                if (err > 0) {
+                        dso__set_long_name(self, strdup(vmlinux_path[i]));
+                        break;
+                }
+        }
+
         return err;
 }
 
 static int dso__load_kernel_sym(struct dso *self, struct map *map,
-                                struct perf_session *session, symbol_filter_t filter)
+                                symbol_filter_t filter)
 {
         int err;
-        bool is_kallsyms;
+        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.
+         *
+         * 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
+         * vmlinux file, obviously we can't fallback to another vmlinux (a
+         * x86_86 one, on the machine where analysis is being performed, say),
+         * or worse, /proc/kallsyms.
+         *
+         * If the specified file _has_ a build-id and there is a build-id
+         * section in the perf.data file, we will still do the expected
+         * validation in dso__load_vmlinux and will bail out if they don't
+         * match.
+         */
+        if (symbol_conf.vmlinux_name != NULL) {
+                err = dso__load_vmlinux(self, map,
+                                        symbol_conf.vmlinux_name, filter);
+                goto out_try_fixup;
+        }
 
         if (vmlinux_path != NULL) {
-                int i;
-                pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-                         vmlinux_path__nr_entries);
-                for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-                        err = dso__load_vmlinux(self, map, session,
-                                                vmlinux_path[i], filter);
-                        if (err > 0) {
-                                pr_debug("Using %s for symbols\n",
-                                         vmlinux_path[i]);
-                                dso__set_long_name(self,
-                                                   strdup(vmlinux_path[i]));
-                                goto out_fixup;
+                err = dso__load_vmlinux_path(self, map, filter);
+                if (err > 0)
+                        goto out_fixup;
+        }
+
+        /*
+         * Say the kernel DSO was created when processing the build-id header table,
+         * we have a build-id, so check if it is the same as the running kernel,
+         * using it if it is.
+         */
+        if (self->has_build_id) {
+                u8 kallsyms_build_id[BUILD_ID_SIZE];
+                char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+                if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
+                                         sizeof(kallsyms_build_id)) == 0) {
+                        if (dso__build_id_equal(self, kallsyms_build_id)) {
+                                kallsyms_filename = "/proc/kallsyms";
+                                goto do_kallsyms;
                         }
                 }
-        }
+                /*
+                 * Now look if we have it on the build-id cache in
+                 * $HOME/.debug/[kernel.kallsyms].
+                 */
+                build_id__sprintf(self->build_id, sizeof(self->build_id),
+                                  sbuild_id);
 
-        is_kallsyms = self->long_name[0] == '[';
-        if (is_kallsyms)
-                goto do_kallsyms;
+                if (asprintf(&kallsyms_allocated_filename,
+                             "%s/.debug/[kernel.kallsyms]/%s",
+                             getenv("HOME"), sbuild_id) == -1) {
+                        pr_err("Not enough memory for kallsyms file lookup\n");
+                        return -1;
+                }
 
-        err = dso__load_vmlinux(self, map, session, self->long_name, filter);
-        if (err <= 0) {
-                pr_info("The file %s cannot be used, "
-                        "trying to use /proc/kallsyms...", self->long_name);
-do_kallsyms:
-                err = dso__load_kallsyms(self, map, session, filter);
-                if (err > 0 && !is_kallsyms)
-                        dso__set_long_name(self, strdup("[kernel.kallsyms]"));
+                kallsyms_filename = kallsyms_allocated_filename;
+
+                if (access(kallsyms_filename, F_OK)) {
+                        pr_err("No kallsyms or vmlinux with build-id %s "
+                               "was found\n", sbuild_id);
+                        free(kallsyms_allocated_filename);
+                        return -1;
+                }
+        } else {
+                /*
+                 * Last resort, if we don't have a build-id and couldn't find
+                 * any vmlinux file, try the running kernel kallsyms table.
+                 */
+                kallsyms_filename = "/proc/kallsyms";
         }
 
+do_kallsyms:
+        err = dso__load_kallsyms(self, kallsyms_filename, map, filter);
+        if (err > 0)
+                pr_debug("Using %s for symbols\n", kallsyms_filename);
+        free(kallsyms_allocated_filename);
+
+out_try_fixup:
         if (err > 0) {
 out_fixup:
+                if (kallsyms_filename != NULL)
+                        dso__set_long_name(self, strdup("[kernel.kallsyms]"));
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
@@ -1564,7 +1708,6 @@ out_fixup:
 
 LIST_HEAD(dsos__user);
 LIST_HEAD(dsos__kernel);
-struct dso *vdso;
 
 static void dsos__add(struct list_head *head, struct dso *dso)
 {
@@ -1576,19 +1719,19 @@ static struct dso *dsos__find(struct list_head *head, const char *name)
         struct dso *pos;
 
         list_for_each_entry(pos, head, node)
-                if (strcmp(pos->name, name) == 0)
+                if (strcmp(pos->long_name, name) == 0)
                         return pos;
         return NULL;
 }
 
-struct dso *dsos__findnew(const char *name)
+struct dso *__dsos__findnew(struct list_head *head, const char *name)
 {
-        struct dso *dso = dsos__find(&dsos__user, name);
+        struct dso *dso = dsos__find(head, name);
 
         if (!dso) {
                 dso = dso__new(name);
                 if (dso != NULL) {
-                        dsos__add(&dsos__user, dso);
+                        dsos__add(head, dso);
                         dso__set_basename(dso);
                 }
         }
@@ -1613,75 +1756,78 @@ void dsos__fprintf(FILE *fp)
         __dsos__fprintf(&dsos__user, fp);
 }
 
-static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp)
+static size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+                                      bool with_hits)
 {
         struct dso *pos;
         size_t ret = 0;
 
         list_for_each_entry(pos, head, node) {
+                if (with_hits && !pos->hit)
+                        continue;
                 ret += dso__fprintf_buildid(pos, fp);
                 ret += fprintf(fp, " %s\n", pos->long_name);
         }
         return ret;
 }
 
-size_t dsos__fprintf_buildid(FILE *fp)
+size_t dsos__fprintf_buildid(FILE *fp, bool with_hits)
 {
-        return (__dsos__fprintf_buildid(&dsos__kernel, fp) +
-                __dsos__fprintf_buildid(&dsos__user, fp));
+        return (__dsos__fprintf_buildid(&dsos__kernel, fp, with_hits) +
+                __dsos__fprintf_buildid(&dsos__user, fp, with_hits));
 }
 
-static struct dso *dsos__create_kernel( const char *vmlinux)
+struct dso *dso__new_kernel(const char *name)
 {
-        struct dso *kernel = dso__new(vmlinux ?: "[kernel.kallsyms]");
+        struct dso *self = dso__new(name ?: "[kernel.kallsyms]");
 
-        if (kernel == NULL)
-                return NULL;
+        if (self != NULL) {
+                self->short_name = "[kernel]";
+                self->kernel     = 1;
+        }
 
-        kernel->short_name = "[kernel]";
-        kernel->kernel     = 1;
+        return self;
+}
 
-        vdso = dso__new("[vdso]");
-        if (vdso == NULL)
-                goto out_delete_kernel_dso;
-        dso__set_loaded(vdso, MAP__FUNCTION);
+void dso__read_running_kernel_build_id(struct dso *self)
+{
+        if (sysfs__read_build_id("/sys/kernel/notes", self->build_id,
+                                 sizeof(self->build_id)) == 0)
+                self->has_build_id = true;
+}
 
-        if (sysfs__read_build_id("/sys/kernel/notes", kernel->build_id,
-                                 sizeof(kernel->build_id)) == 0)
-                kernel->has_build_id = true;
+static struct dso *dsos__create_kernel(const char *vmlinux)
+{
+        struct dso *kernel = dso__new_kernel(vmlinux);
 
-        dsos__add(&dsos__kernel, kernel);
-        dsos__add(&dsos__user, vdso);
+        if (kernel != NULL) {
+                dso__read_running_kernel_build_id(kernel);
+                dsos__add(&dsos__kernel, kernel);
+        }
 
         return kernel;
-
-out_delete_kernel_dso:
-        dso__delete(kernel);
-        return NULL;
 }
 
-static int map_groups__create_kernel_maps(struct map_groups *self, const char *vmlinux)
+int __map_groups__create_kernel_maps(struct map_groups *self,
+                                     struct map *vmlinux_maps[MAP__NR_TYPES],
+                                     struct dso *kernel)
 {
-        struct map *functions, *variables;
-        struct dso *kernel = dsos__create_kernel(vmlinux);
+        enum map_type type;
 
-        if (kernel == NULL)
-                return -1;
+        for (type = 0; type < MAP__NR_TYPES; ++type) {
+                struct kmap *kmap;
 
-        functions = map__new2(0, kernel, MAP__FUNCTION);
-        if (functions == NULL)
-                return -1;
+                vmlinux_maps[type] = map__new2(0, kernel, type);
+                if (vmlinux_maps[type] == NULL)
+                        return -1;
 
-        variables = map__new2(0, kernel, MAP__VARIABLE);
-        if (variables == NULL) {
-                map__delete(functions);
-                return -1;
-        }
+                vmlinux_maps[type]->map_ip =
+                        vmlinux_maps[type]->unmap_ip = identity__map_ip;
 
-        functions->map_ip = functions->unmap_ip =
-                variables->map_ip = variables->unmap_ip = identity__map_ip;
-        map_groups__insert(self, functions);
-        map_groups__insert(self, variables);
+                kmap = map__kmap(vmlinux_maps[type]);
+                kmap->kmaps = self;
+                map_groups__insert(self, vmlinux_maps[type]);
+        }
 
         return 0;
 }
@@ -1791,19 +1937,22 @@ out_free_comm_list:
         return -1;
 }
 
-int perf_session__create_kernel_maps(struct perf_session *self)
+int map_groups__create_kernel_maps(struct map_groups *self,
+                                   struct map *vmlinux_maps[MAP__NR_TYPES])
 {
-        if (map_groups__create_kernel_maps(&self->kmaps,
-                                           symbol_conf.vmlinux_name) < 0)
+        struct dso *kernel = dsos__create_kernel(symbol_conf.vmlinux_name);
+
+        if (kernel == NULL)
+                return -1;
+
+        if (__map_groups__create_kernel_maps(self, vmlinux_maps, kernel) < 0)
                 return -1;
 
-        if (symbol_conf.use_modules &&
-            perf_session__create_module_maps(self) < 0)
-                pr_debug("Failed to load list of modules for session %s, "
-                         "continuing...\n", self->filename);
+        if (symbol_conf.use_modules && map_groups__create_modules(self) < 0)
+                pr_debug("Problems creating module maps, continuing anyway...\n");
         /*
          * Now that we have all the maps created, just set the ->end of them:
          */
-        map_groups__fixup_end(&self->kmaps);
+        map_groups__fixup_end(self);
         return 0;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 8aded2356f79..280dadd32a08 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -8,6 +8,8 @@
 #include <linux/rbtree.h>
 #include "event.h"
 
+#define DEBUG_CACHE_DIR ".debug"
+
 #ifdef HAVE_CPLUS_DEMANGLE
 extern char *cplus_demangle(const char *, int);
 
@@ -49,6 +51,8 @@ struct symbol {
         char            name[0];
 };
 
+void symbol__delete(struct symbol *self);
+
 struct strlist;
 
 struct symbol_conf {
@@ -58,7 +62,8 @@ struct symbol_conf {
                         sort_by_name,
                         show_nr_samples,
                         use_callchain,
-                        exclude_other;
+                        exclude_other,
+                        full_paths;
         const char      *vmlinux_name,
                         *field_sep;
         char            *dso_list_str,
@@ -77,6 +82,12 @@ static inline void *symbol__priv(struct symbol *self)
         return ((void *)self) - symbol_conf.priv_size;
 }
 
+struct ref_reloc_sym {
+        const char      *name;
+        u64             addr;
+        u64             unrelocated_addr;
+};
+
 struct addr_location {
         struct thread *thread;
         struct map    *map;
@@ -94,6 +105,7 @@ struct dso {
         u8               slen_calculated:1;
         u8               has_build_id:1;
         u8               kernel:1;
+        u8               hit:1;
         unsigned char    origin;
         u8               sorted_by_name;
         u8               loaded;
@@ -105,37 +117,55 @@ struct dso {
 };
 
 struct dso *dso__new(const char *name);
+struct dso *dso__new_kernel(const char *name);
 void dso__delete(struct dso *self);
 
 bool dso__loaded(const struct dso *self, enum map_type type);
 bool dso__sorted_by_name(const struct dso *self, enum map_type type);
 
+static inline void dso__set_loaded(struct dso *self, enum map_type type)
+{
+        self->loaded |= (1 << type);
+}
+
 void dso__sort_by_name(struct dso *self, enum map_type type);
 
-struct perf_session;
+extern struct list_head dsos__user, dsos__kernel;
+
+struct dso *__dsos__findnew(struct list_head *head, const char *name);
+
+static inline struct dso *dsos__findnew(const char *name)
+{
+        return __dsos__findnew(&dsos__user, name);
+}
 
-struct dso *dsos__findnew(const char *name);
-int dso__load(struct dso *self, struct map *map, struct perf_session *session,
-              symbol_filter_t filter);
+int dso__load(struct dso *self, struct map *map, 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,
+                       symbol_filter_t filter);
 void dsos__fprintf(FILE *fp);
-size_t dsos__fprintf_buildid(FILE *fp);
+size_t dsos__fprintf_buildid(FILE *fp, bool with_hits);
 
 size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
 char dso__symtab_origin(const struct dso *self);
+void dso__set_long_name(struct dso *self, char *name);
 void dso__set_build_id(struct dso *self, void *build_id);
+void dso__read_running_kernel_build_id(struct dso *self);
 struct symbol *dso__find_symbol(struct dso *self, enum map_type type, u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *self, enum map_type type,
                                         const char *name);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
-bool dsos__read_build_ids(void);
-int build_id__sprintf(u8 *self, int len, char *bf);
+bool dsos__read_build_ids(bool with_hits);
+int build_id__sprintf(const u8 *self, int len, char *bf);
+int kallsyms__parse(const char *filename, void *arg,
+                    int (*process_symbol)(void *arg, const char *name,
+                                          char type, u64 start));
 
 int symbol__init(void);
-int perf_session__create_kernel_maps(struct perf_session *self);
+bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-extern struct list_head dsos__user, dsos__kernel;
-extern struct dso *vdso;
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 4a08dcf50b68..21b92162282b 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -31,12 +31,41 @@ static struct thread *thread__new(pid_t pid)
         return self;
 }
 
+static void map_groups__flush(struct map_groups *self)
+{
+        int type;
+
+        for (type = 0; type < MAP__NR_TYPES; type++) {
+                struct rb_root *root = &self->maps[type];
+                struct rb_node *next = rb_first(root);
+
+                while (next) {
+                        struct map *pos = rb_entry(next, struct map, rb_node);
+                        next = rb_next(&pos->rb_node);
+                        rb_erase(&pos->rb_node, root);
+                        /*
+                         * We may have references to this map, for
+                         * instance in some hist_entry instances, so
+                         * just move them to a separate list.
+                         */
+                        list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+                }
+        }
+}
+
 int thread__set_comm(struct thread *self, const char *comm)
 {
+        int err;
+
         if (self->comm)
                 free(self->comm);
         self->comm = strdup(comm);
-        return self->comm ? 0 : -ENOMEM;
+        err = self->comm == NULL ? -ENOMEM : 0;
+        if (!err) {
+                self->comm_set = true;
+                map_groups__flush(&self->mg);
+        }
+        return err;
 }
 
 int thread__comm_len(struct thread *self)
@@ -50,11 +79,6 @@ int thread__comm_len(struct thread *self)
         return self->comm_len;
 }
 
-static const char *map_type__name[MAP__NR_TYPES] = {
-        [MAP__FUNCTION] = "Functions",
-        [MAP__VARIABLE] = "Variables",
-};
-
 static size_t __map_groups__fprintf_maps(struct map_groups *self,
                                          enum map_type type, FILE *fp)
 {
@@ -255,11 +279,14 @@ int thread__fork(struct thread *self, struct thread *parent)
 {
         int i;
 
-        if (self->comm)
-                free(self->comm);
-        self->comm = strdup(parent->comm);
-        if (!self->comm)
-                return -ENOMEM;
+        if (parent->comm_set) {
+                if (self->comm)
+                        free(self->comm);
+                self->comm = strdup(parent->comm);
+                if (!self->comm)
+                        return -ENOMEM;
+                self->comm_set = true;
+        }
 
         for (i = 0; i < MAP__NR_TYPES; ++i)
                 if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
@@ -282,14 +309,13 @@ size_t perf_session__fprintf(struct perf_session *self, FILE *fp)
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *self,
-                                       struct perf_session *session,
                                        enum map_type type, u64 addr,
                                        symbol_filter_t filter)
 {
         struct map *map = map_groups__find(self, type, addr);
 
         if (map != NULL)
-                return map__find_symbol(map, session, map->map_ip(map, addr), filter);
+                return map__find_symbol(map, map->map_ip(map, addr), filter);
 
         return NULL;
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index c206f72c8881..0a28f39de545 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -15,6 +15,7 @@ struct thread {
         struct map_groups       mg;
         pid_t                   pid;
         char                    shortname[3];
+        bool                    comm_set;
         char                    *comm;
         int                     comm_len;
 };
@@ -48,23 +49,36 @@ static inline struct map *thread__find_map(struct thread *self,
         return self ? map_groups__find(&self->mg, type, addr) : NULL;
 }
 
+void thread__find_addr_map(struct thread *self,
+                           struct perf_session *session, u8 cpumode,
+                           enum map_type type, u64 addr,
+                           struct addr_location *al);
+
 void thread__find_addr_location(struct thread *self,
                                 struct perf_session *session, u8 cpumode,
                                 enum map_type type, u64 addr,
                                 struct addr_location *al,
                                 symbol_filter_t filter);
 struct symbol *map_groups__find_symbol(struct map_groups *self,
-                                       struct perf_session *session,
                                        enum map_type type, u64 addr,
                                        symbol_filter_t filter);
 
-static inline struct symbol *
-map_groups__find_function(struct map_groups *self, struct perf_session *session,
-                          u64 addr, symbol_filter_t filter)
+static inline struct symbol *map_groups__find_function(struct map_groups *self,
+                                                       u64 addr,
+                                                       symbol_filter_t filter)
 {
-        return map_groups__find_symbol(self, session, MAP__FUNCTION, addr, filter);
+        return map_groups__find_symbol(self, MAP__FUNCTION, addr, filter);
 }
 
 struct map *map_groups__find_by_name(struct map_groups *self,
                                      enum map_type type, const char *name);
+
+int __map_groups__create_kernel_maps(struct map_groups *self,
+                                     struct map *vmlinux_maps[MAP__NR_TYPES],
+                                     struct dso *kernel);
+int map_groups__create_kernel_maps(struct map_groups *self,
+                                   struct map *vmlinux_maps[MAP__NR_TYPES]);
+
+struct map *map_groups__new_module(struct map_groups *self, u64 start,
+                                   const char *filename);
 #endif  /* __PERF_THREAD_H */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index cace35595530..5ea8973ad331 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -20,6 +20,7 @@
  */
 #define _GNU_SOURCE
 #include <dirent.h>
+#include <mntent.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -37,6 +38,7 @@
 
 #include "../perf.h"
 #include "trace-event.h"
+#include "debugfs.h"
 
 #define VERSION "0.5"
 
@@ -101,32 +103,12 @@ void *malloc_or_die(unsigned int size)
 
 static const char *find_debugfs(void)
 {
-        static char debugfs[MAX_PATH+1];
-        static int debugfs_found;
-        char type[100];
-        FILE *fp;
-
-        if (debugfs_found)
-                return debugfs;
-
-        if ((fp = fopen("/proc/mounts","r")) == NULL)
-                die("Can't open /proc/mounts for read");
-
-        while (fscanf(fp, "%*s %"
-                      STR(MAX_PATH)
-                      "s %99s %*s %*d %*d\n",
-                      debugfs, type) == 2) {
-                if (strcmp(type, "debugfs") == 0)
-                        break;
-        }
-        fclose(fp);
-
-        if (strcmp(type, "debugfs") != 0)
-                die("debugfs not mounted, please mount");
+        const char *path = debugfs_mount(NULL);
 
-        debugfs_found = 1;
+        if (!path)
+                die("Your kernel not support debugfs filesystem");
 
-        return debugfs;
+        return path;
 }
 
 /*
@@ -271,6 +253,8 @@ static void read_header_files(void)
         write_or_die("header_page", 12);
         write_or_die(&size, 8);
         check_size = copy_file_fd(fd);
+        close(fd);
+
         if (size != check_size)
                 die("wrong size for '%s' size=%lld read=%lld",
                     path, size, check_size);
@@ -289,6 +273,7 @@ static void read_header_files(void)
         if (size != check_size)
                 die("wrong size for '%s'", path);
         put_tracing_file(path);
+        close(fd);
 }
 
 static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
@@ -317,7 +302,8 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps)
                 die("can't read directory '%s'", sys);
 
         while ((dent = readdir(dir))) {
-                if (strcmp(dent->d_name, ".") == 0 ||
+                if (dent->d_type != DT_DIR ||
+                    strcmp(dent->d_name, ".") == 0 ||
                     strcmp(dent->d_name, "..") == 0 ||
                     !name_in_tp_list(dent->d_name, tps))
                         continue;
@@ -334,7 +320,8 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps)
 
         rewinddir(dir);
         while ((dent = readdir(dir))) {
-                if (strcmp(dent->d_name, ".") == 0 ||
+                if (dent->d_type != DT_DIR ||
+                    strcmp(dent->d_name, ".") == 0 ||
                     strcmp(dent->d_name, "..") == 0 ||
                     !name_in_tp_list(dent->d_name, tps))
                         continue;
@@ -353,6 +340,7 @@ static void copy_event_system(const char *sys, struct tracepoint_path *tps)
 
                 free(format);
         }
+        closedir(dir);
 }
 
 static void read_ftrace_files(struct tracepoint_path *tps)
@@ -394,26 +382,21 @@ static void read_event_files(struct tracepoint_path *tps)
                 die("can't read directory '%s'", path);
 
         while ((dent = readdir(dir))) {
-                if (strcmp(dent->d_name, ".") == 0 ||
+                if (dent->d_type != DT_DIR ||
+                    strcmp(dent->d_name, ".") == 0 ||
                     strcmp(dent->d_name, "..") == 0 ||
                     strcmp(dent->d_name, "ftrace") == 0 ||
                     !system_in_tp_list(dent->d_name, tps))
                         continue;
-                sys = malloc_or_die(strlen(path) + strlen(dent->d_name) + 2);
-                sprintf(sys, "%s/%s", path, dent->d_name);
-                ret = stat(sys, &st);
-                free(sys);
-                if (ret < 0)
-                        continue;
-                if (S_ISDIR(st.st_mode))
-                        count++;
+                count++;
         }
 
         write_or_die(&count, 4);
 
         rewinddir(dir);
         while ((dent = readdir(dir))) {
-                if (strcmp(dent->d_name, ".") == 0 ||
+                if (dent->d_type != DT_DIR ||
+                    strcmp(dent->d_name, ".") == 0 ||
                     strcmp(dent->d_name, "..") == 0 ||
                     strcmp(dent->d_name, "ftrace") == 0 ||
                     !system_in_tp_list(dent->d_name, tps))
@@ -422,14 +405,13 @@ static void read_event_files(struct tracepoint_path *tps)
                 sprintf(sys, "%s/%s", path, dent->d_name);
                 ret = stat(sys, &st);
                 if (ret >= 0) {
-                        if (S_ISDIR(st.st_mode)) {
-                                write_or_die(dent->d_name, strlen(dent->d_name) + 1);
-                                copy_event_system(sys, tps);
-                        }
+                        write_or_die(dent->d_name, strlen(dent->d_name) + 1);
+                        copy_event_system(sys, tps);
                 }
                 free(sys);
         }
 
+        closedir(dir);
         put_tracing_file(path);
 }
 
@@ -533,7 +515,7 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
         write_or_die(buf, 1);
 
         /* save page_size */
-        page_size = getpagesize();
+        page_size = sysconf(_SC_PAGESIZE);
         write_or_die(&page_size, 4);
 
         read_header_files();
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index c5c32be040bf..9b3c20f42f98 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1925,6 +1925,15 @@ void *raw_field_ptr(struct event *event, const char *name, void *data)
         if (!field)
                 return NULL;
 
+        if (field->flags & FIELD_IS_STRING) {
+                int offset;
+
+                offset = *(int *)(data + field->offset);
+                offset &= 0xffff;
+
+                return data + offset;
+        }
+
         return data + field->offset;
 }
 
@@ -3277,3 +3286,18 @@ void parse_set_info(int nr_cpus, int long_sz)
         cpus = nr_cpus;
         long_size = long_sz;
 }
+
+int common_pc(struct scripting_context *context)
+{
+        return parse_common_pc(context->event_data);
+}
+
+int common_flags(struct scripting_context *context)
+{
+        return parse_common_flags(context->event_data);
+}
+
+int common_lock_depth(struct scripting_context *context)
+{
+        return parse_common_lock_depth(context->event_data);
+}
diff --git a/tools/perf/util/trace-event-perl.h b/tools/perf/util/trace-event-perl.h
deleted file mode 100644
index e88fb26137bb..000000000000
--- a/tools/perf/util/trace-event-perl.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef __PERF_TRACE_EVENT_PERL_H
-#define __PERF_TRACE_EVENT_PERL_H
-#ifdef NO_LIBPERL
-typedef int INTERP;
-#define dSP
-#define ENTER
-#define SAVETMPS
-#define PUTBACK
-#define SPAGAIN
-#define FREETMPS
-#define LEAVE
-#define SP
-#define ERRSV
-#define G_SCALAR                (0)
-#define G_DISCARD               (0)
-#define G_NOARGS                (0)
-#define PUSHMARK(a)
-#define SvTRUE(a)               (0)
-#define XPUSHs(s)
-#define sv_2mortal(a)
-#define newSVpv(a,b)
-#define newSVuv(a)
-#define newSViv(a)
-#define get_cv(a,b)             (0)
-#define call_pv(a,b)            (0)
-#define perl_alloc()            (0)
-#define perl_construct(a)       (0)
-#define perl_parse(a,b,c,d,e)   (0)
-#define perl_run(a)             (0)
-#define perl_destruct(a)        (0)
-#define perl_free(a)            (0)
-#define pTHX                    void
-#define CV                      void
-#define dXSUB_SYS
-#define pTHX_
-static inline void newXS(const char *a, void *b, const char *c) {}
-static void boot_Perf__Trace__Context(pTHX_ CV *cv) {}
-static void boot_DynaLoader(pTHX_ CV *cv) {}
-#else
-#include <EXTERN.h>
-#include <perl.h>
-void boot_Perf__Trace__Context(pTHX_ CV *cv);
-void boot_DynaLoader(pTHX_ CV *cv);
-typedef PerlInterpreter * INTERP;
-#endif
-
-struct scripting_context {
-        void *event_data;
-};
-
-int common_pc(struct scripting_context *context);
-int common_flags(struct scripting_context *context);
-int common_lock_depth(struct scripting_context *context);
-
-#endif /* __PERF_TRACE_EVENT_PERL_H */
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 1744422cafcb..7cd1193918c7 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -18,7 +18,7 @@
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#define _LARGEFILE64_SOURCE
+#define _FILE_OFFSET_BITS 64
 
 #include <dirent.h>
 #include <stdio.h>
@@ -83,7 +83,7 @@ static char *read_string(void)
         char *str = NULL;
         int size = 0;
         int i;
-        int r;
+        off_t r;
 
         for (;;) {
                 r = read(input_fd, buf, BUFSIZ);
@@ -118,7 +118,7 @@ static char *read_string(void)
 
         /* move the file descriptor to the end of the string */
         r = lseek(input_fd, -(r - i), SEEK_CUR);
-        if (r < 0)
+        if (r == (off_t)-1)
                 die("lseek");
 
         if (str) {
@@ -282,8 +282,8 @@ static void update_cpu_data_index(int cpu)
 
 static void get_next_page(int cpu)
 {
-        off64_t save_seek;
-        off64_t ret;
+        off_t save_seek;
+        off_t ret;
 
         if (!cpu_data[cpu].page)
                 return;
@@ -298,17 +298,17 @@ static void get_next_page(int cpu)
                 update_cpu_data_index(cpu);
 
                 /* other parts of the code may expect the pointer to not move */
-                save_seek = lseek64(input_fd, 0, SEEK_CUR);
+                save_seek = lseek(input_fd, 0, SEEK_CUR);
 
-                ret = lseek64(input_fd, cpu_data[cpu].offset, SEEK_SET);
-                if (ret < 0)
+                ret = lseek(input_fd, cpu_data[cpu].offset, SEEK_SET);
+                if (ret == (off_t)-1)
                         die("failed to lseek");
                 ret = read(input_fd, cpu_data[cpu].page, page_size);
                 if (ret < 0)
                         die("failed to read page");
 
                 /* reset the file pointer back */
-                lseek64(input_fd, save_seek, SEEK_SET);
+                lseek(input_fd, save_seek, SEEK_SET);
 
                 return;
         }
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
new file mode 100644
index 000000000000..7ea983acfaea
--- /dev/null
+++ b/tools/perf/util/trace-event-scripting.c
@@ -0,0 +1,167 @@
+/*
+ * trace-event-scripting.  Scripting engine common and initialization code.
+ *
+ * Copyright (C) 2009-2010 Tom Zanussi <tzanussi@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+#include <errno.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "trace-event.h"
+
+struct scripting_context *scripting_context;
+
+static int stop_script_unsupported(void)
+{
+        return 0;
+}
+
+static void process_event_unsupported(int cpu __unused,
+                                      void *data __unused,
+                                      int size __unused,
+                                      unsigned long long nsecs __unused,
+                                      char *comm __unused)
+{
+}
+
+static void print_python_unsupported_msg(void)
+{
+        fprintf(stderr, "Python scripting not supported."
+                "  Install libpython and rebuild perf to enable it.\n"
+                "For example:\n  # apt-get install python-dev (ubuntu)"
+                "\n  # yum install python-devel (Fedora)"
+                "\n  etc.\n");
+}
+
+static int python_start_script_unsupported(const char *script __unused,
+                                           int argc __unused,
+                                           const char **argv __unused)
+{
+        print_python_unsupported_msg();
+
+        return -1;
+}
+
+static int python_generate_script_unsupported(const char *outfile __unused)
+{
+        print_python_unsupported_msg();
+
+        return -1;
+}
+
+struct scripting_ops python_scripting_unsupported_ops = {
+        .name = "Python",
+        .start_script = python_start_script_unsupported,
+        .stop_script = stop_script_unsupported,
+        .process_event = process_event_unsupported,
+        .generate_script = python_generate_script_unsupported,
+};
+
+static void register_python_scripting(struct scripting_ops *scripting_ops)
+{
+        int err;
+        err = script_spec_register("Python", scripting_ops);
+        if (err)
+                die("error registering Python script extension");
+
+        err = script_spec_register("py", scripting_ops);
+        if (err)
+                die("error registering py script extension");
+
+        scripting_context = malloc(sizeof(struct scripting_context));
+}
+
+#ifdef NO_LIBPYTHON
+void setup_python_scripting(void)
+{
+        register_python_scripting(&python_scripting_unsupported_ops);
+}
+#else
+struct scripting_ops python_scripting_ops;
+
+void setup_python_scripting(void)
+{
+        register_python_scripting(&python_scripting_ops);
+}
+#endif
+
+static void print_perl_unsupported_msg(void)
+{
+        fprintf(stderr, "Perl scripting not supported."
+                "  Install libperl and rebuild perf to enable it.\n"
+                "For example:\n  # apt-get install libperl-dev (ubuntu)"
+                "\n  # yum install 'perl(ExtUtils::Embed)' (Fedora)"
+                "\n  etc.\n");
+}
+
+static int perl_start_script_unsupported(const char *script __unused,
+                                         int argc __unused,
+                                         const char **argv __unused)
+{
+        print_perl_unsupported_msg();
+
+        return -1;
+}
+
+static int perl_generate_script_unsupported(const char *outfile __unused)
+{
+        print_perl_unsupported_msg();
+
+        return -1;
+}
+
+struct scripting_ops perl_scripting_unsupported_ops = {
+        .name = "Perl",
+        .start_script = perl_start_script_unsupported,
+        .stop_script = stop_script_unsupported,
+        .process_event = process_event_unsupported,
+        .generate_script = perl_generate_script_unsupported,
+};
+
+static void register_perl_scripting(struct scripting_ops *scripting_ops)
+{
+        int err;
+        err = script_spec_register("Perl", scripting_ops);
+        if (err)
+                die("error registering Perl script extension");
+
+        err = script_spec_register("pl", scripting_ops);
+        if (err)
+                die("error registering pl script extension");
+
+        scripting_context = malloc(sizeof(struct scripting_context));
+}
+
+#ifdef NO_LIBPERL
+void setup_perl_scripting(void)
+{
+        register_perl_scripting(&perl_scripting_unsupported_ops);
+}
+#else
+struct scripting_ops perl_scripting_ops;
+
+void setup_perl_scripting(void)
+{
+        register_perl_scripting(&perl_scripting_ops);
+}
+#endif
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 6ad405620c9b..c3269b937db4 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -279,7 +279,15 @@ struct scripting_ops {
 
 int script_spec_register(const char *spec, struct scripting_ops *ops);
 
-extern struct scripting_ops perl_scripting_ops;
 void setup_perl_scripting(void);
+void setup_python_scripting(void);
+
+struct scripting_context {
+        void *event_data;
+};
+
+int common_pc(struct scripting_context *context);
+int common_flags(struct scripting_context *context);
+int common_lock_depth(struct scripting_context *context);
 
 #endif /* __PERF_TRACE_EVENTS_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
new file mode 100644
index 000000000000..f9b890fde681
--- /dev/null
+++ b/tools/perf/util/util.c
@@ -0,0 +1,94 @@
+#include "util.h"
+#include <sys/mman.h>
+
+int mkdir_p(char *path, mode_t mode)
+{
+        struct stat st;
+        int err;
+        char *d = path;
+
+        if (*d != '/')
+                return -1;
+
+        if (stat(path, &st) == 0)
+                return 0;
+
+        while (*++d == '/');
+
+        while ((d = strchr(d, '/'))) {
+                *d = '\0';
+                err = stat(path, &st) && mkdir(path, mode);
+                *d++ = '/';
+                if (err)
+                        return -1;
+                while (*d == '/')
+                        ++d;
+        }
+        return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
+}
+
+static int slow_copyfile(const char *from, const char *to)
+{
+        int err = 0;
+        char *line = NULL;
+        size_t n;
+        FILE *from_fp = fopen(from, "r"), *to_fp;
+
+        if (from_fp == NULL)
+                goto out;
+
+        to_fp = fopen(to, "w");
+        if (to_fp == NULL)
+                goto out_fclose_from;
+
+        while (getline(&line, &n, from_fp) > 0)
+                if (fputs(line, to_fp) == EOF)
+                        goto out_fclose_to;
+        err = 0;
+out_fclose_to:
+        fclose(to_fp);
+        free(line);
+out_fclose_from:
+        fclose(from_fp);
+out:
+        return err;
+}
+
+int copyfile(const char *from, const char *to)
+{
+        int fromfd, tofd;
+        struct stat st;
+        void *addr;
+        int err = -1;
+
+        if (stat(from, &st))
+                goto out;
+
+        if (st.st_size == 0) /* /proc? do it slowly... */
+                return slow_copyfile(from, to);
+
+        fromfd = open(from, O_RDONLY);
+        if (fromfd < 0)
+                goto out;
+
+        tofd = creat(to, 0755);
+        if (tofd < 0)
+                goto out_close_from;
+
+        addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
+        if (addr == MAP_FAILED)
+                goto out_close_to;
+
+        if (write(tofd, addr, st.st_size) == st.st_size)
+                err = 0;
+
+        munmap(addr, st.st_size);
+out_close_to:
+        close(tofd);
+        if (err)
+                unlink(to);
+out_close_from:
+        close(fromfd);
+out:
+        return err;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c673d8825883..0f5b2a6f1080 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -403,4 +403,7 @@ void git_qsort(void *base, size_t nmemb, size_t size,
 #endif
 #endif
 
+int mkdir_p(char *path, mode_t mode);
+int copyfile(const char *from, const char *to);
+
 #endif
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 1c15e39f99e3..cfa55d686e3b 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -169,6 +169,7 @@ static void perf_read_values__display_pretty(FILE *fp,
                                 counterwidth[j], values->value[i][j]);
                 fprintf(fp, "\n");
         }
+        free(counterwidth);
 }
 
 static void perf_read_values__display_raw(FILE *fp,