Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1258396365-29217-1-git-send-email-acme@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Build a set of section headers for features right after the
datas. Each implemented feature will have one of such section
header that provides the offset and the size of the data
manipulated by the feature.

The trace informations have moved after the data and are
recorded on exit time.

The new layout is as follows:

 -----------------------
                             ___
 [ magic               ]      |
 [ header size         ]      |
 [ attr size           ]      |
 [ attr content offset ]      |
 [ attr content size   ]      |
 [ data offset         ]  File Headers
 [ data size           ]      |
 [ event_types offset  ]      |
 [ event_types size    ]      |
 [ feature bitmap      ]      v

 [ attr section        ]
 [ events section      ]

                             ___
 [         X           ]      |
 [         X           ]      |
 [         X           ]    Datas
 [         X           ]      |
 [         X           ]      v

                             ___
 [ Feature 1 offset    ]      |
 [ Feature 1 size      ] Features headers
 [ Feature 2 offset    ]      |
 [ Feature 2 size      ]      v

 [ Feature 1 content   ]
 [ Feature 2 content   ]
 -----------------------

We have as many feature's section headers as we have features in
use for the current file.

Say Feat 1 and Feat 3 are used by the file, but not Feat 2. Then
the feature headers will be like follows:

[ Feature 1 offset    ]      |
[ Feature 1 size      ] Features headers
[ Feature 3 offset    ]      |
[ Feature 3 size      ]      v

There is no hole to cover Feature 2 that is not in use here. We
only need to cover the needed headers in order, from the lowest
feature bit to the highest.

Currently we have two features: HEADER_TRACE_INFO and
HEADER_BUILD_ID. Both have their contents that follow the
feature headers. Putting the contents right after the feature
headers is not mandatory though. While we keep the feature
headers right after the data and in order, their offsets can
point everywhere. We have just put the two above feature
contents in the end of the file for convenience.

The purpose of this layout change is to have a file format that
scales while keeping it simple: having such linear feature
headers is less error prone wrt forward/backward compatibility
as the content of a feature can be put anywhere, its location
can even change by the time, it's fine because its headers will
tell where it is. And we know how to find these headers,
following the above rules.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
LKML-Reference: <1257911467-28276-6-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

And drop the alternate checks/sets using set_bit or other kind
of helpers.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
LKML-Reference: <1257911467-28276-5-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Keep the build-ids reading implementation in the data mapping
but move its call to the headers so that we have a better
control on it (offset seeking, size passing, etc..).
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
LKML-Reference: <1257911467-28276-4-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

We are saving the build id once we stop the profiling. And only
after doing that we know if we need to set that feature in the
header through the feature bitmap.

But if we want a proper feature support in the headers, using a
rule of offset/size pairs in sections, we need to know in
advance how many features we need to set in the headers, so that
we can reserve rooms for their section headers.

The current state doesn't allow that, as it forces us to first
save the build-ids to the file right after the datas instead of
planning any structured layout.

That's why this splits up the build-ids processing in two parts:
one that fetches the build-ids from the Dso objects, and one
that saves them into the file.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
LKML-Reference: <1257911467-28276-3-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

So that it makes easier to control it. Especially because we
plan to give it a feature section.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
LKML-Reference: <1257911467-28276-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

With this change 'perf record' will intercept PERF_RECORD_MMAP
calls, creating a linked list of DSOs, then when the session
finishes, it will traverse this list and read the buildids,
stashing them at the end of the file and will set up a new
feature bit in the header bitmask.

'perf report' will then notice this feature and populate the
'dsos' list and set the build ids.

When reading the symtabs it will refuse to load from a file that
doesn't have the same build id. This improves the
reliability of the profiler output, as symbols and profiling
data is more guaranteed to match.

Example:

 [root@doppio ~]# perf report | head
 /home/acme/bin/perf with build id b1ea544ac3746e7538972548a09aadecc5753868 not found, continuing without symbols
  # Samples: 2621434559
  #
  # Overhead          Command                  Shared Object  Symbol
  # ........  ...............  .............................  ......
  #
       7.91%             init  [kernel]        [k] read_hpet
       7.64%             init  [kernel]        [k] mwait_idle_with_hints
       7.60%          swapper  [kernel]        [k] read_hpet
       7.60%          swapper  [kernel]        [k] mwait_idle_with_hints
       3.65%             init  [kernel]        [k] 0xffffffffa02339d9
[root@doppio ~]#

In this case the 'perf' binary was an older one, vanished,
so its symbols probably wouldn't match or would cause subtly
different (and misleading) output.

Next patches will support the kernel as well, reading the build
id notes for it and the modules from /sys.

Another patch should also introduce a new plumbing command:

'perf list-buildids'

that will then be used in porcelain that is distro specific to
fetch -debuginfo packages where such buildids are present. This
will in turn allow for one to run 'perf record' in one machine
and 'perf report' in another.

Future work on having the buildid sent directly from the kernel
in the PERF_RECORD_MMAP event is needed to close races, as the
DSO can be changed during a 'perf record' session, but this
patch at least helps with non-corner cases and current/older
kernels.
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: K. Prasad <prasad@linux.vnet.ibm.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roland McGrath <roland@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1257367843-26224-1-git-send-email-acme@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

We were using eprintf in some places, that looks at a global
'verbose' level, and at other places passing a 'v' parameter to
specify the verbosity level, unify it by introducing
pr_{err,warning,debug,etc}, just like in the kernel.
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1256153646-10097-1-git-send-email-acme@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Use DECLARE_BITMAP instead of an open coded array for our bitmap
of featured sections.

This makes the array an unsigned long instead of a u64 but since
we use a 256 bits bitmap, the array size shouldn't vary between
different boxes.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1255795038-13751-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This provides a new set of bitmasked headers. A new field is
added in the perf headers that implements a bitmap storing
optional features present in the perf.data file.

The layout can be pictured like this:

(Usual perf headers)(Features bitmap)[Feature 0][Feature
n][Feature 255]

If the bit n is set, then the feature n is used in this file.
They are all set in order. This brings a backward and forward
compatibility.

The trace_info section has moved into such optional features,
this is the first and only one for now.

This is backward compatible with the .32 file version although
it doesn't support the previous separate trace.info file.

And finally it doesn't support the current interim development
version.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1255792354-11304-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

We have merged the trace.info file into perf.data by adding one
section in the perf headers. This makes it incompatible with
previous version: the new perf tools can't read the older
perf.data.

To support the previous format, we check the headers size. If they
have the same size than in the previous format, then ignore the
trace info section that doesn't exist.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1255032449-12022-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This drops the trace.info file and move its contents into the
common perf.data file.

This is done by creating a new trace_info section into this file. A
user of perf headers needs to call perf_header__set_trace_info() to
save the trace meta informations into the perf.data file.

A file created by perf after his patch is unsupported by previous
version because the size of the headers have increased.

That said, it's two new fields that have been added in the end of
the headers, and those could be ignored by previous versions if
they just handled the dynamic header size and then ignore the
unknow part. The offsets guarantee the compatibility. We'll do a
-stable fix for that.

But current previous versions handle the header size using its
static size, not dynamic, then it's not backward compatible with
trace records.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20091006213643.GA5343@nowhere>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Bye-bye Performance Counters, welcome Performance Events!

In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.

Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.

All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)

The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.

Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.

User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)

This patch has been generated via the following script:

  FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')

  sed -i \
    -e 's/PERF_EVENT_/PERF_RECORD_/g' \
    -e 's/PERF_COUNTER/PERF_EVENT/g' \
    -e 's/perf_counter/perf_event/g' \
    -e 's/nb_counters/nb_events/g' \
    -e 's/swcounter/swevent/g' \
    -e 's/tpcounter_event/tp_event/g' \
    $FILES

  for N in $(find . -name perf_counter.[ch]); do
    M=$(echo $N | sed 's/perf_counter/perf_event/g')
    mv $N $M
  done

  FILES=$(find . -name perf_event.*)

  sed -i \
    -e 's/COUNTER_MASK/REG_MASK/g' \
    -e 's/COUNTER/EVENT/g' \
    -e 's/\<event\>/event_id/g' \
    -e 's/counter/event/g' \
    -e 's/Counter/Event/g' \
    $FILES

... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.

Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.

( NOTE: 'counters' are still the proper terminology when we deal
  with hardware registers - and these sed scripts are a bit
  over-eager in renaming them. I've undone some of that, but
  in case there's something left where 'counter' would be
  better than 'event' we can undo that on an individual basis
  instead of touching an otherwise nicely automated patch. )
Suggested-by: NStephane Eranian <eranian@google.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NPaul Mackerras <paulus@samba.org>
Reviewed-by: NArjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

As per Ingo's review: use a #define rather than an open coded constant
for the maximum length of a trace event for storing in the perf.data file.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Cc: fweisbec@gmail.com
Cc: peterz@infradead.org
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20090919133630.10533d3e@infradead.org>
[ add a few comments to nearby functions ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The trace event name<->id mapping is dynamic for each kernel
compile. In order for perf.data to be useable outside the actual
system, we thus need to store a table of this mapping for later
use.

This patch adds this table to perf.data, and provides helper
functions for lookup up fields from this table.

To avoid mistakes, lookup-from-table is kept completely seprate
from lookup-from-local-debugfs.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20090912130405.6960d099@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Leave the input fd at the data area.

It does not matter right now - but seeking at the end of it
certainly did not make sense.

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Librarize the sample type and attr fetching from perf data file
headers so that we can also use it from perf trace.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1250448997-30715-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

While toying with perf, I've noticed that perf record can
easily enter a busy loop when doing something as silly as:

    $ perf record -A ls

Yeah, do_read here really wants to read a known size, not being
able to should die(), not busy-loop ;)

That was the cause for the bug.
Signed-off-by: NPierre Habouzit <pierre.habouzit@intersec.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Brice Goglin reported that only the first result from a
multi-counter perf record --stat run is accurate, the
rest looks bogus.

A silly mistake made us re-read the first attribute for
every recorded attribute.
Reported-by: NBrice Goglin <Brice.Goglin@inria.fr>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: NBrice Goglin <Brice.Goglin@inria.fr>
Cc: paulus@samba.org
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Create a structured file format that includes the full
perf_counter_attr and all its relevant counter IDs so that
the reporting program has full information.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: NIngo Molnar <mingo@elte.hu>