Lets use the Git framework of built-in commands.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NIngo Molnar <mingo@elte.hu>

First very raw version at having a central 'perf' command and
a list of subcommands:

  perf top
  perf stat
  perf record
  perf report
  ...

This is done by picking up Git's collection of utility functions,
and hacking them to build fine in this new environment.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

We'd like to have a similar user-space structure as Git has, for the
perfcounter tools - so copy in Git's toplevel makefile as-is.

We'll strip it down in subsequent commits to make it fit the
perfcounters code.

The Git version used: 66996ec: Sync with 1.6.2.4
Signed-off-by: NIngo Molnar <mingo@elte.hu>

It's handier than an <unknown> entry.
Also replace the kernel/user column with a more compact version:

  0.52              cc1  [k]  page_fault
  0.57               :0  [k]   _spin_lock
  0.59            :7506  [.]  <unknown>
  0.69               as  [.]  /usr/bin/as: <unknown>
  0.76              cc1  [.]  /lib64/libc-2.8.so: _int_free
  0.92              cc1  [k]  clear_page_c
  1.00            :7465  [.]  <unknown>
  1.43              cc1  [.]  /lib64/libc-2.8.so: memset
  1.86              cc1  [.]  /lib64/libc-2.8.so: _int_malloc
 70.33              cc1  [.]  /usr/libexec/gcc/x86_64-redhat-linux/4.3.2/cc1: <unknown>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

# perf-record make -j4 kernel/
 # perf-report | tail -15

  0.39              cc1 [kernel] lock_acquired
  0.42              cc1 [kernel] lock_acquire
  0.51              cc1 [ user ] /lib64/libc-2.8.90.so: _int_free
  0.51               as [kernel] clear_page_c
  0.53              cc1 [ user ] /lib64/libc-2.8.90.so: memcpy
  0.56              cc1 [ user ] /lib64/libc-2.8.90.so: _IO_vfprintf
  0.63              cc1 [kernel] lock_release
  0.67              cc1 [ user ] /lib64/libc-2.8.90.so: strlen
  0.68              cc1 [kernel] debug_smp_processor_id
  1.38              cc1 [ user ] /lib64/libc-2.8.90.so: _int_malloc
  1.55              cc1 [ user ] /lib64/libc-2.8.90.so: memset
  1.77              cc1 [kernel] __lock_acquire
  1.88              cc1 [kernel] clear_page_c
  3.61               as [ user ] /usr/bin/as: <unknown>
 59.16              cc1 [ user ] /usr/libexec/gcc/x86_64-redhat-linux/4.3.2/cc1: <unknown>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
LKML-Reference: <20090408130409.220518450@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Update kerneltop to use PERF_EVENT_MISC_OVERFLOW
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090408130408.947197470@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This is a low density serial port so needs a real major/minor
Signed-off-by: NAlan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The sketch file is a file to mark checkpoints with user data.  It was
experimentally introduced in the original implementation, and now
obsolete.  The file was handled differently with regular files; the file
size got truncated when a checkpoint was created.

This stops the special treatment and will treat it as a regular file.
Most users are not affected because mkfs.nilfs2 no longer makes this file.
Signed-off-by: NRyusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This adds a document describing the features, mount options, userland
tools, usage, disk format, and related URLs for the nilfs2 file system.
Signed-off-by: NRyusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Update the old macro DMA_nBIT_MASK related documentations

Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Update the uvesafb documentation to accurately reflect the default options
used by the driver.
Signed-off-by: NMichal Januszewski <spock@gentoo.org>
Cc: Krzysztof Helt <krzysztof.h1@poczta.fm>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add disable/enable_kretprobe() and disable/enable_jprobe().
Signed-off-by: NMasami Hiramatsu <mhiramat@redhat.com>
Acked-by: NAnanth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add disable_kprobe() and enable_kprobe() to disable/enable kprobes
temporarily.

disable_kprobe() asynchronously disables probe handlers of specified
kprobe.  So, after calling it, some handlers can be called at a while.
enable_kprobe() enables specified kprobe.

aggr_pre_handler and aggr_post_handler check disabled probes.  On the
other hand aggr_break_handler and aggr_fault_handler don't check it
because these handlers will be called while executing pre or post handlers
and usually those help error handling.
Signed-off-by: NMasami Hiramatsu <mhiramat@redhat.com>
Acked-by: NAnanth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This controller can be found on the D-Link DNS-323 for instance, where
it is to be configured via static i2c_board_info in the board-specific
mach-orion/dns323-setup.c; this driver supports only the new-style
driver model.
Tested-by: NMartin Michlmayr <tbm@cyrius.com>
Signed-off-by: NHerbert Valerio Riedel <hvr@gnu.org>
Signed-off-by: NMatthew Palmer <mpalmer@debian.org>
Signed-off-by: NLaurie Bradshaw <bradshaw.laurie@googlemail.com>
Signed-off-by: NMartin Michlmayr <tbm@cyrius.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add /proc entries to give the admin the ability to control the minimum and
maximum number of pdflush threads.  This allows finer control of pdflush
on both large and small machines.

The rationale is simply one size does not fit all.  Admins on large and/or
small systems may want to tune the min/max pdflush thread count to best
suit their needs.  Right now the min/max is hardcoded to 2/8.  While
probably a fair estimate for smaller machines, large machines with large
numbers of CPUs and large numbers of filesystems/block devices may benefit
from larger numbers of threads working on different block devices.

Even if the background flushing algorithm is radically changed, it is
still likely that multiple threads will be involved and admins would still
desire finer control on the min/max other than to have to recompile the
kernel.

The patch adds '/proc/sys/vm/nr_pdflush_threads_min' and
'/proc/sys/vm/nr_pdflush_threads_max' with r/w permissions.

The minimum value for nr_pdflush_threads_min is 1 and the maximum value is
the current value of nr_pdflush_threads_max.  This minimum is required
since additional thread creation is performed in a pdflush thread itself.

The minimum value for nr_pdflush_threads_max is the current value of
nr_pdflush_threads_min and the maximum value can be 1000.

Documentation/sysctl/vm.txt is also updated.

[akpm@linux-foundation.org: fix comment, fix whitespace, use __read_mostly]
Signed-off-by: NPeter W Morreale <pmorreale@novell.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

```---------------------------------------------------------------------------
 KernelTop:   90551 irqs/sec  kernel:15.0% [NMI, 100000 CPU cycles],  (all, 4 CPUs)
```

---------------------------------------------------------------------------

             events    pcnt         RIP          kernel function
  ______     ______   _____   ________________   _______________

           16871.00 - 19.1% - ffffffff80328e20 : clear_page_c
            8810.00 -  9.9% - ffffffff8048ce80 : page_fault
            4746.00 -  5.4% - ffffffff8048cae2 : _spin_lock
            4428.00 -  5.0% - ffffffff80328e70 : copy_page_c
            3340.00 -  3.8% - ffffffff80329090 : copy_user_generic_string!
            2679.00 -  3.0% - ffffffff8028a16b : get_page_from_freelist
            2254.00 -  2.5% - ffffffff80296f19 : unmap_vmas
            2082.00 -  2.4% - ffffffff80297e19 : handle_mm_fault
            1754.00 -  2.0% - ffffffff80288dc8 : __rmqueue_smallest
            1553.00 -  1.8% - ffffffff8048ca58 : _spin_lock_irqsave
            1400.00 -  1.6% - ffffffff8028cdc8 : release_pages
            1337.00 -  1.5% - ffffffff80285400 : find_get_page
            1335.00 -  1.5% - ffffffff80225a23 : do_page_fault
            1299.00 -  1.5% - ffffffff802ba8e7 : __d_lookup
            1174.00 -  1.3% - ffffffff802b38f3 : __link_path_walk
            1155.00 -  1.3% - ffffffff802843e1 : perf_swcounter_ctx_event!
            1137.00 -  1.3% - ffffffff8028d118 : ____pagevec_lru_add
             963.00 -  1.1% - ffffffff802a670b : kmem_cache_alloc
             885.00 -  1.0% - ffffffff8024bc61 : __wake_up_bit

Display per function percentage along with event count.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This driver supports mflash IO mode for linux.

Mflash is embedded flash drive and mainly targeted mobile and consumer
electronic devices.

Internally, mflash has nand flash and other hardware logics and supports 2
different operation (ATA, IO) modes.  ATA mode doesn't need any new driver
and currently works well under standard IDE subsystem.  Actually it's one
chip SSD.  IO mode is ATA-like custom mode for the host that doesn't have
IDE interface.

Followings are brief descriptions about IO mode.
A. IO mode based on ATA protocol and uses some custom command. (read confirm,
write confirm)
B. IO mode uses SRAM bus interface.
C. IO mode supports 4kB boot area, so host can boot from mflash.

This driver is quitely similar to a standard ATA driver, but because of
following reasons it is currently seperated with ATA layer.

1. ATA layer deals standard ATA protocol.  ATA layer have many low-
   level device specific interface, but data transfer keeps ATA rule.
   But, mflash IO mode doesn't.

2. Even though currently not used in mflash driver code, mflash has
   some custom command and modes.  (nand fusing, firmware patch, etc) If
   this feature supported in linux kernel, ATA layer more altered.

3. Currently PATA platform device driver doesn't support interrupt.
   (I'm not sure) But, mflash uses interrupt (polling mode is just for
   debug).

4. mflash is somewhat under-develop product.  Even though some company
   already using mflash their own product, I think more time is needed for
   standardization of custom command and mode.  That time (maybe October)
   I will talk to with ATA people.  If they accept integration, I will
   integrate.
Signed-off-by: Nunsik Kim <donari75@gmail.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The functions v4l2_i2c_new_subdev and v4l2_i2c_new_probed_subdev relied on
i2c_get_adapdata to return the v4l2_device. However, this is not always
possible on embedded platforms. So modify the API to pass the v4l2_device
pointer explicitly.
Signed-off-by: NHans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: NMauro Carvalho Chehab <mchehab@redhat.com>

Now that all drivers are converted to v4l2_subdev we can remove legacy code
in v4l2-common. Also move the documentation of the internal API to
v4l2-subdev.h where it really belongs.
Signed-off-by: NHans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: NMauro Carvalho Chehab <mchehab@redhat.com>

If usb_interface.dev is used as dev parameter for v4l2_device_register
v4l2_dev.name contains the v4l driver/module name and usb device and
interface instead of a simple "usb x-y".
It also matches the recommendation to set the parent devices for usb
drivers.
Signed-off-by: NJanne Grunau <j@jannau.net>
Signed-off-by: NMauro Carvalho Chehab <mchehab@redhat.com>

The DMA transfers in pxa_camera showed some weaknesses in
multiple queued buffers context :
 - poll/select problem
   The bug shows up with capture_example tool from v4l2 hg
   tree. The process just "stalls" on a "select timeout".

 - multiple buffers DMA starting
   When multiple buffers were queued, the DMA channels were
   always started right away. This is not optimal, as a
   special case appears when the first EOF was not yet
   reached, and the DMA channels were prematurely started.

 - Maintainability
   DMA code was a bit obfuscated. Rationalize the code to be
   easily maintainable by anyone.

 - DMA hot chaining
   DMA is not stopped anymore to queue a buffer, the buffer
   is queued with DMA running. As a tribute, a corner case
   exists where chaining happens while DMA finishes the
   chain, and the capture is restarted to deal with the
   missed link buffer.

This patch attemps to address these issues / improvements.

 create mode 100644 Documentation/video4linux/pxa_camera.txt
Signed-off-by: NRobert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: NGuennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: NMauro Carvalho Chehab <mchehab@redhat.com>

Update, correct and clarify instructions for loading the driver
and for setting the UNDOCREQ kernel configuration option.

Impact: documentation
Signed-off-by: NTilman Schmidt <tilman@imap.cc>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As noted by Janne Grunau it would be good if the date was also right.

(Web site also resynched)
Signed-off-by: NAlan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Move entries to be in alpha order as specified near the beginning
of this file.

Clean up some whitespace and line-length miscues.

Add '=' to "selinux" option syntax.
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix docbook fatal error:

docproc: block/blktrace.c: No such file or directory
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The new i2c binding model makes the client_register and
client_unregister methods of struct i2c_adapter useless, so we can
remove them with the rest of the legacy model.
Signed-off-by: NJean Delvare <khali@linux-fr.org>

Add bindings to support LEDs defined as of_platform devices in addition to
the existing bindings for platform devices.

New options in Kconfig allow the platform binding code and/or the
of_platform code to be turned on.  The of_platform code is of course only
available on archs that have OF support.

The existing probe and remove methods are refactored to use new functions
create_gpio_led(), to create and register one led, and delete_gpio_led(),
to unregister and free one led.  The new probe and remove methods for the
of_platform driver can then share most of the common probe and remove code
with the platform driver.

The suspend and resume methods aren't shared, but they are very short.  The
actual led driving code is the same for LEDs created by either binding.

The OF bindings are based on patch by Anton Vorontsov
<avorontsov@ru.mvista.com>.  They have been extended to allow multiple LEDs
per device.
Signed-off-by: NTrent Piepho <tpiepho@freescale.com>
Acked-by: NGrant Likely <grant.likely@secretlab.ca>
Acked-by: NSean MacLennan <smaclennan@pikatech.com>
Signed-off-by: NRichard Purdie <rpurdie@linux.intel.com>

This patch adds documentation for the new NAND FSL UPM bindings for:

 NAND: FSL-UPM: add multi chip support
 NAND: FSL-UPM: Add wait flags to support board/chip specific delays

It also documents the old binding for "chip-delay".
Signed-off-by: NWolfgang Grandegger <wg@grandegger.com>
Acked-by: NAnton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: NDavid Woodhouse <David.Woodhouse@intel.com>

Update to reflect the new record_type ABI changes.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Orig-LKML-Reference: <20090402091319.407283141@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Decouple kerneltop display from event acquisition by introducing
a separate data acquisition thread. This fixes annnoying kerneltop
display refresh jitter and missed events.

Also add a -r <prio> option, to switch the data acquisition thread
to real-time priority.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Orig-LKML-Reference: <new-submission>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Go along with the new perf_event_type ABI.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NPaul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090330171024.133985461@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: new functionality

This adds add an option to the perfstat mode of kerneltop to scale the
reported counter values according to the fraction of time that each
counter gets to count.  This is invoked with the -l option (I used 'l'
because s, c, a and e were all taken already.)  This uses the new
PERF_RECORD_TOTAL_TIME_{ENABLED,RUNNING} read format options.

With this, we get output like this:

$ ./perfstat -l -e 0:0,0:1,0:2,0:3,0:4,0:5 ./spin

 Performance counter stats for './spin':

     4016072055  CPU cycles           (events)  (scaled from 66.53%)
     2005887318  instructions         (events)  (scaled from 66.53%)
        1762849  cache references     (events)  (scaled from 66.69%)
         165229  cache misses         (events)  (scaled from 66.85%)
     1001298009  branches             (events)  (scaled from 66.78%)
          41566  branch misses        (events)  (scaled from 66.61%)

 Wall-clock time elapsed:  2438.227446 msecs

This also lets us detect when a counter is zero because the counter
never got to go on the CPU at all.  In that case we print <not counted>
rather than 0.
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Orig-LKML-Reference: <20090330171023.871484899@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

frob the kerneltop code to print the mmap data in the stream

Better use would be collecting the IPs per PID and mapping them onto
the provided userspace code.. TODO
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NPaul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090330171023.501902515@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Now that the kernel side changed, match up again.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NPaul Mackerras <paulus@samba.org>
Orig-LKML-Reference: <20090330171023.327144324@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Teach kerneltop about the new output ABI.

XXX: anybody fancy integrating the PID/TID data into the output?

Bump the mmap_data pages a little because we bloated the output and
have to be more careful about overruns with structured data.
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113317.192910290@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

provide a knob to set the number of mmap data pages.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Orig-LKML-Reference: <20090325113317.104545398@chello.nl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: documentation fix

This updates the perfcounter documentation to reflect recent changes.
Signed-off-by: NPaul Mackerras <paulus@samba.org>

Paul Mackerras wrote:

> I noticed the poll stuff is bogus - we have a 2D array of struct
> pollfds (MAX_NR_CPUS x MAX_COUNTERS), we fill in a sub-array (with the
> rest being uninitialized, since the array is on the stack) and then
> pass the first nr_cpus elements to poll.  Not what we really meant, I
> suspect. :)  Not even if we only have one counter, since it's the
> counter dimension that varies fastest.

This should fix the most obvious poll fubar.. not enough to fix the
full problem though..
Reported-by: NPaul Mackerras <paulus@samba.org>
Reported-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Orig-LKML-Reference: <18888.29986.340328.540512@cargo.ozlabs.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The glib dependency in kerneltop.c is only for a little bit of list
manipulation, and I find it inconvenient.  This adds a 'next' field to
struct source_line, which lets us link them together into a list.  The
code to do the linking ourselves turns out to be no longer or more
difficult than using glib.

This also fixes a few other problems:

- We need to #include <limits.h> to get PATH_MAX on powerpc.

- We need to #include <linux/types.h> rather than have our own
  definitions of __u64 and __s64; on powerpc the installed headers
  define them to be unsigned long and long respectively, and if we
  have our own, different definition here that causes a compile error.

- This takes out the x86 setting of errno from -ret in
  sys_perf_counter_open.  My experiments on x86 indicate that the
  glibc syscall() does this for us already.

- We had two CPU migration counters in the default set, which seems
  unnecessary; I changed one of them to a context switch counter.

- In perfstat mode we were printing CPU cycles and instructions as
  milliseconds, and the cpu clock and task clock counters as events.
  This fixes that.

- In perfstat mode we were still printing a blank line after the first
  counter, which was a holdover from when a task clock counter was
  automatically included as the first counter.  This removes the blank
  line.

- On a test machine here, parse_symbols() and parse_vmlinux() were
  taking long enough (almost 0.5 seconds) for the mmap buffer to
  overflow before we got to the first mmap_read() call, so this moves
  them before we open all the counters.

- The error message if sys_perf_counter_open fails needs to use errno,
  not -fd[i][counter].
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: NMike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Orig-LKML-Reference: <18888.29986.340328.540512@cargo.ozlabs.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>