Newer Intel CPUs (Core1+) have support for architectural
events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details.

The advantage of this is that it can be done without knowing about
the specific CPU, because the CPU describes by itself what
performance events are supported. This is only a fallback
because only a limited set of 6 events are supported.
This allows to do profiling on Nehalem and on Atom systems
(later not tested)

This patch implements support for that in oprofile's Intel
Family 6 profiling module. It also has the advantage of supporting
an arbitary number of events now as reported by the CPU.
Also allow arbitary counter widths >32bit while we're at it.

Requires a patched oprofile userland to support the new
architecture.

v2: update for latest oprofile tree
    remove force_arch_perfmon
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This essentially reverts Linus' earlier 4b9f12a3
commit. Nehalem is not core_2, so it shouldn't be reported as such.
However with the earlier arch perfmon patch it will fall back to
arch perfmon mode now, so there is no need to fake it as core_2.
The only drawback is that Linus will need to patch the arch perfmon
support into his oprofile binary now, but I think he can do that.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

allow to modify it at runtime
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

Reverting commit 1a960b40 for the main
branch. Multiplexing will be tracked on a separate feature branch.

Conflicts:

    arch/x86/oprofile/nmi_int.c

Add __raw access before setting per cpu variable switch_index, to avoid
the following BUG:

[  449.166827] BUG: using smp_processor_id() in preemptible [00000000] code: modprobe/6998
[  449.166848] caller is op_nmi_init+0xf0/0x2b0 [oprofile]
[  449.166855] Pid: 6998, comm: modprobe Not tainted 2.6.27-rc5-mm1 #29
[  449.166860] Call Trace:
[  449.166872]  [<ffffffff80362d67>] debug_smp_processor_id+0xd7/0xe0
[  449.166887]  [<ffffffffa00181c0>] op_nmi_init+0xf0/0x2b0 [oprofile]
[  449.166902]  [<ffffffffa0018000>] oprofile_init+0x0/0x60 [oprofile]
[  449.166915]  [<ffffffffa00180a9>] oprofile_arch_init+0x9/0x30 [oprofile]
[  449.166928]  [<ffffffffa001801e>] oprofile_init+0x1e/0x60 [oprofile]
[  449.166937]  [<ffffffff8020903b>] _stext+0x3b/0x160
[  449.166946]  [<ffffffff80477985>] __mutex_unlock_slowpath+0xe5/0x190
[  449.166955]  [<ffffffff80262c1a>] trace_hardirqs_on_caller+0xca/0x140
[  449.166965]  [<ffffffff8026f7fc>] sys_init_module+0xdc/0x210
[  449.166972]  [<ffffffff8020b7cb>] system_call_fastpath+0x16/0x1b
Signed-off-by: NAndrea Righi <righi.andrea@gmail.com>
Acked-by: NRobert Richter <robert.richter@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

nmi_shutdown() calls unregister_die_notifier() from an atomic context
after setting preempt_disable() via get_cpu_var():

[ 1049.404154] BUG: scheduling while atomic: oprofiled/7796/0x00000002
[ 1049.404171] INFO: lockdep is turned off.
[ 1049.404176] Modules linked in: oprofile af_packet rfcomm l2cap kvm_intel kvm i915 drm acpi_cpufreq cpufreq_userspace cpufreq_conservative cpufreq_ondemand cpufreq_powersave freq_table container sbs sbshc dm_mod arc4 ecb cryptomgr aead snd_hda_intel crypto_blkcipher snd_pcm_oss crypto_algapi snd_pcm iwlagn iwlcore snd_timer iTCO_wdt led_class btusb iTCO_vendor_support snd psmouse bluetooth mac80211 soundcore cfg80211 snd_page_alloc intel_agp video output button battery ac dcdbas evdev ext3 jbd mbcache sg sd_mod piix ata_piix libata scsi_mod dock tg3 libphy ehci_hcd uhci_hcd usbcore thermal processor fan fuse
[ 1049.404362] Pid: 7796, comm: oprofiled Not tainted 2.6.27-rc5-mm1 #30
[ 1049.404368] Call Trace:
[ 1049.404384]  [<ffffffff804769fd>] thread_return+0x4a0/0x7d3
[ 1049.404396]  [<ffffffff8026ad92>] generic_exec_single+0x52/0xe0
[ 1049.404405]  [<ffffffff8026ae1a>] generic_exec_single+0xda/0xe0
[ 1049.404414]  [<ffffffff8026aee3>] smp_call_function_single+0x73/0x150
[ 1049.404423]  [<ffffffff804770c5>] schedule_timeout+0x95/0xd0
[ 1049.404430]  [<ffffffff80476083>] wait_for_common+0x43/0x180
[ 1049.404438]  [<ffffffff80476154>] wait_for_common+0x114/0x180
[ 1049.404448]  [<ffffffff80236980>] default_wake_function+0x0/0x10
[ 1049.404457]  [<ffffffff8024f810>] synchronize_rcu+0x30/0x40
[ 1049.404463]  [<ffffffff8024f890>] wakeme_after_rcu+0x0/0x10
[ 1049.404472]  [<ffffffff80479ca0>] _spin_unlock_irqrestore+0x40/0x80
[ 1049.404482]  [<ffffffff80256def>] atomic_notifier_chain_unregister+0x3f/0x60
[ 1049.404501]  [<ffffffffa03d8801>] nmi_shutdown+0x51/0x90 [oprofile]
[ 1049.404517]  [<ffffffffa03d6134>] oprofile_shutdown+0x34/0x70 [oprofile]
[ 1049.404532]  [<ffffffffa03d721e>] event_buffer_release+0xe/0x40 [oprofile]
[ 1049.404543]  [<ffffffff802bdcdd>] __fput+0xcd/0x240
[ 1049.404551]  [<ffffffff802baa74>] filp_close+0x54/0x90
[ 1049.404560]  [<ffffffff8023e1d1>] put_files_struct+0xb1/0xd0
[ 1049.404568]  [<ffffffff8023f82f>] do_exit+0x18f/0x930
[ 1049.404576]  [<ffffffff8020be03>] restore_args+0x0/0x30
[ 1049.404584]  [<ffffffff80240006>] do_group_exit+0x36/0xa0
[ 1049.404592]  [<ffffffff8020b7cb>] system_call_fastpath+0x16/0x1b

This can be easily triggered with 'opcontrol --shutdown'.

Simply move get_cpu_var() above unregister_die_notifier().
Signed-off-by: NAndrea Righi <righi.andrea@gmail.com>
Acked-by: NRobert Richter <robert.richter@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Vegard Nossum reported oprofile + hibernation problems:

> Now some warnings:
>
> ------------[ cut here ]------------
> WARNING: at /uio/arkimedes/s29/vegardno/git-working/linux-2.6/kernel/smp.c:328 s
> mp_call_function_mask+0x194/0x1a0()

The usual problem: the suspend function when interrupts are
already disabled calls smp_call_function which is not allowed with
interrupt off. But at this point all the other CPUs should be already
down anyways, so it should be enough to just drop that.

This patch should fix that problem at least by fixing cpu hotplug&
suspend support.

[ mingo@elte.hu: fixed 5 coding style errors. ]
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Tested-by: NVegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

A coding style patch to arch/x86/oprofile/op_model_p4.c that
removes 87 errors and 4 warnings.

Before:
total: 89 errors, 13 warnings, 722 lines checked

After:
total: 2 errors, 9 warnings, 721 lines checked

Compile tested, binary verified as follow:

paolo@paolo-desktop:~/linux.trees.git$ size /tmp/op_model_p4.o.*
   text    data     bss     dec     hex filename
   2691     968      32    3691     e6b /tmp/op_model_p4.o.after
   2691     968      32    3691     e6b /tmp/op_model_p4.o.before

paolo@paolo-desktop:~/linux.trees.git$ md5sum /tmp/op_model_p4.o.*
8c1c9823bab33333e1f7f76574e62561  /tmp/op_model_p4.o.after
8c1c9823bab33333e1f7f76574e62561  /tmp/op_model_p4.o.before
Signed-off-by: NPaolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Cc: robert.richter@amd.com
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Jason Yeh <jason.yeh@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patch introduces multiplexing support for the Oprofile kernel
module. It basically adds a new function pointer in oprofile_operator
allowing each architecture to supply its callback to switch between
different sets of event when the timer expires. Userspace tools can
modify the time slice through /dev/oprofile/time_slice.

It also modifies the number of counters exposed to the userspace through
/dev/oprofile. For example, the number of counters for AMD CPUs are
changed to 32 and multiplexed in the sets of 4.
Signed-off-by: NJason Yeh <jason.yeh@amd.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patchset supports the new profiling hardware available in the
latest AMD CPUs in the oProfile driver.
Signed-off-by: NBarry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

These functions contain code for all AMD CPUs. The new names fit
better.
Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Cc: Barry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patch implements model specific OProfile init/exit functions for
x86 CPUs. Though there is more rework needed at the initialization
code, this new introduced functions allow it to keep model specific
code in the corresponding op_model_*.c files.

The function interface is the same as for oprofile_arch_init/exit().
Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patch add support for AMD Family 11h CPUs.
Signed-off-by: NBarry Kasindorf <barry.kasindorf@amd.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>
Cc: oprofile-list <oprofile-list@lists.sourceforge.net>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

..otherwise oprofile will fall back on that poor timer interrupt.

Also replace the unreadable chain of if-statements with a "switch()"
statement instead. It generates better code, and is a lot clearer.
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It's not even passed on to smp_call_function() anymore, since that
was removed. So kill it.
Acked-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Reviewed-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

fix:

    BUG: using smp_processor_id() in preemptible [00000000] code: oprofiled/27301
    caller is nmi_shutdown+0x11/0x60
    Pid: 27301, comm: oprofiled Not tainted 2.6.26-rc7 #25
     [<c028a90d>] debug_smp_processor_id+0xbd/0xc0
     [<c045fba1>] nmi_shutdown+0x11/0x60
     [<c045dd4a>] oprofile_shutdown+0x2a/0x60

Note that we don't need this for the other functions, since they are all
called with on_each_cpu() (which disables preemption for us anyway).
Signed-off-by: NVegard Nossum <vegard.nossum@gmail.com>
Cc: Philippe Elie <phil.el@wanadoo.fr>
Cc: oprofile-list@lists.sf.net
Cc: Johannes Weiner <hannes@saeurebad.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Change the following arrays sized by NR_CPUS to be PERCPU variables:

	static struct op_msrs cpu_msrs[NR_CPUS];
	static unsigned long saved_lvtpc[NR_CPUS];

Also some minor complaints from checkpatch.pl fixed.

Based on:
	git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
	git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git

All changes were transparent except for:

 static void nmi_shutdown(void)
 {
+	struct op_msrs *msrs = &__get_cpu_var(cpu_msrs);
 	nmi_enabled = 0;
 	on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
 	unregister_die_notifier(&profile_exceptions_nb);
-	model->shutdown(cpu_msrs);
+	model->shutdown(msrs);
 	free_msrs();
 }

The existing code passed a reference to cpu 0's instance of struct op_msrs
to model->shutdown, whilst the other functions are passed a reference to
<this cpu's> instance of a struct op_msrs.  This seemed to be a bug to me
even though as long as cpu 0 and <this cpu> are of the same type it would
have the same effect...?

Cc: Philippe Elie <phil.el@wanadoo.fr>
Signed-off-by: NMike Travis <travis@sgi.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Before:
   total: 3 errors, 0 warnings, 69 lines checked
After:
   total: 0 errors, 0 warnings, 69 lines checked

No code changed:

arch/x86/oprofile/nmi_timer_int.o:

   text	   data	    bss	    dec	    hex	filename
    180	     12	      0	    192	     c0	nmi_timer_int.o.before
    180	     12	      0	    192	     c0	nmi_timer_int.o.after

md5:
   0433c31d758e81da574e01722a8036ea  nmi_timer_int.o.before.asm
   0433c31d758e81da574e01722a8036ea  nmi_timer_int.o.after.asm
Signed-off-by: NPaolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Before:
   total: 5 errors, 4 warnings, 48 lines checked
After:
   total: 0 errors, 4 warnings, 49 lines checked

No code changed:

arch/x86/oprofile/init.o:

   text	   data	    bss	    dec	    hex	filename
     42	      0	      0	     42	     2a	init.o.before
     42	      0	      0	     42	     2a	init.o.after

md5:
   74c94c315cfbf245aeba36eceac57e66  init.o.before.asm
   74c94c315cfbf245aeba36eceac57e66  init.o.after.asm
Signed-off-by: NPaolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The patch fixes 33 errors and a few warnings reported by checkpatch.pl

arch/x86/oprofile/op_model_athlon.o:
   text    data     bss     dec     hex filename
   1691       0      32    1723     6bb op_model_athlon.o.before
   1691       0      32    1723     6bb op_model_athlon.o.after
md5:
c354bc2d7140e1e626c03390eddaa0a6  op_model_athlon.o.before.asm
c354bc2d7140e1e626c03390eddaa0a6  op_model_athlon.o.after.asm
Signed-off-by: NPaolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

no code changed:

arch/x86/oprofile/op_model_ppro.o:
   text    data     bss     dec     hex filename
   1765       0      16    1781     6f5 op_model_ppro.o.before
   1765       0      16    1781     6f5 op_model_ppro.o.after
md5:
71c7f68d2197d686e3d1121bc18a6b6e  op_model_ppro.o.before.asm
71c7f68d2197d686e3d1121bc18a6b6e  op_model_ppro.o.after.asm
Signed-off-by: NPaolo Ciarrocchi <paolo.ciarrocchi@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Choose a less generic name for such a special case.  Add
a comment explaining the odd use in X86_32.

Change the one user of stack_pointer.
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Right now, we take the stack pointer early during the backtrace path, but
only calculate bp several functions deep later, making it hard to reconcile
the stack and bp backtraces (as well as showing several internal backtrace
functions on the stack with bp based backtracing).

This patch moves the bp taking to the same place we take the stack pointer;
sadly this ripples through several layers of the back tracing stack,
but it's not all that bad in the end I hope.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

For enhancing the 32 bit EBP based backtracer, I need the capability
for the backtracer to tell it's customer that an entry is either
reliable or unreliable, and the backtrace printing code then needs to
print the unreliable ones slightly different.

This patch adds the basic capability, the next patch will add a user
of this capability.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

This patch fixes most errors detected by checkpatch.pl.

                                     errors   lines of code   errors/KLOC
arch/x86/oprofile/nmi_int.c (after)       1             461           2.1
arch/x86/oprofile/nmi_int.c (before)     60             477         125.7

No code changed.

size:
   text    data     bss     dec     hex filename
   2675     264     472    3411     d53 nmi_int.o.after
   2675     264     472    3411     d53 nmi_int.o.before

md5sum:
  847aea0cc68fe1a2b5e7019439f3b4dd  nmi_int.o.after
  847aea0cc68fe1a2b5e7019439f3b4dd  nmi_int.o.before
Signed-off-by: NCarlos R. Mafra <crmafra@gmail.com>
Reviewed-by: NJesper Juhl <jesper.juhl@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

We have a lot of code which differs only by the naming of specific
members of structures that contain registers.  In order to enable
additional unifications, this patch drops the e- or r- size prefix
from the register names in struct pt_regs, and drops the x- prefixes
for segment registers on the 32-bit side.

This patch also performs the equivalent renames in some additional
places that might be candidates for unification in the future.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

All kobjects require a dynamically allocated name now. We no longer
need to keep track if the name is statically assigned, we can just
unconditionally free() all kobject names on cleanup.
Signed-off-by: NKay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>