This patch implements nmi_setup_mux() and nmi_shutdown_mux() functions
to setup/shutdown multiplexing. Multiplexing code in nmi_int.c is now
much more separated.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This new function translates physical to virtual counter numbers.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

Variable switch_index must be initialized for each cpu. This patch
fixes the initialization by moving it to the per-cpu init function
nmi_cpu_setup().
Signed-off-by: NRobert Richter <robert.richter@amd.com>

__get_cpu_var() calls smp_processor_id(). When the cpu id is already
known, instead use per_cpu() to avoid generating the id again.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

The number of hardware counters is limited. The multiplexing feature
enables OProfile to gather more events than counters are provided by
the hardware. This is realized by switching between events at an user
specified time interval.

A new file (/dev/oprofile/time_slice) is added for the user to specify
the timer interval in ms. If the number of events to profile is higher
than the number of hardware counters available, the patch will
schedule a work queue that switches the event counter and re-writes
the different sets of values into it. The switching mechanism needs to
be implemented for each architecture to support multiplexing. This
patch only implements AMD CPU support, but multiplexing can be easily
extended for other models and architectures.

There are follow-on patches that rework parts of this patch.
Signed-off-by: NJason Yeh <jason.yeh@amd.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This patch fixes whitespace changes of code that will be touched in
follow-on patches.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This patch removes the function nmi_save_registers(). Per-cpu code is
now executed only in the function nmi_cpu_setup().  Also, it renames
the per-cpu function nmi_restore_registers() to
nmi_cpu_restore_registers().
Signed-off-by: NRobert Richter <robert.richter@amd.com>

The short name of the achitecture is 'arch_perfmon'. This patch
changes the kernel parameter to use this name.

Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: NRobert Richter <robert.richter@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Commit:

 e419294e x86/oprofile: moving arch_perfmon counter setup to op_x86_model_spec.init

introduced a bug in the initialization of core_i7 leading to the
incorrect model setup to &op_ppro_spec. This patch fixes this.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

The patch removes some local variables in these functions.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This patch removes struct op_saved_msr and replaces it by an u64
variable. This makes code easier and it is possible to use 64 bit MSR
functions.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This patch introduces op_x86_get_ctrl() to calculate the value of the
performance control register. This is generic code usable for all
models. The event and reserved masks are model specific and stored in
struct op_x86_model_spec. 64 bit MSR functions are used now. The patch
removes many hard to read macros used for ctrl calculation.

The function op_x86_get_ctrl() is common code and the first step to
further merge performance counter implementations for x86 models.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

In follow-on patches the setup_ctrs() functions will need data that
describes the model. This patch extends the function argument list to
pass a pointer of the model to these function.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

Signed-off-by: NRobert Richter <robert.richter@amd.com>

The function arch_perfmon_init() in nmi_int.c is model specific. This
patch moves it to op_model_ppro.c by using the init function pointer
in struct op_x86_model_spec.

Cc: Andi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This patch removes module_param oprofile.force_arch_perfmon and
introduces oprofile.cpu_type=archperfmon instead. This new parameter
can be reused for other models and architectures.

Currently only archperfmon is supported.

Cc: Andi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

The registers are about the same as other Family 6 CPUs
so we only need to add detection.

I'm not completely happy with calling Nehalem Core i7 because
there will be undoubtedly other Nehalem based CPUs
in the future with different marketing names, but it's
the best we got for now.

Requires updated oprofile userland for the new event files.

If you don't want to update right now you can also use
oprofile.force_arch_perfmon=1 (added in the next patch) with 0.9.4
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

There are no new P4s and the oprofile code knows about all existing
ones, so we don't really need the p4force option anymore.

Remove it.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

This re-adds the force_arch_perfmon option that was in the original
arch perfmon patchkit. Originally this was rejected in favour
of a generalized perfmon=name option, but it turned out implementing
the later in a reliable way is hard (and it would have been easy
to crash the kernel if a user gets it wrong)

But now Atom and Core i7 support being readded a user would
need to update their oprofile userland to beyond 0.9.4 to use oprofile again
on Atom or Core i7.

To avoid this problem readd the force_arch_perfmon option.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

Impact: cleanup

Remove genapic.h and remove all references to it.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

- make oprofile build
- select X86_X2APIC from X86_UV - it relies on it
- export genapic for oprofile modular build
Signed-off-by: NIngo Molnar <mingo@elte.hu>

With oprofile as a module, and unloaded by profiling script,
both oprofile and kerneltop work fine.. unless you leave kerneltop
running when you start profiling, then you may see badness.
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Alan Jenkins wrote:
> This is on an EeePC 701, /proc/cpuinfo as attached.
>
> Is this expected?  Will the next release work?
>
> Thanks, Alan
>
> # opcontrol --setup --no-vmlinux
> cpu_type 'unset' is not valid
> you should upgrade oprofile or force the use of timer mode
>
> # opcontrol -v
> opcontrol: oprofile 0.9.4 compiled on Nov 29 2008 22:44:10
>
> # cat /dev/oprofile/cpu_type
> i386/p6
> # uname -r
> 2.6.28-rc6eeepc

Hi Alan,

Looking at the kernel driver code for oprofile it can return the "i386/p6" for
the cpu_type. However, looking at the user-space oprofile code there isn't the
matching entry in libop/op_cpu_type.c or the events/unit_mask files in
events/i386 directory.

The Intel AP-485 says this is a "Intel Pentium M processor model D". Seems like
the oprofile kernel driver should be identifying the processor as "i386/p6_mobile"

The driver identification code doesn't look quite right in nmi_init.c

http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git;a=blob;f=arch/x86/oprofile/nmi_int.c;h=022cd41ea9b4106e5884277096e80e9088a7c7a9;hb=HEAD

has:

409         case 10 ... 13:
410                 *cpu_type = "i386/p6";
411                 break;

Referring to the Intel AP-485:
case 10 and 11 should produce "i386/piii"
case 13 should produce "i386/p6_mobile"

I didn't see anything for case 12.

Something like the attached patch. I don't have a celeron machine to verify that
changes in this area of the kernel fix thing.

-Will
Signed-off-by: NWilliam Cohen <wcohen@redhat.com>
Tested-by: NAlan Jenkins <alan-jenkins@tuffmail.co.uk>
Acked-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NRobert Richter <robert.richter@amd.com>

No functional changes. The intension is to remove static function
declarations.
Signed-off-by: NRobert Richter <robert.richter@amd.com>

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>

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>

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>

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>

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>