With this patch you have following minimal sampling rate restrictions:

Kernel restrictions:
If CONFIG_NO_HZ is set, the limit is 10ms fixed.
If CONFIG_NO_HZ is not set or no_hz=off boot parameter is used, the
limits depend on the CONFIG_HZ option:
HZ=1000: min=20000us  (20ms)
HZ=250:  min=80000us  (80ms)
HZ=100:  min=200000us (200ms)

HW restrictions:
Do not sample/poll more often than HW latency * 100  exported by the low
level cpufreq HW driver

The higher value of above restrictions is the minimal sampling rate
that can be set (and can be seen via ondemand/sampling_rate_min sysfs file)

Default sampling rate still is HW latency * 1000, but this will now end
up in lower values on latest (Intel and AMD) hardware as these can switch
really fast and sampling rate mostly was limited to the 80ms or 200ms
(depending on whether HZ=250 or HZ=1000 is used).
Signed-off-by: NThomas Renninger <trenn@suse.de>
Cc: Pallipadi Venkatesh <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

* Rafael J. Wysocki (rjw@sisk.pl) wrote:
> This message has been generated automatically as a part of a report
> of regressions introduced between 2.6.28 and 2.6.29.
>
> The following bug entry is on the current list of known regressions
> introduced between 2.6.28 and 2.6.29.  Please verify if it still should
> be listed and let me know (either way).
>
>
> Bug-Entry	: http://bugzilla.kernel.org/show_bug.cgi?id=13186
> Subject		: cpufreq timer teardown problem
> Submitter	: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
> Date		: 2009-04-23 14:00 (24 days old)
> References	: http://marc.info/?l=linux-kernel&m=124049523515036&w=4
> Handled-By	: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
> Patch		: http://patchwork.kernel.org/patch/19754/
> 		  http://patchwork.kernel.org/patch/19753/
>

(re-send with updated changelog)

cpufreq fix timer teardown in conservative governor

The problem is that dbs_timer_exit() uses cancel_delayed_work() when it should
use cancel_delayed_work_sync(). cancel_delayed_work() does not wait for the
workqueue handler to exit.

The ondemand governor does not seem to be affected because the
"if (!dbs_info->enable)" check at the beginning of the workqueue handler returns
immediately without rescheduling the work. The conservative governor in
2.6.30-rc has the same check as the ondemand governor, which makes things
usually run smoothly. However, if the governor is quickly stopped and then
started, this could lead to the following race :

dbs_enable could be reenabled and multiple do_dbs_timer handlers would run.
This is why a synchronized teardown is required.

Depends on patch
cpufreq: remove rwsem lock from CPUFREQ_GOV_STOP call

The following patch applies to 2.6.30-rc2. Stable kernels have a similar
issue which should also be fixed, but the code changed between 2.6.29
and 2.6.30, so this patch only applies to 2.6.30-rc.
Signed-off-by: NMathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: gregkh@suse.de
CC: stable@kernel.org
CC: cpufreq@vger.kernel.org
CC: Ingo Molnar <mingo@elte.hu>
CC: rjw@sisk.pl
CC: Ben Slusky <sluskyb@paranoiacs.org>
Signed-off-by: NDave Jones <davej@redhat.com>

AMD users get particular hit by this issue (bug 8081) as it caps at
typically 90 seconds as the minimum period for a frequency change.
Harsh eh?  Years ago I borked this buy puting the 10x in the wrong
place...I fix that by removing it altogether.
Signed-off-by: NAlexander Clouter <alex@digriz.org.uk>
Signed-off-by: NDave Jones <davej@redhat.com>

As conservative is based off ondemand the codebases occasionally need to be
resync'd.  This patch, although ugly, does this.
Signed-off-by: NAlexander Clouter <alex@digriz.org.uk>
Signed-off-by: NDave Jones <davej@redhat.com>

When someone added the dbs_cpufreq_notifier section to the governor the
code ended up causing the frequency to only fall.  This is because
requested_freq is tinkered with and that should only modified if it has
an invlaid value due to changes in the available frequency ranges

This should fix #10055.
Signed-off-by: NAlexander Clouter <alex@digriz.org.uk>
Signed-off-by: NDave Jones <davej@redhat.com>

Amend author's email address.
Signed-off-by: NAlexander Clouter <alex@digriz.org.uk>
Signed-off-by: NDave Jones <davej@redhat.com>

Limit sampling rate to transition_latency * 100 or kernel limits.
If sampling_rate is tried to be set too low, set the lowest allowed value.
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>

The same info can be obtained via the transition_latency sysfs file
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>

Signed-off-by: NDave Jones <davej@redhat.com>

Impact: use new cpumask API to reduce memory usage

This is part of an effort to reduce structure sizes for machines
configured with large NR_CPUS.  cpumask_t gets replaced by
cpumask_var_t, which is either struct cpumask[1] (small NR_CPUS) or
struct cpumask * (large NR_CPUS).
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NMike Travis <travis@sgi.com>
Acked-by: NDave Jones <davej@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

We don't need to export the governors for use as the default governor,
because the default governor will be built-in anyway and we can access
the symbol directly.

This also fixes the following sparse warnings:

drivers/cpufreq/cpufreq_conservative.c:578:25: warning: symbol 'cpufreq_gov_conservative' was not declared. Should it be static?
drivers/cpufreq/cpufreq_ondemand.c:582:25: warning: symbol 'cpufreq_gov_ondemand' was not declared. Should it be static?
drivers/cpufreq/cpufreq_performance.c:39:25: warning: symbol 'cpufreq_gov_performance' was not declared. Should it be static?
drivers/cpufreq/cpufreq_powersave.c:38:25: warning: symbol 'cpufreq_gov_powersave' was not declared. Should it be static?
drivers/cpufreq/cpufreq_userspace.c:190:25: warning: symbol 'cpufreq_gov_userspace' was not declared. Should it be static?
Signed-off-by: NSven Wegener <sven.wegener@stealer.net>
Signed-off-by: NDave Jones <davej@redhat.com>

Venki Pallipadi made a similar change to the ondemand governor a while
back (in commit 28287033). It seems to
work just as well in the conservative governor, leading to fewer wakeups
as reported by powertop.
Signed-off-by: NBen Slusky <sluskyb@paranoiacs.org>
Signed-off-by: NDave Jones <davej@redhat.com>

drivers/cpufreq/cpufreq_conservative.c:336:15: warning: symbol 'freq_step' shadows an earlier one

Just rename the local variable.
Signed-off-by: NDave Jones <davej@redhat.com>

Change references from for_each_cpu_mask to for_each_cpu_mask_nr
where appropriate
Reviewed-by: NPaul Jackson <pj@sgi.com>
Reviewed-by: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NMike Travis <travis@sgi.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

When the cpufreq driver starts up at boot time, it calls into the default
governor which might not be initialised yet.  This hurts when the
governor's worker function relies on memory that is not yet set up by its
init function.

This migrates all governors from module_init() to fs_initcall() when being
the default, as was already done in cpufreq_performance when it was the
only possible choice.  The performance governor is always initialized early
because it might be used as fallback even when not being the default.

Fixes at least one actual oops where ondemand is the default governor and
cpufreq_governor_dbs() uses the uninitialised kondemand_wq work-queue
during boot-time.
Signed-off-by: NJohannes Weiner <hannes@saeurebad.de>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NDave Jones <davej@redhat.com>

Make cpufreq_conservative handle out-of-sync events properly

Currently, the cpufreq_conservative governor doesn't get notified when the
actual frequency the cpu is running at differs from what cpufreq thought it
was. As a result the cpu may stay at the maximum frequency after a s2ram /
resume cycle even though the system is idle.
Signed-off-by: NElias Oltmanns <eo@nebensachen.de>
Signed-off-by: NDave Jones <davej@redhat.com>

Depending on the transition latency of the HW for cpufreq switches, the
ondemand or conservative governor cannot be used with certain cpufreq
drivers.  Still the ondemand should be the default governor on a wide range
of systems.  This patch allows this and lets the governor fallback to the
performance governor at cpufreq driver load time, if the driver does not
support fast enough frequency switching.

Main benefit is that on e.g.  installation or other systems without
userspace support a working dynamic cpufreq support can be achieved on most
systems by simply loading the cpufreq driver.  This is especially essential
for recent x86(_64) laptop hardware which may rely on working dynamic
cpufreq OS support.
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Bryan Wu <bryan.wu@analog.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDave Jones <davej@redhat.com>

After Al Viro (finally) succeeded in removing the sched.h #include in module.h
recently, it makes sense again to remove other superfluous sched.h includes.
There are quite a lot of files which include it but don't actually need
anything defined in there.  Presumably these includes were once needed for
macros that used to live in sched.h, but moved to other header files in the
course of cleaning it up.

To ease the pain, this time I did not fiddle with any header files and only
removed #includes from .c-files, which tend to cause less trouble.

Compile tested against 2.6.20-rc2 and 2.6.20-rc2-mm2 (with offsets) on alpha,
arm, i386, ia64, mips, powerpc, and x86_64 with allnoconfig, defconfig,
allmodconfig, and allyesconfig as well as a few randconfigs on x86_64 and all
configs in arch/arm/configs on arm.  I also checked that no new warnings were
introduced by the patch (actually, some warnings are removed that were emitted
by unnecessarily included header files).
Signed-off-by: NTim Schmielau <tim@physik3.uni-rostock.de>
Acked-by: NRussell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The hotplug CPU locking in cpufreq is horrendous.  No-one seems to care
enough to fix it, so just remove it so that the 99.9% of the real world
users of this code can use cpufreq without being bothered by warnings.
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDave Jones <davej@redhat.com>

Fix up for make allyesconfig.
Signed-Off-By: NDavid Howells <dhowells@redhat.com>

Clean up cpufreq subsystem to fix coding style issues and to improve
the readability.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NDave Jones <davej@redhat.com>

Signed-off-by: NJeff Garzik <jeff@garzik.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NDave Jones <davej@redhat.com>

The patch below moves the cpu hotplugging higher up in the cpufreq
layering; this is needed to avoid recursive taking of the cpu hotplug
lock and to otherwise detangle the mess.

The new rules are:
1. you must do lock_cpu_hotplug() around the following functions:
   __cpufreq_driver_target
   __cpufreq_governor (for CPUFREQ_GOV_LIMITS operation only)
   __cpufreq_set_policy
2. governer methods (.governer) must NOT take the lock_cpu_hotplug()
   lock in any way; they are called with the lock taken already
3. if your governer spawns a thread that does things, like calling
   __cpufreq_driver_target, your thread must honor rule #1.
4. the policy lock and other cpufreq internal locks nest within
   the lock_cpu_hotplug() lock.

I'm not entirely happy about how the __cpufreq_governor rule ended up
(conditional locking rule depending on the argument) but basically all
callers pass this as a constant so it's not too horrible.

The patch also removes the cpufreq_governor() function since during the
locking audit it turned out to be entirely unused (so no need to fix it)

The patch works on my testbox, but it could use more testing
(otoh... it can't be much worse than the current code)
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

drivers/cpufreq/cpufreq_ondemand.c: In function 'do_dbs_timer':
drivers/cpufreq/cpufreq_ondemand.c:374: warning: implicit declaration of function 'lock_cpu_hotplug'
drivers/cpufreq/cpufreq_ondemand.c:381: warning: implicit declaration of function 'unlock_cpu_hotplug'
drivers/cpufreq/cpufreq_conservative.c: In function 'do_dbs_timer':
drivers/cpufreq/cpufreq_conservative.c:425: warning: implicit declaration of function 'lock_cpu_hotplug'
drivers/cpufreq/cpufreq_conservative.c:432: warning: implicit declaration of function 'unlock_cpu_hotplug'

Cc: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Rootcaused the bug to a deadlock in cpufreq and ondemand. Due to non-existent
ordering between cpu_hotplug lock and dbs_mutex. Basically a race condition
between cpu_down() and do_dbs_timer().

cpu_down() flow:
* cpu_down() call for CPU 1
* Takes hot plug lock
* Calls pre down notifier
*     cpufreq notifier handler calls cpufreq_driver_target() which takes
      cpu_hotplug lock again. OK as cpu_hotplug lock is recursive in same
      process context
* CPU 1 goes down
* Calls post down notifier
*     cpufreq notifier handler calls ondemand event stop which takes dbs_mutex

So, cpu_hotplug lock is taken before dbs_mutex in this flow.

do_dbs_timer is triggerred by a periodic timer event.
It first takes dbs_mutex and then takes cpu_hotplug lock in
cpufreq_driver_target().
Note the reverse order here compared to above. So, if this timer event happens
at right moment during cpu_down, system will deadlok.

Attached patch fixes the issue for both ondemand and conservative.
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

< 0 checks on unsigned variables are pointless.
Signed-off-by: NDave Jones <davej@redhat.com>

Keep the value of ignore_nice_load and freq_step of the conservative
governor after the governor is deselected and reselected.
Signed-off-by: NMattia Dongili <malattia@linux.it>
Signed-off-by: NDave Jones <davej@redhat.com>

Venki, author of cpufreq_ondemand, came up with a neater way to remove the
initialiser code from the main loop of my code and out to the point when the
governor is actually initialised.

Not only does it look but it also feels cleaner, plus its simpler to
understand.  It also saves a bunch of pointless conditional statements in the
main loop.
Signed-off-by: NAlexander Clouter <alex-kernel@digriz.org.uk>
Signed-off-by: NDominik Brodowski <linux@dominikbrodowski.net>

All these changes should make cpufreq_conservative safe in regards to the x86
for_each_cpu cpumask.h changes and whatnot.

Whilst making it safe a number of pointless for loops related to the cpu
mask's were removed.  I was never comfortable with all those for loops,
especially as the iteration is over the same data again and again for each
CPU you had in a single poll, an O(n^2) outcome to frequency scaling.

The approach I use is to assume by default no CPU's exist and it sets the
requested_freq to zero as a kind of flag, the reasoning is in the source ;)
If the CPU is queried and requested_freq is zero then it initialises the
variable to current_freq and then continues as if nothing happened which
should be the same net effect as before?
Signed-off-by: NAlexander Clouter <alex-kernel@digriz.org.uk>
Signed-off-by: NDominik Brodowski <linux@dominikbrodowski.net>

The sensible approach to making conservative less responsive than ondemand :)
As mentioned in patch [1/4].  We do not want conservative to shoot through
all the frequencies, its point (by default) is to slowly move through them.

By default its ten times less responsive.
Signed-off-by: NAlexander Clouter <alex-kernel@digriz.org.uk>
Signed-off-by: NDominik Brodowski <linux@dominikbrodowski.net>

Since the conservative govenor was released its codebase has drifted from the
the direction and updates that have been applied to the ondemand govornor.

This patch addresses the lack of updates in that period and brings
conservative back up to date.  The resulting diff file between
cpufreq_ondemand.c and cpufreq_conservative.c is now much smaller and shows
more clearly the differences between the two.

Another reason to do this is ages ago, knowingly, I did a piss poor attempt
at making conservative less responsive by knocking up
DEF_SAMPLING_RATE_LATENCY_MULTIPLIER by two orders of magnitude.  I did fix
this ages ago but in my dis-organisation I must have toasted the diff and
left it the way it was.  About two weeks ago a user contacted me saying he
was having problems with the conservative governor with his AMD Athlon XP-M
2800+ as /sys/devices/system/cpu/cpu0/cpufreq/conservative showed
  sampling_rate_min   9950000
  sampling_rate_max   1360065408

Nine seconds to decide about changing the frequency....not too responsive :)
Signed-off-by: NAlexander Clouter <alex-kernel@digriz.org.uk>
Signed-off-by: NDominik Brodowski <linux@dominikbrodowski.net>

Semaphore to mutex conversion.

The conversion was generated via scripts, and the result was validated
automatically via a script as well.
Signed-off-by: NArjan van de Ven <arjan@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NDave Jones <davej@redhat.com>

The use of the 'ignore_nice' sysfs file is confusing to anyone using it.
This removes the sysfs file 'ignore_nice' and in its place creates a
'ignore_nice_load' entry that defaults to '0'; meaning nice'd processes
_are_ counted towards the 'business' calculation.

WARNING: this obvious breaks any userland tools that expected ignore_nice'
to exist, to draw attention to this fact it was concluded on the mailing
list that the entry should be removed altogether so the userland app breaks
and so the author can build simple to detect workaround.  Having said that
it seems currently very few tools even make use of this functionality; all
I could find was a Gentoo Wiki entry.
Signed-off-by: NAlexander Clouter <alex-kernel@digriz.org.uk>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NDave Jones <davej@redhat.com>

Don't try to access not-present CPUs.  Conservative governor will always
oops on SMP without this fix.

Fixes http://bugzilla.kernel.org/show_bug.cgi?id=4781Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

[PATCH] [3/5] ondemand,conservative governor idle_tick clean-up

Ondemand and conservative governor clean-up, it factorises the idle ticks 
measurement.
Signed-off-by: NEric Piel <eric.piel@tremplin-utc.net>
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

[PATCH] [2/5] ondemand,conservative governor store the idle ticks for all cpus

Ondemand, conservative governor did not store prev_cpu_idle_up into 
prev_cpu_idle_down for other CPUs than the current CPU.
Signed-off-by: NEric Piel <eric.piel@tremplin-utc.net>
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

[PATCH] [1/5] ondemand,conservative minor bug-fix and cleanup

Attached patch fixes some minor issues with Alexander's patch and related
cleanup in both ondemand and conservative governor.
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

A new cpufreq module, based on the ondemand one with my additional patches
just posted.  This one is more suitable for battery environments where its
probably more appealing to have the cpu freq gracefully increase and decrease
rather than flip between the min and max freq's.

N.B. Bruno Ducrot pointed out that the amd64's "do have unacceptable latency
between min and max freq transition, due to the step-by-step requirements
(200MHz IIRC)"; so AMD64 users would probably benefit from this too.
Signed-off-by: NAlexander Clouter <alex-kernel@digriz.org.uk>
Signed-off-by: NDave Jones <davej@redhat.com>

This patch makes a needlessly global and EXPORT_SYMBOL'ed struct static.
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NDave Jones <davej@redhat.com>