Currently we always calculate the CPU iowait time and add it to idle time.
If we are in ondemand and we use io_is_busy, we re-calculate iowait time
and we subtract it from idle time.

With this patch iowait time is calculated only when necessary avoiding
the double call to get_cpu_iowait_time_us. We use a parameter in
function get_cpu_idle_time to distinguish when the iowait time will be
added to idle time or not, without the need of keeping the prev_io_wait.
Signed-off-by: NStratos Karafotis <stratosk@semaphore.gr>
Acked-by: NViresh Kumar <viresh.kumar@linaro.,org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Following patch has introduced per cpu timers or works for ondemand and
conservative governors.

	commit 2abfa876
	Author: Rickard Andersson <rickard.andersson@stericsson.com>
	Date:   Thu Dec 27 14:55:38 2012 +0000

	    cpufreq: handle SW coordinated CPUs

This causes additional unnecessary interrupts on all cpus when the load is
recently evaluated by any other cpu. i.e. When load is recently evaluated by cpu
x, we don't really need any other cpu to evaluate this load again for the next
sampling_rate time.

Some sort of code is present to avoid that but we are still getting timer
interrupts for all cpus. A good way of avoiding this would be to modify delays
for all cpus (policy->cpus) whenever any cpu has evaluated load.

This patch does this change and some related code cleanup.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Because we have per cpu timer now, we check if we need to evaluate load again or
not (In case it is recently evaluated). Here the 2nd cpu which got timer
interrupt updates core_dbs_info->sample_type irrespective of load evaluation is
required or not. Which is wrong as the first cpu is dependent on this variable
set to an older value.

Moreover it would be best in this case to schedule 2nd cpu's timer to
sampling_rate instead of freq_lo or hi as that must be managed by the other cpu.
In case the other cpu idles in between then also we wouldn't loose much power.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Currently, there can't be multiple instances of single governor_type.
If we have a multi-package system, where we have multiple instances
of struct policy (per package), we can't have multiple instances of
same governor. i.e. We can't have multiple instances of ondemand
governor for multiple packages.

Governors directory in sysfs is created at /sys/devices/system/cpu/cpufreq/
governor-name/. Which again reflects that there can be only one
instance of a governor_type in the system.

This is a bottleneck for multicluster system, where we want different
packages to use same governor type, but with different tunables.

This patch uses the infrastructure provided by earlier patch and
implements init/exit routines for ondemand and conservative
governors.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Fix some typos in comments.
Signed-off-by: NStratos Karafotis <stratosk@semaphore.gr>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

In order to avoid the calculation of up_threshold - down_differential
every time that the frequency must be decreased, we replace the
down_differential tuner with the adj_up_threshold which keeps the
difference across multiple checks.

Update the adj_up_threshold only when the up_theshold is also updated.
Signed-off-by: NStratos Karafotis <stratosk@semaphore.gr>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

With the inclusion of following patches:

9f4eb10 cpufreq: conservative: call dbs_check_cpu only when necessary
772b4b1 cpufreq: ondemand: call dbs_check_cpu only when necessary

code redundancy between the conservative and ondemand governors is
introduced again, so get rid of it.

[rjw: Changelog]
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Tested-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Fix governors code to set all cpu's cdbs->cpu to the the actual cpu id
and use cur_policy->cpu istead of cdbs->cpu to track current governor's
leader cpu.
Reported-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Implement a generic helper function policy_is_shared() to replace the
current dbs_sw_coordinated_cpus() at cpufreq level, so that it can be
used by code other than cpufreq governors.
Suggested-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Acked-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Modify update_sampling_rate() to check, and eventually immediately
schedule, all CPU's do_dbs_timer delayed work.

This is required in case of software coordinated CPUs, as we now have a
separate delayed work for each CPU.
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Modify ondemand timer to not resample CPU utilization if recently
sampled from another SW coordinated core.
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

This patch fixes a bug that occurred when we had load on a secondary CPU
and the primary CPU was sleeping. Only one sampling timer was spawned
and it was spawned as a deferred timer on the primary CPU, so when a
secondary CPU had a change in load this was not detected by the cpufreq
governor (both ondemand and conservative).

This patch make sure that deferred timers are run on all CPUs in the
case of software controlled CPUs that run on the same frequency.
Signed-off-by: NRickard Andersson <rickard.andersson@stericsson.com>
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Fix cpufreq_gov_ondemand to skip CPU where another governor is used.

The bug present itself as NULL pointer access on the mutex_lock() call,
an can be reproduced on an SMP machine by setting the default governor
to anything other than ondemand, setting a single CPU's governor to
ondemand, then changing the sample rate by writing on:

> /sys/devices/system/cpu/cpufreq/ondemand/sampling_rate

Backtrace:

Nov 26 17:36:54 balto kernel: [  839.585241] BUG: unable to handle kernel NULL pointer dereference at           (null)
Nov 26 17:36:54 balto kernel: [  839.585311] IP: [<ffffffff8174e082>] __mutex_lock_slowpath+0xb2/0x170
[snip]
Nov 26 17:36:54 balto kernel: [  839.587005] Call Trace:
Nov 26 17:36:54 balto kernel: [  839.587030]  [<ffffffff8174da82>] mutex_lock+0x22/0x40
Nov 26 17:36:54 balto kernel: [  839.587067]  [<ffffffff81610b8f>] store_sampling_rate+0xbf/0x150
Nov 26 17:36:54 balto kernel: [  839.587110]  [<ffffffff81031e9c>] ?  __do_page_fault+0x1cc/0x4c0
Nov 26 17:36:54 balto kernel: [  839.587153]  [<ffffffff813309bf>] kobj_attr_store+0xf/0x20
Nov 26 17:36:54 balto kernel: [  839.587192]  [<ffffffff811bb62d>] sysfs_write_file+0xcd/0x140
Nov 26 17:36:54 balto kernel: [  839.587234]  [<ffffffff8114c12c>] vfs_write+0xac/0x180
Nov 26 17:36:54 balto kernel: [  839.587271]  [<ffffffff8114c472>] sys_write+0x52/0xa0
Nov 26 17:36:54 balto kernel: [  839.587306]  [<ffffffff810321ce>] ?  do_page_fault+0xe/0x10
Nov 26 17:36:54 balto kernel: [  839.587345]  [<ffffffff81751202>] system_call_fastpath+0x16/0x1b
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Restore the correct delay value for ondemand's od_dbs_timer, as it was
changed erroneously in commit 83f0e55 (cpufreq: governors: remove
redundant code).
Signed-off-by: NFabio Baltieri <fabio.baltieri@linaro.org>
Reviewed-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Initially ondemand governor was written and then using its code conservative
governor is written. It used a lot of code from ondemand governor, but copy of
code was created instead of using the same routines from both governors. Which
increased code redundancy, which is difficult to manage.

This patch is an attempt to move common part of both the governors to
cpufreq_governor.c file to come over above mentioned issues.

This shouldn't change anything from functionality point of view.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Multiple cpufreq governers have defined similar get_cpu_idle_time_***()
routines. These routines must be moved to some common place, so that all
governors can use them.

So moving them to cpufreq_governor.c, which seems to be a better place for
keeping these routines.
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Reevaluate CPU load and update frequency immediately whenever limits
are changed. Currently ondemand doesn't do that when limits are
relaxed, wasting power on systems with relatively low sampling rate.
Signed-off-by: NMichal Pecio <mpecio@nvidia.com>
Reviewed-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>

Initalizers for deferrable delayed_work are confused.

* __DEFERRED_WORK_INITIALIZER()
* DECLARE_DEFERRED_WORK()
* INIT_DELAYED_WORK_DEFERRABLE()

Rename them to

* __DEFERRABLE_WORK_INITIALIZER()
* DECLARE_DEFERRABLE_WORK()
* INIT_DEFERRABLE_WORK()

This patch doesn't cause any functional changes.
Signed-off-by: NTejun Heo <tj@kernel.org>

When a new sampling rate is shorter than the current one, (e.g., 1 sec
--> 10 ms) regardless how short the new one is, the current ondemand
mechanism wait for the previously set timer to be expired.

For example, if the user has just expressed that the sampling rate
should be 10 ms from now and the previous was 1000 ms, the new rate may
become effective 999 ms later, which could be not acceptable for the
user if the user has intended to speed up sampling because the system is
expected to react to CPU load fluctuation quickly from __now__.

In order to address this issue, we need to cancel the previously set
timer (schedule_delayed_work) and reset the timer if resetting timer is
expected to trigger the delayed_work ealier.
Signed-off-by: NMyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NDave Jones <davej@redhat.com>

Make cputime_t and cputime64_t nocast to enable sparse checking to
detect incorrect use of cputime. Drop the cputime macros for simple
scalar operations. The conversion macros are still needed.
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>

CPUFREQ Remove wall variable from cpufreq_gov_dbs_init()

Remove wall variable from cpufreq_gov_dbs_init() as
get_cpu_idle_time_us() no longer updates the last_update_time
unconditionally. Passing non-NULL last_update_time address
will result in accounting additional idle time with
update_ts_time_stats() before returning idle_sleeptime.
Signed-off-by: NKamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: NDave Jones <davej@redhat.com>
--
 drivers/cpufreq/cpufreq_ondemand.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

This patch changes fields in cpustat from a structure, to an
u64 array. Math gets easier, and the code is more flexible.
Signed-off-by: NGlauber Costa <glommer@parallels.com>
Reviewed-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul Tuner <pjt@google.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322498719-2255-2-git-send-email-glommer@parallels.comSigned-off-by: NIngo Molnar <mingo@elte.hu>

update_ts_time_stat currently updates idle time even if we are in
iowait loop at the moment. The only real users of the idle counter
(via get_cpu_idle_time_us) are CPU governors and they expect to get
cumulative time for both idle and iowait times.
The value (idle_sleeptime) is also printed to userspace by print_cpu
but it prints both idle and iowait times so the idle part is misleading.

Let's clean this up and fix update_ts_time_stat to account both counters
properly and update consumers of idle to consider iowait time as well.
If we do this we might use get_cpu_{idle,iowait}_time_us from other
contexts as well and we will get expected values.
Signed-off-by: NMichal Hocko <mhocko@suse.cz>
Cc: Dave Jones <davej@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Link: http://lkml.kernel.org/r/e9c909c221a8da402c4da07e4cd968c3218f8eb1.1314172057.git.mhocko@suse.czSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

Signed-off-by: NPaul Bolle <pebolle@tiscali.nl>
Acked-by: NLen Brown <len.brown@intel.com>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>

There cannot be any concurrent access to these through
different cpu sysfs files anymore, because these tunables
are now all global (not per cpu).

I still have some doubts whether some of these locks
were needed at all. Anyway, let's get rid of them.
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>
CC: cpufreq@vger.kernel.org

Marked deprecated for quite a whilte now...
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>
CC: cpufreq@vger.kernel.org

Marked deprecated for quite a while now...
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>
CC: cpufreq@vger.kernel.org

calculate ondemand delay after dbs_check_cpu call because it can
modify rate_mult value

use freq_lo_jiffies value for the sub sample period of powersave_bias mode
Signed-off-by: NVincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: NDave Jones <davej@redhat.com>

With cmwq, there's no reason for cpufreq drivers to use separate
workqueues.  Remove the dedicated workqueues from cpufreq_conservative
and cpufreq_ondemand and use system_wq instead.  The work items are
already sync canceled on stop, so it's already guaranteed that no work
is running on module exit.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NDave Jones <davej@redhat.com>
Cc: cpufreq@vger.kernel.org

Adds a new global tunable, sampling_down_factor.  Set to 1 it makes no
changes from existing behavior, but set to greater than 1 (e.g. 100)
it acts as a multiplier for the scheduling interval for reevaluating
load when the CPU is at its top speed due to high load.  This improves
performance by reducing the overhead of load evaluation and helping
the CPU stay at its top speed when truly busy, rather than shifting
back and forth in speed.  This tunable has no effect on behavior at
lower speeds/lower CPU loads.

This patch is against 2.6.36-rc6.

This patch should help solve kernel bug 19672 "ondemand is slow".
Signed-off-by: NDavid Niemi <dniemi@verisign.com>
Acked-by: NVenkatesh Pallipadi <venki@google.com>
CC: Daniel Hollocher <danielhollocher@gmail.com>
CC: <cpufreq-list@vger.kernel.org>
CC: <linux-kernel@vger.kernel.org>
Signed-off-by: NDave Jones <davej@redhat.com>

For UP systems this is not required, and results in a more consistent
sample interval.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NJocelyn Falempe <jocelyn.falempe@motorola.com>
Signed-off-by: NMike Chan <mike@android.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDave Jones <davej@redhat.com>

Make simpler to read and call.

*** v3 - Always call when powersave_bias is enabled.
Acked-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NMike Chan <mike@android.com>
Signed-off-by: NDave Jones <davej@redhat.com>

Pavel Machek pointed out that not all CPUs have an efficient
idle at high frequency. Specifically, older Intel and various
AMD cpus would get a higher powerusage when copying files from
USB.

Mike Chan pointed out that the same is true for various ARM
chips as well.

Thomas Renninger suggested to make this a sysfs tunable with a
reasonable default.

This patch adds a sysfs tunable for the new behavior, and uses
a very simple function to determine a reasonable default,
depending on the CPU vendor/type.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Acked-by: NRik van Riel <riel@redhat.com>
Acked-by: NPavel Machek <pavel@ucw.cz>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082651.46914d04@infradead.org>
[ minor tidyup ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>

The ondemand cpufreq governor uses CPU busy time (e.g. not-idle
time) as a measure for scaling the CPU frequency up or down.
If the CPU is busy, the CPU frequency scales up, if it's idle,
the CPU frequency scales down. Effectively, it uses the CPU busy
time as proxy variable for the more nebulous "how critical is
performance right now" question.

This algorithm falls flat on its face in the light of workloads
where you're alternatingly disk and CPU bound, such as the ever
popular "git grep", but also things like startup of programs and
maildir using email clients... much to the chagarin of Andrew
Morton.

This patch changes the ondemand algorithm to count iowait time
as busy, not idle, time. As shown in the breakdown cases above,
iowait is performance critical often, and by counting iowait,
the proxy variable becomes a more accurate representation of the
"how critical is performance" question.

The problem and fix are both verified with the "perf timechar"
tool.
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NDave Jones <davej@redhat.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100509082606.3d9f00d0@infradead.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Multiple modules used to define those which are with identical
functionality and were needlessly replicated among the different cpufreq
drivers. Push them into the header and remove duplication.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <1270065406-1814-7-git-send-email-bp@amd64.org>
Reviewed-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Dominik said:
target_freq cannot be below policy->min or above policy->max.
If it were, the whole cpufreq subsystem is broken.

But (answer):
I think the "ondemand" governor can ask for a target frequency that is
below policy->min.
...
A patch such as below may be needed to sanitize the target frequency
requested by "ondemand". The "conservative" governor already has this check:
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>

# diff -bur x/drivers/cpufreq/cpufreq_ondemand.c.orig y/drivers/cpufreq/cpufreq_ondemand.c

ondemand and conservative governors are messing up time units in the
code path where NO_HZ is not enabled and ignore_nice is set. The walltime
idletime stored is in jiffies and nice time calculation is happening in
microseconds.

The problem was reported and diagnosed by Alexander here.
http://marc.info/?l=linux-kernel&m=125752550404513&w=2

The patch below fixes this thinko.
Reported-by: NAlexander Miller <Miller@fmi.uni-stuttgart.de>
Tested-by: NAlexander Miller <Miller@fmi.uni-stuttgart.de>
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

Ondemand has only global variables for userspace tunings via sysfs.
But they were exposed per CPU which wrongly implies to the user that
his settings are applied per cpu. Also locking sysfs against concurrent
access won't be necessary anymore after deprecation time.

This means the ondemand config dir is moved:
/sys/devices/system/cpu/cpu*/cpufreq/ondemand ->
     /sys/devices/system/cpu/cpufreq/ondemand

The old files will still exist, but reading or writing to them will
result in one (printk_once) deprecation msg to syslog per file.
Signed-off-by: NThomas Renninger <trenn@suse.de>
Signed-off-by: NDave Jones <davej@redhat.com>

Redesign the locking inside ondemand driver. Make dbs_mutex handle all the
global state changes inside the driver and invent a new percpu mutex
to serialize percpu timer and frequency limit change.
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>

Commit b14893a6 although it was very
much needed to properly cleanup ondemand timer, opened-up a can of worms
related to locking dependencies in cpufreq.

Patch here defines the need for dbs_mutex and cleans up its usage in
ondemand governor. This also resolves the lockdep warnings reported here

http://lkml.indiana.edu/hypermail/linux/kernel/0906.1/01925.html
http://lkml.indiana.edu/hypermail/linux/kernel/0907.0/00820.html

and few others..
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: NDave Jones <davej@redhat.com>