Commit Graph

134 Commits

Author SHA1 Message Date
Viresh Kumar f08f638b9c cpufreq: ondemand: update update_sampling_rate() to make it more efficient
Currently update_sampling_rate() runs over each online CPU and
cancels/queues timers on all policy->cpus every time. This should be
done just once for any cpu belonging to a policy.

Create a cpumask and keep on clearing it as and when we process
policies, so that we don't have to traverse through all CPUs of the same
policy.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-12-09 22:26:12 +01:00
Viresh Kumar 70f43e5e79 cpufreq: governor: replace per-CPU delayed work with timers
cpufreq governors evaluate load at sampling rate and based on that they
update frequency for a group of CPUs belonging to the same cpufreq
policy.

This is required to be done in a single thread for all policy->cpus, but
because we don't want to wakeup idle CPUs to do just that, we use
deferrable work for this. If we would have used a single delayed
deferrable work for the entire policy, there were chances that the CPU
required to run the handler can be in idle and we might end up not
changing the frequency for the entire group with load variations.

And so we were forced to keep per-cpu works, and only the one that
expires first need to do the real work and others are rescheduled for
next sampling time.

We have been using the more complex solution until now, where we used a
delayed deferrable work for this, which is a combination of a timer and
a work.

This could be made lightweight by keeping per-cpu deferred timers with a
single work item, which is scheduled by the first timer that expires.

This patch does just that and here are important changes:
- The timer handler will run in irq context and so we need to use a
  spin_lock instead of the timer_mutex. And so a separate timer_lock is
  created. This also makes the use of the mutex and lock quite clear, as
  we know what exactly they are protecting.
- A new field 'skip_work' is added to track when the timer handlers can
  queue a work. More comments present in code.

Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Ashwin Chaugule <ashwin.chaugule@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-12-09 22:26:00 +01:00
Viresh Kumar affde5d06a cpufreq: governor: Pass policy as argument to ->gov_dbs_timer()
Pass 'policy' as argument to ->gov_dbs_timer() instead of cdbs and
dbs_data.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-12-07 02:20:22 +01:00
Viresh Kumar e68fe18c5b cpufreq: ondemand: Work is guaranteed to be pending
We are guaranteed to have works scheduled for policy->cpus, as the
policy isn't stopped yet. And so there is no need to check that again.
Drop it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-12-07 02:20:21 +01:00
Viresh Kumar e128c86407 cpufreq: ondemand: Update sampling rate only for concerned policies
We are comparing policy->governor against cpufreq_gov_ondemand to make
sure that we update sampling rate only for the concerned CPUs. But that
isn't enough.

In case of governor_per_policy, there can be multiple instances of
ondemand governor and we will always end up updating all of them with
current code. What we rather need to do, is to compare dbs_data with
poilcy->governor_data, which will match only for the policies governed
by dbs_data.

This code is also racy as the governor might be getting stopped at that
time and we may end up scheduling work for a policy, which we have just
disabled.

Fix that by protecting the entire function with &od_dbs_cdata.mutex,
which will prevent against races with policy START/STOP/etc.

After these locks are in place, we can safely get the policy via per-cpu
dbs_info.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-12-07 02:20:10 +01:00
Viresh Kumar 083701b13c cpufreq: ondemand: Drop unnecessary locks from update_sampling_rate()
'timer_mutex' is required to sync work-handlers of policy->cpus.
update_sampling_rate() is just canceling the works and queuing them
again. This isn't protecting anything at all in update_sampling_rate()
and is not gonna be of any use.

Even if a work-handler is already running for a CPU,
cancel_delayed_work_sync() will wait for it to finish.

Drop these unnecessary locks.

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-10-28 09:20:04 +01:00
Viresh Kumar 43e0ee361e cpufreq: governor: split out common part of {cs|od}_dbs_timer()
Some part of cs_dbs_timer() and od_dbs_timer() is exactly same and is
unnecessarily duplicated.

Create the real work-handler in cpufreq_governor.c and put the common
code in this routine (dbs_timer()).

Shouldn't make any functional change.

Reviewed-and-tested-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-07-21 01:12:01 +02:00
Viresh Kumar 44152cb82d cpufreq: governor: Keep single copy of information common to policy->cpus
Some information is common to all CPUs belonging to a policy, but are
kept on per-cpu basis. Lets keep that in another structure common to all
policy->cpus. That will make updates/reads to that less complex and less
error prone.

The memory for cpu_common_dbs_info is allocated/freed at INIT/EXIT, so
that it we don't reallocate it for STOP/START sequence. It will be also
be used (in next patch) while the governor is stopped and so must not be
freed that early.

Reviewed-and-tested-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-07-21 01:12:01 +02:00
Viresh Kumar 42994af63c cpufreq: governor: rename cur_policy as policy
Just call it 'policy', cur_policy is unnecessarily long and doesn't
have any special meaning.

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-07-17 23:46:48 +02:00
Viresh Kumar 386d46e6d5 cpufreq: governor: Name delayed-work as dwork
Delayed work was named as 'work' and to access work within it we do
work.work. Not much readable. Rename delayed_work as 'dwork'.

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-07-17 23:46:47 +02:00
Viresh Kumar 732b6d617a cpufreq: governor: Serialize governor callbacks
There are several races reported in cpufreq core around governors (only
ondemand and conservative) by different people.

There are at least two race scenarios present in governor code:
 (a) Concurrent access/updates of governor internal structures.

 It is possible that fields such as 'dbs_data->usage_count', etc.  are
 accessed simultaneously for different policies using same governor
 structure (i.e. CPUFREQ_HAVE_GOVERNOR_PER_POLICY flag unset). And
 because of this we can dereference bad pointers.

 For example consider a system with two CPUs with separate 'struct
 cpufreq_policy' instances. CPU0 governor: ondemand and CPU1: powersave.
 CPU0 switching to powersave and CPU1 to ondemand:
	CPU0				CPU1

	store*				store*

	cpufreq_governor_exit()		cpufreq_governor_init()
					dbs_data = cdata->gdbs_data;

	if (!--dbs_data->usage_count)
		kfree(dbs_data);

					dbs_data->usage_count++;
					*Bad pointer dereference*

 There are other races possible between EXIT and START/STOP/LIMIT as
 well. Its really complicated.

 (b) Switching governor state in bad sequence:

 For example trying to switch a governor to START state, when the
 governor is in EXIT state. There are some checks present in
 __cpufreq_governor() but they aren't sufficient as they compare events
 against 'policy->governor_enabled', where as we need to take governor's
 state into account, which can be used by multiple policies.

These two issues need to be solved separately and the responsibility
should be properly divided between cpufreq and governor core.

The first problem is more about the governor core, as it needs to
protect its structures properly. And the second problem should be fixed
in cpufreq core instead of governor, as its all about sequence of
events.

This patch is trying to solve only the first problem.

There are two types of data we need to protect,
- 'struct common_dbs_data': No matter what, there is going to be a
  single copy of this per governor.
- 'struct dbs_data': With CPUFREQ_HAVE_GOVERNOR_PER_POLICY flag set, we
  will have per-policy copy of this data, otherwise a single copy.

Because of such complexities, the mutex present in 'struct dbs_data' is
insufficient to solve our problem. For example we need to protect
fetching of 'dbs_data' from different structures at the beginning of
cpufreq_governor_dbs(), to make sure it isn't currently being updated.

This can be fixed if we can guarantee serialization of event parsing
code for an individual governor. This is best solved with a mutex per
governor, and the placeholder for that is 'struct common_dbs_data'.

And so this patch moves the mutex from 'struct dbs_data' to 'struct
common_dbs_data' and takes it at the beginning and drops it at the end
of cpufreq_governor_dbs().

Tested with and without following configuration options:

CONFIG_LOCKDEP_SUPPORT=y
CONFIG_DEBUG_RT_MUTEXES=y
CONFIG_DEBUG_PI_LIST=y
CONFIG_DEBUG_SPINLOCK=y
CONFIG_DEBUG_MUTEXES=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
CONFIG_LOCKDEP=y
CONFIG_DEBUG_ATOMIC_SLEEP=y

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-06-15 15:42:53 +02:00
Viresh Kumar 8e0484d2b3 cpufreq: governor: register notifier from cs_init()
Notifiers are required only for conservative governor and the common
governor code is unnecessarily polluted with that. Handle that from
cs_init/exit() instead of cpufreq_governor_dbs().

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-06-15 15:37:12 +02:00
Stratos Karafotis 6393d6a102 cpufreq: ondemand: Eliminate the deadband effect
Currently, ondemand calculates the target frequency proportional to load
using the formula:
	Target frequency = C * load
	where C = policy->cpuinfo.max_freq / 100

Though, in many cases, the minimum available frequency is pretty high and
the above calculation introduces a dead band from load 0 to
100 * policy->cpuinfo.min_freq / policy->cpuinfo.max_freq where the target
frequency is always calculated to less than policy->cpuinfo.min_freq and
the minimum frequency is selected.

For example: on Intel i7-3770 @ 3.4GHz the policy->cpuinfo.min_freq = 1600000
and the policy->cpuinfo.max_freq = 3400000 (without turbo). Thus, the CPU
starts to scale up at a load above 47.
On quad core 1500MHz Krait the policy->cpuinfo.min_freq = 384000
and the policy->cpuinfo.max_freq = 1512000. Thus, the CPU starts to scale
at load above 25.

Change the calculation of target frequency to eliminate the above effect using
the formula:

	Target frequency = A + B * load
	where A = policy->cpuinfo.min_freq and
	      B = (policy->cpuinfo.max_freq - policy->cpuinfo->min_freq) / 100

This will map load values 0 to 100 linearly to cpuinfo.min_freq to
cpuinfo.max_freq.

Also, use the CPUFREQ_RELATION_C in __cpufreq_driver_target to select the
closest frequency in frequency_table. This is necessary to avoid selection
of minimum frequency only when load equals to 0. It will also help for selection
of frequencies using a more 'fair' criterion.

Tables below show the difference in selected frequency for specific values
of load without and with this patch. On Intel i7-3770 @ 3.40GHz:
	Without			With
Load	Target	Selected	Target	Selected
0	0	1600000		1600000	1600000
5	170050	1600000		1690050	1700000
10	340100	1600000		1780100	1700000
15	510150	1600000		1870150	1900000
20	680200	1600000		1960200	2000000
25	850250	1600000		2050250	2100000
30	1020300	1600000		2140300	2100000
35	1190350	1600000		2230350	2200000
40	1360400	1600000		2320400	2400000
45	1530450	1600000		2410450	2400000
50	1700500	1900000		2500500	2500000
55	1870550	1900000		2590550	2600000
60	2040600	2100000		2680600	2600000
65	2210650	2400000		2770650	2800000
70	2380700	2400000		2860700	2800000
75	2550750	2600000		2950750	3000000
80	2720800	2800000		3040800	3000000
85	2890850	2900000		3130850	3100000
90	3060900	3100000		3220900	3300000
95	3230950	3300000		3310950	3300000
100	3401000	3401000		3401000	3401000

On ARM quad core 1500MHz Krait:
	Without			With
Load	Target	Selected	Target	Selected
0	0	384000		384000	384000
5	75600	384000		440400	486000
10	151200	384000		496800	486000
15	226800	384000		553200	594000
20	302400	384000		609600	594000
25	378000	384000		666000	702000
30	453600	486000		722400	702000
35	529200	594000		778800	810000
40	604800	702000		835200	810000
45	680400	702000		891600	918000
50	756000	810000		948000	918000
55	831600	918000		1004400	1026000
60	907200	918000		1060800	1026000
65	982800	1026000		1117200	1134000
70	1058400	1134000		1173600	1134000
75	1134000	1134000		1230000	1242000
80	1209600	1242000		1286400	1242000
85	1285200	1350000		1342800	1350000
90	1360800	1458000		1399200	1350000
95	1436400	1458000		1455600	1458000
100	1512000	1512000		1512000	1512000

Tested on Intel i7-3770 CPU @ 3.40GHz and on ARM quad core 1500MHz Krait
(Android smartphone).
Benchmarks on Intel i7 shows a performance improvement on low and medium
work loads with lower power consumption. Specifics:

Phoronix Linux Kernel Compilation 3.1:
Time: -0.40%, energy: -0.07%
Phoronix Apache:
Time: -4.98%, energy: -2.35%
Phoronix FFMPEG:
Time: -6.29%, energy: -4.02%

Also, running mp3 decoding (very low load) shows no differences with and
without this patch.

Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-07-21 13:43:19 +02:00
Stratos Karafotis 880eef0416 cpufreq: ondemand: Remove redundant return statement
After commit dfa5bb6225 (cpufreq: ondemand: Change the calculation
of target frequency), this return statement is no longer needed.

Reported-by: Henrik Nilsson <Karl.Henrik.Nilsson@gmail.com>
Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-11-01 00:44:34 +01:00
Stratos Karafotis 934dac1ea0 cpufreq: governors: Remove duplicate check of target freq in supported range
Function __cpufreq_driver_target() checks if target_freq is within
policy->min and policy->max range. generic_powersave_bias_target() also
checks if target_freq is valid via a cpufreq_frequency_table_target()
call. So, drop the unnecessary duplicate check in *_check_cpu().

Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-28 22:03:02 +02:00
Rafael J. Wysocki c49a089c3e Merge back earlier 'pm-cpufreq' material 2013-08-14 22:21:16 +02:00
Viresh Kumar d5b73cd870 cpufreq: Use sizeof(*ptr) convetion for computing sizes
Chapter 14 of Documentation/CodingStyle says:

The preferred form for passing a size of a struct is the following:

	p = kmalloc(sizeof(*p), ...);

The alternative form where struct name is spelled out hurts
readability and introduces an opportunity for a bug when the pointer
variable type is changed but the corresponding sizeof that is passed
to a memory allocator is not.

This wasn't followed consistently in drivers/cpufreq, let's make it
more consistent by always following this rule.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-07 23:34:10 +02:00
Viresh Kumar 3a3e9e06d0 cpufreq: Give consistent names to cpufreq_policy objects
They are called policy, cur_policy, new_policy, data, etc.  Just call
them policy wherever possible.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-07 23:34:10 +02:00
Viresh Kumar 5ff0a26803 cpufreq: Clean up header files included in the core
This patch addresses the following issues in the header files in the
cpufreq core:
 - Include headers in ascending order, so that we don't add same
   many times by mistake.
 - <asm/> must be included after <linux/>, so that they override
   whatever they need to.
 - Remove unnecessary includes.
 - Don't include files already included by cpufreq.h or
   cpufreq_governor.h.

[rjw: Changelog]
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-07 23:34:09 +02:00
Viresh Kumar 6c4640c3ad cpufreq: rename ignore_nice as ignore_nice_load
This sysfs file was called ignore_nice_load earlier and commit
4d5dcc4 (cpufreq: governor: Implement per policy instances of
governors) changed its name to ignore_nice by mistake.

Lets get it renamed back to its original name.

Reported-by: Martin von Gagern <Martin.vGagern@gmx.net>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 3.10+ <stable@vger.kernel.org> # 3.10+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-08-07 22:25:06 +02:00
Stratos Karafotis dfa5bb6225 cpufreq: ondemand: Change the calculation of target frequency
The ondemand governor calculates load in terms of frequency and
increases it only if load_freq is greater than up_threshold
multiplied by the current or average frequency.  This appears to
produce oscillations of frequency between min and max because,
for example, a relatively small load can easily saturate minimum
frequency and lead the CPU to the max.  Then, it will decrease
back to the min due to small load_freq.

Change the calculation method of load and target frequency on the
basis of the following two observations:

 - Load computation should not depend on the current or average
   measured frequency.  For example, absolute load of 80% at 100MHz
   is not necessarily equivalent to 8% at 1000MHz in the next
   sampling interval.

 - It should be possible to increase the target frequency to any
   value present in the frequency table proportional to the absolute
   load, rather than to the max only, so that:

   Target frequency = C * load

   where we take C = policy->cpuinfo.max_freq / 100.

Tested on Intel i7-3770 CPU @ 3.40GHz and on Quad core 1500MHz Krait.
Phoronix benchmark of Linux Kernel Compilation 3.1 test shows an
increase ~1.5% in performance. cpufreq_stats (time_in_state) shows
that middle frequencies are used more, with this patch.  Highest
and lowest frequencies were used less by ~9%.

[rjw: We have run multiple other tests on kernels with this
 change applied and in the vast majority of cases it turns out
 that the resulting performance improvement also leads to reduced
 consumption of energy.  The change is additionally justified by
 the overall simplification of the code in question.]

Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-07-26 01:06:43 +02:00
Jacob Shin c28375583b cpufreq: fix NULL pointer deference at od_set_powersave_bias()
When initializing the default powersave_bias value, we need to first
make sure that this policy is running the ondemand governor.

Reported-and-tested-by: Tim Gardner <tim.gardner@canonical.com>
Signed-off-by: Jacob Shin <jacob.shin@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-06-25 22:42:37 +02:00
Borislav Petkov 60e6726c7b cpufreq, ondemand: Remove leftover debug line
I don't see how the virtual address of the tuners pointer would be of
any help to anyone so remove it.

Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-05-13 14:02:31 +02:00
Jacob Shin fb30809efa cpufreq: ondemand: allow custom powersave_bias_target handler to be registered
This allows for another [arch specific] driver to hook into existing
powersave bias function of the ondemand governor. i.e. This allows AMD
specific powersave bias function (in a separate AMD specific driver)
to aid ondemand governor's frequency transition decisions.

Signed-off-by: Jacob Shin <jacob.shin@amd.com>
Acked-by: Thomas Renninger <trenn@suse.de>
Acked-by: Borislav Petkov <bp@suse.de>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-10 13:19:26 +02:00
Stratos Karafotis 9366d84052 cpufreq: governors: Calculate iowait time only when necessary
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: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.,org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-01 01:11:35 +02:00
Viresh Kumar 031299b3be cpufreq: governors: Avoid unnecessary per cpu timer interrupts
Following patch has introduced per cpu timers or works for ondemand and
conservative governors.

	commit 2abfa876f1
	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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-01 01:11:35 +02:00
Viresh Kumar 9d44592018 cpufreq: ondemand: Don't update sample_type if we don't evaluate load again
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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-01 01:11:34 +02:00
Viresh Kumar 4d5dcc4211 cpufreq: governor: Implement per policy instances of governors
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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-04-01 01:11:34 +02:00
Stratos Karafotis 06eb09d17c cpufreq: ondemand: Fix typos in comments
Fix some typos in comments.

Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-09 12:56:19 +01:00
Stratos Karafotis 4bd4e42819 cpufreq: ondemand: Replace down_differential tuner with adj_up_threshold
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: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-09 01:18:47 +01:00
Viresh Kumar 4447266b84 cpufreq: governors: Remove code redundancy between governors
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: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Fabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-02 01:02:44 +01:00
Fabio Baltieri 09dca5ae75 cpufreq: governors: fix misuse of cdbs.cpu
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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Fabio Baltieri <fabio.baltieri@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-02 00:01:16 +01:00
Fabio Baltieri 2624f90c16 cpufreq: governors: implement generic policy_is_shared
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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Fabio Baltieri <fabio.baltieri@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-02 00:01:16 +01:00
Fabio Baltieri 8ee2ec51d0 cpufreq: ondemand: use all CPUs in update_sampling_rate
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: Fabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-02 00:01:14 +01:00
Fabio Baltieri da53d61e21 cpufreq: ondemand: call dbs_check_cpu only when necessary
Modify ondemand timer to not resample CPU utilization if recently
sampled from another SW coordinated core.

Signed-off-by: Fabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-02 00:01:13 +01:00
Rickard Andersson 2abfa876f1 cpufreq: handle SW coordinated CPUs
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: Rickard Andersson <rickard.andersson@stericsson.com>
Signed-off-by: Fabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2013-02-02 00:01:13 +01:00
Fabio Baltieri 3e33ee9e08 cpufreq: ondemand: update sampling rate only on right CPUs
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: Fabio Baltieri <fabio.baltieri@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2012-11-27 14:11:19 +01:00
Fabio Baltieri d3c31a773f cpufreq: ondemand: fix wrong delay sampling rate
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: Fabio Baltieri <fabio.baltieri@linaro.org>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2012-11-23 20:48:08 +01:00
Viresh Kumar 4471a34f9a cpufreq: governors: remove redundant code
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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2012-11-15 00:33:07 +01:00
viresh kumar 2aacdfff9c cpufreq: Move common part from governors to separate file, v2
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: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2012-11-15 00:33:06 +01:00
Linus Torvalds 16642a2e7b Power management updates for 3.7-rc1
* Improved system suspend/resume and runtime PM handling for the SH TMU, CMT
   and MTU2 clock event devices (also used by ARM/shmobile).
 
 * Generic PM domains framework extensions related to cpuidle support and
   domain objects lookup using names.
 
 * ARM/shmobile power management updates including improved support for the
   SH7372's A4S power domain containing the CPU core.
 
 * cpufreq changes related to AMD CPUs support from Matthew Garrett, Andre
   Przywara and Borislav Petkov.
 
 * cpu0 cpufreq driver from Shawn Guo.
 
 * cpufreq governor fixes related to the relaxing of limit from Michal Pecio.
 
 * OMAP cpufreq updates from Axel Lin and Richard Zhao.
 
 * cpuidle ladder governor fixes related to the disabling of states from
   Carsten Emde and me.
 
 * Runtime PM core updates related to the interactions with the system suspend
   core from Alan Stern and Kevin Hilman.
 
 * Wakeup sources modification allowing more helper functions to be called from
   interrupt context from John Stultz and additional diagnostic code from Todd
   Poynor.
 
 * System suspend error code path fix from Feng Hong.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.18 (GNU/Linux)
 
 iQIcBAABAgAGBQJQa1rRAAoJEKhOf7ml8uNsYZ0P/2RZ71sgLWcUCfr0yHaiZeOd
 2GxEYSZ+9BZJHADgoAK/bHRTv8crm40Y2RkbaWbxPDRNuE4SutbvNTGTlJSAguSD
 yHkU/6AFC7u8Jwq+afsWIdGX7eHd78zPpj6EVtVtjHM903WDwbMU2vUz7tQ+fFa+
 ZZ7eydq9j0ec0OoH3UeNhet7JSOpT5BSLgjmIkHMBgIvTxNVDbkB31QUxnUxocxn
 k6S2wQaUSJJWGMLksRRNrhwLq+cGYwTsaOtG/KzRLH1raUyn33B5pcZr0aqhOkjg
 ClaCks3V8o3vRghSwOPB5aVXzjBKvM3UnSyJNIl+FeCeyWuwSNbkEFdA/e7oPuxG
 UsW6dcHiuVo6Ir4+zhd9+lN+/AcPTChO5b7lbU8qRF4ce04czWlUY/KzJjaM+YOE
 CKGq6eX9AHwFjE+h4+VcCXgmzcioiS8Y/CPz13u8N1y0zzwW+ftjb12K+7lVBEG1
 fhrePKHgLw3kJ9LqGpR+4vVur7C+rCf6WwCReTY2vXXVYJ+SuKWTRI4zAjTPXtHa
 i9dpMRASpF+ScRYBcgwIpv789WuHATFKqdBSinZUKBaxQZ5flJ2qIrfqN5VeAejh
 oQs/zZCdIuAtFKqVycQ0L42YxFNKgPFKQErUCSu3M5OuZLlLVLu7yQvIo2Xmo9qf
 Hcrpvo5K+w29YkiwGP9e
 =rbCk
 -----END PGP SIGNATURE-----

Merge tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael J Wysocki:

 - Improved system suspend/resume and runtime PM handling for the SH
   TMU, CMT and MTU2 clock event devices (also used by ARM/shmobile).

 - Generic PM domains framework extensions related to cpuidle support
   and domain objects lookup using names.

 - ARM/shmobile power management updates including improved support for
   the SH7372's A4S power domain containing the CPU core.

 - cpufreq changes related to AMD CPUs support from Matthew Garrett,
   Andre Przywara and Borislav Petkov.

 - cpu0 cpufreq driver from Shawn Guo.

 - cpufreq governor fixes related to the relaxing of limit from Michal
   Pecio.

 - OMAP cpufreq updates from Axel Lin and Richard Zhao.

 - cpuidle ladder governor fixes related to the disabling of states from
   Carsten Emde and me.

 - Runtime PM core updates related to the interactions with the system
   suspend core from Alan Stern and Kevin Hilman.

 - Wakeup sources modification allowing more helper functions to be
   called from interrupt context from John Stultz and additional
   diagnostic code from Todd Poynor.

 - System suspend error code path fix from Feng Hong.

Fixed up conflicts in cpufreq/powernow-k8 that stemmed from the
workqueue fixes conflicting fairly badly with the removal of support for
hardware P-state chips.  The changes were independent but somewhat
intertwined.

* tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (76 commits)
  Revert "PM QoS: Use spinlock in the per-device PM QoS constraints code"
  PM / Runtime: let rpm_resume() succeed if RPM_ACTIVE, even when disabled, v2
  cpuidle: rename function name "__cpuidle_register_driver", v2
  cpufreq: OMAP: Check IS_ERR() instead of NULL for omap_device_get_by_hwmod_name
  cpuidle: remove some empty lines
  PM: Prevent runtime suspend during system resume
  PM QoS: Use spinlock in the per-device PM QoS constraints code
  PM / Sleep: use resume event when call dpm_resume_early
  cpuidle / ACPI : move cpuidle_device field out of the acpi_processor_power structure
  ACPI / processor: remove pointless variable initialization
  ACPI / processor: remove unused function parameter
  cpufreq: OMAP: remove loops_per_jiffy recalculate for smp
  sections: fix section conflicts in drivers/cpufreq
  cpufreq: conservative: update frequency when limits are relaxed
  cpufreq / ondemand: update frequency when limits are relaxed
  properly __init-annotate pm_sysrq_init()
  cpufreq: Add a generic cpufreq-cpu0 driver
  PM / OPP: Initialize OPP table from device tree
  ARM: add cpufreq transiton notifier to adjust loops_per_jiffy for smp
  cpufreq: Remove support for hardware P-state chips from powernow-k8
  ...
2012-10-02 18:32:35 -07:00
Michal Pecio f26365179d cpufreq / ondemand: update frequency when limits are relaxed
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: Michal Pecio <mpecio@nvidia.com>
Reviewed-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
2012-09-14 21:07:39 +02:00
Tejun Heo 203b42f731 workqueue: make deferrable delayed_work initializer names consistent
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: Tejun Heo <tj@kernel.org>
2012-08-21 13:18:23 -07:00
MyungJoo Ham fd0ef7a058 [CPUFREQ] CPUfreq ondemand: update sampling rate without waiting for next sampling
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: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Dave Jones <davej@redhat.com>
2012-02-29 22:24:40 -05:00
Linus Torvalds 02d929502c Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq: (23 commits)
  [CPUFREQ] EXYNOS: Removed useless headers and codes
  [CPUFREQ] EXYNOS: Make EXYNOS common cpufreq driver
  [CPUFREQ] powernow-k8: Update copyright, maintainer and documentation information
  [CPUFREQ] powernow-k8: Fix indexing issue
  [CPUFREQ] powernow-k8: Avoid Pstate MSR accesses on systems supporting CPB
  [CPUFREQ] update lpj only if frequency has changed
  [CPUFREQ] cpufreq:userspace: fix cpu_cur_freq updation
  [CPUFREQ] Remove wall variable from cpufreq_gov_dbs_init()
  [CPUFREQ] EXYNOS4210: cpufreq code is changed for stable working
  [CPUFREQ] EXYNOS4210: Update frequency table for cpu divider
  [CPUFREQ] EXYNOS4210: Remove code about bus on cpufreq
  [CPUFREQ] s3c64xx: Use pr_fmt() for consistent log messages
  cpufreq: OMAP: fixup for omap_device changes, include <linux/module.h>
  cpufreq: OMAP: fix freq_table leak
  cpufreq: OMAP: put clk if cpu_init failed
  cpufreq: OMAP: only supports OPP library
  cpufreq: OMAP: dont support !freq_table
  cpufreq: OMAP: deny initialization if no mpudev
  cpufreq: OMAP: move clk name decision to init
  cpufreq: OMAP: notify even with bad boot frequency
  ...
2012-01-11 18:53:33 -08:00
Martin Schwidefsky 612ef28a04 Merge branch 'sched/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into cputime-tip
Conflicts:
	drivers/cpufreq/cpufreq_conservative.c
	drivers/cpufreq/cpufreq_ondemand.c
	drivers/macintosh/rack-meter.c
	fs/proc/stat.c
	fs/proc/uptime.c
	kernel/sched/core.c
2011-12-19 19:23:15 +01:00
Martin Schwidefsky 648616343c [S390] cputime: add sparse checking and cleanup
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: Martin Schwidefsky <schwidefsky@de.ibm.com>
2011-12-15 14:56:19 +01:00
Kamalesh Babulal 21f2e3c86b [CPUFREQ] Remove wall variable from cpufreq_gov_dbs_init()
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: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: Dave Jones <davej@redhat.com>
--
 drivers/cpufreq/cpufreq_ondemand.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)
2011-12-09 10:40:23 -05:00
Glauber Costa 3292beb340 sched/accounting: Change cpustat fields to an array
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: Glauber Costa <glommer@parallels.com>
Reviewed-by: KAMEZAWA 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: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322498719-2255-2-git-send-email-glommer@parallels.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-12-06 09:06:38 +01:00
Linus Torvalds 39adff5f69 Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  time, s390: Get rid of compile warning
  dw_apb_timer: constify clocksource name
  time: Cleanup old CONFIG_GENERIC_TIME references that snuck in
  time: Change jiffies_to_clock_t() argument type to unsigned long
  alarmtimers: Fix error handling
  clocksource: Make watchdog reset lockless
  posix-cpu-timers: Cure SMP accounting oddities
  s390: Use direct ktime path for s390 clockevent device
  clockevents: Add direct ktime programming function
  clockevents: Make minimum delay adjustments configurable
  nohz: Remove "Switched to NOHz mode" debugging messages
  proc: Consider NO_HZ when printing idle and iowait times
  nohz: Make idle/iowait counter update conditional
  nohz: Fix update_ts_time_stat idle accounting
  cputime: Clean up cputime_to_usecs and usecs_to_cputime macros
  alarmtimers: Rework RTC device selection using class interface
  alarmtimers: Add try_to_cancel functionality
  alarmtimers: Add more refined alarm state tracking
  alarmtimers: Remove period from alarm structure
  alarmtimers: Remove interval cap limit hack
  ...
2011-10-26 17:15:03 +02:00