| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
If the policy limits change between invocations of cs_dbs_update(),
the requested frequency value stored in dbs_info may not be updated
and the function may use a stale value of it next time. Moreover, if
idle periods are takem into account by cs_dbs_update(), the requested
frequency value stored in dbs_info may be below the min policy limit,
which is incorrect.
To fix these problems, always update the requested frequency value
in dbs_info along with the local copy of it when the previous
requested frequency is beyond the policy limits and avoid decreasing
the requested frequency below the min policy limit when taking
idle periods into account.
Fixes: abb6627910a1 (cpufreq: conservative: Fix next frequency selection)
Fixes: 00bfe05889e9 (cpufreq: conservative: Decrease frequency faster for deferred updates)
Reported-by: Waldemar Rymarkiewicz <waldemarx.rymarkiewicz@intel.com>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Waldemar Rymarkiewicz <waldemarx.rymarkiewicz@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The cpufreq core and governors aren't supposed to set a limit on how
fast we want to try changing the frequency. This is currently done for
the legacy governors with help of min_sampling_rate.
At worst, we may end up setting the sampling rate to a value lower than
the rate at which frequency can be changed and then one of the CPUs in
the policy will be only changing frequency for ever.
But that is something for the user to decide and there is no need to
have special handling for such cases in the core. Leave it for the user
to figure out.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Commit 27ed3cd2ebf4 (cpufreq: conservative: Fix the logic in frequency
decrease checking) removed the 10 point substraction when comparing the
load against down_threshold but did not remove the related limit for the
down_threshold value. As a result, down_threshold lower than 11 is not
allowed even though values from 1 to 10 do work correctly too. The
comment ("cannot be lower than 11 otherwise freq will not fall") also
does not apply after removing the substraction.
For this reason, allow down_threshold to take any value from 1 to 99
and fix the related comment.
Fixes: 27ed3cd2ebf4 (cpufreq: conservative: Fix the logic in frequency decrease checking)
Signed-off-by: Tomasz Wilczyński <twilczynski@naver.com>
Acked-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>
|
| |
|
|
|
|
|
|
|
| |
The original comment about the frequency increase to maximum is wrong.
Both increase and decrease happen at steps.
Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Conservative governor changes the CPU frequency in steps.
That means that if a CPU runs at max frequency, it will need several
sampling periods to return to min frequency when the workload
is finished.
If the update function that calculates the load and target frequency
is deferred, the governor might need even more time to decrease the
frequency.
This may have impact to power consumption and after all conservative
should decrease the frequency if there is no workload at every sampling
rate.
To resolve the above issue calculate the number of sampling periods
that the update is deferred. Considering that for each sampling period
conservative should drop the frequency by a freq_step because the
CPU was idle apply the proper subtraction to requested frequency.
Below, the kernel trace with and without this patch. First an
intensive workload is applied on a specific CPU. Then the workload
is removed and the CPU goes to idle.
WITHOUT
<idle>-0 [007] dN.. 620.329153: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 620.350857: cpu_frequency: state=1700000 cpu_id=7
kworker/7:2-556 [007] .... 620.370856: cpu_frequency: state=1900000 cpu_id=7
kworker/7:2-556 [007] .... 620.390854: cpu_frequency: state=2100000 cpu_id=7
kworker/7:2-556 [007] .... 620.411853: cpu_frequency: state=2200000 cpu_id=7
kworker/7:2-556 [007] .... 620.432854: cpu_frequency: state=2400000 cpu_id=7
kworker/7:2-556 [007] .... 620.453854: cpu_frequency: state=2600000 cpu_id=7
kworker/7:2-556 [007] .... 620.494856: cpu_frequency: state=2900000 cpu_id=7
kworker/7:2-556 [007] .... 620.515856: cpu_frequency: state=3100000 cpu_id=7
kworker/7:2-556 [007] .... 620.536858: cpu_frequency: state=3300000 cpu_id=7
kworker/7:2-556 [007] .... 620.557857: cpu_frequency: state=3401000 cpu_id=7
<idle>-0 [007] d... 669.591363: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 669.591939: cpu_idle: state=4294967295 cpu_id=7
<idle>-0 [007] d... 669.591980: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] dN.. 669.591989: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 670.201224: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 670.221975: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 670.222016: cpu_frequency: state=3300000 cpu_id=7
<idle>-0 [007] d... 670.222026: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 670.234964: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 670.801251: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 671.236046: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 671.236073: cpu_frequency: state=3100000 cpu_id=7
<idle>-0 [007] d... 671.236112: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 671.393437: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 671.401277: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 671.404083: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 671.404111: cpu_frequency: state=2900000 cpu_id=7
<idle>-0 [007] d... 671.404125: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 671.404974: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 671.501180: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 671.995414: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 671.995459: cpu_frequency: state=2800000 cpu_id=7
<idle>-0 [007] d... 671.995469: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 671.996287: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 672.001305: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.078374: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 672.078410: cpu_frequency: state=2600000 cpu_id=7
<idle>-0 [007] d... 672.078419: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.158020: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 672.158040: cpu_frequency: state=2400000 cpu_id=7
<idle>-0 [007] d... 672.158044: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.160038: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 672.234557: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.237121: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 672.237174: cpu_frequency: state=2100000 cpu_id=7
<idle>-0 [007] d... 672.237186: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.237778: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 672.267902: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.269860: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 672.269906: cpu_frequency: state=1900000 cpu_id=7
<idle>-0 [007] d... 672.269914: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.271902: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 672.751342: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 672.823056: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-556 [007] .... 672.823095: cpu_frequency: state=1600000 cpu_id=7
WITH
<idle>-0 [007] dN.. 4380.928009: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-399 [007] .... 4380.949767: cpu_frequency: state=2000000 cpu_id=7
kworker/7:2-399 [007] .... 4380.969765: cpu_frequency: state=2200000 cpu_id=7
kworker/7:2-399 [007] .... 4381.009766: cpu_frequency: state=2500000 cpu_id=7
kworker/7:2-399 [007] .... 4381.029767: cpu_frequency: state=2600000 cpu_id=7
kworker/7:2-399 [007] .... 4381.049769: cpu_frequency: state=2800000 cpu_id=7
kworker/7:2-399 [007] .... 4381.069769: cpu_frequency: state=3000000 cpu_id=7
kworker/7:2-399 [007] .... 4381.089771: cpu_frequency: state=3100000 cpu_id=7
kworker/7:2-399 [007] .... 4381.109772: cpu_frequency: state=3400000 cpu_id=7
kworker/7:2-399 [007] .... 4381.129773: cpu_frequency: state=3401000 cpu_id=7
<idle>-0 [007] d... 4428.226159: cpu_idle: state=1 cpu_id=7
<idle>-0 [007] d... 4428.226176: cpu_idle: state=4294967295 cpu_id=7
<idle>-0 [007] d... 4428.226181: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 4428.227177: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 4428.551640: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 4428.649239: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-399 [007] .... 4428.649268: cpu_frequency: state=2800000 cpu_id=7
<idle>-0 [007] d... 4428.649278: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 4428.689856: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 4428.799542: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 4428.801683: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-399 [007] .... 4428.801748: cpu_frequency: state=1700000 cpu_id=7
<idle>-0 [007] d... 4428.801761: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 4428.806545: cpu_idle: state=4294967295 cpu_id=7
...
<idle>-0 [007] d... 4429.051880: cpu_idle: state=4 cpu_id=7
<idle>-0 [007] d... 4429.086240: cpu_idle: state=4294967295 cpu_id=7
kworker/7:2-399 [007] .... 4429.086293: cpu_frequency: state=1600000 cpu_id=7
Without the patch the CPU dropped to min frequency after 3.2s
With the patch applied the CPU dropped to min frequency after 0.86s
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>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
What's returned from this function is the delta by which the frequency
must be increased or decreased and not the final frequency that should
be selected.
Name it properly to match its purpose. Also update the variables used to
store that value.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
| |
The earlier implementation of governors used background timers and so
functions, mutex, etc had 'timer' keyword in their names.
But that's not true anymore. Replace 'timer' with 'update', as those
functions, variables are based around updates to frequency.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Commit d352cf47d93e (cpufreq: conservative: Do not use transition
notifications) overlooked the case when the "frequency step" used
by the conservative governor is small relative to the distances
between the available frequencies and broke the algorithm by
using policy->cur instead of the previously requested frequency
when computing the next one.
As a result, the governor may not be able to go outside of a narrow
range between two consecutive available frequencies.
Fix the problem by making the governor save the previously requested
frequency and select the next one relative that value (unless it is
out of range, in which case policy->cur will be used instead).
Fixes: d352cf47d93e (cpufreq: conservative: Do not use transition notifications)
Link: https://bugzilla.kernel.org/show_bug.cgi?id=177171
Reported-and-tested-by: Aleksey Rybalkin <aleksey@rybalkin.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 4.8+ <stable@vger.kernel.org> # 4.8+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The conservative governor registers a transition notifier so it
can update its internal requested_freq value if it falls out of the
policy->min...policy->max range, but requested_freq is not really
necessary.
That value is used to track the frequency requested by the governor
previously, but policy->cur can be used instead of it and then the
governor will not have to worry about updating the tracked value when
the current frequency changes independently (for example, as a result
of min or max changes).
Accodringly, drop requested_freq from struct cs_policy_dbs_info
and modify cs_dbs_timer() to use policy->cur instead of it.
While at it, notice that __cpufreq_driver_target() clamps its
target_freq argument between policy->min and policy->max, so
the callers of it don't have to do that and make additional
changes in cs_dbs_timer() in accordance with that.
After these changes the transition notifier used by the conservative
governor is not necessary any more, so drop it, which also makes it
possible to drop the struct cs_governor definition and simplify the
code accordingly.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The 'initialized' field in struct cpufreq_governor is only used by
the conservative governor (as a usage counter) and the way that
happens is far from straightforward and arguably incorrect.
Namely, the value of 'initialized' is checked by
cpufreq_dbs_governor_init() and cpufreq_dbs_governor_exit() and
the results of those checks are passed (as the second argument) to
the ->init() and ->exit() callbacks in struct dbs_governor. Those
callbacks are only implemented by the ondemand and conservative
governors and ondemand doesn't use their second argument at all.
In turn, the conservative governor uses it to decide whether or not
to either register or unregister a transition notifier.
That whole mechanism is not only unnecessarily convoluted, but also
racy, because the 'initialized' field of struct cpufreq_governor is
updated in cpufreq_init_governor() and cpufreq_exit_governor() under
policy->rwsem which doesn't help if one of these functions is run
twice in parallel for different policies (which isn't impossible in
principle), for example.
Instead of it, add a proper usage counter to the conservative
governor and update it from cs_init() and cs_exit() which is
guaranteed to be non-racy, as those functions are only called
under gov_dbs_data_mutex which is global.
With that in place, drop the 'initialized' field from struct
cpufreq_governor as it is not used any more.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
| |
These aren't required anymore as the allocation core already prints such
messages. Remove the redundant ones.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The design of the cpufreq governor API is not very straightforward,
as struct cpufreq_governor provides only one callback to be invoked
from different code paths for different purposes. The purpose it is
invoked for is determined by its second "event" argument, causing it
to act as a "callback multiplexer" of sorts.
Unfortunately, that leads to extra complexity in governors, some of
which implement the ->governor() callback as a switch statement
that simply checks the event argument and invokes a separate function
to handle that specific event.
That extra complexity can be eliminated by replacing the all-purpose
->governor() callback with a family of callbacks to carry out specific
governor operations: initialization and exit, start and stop and policy
limits updates. That also turns out to reduce the code size too, so
do it.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
In addition to fields representing governor tunables, struct dbs_data
contains some fields needed for the management of objects of that
type. As it turns out, that part of struct dbs_data may be shared
with (future) governors that won't use the common code used by
"ondemand" and "conservative", so move it to a separate struct type
and modify the code using struct dbs_data to follow.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Move the definitions of struct od_dbs_tuners and struct cs_dbs_tuners
from the common governor header to the ondemand and conservative
governor code, respectively, as they don't need to be in the common
header any more.
No functional changes.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
After previous changes there is only one piece of code in the
ondemand governor making references to per-CPU data structures,
but it can be easily modified to avoid doing that, so modify it
accordingly and move the definition of per-CPU data used by the
ondemand and conservative governors to the common code. Next,
change that code to access the per-CPU data structures directly
rather than via a governor callback.
This causes the ->get_cpu_cdbs governor callback to become
unnecessary, so drop it along with the macro and function
definitions related to it.
Finally, drop the definitions of struct od_cpu_dbs_info_s and
struct cs_cpu_dbs_info_s that aren't necessary any more.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Some fields in struct od_cpu_dbs_info_s and struct cs_cpu_dbs_info_s
are only used for a limited set of CPUs. Namely, if a policy is
shared between multiple CPUs, those fields will only be used for one
of them (policy->cpu). This means that they really are per-policy
rather than per-CPU and holding room for them in per-CPU data
structures is generally wasteful. Also moving those fields into
per-policy data structures will allow some significant simplifications
to be made going forward.
For this reason, introduce struct cs_policy_dbs_info and
struct od_policy_dbs_info to hold those fields. Define each of the
new structures as an extension of struct policy_dbs_info (such that
struct policy_dbs_info is embedded in each of them) and introduce
new ->alloc and ->free governor callbacks to allocate and free
those structures, respectively, such that ->alloc() will return
a pointer to the struct policy_dbs_info embedded in the allocated
data structure and ->free() will take that pointer as its argument.
With that, modify the code accessing the data fields in question
in per-CPU data objects to look for them in the new structures
via the struct policy_dbs_info pointer available to it and drop
them from struct od_cpu_dbs_info_s and struct cs_cpu_dbs_info_s.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The ->store() callbacks of some tunable sysfs attributes of the
ondemand and conservative governors trigger immediate updates of
the CPU load information for all CPUs "governed" by the given
dbs_data by walking the cpu_dbs_info structures for all online
CPUs in the system and updating them.
This is questionable for two reasons. First, it may lead to a lot of
extra overhead on a system with many CPUs if the given dbs_data is
only associated with a few of them. Second, if governor tunables are
per-policy, the CPUs associated with the other sets of governor
tunables should not be updated.
To address this issue, use the observation that in all of the places
in question the update operation may be carried out in the same way
(because all of the tunables involved are now located in struct
dbs_data and readily available to the common code) and make the
code in those places invoke the same (new) helper function that
will carry out the update correctly.
That new function always checks the ignore_nice_load tunable value
and updates the CPUs' prev_cpu_nice data fields if that's set, which
wasn't done by the original code in store_io_is_busy(), but it
should have been done in there too.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
After some previous changes, the ->get_cpu_dbs_info_s governor
callback and the "governor" field in struct dbs_governor (whose
value represents the governor type) are not used any more, so
drop them.
Also drop the unused gov_ops field from struct dbs_governor.
No functional changes.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
| |
To avoid having to check the governor type explicitly in the common
code in order to initialize data structures specific to the governor
type properly, add a ->start callback to struct dbs_governor and
use it to initialize those data structures for the ondemand and
conservative governors.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
| |
Do not convert microseconds to jiffies and the other way around
in governor computations related to the sampling rate and sample
delay and drop delay_for_sampling_rate() which isn't of any use
then.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The way the ->gov_check_cpu governor callback is used by the ondemand
and conservative governors is not really straightforward. Namely, the
governor calls dbs_check_cpu() that updates the load information for
the policy and the invokes ->gov_check_cpu() for the governor.
To get rid of that entanglement, notice that cpufreq_governor_limits()
doesn't need to call dbs_check_cpu() directly. Instead, it can simply
reset the sample delay to 0 which will cause a sample to be taken
immediately. The result of that is practically equivalent to calling
dbs_check_cpu() except that it will trigger a full update of governor
internal state and not just the ->gov_check_cpu() part.
Following that observation, make cpufreq_governor_limits() reset
the sample delay and turn dbs_check_cpu() into a function that will
simply evaluate the load and return the result called dbs_update().
That function can now be called by governors from the routines that
previously were pointed to by ->gov_check_cpu and those routines
can be called directly by each governor instead of dbs_check_cpu().
This way ->gov_check_cpu becomes unnecessary, so drop it.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The ondemand governor already updates sample_delay_ns immediately on
updates to the sampling rate, but conservative doesn't do that.
It was left out earlier as the code was really too complex to get
that done easily. Things are sorted out very well now, however, and
the conservative governor can be modified to follow ondemand in that
respect.
Moreover, since the code needed to implement that in the
conservative governor would be identical to the corresponding
ondemand governor's code, make that code common and change both
governors to use it.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Juri Lelli <juri.lelli@arm.com>
Tested-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The ondemand and conservative governors use the global-attr or freq-attr
structures to represent sysfs attributes corresponding to their tunables
(which of them is actually used depends on whether or not different
policy objects can use the same governor with different tunables at the
same time and, consequently, on where those attributes are located in
sysfs).
Unfortunately, in the freq-attr case, the standard cpufreq show/store
sysfs attribute callbacks are applied to the governor tunable attributes
and they always acquire the policy->rwsem lock before carrying out the
operation. That may lead to an ABBA deadlock if governor tunable
attributes are removed under policy->rwsem while one of them is being
accessed concurrently (if sysfs attributes removal wins the race, it
will wait for the access to complete with policy->rwsem held while the
attribute callback will block on policy->rwsem indefinitely).
We attempted to address this issue by dropping policy->rwsem around
governor tunable attributes removal (that is, around invocations of the
->governor callback with the event arg equal to CPUFREQ_GOV_POLICY_EXIT)
in cpufreq_set_policy(), but that opened up race conditions that had not
been possible with policy->rwsem held all the time. Therefore
policy->rwsem cannot be dropped in cpufreq_set_policy() at any point,
but the deadlock situation described above must be avoided too.
To that end, use the observation that in principle governor tunables may
be represented by the same data type regardless of whether the governor
is system-wide or per-policy and introduce a new structure, struct
governor_attr, for representing them and new corresponding macros for
creating show/store sysfs callbacks for them. Also make their parent
kobject use a new kobject type whose default show/store callbacks are
not related to the standard core cpufreq ones in any way (and they don't
acquire policy->rwsem in particular).
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Juri Lelli <juri.lelli@arm.com>
Tested-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
[ rjw: Subject & changelog + rebase ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
There are a few common tunables shared between the ondemand and
conservative governors. Move them to struct dbs_data to simplify
code.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Juri Lelli <juri.lelli@arm.com>
Tested-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Some tunables are present in governor-specific structures, whereas one
(min_sampling_rate) is located directly in struct dbs_data.
There is a special macro for creating its sysfs attribute and the
show/store callbacks, but since more tunables are going to be moved
to struct dbs_data, a new generic macro for such cases will be useful,
so add it and use it for min_sampling_rate.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Juri Lelli <juri.lelli@arm.com>
Tested-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
[ rjw: Subject & changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The struct policy_dbs_info objects representing per-policy governor
data are not accessible directly from the corresponding policy
objects. To access them, one has to get a pointer to the
struct cpu_dbs_info of policy->cpu and use the policy_dbs field of
that which isn't really straightforward.
To address that rearrange the governor data structures so the
governor_data pointer in struct cpufreq_policy will point to
struct policy_dbs_info (instead of struct dbs_data) and that will
contain a pointer to struct dbs_data.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
| |
Since policy->cpu is always passed as the second argument to
dbs_check_cpu(), it is not really necessary to pass it, because
the function can obtain that value via its first argument just fine.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
The struct cpu_common_dbs_info structure represents the per-policy
part of the governor data (for the ondemand and conservative
governors), but its name doesn't reflect its purpose.
Rename it to struct policy_dbs_info and rename variables related to
it accordingly.
No functional changes.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Since it is possible to obtain a pointer to struct dbs_governor
from a pointer to the struct governor embedded in it with the help
of container_of(), the additional gov pointer in struct dbs_data
isn't really necessary.
Drop that pointer and make the code using it reach the dbs_governor
object via policy->governor.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Since it is possible to obtain a pointer to struct dbs_governor
from a pointer to the struct governor embedded in it via
container_of(), the second argument of cpufreq_governor_init()
is not necessary. Accordingly, cpufreq_governor_dbs() doesn't
need its second argument either and the ->governor callbacks
for both the ondemand and conservative governors may be set
to cpufreq_governor_dbs() directly. Make that happen.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Saravana Kannan <skannan@codeaurora.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
The ondemand and conservative governors are represented by
struct common_dbs_data whose name doesn't reflect the purpose it
is used for, so rename it to struct dbs_governor and rename
variables of that type accordingly.
No functional changes.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
For the ondemand and conservative governors (generally, governors
that use the common code in cpufreq_governor.c), there are two static
data structures representing the governor, the struct governor
structure (the interface to the cpufreq core) and the struct
common_dbs_data one (the interface to the cpufreq_governor.c code).
There's no fundamental reason why those two structures have to be
separate. Moreover, if the struct governor one is included into
struct common_dbs_data, it will be possible to reach the latter from
the policy via its policy->governor pointer, so it won't be necessary
to pass a separate pointer to it around. For this reason, embed
struct governor in struct common_dbs_data.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Saravana Kannan <skannan@codeaurora.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Every governor relying on the common code in cpufreq_governor.c
has to provide its own mutex in struct common_dbs_data. However,
there actually is no need to have a separate mutex per governor
for this purpose, they may be using the same global mutex just
fine. Accordingly, introduce a single common mutex for that and
drop the mutex field from struct common_dbs_data.
That at least will ensure that the mutex is always present and
initialized regardless of what the particular governors do.
Another benefit is that the common code does not need a pointer to
a governor-related structure to get to the mutex which sometimes
helps.
Finally, it makes the code generally easier to follow.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Saravana Kannan <skannan@codeaurora.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Instead of using a per-CPU deferrable timer for queuing up governor
work items, register a utilization update callback that will be
invoked from the scheduler on utilization changes.
The sampling rate is still the same as what was used for the
deferrable timers and the added irq_work overhead should be offset by
the eliminated timers overhead, so in theory the functional impact of
this patch should not be significant.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
|
| |
|
|
|
|
|
|
|
|
|
| |
The preprocessor magic used for setting the default cpufreq governor
(and for using the performance governor as a fallback one for that
matter) is really nasty, so replace it with __weak functions and
overrides.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Saravana Kannan <skannan@codeaurora.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
|
| |
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Conservative governor has its own 'enable' field to check if
conservative governor is used for a CPU or not
This can be checked by policy->governor with 'cpufreq_gov_conservative'
and so this field can be dropped.
Because its not guaranteed that dbs_info->cdbs.shared will a valid
pointer for all CPUs (will be NULL for CPUs that don't use
ondemand/conservative governors), we can't use it anymore. Lets get
policy with cpufreq_cpu_get_raw() instead.
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
|
| |
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>
|
| |
|
|
|
|
|
|
|
|
|
| |
policy max
When requested_freq is over policy->max, set it to policy->max.
This can help to speed up decreasing frequency.
Signed-off-by: Xiaoguang Chen <chenxg@marvell.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When decreasing frequency, requested_freq may be less than
freq_target, So requested_freq minus freq_target may be negative,
But reqested_freq's unit is unsigned int, then the negative result
will be one larger interger which may be even higher than
requested_freq.
This patch is to fix such issue. when result becomes negative,
set requested_freq as the min value of policy.
Signed-off-by: Xiaoguang Chen <chenxg@marvell.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
| |
|
|
|
|
|
|
|
|
|
| |
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>
|
| |\ |
|
| | |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
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>
|
| | |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
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>
|
| |/
|
|
|
|
|
|
|
|
|
|
|
| |
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>
|
