Right now, guest current governors have the following ratings:
* ladder -> 10
* teo -> 19
* menu -> 20
* haltpoll -> 21
* ladder + nohz=off -> 25
haltpoll governor got introduced and it is now the default governor given
its highest rating -- with ladder+nohz being the exception -- regardless of
idle driver in the guest. An example of an undesirable case is x86 KVM
guests with MWAIT which have intel_idle registered first, and consequently
will have haltpoll be used as governor which would get limited to a poll
state and state 1 and the other states wouldn't get used.
To keep the previous defaults we decrease rating of governor to 9 (below
current lowest rating) and thus rely on @governor switch on
cpuidle_register_driver() to tie in haltpoll idle driver and governor
together.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Notice that setting measured_us to UINT_MAX in teo_update() earlier
doesn't change the behavior of the following code, so do that and
eliminate a redundant check used for setting measured_us to UINT_MAX.
This change is not expected to alter functionality.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The TEO goveror prevents the scheduler tick from being stopped (unless
stopped already) if there is a PM QoS latency constraint for the given
CPU and the target residency of the deepest idle state matching that
constraint is below the tick boundary.
However, that is problematic if CPUs with PM QoS latency constraints
are idle for long times, because it effectively causes the tick to
run on them all the time which is wasteful. [It is also confusing
and questionable if they are full dynticks CPUs.]
To address that issue, modify the TEO governor to carry out the
entire search for the most suitable idle state (from the target
residency perspective) even if a latency constraint is present,
to allow it to determine the expected idle duration in all cases.
Also, when using the last several measured idle duration values
to refine the idle state selection, make it compare those values
with the current expected idle duration value (instead of
comparing them with the target residency of the idle state
selected so far) which should prevent the tick from being
retained when it makes sense to stop it sometimes (especially
in the presence of PM QoS latency constraints).
Fixes: b26bf6ab71 ("cpuidle: New timer events oriented governor for tickless systems")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
After commit 554c8aa8ec ("sched: idle: Select idle state before
stopping the tick") the menu governor prevents the scheduler tick from
being stopped (unless stopped already) if there is a PM QoS latency
constraint for the given CPU and the target residency of the deepest
idle state matching that constraint is below the tick boundary.
However, that is problematic if CPUs with PM QoS latency constraints
are idle for long times, because it effectively causes the tick to
run on them all the time which is wasteful. [It is also confusing
and questionable if they are full dynticks CPUs.]
To address that issue, make the menu governor allow the tick to be
stopped only if the idle duration predicted by it is beyond the tick
boundary, except when the shallowest idle state is selected upfront
and it is not a "polling" one.
Fixes: 554c8aa8ec ("sched: idle: Select idle state before stopping the tick")
Link: https://lore.kernel.org/lkml/79b247b3-e056-610e-9a07-e685dfdaa6c9@gmail.com/
Reported-by: Thomas Lindroth <thomas.lindroth@gmail.com>
Tested-by: Thomas Lindroth <thomas.lindroth@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The cpuidle_haltpoll governor, in conjunction with the haltpoll cpuidle
driver, allows guest vcpus to poll for a specified amount of time before
halting.
This provides the following benefits to host side polling:
1) The POLL flag is set while polling is performed, which allows
a remote vCPU to avoid sending an IPI (and the associated
cost of handling the IPI) when performing a wakeup.
2) The VM-exit cost can be avoided.
The downside of guest side polling is that polling is performed
even with other runnable tasks in the host.
Results comparing halt_poll_ns and server/client application
where a small packet is ping-ponged:
host --> 31.33
halt_poll_ns=300000 / no guest busy spin --> 33.40 (93.8%)
halt_poll_ns=0 / guest_halt_poll_ns=300000 --> 32.73 (95.7%)
For the SAP HANA benchmarks (where idle_spin is a parameter
of the previous version of the patch, results should be the
same):
hpns == halt_poll_ns
idle_spin=0/ idle_spin=800/ idle_spin=0/
hpns=200000 hpns=0 hpns=800000
DeleteC06T03 (100 thread) 1.76 1.71 (-3%) 1.78 (+1%)
InsertC16T02 (100 thread) 2.14 2.07 (-3%) 2.18 (+1.8%)
DeleteC00T01 (1 thread) 1.34 1.28 (-4.5%) 1.29 (-3.7%)
UpdateC00T03 (1 thread) 4.72 4.18 (-12%) 4.53 (-5%)
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Since this field is shared by all governors, move it to
cpuidle device structure.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Based on 1 normalized pattern(s):
this code is licenced under the gpl version 2 as described in the
copying file that acompanies the linux kernel
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 1 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Steve Winslow <swinslow@gmail.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190528171439.466585205@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add SPDX license identifiers to all Make/Kconfig files which:
- Have no license information of any form
These files fall under the project license, GPL v2 only. The resulting SPDX
license identifier is:
GPL-2.0-only
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The variance computation in get_typical_interval() may overflow if
the square of the value of diff exceeds the maximum for the int64_t
data type value which basically is the case when it is of the order
of UINT_MAX.
However, data points so far in the future don't matter for idle
state selection anyway, so change the initial threshold value in
get_typical_interval() to INT_MAX which will cause more "outlying"
data points to be discarded without affecting the selection result.
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The venerable menu governor does some things that are quite
questionable in my view.
First, it includes timer wakeups in the pattern detection data and
mixes them up with wakeups from other sources which in some cases
causes it to expect what essentially would be a timer wakeup in a
time frame in which no timer wakeups are possible (because it knows
the time until the next timer event and that is later than the
expected wakeup time).
Second, it uses the extra exit latency limit based on the predicted
idle duration and depending on the number of tasks waiting on I/O,
even though those tasks may run on a different CPU when they are
woken up. Moreover, the time ranges used by it for the sleep length
correction factors depend on whether or not there are tasks waiting
on I/O, which again doesn't imply anything in particular, and they
are not correlated to the list of available idle states in any way
whatever.
Also, the pattern detection code in menu may end up considering
values that are too large to matter at all, in which cases running
it is a waste of time.
A major rework of the menu governor would be required to address
these issues and the performance of at least some workloads (tuned
specifically to the current behavior of the menu governor) is likely
to suffer from that. It is thus better to introduce an entirely new
governor without them and let everybody use the governor that works
better with their actual workloads.
The new governor introduced here, the timer events oriented (TEO)
governor, uses the same basic strategy as menu: it always tries to
find the deepest idle state that can be used in the given conditions.
However, it applies a different approach to that problem.
First, it doesn't use "correction factors" for the time till the
closest timer, but instead it tries to correlate the measured idle
duration values with the available idle states and use that
information to pick up the idle state that is most likely to "match"
the upcoming CPU idle interval.
Second, it doesn't take the number of "I/O waiters" into account at
all and the pattern detection code in it avoids taking timer wakeups
into account. It also only uses idle duration values less than the
current time till the closest timer (with the tick excluded) for that
purpose.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
- Fix build regression in the intel_pstate driver that doesn't
build without CONFIG_ACPI after recent changes (Dominik Brodowski).
- One of the heuristics in the menu cpuidle governor is based on a
function returning 0 most of the time, so drop it and clean up
the scheduler code related to it (Daniel Lezcano).
- Prevent the arm_big_little cpufreq driver from being used on ARM64
which is not suitable for it and drop the arm_big_little_dt driver
that is not used any more (Sudeep Holla).
- Prevent the hung task watchdog from triggering during resume from
system-wide sleep states by disabling it before freezing tasks and
enabling it again after they have been thawed (Vitaly Kuznetsov).
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2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=/bnR
-----END PGP SIGNATURE-----
Merge tag 'pm-4.20-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more power management updates from Rafael Wysocki:
"These remove a questionable heuristic from the menu cpuidle governor,
fix a recent build regression in the intel_pstate driver, clean up ARM
big-Little support in cpufreq and fix up hung task watchdog's
interaction with system-wide power management transitions.
Specifics:
- Fix build regression in the intel_pstate driver that doesn't build
without CONFIG_ACPI after recent changes (Dominik Brodowski).
- One of the heuristics in the menu cpuidle governor is based on a
function returning 0 most of the time, so drop it and clean up the
scheduler code related to it (Daniel Lezcano).
- Prevent the arm_big_little cpufreq driver from being used on ARM64
which is not suitable for it and drop the arm_big_little_dt driver
that is not used any more (Sudeep Holla).
- Prevent the hung task watchdog from triggering during resume from
system-wide sleep states by disabling it before freezing tasks and
enabling it again after they have been thawed (Vitaly Kuznetsov)"
* tag 'pm-4.20-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
kernel: hung_task.c: disable on suspend
cpufreq: remove unused arm_big_little_dt driver
cpufreq: drop ARM_BIG_LITTLE_CPUFREQ support for ARM64
cpufreq: intel_pstate: Fix compilation for !CONFIG_ACPI
cpuidle: menu: Remove get_loadavg() from the performance multiplier
sched: Factor out nr_iowait and nr_iowait_cpu
There are several definitions of those functions/macros in places that
mess with fixed-point load averages. Provide an official version.
[akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c]
Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Tested-by: Daniel Drake <drake@endlessm.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The function get_loadavg() returns almost always zero. To be more
precise, statistically speaking for a total of 1023379 times passing
in the function, the load is equal to zero 1020728 times, greater than
100, 610 times, the remaining is between 0 and 5.
In 2011, the get_loadavg() was removed from the Android tree because
of the above [1]. At this time, the load was:
unsigned long this_cpu_load(void)
{
struct rq *this = this_rq();
return this->cpu_load[0];
}
In 2014, the code was changed by commit 372ba8cb46 (cpuidle: menu: Lookup CPU
runqueues less) and the load is:
void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
struct rq *rq = this_rq();
*nr_waiters = atomic_read(&rq->nr_iowait);
*load = rq->load.weight;
}
with the same result.
Both measurements show using the load in this code path does no matter
anymore. Removing it.
[1] 4dedd9f124
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
If the minimum interval taken into account in the average computation
loop in get_typical_interval() is less than the expected idle
duration determined so far, the resultant average cannot be greater
than that value as well and the entire return result of the function
is going to be discarded anyway going forward.
In that case, it is a waste of time to carry out the remaining
computations in get_typical_interval(), so avoid that by returning
early if the minimum interval is not below the expected idle duration.
No intentional changes of behavior.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Since the correction factor cannot be greater than RESOLUTION * DECAY,
the result of the predicted_us computation in menu_select() cannot be
greater than data->next_timer_us, so it is not necessary to compare
the "typical interval" value coming from get_typical_interval() with
data->next_timer_us separately.
It is sufficient to copmare predicted_us with the return value of
get_typical_interval() directly, so do that and drop the now
redundant expected_interval variable.
No intentional changes of behavior.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
After some recent menu governor changes, the promotion of the
"polling" state to a physical one is mostly controlled by the
latency limit (resulting from the "interactivity" factor) and
not by the time to the closest timer event, so it should be
sufficient to check the exit latency of that state for this
purpose (of course, its target residency still needs to be
within the next timer event range for energy-efficiency).
Also, the physical state the "polling" one is promoted to need not
be the next one in principle (in case the next state is disabled,
for example).
For these reasons, simplify the checks made to decide whether or
not to promote the "polling" state to a physical one and update
the target idle duration when it is promoted in case the residency
of the new state turns out to be above the tick boundary (in which
case there is no reason to stop the tick).
Tested-by: Doug Smythies <dsmythies@telus.net>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
It is better to always update data->bucket before returning from
menu_select() to avoid updating the correction factor for a stale
bucket, so combine the latency_req == 0 special check with the more
general check below.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
If the next timer event (not including the tick) is closer than the
target residency of the second state or the PM QoS latency constraint
is below its exit latency, state[0] will be used regardless of any
other factors, so skip the computations in menu_select() then and
return 0 straight away from it.
Still, do that after the bucket has been determined to avoid
updating the correction factor for a stale bucket.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
It is not necessary to update data->last_state_idx in menu_select()
as it only is used in menu_update() which only runs when
data->needs_update is set and that is set only when updating
data->last_state_idx in menu_reflect().
Accordingly, drop the update of data->last_state_idx from
menu_select() and get rid of the (now redundant) "out" label
from it.
No intentional behavior changes.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Rearrange the code in menu_select() so that the loop over idle states
always starts from 0 and get rid of the first_idx variable.
While at it, add two empty lines to separate conditional statements
from one another.
No intentional behavior changes.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Since menu_select() can only set first_idx to 1 if the exit latency
of the second state is not greater than the latency limit, it should
first determine that limit. Thus first_idx should be computed after
the "interactivity" factor has been taken into account.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewedy-by: Daniel Lezcano <daniel.lezcano@linaro.org>
If the CPU exits the "polling" state due to the time limit in the
loop in poll_idle(), this is not a real wakeup and it just means
that the "polling" state selection was not adequate. The governor
mispredicted short idle duration, but had a more suitable state been
selected, the CPU might have spent more time in it. In fact, there
is no reason to expect that there would have been a wakeup event
earlier than the next timer in that case.
Handling such cases as regular wakeups in menu_update() may cause the
menu governor to make suboptimal decisions going forward, but ignoring
them altogether would not be correct either, because every time
menu_select() is invoked, it makes a separate new attempt to predict
the idle duration taking distinct time to the closest timer event as
input and the outcomes of all those attempts should be recorded.
For this reason, make menu_update() always assume that if the
"polling" state was exited due to the time limit, the next proper
wakeup event for the CPU would be the next timer event (not
including the tick).
Fixes: a37b969a61 "cpuidle: poll_state: Add time limit to poll_idle()"
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
The predicted_us field in struct menu_device is only accessed in
menu_select(), so replace it with a local variable in that function.
With that, stop using expected_interval instead of predicted_us to
store the new predicted idle duration value if it is set to the
selected state's target residency which is quite confusing.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
cpuidle_get_last_residency() is just a wrapper for retrieving
the last_residency member of struct cpuidle_device. It's also
weirdly the only wrapper function for accessing cpuidle_* struct
member (by my best guess is it could be a leftover from v2.x).
Anyhow, since the only two users (the ladder and menu governors)
can access dev->last_residency directly, and it's more intuitive to
do it that way, let's just get rid of the wrapper.
This patch tidies up CPU idle code a bit without functional changes.
Signed-off-by: Fieah Lim <kw@fieahl.im>
[ rjw: Changelog cleanup ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The case addressed by commit 5ef499cd57 (cpuidle: menu: Handle
stopped tick more aggressively) in the stopped tick case is present
when the tick has not been stopped yet too. Namely, if only two CPU
idle states, shallow state A with target residency significantly
below the tick boundary and deep state B with target residency
significantly above it, are available and the predicted idle
duration is above the tick boundary, but below the target residency
of state B, state A will be selected and the CPU may spend indefinite
amount of time in it, which is not quite energy-efficient.
However, if the tick has not been stopped yet and the governor is
about to select a shallow idle state for the CPU even though the idle
duration predicted by it is above the tick boundary, it should be
fine to wake up the CPU early, so the tick can be retained then and
the governor will have a chance to select a deeper state when it runs
next time.
[Note that when this really happens, it will make the idle duration
predictor believe that the CPU might be idle longer than predicted,
which will make it more likely to predict longer idle durations going
forward, but that will also cause deeper idle states to be selected
going forward, on average, which is what's needed here.]
Fixes: 87c9fe6ee4 (cpuidle: menu: Avoid selecting shallow states with stopped tick)
Reported-by: Leo Yan <leo.yan@linaro.org>
Cc: 4.17+ <stable@vger.kernel.org> # 4.17+: 5ef499cd57 (cpuidle: menu: Handle ...)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Commit 87c9fe6ee4 (cpuidle: menu: Avoid selecting shallow states
with stopped tick) missed the case when the target residencies of
deep idle states of CPUs are above the tick boundary which may cause
the CPU to get stuck in a shallow idle state for a long time.
Say there are two CPU idle states available: one shallow, with the
target residency much below the tick boundary and one deep, with
the target residency significantly above the tick boundary. In
that case, if the tick has been stopped already and the expected
next timer event is relatively far in the future, the governor will
assume the idle duration to be equal to TICK_USEC and it will select
the idle state for the CPU accordingly. However, that will cause the
shallow state to be selected even though it would have been more
energy-efficient to select the deep one.
To address this issue, modify the governor to always use the time
till the closest timer event instead of the predicted idle duration
if the latter is less than the tick period length and the tick has
been stopped already. Also make it extend the search for a matching
idle state if the tick is stopped to avoid settling on a shallow
state if deep states with target residencies above the tick period
length are available.
In addition, make it always indicate that the tick should be stopped
if it has been stopped already for consistency.
Fixes: 87c9fe6ee4 (cpuidle: menu: Avoid selecting shallow states with stopped tick)
Reported-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: 4.17+ <stable@vger.kernel.org> # 4.17+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The comment to explain why the menu governor uses idle state 1
instead of idle state 0 as the first one sometimes is stale (among
other things it mentions a user setting not present any more),
so update it.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
There is some code duplication related to the PM QoS handling between
the existing cpuidle governors, so move that code to a common helper
function and call that from the governors.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
PM_QOS_RESUME_LATENCY_NO_CONSTRAINT is defined as the 32-bit integer
maximum, so it is not necessary to test the return value of
dev_pm_qos_raw_read_value() against it directly in the menu and
ladder cpuidle governors.
Drop these redundant checks.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
If the scheduler tick has been stopped already and the governor
selects a shallow idle state, the CPU can spend a long time in that
state if the selection is based on an inaccurate prediction of idle
time. That effect turns out to be relevant, so it needs to be
mitigated.
To that end, modify the menu governor to discard the result of the
idle time prediction if the tick is stopped and the predicted idle
time is less than the tick period length, unless the tick timer is
going to expire soon.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
If the tick isn't stopped, the target residency of the state selected
by the menu governor may be greater than the actual time to the next
tick and that means lost energy.
To avoid that, make tick_nohz_get_sleep_length() return the current
time to the next event (before stopping the tick) in addition to the
estimated one via an extra pointer argument and make menu_select()
use that value to refine the state selection when necessary.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Add a new pointer argument to cpuidle_select() and to the ->select
cpuidle governor callback to allow a boolean value indicating
whether or not the tick should be stopped before entering the
selected state to be returned from there.
Make the ladder governor ignore that pointer (to preserve its
current behavior) and make the menu governor return 'false" through
it if:
(1) the idle exit latency is constrained at 0, or
(2) the selected state is a polling one, or
(3) the expected idle period duration is within the tick period
range.
In addition to that, the correction factor computations in the menu
governor need to take the possibility that the tick may not be
stopped into account to avoid artificially small correction factor
values. To that end, add a mechanism to record tick wakeups, as
suggested by Peter Zijlstra, and use it to modify the menu_update()
behavior when tick wakeup occurs. Namely, if the CPU is woken up by
the tick and the return value of tick_nohz_get_sleep_length() is not
within the tick boundary, the predicted idle duration is likely too
short, so make menu_update() try to compensate for that by updating
the governor statistics as though the CPU was idle for a long time.
Since the value returned through the new argument pointer of
cpuidle_select() is not used by its caller yet, this change by
itself is not expected to alter the functionality of the code.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Individual CPUs may have special requirements to not enter
deep idle states. For example, a CPU running real time
applications would not want to enter deep idle states to
avoid latency impacts. At the same time other CPUs that
do not have such a requirement could allow deep idle
states to save power.
This was already implemented in the menu governor.
Implementing similar changes in the ladder governor which
gets selected when CONFIG_NO_HZ and CONFIG_NO_HZ_IDLE are not
set. Refer following commits for the menu governor changes.
Signed-off-by: Ramesh Thomas <ramesh.thomas@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The special value of 0 for device resume latency PM QoS means
"no restriction", but there are two problems with that.
First, device resume latency PM QoS requests with 0 as the
value are always put in front of requests with positive
values in the priority lists used internally by the PM QoS
framework, causing 0 to be chosen as an effective constraint
value. However, that 0 is then interpreted as "no restriction"
effectively overriding the other requests with specific
restrictions which is incorrect.
Second, the users of device resume latency PM QoS have no
way to specify that *any* resume latency at all should be
avoided, which is an artificial limitation in general.
To address these issues, modify device resume latency PM QoS to
use S32_MAX as the "no constraint" value and 0 as the "no
latency at all" one and rework its users (the cpuidle menu
governor, the genpd QoS governor and the runtime PM framework)
to follow these changes.
Also add a special "n/a" value to the corresponding user space I/F
to allow user space to indicate that it cannot accept any resume
latencies at all for the given device.
Fixes: 85dc0b8a40 (PM / QoS: Make it possible to expose PM QoS latency constraints)
Link: https://bugzilla.kernel.org/show_bug.cgi?id=197323
Reported-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Tero Kristo <t-kristo@ti.com>
Reviewed-by: Ramesh Thomas <ramesh.thomas@intel.com>
On some architectures the first (index 0) idle state is a polling
one and it doesn't really save energy, so there is the
CPUIDLE_DRIVER_STATE_START symbol allowing some pieces of
cpuidle code to avoid using that state.
However, this makes the code rather hard to follow. It is better
to explicitly avoid the polling state, so add a new cpuidle state
flag CPUIDLE_FLAG_POLLING to mark it and make the relevant code
check that flag for the first state instead of using the
CPUIDLE_DRIVER_STATE_START symbol.
In the ACPI processor driver that cannot always rely on the state
flags (like before the states table has been set up) define
a new internal symbol ACPI_IDLE_STATE_START equivalent to the
CPUIDLE_DRIVER_STATE_START one and drop the latter.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
The menu driver does not allow state0 to be disabled completely.
If it is disabled but other enabled states don't meet latency
requirements, it is still used.
Fix this by starting with the first enabled idle state. Fall back
to state 0 if no idle states are enabled (arguably this should be
-EINVAL if it is attempted, but this is the minimal fix).
Acked-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Pull sched.h split-up from Ingo Molnar:
"The point of these changes is to significantly reduce the
<linux/sched.h> header footprint, to speed up the kernel build and to
have a cleaner header structure.
After these changes the new <linux/sched.h>'s typical preprocessed
size goes down from a previous ~0.68 MB (~22K lines) to ~0.45 MB (~15K
lines), which is around 40% faster to build on typical configs.
Not much changed from the last version (-v2) posted three weeks ago: I
eliminated quirks, backmerged fixes plus I rebased it to an upstream
SHA1 from yesterday that includes most changes queued up in -next plus
all sched.h changes that were pending from Andrew.
I've re-tested the series both on x86 and on cross-arch defconfigs,
and did a bisectability test at a number of random points.
I tried to test as many build configurations as possible, but some
build breakage is probably still left - but it should be mostly
limited to architectures that have no cross-compiler binaries
available on kernel.org, and non-default configurations"
* 'WIP.sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (146 commits)
sched/headers: Clean up <linux/sched.h>
sched/headers: Remove #ifdefs from <linux/sched.h>
sched/headers: Remove the <linux/topology.h> include from <linux/sched.h>
sched/headers, hrtimer: Remove the <linux/wait.h> include from <linux/hrtimer.h>
sched/headers, x86/apic: Remove the <linux/pm.h> header inclusion from <asm/apic.h>
sched/headers, timers: Remove the <linux/sysctl.h> include from <linux/timer.h>
sched/headers: Remove <linux/magic.h> from <linux/sched/task_stack.h>
sched/headers: Remove <linux/sched.h> from <linux/sched/init.h>
sched/core: Remove unused prefetch_stack()
sched/headers: Remove <linux/rculist.h> from <linux/sched.h>
sched/headers: Remove the 'init_pid_ns' prototype from <linux/sched.h>
sched/headers: Remove <linux/signal.h> from <linux/sched.h>
sched/headers: Remove <linux/rwsem.h> from <linux/sched.h>
sched/headers: Remove the runqueue_is_locked() prototype
sched/headers: Remove <linux/sched.h> from <linux/sched/hotplug.h>
sched/headers: Remove <linux/sched.h> from <linux/sched/debug.h>
sched/headers: Remove <linux/sched.h> from <linux/sched/nohz.h>
sched/headers: Remove <linux/sched.h> from <linux/sched/stat.h>
sched/headers: Remove the <linux/gfp.h> include from <linux/sched.h>
sched/headers: Remove <linux/rtmutex.h> from <linux/sched.h>
...
We are going to split <linux/sched/stat.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.
Create a trivial placeholder <linux/sched/stat.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.
Include the new header in the files that are going to need it.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We are going to split <linux/sched/loadavg.h> out of <linux/sched.h>, which
will have to be picked up from a couple of .c files.
Create a trivial placeholder <linux/sched/topology.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.
Include the new header in the files that are going to need it.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
After commit 9908859aca (cpuidle/menu: add per CPU PM QoS resume
latency consideration) the cpuidle menu governor calls
dev_pm_qos_read_value() on CPU devices to read the current resume
latency QoS constraint values for them. That function takes a spinlock
to prevent the device's power.qos pointer from becoming NULL during
the access which is a problem for the RT patchset where spinlocks are
converted into mutexes and the idle loop stops working.
However, it is not even necessary for the menu governor to take
that spinlock, because the power.qos pointer accessed under it
cannot be modified during the access anyway.
For this reason, introduce a "raw" routine for accessing device
QoS resume latency constraints without locking and use it in the
menu governor.
Fixes: 9908859aca (cpuidle/menu: add per CPU PM QoS resume latency consideration)
Acked-by: Alex Shi <alex.shi@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
There may be special requirements on CPU response time, like if a
interrupt is pinned to a CPU, that CPU should not go into excessively
deep idle states. For this reason, add a mechanism for adding
PM QoS resume latency constraints for individual CPUs and modify the
menu governor to take them into account.
To that end, extend the device PM QoS pm_qos_resume_latency attribute
to CPUs, which is possible, because the exit latency for CPUs is
effectively equivalent to the resume latency for devices.
Signed-off-by: Alex Shi <alex.shi@linaro.org>
Acked-by: Rik van Riel <riel@redhat.com>
[ rjw : Subject & changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Obsolete commit 71abbbf856 (cpuidle: extend cpuidle and menu governor
to handle dynamic states) wanted to introduce dynamic C-states, but that
idea was dropped long ago. The nonsense deeper C-state checking
remained, though.
Since both target_residency and exit_latency are longer for deeper
idle state, there's no need to waste CPU time on useless checks.
Signed-off-by: Alex Shi <alex.shi@linaro.org>
Acked-by: Rik van Riel <riel@redhat.com>
[ rjw: Subject & changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
This was entirely automated, using the script by Al:
PATT='^[[:blank:]]*#[[:blank:]]*include[[:blank:]]*<asm/uaccess.h>'
sed -i -e "s!$PATT!#include <linux/uaccess.h>!" \
$(git grep -l "$PATT"|grep -v ^include/linux/uaccess.h)
to do the replacement at the end of the merge window.
Requested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The governor's code use try_module_get() and put_module() to refcount
the governor's module. But the governors are not compiled as module.
The refcount does not prevent to switch the governor or unload
a module as they aren't compiled as modules. The code is pointless,
so remove it.
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Commit a9ceb78bc7 (cpuidle,menu: use interactivity_req to disable
polling) changed the behavior of the fallback state selection part
of menu_select() so it looks at interactivity_req instead of
data->next_timer_us when it makes its decision. That effectively
caused polling to be used more often as fallback idle which led to
significant increases of energy consumption in some cases.
Commit e132b9b3bc (cpuidle: menu: use high confidence factors
only when considering polling) changed that logic again to be more
predictable, but that didn't help with the increased energy
consumption problem.
For this reason, go back to making decisions on which state to fall
back to based on data->next_timer_us which is the time we know for
sure something will happen rather than a prediction (which may be
inaccurate and turns out to be so often enough to be problematic).
However, take the target residency of the first proper idle state
(C1) into account, so that state is not used as the fallback one
if its target residency is greater than data->next_timer_us.
Fixes: a9ceb78bc7 (cpuidle,menu: use interactivity_req to disable polling)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reported-and-tested-by: Doug Smythies <dsmythies@telus.net>
The menu governor uses five different factors to pick the
idle state:
- the user configured latency_req
- the time until the next timer (next_timer_us)
- the typical sleep interval, as measured recently
- an estimate of sleep time by dividing next_timer_us by an observed factor
- a load corrected version of the above, divided again by load
Only the first three items are known with enough confidence that
we can use them to consider polling, instead of an actual CPU
idle state, because the cost of being wrong about polling can be
excessive power use.
The latter two are used in the menu governor's main selection
loop, and can result in choosing a shallower idle state when
the system is expected to be busy again soon.
This pushes a busy system in the "performance" direction of
the performance<>power tradeoff, when choosing between idle
states, but stays more strictly on the "power" state when
deciding between polling and C1.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
We know that the avg variable actually ends up holding a 32 bit
quantity, since it's an average of such numbers. It is only a u64
because it is temporarily used to hold the sum. Making it an actual
u32 allows gcc to generate slightly better code, e.g. when computing
the square, it can do a 32x32->64 multiply.
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Computing the integer square root is a rather expensive operation, at
least compared to doing a 64x64 -> 64 multiply (avg*avg) and, on 64
bit platforms, doing an extra comparison to a constant (variance <=
U64_MAX/36).
On 64 bit platforms, this does mean that we add a restriction on the
range of the variance where we end up using the estimate (since
previously the stddev <= ULONG_MAX was a tautology), but on the other
hand, we extend the range quite substantially on 32 bit platforms - in
both cases, we now allow standard deviations up to 715 seconds, which
is for example guaranteed if all observations are less than 1430
seconds.
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
If menu_select() cannot find a suitable state to return, it will
return the state index stored in data->last_state_idx. This
means that it is pointless to look at the states whose indices
are less than or equal to data->last_state_idx in the main loop,
so don't do that.
Given that those checks are done on every idle state selection, this
change can save quite a bit of completely unnecessary overhead.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Sudeep Holla <sudeep.holla@arm.com>
