Pull power management updates from Rafael Wysocki:
 "These include cpuidle changes to use nanoseconds (instead of
  microseconds) as the unit of time and to simplify checks for disabled
  idle states in the idle loop, some cpuidle fixes and governor updates,
  assorted cpufreq updates (driver updates mostly and a few core fixes
  and cleanups), devfreq updates (dominated by the tegra30 driver
  changes), new CPU IDs for the RAPL power capping driver, relatively
  minor updates of the generic power domains (genpd) and operation
  performance points (OPP) frameworks, and assorted fixes and cleanups.

  There are also two maintainer information updates: Chanwoo Choi will
  be maintaining the devfreq subsystem going forward and Todd Brandt is
  going to maintain the pm-graph utility (created by him).

  Specifics:

   - Use nanoseconds (instead of microseconds) as the unit of time in
     the cpuidle core and simplify checks for disabled idle states in
     the idle loop (Rafael Wysocki)

   - Fix and clean up the teo cpuidle governor (Rafael Wysocki)

   - Fix the cpuidle registration error code path (Zhenzhong Duan)

   - Avoid excessive vmexits in the ACPI cpuidle driver (Yin Fengwei)

   - Extend the idle injection infrastructure to be able to measure the
     requested duration in nanoseconds and to allow an exit latency
     limit for idle states to be specified (Daniel Lezcano)

   - Fix cpufreq driver registration and clarify a comment in the
     cpufreq core (Viresh Kumar)

   - Add NULL checks to the show() and store() methods of sysfs
     attributes exposed by cpufreq (Kai Shen)

   - Update cpufreq drivers:
      * Fix for a plain int as pointer warning from sparse in
        intel_pstate (Jamal Shareef)
      * Fix for a hardcoded number of CPUs and stack bloat in the
        powernv driver (John Hubbard)
      * Updates to the ti-cpufreq driver and DT files to support new
        platforms and migrate bindings from opp-v1 to opp-v2 (Adam Ford,
        H. Nikolaus Schaller)
      * Merging of the arm_big_little and vexpress-spc drivers and
        related cleanup (Sudeep Holla)
      * Fix for imx's default speed grade value (Anson Huang)
      * Minor cleanup of the s3c64xx driver (Nathan Chancellor)
      * CPU speed bin detection fix for sun50i (Ondrej Jirman)

   - Appoint Chanwoo Choi as the new devfreq maintainer.

   - Update the devfreq core:
      * Check NULL governor in available_governors_show sysfs to prevent
        showing wrong governor information and fix a race condition
        between devfreq_update_status() and trans_stat_show() (Leonard
        Crestez)
      * Add new 'interrupt-driven' flag for devfreq governors to allow
        interrupt-driven governors to prevent the devfreq core from
        polling devices for status (Dmitry Osipenko)
      * Improve an error message in devfreq_add_device() (Matthias
        Kaehlcke)

   - Update devfreq drivers:
      * tegra30 driver fixes and cleanups (Dmitry Osipenko)
      * Removal of unused property from dt-binding documentation for the
        exynos-bus driver (Kamil Konieczny)
      * exynos-ppmu cleanup and DT bindings update (Lukasz Luba, Marek
        Szyprowski)

   - Add new CPU IDs for CometLake Mobile and Desktop to the Intel RAPL
     power capping driver (Zhang Rui)

   - Allow device initialization in the generic power domains (genpd)
     framework to be more straightforward and clean it up (Ulf Hansson)

   - Add support for adjusting OPP voltages at run time to the OPP
     framework (Stephen Boyd)

   - Avoid freeing memory that has never been allocated in the
     hibernation core (Andy Whitcroft)

   - Clean up function headers in a header file and coding style in the
     wakeup IRQs handling code (Ulf Hansson, Xiaofei Tan)

   - Clean up the SmartReflex adaptive voltage scaling (AVS) driver for
     ARM (Ben Dooks, Geert Uytterhoeven)

   - Wrap power management documentation to fit in 80 columns (Bjorn
     Helgaas)

   - Add pm-graph utility entry to MAINTAINERS (Todd Brandt)

   - Update the cpupower utility:
      * Fix the handling of set and info subcommands (Abhishek Goel)
      * Fix build warnings (Nathan Chancellor)
      * Improve mperf_monitor handling (Janakarajan Natarajan)"

* tag 'pm-5.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (83 commits)
  PM: Wrap documentation to fit in 80 columns
  cpuidle: Pass exit latency limit to cpuidle_use_deepest_state()
  cpuidle: Allow idle injection to apply exit latency limit
  cpuidle: Introduce cpuidle_driver_state_disabled() for driver quirks
  cpuidle: teo: Avoid code duplication in conditionals
  cpufreq: Register drivers only after CPU devices have been registered
  cpuidle: teo: Avoid using "early hits" incorrectly
  cpuidle: teo: Exclude cpuidle overhead from computations
  PM / Domains: Convert to dev_to_genpd_safe() in genpd_syscore_switch()
  mmc: tmio: Avoid boilerplate code in ->runtime_suspend()
  PM / Domains: Implement the ->start() callback for genpd
  PM / Domains: Introduce dev_pm_domain_start()
  ARM: OMAP2+: SmartReflex: add omap_sr_pdata definition
  PM / wakeirq: remove unnecessary parentheses
  power: avs: smartreflex: Remove superfluous cast in debugfs_create_file() call
  cpuidle: Use nanoseconds as the unit of time
  PM / OPP: Support adjusting OPP voltages at runtime
  PM / core: Clean up some function headers in power.h
  cpufreq: Add NULL checks to show() and store() methods of cpufreq
  cpufreq: intel_pstate: Fix plain int as pointer warning from sparse
  ...

* pm-cpuidle:
  cpuidle: Pass exit latency limit to cpuidle_use_deepest_state()
  cpuidle: Allow idle injection to apply exit latency limit
  cpuidle: Introduce cpuidle_driver_state_disabled() for driver quirks
  cpuidle: teo: Avoid code duplication in conditionals
  cpuidle: teo: Avoid using "early hits" incorrectly
  cpuidle: teo: Exclude cpuidle overhead from computations
  cpuidle: Use nanoseconds as the unit of time
  cpuidle: Consolidate disabled state checks
  ACPI: processor_idle: Skip dummy wait if kernel is in guest
  cpuidle: Do not unset the driver if it is there already
  cpuidle: teo: Fix "early hits" handling for disabled idle states
  cpuidle: teo: Consider hits and misses metrics of disabled states
  cpuidle: teo: Rename local variable in teo_select()
  cpuidle: teo: Ignore disabled idle states that are too deep

Modify cpuidle_use_deepest_state() to take an additional exit latency
limit argument to be passed to find_deepest_idle_state() and make
cpuidle_idle_call() pass dev->forced_idle_latency_limit_ns to it for
forced idle.

Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Rebase and rearrange code, subject & changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

In some cases it may be useful to specify an exit latency limit for
the idle state to be used during CPU idle time injection.

Instead of duplicating the information in struct cpuidle_device
or propagating the latency limit in the call stack, replace the
use_deepest_state field with forced_latency_limit_ns to represent
that limit, so that the deepest idle state with exit latency within
that limit is forced (i.e. no governors) when it is set.

A zero exit latency limit for forced idle means to use governors in
the usual way (analogous to use_deepest_state equal to "false" before
this change).

Additionally, add play_idle_precise() taking two arguments, the
duration of forced idle and the idle state exit latency limit, both
in nanoseconds, and redefine play_idle() as a wrapper around that
new function.

This change is preparatory, no functional impact is expected.

Suggested-by: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Currently, the cpuidle subsystem uses microseconds as the unit of
time which (among other things) causes the idle loop to incur some
integer division overhead for no clear benefit.

In order to allow cpuidle to measure time in nanoseconds, add two
new fields, exit_latency_ns and target_residency_ns, to represent the
exit latency and target residency of an idle state in nanoseconds,
respectively, to struct cpuidle_state and initialize them with the
help of the corresponding values in microseconds provided by drivers.
Additionally, change cpuidle_governor_latency_req() to return the
idle state exit latency constraint in nanoseconds.

Also meeasure idle state residency (last_residency_ns in struct
cpuidle_device and time_ns in struct cpuidle_driver) in nanoseconds
and update the cpuidle core and governors accordingly.

However, the menu governor still computes typical intervals in
microseconds to avoid integer overflows.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Doug Smythies <dsmythies@telus.net>
Tested-by: Doug Smythies <dsmythies@telus.net>

It turns out there really is something special to the first
set_next_task() invocation. In specific the 'change' pattern really
should not cause balance callbacks.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: juri.lelli@redhat.com
Cc: ktkhai@virtuozzo.com
Cc: mgorman@suse.de
Cc: qais.yousef@arm.com
Cc: qperret@google.com
Cc: rostedt@goodmis.org
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Fixes: f95d4eaee6d0 ("sched/{rt,deadline}: Fix set_next_task vs pick_next_task")
Link: https://lkml.kernel.org/r/20191108131909.775434698@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Now that the indirect class call never uses the last two arguments of
pick_next_task(), remove them.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: juri.lelli@redhat.com
Cc: ktkhai@virtuozzo.com
Cc: mgorman@suse.de
Cc: qais.yousef@arm.com
Cc: qperret@google.com
Cc: rostedt@goodmis.org
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Link: https://lkml.kernel.org/r/20191108131909.660595546@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Ever since we moved the sched_class definitions into their own files,
the constant expression {fair,idle}_sched_class.pick_next_task() is
not in fact a compile time constant anymore and results in an indirect
call (barring LTO).

Fix that by exposing pick_next_task_{fair,idle}() directly, this gets
rid of the indirect call (and RETPOLINE) on the fast path.

Also remove the unlikely() from the idle case, it is in fact /the/ way
we select idle -- and that is a very common thing to do.

Performance for will-it-scale/sched_yield improves by 2% (as reported
by 0-day).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: juri.lelli@redhat.com
Cc: ktkhai@virtuozzo.com
Cc: mgorman@suse.de
Cc: qais.yousef@arm.com
Cc: qperret@google.com
Cc: rostedt@goodmis.org
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Link: https://lkml.kernel.org/r/20191108131909.603037345@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Only pick_next_task_fair() needs the @prev and @rf argument; these are
required to implement the cpu-cgroup optimization. None of the other
pick_next_task() methods need this. Make pick_next_task_idle() more
consistent.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: juri.lelli@redhat.com
Cc: ktkhai@virtuozzo.com
Cc: mgorman@suse.de
Cc: qais.yousef@arm.com
Cc: qperret@google.com
Cc: rostedt@goodmis.org
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Link: https://lkml.kernel.org/r/20191108131909.545730862@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Commit 67692435c411 ("sched: Rework pick_next_task() slow-path")
inadvertly introduced a race because it changed a previously
unexplored dependency between dropping the rq->lock and
sched_class::put_prev_task().

The comments about dropping rq->lock, in for example
newidle_balance(), only mentions the task being current and ->on_cpu
being set. But when we look at the 'change' pattern (in for example
sched_setnuma()):

	queued = task_on_rq_queued(p); /* p->on_rq == TASK_ON_RQ_QUEUED */
	running = task_current(rq, p); /* rq->curr == p */

	if (queued)
		dequeue_task(...);
	if (running)
		put_prev_task(...);

	/* change task properties */

	if (queued)
		enqueue_task(...);
	if (running)
		set_next_task(...);

It becomes obvious that if we do this after put_prev_task() has
already been called on @p, things go sideways. This is exactly what
the commit in question allows to happen when it does:

	prev->sched_class->put_prev_task(rq, prev, rf);
	if (!rq->nr_running)
		newidle_balance(rq, rf);

The newidle_balance() call will drop rq->lock after we've called
put_prev_task() and that allows the above 'change' pattern to
interleave and mess up the state.

Furthermore, it turns out we lost the RT-pull when we put the last DL
task.

Fix both problems by extracting the balancing from put_prev_task() and
doing a multi-class balance() pass before put_prev_task().

Fixes: 67692435c411 ("sched: Rework pick_next_task() slow-path")
Reported-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Quentin Perret <qperret@google.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>