Merge tag 'pm-5.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These fix fallout after starting to use hrtimers in the runtime PM
  framework, fix a few cpufreq issues, fix a recently broken reference
  to cpuidle documentation, update MAINTAINERS entries for cpufreq and
  cpuidle and make the recently added system suspend and resume support
  in devfreq actually work.

  Specifics:

   - Prevent integer overflows from occurring on 32-bit when converting
     milliseconds to nanoseconds in the runtime PM framework and update
     comments that still refer to jiffies in it (Vincent Guittot,
     Ladislav Michl).

   - Fix the SCMI cpufreq driver to always use the same frequency units
     for arch_set_freq_scale() and make the scale-invariant load
     tracking acutally work with this driver (Quentin Perret).

   - Fix freeing of dynamic OPPs in the SCPI and SCMI cpufreq drivers
     broken during the 4.20 defelopment cycle (Viresh Kumar).

   - Prevent the cpufreq core from attempting to return the current
     frequency of offline CPUs (Sudeep Holla).

   - Add devfreq suspend and resume hooks (missed previously) to the PM
     core to make the recently added system suspend and resume support
     in devfreq actually work (Lukasz Luba).

   - Update MAINTAINERS entries for cpufreq and cpuidle, mostly to add
     references to new/current documentation to them (Rafael Wysocki).

   - Fix a recently broken reference to cpuidle documentation (Otto
     Sabart)"

* tag 'pm-5.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM-runtime: Fix autosuspend_delay on 32bits arch
  PM-runtime: Fix 'jiffies' in comments after switch to hrtimers
  cpufreq: scmi: Fix frequency invariance in slow path
  doc: trace: fix reference to cpuidle documentation file
  cpufreq: check if policy is inactive early in __cpufreq_get()
  cpufreq: scpi/scmi: Fix freeing of dynamic OPPs
  cpuidle / Documentation: Update cpuidle MAINTAINERS entry
  cpufreq / Documentation: Update cpufreq MAINTAINERS entry
  PM: sleep: call devfreq suspend/resume

9 files changed, 89 insertions, 26 deletions

diff --git a/Documentation/trace/coresight-cpu-debug.txt b/Documentation/trace/coresight-cpu-debug.txt
index 89ab09e78e8d..f07e38094b40 100644
--- a/Documentation/trace/coresight-cpu-debug.txt
+++ b/Documentation/trace/coresight-cpu-debug.txt
@@ -165,7 +165,7 @@ Do some work...
 The same can also be done from an application program.
 
 Disable specific CPU's specific idle state from cpuidle sysfs (see
-Documentation/cpuidle/sysfs.txt):
+Documentation/admin-guide/pm/cpuidle.rst):
 # echo 1 > /sys/devices/system/cpu/cpu$cpu/cpuidle/state$state/disable
 
 
diff --git a/MAINTAINERS b/MAINTAINERS
index f3a226379e57..2cf9c1ceb502 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3951,7 +3951,7 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/ti/cpmac.c
 
-CPU FREQUENCY DRIVERS
+CPU FREQUENCY SCALING FRAMEWORK
 M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 L:	linux-pm@vger.kernel.org
@@ -3959,6 +3959,8 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 T:	git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates)
 B:	https://bugzilla.kernel.org
+F:	Documentation/admin-guide/pm/cpufreq.rst
+F:	Documentation/admin-guide/pm/intel_pstate.rst
 F:	Documentation/cpu-freq/
 F:	Documentation/devicetree/bindings/cpufreq/
 F:	drivers/cpufreq/
@@ -4006,13 +4008,14 @@ S:	Supported
 F:	drivers/cpuidle/cpuidle-exynos.c
 F:	arch/arm/mach-exynos/pm.c
 
-CPUIDLE DRIVERS
+CPU IDLE TIME MANAGEMENT FRAMEWORK
 M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 M:	Daniel Lezcano <daniel.lezcano@linaro.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 B:	https://bugzilla.kernel.org
+F:	Documentation/admin-guide/pm/cpuidle.rst
 F:	drivers/cpuidle/*
 F:	include/linux/cpuidle.h
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index a690fd400260..0992e67e862b 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -32,6 +32,7 @@
 #include <trace/events/power.h>
 #include <linux/cpufreq.h>
 #include <linux/cpuidle.h>
+#include <linux/devfreq.h>
 #include <linux/timer.h>
 
 #include "../base.h"
@@ -1078,6 +1079,7 @@ void dpm_resume(pm_message_t state)
 	dpm_show_time(starttime, state, 0, NULL);
 
 	cpufreq_resume();
+	devfreq_resume();
 	trace_suspend_resume(TPS("dpm_resume"), state.event, false);
 }
 
@@ -1852,6 +1854,7 @@ int dpm_suspend(pm_message_t state)
 	trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
 	might_sleep();
 
+	devfreq_suspend();
 	cpufreq_suspend();
 
 	mutex_lock(&dpm_list_mtx);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 70624695b6d5..457be03b744d 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -121,7 +121,7 @@ static void pm_runtime_cancel_pending(struct device *dev)
  * Compute the autosuspend-delay expiration time based on the device's
  * power.last_busy time.  If the delay has already expired or is disabled
  * (negative) or the power.use_autosuspend flag isn't set, return 0.
- * Otherwise return the expiration time in jiffies (adjusted to be nonzero).
+ * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero).
  *
  * This function may be called either with or without dev->power.lock held.
  * Either way it can be racy, since power.last_busy may be updated at any time.
@@ -141,7 +141,7 @@ u64 pm_runtime_autosuspend_expiration(struct device *dev)
 
 	last_busy = READ_ONCE(dev->power.last_busy);
 
-	expires = last_busy + autosuspend_delay * NSEC_PER_MSEC;
+	expires = last_busy + (u64)autosuspend_delay * NSEC_PER_MSEC;
 	if (expires <= now)
 		expires = 0;	/* Already expired. */
 
@@ -525,7 +525,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 				 * We add a slack of 25% to gather wakeups
 				 * without sacrificing the granularity.
 				 */
-				u64 slack = READ_ONCE(dev->power.autosuspend_delay) *
+				u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) *
 						    (NSEC_PER_MSEC >> 2);
 
 				dev->power.timer_expires = expires;
@@ -905,7 +905,10 @@ static enum hrtimer_restart  pm_suspend_timer_fn(struct hrtimer *timer)
 	spin_lock_irqsave(&dev->power.lock, flags);
 
 	expires = dev->power.timer_expires;
-	/* If 'expire' is after 'jiffies' we've been called too early. */
+	/*
+	 * If 'expires' is after the current time, we've been called
+	 * too early.
+	 */
 	if (expires > 0 && expires < ktime_to_ns(ktime_get())) {
 		dev->power.timer_expires = 0;
 		rpm_suspend(dev, dev->power.timer_autosuspends ?
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 6f23ebb395f1..e35a886e00bc 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1530,17 +1530,16 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
 {
 	unsigned int ret_freq = 0;
 
-	if (!cpufreq_driver->get)
+	if (unlikely(policy_is_inactive(policy)) || !cpufreq_driver->get)
 		return ret_freq;
 
 	ret_freq = cpufreq_driver->get(policy->cpu);
 
 	/*
-	 * Updating inactive policies is invalid, so avoid doing that.  Also
-	 * if fast frequency switching is used with the given policy, the check
+	 * If fast frequency switching is used with the given policy, the check
 	 * against policy->cur is pointless, so skip it in that case too.
 	 */
-	if (unlikely(policy_is_inactive(policy)) || policy->fast_switch_enabled)
+	if (policy->fast_switch_enabled)
 		return ret_freq;
 
 	if (ret_freq && policy->cur &&
@@ -1569,10 +1568,7 @@ unsigned int cpufreq_get(unsigned int cpu)
 
 	if (policy) {
 		down_read(&policy->rwsem);
-
-		if (!policy_is_inactive(policy))
-			ret_freq = __cpufreq_get(policy);
-
+		ret_freq = __cpufreq_get(policy);
 		up_read(&policy->rwsem);
 
 		cpufreq_cpu_put(policy);
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 50b1551ba894..242c3370544e 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -52,9 +52,9 @@ scmi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 	int ret;
 	struct scmi_data *priv = policy->driver_data;
 	struct scmi_perf_ops *perf_ops = handle->perf_ops;
-	u64 freq = policy->freq_table[index].frequency * 1000;
+	u64 freq = policy->freq_table[index].frequency;
 
-	ret = perf_ops->freq_set(handle, priv->domain_id, freq, false);
+	ret = perf_ops->freq_set(handle, priv->domain_id, freq * 1000, false);
 	if (!ret)
 		arch_set_freq_scale(policy->related_cpus, freq,
 				    policy->cpuinfo.max_freq);
@@ -176,7 +176,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	dev_pm_opp_cpumask_remove_table(policy->cpus);
+	dev_pm_opp_remove_all_dynamic(cpu_dev);
 
 	return ret;
 }
@@ -188,7 +188,7 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	kfree(priv);
-	dev_pm_opp_cpumask_remove_table(policy->related_cpus);
+	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 87a98ec77773..99449738faa4 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -177,7 +177,7 @@ out_free_cpufreq_table:
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	dev_pm_opp_cpumask_remove_table(policy->cpus);
+	dev_pm_opp_remove_all_dynamic(cpu_dev);
 
 	return ret;
 }
@@ -190,7 +190,7 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy)
 	clk_put(priv->clk);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	kfree(priv);
-	dev_pm_opp_cpumask_remove_table(policy->related_cpus);
+	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
 
 	return 0;
 }
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index e5507add8f04..18f1639dbc4a 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -988,11 +988,9 @@ void _opp_free(struct dev_pm_opp *opp)
 	kfree(opp);
 }
 
-static void _opp_kref_release(struct kref *kref)
+static void _opp_kref_release(struct dev_pm_opp *opp,
+			      struct opp_table *opp_table)
 {
-	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
-	struct opp_table *opp_table = opp->opp_table;
-
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
@@ -1002,7 +1000,22 @@ static void _opp_kref_release(struct kref *kref)
 	opp_debug_remove_one(opp);
 	list_del(&opp->node);
 	kfree(opp);
+}
 
+static void _opp_kref_release_unlocked(struct kref *kref)
+{
+	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
+	struct opp_table *opp_table = opp->opp_table;
+
+	_opp_kref_release(opp, opp_table);
+}
+
+static void _opp_kref_release_locked(struct kref *kref)
+{
+	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
+	struct opp_table *opp_table = opp->opp_table;
+
+	_opp_kref_release(opp, opp_table);
 	mutex_unlock(&opp_table->lock);
 }
 
@@ -1013,10 +1026,16 @@ void dev_pm_opp_get(struct dev_pm_opp *opp)
 
 void dev_pm_opp_put(struct dev_pm_opp *opp)
 {
-	kref_put_mutex(&opp->kref, _opp_kref_release, &opp->opp_table->lock);
+	kref_put_mutex(&opp->kref, _opp_kref_release_locked,
+		       &opp->opp_table->lock);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put);
 
+static void dev_pm_opp_put_unlocked(struct dev_pm_opp *opp)
+{
+	kref_put(&opp->kref, _opp_kref_release_unlocked);
+}
+
 /**
  * dev_pm_opp_remove()  - Remove an OPP from OPP table
  * @dev:	device for which we do this operation
@@ -1060,6 +1079,40 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
+/**
+ * dev_pm_opp_remove_all_dynamic() - Remove all dynamically created OPPs
+ * @dev:	device for which we do this operation
+ *
+ * This function removes all dynamically created OPPs from the opp table.
+ */
+void dev_pm_opp_remove_all_dynamic(struct device *dev)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *opp, *temp;
+	int count = 0;
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return;
+
+	mutex_lock(&opp_table->lock);
+	list_for_each_entry_safe(opp, temp, &opp_table->opp_list, node) {
+		if (opp->dynamic) {
+			dev_pm_opp_put_unlocked(opp);
+			count++;
+		}
+	}
+	mutex_unlock(&opp_table->lock);
+
+	/* Drop the references taken by dev_pm_opp_add() */
+	while (count--)
+		dev_pm_opp_put_opp_table(opp_table);
+
+	/* Drop the reference taken by _find_opp_table() */
+	dev_pm_opp_put_opp_table(opp_table);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove_all_dynamic);
+
 struct dev_pm_opp *_opp_allocate(struct opp_table *table)
 {
 	struct dev_pm_opp *opp;
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 0a2a88e5a383..b895f4e79868 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -108,6 +108,7 @@ void dev_pm_opp_put(struct dev_pm_opp *opp);
 int dev_pm_opp_add(struct device *dev, unsigned long freq,
 		   unsigned long u_volt);
 void dev_pm_opp_remove(struct device *dev, unsigned long freq);
+void dev_pm_opp_remove_all_dynamic(struct device *dev);
 
 int dev_pm_opp_enable(struct device *dev, unsigned long freq);
 
@@ -217,6 +218,10 @@ static inline void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 {
 }
 
+static inline void dev_pm_opp_remove_all_dynamic(struct device *dev)
+{
+}
+
 static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq)
 {
 	return 0;