Merge tag 'pm-5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add hybrid processors support to the intel_pstate driver and
  make it work with more processor models when HWP is disabled, make the
  intel_idle driver use special C6 idle state paremeters when package
  C-states are disabled, add cooling support to the tegra30 devfreq
  driver, rework the TEO (timer events oriented) cpuidle governor,
  extend the OPP (operating performance points) framework to use the
  required-opps DT property in more cases, fix some issues and clean up
  a number of assorted pieces of code.

  Specifics:

   - Make intel_pstate support hybrid processors using abstract
     performance units in the HWP interface (Rafael Wysocki).

   - Add Icelake servers and Cometlake support in no-HWP mode to
     intel_pstate (Giovanni Gherdovich).

   - Make cpufreq_online() error path be consistent with the CPU device
     removal path in cpufreq (Rafael Wysocki).

   - Clean up 3 cpufreq drivers and the statistics code (Hailong Liu,
     Randy Dunlap, Shaokun Zhang).

   - Make intel_idle use special idle state parameters for C6 when
     package C-states are disabled (Chen Yu).

   - Rework the TEO (timer events oriented) cpuidle governor to address
     some theoretical shortcomings in it (Rafael Wysocki).

   - Drop unneeded semicolon from the TEO governor (Wan Jiabing).

   - Modify the runtime PM framework to accept unassigned suspend and
     resume callback pointers (Ulf Hansson).

   - Improve pm_runtime_get_sync() documentation (Krzysztof Kozlowski).

   - Improve device performance states support in the generic power
     domains (genpd) framework (Ulf Hansson).

   - Fix some documentation issues in genpd (Yang Yingliang).

   - Make the operating performance points (OPP) framework use the
     required-opps DT property in use cases that are not related to
     genpd (Hsin-Yi Wang).

   - Make lazy_link_required_opp_table() use list_del_init instead of
     list_del/INIT_LIST_HEAD (Yang Yingliang).

   - Simplify wake IRQs handling in the core system-wide sleep support
     code and clean up some coding style inconsistencies in it (Tian
     Tao, Zhen Lei).

   - Add cooling support to the tegra30 devfreq driver and improve its
     DT bindings (Dmitry Osipenko).

   - Fix some assorted issues in the devfreq core and drivers (Chanwoo
     Choi, Dong Aisheng, YueHaibing)"

* tag 'pm-5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (39 commits)
  PM / devfreq: passive: Fix get_target_freq when not using required-opp
  cpufreq: Make cpufreq_online() call driver->offline() on errors
  opp: Allow required-opps to be used for non genpd use cases
  cpuidle: teo: remove unneeded semicolon in teo_select()
  dt-bindings: devfreq: tegra30-actmon: Add cooling-cells
  dt-bindings: devfreq: tegra30-actmon: Convert to schema
  PM / devfreq: userspace: Use DEVICE_ATTR_RW macro
  PM: runtime: Clarify documentation when callbacks are unassigned
  PM: runtime: Allow unassigned ->runtime_suspend|resume callbacks
  PM: runtime: Improve path in rpm_idle() when no callback
  PM: hibernate: remove leading spaces before tabs
  PM: sleep: remove trailing spaces and tabs
  PM: domains: Drop/restore performance state votes for devices at runtime PM
  PM: domains: Return early if perf state is already set for the device
  PM: domains: Split code in dev_pm_genpd_set_performance_state()
  cpuidle: teo: Use kerneldoc documentation in admin-guide
  cpuidle: teo: Rework most recent idle duration values treatment
  cpuidle: teo: Change the main idle state selection logic
  cpuidle: teo: Cosmetic modification of teo_select()
  cpuidle: teo: Cosmetic modifications of teo_update()
  ...

4 files changed, 60 insertions, 27 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index b6a782c31613..ab0b740cc0f1 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -379,6 +379,44 @@ err:
 	return ret;
 }
 
+static int genpd_set_performance_state(struct device *dev, unsigned int state)
+{
+	struct generic_pm_domain *genpd = dev_to_genpd(dev);
+	struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev);
+	unsigned int prev_state;
+	int ret;
+
+	prev_state = gpd_data->performance_state;
+	if (prev_state == state)
+		return 0;
+
+	gpd_data->performance_state = state;
+	state = _genpd_reeval_performance_state(genpd, state);
+
+	ret = _genpd_set_performance_state(genpd, state, 0);
+	if (ret)
+		gpd_data->performance_state = prev_state;
+
+	return ret;
+}
+
+static int genpd_drop_performance_state(struct device *dev)
+{
+	unsigned int prev_state = dev_gpd_data(dev)->performance_state;
+
+	if (!genpd_set_performance_state(dev, 0))
+		return prev_state;
+
+	return 0;
+}
+
+static void genpd_restore_performance_state(struct device *dev,
+					    unsigned int state)
+{
+	if (state)
+		genpd_set_performance_state(dev, state);
+}
+
 /**
  * dev_pm_genpd_set_performance_state- Set performance state of device's power
  * domain.
@@ -397,8 +435,6 @@ err:
 int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 {
 	struct generic_pm_domain *genpd;
-	struct generic_pm_domain_data *gpd_data;
-	unsigned int prev;
 	int ret;
 
 	genpd = dev_to_genpd_safe(dev);
@@ -410,16 +446,7 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 		return -EINVAL;
 
 	genpd_lock(genpd);
-
-	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	prev = gpd_data->performance_state;
-	gpd_data->performance_state = state;
-
-	state = _genpd_reeval_performance_state(genpd, state);
-	ret = _genpd_set_performance_state(genpd, state, 0);
-	if (ret)
-		gpd_data->performance_state = prev;
-
+	ret = genpd_set_performance_state(dev, state);
 	genpd_unlock(genpd);
 
 	return ret;
@@ -572,6 +599,7 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
  * RPM status of the releated device is in an intermediate state, not yet turned
  * into RPM_SUSPENDED. This means genpd_power_off() must allow one device to not
  * be RPM_SUSPENDED, while it tries to power off the PM domain.
+ * @depth: nesting count for lockdep.
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
  * have been powered down, remove power from @genpd.
@@ -832,7 +860,8 @@ static int genpd_runtime_suspend(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
 	bool (*suspend_ok)(struct device *__dev);
-	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev);
+	struct gpd_timing_data *td = &gpd_data->td;
 	bool runtime_pm = pm_runtime_enabled(dev);
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -889,6 +918,7 @@ static int genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	genpd_lock(genpd);
+	gpd_data->rpm_pstate = genpd_drop_performance_state(dev);
 	genpd_power_off(genpd, true, 0);
 	genpd_unlock(genpd);
 
@@ -906,7 +936,8 @@ static int genpd_runtime_suspend(struct device *dev)
 static int genpd_runtime_resume(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
+	struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev);
+	struct gpd_timing_data *td = &gpd_data->td;
 	bool runtime_pm = pm_runtime_enabled(dev);
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -930,6 +961,8 @@ static int genpd_runtime_resume(struct device *dev)
 
 	genpd_lock(genpd);
 	ret = genpd_power_on(genpd, 0);
+	if (!ret)
+		genpd_restore_performance_state(dev, gpd_data->rpm_pstate);
 	genpd_unlock(genpd);
 
 	if (ret)
@@ -968,6 +1001,7 @@ err_stop:
 err_poweroff:
 	if (!pm_runtime_is_irq_safe(dev) || genpd_is_irq_safe(genpd)) {
 		genpd_lock(genpd);
+		gpd_data->rpm_pstate = genpd_drop_performance_state(dev);
 		genpd_power_off(genpd, true, 0);
 		genpd_unlock(genpd);
 	}
@@ -2505,7 +2539,7 @@ EXPORT_SYMBOL_GPL(of_genpd_remove_subdomain);
 
 /**
  * of_genpd_remove_last - Remove the last PM domain registered for a provider
- * @provider: Pointer to device structure associated with provider
+ * @np: Pointer to device node associated with provider
  *
  * Find the last PM domain that was added by a particular provider and
  * remove this PM domain from the list of PM domains. The provider is
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index c6c218758f0b..cd08c5885190 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -252,6 +252,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 /**
  * _default_power_down_ok - Default generic PM domain power off governor routine.
  * @pd: PM domain to check.
+ * @now: current ktime.
  *
  * This routine must be executed under the PM domain's lock.
  */
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index b570848d23e0..8a66eaf731e4 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -345,7 +345,7 @@ static void rpm_suspend_suppliers(struct device *dev)
 static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 	__releases(&dev->power.lock) __acquires(&dev->power.lock)
 {
-	int retval, idx;
+	int retval = 0, idx;
 	bool use_links = dev->power.links_count > 0;
 
 	if (dev->power.irq_safe) {
@@ -373,7 +373,8 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 		}
 	}
 
-	retval = cb(dev);
+	if (cb)
+		retval = cb(dev);
 
 	if (dev->power.irq_safe) {
 		spin_lock(&dev->power.lock);
@@ -446,7 +447,10 @@ static int rpm_idle(struct device *dev, int rpmflags)
 	/* Pending requests need to be canceled. */
 	dev->power.request = RPM_REQ_NONE;
 
-	if (dev->power.no_callbacks)
+	callback = RPM_GET_CALLBACK(dev, runtime_idle);
+
+	/* If no callback assume success. */
+	if (!callback || dev->power.no_callbacks)
 		goto out;
 
 	/* Carry out an asynchronous or a synchronous idle notification. */
@@ -462,10 +466,7 @@ static int rpm_idle(struct device *dev, int rpmflags)
 
 	dev->power.idle_notification = true;
 
-	callback = RPM_GET_CALLBACK(dev, runtime_idle);
-
-	if (callback)
-		retval = __rpm_callback(callback, dev);
+	retval = __rpm_callback(callback, dev);
 
 	dev->power.idle_notification = false;
 	wake_up_all(&dev->power.wait_queue);
@@ -484,9 +485,6 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev)
 {
 	int retval;
 
-	if (!cb)
-		return -ENOSYS;
-
 	if (dev->power.memalloc_noio) {
 		unsigned int noio_flag;
 
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 8e021082dba8..3bad3266a2ad 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -182,7 +182,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 
 	wirq->dev = dev;
 	wirq->irq = irq;
-	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 
 	/* Prevent deferred spurious wakeirqs with disable_irq_nosync() */
 	irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY);
@@ -192,7 +191,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	 * so we use a threaded irq.
 	 */
 	err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq,
-				   IRQF_ONESHOT, wirq->name, wirq);
+				   IRQF_ONESHOT | IRQF_NO_AUTOEN,
+				   wirq->name, wirq);
 	if (err)
 		goto err_free_name;