Merge tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These are PM-runtime framework changes to use ktime instead of jiffies
  for accounting, new PM core flag to mark devices that don't need any
  form of power management, cpuidle updates including driver API
  documentation and a new governor, cpufreq updates including a new
  driver for Armada 8K, thermal cleanups and more, some energy-aware
  scheduling (EAS) enabling changes, new chips support in the intel_idle
  and RAPL drivers and assorted cleanups in some other places.

  Specifics:

   - Update the PM-runtime framework to use ktime instead of jiffies for
     accounting (Thara Gopinath, Vincent Guittot)

   - Optimize the autosuspend code in the PM-runtime framework somewhat
     (Ladislav Michl)

   - Add a PM core flag to mark devices that don't need any form of
     power management (Sudeep Holla)

   - Introduce driver API documentation for cpuidle and add a new
     cpuidle governor for tickless systems (Rafael Wysocki)

   - Add Jacobsville support to the intel_idle driver (Zhang Rui)

   - Clean up a cpuidle core header file and the cpuidle-dt and ACPI
     processor-idle drivers (Yangtao Li, Joseph Lo, Yazen Ghannam)

   - Add new cpufreq driver for Armada 8K (Gregory Clement)

   - Fix and clean up cpufreq core (Rafael Wysocki, Viresh Kumar, Amit
     Kucheria)

   - Add support for light-weight tear-down and bring-up of CPUs to the
     cpufreq core and use it in the cpufreq-dt driver (Viresh Kumar)

   - Fix cpu_cooling Kconfig dependencies, add support for CPU cooling
     auto-registration to the cpufreq core and use it in multiple
     cpufreq drivers (Amit Kucheria)

   - Fix some minor issues and do some cleanups in the davinci,
     e_powersaver, ap806, s5pv210, qcom and kryo cpufreq drivers
     (Bartosz Golaszewski, Gustavo Silva, Julia Lawall, Paweł Chmiel,
     Taniya Das, Viresh Kumar)

   - Add a Hisilicon CPPC quirk to the cppc_cpufreq driver (Xiongfeng
     Wang)

   - Clean up the intel_pstate and acpi-cpufreq drivers (Erwan Velu,
     Rafael Wysocki)

   - Clean up multiple cpufreq drivers (Yangtao Li)

   - Update cpufreq-related MAINTAINERS entries (Baruch Siach, Lukas
     Bulwahn)

   - Add support for exposing the Energy Model via debugfs and make
     multiple cpufreq drivers register an Energy Model to support
     energy-aware scheduling (Quentin Perret, Dietmar Eggemann, Matthias
     Kaehlcke)

   - Add Ice Lake mobile and Jacobsville support to the Intel RAPL
     power-capping driver (Gayatri Kammela, Zhang Rui)

   - Add a power estimation helper to the operating performance points
     (OPP) framework and clean up a core function in it (Quentin Perret,
     Viresh Kumar)

   - Make minor improvements in the generic power domains (genpd), OPP
     and system suspend frameworks and in the PM core (Aditya Pakki,
     Douglas Anderson, Greg Kroah-Hartman, Rafael Wysocki, Yangtao Li)"

* tag 'pm-5.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (80 commits)
  cpufreq: kryo: Release OPP tables on module removal
  cpufreq: ap806: add missing of_node_put after of_device_is_available
  cpufreq: acpi-cpufreq: Report if CPU doesn't support boost technologies
  cpufreq: Pass updated policy to driver ->setpolicy() callback
  cpufreq: Fix two debug messages in cpufreq_set_policy()
  cpufreq: Reorder and simplify cpufreq_update_policy()
  cpufreq: Add kerneldoc comments for two core functions
  PM / core: Add support to skip power management in device/driver model
  cpufreq: intel_pstate: Rework iowait boosting to be less aggressive
  cpufreq: intel_pstate: Eliminate intel_pstate_get_base_pstate()
  cpufreq: intel_pstate: Avoid redundant initialization of local vars
  powercap/intel_rapl: add Ice Lake mobile
  ACPI / processor: Set P_LVL{2,3} idle state descriptions
  cpufreq / cppc: Work around for Hisilicon CPPC cpufreq
  ACPI / CPPC: Add a helper to get desired performance
  cpufreq: davinci: move configuration to include/linux/platform_data
  cpufreq: speedstep: convert BUG() to BUG_ON()
  cpufreq: powernv: fix missing check of return value in init_powernv_pstates()
  cpufreq: longhaul: remove unneeded semicolon
  cpufreq: pcc-cpufreq: remove unneeded semicolon
  ..

drivers/base/cpu.c

@@ -427,6 +427,7 @@ __cpu_device_create(struct device *parent, void *drvdata,
 	dev->parent = parent;
 	dev->groups = groups;
 	dev->release = device_create_release;
+	device_set_pm_not_required(dev);
 	dev_set_drvdata(dev, drvdata);
 
 	retval = kobject_set_name_vargs(&dev->kobj, fmt, args);

drivers/base/power/clock_ops.c

@@ -65,10 +65,15 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
 	if (IS_ERR(ce->clk)) {
 		ce->status = PCE_STATUS_ERROR;
 	} else {
-		clk_prepare(ce->clk);
-		ce->status = PCE_STATUS_ACQUIRED;
-		dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n",
-			ce->clk, ce->con_id);
+		if (clk_prepare(ce->clk)) {
+			ce->status = PCE_STATUS_ERROR;
+			dev_err(dev, "clk_prepare() failed\n");
+		} else {
+			ce->status = PCE_STATUS_ACQUIRED;
+			dev_dbg(dev,
+				"Clock %pC con_id %s managed by runtime PM.\n",
+				ce->clk, ce->con_id);
+		}
 	}
 }
 

drivers/base/power/common.c

@@ -160,7 +160,7 @@ EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
  * For a detailed function description, see dev_pm_domain_attach_by_id().
  */
 struct device *dev_pm_domain_attach_by_name(struct device *dev,
-					    char *name)
+					    const char *name)
 {
 	if (dev->pm_domain)
 		return ERR_PTR(-EEXIST);

drivers/base/power/domain.c

@@ -2483,7 +2483,7 @@ EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
  * power-domain-names DT property. For further description see
  * genpd_dev_pm_attach_by_id().
  */
-struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name)
+struct device *genpd_dev_pm_attach_by_name(struct device *dev, const char *name)
 {
 	int index;
 
@@ -2948,18 +2948,11 @@ static int __init genpd_debug_init(void)
 
 	genpd_debugfs_dir = debugfs_create_dir("pm_genpd", NULL);
 
-	if (!genpd_debugfs_dir)
-		return -ENOMEM;
-
-	d = debugfs_create_file("pm_genpd_summary", S_IRUGO,
-			genpd_debugfs_dir, NULL, &summary_fops);
-	if (!d)
-		return -ENOMEM;
+	debugfs_create_file("pm_genpd_summary", S_IRUGO, genpd_debugfs_dir,
+			    NULL, &summary_fops);
 
 	list_for_each_entry(genpd, &gpd_list, gpd_list_node) {
 		d = debugfs_create_dir(genpd->name, genpd_debugfs_dir);
-		if (!d)
-			return -ENOMEM;
 
 		debugfs_create_file("current_state", 0444,
 				d, genpd, &status_fops);

drivers/base/power/main.c

@@ -124,6 +124,10 @@ void device_pm_unlock(void)
  */
 void device_pm_add(struct device *dev)
 {
+	/* Skip PM setup/initialization. */
+	if (device_pm_not_required(dev))
+		return;
+
 	pr_debug("PM: Adding info for %s:%s\n",
 		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
 	device_pm_check_callbacks(dev);
@@ -142,6 +146,9 @@ void device_pm_add(struct device *dev)
  */
 void device_pm_remove(struct device *dev)
 {
+	if (device_pm_not_required(dev))
+		return;
+
 	pr_debug("PM: Removing info for %s:%s\n",
 		 dev->bus ? dev->bus->name : "No Bus", dev_name(dev));
 	complete_all(&dev->power.completion);
@@ -1741,8 +1748,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
 			pm_runtime_disable(dev);
-			if (pm_runtime_status_suspended(dev))
+			if (pm_runtime_status_suspended(dev)) {
+				pm_dev_dbg(dev, state, "direct-complete ");
 				goto Complete;
+			}
 
 			pm_runtime_enable(dev);
 		}

drivers/base/power/runtime.c

@@ -66,20 +66,30 @@ static int rpm_suspend(struct device *dev, int rpmflags);
  */
 void update_pm_runtime_accounting(struct device *dev)
 {
-	unsigned long now = jiffies;
-	unsigned long delta;
-
-	delta = now - dev->power.accounting_timestamp;
-
-	dev->power.accounting_timestamp = now;
+	u64 now, last, delta;
 
 	if (dev->power.disable_depth > 0)
 		return;
 
+	last = dev->power.accounting_timestamp;
+
+	now = ktime_get_mono_fast_ns();
+	dev->power.accounting_timestamp = now;
+
+	/*
+	 * Because ktime_get_mono_fast_ns() is not monotonic during
+	 * timekeeping updates, ensure that 'now' is after the last saved
+	 * timesptamp.
+	 */
+	if (now < last)
+		return;
+
+	delta = now - last;
+
 	if (dev->power.runtime_status == RPM_SUSPENDED)
-		dev->power.suspended_jiffies += delta;
+		dev->power.suspended_time += delta;
 	else
-		dev->power.active_jiffies += delta;
+		dev->power.active_time += delta;
 }
 
 static void __update_runtime_status(struct device *dev, enum rpm_status status)
@@ -88,6 +98,22 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status)
 	dev->power.runtime_status = status;
 }
 
+u64 pm_runtime_suspended_time(struct device *dev)
+{
+	u64 time;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+
+	update_pm_runtime_accounting(dev);
+	time = dev->power.suspended_time;
+
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	return time;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_suspended_time);
+
 /**
  * pm_runtime_deactivate_timer - Deactivate given device's suspend timer.
  * @dev: Device to handle.
@@ -129,24 +155,21 @@ static void pm_runtime_cancel_pending(struct device *dev)
 u64 pm_runtime_autosuspend_expiration(struct device *dev)
 {
 	int autosuspend_delay;
-	u64 last_busy, expires = 0;
-	u64 now = ktime_get_mono_fast_ns();
+	u64 expires;
 
 	if (!dev->power.use_autosuspend)
-		goto out;
+		return 0;
 
 	autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay);
 	if (autosuspend_delay < 0)
-		goto out;
+		return 0;
 
-	last_busy = READ_ONCE(dev->power.last_busy);
+	expires  = READ_ONCE(dev->power.last_busy);
+	expires += (u64)autosuspend_delay * NSEC_PER_MSEC;
+	if (expires > ktime_get_mono_fast_ns())
+		return expires;	/* Expires in the future */
 
-	expires = last_busy + (u64)autosuspend_delay * NSEC_PER_MSEC;
-	if (expires <= now)
-		expires = 0;	/* Already expired. */
-
- out:
-	return expires;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration);
 
@@ -1276,6 +1299,9 @@ void __pm_runtime_disable(struct device *dev, bool check_resume)
 		pm_runtime_put_noidle(dev);
 	}
 
+	/* Update time accounting before disabling PM-runtime. */
+	update_pm_runtime_accounting(dev);
+
 	if (!dev->power.disable_depth++)
 		__pm_runtime_barrier(dev);
 
@@ -1294,10 +1320,15 @@ void pm_runtime_enable(struct device *dev)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	if (dev->power.disable_depth > 0)
+	if (dev->power.disable_depth > 0) {
 		dev->power.disable_depth--;
-	else
+
+		/* About to enable runtime pm, set accounting_timestamp to now */
+		if (!dev->power.disable_depth)
+			dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
+	} else {
 		dev_warn(dev, "Unbalanced %s!\n", __func__);
+	}
 
 	WARN(!dev->power.disable_depth &&
 	     dev->power.runtime_status == RPM_SUSPENDED &&
@@ -1494,7 +1525,6 @@ void pm_runtime_init(struct device *dev)
 	dev->power.request_pending = false;
 	dev->power.request = RPM_REQ_NONE;
 	dev->power.deferred_resume = false;
-	dev->power.accounting_timestamp = jiffies;
 	INIT_WORK(&dev->power.work, pm_runtime_work);
 
 	dev->power.timer_expires = 0;

drivers/base/power/sysfs.c

@@ -125,9 +125,12 @@ static ssize_t runtime_active_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
+	u64 tmp;
 	spin_lock_irq(&dev->power.lock);
 	update_pm_runtime_accounting(dev);
-	ret = sprintf(buf, "%i\n", jiffies_to_msecs(dev->power.active_jiffies));
+	tmp = dev->power.active_time;
+	do_div(tmp, NSEC_PER_MSEC);
+	ret = sprintf(buf, "%llu\n", tmp);
 	spin_unlock_irq(&dev->power.lock);
 	return ret;
 }
@@ -138,10 +141,12 @@ static ssize_t runtime_suspended_time_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int ret;
+	u64 tmp;
 	spin_lock_irq(&dev->power.lock);
 	update_pm_runtime_accounting(dev);
-	ret = sprintf(buf, "%i\n",
-		jiffies_to_msecs(dev->power.suspended_jiffies));
+	tmp = dev->power.suspended_time;
+	do_div(tmp, NSEC_PER_MSEC);
+	ret = sprintf(buf, "%llu\n", tmp);
 	spin_unlock_irq(&dev->power.lock);
 	return ret;
 }
@@ -648,6 +653,10 @@ int dpm_sysfs_add(struct device *dev)
 {
 	int rc;
 
+	/* No need to create PM sysfs if explicitly disabled. */
+	if (device_pm_not_required(dev))
+		return 0;
+
 	rc = sysfs_create_group(&dev->kobj, &pm_attr_group);
 	if (rc)
 		return rc;
@@ -727,6 +736,8 @@ void rpm_sysfs_remove(struct device *dev)
 
 void dpm_sysfs_remove(struct device *dev)
 {
+	if (device_pm_not_required(dev))
+		return;
 	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
 	dev_pm_qos_constraints_destroy(dev);
 	rpm_sysfs_remove(dev);

drivers/base/power/wakeup.c

@@ -783,7 +783,7 @@ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard)
 EXPORT_SYMBOL_GPL(pm_wakeup_ws_event);
 
 /**
- * pm_wakeup_event - Notify the PM core of a wakeup event.
+ * pm_wakeup_dev_event - Notify the PM core of a wakeup event.
  * @dev: Device the wakeup event is related to.
  * @msec: Anticipated event processing time (in milliseconds).
  * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.