Merge tag 'pm-4.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "Again, cpufreq gets more changes than the other parts this time (one
  new driver, one old driver less, a bunch of enhancements of the
  existing code, new CPU IDs, fixes, cleanups)

  There also are some changes in cpuidle (idle injection rework, a
  couple of new CPU IDs, online/offline rework in intel_idle, fixes and
  cleanups), in the generic power domains framework (mostly related to
  supporting power domains containing CPUs), and in the Operating
  Performance Points (OPP) library (mostly related to supporting devices
  with multiple voltage regulators)

  In addition to that, the system sleep state selection interface is
  modified to make it easier for distributions with unchanged user space
  to support suspend-to-idle as the default system suspend method, some
  issues are fixed in the PM core, the latency tolerance PM QoS
  framework is improved a bit, the Intel RAPL power capping driver is
  cleaned up and there are some fixes and cleanups in the devfreq
  subsystem

  Specifics:

   - New cpufreq driver for Broadcom STB SoCs and a Device Tree binding
     for it (Markus Mayer)

   - Support for ARM Integrator/AP and Integrator/CP in the generic DT
     cpufreq driver and elimination of the old Integrator cpufreq driver
     (Linus Walleij)

   - Support for the zx296718, r8a7743 and r8a7745, Socionext UniPhier,
     and PXA SoCs in the the generic DT cpufreq driver (Baoyou Xie,
     Geert Uytterhoeven, Masahiro Yamada, Robert Jarzmik)

   - cpufreq core fix to eliminate races that may lead to using inactive
     policy objects and related cleanups (Rafael Wysocki)

   - cpufreq schedutil governor update to make it use SCHED_FIFO kernel
     threads (instead of regular workqueues) for doing delayed work (to
     reduce the response latency in some cases) and related cleanups
     (Viresh Kumar)

   - New cpufreq sysfs attribute for resetting statistics (Markus Mayer)

   - cpufreq governors fixes and cleanups (Chen Yu, Stratos Karafotis,
     Viresh Kumar)

   - Support for using generic cpufreq governors in the intel_pstate
     driver (Rafael Wysocki)

   - Support for per-logical-CPU P-state limits and the EPP/EPB (Energy
     Performance Preference/Energy Performance Bias) knobs in the
     intel_pstate driver (Srinivas Pandruvada)

   - New CPU ID for Knights Mill in intel_pstate (Piotr Luc)

   - intel_pstate driver modification to use the P-state selection
     algorithm based on CPU load on platforms with the system profile in
     the ACPI tables set to "mobile" (Srinivas Pandruvada)

   - intel_pstate driver cleanups (Arnd Bergmann, Rafael Wysocki,
     Srinivas Pandruvada)

   - cpufreq powernv driver updates including fast switching support
     (for the schedutil governor), fixes and cleanus (Akshay Adiga,
     Andrew Donnellan, Denis Kirjanov)

   - acpi-cpufreq driver rework to switch it over to the new CPU
     offline/online state machine (Sebastian Andrzej Siewior)

   - Assorted cleanups in cpufreq drivers (Wei Yongjun, Prashanth
     Prakash)

   - Idle injection rework (to make it use the regular idle path instead
     of a home-grown custom one) and related powerclamp thermal driver
     updates (Peter Zijlstra, Jacob Pan, Petr Mladek, Sebastian Andrzej
     Siewior)

   - New CPU IDs for Atom Z34xx and Knights Mill in intel_idle (Andy
     Shevchenko, Piotr Luc)

   - intel_idle driver cleanups and switch over to using the new CPU
     offline/online state machine (Anna-Maria Gleixner, Sebastian
     Andrzej Siewior)

   - cpuidle DT driver update to support suspend-to-idle properly
     (Sudeep Holla)

   - cpuidle core cleanups and misc updates (Daniel Lezcano, Pan Bian,
     Rafael Wysocki)

   - Preliminary support for power domains including CPUs in the generic
     power domains (genpd) framework and related DT bindings (Lina Iyer)

   - Assorted fixes and cleanups in the generic power domains (genpd)
     framework (Colin Ian King, Dan Carpenter, Geert Uytterhoeven)

   - Preliminary support for devices with multiple voltage regulators
     and related fixes and cleanups in the Operating Performance Points
     (OPP) library (Viresh Kumar, Masahiro Yamada, Stephen Boyd)

   - System sleep state selection interface rework to make it easier to
     support suspend-to-idle as the default system suspend method
     (Rafael Wysocki)

   - PM core fixes and cleanups, mostly related to the interactions
     between the system suspend and runtime PM frameworks (Ulf Hansson,
     Sahitya Tummala, Tony Lindgren)

   - Latency tolerance PM QoS framework imorovements (Andrew Lutomirski)

   - New Knights Mill CPU ID for the Intel RAPL power capping driver
     (Piotr Luc)

   - Intel RAPL power capping driver fixes, cleanups and switch over to
     using the new CPU offline/online state machine (Jacob Pan, Thomas
     Gleixner, Sebastian Andrzej Siewior)

   - Fixes and cleanups in the exynos-ppmu, exynos-nocp, rk3399_dmc,
     rockchip-dfi devfreq drivers and the devfreq core (Axel Lin,
     Chanwoo Choi, Javier Martinez Canillas, MyungJoo Ham, Viresh Kumar)

   - Fix for false-positive KASAN warnings during resume from ACPI S3
     (suspend-to-RAM) on x86 (Josh Poimboeuf)

   - Memory map verification during resume from hibernation on x86 to
     ensure a consistent address space layout (Chen Yu)

   - Wakeup sources debugging enhancement (Xing Wei)

   - rockchip-io AVS driver cleanup (Shawn Lin)"

* tag 'pm-4.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (127 commits)
  devfreq: rk3399_dmc: Don't use OPP structures outside of RCU locks
  devfreq: rk3399_dmc: Remove dangling rcu_read_unlock()
  devfreq: exynos: Don't use OPP structures outside of RCU locks
  Documentation: intel_pstate: Document HWP energy/performance hints
  cpufreq: intel_pstate: Support for energy performance hints with HWP
  cpufreq: intel_pstate: Add locking around HWP requests
  PM / sleep: Print active wakeup sources when blocking on wakeup_count reads
  PM / core: Fix bug in the error handling of async suspend
  PM / wakeirq: Fix dedicated wakeirq for drivers not using autosuspend
  PM / Domains: Fix compatible for domain idle state
  PM / OPP: Don't WARN on multiple calls to dev_pm_opp_set_regulators()
  PM / OPP: Allow platform specific custom set_opp() callbacks
  PM / OPP: Separate out _generic_set_opp()
  PM / OPP: Add infrastructure to manage multiple regulators
  PM / OPP: Pass struct dev_pm_opp_supply to _set_opp_voltage()
  PM / OPP: Manage supply's voltage/current in a separate structure
  PM / OPP: Don't use OPP structure outside of rcu protected section
  PM / OPP: Reword binding supporting multiple regulators per device
  PM / OPP: Fix incorrect cpu-supply property in binding
  cpuidle: Add a kerneldoc comment to cpuidle_use_deepest_state()
  ..

12 files changed, 977 insertions, 270 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e023066e4215..5711708532db 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -39,6 +39,105 @@
 static LIST_HEAD(gpd_list);
 static DEFINE_MUTEX(gpd_list_lock);
 
+struct genpd_lock_ops {
+	void (*lock)(struct generic_pm_domain *genpd);
+	void (*lock_nested)(struct generic_pm_domain *genpd, int depth);
+	int (*lock_interruptible)(struct generic_pm_domain *genpd);
+	void (*unlock)(struct generic_pm_domain *genpd);
+};
+
+static void genpd_lock_mtx(struct generic_pm_domain *genpd)
+{
+	mutex_lock(&genpd->mlock);
+}
+
+static void genpd_lock_nested_mtx(struct generic_pm_domain *genpd,
+					int depth)
+{
+	mutex_lock_nested(&genpd->mlock, depth);
+}
+
+static int genpd_lock_interruptible_mtx(struct generic_pm_domain *genpd)
+{
+	return mutex_lock_interruptible(&genpd->mlock);
+}
+
+static void genpd_unlock_mtx(struct generic_pm_domain *genpd)
+{
+	return mutex_unlock(&genpd->mlock);
+}
+
+static const struct genpd_lock_ops genpd_mtx_ops = {
+	.lock = genpd_lock_mtx,
+	.lock_nested = genpd_lock_nested_mtx,
+	.lock_interruptible = genpd_lock_interruptible_mtx,
+	.unlock = genpd_unlock_mtx,
+};
+
+static void genpd_lock_spin(struct generic_pm_domain *genpd)
+	__acquires(&genpd->slock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&genpd->slock, flags);
+	genpd->lock_flags = flags;
+}
+
+static void genpd_lock_nested_spin(struct generic_pm_domain *genpd,
+					int depth)
+	__acquires(&genpd->slock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave_nested(&genpd->slock, flags, depth);
+	genpd->lock_flags = flags;
+}
+
+static int genpd_lock_interruptible_spin(struct generic_pm_domain *genpd)
+	__acquires(&genpd->slock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&genpd->slock, flags);
+	genpd->lock_flags = flags;
+	return 0;
+}
+
+static void genpd_unlock_spin(struct generic_pm_domain *genpd)
+	__releases(&genpd->slock)
+{
+	spin_unlock_irqrestore(&genpd->slock, genpd->lock_flags);
+}
+
+static const struct genpd_lock_ops genpd_spin_ops = {
+	.lock = genpd_lock_spin,
+	.lock_nested = genpd_lock_nested_spin,
+	.lock_interruptible = genpd_lock_interruptible_spin,
+	.unlock = genpd_unlock_spin,
+};
+
+#define genpd_lock(p)			p->lock_ops->lock(p)
+#define genpd_lock_nested(p, d)		p->lock_ops->lock_nested(p, d)
+#define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
+#define genpd_unlock(p)			p->lock_ops->unlock(p)
+
+#define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
+
+static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
+		struct generic_pm_domain *genpd)
+{
+	bool ret;
+
+	ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
+
+	/* Warn once for each IRQ safe dev in no sleep domain */
+	if (ret)
+		dev_warn_once(dev, "PM domain %s will not be powered off\n",
+				genpd->name);
+
+	return ret;
+}
+
 /*
  * Get the generic PM domain for a particular struct device.
  * This validates the struct device pointer, the PM domain pointer,
@@ -200,9 +299,9 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 
 		genpd_sd_counter_inc(master);
 
-		mutex_lock_nested(&master->lock, depth + 1);
+		genpd_lock_nested(master, depth + 1);
 		ret = genpd_poweron(master, depth + 1);
-		mutex_unlock(&master->lock);
+		genpd_unlock(master);
 
 		if (ret) {
 			genpd_sd_counter_dec(master);
@@ -255,9 +354,9 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 		spin_unlock_irq(&dev->power.lock);
 
 		if (!IS_ERR(genpd)) {
-			mutex_lock(&genpd->lock);
+			genpd_lock(genpd);
 			genpd->max_off_time_changed = true;
-			mutex_unlock(&genpd->lock);
+			genpd_unlock(genpd);
 		}
 
 		dev = dev->parent;
@@ -303,7 +402,12 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
 		if (stat > PM_QOS_FLAGS_NONE)
 			return -EBUSY;
 
-		if (!pm_runtime_suspended(pdd->dev) || pdd->dev->power.irq_safe)
+		/*
+		 * Do not allow PM domain to be powered off, when an IRQ safe
+		 * device is part of a non-IRQ safe domain.
+		 */
+		if (!pm_runtime_suspended(pdd->dev) ||
+			irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd))
 			not_suspended++;
 	}
 
@@ -354,9 +458,9 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 	genpd_poweroff(genpd, true);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 }
 
 /**
@@ -466,15 +570,15 @@ static int genpd_runtime_suspend(struct device *dev)
 	}
 
 	/*
-	 * If power.irq_safe is set, this routine will be run with interrupts
-	 * off, so it can't use mutexes.
+	 * If power.irq_safe is set, this routine may be run with
+	 * IRQs disabled, so suspend only if the PM domain also is irq_safe.
 	 */
-	if (dev->power.irq_safe)
+	if (irq_safe_dev_in_no_sleep_domain(dev, genpd))
 		return 0;
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 	genpd_poweroff(genpd, false);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	return 0;
 }
@@ -503,15 +607,18 @@ static int genpd_runtime_resume(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	/* If power.irq_safe, the PM domain is never powered off. */
-	if (dev->power.irq_safe) {
+	/*
+	 * As we don't power off a non IRQ safe domain, which holds
+	 * an IRQ safe device, we don't need to restore power to it.
+	 */
+	if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) {
 		timed = false;
 		goto out;
 	}
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 	ret = genpd_poweron(genpd, 0);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	if (ret)
 		return ret;
@@ -546,10 +653,11 @@ static int genpd_runtime_resume(struct device *dev)
 err_stop:
 	genpd_stop_dev(genpd, dev);
 err_poweroff:
-	if (!dev->power.irq_safe) {
-		mutex_lock(&genpd->lock);
+	if (!pm_runtime_is_irq_safe(dev) ||
+		(pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) {
+		genpd_lock(genpd);
 		genpd_poweroff(genpd, 0);
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 	}
 
 	return ret;
@@ -732,20 +840,20 @@ static int pm_genpd_prepare(struct device *dev)
 	if (resume_needed(dev, genpd))
 		pm_runtime_resume(dev);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->prepared_count++ == 0)
 		genpd->suspended_count = 0;
 
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	ret = pm_generic_prepare(dev);
 	if (ret) {
-		mutex_lock(&genpd->lock);
+		genpd_lock(genpd);
 
 		genpd->prepared_count--;
 
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 	}
 
 	return ret;
@@ -936,13 +1044,13 @@ static void pm_genpd_complete(struct device *dev)
 
 	pm_generic_complete(dev);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	genpd->prepared_count--;
 	if (!genpd->prepared_count)
 		genpd_queue_power_off_work(genpd);
 
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 }
 
 /**
@@ -1071,7 +1179,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1088,7 +1196,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
  out:
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	if (ret)
 		genpd_free_dev_data(dev, gpd_data);
@@ -1130,7 +1238,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 	gpd_data = to_gpd_data(pdd);
 	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1145,14 +1253,14 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 
 	list_del_init(&pdd->list_node);
 
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	genpd_free_dev_data(dev, gpd_data);
 
 	return 0;
 
  out:
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
@@ -1183,12 +1291,23 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 	    || genpd == subdomain)
 		return -EINVAL;
 
+	/*
+	 * If the domain can be powered on/off in an IRQ safe
+	 * context, ensure that the subdomain can also be
+	 * powered on/off in that context.
+	 */
+	if (!genpd_is_irq_safe(genpd) && genpd_is_irq_safe(subdomain)) {
+		WARN(1, "Parent %s of subdomain %s must be IRQ safe\n",
+				genpd->name, subdomain->name);
+		return -EINVAL;
+	}
+
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link)
 		return -ENOMEM;
 
-	mutex_lock(&subdomain->lock);
-	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
+	genpd_lock(subdomain);
+	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
 	if (genpd->status == GPD_STATE_POWER_OFF
 	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
@@ -1211,8 +1330,8 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 		genpd_sd_counter_inc(genpd);
 
  out:
-	mutex_unlock(&genpd->lock);
-	mutex_unlock(&subdomain->lock);
+	genpd_unlock(genpd);
+	genpd_unlock(subdomain);
 	if (ret)
 		kfree(link);
 	return ret;
@@ -1250,8 +1369,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
 		return -EINVAL;
 
-	mutex_lock(&subdomain->lock);
-	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
+	genpd_lock(subdomain);
+	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
 	if (!list_empty(&subdomain->master_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n", genpd->name,
@@ -1275,13 +1394,39 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	}
 
 out:
-	mutex_unlock(&genpd->lock);
-	mutex_unlock(&subdomain->lock);
+	genpd_unlock(genpd);
+	genpd_unlock(subdomain);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 
+static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
+{
+	struct genpd_power_state *state;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	genpd->states = state;
+	genpd->state_count = 1;
+	genpd->free = state;
+
+	return 0;
+}
+
+static void genpd_lock_init(struct generic_pm_domain *genpd)
+{
+	if (genpd->flags & GENPD_FLAG_IRQ_SAFE) {
+		spin_lock_init(&genpd->slock);
+		genpd->lock_ops = &genpd_spin_ops;
+	} else {
+		mutex_init(&genpd->mlock);
+		genpd->lock_ops = &genpd_mtx_ops;
+	}
+}
+
 /**
  * pm_genpd_init - Initialize a generic I/O PM domain object.
  * @genpd: PM domain object to initialize.
@@ -1293,13 +1438,15 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 int pm_genpd_init(struct generic_pm_domain *genpd,
 		  struct dev_power_governor *gov, bool is_off)
 {
+	int ret;
+
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&genpd->master_links);
 	INIT_LIST_HEAD(&genpd->slave_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
-	mutex_init(&genpd->lock);
+	genpd_lock_init(genpd);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
@@ -1325,19 +1472,12 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 		genpd->dev_ops.start = pm_clk_resume;
 	}
 
-	if (genpd->state_idx >= GENPD_MAX_NUM_STATES) {
-		pr_warn("Initial state index out of bounds.\n");
-		genpd->state_idx = GENPD_MAX_NUM_STATES - 1;
-	}
-
-	if (genpd->state_count > GENPD_MAX_NUM_STATES) {
-		pr_warn("Limiting states to  %d\n", GENPD_MAX_NUM_STATES);
-		genpd->state_count = GENPD_MAX_NUM_STATES;
-	}
-
 	/* Use only one "off" state if there were no states declared */
-	if (genpd->state_count == 0)
-		genpd->state_count = 1;
+	if (genpd->state_count == 0) {
+		ret = genpd_set_default_power_state(genpd);
+		if (ret)
+			return ret;
+	}
 
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
@@ -1354,16 +1494,16 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->has_provider) {
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 		pr_err("Provider present, unable to remove %s\n", genpd->name);
 		return -EBUSY;
 	}
 
 	if (!list_empty(&genpd->master_links) || genpd->device_count) {
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 		pr_err("%s: unable to remove %s\n", __func__, genpd->name);
 		return -EBUSY;
 	}
@@ -1375,8 +1515,9 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	}
 
 	list_del(&genpd->gpd_list_node);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 	cancel_work_sync(&genpd->power_off_work);
+	kfree(genpd->free);
 	pr_debug("%s: removed %s\n", __func__, genpd->name);
 
 	return 0;
@@ -1890,21 +2031,117 @@ int genpd_dev_pm_attach(struct device *dev)
 	mutex_unlock(&gpd_list_lock);
 
 	if (ret < 0) {
-		dev_err(dev, "failed to add to PM domain %s: %d",
-			pd->name, ret);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to add to PM domain %s: %d",
+				pd->name, ret);
 		goto out;
 	}
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
 
-	mutex_lock(&pd->lock);
+	genpd_lock(pd);
 	ret = genpd_poweron(pd, 0);
-	mutex_unlock(&pd->lock);
+	genpd_unlock(pd);
 out:
 	return ret ? -EPROBE_DEFER : 0;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+
+static const struct of_device_id idle_state_match[] = {
+	{ .compatible = "domain-idle-state", },
+	{ }
+};
+
+static int genpd_parse_state(struct genpd_power_state *genpd_state,
+				    struct device_node *state_node)
+{
+	int err;
+	u32 residency;
+	u32 entry_latency, exit_latency;
+	const struct of_device_id *match_id;
+
+	match_id = of_match_node(idle_state_match, state_node);
+	if (!match_id)
+		return -EINVAL;
+
+	err = of_property_read_u32(state_node, "entry-latency-us",
+						&entry_latency);
+	if (err) {
+		pr_debug(" * %s missing entry-latency-us property\n",
+						state_node->full_name);
+		return -EINVAL;
+	}
+
+	err = of_property_read_u32(state_node, "exit-latency-us",
+						&exit_latency);
+	if (err) {
+		pr_debug(" * %s missing exit-latency-us property\n",
+						state_node->full_name);
+		return -EINVAL;
+	}
+
+	err = of_property_read_u32(state_node, "min-residency-us", &residency);
+	if (!err)
+		genpd_state->residency_ns = 1000 * residency;
+
+	genpd_state->power_on_latency_ns = 1000 * exit_latency;
+	genpd_state->power_off_latency_ns = 1000 * entry_latency;
+	genpd_state->fwnode = &state_node->fwnode;
+
+	return 0;
+}
+
+/**
+ * of_genpd_parse_idle_states: Return array of idle states for the genpd.
+ *
+ * @dn: The genpd device node
+ * @states: The pointer to which the state array will be saved.
+ * @n: The count of elements in the array returned from this function.
+ *
+ * Returns the device states parsed from the OF node. The memory for the states
+ * is allocated by this function and is the responsibility of the caller to
+ * free the memory after use.
+ */
+int of_genpd_parse_idle_states(struct device_node *dn,
+			struct genpd_power_state **states, int *n)
+{
+	struct genpd_power_state *st;
+	struct device_node *np;
+	int i = 0;
+	int err, ret;
+	int count;
+	struct of_phandle_iterator it;
+
+	count = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
+	if (count <= 0)
+		return -EINVAL;
+
+	st = kcalloc(count, sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return -ENOMEM;
+
+	/* Loop over the phandles until all the requested entry is found */
+	of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) {
+		np = it.node;
+		ret = genpd_parse_state(&st[i++], np);
+		if (ret) {
+			pr_err
+			("Parsing idle state node %s failed with err %d\n",
+							np->full_name, ret);
+			of_node_put(np);
+			kfree(st);
+			return ret;
+		}
+	}
+
+	*n = count;
+	*states = st;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
+
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 
@@ -1958,7 +2195,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 	char state[16];
 	int ret;
 
-	ret = mutex_lock_interruptible(&genpd->lock);
+	ret = genpd_lock_interruptible(genpd);
 	if (ret)
 		return -ERESTARTSYS;
 
@@ -1984,7 +2221,9 @@ static int pm_genpd_summary_one(struct seq_file *s,
 	}
 
 	list_for_each_entry(pm_data, &genpd->dev_list, list_node) {
-		kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL);
+		kobj_path = kobject_get_path(&pm_data->dev->kobj,
+				genpd_is_irq_safe(genpd) ?
+				GFP_ATOMIC : GFP_KERNEL);
 		if (kobj_path == NULL)
 			continue;
 
@@ -1995,7 +2234,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	seq_puts(s, "\n");
 exit:
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	return 0;
 }
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 2932a5bd892f..eb474c882ebe 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1460,10 +1460,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	dpm_watchdog_clear(&wd);
 
  Complete:
-	complete_all(&dev->power.completion);
 	if (error)
 		async_error = error;
 
+	complete_all(&dev->power.completion);
 	TRACE_SUSPEND(error);
 	return error;
 }
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 4c7c6da7a989..35ff06283738 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -93,6 +93,8 @@ struct opp_table *_find_opp_table(struct device *dev)
  * Return: voltage in micro volt corresponding to the opp, else
  * return 0
  *
+ * This is useful only for devices with single power supply.
+ *
  * Locking: This function must be called under rcu_read_lock(). opp is a rcu
  * protected pointer. This means that opp which could have been fetched by
  * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
@@ -112,7 +114,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	if (IS_ERR_OR_NULL(tmp_opp))
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
-		v = tmp_opp->u_volt;
+		v = tmp_opp->supplies[0].u_volt;
 
 	return v;
 }
@@ -210,6 +212,24 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
 
+static int _get_regulator_count(struct device *dev)
+{
+	struct opp_table *opp_table;
+	int count;
+
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (!IS_ERR(opp_table))
+		count = opp_table->regulator_count;
+	else
+		count = 0;
+
+	rcu_read_unlock();
+
+	return count;
+}
+
 /**
  * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds
  * @dev: device for which we do this operation
@@ -222,34 +242,51 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct dev_pm_opp *opp;
-	struct regulator *reg;
+	struct regulator *reg, **regulators;
 	unsigned long latency_ns = 0;
-	unsigned long min_uV = ~0, max_uV = 0;
-	int ret;
+	int ret, i, count;
+	struct {
+		unsigned long min;
+		unsigned long max;
+	} *uV;
+
+	count = _get_regulator_count(dev);
+
+	/* Regulator may not be required for the device */
+	if (!count)
+		return 0;
+
+	regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL);
+	if (!regulators)
+		return 0;
+
+	uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL);
+	if (!uV)
+		goto free_regulators;
 
 	rcu_read_lock();
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		rcu_read_unlock();
-		return 0;
+		goto free_uV;
 	}
 
-	reg = opp_table->regulator;
-	if (IS_ERR(reg)) {
-		/* Regulator may not be required for device */
-		rcu_read_unlock();
-		return 0;
-	}
+	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
-	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
-		if (!opp->available)
-			continue;
+	for (i = 0; i < count; i++) {
+		uV[i].min = ~0;
+		uV[i].max = 0;
+
+		list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+			if (!opp->available)
+				continue;
 
-		if (opp->u_volt_min < min_uV)
-			min_uV = opp->u_volt_min;
-		if (opp->u_volt_max > max_uV)
-			max_uV = opp->u_volt_max;
+			if (opp->supplies[i].u_volt_min < uV[i].min)
+				uV[i].min = opp->supplies[i].u_volt_min;
+			if (opp->supplies[i].u_volt_max > uV[i].max)
+				uV[i].max = opp->supplies[i].u_volt_max;
+		}
 	}
 
 	rcu_read_unlock();
@@ -258,9 +295,16 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	 * The caller needs to ensure that opp_table (and hence the regulator)
 	 * isn't freed, while we are executing this routine.
 	 */
-	ret = regulator_set_voltage_time(reg, min_uV, max_uV);
-	if (ret > 0)
-		latency_ns = ret * 1000;
+	for (i = 0; reg = regulators[i], i < count; i++) {
+		ret = regulator_set_voltage_time(reg, uV[i].min, uV[i].max);
+		if (ret > 0)
+			latency_ns += ret * 1000;
+	}
+
+free_uV:
+	kfree(uV);
+free_regulators:
+	kfree(regulators);
 
 	return latency_ns;
 }
@@ -542,8 +586,7 @@ unlock:
 }
 
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
-			    unsigned long u_volt, unsigned long u_volt_min,
-			    unsigned long u_volt_max)
+			    struct dev_pm_opp_supply *supply)
 {
 	int ret;
 
@@ -554,14 +597,78 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 		return 0;
 	}
 
-	dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__, u_volt_min,
-		u_volt, u_volt_max);
+	dev_dbg(dev, "%s: voltages (mV): %lu %lu %lu\n", __func__,
+		supply->u_volt_min, supply->u_volt, supply->u_volt_max);
 
-	ret = regulator_set_voltage_triplet(reg, u_volt_min, u_volt,
-					    u_volt_max);
+	ret = regulator_set_voltage_triplet(reg, supply->u_volt_min,
+					    supply->u_volt, supply->u_volt_max);
 	if (ret)
 		dev_err(dev, "%s: failed to set voltage (%lu %lu %lu mV): %d\n",
-			__func__, u_volt_min, u_volt, u_volt_max, ret);
+			__func__, supply->u_volt_min, supply->u_volt,
+			supply->u_volt_max, ret);
+
+	return ret;
+}
+
+static inline int
+_generic_set_opp_clk_only(struct device *dev, struct clk *clk,
+			  unsigned long old_freq, unsigned long freq)
+{
+	int ret;
+
+	ret = clk_set_rate(clk, freq);
+	if (ret) {
+		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
+			ret);
+	}
+
+	return ret;
+}
+
+static int _generic_set_opp(struct dev_pm_set_opp_data *data)
+{
+	struct dev_pm_opp_supply *old_supply = data->old_opp.supplies;
+	struct dev_pm_opp_supply *new_supply = data->new_opp.supplies;
+	unsigned long old_freq = data->old_opp.rate, freq = data->new_opp.rate;
+	struct regulator *reg = data->regulators[0];
+	struct device *dev= data->dev;
+	int ret;
+
+	/* This function only supports single regulator per device */
+	if (WARN_ON(data->regulator_count > 1)) {
+		dev_err(dev, "multiple regulators are not supported\n");
+		return -EINVAL;
+	}
+
+	/* Scaling up? Scale voltage before frequency */
+	if (freq > old_freq) {
+		ret = _set_opp_voltage(dev, reg, new_supply);
+		if (ret)
+			goto restore_voltage;
+	}
+
+	/* Change frequency */
+	ret = _generic_set_opp_clk_only(dev, data->clk, old_freq, freq);
+	if (ret)
+		goto restore_voltage;
+
+	/* Scaling down? Scale voltage after frequency */
+	if (freq < old_freq) {
+		ret = _set_opp_voltage(dev, reg, new_supply);
+		if (ret)
+			goto restore_freq;
+	}
+
+	return 0;
+
+restore_freq:
+	if (_generic_set_opp_clk_only(dev, data->clk, freq, old_freq))
+		dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
+			__func__, old_freq);
+restore_voltage:
+	/* This shouldn't harm even if the voltages weren't updated earlier */
+	if (old_supply->u_volt)
+		_set_opp_voltage(dev, reg, old_supply);
 
 	return ret;
 }
@@ -579,12 +686,13 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
 	struct opp_table *opp_table;
+	unsigned long freq, old_freq;
+	int (*set_opp)(struct dev_pm_set_opp_data *data);
 	struct dev_pm_opp *old_opp, *opp;
-	struct regulator *reg;
+	struct regulator **regulators;
+	struct dev_pm_set_opp_data *data;
 	struct clk *clk;
-	unsigned long freq, old_freq;
-	unsigned long u_volt, u_volt_min, u_volt_max;
-	int ret;
+	int ret, size;
 
 	if (unlikely(!target_freq)) {
 		dev_err(dev, "%s: Invalid target frequency %lu\n", __func__,
@@ -633,55 +741,41 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return ret;
 	}
 
-	u_volt = opp->u_volt;
-	u_volt_min = opp->u_volt_min;
-	u_volt_max = opp->u_volt_max;
+	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__,
+		old_freq, freq);
 
-	reg = opp_table->regulator;
+	regulators = opp_table->regulators;
 
-	rcu_read_unlock();
-
-	/* Scaling up? Scale voltage before frequency */
-	if (freq > old_freq) {
-		ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min,
-				       u_volt_max);
-		if (ret)
-			goto restore_voltage;
-	}
-
-	/* Change frequency */
-
-	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n",
-		__func__, old_freq, freq);
-
-	ret = clk_set_rate(clk, freq);
-	if (ret) {
-		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
-			ret);
-		goto restore_voltage;
+	/* Only frequency scaling */
+	if (!regulators) {
+		rcu_read_unlock();
+		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
 	}
 
-	/* Scaling down? Scale voltage after frequency */
-	if (freq < old_freq) {
-		ret = _set_opp_voltage(dev, reg, u_volt, u_volt_min,
-				       u_volt_max);
-		if (ret)
-			goto restore_freq;
-	}
+	if (opp_table->set_opp)
+		set_opp = opp_table->set_opp;
+	else
+		set_opp = _generic_set_opp;
+
+	data = opp_table->set_opp_data;
+	data->regulators = regulators;
+	data->regulator_count = opp_table->regulator_count;
+	data->clk = clk;
+	data->dev = dev;
+
+	data->old_opp.rate = old_freq;
+	size = sizeof(*opp->supplies) * opp_table->regulator_count;
+	if (IS_ERR(old_opp))
+		memset(data->old_opp.supplies, 0, size);
+	else
+		memcpy(data->old_opp.supplies, old_opp->supplies, size);
 
-	return 0;
+	data->new_opp.rate = freq;
+	memcpy(data->new_opp.supplies, opp->supplies, size);
 
-restore_freq:
-	if (clk_set_rate(clk, old_freq))
-		dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
-			__func__, old_freq);
-restore_voltage:
-	/* This shouldn't harm even if the voltages weren't updated earlier */
-	if (!IS_ERR(old_opp))
-		_set_opp_voltage(dev, reg, old_opp->u_volt,
-				 old_opp->u_volt_min, old_opp->u_volt_max);
+	rcu_read_unlock();
 
-	return ret;
+	return set_opp(data);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
 
@@ -764,9 +858,6 @@ static struct opp_table *_add_opp_table(struct device *dev)
 
 	_of_init_opp_table(opp_table, dev);
 
-	/* Set regulator to a non-NULL error value */
-	opp_table->regulator = ERR_PTR(-ENXIO);
-
 	/* Find clk for the device */
 	opp_table->clk = clk_get(dev, NULL);
 	if (IS_ERR(opp_table->clk)) {
@@ -815,7 +906,10 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	if (opp_table->prop_name)
 		return;
 
-	if (!IS_ERR(opp_table->regulator))
+	if (opp_table->regulators)
+		return;
+
+	if (opp_table->set_opp)
 		return;
 
 	/* Release clk */
@@ -924,34 +1018,50 @@ struct dev_pm_opp *_allocate_opp(struct device *dev,
 				 struct opp_table **opp_table)
 {
 	struct dev_pm_opp *opp;
+	int count, supply_size;
+	struct opp_table *table;
 
-	/* allocate new OPP node */
-	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
-	if (!opp)
+	table = _add_opp_table(dev);
+	if (!table)
 		return NULL;
 
-	INIT_LIST_HEAD(&opp->node);
+	/* Allocate space for at least one supply */
+	count = table->regulator_count ? table->regulator_count : 1;
+	supply_size = sizeof(*opp->supplies) * count;
 
-	*opp_table = _add_opp_table(dev);
-	if (!*opp_table) {
-		kfree(opp);
+	/* allocate new OPP node and supplies structures */
+	opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL);
+	if (!opp) {
+		kfree(table);
 		return NULL;
 	}
 
+	/* Put the supplies at the end of the OPP structure as an empty array */
+	opp->supplies = (struct dev_pm_opp_supply *)(opp + 1);
+	INIT_LIST_HEAD(&opp->node);
+
+	*opp_table = table;
+
 	return opp;
 }
 
 static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 					 struct opp_table *opp_table)
 {
-	struct regulator *reg = opp_table->regulator;
-
-	if (!IS_ERR(reg) &&
-	    !regulator_is_supported_voltage(reg, opp->u_volt_min,
-					    opp->u_volt_max)) {
-		pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n",
-			__func__, opp->u_volt_min, opp->u_volt_max);
-		return false;
+	struct regulator *reg;
+	int i;
+
+	for (i = 0; i < opp_table->regulator_count; i++) {
+		reg = opp_table->regulators[i];
+
+		if (!regulator_is_supported_voltage(reg,
+					opp->supplies[i].u_volt_min,
+					opp->supplies[i].u_volt_max)) {
+			pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n",
+				__func__, opp->supplies[i].u_volt_min,
+				opp->supplies[i].u_volt_max);
+			return false;
+		}
 	}
 
 	return true;
@@ -983,11 +1093,13 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
-			 __func__, opp->rate, opp->u_volt, opp->available,
-			 new_opp->rate, new_opp->u_volt, new_opp->available);
+			 __func__, opp->rate, opp->supplies[0].u_volt,
+			 opp->available, new_opp->rate,
+			 new_opp->supplies[0].u_volt, new_opp->available);
 
-		return opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
+		/* Should we compare voltages for all regulators here ? */
+		return opp->available &&
+		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST;
 	}
 
 	new_opp->opp_table = opp_table;
@@ -1054,9 +1166,9 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	/* populate the opp table */
 	new_opp->rate = freq;
 	tol = u_volt * opp_table->voltage_tolerance_v1 / 100;
-	new_opp->u_volt = u_volt;
-	new_opp->u_volt_min = u_volt - tol;
-	new_opp->u_volt_max = u_volt + tol;
+	new_opp->supplies[0].u_volt = u_volt;
+	new_opp->supplies[0].u_volt_min = u_volt - tol;
+	new_opp->supplies[0].u_volt_max = u_volt + tol;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
@@ -1300,13 +1412,47 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
+static int _allocate_set_opp_data(struct opp_table *opp_table)
+{
+	struct dev_pm_set_opp_data *data;
+	int len, count = opp_table->regulator_count;
+
+	if (WARN_ON(!count))
+		return -EINVAL;
+
+	/* space for set_opp_data */
+	len = sizeof(*data);
+
+	/* space for old_opp.supplies and new_opp.supplies */
+	len += 2 * sizeof(struct dev_pm_opp_supply) * count;
+
+	data = kzalloc(len, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->old_opp.supplies = (void *)(data + 1);
+	data->new_opp.supplies = data->old_opp.supplies + count;
+
+	opp_table->set_opp_data = data;
+
+	return 0;
+}
+
+static void _free_set_opp_data(struct opp_table *opp_table)
+{
+	kfree(opp_table->set_opp_data);
+	opp_table->set_opp_data = NULL;
+}
+
 /**
- * dev_pm_opp_set_regulator() - Set regulator name for the device
+ * dev_pm_opp_set_regulators() - Set regulator names for the device
  * @dev: Device for which regulator name is being set.
- * @name: Name of the regulator.
+ * @names: Array of pointers to the names of the regulator.
+ * @count: Number of regulators.
  *
  * In order to support OPP switching, OPP layer needs to know the name of the
- * device's regulator, as the core would be required to switch voltages as well.
+ * device's regulators, as the core would be required to switch voltages as
+ * well.
  *
  * This must be called before any OPPs are initialized for the device.
  *
@@ -1316,11 +1462,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-int dev_pm_opp_set_regulator(struct device *dev, const char *name)
+struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
+					    const char * const names[],
+					    unsigned int count)
 {
 	struct opp_table *opp_table;
 	struct regulator *reg;
-	int ret;
+	int ret, i;
 
 	mutex_lock(&opp_table_lock);
 
@@ -1336,22 +1484,146 @@ int dev_pm_opp_set_regulator(struct device *dev, const char *name)
 		goto err;
 	}
 
-	/* Already have a regulator set */
-	if (WARN_ON(!IS_ERR(opp_table->regulator))) {
+	/* Already have regulators set */
+	if (opp_table->regulators) {
 		ret = -EBUSY;
 		goto err;
 	}
-	/* Allocate the regulator */
-	reg = regulator_get_optional(dev, name);
-	if (IS_ERR(reg)) {
-		ret = PTR_ERR(reg);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "%s: no regulator (%s) found: %d\n",
-				__func__, name, ret);
+
+	opp_table->regulators = kmalloc_array(count,
+					      sizeof(*opp_table->regulators),
+					      GFP_KERNEL);
+	if (!opp_table->regulators) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	for (i = 0; i < count; i++) {
+		reg = regulator_get_optional(dev, names[i]);
+		if (IS_ERR(reg)) {
+			ret = PTR_ERR(reg);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "%s: no regulator (%s) found: %d\n",
+					__func__, names[i], ret);
+			goto free_regulators;
+		}
+
+		opp_table->regulators[i] = reg;
+	}
+
+	opp_table->regulator_count = count;
+
+	/* Allocate block only once to pass to set_opp() routines */
+	ret = _allocate_set_opp_data(opp_table);
+	if (ret)
+		goto free_regulators;
+
+	mutex_unlock(&opp_table_lock);
+	return opp_table;
+
+free_regulators:
+	while (i != 0)
+		regulator_put(opp_table->regulators[--i]);
+
+	kfree(opp_table->regulators);
+	opp_table->regulators = NULL;
+	opp_table->regulator_count = 0;
+err:
+	_remove_opp_table(opp_table);
+unlock:
+	mutex_unlock(&opp_table_lock);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators);
+
+/**
+ * dev_pm_opp_put_regulators() - Releases resources blocked for regulator
+ * @opp_table: OPP table returned from dev_pm_opp_set_regulators().
+ *
+ * Locking: The internal opp_table and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+void dev_pm_opp_put_regulators(struct opp_table *opp_table)
+{
+	int i;
+
+	mutex_lock(&opp_table_lock);
+
+	if (!opp_table->regulators) {
+		pr_err("%s: Doesn't have regulators set\n", __func__);
+		goto unlock;
+	}
+
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
+
+	for (i = opp_table->regulator_count - 1; i >= 0; i--)
+		regulator_put(opp_table->regulators[i]);
+
+	_free_set_opp_data(opp_table);
+
+	kfree(opp_table->regulators);
+	opp_table->regulators = NULL;
+	opp_table->regulator_count = 0;
+
+	/* Try freeing opp_table if this was the last blocking resource */
+	_remove_opp_table(opp_table);
+
+unlock:
+	mutex_unlock(&opp_table_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
+
+/**
+ * dev_pm_opp_register_set_opp_helper() - Register custom set OPP helper
+ * @dev: Device for which the helper is getting registered.
+ * @set_opp: Custom set OPP helper.
+ *
+ * This is useful to support complex platforms (like platforms with multiple
+ * regulators per device), instead of the generic OPP set rate helper.
+ *
+ * This must be called before any OPPs are initialized for the device.
+ *
+ * Locking: The internal opp_table and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+int dev_pm_opp_register_set_opp_helper(struct device *dev,
+			int (*set_opp)(struct dev_pm_set_opp_data *data))
+{
+	struct opp_table *opp_table;
+	int ret;
+
+	if (!set_opp)
+		return -EINVAL;
+
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	/* This should be called before OPPs are initialized */
+	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
+		ret = -EBUSY;
 		goto err;
 	}
 
-	opp_table->regulator = reg;
+	/* Already have custom set_opp helper */
+	if (WARN_ON(opp_table->set_opp)) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	opp_table->set_opp = set_opp;
 
 	mutex_unlock(&opp_table_lock);
 	return 0;
@@ -1363,11 +1635,12 @@ unlock:
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
+EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
 
 /**
- * dev_pm_opp_put_regulator() - Releases resources blocked for regulator
- * @dev: Device for which regulator was set.
+ * dev_pm_opp_register_put_opp_helper() - Releases resources blocked for
+ *					   set_opp helper
+ * @dev: Device for which custom set_opp helper has to be cleared.
  *
  * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -1375,7 +1648,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-void dev_pm_opp_put_regulator(struct device *dev)
+void dev_pm_opp_register_put_opp_helper(struct device *dev)
 {
 	struct opp_table *opp_table;
 
@@ -1389,16 +1662,16 @@ void dev_pm_opp_put_regulator(struct device *dev)
 		goto unlock;
 	}
 
-	if (IS_ERR(opp_table->regulator)) {
-		dev_err(dev, "%s: Doesn't have regulator set\n", __func__);
+	if (!opp_table->set_opp) {
+		dev_err(dev, "%s: Doesn't have custom set_opp helper set\n",
+			__func__);
 		goto unlock;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	regulator_put(opp_table->regulator);
-	opp_table->regulator = ERR_PTR(-ENXIO);
+	opp_table->set_opp = NULL;
 
 	/* Try freeing opp_table if this was the last blocking resource */
 	_remove_opp_table(opp_table);
@@ -1406,7 +1679,7 @@ void dev_pm_opp_put_regulator(struct device *dev)
 unlock:
 	mutex_unlock(&opp_table_lock);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator);
+EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
 
 /**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c
index ef1ae6b52042..95f433db4ac7 100644
--- a/drivers/base/power/opp/debugfs.c
+++ b/drivers/base/power/opp/debugfs.c
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/limits.h>
+#include <linux/slab.h>
 
 #include "opp.h"
 
@@ -34,6 +35,46 @@ void opp_debug_remove_one(struct dev_pm_opp *opp)
 	debugfs_remove_recursive(opp->dentry);
 }
 
+static bool opp_debug_create_supplies(struct dev_pm_opp *opp,
+				      struct opp_table *opp_table,
+				      struct dentry *pdentry)
+{
+	struct dentry *d;
+	int i = 0;
+	char *name;
+
+	/* Always create at least supply-0 directory */
+	do {
+		name = kasprintf(GFP_KERNEL, "supply-%d", i);
+
+		/* Create per-opp directory */
+		d = debugfs_create_dir(name, pdentry);
+
+		kfree(name);
+
+		if (!d)
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d,
+					  &opp->supplies[i].u_volt))
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d,
+					  &opp->supplies[i].u_volt_min))
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d,
+					  &opp->supplies[i].u_volt_max))
+			return false;
+
+		if (!debugfs_create_ulong("u_amp", S_IRUGO, d,
+					  &opp->supplies[i].u_amp))
+			return false;
+	} while (++i < opp_table->regulator_count);
+
+	return true;
+}
+
 int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 {
 	struct dentry *pdentry = opp_table->dentry;
@@ -63,16 +104,7 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 	if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate))
 		return -ENOMEM;
 
-	if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->u_volt))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->u_volt_min))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->u_volt_max))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->u_amp))
+	if (!opp_debug_create_supplies(opp, opp_table, d))
 		return -ENOMEM;
 
 	if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 5552211e6fcd..3f7d2591b173 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/of.h>
+#include <linux/slab.h>
 #include <linux/export.h>
 
 #include "opp.h"
@@ -101,16 +102,16 @@ static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
 	return true;
 }
 
-/* TODO: Support multiple regulators */
 static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 			      struct opp_table *opp_table)
 {
-	u32 microvolt[3] = {0};
-	u32 val;
-	int count, ret;
+	u32 *microvolt, *microamp = NULL;
+	int supplies, vcount, icount, ret, i, j;
 	struct property *prop = NULL;
 	char name[NAME_MAX];
 
+	supplies = opp_table->regulator_count ? opp_table->regulator_count : 1;
+
 	/* Search for "opp-microvolt-<name>" */
 	if (opp_table->prop_name) {
 		snprintf(name, sizeof(name), "opp-microvolt-%s",
@@ -128,34 +129,29 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 			return 0;
 	}
 
-	count = of_property_count_u32_elems(opp->np, name);
-	if (count < 0) {
+	vcount = of_property_count_u32_elems(opp->np, name);
+	if (vcount < 0) {
 		dev_err(dev, "%s: Invalid %s property (%d)\n",
-			__func__, name, count);
-		return count;
+			__func__, name, vcount);
+		return vcount;
 	}
 
-	/* There can be one or three elements here */
-	if (count != 1 && count != 3) {
-		dev_err(dev, "%s: Invalid number of elements in %s property (%d)\n",
-			__func__, name, count);
+	/* There can be one or three elements per supply */
+	if (vcount != supplies && vcount != supplies * 3) {
+		dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+			__func__, name, vcount, supplies);
 		return -EINVAL;
 	}
 
-	ret = of_property_read_u32_array(opp->np, name, microvolt, count);
+	microvolt = kmalloc_array(vcount, sizeof(*microvolt), GFP_KERNEL);
+	if (!microvolt)
+		return -ENOMEM;
+
+	ret = of_property_read_u32_array(opp->np, name, microvolt, vcount);
 	if (ret) {
 		dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret);
-		return -EINVAL;
-	}
-
-	opp->u_volt = microvolt[0];
-
-	if (count == 1) {
-		opp->u_volt_min = opp->u_volt;
-		opp->u_volt_max = opp->u_volt;
-	} else {
-		opp->u_volt_min = microvolt[1];
-		opp->u_volt_max = microvolt[2];
+		ret = -EINVAL;
+		goto free_microvolt;
 	}
 
 	/* Search for "opp-microamp-<name>" */
@@ -172,10 +168,59 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 		prop = of_find_property(opp->np, name, NULL);
 	}
 
-	if (prop && !of_property_read_u32(opp->np, name, &val))
-		opp->u_amp = val;
+	if (prop) {
+		icount = of_property_count_u32_elems(opp->np, name);
+		if (icount < 0) {
+			dev_err(dev, "%s: Invalid %s property (%d)\n", __func__,
+				name, icount);
+			ret = icount;
+			goto free_microvolt;
+		}
 
-	return 0;
+		if (icount != supplies) {
+			dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+				__func__, name, icount, supplies);
+			ret = -EINVAL;
+			goto free_microvolt;
+		}
+
+		microamp = kmalloc_array(icount, sizeof(*microamp), GFP_KERNEL);
+		if (!microamp) {
+			ret = -EINVAL;
+			goto free_microvolt;
+		}
+
+		ret = of_property_read_u32_array(opp->np, name, microamp,
+						 icount);
+		if (ret) {
+			dev_err(dev, "%s: error parsing %s: %d\n", __func__,
+				name, ret);
+			ret = -EINVAL;
+			goto free_microamp;
+		}
+	}
+
+	for (i = 0, j = 0; i < supplies; i++) {
+		opp->supplies[i].u_volt = microvolt[j++];
+
+		if (vcount == supplies) {
+			opp->supplies[i].u_volt_min = opp->supplies[i].u_volt;
+			opp->supplies[i].u_volt_max = opp->supplies[i].u_volt;
+		} else {
+			opp->supplies[i].u_volt_min = microvolt[j++];
+			opp->supplies[i].u_volt_max = microvolt[j++];
+		}
+
+		if (microamp)
+			opp->supplies[i].u_amp = microamp[i];
+	}
+
+free_microamp:
+	kfree(microamp);
+free_microvolt:
+	kfree(microvolt);
+
+	return ret;
 }
 
 /**
@@ -198,7 +243,7 @@ void dev_pm_opp_of_remove_table(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
 /* Returns opp descriptor node for a device, caller must do of_node_put() */
-struct device_node *_of_get_opp_desc_node(struct device *dev)
+static struct device_node *_of_get_opp_desc_node(struct device *dev)
 {
 	/*
 	 * TODO: Support for multiple OPP tables.
@@ -303,9 +348,9 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	mutex_unlock(&opp_table_lock);
 
 	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
-		 __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt,
-		 new_opp->u_volt_min, new_opp->u_volt_max,
-		 new_opp->clock_latency_ns);
+		 __func__, new_opp->turbo, new_opp->rate,
+		 new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min,
+		 new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns);
 
 	/*
 	 * Notify the changes in the availability of the operable
@@ -562,7 +607,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 	/* Get OPP descriptor node */
 	np = _of_get_opp_desc_node(cpu_dev);
 	if (!np) {
-		dev_dbg(cpu_dev, "%s: Couldn't find cpu_dev node.\n", __func__);
+		dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__);
 		return -ENOENT;
 	}
 
@@ -587,7 +632,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 		/* Get OPP descriptor node */
 		tmp_np = _of_get_opp_desc_node(tcpu_dev);
 		if (!tmp_np) {
-			dev_err(tcpu_dev, "%s: Couldn't find tcpu_dev node.\n",
+			dev_err(tcpu_dev, "%s: Couldn't find opp node.\n",
 				__func__);
 			ret = -ENOENT;
 			goto put_cpu_node;
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index fabd5ca1a083..af9f2b849a66 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -61,10 +61,7 @@ extern struct list_head opp_tables;
  * @turbo:	true if turbo (boost) OPP
  * @suspend:	true if suspend OPP
  * @rate:	Frequency in hertz
- * @u_volt:	Target voltage in microvolts corresponding to this OPP
- * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
- * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
- * @u_amp:	Maximum current drawn by the device in microamperes
+ * @supplies:	Power supplies voltage/current values
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
  * @opp_table:	points back to the opp_table struct this opp belongs to
@@ -83,10 +80,8 @@ struct dev_pm_opp {
 	bool suspend;
 	unsigned long rate;
 
-	unsigned long u_volt;
-	unsigned long u_volt_min;
-	unsigned long u_volt_max;
-	unsigned long u_amp;
+	struct dev_pm_opp_supply *supplies;
+
 	unsigned long clock_latency_ns;
 
 	struct opp_table *opp_table;
@@ -144,7 +139,10 @@ enum opp_table_access {
  * @supported_hw_count: Number of elements in supported_hw array.
  * @prop_name: A name to postfix to many DT properties, while parsing them.
  * @clk: Device's clock handle
- * @regulator: Supply regulator
+ * @regulators: Supply regulators
+ * @regulator_count: Number of power supply regulators
+ * @set_opp: Platform specific set_opp callback
+ * @set_opp_data: Data to be passed to set_opp callback
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -179,7 +177,11 @@ struct opp_table {
 	unsigned int supported_hw_count;
 	const char *prop_name;
 	struct clk *clk;
-	struct regulator *regulator;
+	struct regulator **regulators;
+	unsigned int regulator_count;
+
+	int (*set_opp)(struct dev_pm_set_opp_data *data);
+	struct dev_pm_set_opp_data *set_opp_data;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -190,7 +192,6 @@ struct opp_table {
 /* Routines internal to opp core */
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
-struct device_node *_of_get_opp_desc_node(struct device *dev);
 void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
 struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 50e30e7b059d..a84332aefc2d 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -21,14 +21,22 @@ extern void pm_runtime_init(struct device *dev);
 extern void pm_runtime_reinit(struct device *dev);
 extern void pm_runtime_remove(struct device *dev);
 
+#define WAKE_IRQ_DEDICATED_ALLOCATED	BIT(0)
+#define WAKE_IRQ_DEDICATED_MANAGED	BIT(1)
+#define WAKE_IRQ_DEDICATED_MASK		(WAKE_IRQ_DEDICATED_ALLOCATED | \
+					 WAKE_IRQ_DEDICATED_MANAGED)
+
 struct wake_irq {
 	struct device *dev;
+	unsigned int status;
 	int irq;
-	bool dedicated_irq:1;
 };
 
 extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
 extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_enable_wake_irq_check(struct device *dev,
+					 bool can_change_status);
+extern void dev_pm_disable_wake_irq_check(struct device *dev);
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -104,6 +112,15 @@ static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
 {
 }
 
+static inline void dev_pm_enable_wake_irq_check(struct device *dev,
+						bool can_change_status)
+{
+}
+
+static inline void dev_pm_disable_wake_irq_check(struct device *dev)
+{
+}
+
 #endif
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 7f3646e459cb..58fcc758334e 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -856,7 +856,10 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
 		struct dev_pm_qos_request *req;
 
 		if (val < 0) {
-			ret = -EINVAL;
+			if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT)
+				ret = 0;
+			else
+				ret = -EINVAL;
 			goto out;
 		}
 		req = kzalloc(sizeof(*req), GFP_KERNEL);
@@ -883,6 +886,7 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance);
 
 /**
  * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 82a081ea4317..26856d050037 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -241,7 +241,8 @@ static int rpm_check_suspend_allowed(struct device *dev)
 		retval = -EACCES;
 	else if (atomic_read(&dev->power.usage_count) > 0)
 		retval = -EAGAIN;
-	else if (!pm_children_suspended(dev))
+	else if (!dev->power.ignore_children &&
+			atomic_read(&dev->power.child_count))
 		retval = -EBUSY;
 
 	/* Pending resume requests take precedence over suspends. */
@@ -515,7 +516,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
-	dev_pm_enable_wake_irq(dev);
+	dev_pm_enable_wake_irq_check(dev, true);
 	retval = rpm_callback(callback, dev);
 	if (retval)
 		goto fail;
@@ -554,7 +555,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	return retval;
 
  fail:
-	dev_pm_disable_wake_irq(dev);
+	dev_pm_disable_wake_irq_check(dev);
 	__update_runtime_status(dev, RPM_ACTIVE);
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
@@ -712,8 +713,8 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 		spin_lock(&parent->power.lock);
 		/*
-		 * We can resume if the parent's runtime PM is disabled or it
-		 * is set to ignore children.
+		 * Resume the parent if it has runtime PM enabled and not been
+		 * set to ignore its children.
 		 */
 		if (!parent->power.disable_depth
 		    && !parent->power.ignore_children) {
@@ -737,12 +738,12 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
-	dev_pm_disable_wake_irq(dev);
+	dev_pm_disable_wake_irq_check(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
-		dev_pm_enable_wake_irq(dev);
+		dev_pm_enable_wake_irq_check(dev, false);
 	} else {
  no_callback:
 		__update_runtime_status(dev, RPM_ACTIVE);
@@ -1027,7 +1028,17 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status)
 		goto out_set;
 
 	if (status == RPM_SUSPENDED) {
-		/* It always is possible to set the status to 'suspended'. */
+		/*
+		 * It is invalid to suspend a device with an active child,
+		 * unless it has been set to ignore its children.
+		 */
+		if (!dev->power.ignore_children &&
+			atomic_read(&dev->power.child_count)) {
+			dev_err(dev, "runtime PM trying to suspend device but active child\n");
+			error = -EBUSY;
+			goto out;
+		}
+
 		if (parent) {
 			atomic_add_unless(&parent->power.child_count, -1, 0);
 			notify_parent = !parent->power.ignore_children;
@@ -1478,6 +1489,16 @@ int pm_runtime_force_suspend(struct device *dev)
 	if (ret)
 		goto err;
 
+	/*
+	 * Increase the runtime PM usage count for the device's parent, in case
+	 * when we find the device being used when system suspend was invoked.
+	 * This informs pm_runtime_force_resume() to resume the parent
+	 * immediately, which is needed to be able to resume its children,
+	 * when not deferring the resume to be managed via runtime PM.
+	 */
+	if (dev->parent && atomic_read(&dev->power.usage_count) > 1)
+		pm_runtime_get_noresume(dev->parent);
+
 	pm_runtime_set_suspended(dev);
 	return 0;
 err:
@@ -1487,16 +1508,20 @@ err:
 EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
 
 /**
- * pm_runtime_force_resume - Force a device into resume state.
+ * pm_runtime_force_resume - Force a device into resume state if needed.
  * @dev: Device to resume.
  *
  * Prior invoking this function we expect the user to have brought the device
  * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
- * those actions and brings the device into full power. We update the runtime PM
- * status and re-enables runtime PM.
+ * those actions and brings the device into full power, if it is expected to be
+ * used on system resume. To distinguish that, we check whether the runtime PM
+ * usage count is greater than 1 (the PM core increases the usage count in the
+ * system PM prepare phase), as that indicates a real user (such as a subsystem,
+ * driver, userspace, etc.) is using it. If that is the case, the device is
+ * expected to be used on system resume as well, so then we resume it. In the
+ * other case, we defer the resume to be managed via runtime PM.
  *
- * Typically this function may be invoked from a system resume callback to make
- * sure the device is put into full power state.
+ * Typically this function may be invoked from a system resume callback.
  */
 int pm_runtime_force_resume(struct device *dev)
 {
@@ -1513,6 +1538,17 @@ int pm_runtime_force_resume(struct device *dev)
 	if (!pm_runtime_status_suspended(dev))
 		goto out;
 
+	/*
+	 * Decrease the parent's runtime PM usage count, if we increased it
+	 * during system suspend in pm_runtime_force_suspend().
+	*/
+	if (atomic_read(&dev->power.usage_count) > 1) {
+		if (dev->parent)
+			pm_runtime_put_noidle(dev->parent);
+	} else {
+		goto out;
+	}
+
 	ret = pm_runtime_set_active(dev);
 	if (ret)
 		goto out;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index a7b46798c81d..33b4b902741a 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -263,7 +263,11 @@ static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
 	s32 value;
 	int ret;
 
-	if (kstrtos32(buf, 0, &value)) {
+	if (kstrtos32(buf, 0, &value) == 0) {
+		/* Users can't write negative values directly */
+		if (value < 0)
+			return -EINVAL;
+	} else {
 		if (!strcmp(buf, "auto") || !strcmp(buf, "auto\n"))
 			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 		else if (!strcmp(buf, "any") || !strcmp(buf, "any\n"))
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 0d77cd6fd8d1..404d94c6c8bc 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -110,8 +110,10 @@ void dev_pm_clear_wake_irq(struct device *dev)
 	dev->power.wakeirq = NULL;
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	if (wirq->dedicated_irq)
+	if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) {
 		free_irq(wirq->irq, wirq);
+		wirq->status &= ~WAKE_IRQ_DEDICATED_MASK;
+	}
 	kfree(wirq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
@@ -179,7 +181,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 
 	wirq->dev = dev;
 	wirq->irq = irq;
-	wirq->dedicated_irq = true;
 	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 
 	/*
@@ -195,6 +196,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	if (err)
 		goto err_free_irq;
 
+	wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED;
+
 	return err;
 
 err_free_irq:
@@ -210,9 +213,9 @@ EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq);
  * dev_pm_enable_wake_irq - Enable device wake-up interrupt
  * @dev: Device
  *
- * Called from the bus code or the device driver for
- * runtime_suspend() to enable the wake-up interrupt while
- * the device is running.
+ * Optionally called from the bus code or the device driver for
+ * runtime_resume() to override the PM runtime core managed wake-up
+ * interrupt handling to enable the wake-up interrupt.
  *
  * Note that for runtime_suspend()) the wake-up interrupts
  * should be unconditionally enabled unlike for suspend()
@@ -222,7 +225,7 @@ void dev_pm_enable_wake_irq(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (wirq && wirq->dedicated_irq)
+	if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED))
 		enable_irq(wirq->irq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
@@ -231,20 +234,73 @@ EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
  * dev_pm_disable_wake_irq - Disable device wake-up interrupt
  * @dev: Device
  *
- * Called from the bus code or the device driver for
- * runtime_resume() to disable the wake-up interrupt while
- * the device is running.
+ * Optionally called from the bus code or the device driver for
+ * runtime_suspend() to override the PM runtime core managed wake-up
+ * interrupt handling to disable the wake-up interrupt.
  */
 void dev_pm_disable_wake_irq(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (wirq && wirq->dedicated_irq)
+	if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED))
 		disable_irq_nosync(wirq->irq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq);
 
 /**
+ * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt
+ * @dev: Device
+ * @can_change_status: Can change wake-up interrupt status
+ *
+ * Enables wakeirq conditionally. We need to enable wake-up interrupt
+ * lazily on the first rpm_suspend(). This is needed as the consumer device
+ * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would
+ * otherwise try to disable already disabled wakeirq. The wake-up interrupt
+ * starts disabled with IRQ_NOAUTOEN set.
+ *
+ * Should be only called from rpm_suspend() and rpm_resume() path.
+ * Caller must hold &dev->power.lock to change wirq->status
+ */
+void dev_pm_enable_wake_irq_check(struct device *dev,
+				  bool can_change_status)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+		return;
+
+	if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) {
+		goto enable;
+	} else if (can_change_status) {
+		wirq->status |= WAKE_IRQ_DEDICATED_MANAGED;
+		goto enable;
+	}
+
+	return;
+
+enable:
+	enable_irq(wirq->irq);
+}
+
+/**
+ * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt
+ * @dev: Device
+ *
+ * Disables wake-up interrupt conditionally based on status.
+ * Should be only called from rpm_suspend() and rpm_resume() path.
+ */
+void dev_pm_disable_wake_irq_check(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+		return;
+
+	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED)
+		disable_irq_nosync(wirq->irq);
+}
+
+/**
  * dev_pm_arm_wake_irq - Arm device wake-up
  * @wirq: Device wake-up interrupt
  *
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 62e4de2aa8d1..bf9ba26981a5 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -811,7 +811,7 @@ void pm_print_active_wakeup_sources(void)
 	rcu_read_lock();
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
-			pr_info("active wakeup source: %s\n", ws->name);
+			pr_debug("active wakeup source: %s\n", ws->name);
 			active = 1;
 		} else if (!active &&
 			   (!last_activity_ws ||
@@ -822,7 +822,7 @@ void pm_print_active_wakeup_sources(void)
 	}
 
 	if (!active && last_activity_ws)
-		pr_info("last active wakeup source: %s\n",
+		pr_debug("last active wakeup source: %s\n",
 			last_activity_ws->name);
 	rcu_read_unlock();
 }
@@ -905,7 +905,7 @@ bool pm_get_wakeup_count(unsigned int *count, bool block)
 			split_counters(&cnt, &inpr);
 			if (inpr == 0 || signal_pending(current))
 				break;
-
+			pm_print_active_wakeup_sources();
 			schedule();
 		}
 		finish_wait(&wakeup_count_wait_queue, &wait);