Merge tag 'pm+acpi-4.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management and ACPI updates from Rafael Wysocki:
 "From the number of commits perspective, the biggest items are ACPICA
  and cpufreq changes with the latter taking the lead (over 50 commits).

  On the cpufreq front, there are many cleanups and minor fixes in the
  core and governors, driver updates etc.  We also have a new cpufreq
  driver for Mediatek MT8173 chips.

  ACPICA mostly updates its debug infrastructure and adds a number of
  fixes and cleanups for a good measure.

  The Operating Performance Points (OPP) framework is updated with new
  DT bindings and support for them among other things.

  We have a few updates of the generic power domains framework and a
  reorganization of the ACPI device enumeration code and bus type
  operations.

  And a lot of fixes and cleanups all over.

  Included is one branch from the MFD tree as it contains some
  PM-related driver core and ACPI PM changes a few other commits are
  based on.

  Specifics:

   - ACPICA update to upstream revision 20150818 including method
     tracing extensions to allow more in-depth AML debugging in the
     kernel and a number of assorted fixes and cleanups (Bob Moore, Lv
     Zheng, Markus Elfring).

   - ACPI sysfs code updates and a documentation update related to AML
     method tracing (Lv Zheng).

   - ACPI EC driver fix related to serialized evaluations of _Qxx
     methods and ACPI tools updates allowing the EC userspace tool to be
     built from the kernel source (Lv Zheng).

   - ACPI processor driver updates preparing it for future introduction
     of CPPC support and ACPI PCC mailbox driver updates (Ashwin
     Chaugule).

   - ACPI interrupts enumeration fix for a regression related to the
     handling of IRQ attribute conflicts between MADT and the ACPI
     namespace (Jiang Liu).

   - Fixes related to ACPI device PM (Mika Westerberg, Srinidhi
     Kasagar).

   - ACPI device registration code reorganization to separate the
     sysfs-related code and bus type operations from the rest (Rafael J
     Wysocki).

   - Assorted cleanups in the ACPI core (Jarkko Nikula, Mathias Krause,
     Andy Shevchenko, Rafael J Wysocki, Nicolas Iooss).

   - ACPI cpufreq driver and ia64 cpufreq driver fixes and cleanups (Pan
     Xinhui, Rafael J Wysocki).

   - cpufreq core cleanups on top of the previous changes allowing it to
     preseve its sysfs directories over system suspend/resume (Viresh
     Kumar, Rafael J Wysocki, Sebastian Andrzej Siewior).

   - cpufreq fixes and cleanups related to governors (Viresh Kumar).

   - cpufreq updates (core and the cpufreq-dt driver) related to the
     turbo/boost mode support (Viresh Kumar, Bartlomiej Zolnierkiewicz).

   - New DT bindings for Operating Performance Points (OPP), support for
     them in the OPP framework and in the cpufreq-dt driver plus related
     OPP framework fixes and cleanups (Viresh Kumar).

   - cpufreq powernv driver updates (Shilpasri G Bhat).

   - New cpufreq driver for Mediatek MT8173 (Pi-Cheng Chen).

   - Assorted cpufreq driver (speedstep-lib, sfi, integrator) cleanups
     and fixes (Abhilash Jindal, Andrzej Hajda, Cristian Ardelean).

   - intel_pstate driver updates including Skylake-S support, support
     for enabling HW P-states per CPU and an additional vendor bypass
     list entry (Kristen Carlson Accardi, Chen Yu, Ethan Zhao).

   - cpuidle core fixes related to the handling of coupled idle states
     (Xunlei Pang).

   - intel_idle driver updates including Skylake Client support and
     support for freeze-mode-specific idle states (Len Brown).

   - Driver core updates related to power management (Andy Shevchenko,
     Rafael J Wysocki).

   - Generic power domains framework fixes and cleanups (Jon Hunter,
     Geert Uytterhoeven, Rajendra Nayak, Ulf Hansson).

   - Device PM QoS framework update to allow the latency tolerance
     setting to be exposed to user space via sysfs (Mika Westerberg).

   - devfreq support for PPMUv2 in Exynos5433 and a fix for an incorrect
     exynos-ppmu DT binding (Chanwoo Choi, Javier Martinez Canillas).

   - System sleep support updates (Alan Stern, Len Brown, SungEun Kim).

   - rockchip-io AVS support updates (Heiko Stuebner).

   - PM core clocks support fixup (Colin Ian King).

   - Power capping RAPL driver update including support for Skylake H/S
     and Broadwell-H (Radivoje Jovanovic, Seiichi Ikarashi).

   - Generic device properties framework fixes related to the handling
     of static (driver-provided) property sets (Andy Shevchenko).

   - turbostat and cpupower updates (Len Brown, Shilpasri G Bhat,
     Shreyas B Prabhu)"

* tag 'pm+acpi-4.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (180 commits)
  cpufreq: speedstep-lib: Use monotonic clock
  cpufreq: powernv: Increase the verbosity of OCC console messages
  cpufreq: sfi: use kmemdup rather than duplicating its implementation
  cpufreq: drop !cpufreq_driver check from cpufreq_parse_governor()
  cpufreq: rename cpufreq_real_policy as cpufreq_user_policy
  cpufreq: remove redundant 'policy' field from user_policy
  cpufreq: remove redundant 'governor' field from user_policy
  cpufreq: update user_policy.* on success
  cpufreq: use memcpy() to copy policy
  cpufreq: remove redundant CPUFREQ_INCOMPATIBLE notifier event
  cpufreq: mediatek: Add MT8173 cpufreq driver
  dt-bindings: mediatek: Add MT8173 CPU DVFS clock bindings
  PM / Domains: Fix typo in description of genpd_dev_pm_detach()
  PM / Domains: Remove unusable governor dummies
  PM / Domains: Make pm_genpd_init() available to modules
  PM / domains: Align column headers and data in pm_genpd_summary output
  powercap / RAPL: disable the 2nd power limit properly
  tools: cpupower: Fix error when running cpupower monitor
  PM / OPP: Drop unlikely before IS_ERR(_OR_NULL)
  PM / OPP: Fix static checker warning (broken 64bit big endian systems)
  ...

7 files changed, 950 insertions, 495 deletions

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index acef9f9f759a..652b5a367c1f 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -38,7 +38,7 @@ struct pm_clock_entry {
  * @dev: The device for the given clock
  * @ce: PM clock entry corresponding to the clock.
  */
-static inline int __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
+static inline void __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
 {
 	int ret;
 
@@ -50,8 +50,6 @@ static inline int __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce)
 			dev_err(dev, "%s: failed to enable clk %p, error %d\n",
 				__func__, ce->clk, ret);
 	}
-
-	return ret;
 }
 
 /**
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 0ee43c1056e0..416720159e96 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -114,8 +114,12 @@ static int genpd_stop_dev(struct generic_pm_domain *genpd, struct device *dev)
 					stop_latency_ns, "stop");
 }
 
-static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev)
+static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev,
+			bool timed)
 {
+	if (!timed)
+		return GENPD_DEV_CALLBACK(genpd, int, start, dev);
+
 	return GENPD_DEV_TIMED_CALLBACK(genpd, int, start, dev,
 					start_latency_ns, "start");
 }
@@ -136,41 +140,6 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 	smp_mb__after_atomic();
 }
 
-static void genpd_acquire_lock(struct generic_pm_domain *genpd)
-{
-	DEFINE_WAIT(wait);
-
-	mutex_lock(&genpd->lock);
-	/*
-	 * Wait for the domain to transition into either the active,
-	 * or the power off state.
-	 */
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		if (genpd->status == GPD_STATE_ACTIVE
-		    || genpd->status == GPD_STATE_POWER_OFF)
-			break;
-		mutex_unlock(&genpd->lock);
-
-		schedule();
-
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-}
-
-static void genpd_release_lock(struct generic_pm_domain *genpd)
-{
-	mutex_unlock(&genpd->lock);
-}
-
-static void genpd_set_active(struct generic_pm_domain *genpd)
-{
-	if (genpd->resume_count == 0)
-		genpd->status = GPD_STATE_ACTIVE;
-}
-
 static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
 {
 	s64 usecs64;
@@ -251,35 +220,14 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
  * resume a device belonging to it.
  */
 static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
 {
 	struct gpd_link *link;
-	DEFINE_WAIT(wait);
 	int ret = 0;
 
-	/* If the domain's master is being waited for, we have to wait too. */
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		if (genpd->status != GPD_STATE_WAIT_MASTER)
-			break;
-		mutex_unlock(&genpd->lock);
-
-		schedule();
-
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-
 	if (genpd->status == GPD_STATE_ACTIVE
 	    || (genpd->prepared_count > 0 && genpd->suspend_power_off))
 		return 0;
 
-	if (genpd->status != GPD_STATE_POWER_OFF) {
-		genpd_set_active(genpd);
-		return 0;
-	}
-
 	if (genpd->cpuidle_data) {
 		cpuidle_pause_and_lock();
 		genpd->cpuidle_data->idle_state->disabled = true;
@@ -294,20 +242,8 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 	 */
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_inc(link->master);
-		genpd->status = GPD_STATE_WAIT_MASTER;
-
-		mutex_unlock(&genpd->lock);
 
 		ret = pm_genpd_poweron(link->master);
-
-		mutex_lock(&genpd->lock);
-
-		/*
-		 * The "wait for parent" status is guaranteed not to change
-		 * while the master is powering on.
-		 */
-		genpd->status = GPD_STATE_POWER_OFF;
-		wake_up_all(&genpd->status_wait_queue);
 		if (ret) {
 			genpd_sd_counter_dec(link->master);
 			goto err;
@@ -319,8 +255,7 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 		goto err;
 
  out:
-	genpd_set_active(genpd);
-
+	genpd->status = GPD_STATE_ACTIVE;
 	return 0;
 
  err:
@@ -356,20 +291,18 @@ int pm_genpd_name_poweron(const char *domain_name)
 	return genpd ? pm_genpd_poweron(genpd) : -EINVAL;
 }
 
-static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd,
-				     struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, start, dev);
-}
-
 static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
 {
 	return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev,
 					save_state_latency_ns, "state save");
 }
 
-static int genpd_restore_dev(struct generic_pm_domain *genpd, struct device *dev)
+static int genpd_restore_dev(struct generic_pm_domain *genpd,
+			struct device *dev, bool timed)
 {
+	if (!timed)
+		return GENPD_DEV_CALLBACK(genpd, int, restore_state, dev);
+
 	return GENPD_DEV_TIMED_CALLBACK(genpd, int, restore_state, dev,
 					restore_state_latency_ns,
 					"state restore");
@@ -416,89 +349,6 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 }
 
 /**
- * __pm_genpd_save_device - Save the pre-suspend state of a device.
- * @pdd: Domain data of the device to save the state of.
- * @genpd: PM domain the device belongs to.
- */
-static int __pm_genpd_save_device(struct pm_domain_data *pdd,
-				  struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
-{
-	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
-	struct device *dev = pdd->dev;
-	int ret = 0;
-
-	if (gpd_data->need_restore > 0)
-		return 0;
-
-	/*
-	 * If the value of the need_restore flag is still unknown at this point,
-	 * we trust that pm_genpd_poweroff() has verified that the device is
-	 * already runtime PM suspended.
-	 */
-	if (gpd_data->need_restore < 0) {
-		gpd_data->need_restore = 1;
-		return 0;
-	}
-
-	mutex_unlock(&genpd->lock);
-
-	genpd_start_dev(genpd, dev);
-	ret = genpd_save_dev(genpd, dev);
-	genpd_stop_dev(genpd, dev);
-
-	mutex_lock(&genpd->lock);
-
-	if (!ret)
-		gpd_data->need_restore = 1;
-
-	return ret;
-}
-
-/**
- * __pm_genpd_restore_device - Restore the pre-suspend state of a device.
- * @pdd: Domain data of the device to restore the state of.
- * @genpd: PM domain the device belongs to.
- */
-static void __pm_genpd_restore_device(struct pm_domain_data *pdd,
-				      struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
-{
-	struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd);
-	struct device *dev = pdd->dev;
-	int need_restore = gpd_data->need_restore;
-
-	gpd_data->need_restore = 0;
-	mutex_unlock(&genpd->lock);
-
-	genpd_start_dev(genpd, dev);
-
-	/*
-	 * Call genpd_restore_dev() for recently added devices too (need_restore
-	 * is negative then).
-	 */
-	if (need_restore)
-		genpd_restore_dev(genpd, dev);
-
-	mutex_lock(&genpd->lock);
-}
-
-/**
- * genpd_abort_poweroff - Check if a PM domain power off should be aborted.
- * @genpd: PM domain to check.
- *
- * Return true if a PM domain's status changed to GPD_STATE_ACTIVE during
- * a "power off" operation, which means that a "power on" has occured in the
- * meantime, or if its resume_count field is different from zero, which means
- * that one of its devices has been resumed in the meantime.
- */
-static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
-{
-	return genpd->status == GPD_STATE_WAIT_MASTER
-		|| genpd->status == GPD_STATE_ACTIVE || genpd->resume_count > 0;
-}
-
-/**
  * genpd_queue_power_off_work - Queue up the execution of pm_genpd_poweroff().
  * @genpd: PM domait to power off.
  *
@@ -515,34 +365,26 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
  * @genpd: PM domain to power down.
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
- * have been powered down, run the runtime suspend callbacks provided by all of
- * the @genpd's devices' drivers and remove power from @genpd.
+ * have been powered down, remove power from @genpd.
  */
 static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
-	__releases(&genpd->lock) __acquires(&genpd->lock)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
-	unsigned int not_suspended;
-	int ret = 0;
+	unsigned int not_suspended = 0;
 
- start:
 	/*
 	 * Do not try to power off the domain in the following situations:
 	 * (1) The domain is already in the "power off" state.
-	 * (2) The domain is waiting for its master to power up.
-	 * (3) One of the domain's devices is being resumed right now.
-	 * (4) System suspend is in progress.
+	 * (2) System suspend is in progress.
 	 */
 	if (genpd->status == GPD_STATE_POWER_OFF
-	    || genpd->status == GPD_STATE_WAIT_MASTER
-	    || genpd->resume_count > 0 || genpd->prepared_count > 0)
+	    || genpd->prepared_count > 0)
 		return 0;
 
 	if (atomic_read(&genpd->sd_count) > 0)
 		return -EBUSY;
 
-	not_suspended = 0;
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
 		enum pm_qos_flags_status stat;
 
@@ -560,41 +402,11 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 	if (not_suspended > genpd->in_progress)
 		return -EBUSY;
 
-	if (genpd->poweroff_task) {
-		/*
-		 * Another instance of pm_genpd_poweroff() is executing
-		 * callbacks, so tell it to start over and return.
-		 */
-		genpd->status = GPD_STATE_REPEAT;
-		return 0;
-	}
-
 	if (genpd->gov && genpd->gov->power_down_ok) {
 		if (!genpd->gov->power_down_ok(&genpd->domain))
 			return -EAGAIN;
 	}
 
-	genpd->status = GPD_STATE_BUSY;
-	genpd->poweroff_task = current;
-
-	list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) {
-		ret = atomic_read(&genpd->sd_count) == 0 ?
-			__pm_genpd_save_device(pdd, genpd) : -EBUSY;
-
-		if (genpd_abort_poweroff(genpd))
-			goto out;
-
-		if (ret) {
-			genpd_set_active(genpd);
-			goto out;
-		}
-
-		if (genpd->status == GPD_STATE_REPEAT) {
-			genpd->poweroff_task = NULL;
-			goto start;
-		}
-	}
-
 	if (genpd->cpuidle_data) {
 		/*
 		 * If cpuidle_data is set, cpuidle should turn the domain off
@@ -607,14 +419,14 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		cpuidle_pause_and_lock();
 		genpd->cpuidle_data->idle_state->disabled = false;
 		cpuidle_resume_and_unlock();
-		goto out;
+		return 0;
 	}
 
 	if (genpd->power_off) {
-		if (atomic_read(&genpd->sd_count) > 0) {
-			ret = -EBUSY;
-			goto out;
-		}
+		int ret;
+
+		if (atomic_read(&genpd->sd_count) > 0)
+			return -EBUSY;
 
 		/*
 		 * If sd_count > 0 at this point, one of the subdomains hasn't
@@ -625,10 +437,8 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		 * happen very often).
 		 */
 		ret = genpd_power_off(genpd, true);
-		if (ret == -EBUSY) {
-			genpd_set_active(genpd);
-			goto out;
-		}
+		if (ret)
+			return ret;
 	}
 
 	genpd->status = GPD_STATE_POWER_OFF;
@@ -638,10 +448,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		genpd_queue_power_off_work(link->master);
 	}
 
- out:
-	genpd->poweroff_task = NULL;
-	wake_up_all(&genpd->status_wait_queue);
-	return ret;
+	return 0;
 }
 
 /**
@@ -654,9 +461,9 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 	pm_genpd_poweroff(genpd);
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 }
 
 /**
@@ -670,7 +477,6 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 static int pm_genpd_runtime_suspend(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	struct generic_pm_domain_data *gpd_data;
 	bool (*stop_ok)(struct device *__dev);
 	int ret;
 
@@ -684,10 +490,16 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	if (stop_ok && !stop_ok(dev))
 		return -EBUSY;
 
-	ret = genpd_stop_dev(genpd, dev);
+	ret = genpd_save_dev(genpd, dev);
 	if (ret)
 		return ret;
 
+	ret = genpd_stop_dev(genpd, dev);
+	if (ret) {
+		genpd_restore_dev(genpd, dev, true);
+		return ret;
+	}
+
 	/*
 	 * If power.irq_safe is set, this routine will be run with interrupts
 	 * off, so it can't use mutexes.
@@ -696,16 +508,6 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	mutex_lock(&genpd->lock);
-
-	/*
-	 * If we have an unknown state of the need_restore flag, it means none
-	 * of the runtime PM callbacks has been invoked yet. Let's update the
-	 * flag to reflect that the current state is active.
-	 */
-	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	if (gpd_data->need_restore < 0)
-		gpd_data->need_restore = 0;
-
 	genpd->in_progress++;
 	pm_genpd_poweroff(genpd);
 	genpd->in_progress--;
@@ -725,8 +527,8 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 static int pm_genpd_runtime_resume(struct device *dev)
 {
 	struct generic_pm_domain *genpd;
-	DEFINE_WAIT(wait);
 	int ret;
+	bool timed = true;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -735,39 +537,21 @@ static int pm_genpd_runtime_resume(struct device *dev)
 		return -EINVAL;
 
 	/* If power.irq_safe, the PM domain is never powered off. */
-	if (dev->power.irq_safe)
-		return genpd_start_dev_no_timing(genpd, dev);
+	if (dev->power.irq_safe) {
+		timed = false;
+		goto out;
+	}
 
 	mutex_lock(&genpd->lock);
 	ret = __pm_genpd_poweron(genpd);
-	if (ret) {
-		mutex_unlock(&genpd->lock);
-		return ret;
-	}
-	genpd->status = GPD_STATE_BUSY;
-	genpd->resume_count++;
-	for (;;) {
-		prepare_to_wait(&genpd->status_wait_queue, &wait,
-				TASK_UNINTERRUPTIBLE);
-		/*
-		 * If current is the powering off task, we have been called
-		 * reentrantly from one of the device callbacks, so we should
-		 * not wait.
-		 */
-		if (!genpd->poweroff_task || genpd->poweroff_task == current)
-			break;
-		mutex_unlock(&genpd->lock);
+	mutex_unlock(&genpd->lock);
 
-		schedule();
+	if (ret)
+		return ret;
 
-		mutex_lock(&genpd->lock);
-	}
-	finish_wait(&genpd->status_wait_queue, &wait);
-	__pm_genpd_restore_device(dev->power.subsys_data->domain_data, genpd);
-	genpd->resume_count--;
-	genpd_set_active(genpd);
-	wake_up_all(&genpd->status_wait_queue);
-	mutex_unlock(&genpd->lock);
+ out:
+	genpd_start_dev(genpd, dev, timed);
+	genpd_restore_dev(genpd, dev, timed);
 
 	return 0;
 }
@@ -883,7 +667,7 @@ static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd,
 {
 	struct gpd_link *link;
 
-	if (genpd->status != GPD_STATE_POWER_OFF)
+	if (genpd->status == GPD_STATE_ACTIVE)
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
@@ -960,14 +744,14 @@ static int pm_genpd_prepare(struct device *dev)
 	if (resume_needed(dev, genpd))
 		pm_runtime_resume(dev);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count++ == 0) {
 		genpd->suspended_count = 0;
 		genpd->suspend_power_off = genpd->status == GPD_STATE_POWER_OFF;
 	}
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	if (genpd->suspend_power_off) {
 		pm_runtime_put_noidle(dev);
@@ -1102,7 +886,7 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	pm_genpd_sync_poweron(genpd, true);
 	genpd->suspended_count--;
 
-	return genpd_start_dev(genpd, dev);
+	return genpd_start_dev(genpd, dev, true);
 }
 
 /**
@@ -1230,7 +1014,7 @@ static int pm_genpd_thaw_noirq(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : genpd_start_dev(genpd, dev, true);
 }
 
 /**
@@ -1324,7 +1108,7 @@ static int pm_genpd_restore_noirq(struct device *dev)
 
 	pm_genpd_sync_poweron(genpd, true);
 
-	return genpd_start_dev(genpd, dev);
+	return genpd_start_dev(genpd, dev, true);
 }
 
 /**
@@ -1440,7 +1224,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 		gpd_data->td = *td;
 
 	gpd_data->base.dev = dev;
-	gpd_data->need_restore = -1;
 	gpd_data->td.constraint_changed = true;
 	gpd_data->td.effective_constraint_ns = -1;
 	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
@@ -1502,7 +1285,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1519,7 +1302,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	if (ret)
 		genpd_free_dev_data(dev, gpd_data);
@@ -1563,7 +1346,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	gpd_data = to_gpd_data(pdd);
 	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1578,14 +1361,14 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 
 	list_del_init(&pdd->list_node);
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	genpd_free_dev_data(dev, gpd_data);
 
 	return 0;
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
@@ -1606,17 +1389,9 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 	    || genpd == subdomain)
 		return -EINVAL;
 
- start:
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 	mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
-	if (subdomain->status != GPD_STATE_POWER_OFF
-	    && subdomain->status != GPD_STATE_ACTIVE) {
-		mutex_unlock(&subdomain->lock);
-		genpd_release_lock(genpd);
-		goto start;
-	}
-
 	if (genpd->status == GPD_STATE_POWER_OFF
 	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
 		ret = -EINVAL;
@@ -1644,7 +1419,7 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 
  out:
 	mutex_unlock(&subdomain->lock);
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	return ret;
 }
@@ -1692,8 +1467,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
 		return -EINVAL;
 
- start:
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	list_for_each_entry(link, &genpd->master_links, master_node) {
 		if (link->slave != subdomain)
@@ -1701,13 +1475,6 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 
 		mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
 
-		if (subdomain->status != GPD_STATE_POWER_OFF
-		    && subdomain->status != GPD_STATE_ACTIVE) {
-			mutex_unlock(&subdomain->lock);
-			genpd_release_lock(genpd);
-			goto start;
-		}
-
 		list_del(&link->master_node);
 		list_del(&link->slave_node);
 		kfree(link);
@@ -1720,7 +1487,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 		break;
 	}
 
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 
 	return ret;
 }
@@ -1744,7 +1511,7 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 	if (IS_ERR_OR_NULL(genpd) || state < 0)
 		return -EINVAL;
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	if (genpd->cpuidle_data) {
 		ret = -EEXIST;
@@ -1775,7 +1542,7 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 	genpd_recalc_cpu_exit_latency(genpd);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	return ret;
 
  err:
@@ -1812,7 +1579,7 @@ int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
-	genpd_acquire_lock(genpd);
+	mutex_lock(&genpd->lock);
 
 	cpuidle_data = genpd->cpuidle_data;
 	if (!cpuidle_data) {
@@ -1830,7 +1597,7 @@ int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 	kfree(cpuidle_data);
 
  out:
-	genpd_release_lock(genpd);
+	mutex_unlock(&genpd->lock);
 	return ret;
 }
 
@@ -1912,9 +1679,6 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->in_progress = 0;
 	atomic_set(&genpd->sd_count, 0);
 	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
-	init_waitqueue_head(&genpd->status_wait_queue);
-	genpd->poweroff_task = NULL;
-	genpd->resume_count = 0;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
@@ -1952,6 +1716,7 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+EXPORT_SYMBOL_GPL(pm_genpd_init);
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_OF
 /*
@@ -2125,7 +1890,7 @@ EXPORT_SYMBOL_GPL(of_genpd_get_from_provider);
 
 /**
  * genpd_dev_pm_detach - Detach a device from its PM domain.
- * @dev: Device to attach.
+ * @dev: Device to detach.
  * @power_off: Currently not used
  *
  * Try to locate a corresponding generic PM domain, which the device was
@@ -2183,7 +1948,10 @@ static void genpd_dev_pm_sync(struct device *dev)
  * Both generic and legacy Samsung-specific DT bindings are supported to keep
  * backwards compatibility with existing DTBs.
  *
- * Returns 0 on successfully attached PM domain or negative error code.
+ * Returns 0 on successfully attached PM domain or negative error code. Note
+ * that if a power-domain exists for the device, but it cannot be found or
+ * turned on, then return -EPROBE_DEFER to ensure that the device is not
+ * probed and to re-try again later.
  */
 int genpd_dev_pm_attach(struct device *dev)
 {
@@ -2220,7 +1988,7 @@ int genpd_dev_pm_attach(struct device *dev)
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
 		of_node_put(dev->of_node);
-		return PTR_ERR(pd);
+		return -EPROBE_DEFER;
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
@@ -2238,14 +2006,15 @@ int genpd_dev_pm_attach(struct device *dev)
 		dev_err(dev, "failed to add to PM domain %s: %d",
 			pd->name, ret);
 		of_node_put(dev->of_node);
-		return ret;
+		goto out;
 	}
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
-	pm_genpd_poweron(pd);
+	ret = pm_genpd_poweron(pd);
 
-	return 0;
+out:
+	return ret ? -EPROBE_DEFER : 0;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -2293,9 +2062,6 @@ static int pm_genpd_summary_one(struct seq_file *s,
 {
 	static const char * const status_lookup[] = {
 		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_WAIT_MASTER] = "wait-master",
-		[GPD_STATE_BUSY] = "busy",
-		[GPD_STATE_REPEAT] = "off-in-progress",
 		[GPD_STATE_POWER_OFF] = "off"
 	};
 	struct pm_domain_data *pm_data;
@@ -2309,7 +2075,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
-	seq_printf(s, "%-30s  %-15s  ", genpd->name, status_lookup[genpd->status]);
+	seq_printf(s, "%-30s  %-15s ", genpd->name, status_lookup[genpd->status]);
 
 	/*
 	 * Modifications on the list require holding locks on both
@@ -2344,8 +2110,8 @@ static int pm_genpd_summary_show(struct seq_file *s, void *data)
 	struct generic_pm_domain *genpd;
 	int ret = 0;
 
-	seq_puts(s, "    domain                      status         slaves\n");
-	seq_puts(s, "           /device                                      runtime status\n");
+	seq_puts(s, "domain                          status          slaves\n");
+	seq_puts(s, "    /device                                             runtime status\n");
 	seq_puts(s, "----------------------------------------------------------------------\n");
 
 	ret = mutex_lock_interruptible(&gpd_list_lock);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 30b7bbfdc558..1710c26ba097 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1377,7 +1377,7 @@ 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_suspended_if_enabled(dev))
+			if (pm_runtime_status_suspended(dev))
 				goto Complete;
 
 			pm_runtime_enable(dev);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 3b188f20b43f..eb254497a494 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -51,10 +52,17 @@
  *		order.
  * @dynamic:	not-created from static DT entries.
  * @available:	true/false - marks if this OPP as available or not
+ * @turbo:	true if turbo (boost) OPP
  * @rate:	Frequency in hertz
- * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
+ * @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
+ * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
+ *		frequency from any other OPP's frequency.
  * @dev_opp:	points back to the device_opp struct this opp belongs to
  * @rcu_head:	RCU callback head used for deferred freeing
+ * @np:		OPP's device node.
  *
  * This structure stores the OPP information for a given device.
  */
@@ -63,11 +71,34 @@ struct dev_pm_opp {
 
 	bool available;
 	bool dynamic;
+	bool turbo;
 	unsigned long rate;
+
 	unsigned long u_volt;
+	unsigned long u_volt_min;
+	unsigned long u_volt_max;
+	unsigned long u_amp;
+	unsigned long clock_latency_ns;
 
 	struct device_opp *dev_opp;
 	struct rcu_head rcu_head;
+
+	struct device_node *np;
+};
+
+/**
+ * struct device_list_opp - devices managed by 'struct device_opp'
+ * @node:	list node
+ * @dev:	device to which the struct object belongs
+ * @rcu_head:	RCU callback head used for deferred freeing
+ *
+ * This is an internal data structure maintaining the list of devices that are
+ * managed by 'struct device_opp'.
+ */
+struct device_list_opp {
+	struct list_head node;
+	const struct device *dev;
+	struct rcu_head rcu_head;
 };
 
 /**
@@ -77,10 +108,12 @@ struct dev_pm_opp {
  *		list.
  *		RCU usage: nodes are not modified in the list of device_opp,
  *		however addition is possible and is secured by dev_opp_list_lock
- * @dev:	device pointer
  * @srcu_head:	notifier head to notify the OPP availability changes.
  * @rcu_head:	RCU callback head used for deferred freeing
+ * @dev_list:	list of devices that share these OPPs
  * @opp_list:	list of opps
+ * @np:		struct device_node pointer for opp's DT node.
+ * @shared_opp: OPP is shared between multiple devices.
  *
  * This is an internal data structure maintaining the link to opps attached to
  * a device. This structure is not meant to be shared to users as it is
@@ -93,10 +126,15 @@ struct dev_pm_opp {
 struct device_opp {
 	struct list_head node;
 
-	struct device *dev;
 	struct srcu_notifier_head srcu_head;
 	struct rcu_head rcu_head;
+	struct list_head dev_list;
 	struct list_head opp_list;
+
+	struct device_node *np;
+	unsigned long clock_latency_ns_max;
+	bool shared_opp;
+	struct dev_pm_opp *suspend_opp;
 };
 
 /*
@@ -116,6 +154,38 @@ do {									\
 			   "dev_opp_list_lock protection");		\
 } while (0)
 
+static struct device_list_opp *_find_list_dev(const struct device *dev,
+					      struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_for_each_entry(list_dev, &dev_opp->dev_list, node)
+		if (list_dev->dev == dev)
+			return list_dev;
+
+	return NULL;
+}
+
+static struct device_opp *_managed_opp(const struct device_node *np)
+{
+	struct device_opp *dev_opp;
+
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) {
+		if (dev_opp->np == np) {
+			/*
+			 * Multiple devices can point to the same OPP table and
+			 * so will have same node-pointer, np.
+			 *
+			 * But the OPPs will be considered as shared only if the
+			 * OPP table contains a "opp-shared" property.
+			 */
+			return dev_opp->shared_opp ? dev_opp : NULL;
+		}
+	}
+
+	return NULL;
+}
+
 /**
  * _find_device_opp() - find device_opp struct using device pointer
  * @dev:	device pointer used to lookup device OPPs
@@ -132,21 +202,18 @@ do {									\
  */
 static struct device_opp *_find_device_opp(struct device *dev)
 {
-	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	struct device_opp *dev_opp;
 
-	if (unlikely(IS_ERR_OR_NULL(dev))) {
+	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
-		if (tmp_dev_opp->dev == dev) {
-			dev_opp = tmp_dev_opp;
-			break;
-		}
-	}
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node)
+		if (_find_list_dev(dev, dev_opp))
+			return dev_opp;
 
-	return dev_opp;
+	return ERR_PTR(-ENODEV);
 }
 
 /**
@@ -172,7 +239,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		v = tmp_opp->u_volt;
@@ -204,7 +271,7 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		f = tmp_opp->rate;
@@ -214,6 +281,66 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
 /**
+ * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not
+ * @opp: opp for which turbo mode is being verified
+ *
+ * Turbo OPPs are not for normal use, and can be enabled (under certain
+ * conditions) for short duration of times to finish high throughput work
+ * quickly. Running on them for longer times may overheat the chip.
+ *
+ * Return: true if opp is turbo opp, else false.
+ *
+ * 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
+ * under RCU lock. The pointer returned by the opp_find_freq family must be
+ * used in the same section as the usage of this function with the pointer
+ * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
+ * pointer.
+ */
+bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
+{
+	struct dev_pm_opp *tmp_opp;
+
+	opp_rcu_lockdep_assert();
+
+	tmp_opp = rcu_dereference(opp);
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return false;
+	}
+
+	return tmp_opp->turbo;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
+
+/**
+ * dev_pm_opp_get_max_clock_latency() - Get max clock latency in nanoseconds
+ * @dev:	device for which we do this operation
+ *
+ * Return: This function returns the max clock latency in nanoseconds.
+ *
+ * Locking: This function takes rcu_read_lock().
+ */
+unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	unsigned long clock_latency_ns;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		clock_latency_ns = 0;
+	else
+		clock_latency_ns = dev_opp->clock_latency_ns_max;
+
+	rcu_read_unlock();
+	return clock_latency_ns;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
+
+/**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
  * @dev:	device for which we do this operation
  *
@@ -407,18 +534,57 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
+/* List-dev Helpers */
+static void _kfree_list_dev_rcu(struct rcu_head *head)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = container_of(head, struct device_list_opp, rcu_head);
+	kfree_rcu(list_dev, rcu_head);
+}
+
+static void _remove_list_dev(struct device_list_opp *list_dev,
+			     struct device_opp *dev_opp)
+{
+	list_del(&list_dev->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head,
+		  _kfree_list_dev_rcu);
+}
+
+static struct device_list_opp *_add_list_dev(const struct device *dev,
+					     struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL);
+	if (!list_dev)
+		return NULL;
+
+	/* Initialize list-dev */
+	list_dev->dev = dev;
+	list_add_rcu(&list_dev->node, &dev_opp->dev_list);
+
+	return list_dev;
+}
+
 /**
- * _add_device_opp() - Allocate a new device OPP table
+ * _add_device_opp() - Find device OPP table or allocate a new one
  * @dev:	device for which we do this operation
  *
- * New device node which uses OPPs - used when multiple devices with OPP tables
- * are maintained.
+ * It tries to find an existing table first, if it couldn't find one, it
+ * allocates a new OPP table and returns that.
  *
  * Return: valid device_opp pointer if success, else NULL.
  */
 static struct device_opp *_add_device_opp(struct device *dev)
 {
 	struct device_opp *dev_opp;
+	struct device_list_opp *list_dev;
+
+	/* Check for existing list for 'dev' first */
+	dev_opp = _find_device_opp(dev);
+	if (!IS_ERR(dev_opp))
+		return dev_opp;
 
 	/*
 	 * Allocate a new device OPP table. In the infrequent case where a new
@@ -428,7 +594,14 @@ static struct device_opp *_add_device_opp(struct device *dev)
 	if (!dev_opp)
 		return NULL;
 
-	dev_opp->dev = dev;
+	INIT_LIST_HEAD(&dev_opp->dev_list);
+
+	list_dev = _add_list_dev(dev, dev_opp);
+	if (!list_dev) {
+		kfree(dev_opp);
+		return NULL;
+	}
+
 	srcu_init_notifier_head(&dev_opp->srcu_head);
 	INIT_LIST_HEAD(&dev_opp->opp_list);
 
@@ -438,6 +611,185 @@ static struct device_opp *_add_device_opp(struct device *dev)
 }
 
 /**
+ * _kfree_device_rcu() - Free device_opp RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_device_rcu(struct rcu_head *head)
+{
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+
+	kfree_rcu(device_opp, rcu_head);
+}
+
+/**
+ * _remove_device_opp() - Removes a device OPP table
+ * @dev_opp: device OPP table to be removed.
+ *
+ * Removes/frees device OPP table it it doesn't contain any OPPs.
+ */
+static void _remove_device_opp(struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	if (!list_empty(&dev_opp->opp_list))
+		return;
+
+	list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp,
+				    node);
+
+	_remove_list_dev(list_dev, dev_opp);
+
+	/* dev_list must be empty now */
+	WARN_ON(!list_empty(&dev_opp->dev_list));
+
+	list_del_rcu(&dev_opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+		  _kfree_device_rcu);
+}
+
+/**
+ * _kfree_opp_rcu() - Free OPP RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_opp_rcu(struct rcu_head *head)
+{
+	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+
+	kfree_rcu(opp, rcu_head);
+}
+
+/**
+ * _opp_remove()  - Remove an OPP from a table definition
+ * @dev_opp:	points back to the device_opp struct this opp belongs to
+ * @opp:	pointer to the OPP to remove
+ * @notify:	OPP_EVENT_REMOVE notification should be sent or not
+ *
+ * This function removes an opp definition from the opp list.
+ *
+ * Locking: The internal device_opp and opp structures are RCU protected.
+ * It is assumed that the caller holds required mutex for an RCU updater
+ * strategy.
+ */
+static void _opp_remove(struct device_opp *dev_opp,
+			struct dev_pm_opp *opp, bool notify)
+{
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	if (notify)
+		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+	list_del_rcu(&opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+
+	_remove_device_opp(dev_opp);
+}
+
+/**
+ * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * @dev:	device for which we do this operation
+ * @freq:	OPP to remove with matching 'freq'
+ *
+ * This function removes an opp from the opp list.
+ *
+ * Locking: The internal device_opp 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_remove(struct device *dev, unsigned long freq)
+{
+	struct dev_pm_opp *opp;
+	struct device_opp *dev_opp;
+	bool found = false;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		goto unlock;
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->rate == freq) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
+			 __func__, freq);
+		goto unlock;
+	}
+
+	_opp_remove(dev_opp, opp, true);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
+static struct dev_pm_opp *_allocate_opp(struct device *dev,
+					struct device_opp **dev_opp)
+{
+	struct dev_pm_opp *opp;
+
+	/* allocate new OPP node */
+	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
+	if (!opp)
+		return NULL;
+
+	INIT_LIST_HEAD(&opp->node);
+
+	*dev_opp = _add_device_opp(dev);
+	if (!*dev_opp) {
+		kfree(opp);
+		return NULL;
+	}
+
+	return opp;
+}
+
+static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+		    struct device_opp *dev_opp)
+{
+	struct dev_pm_opp *opp;
+	struct list_head *head = &dev_opp->opp_list;
+
+	/*
+	 * Insert new OPP in order of increasing frequency and discard if
+	 * already present.
+	 *
+	 * Need to use &dev_opp->opp_list in the condition part of the 'for'
+	 * loop, don't replace it with head otherwise it will become an infinite
+	 * loop.
+	 */
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate > opp->rate) {
+			head = &opp->node;
+			continue;
+		}
+
+		if (new_opp->rate < opp->rate)
+			break;
+
+		/* 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);
+
+		return opp->available && new_opp->u_volt == opp->u_volt ?
+			0 : -EEXIST;
+	}
+
+	new_opp->dev_opp = dev_opp;
+	list_add_rcu(&new_opp->node, head);
+
+	return 0;
+}
+
+/**
  * _opp_add_dynamic() - Allocate a dynamic OPP.
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
@@ -467,64 +819,29 @@ static struct device_opp *_add_device_opp(struct device *dev)
 static int _opp_add_dynamic(struct device *dev, unsigned long freq,
 			    long u_volt, bool dynamic)
 {
-	struct device_opp *dev_opp = NULL;
-	struct dev_pm_opp *opp, *new_opp;
-	struct list_head *head;
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
 	int ret;
 
-	/* allocate new OPP node */
-	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);
 
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
 	/* populate the opp table */
 	new_opp->rate = freq;
 	new_opp->u_volt = u_volt;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_opp = _add_device_opp(dev);
-		if (!dev_opp) {
-			ret = -ENOMEM;
-			goto free_opp;
-		}
-
-		head = &dev_opp->opp_list;
-		goto list_add;
-	}
-
-	/*
-	 * Insert new OPP in order of increasing frequency
-	 * and discard if already present
-	 */
-	head = &dev_opp->opp_list;
-	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
-		if (new_opp->rate <= opp->rate)
-			break;
-		else
-			head = &opp->node;
-	}
-
-	/* Duplicate OPPs ? */
-	if (new_opp->rate == opp->rate) {
-		ret = opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
-
-		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);
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
 		goto free_opp;
-	}
 
-list_add:
-	new_opp->dev_opp = dev_opp;
-	list_add_rcu(&new_opp->node, head);
 	mutex_unlock(&dev_opp_list_lock);
 
 	/*
@@ -535,20 +852,52 @@ list_add:
 	return 0;
 
 free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
 	mutex_unlock(&dev_opp_list_lock);
-	kfree(new_opp);
 	return ret;
 }
 
+/* TODO: Support multiple regulators */
+static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev)
+{
+	u32 microvolt[3] = {0};
+	int count, ret;
+
+	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+	if (!count)
+		return 0;
+
+	/* There can be one or three elements here */
+	if (count != 1 && count != 3) {
+		dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
+			__func__, count);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_array(opp->np, "opp-microvolt", microvolt,
+					 count);
+	if (ret) {
+		dev_err(dev, "%s: error parsing opp-microvolt: %d\n", __func__,
+			ret);
+		return -EINVAL;
+	}
+
+	opp->u_volt = microvolt[0];
+	opp->u_volt_min = microvolt[1];
+	opp->u_volt_max = microvolt[2];
+
+	return 0;
+}
+
 /**
- * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
  * @dev:	device for which we do this operation
- * @freq:	Frequency in Hz for this OPP
- * @u_volt:	Voltage in uVolts for this OPP
+ * @np:		device node
  *
- * This function adds an opp definition to the opp list and returns status.
- * The opp is made available by default and it can be controlled using
- * dev_pm_opp_enable/disable functions.
+ * This function adds an opp definition to the opp list and returns status. The
+ * opp can be controlled using dev_pm_opp_enable/disable functions and may be
+ * removed by dev_pm_opp_remove.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -562,108 +911,119 @@ free_opp:
  * -EEXIST	Freq are same and volt are different OR
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
+ * -EINVAL	Failed parsing the OPP node
  */
-int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 {
-	return _opp_add_dynamic(dev, freq, u_volt, true);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
 
-/**
- * _kfree_opp_rcu() - Free OPP RCU handler
- * @head:	RCU head
- */
-static void _kfree_opp_rcu(struct rcu_head *head)
-{
-	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
 
-	kfree_rcu(opp, rcu_head);
-}
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
 
-/**
- * _kfree_device_rcu() - Free device_opp RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
-{
-	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+	ret = of_property_read_u64(np, "opp-hz", &rate);
+	if (ret < 0) {
+		dev_err(dev, "%s: opp-hz not found\n", __func__);
+		goto free_opp;
+	}
 
-	kfree_rcu(device_opp, rcu_head);
-}
+	/*
+	 * Rate is defined as an unsigned long in clk API, and so casting
+	 * explicitly to its type. Must be fixed once rate is 64 bit
+	 * guaranteed in clk API.
+	 */
+	new_opp->rate = (unsigned long)rate;
+	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
+
+	new_opp->np = np;
+	new_opp->dynamic = false;
+	new_opp->available = true;
+
+	if (!of_property_read_u32(np, "clock-latency-ns", &val))
+		new_opp->clock_latency_ns = val;
+
+	ret = opp_get_microvolt(new_opp, dev);
+	if (ret)
+		goto free_opp;
+
+	if (!of_property_read_u32(new_opp->np, "opp-microamp", &val))
+		new_opp->u_amp = val;
+
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (dev_opp->suspend_opp)
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, dev_opp->suspend_opp->rate,
+				 new_opp->rate);
+		else
+			dev_opp->suspend_opp = new_opp;
+	}
+
+	if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max)
+		dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	mutex_unlock(&dev_opp_list_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);
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @dev_opp:	points back to the device_opp struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- *
- * This function removes an opp definition from the opp list.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * It is assumed that the caller holds required mutex for an RCU updater
- * strategy.
- */
-static void _opp_remove(struct device_opp *dev_opp,
-			struct dev_pm_opp *opp)
-{
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
 
-	if (list_empty(&dev_opp->opp_list)) {
-		list_del_rcu(&dev_opp->node);
-		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
-			  _kfree_device_rcu);
-	}
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	return ret;
 }
 
 /**
- * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
- * @freq:	OPP to remove with matching 'freq'
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
  *
- * This function removes an opp from the opp list.
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions.
  *
  * Locking: The internal device_opp 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.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
  */
-void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
-	struct dev_pm_opp *opp;
-	struct device_opp *dev_opp;
-	bool found = false;
-
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
-
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
-		goto unlock;
-
-	list_for_each_entry(opp, &dev_opp->opp_list, node) {
-		if (opp->rate == freq) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
-			 __func__, freq);
-		goto unlock;
-	}
-
-	_opp_remove(dev_opp, opp);
-unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	return _opp_add_dynamic(dev, freq, u_volt, true);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
 /**
  * _opp_set_availability() - helper to set the availability of an opp
@@ -825,28 +1185,179 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
 #ifdef CONFIG_OF
 /**
- * of_init_opp_table() - Initialize opp table from device tree
+ * of_free_opp_table() - Free OPP table entries created from static DT entries
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Register the initial OPP table with the OPP library for given device.
+ * Free OPPs created using static entries present in DT.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly 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.
- *
- * Return:
- * 0		On success OR
- *		Duplicate OPPs (both freq and volt are same) and opp->available
- * -EEXIST	Freq are same and volt are different OR
- *		Duplicate OPPs (both freq and volt are same) and !opp->available
- * -ENOMEM	Memory allocation failure
- * -ENODEV	when 'operating-points' property is not found or is invalid data
- *		in device node.
- * -ENODATA	when empty 'operating-points' property is found
  */
-int of_init_opp_table(struct device *dev)
+void of_free_opp_table(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int error = PTR_ERR(dev_opp);
+
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
+		goto unlock;
+	}
+
+	/* Find if dev_opp manages a single device */
+	if (list_is_singular(&dev_opp->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+			if (!opp->dynamic)
+				_opp_remove(dev_opp, opp, true);
+		}
+	} else {
+		_remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp);
+	}
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_free_opp_table);
+
+void of_cpumask_free_opp_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		of_free_opp_table(cpu_dev);
+	}
+}
+EXPORT_SYMBOL_GPL(of_cpumask_free_opp_table);
+
+/* Returns opp descriptor node from its phandle. Caller must do of_node_put() */
+static struct device_node *
+_of_get_opp_desc_node_from_prop(struct device *dev, const struct property *prop)
+{
+	struct device_node *opp_np;
+
+	opp_np = of_find_node_by_phandle(be32_to_cpup(prop->value));
+	if (!opp_np) {
+		dev_err(dev, "%s: Prop: %s contains invalid opp desc phandle\n",
+			__func__, prop->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return opp_np;
+}
+
+/* Returns opp descriptor node for a device. Caller must do of_node_put() */
+static struct device_node *_of_get_opp_desc_node(struct device *dev)
+{
+	const struct property *prop;
+
+	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
+	if (!prop)
+		return ERR_PTR(-ENODEV);
+	if (!prop->value)
+		return ERR_PTR(-ENODATA);
+
+	/*
+	 * TODO: Support for multiple OPP tables.
+	 *
+	 * There should be only ONE phandle present in "operating-points-v2"
+	 * property.
+	 */
+	if (prop->length != sizeof(__be32)) {
+		dev_err(dev, "%s: Invalid opp desc phandle\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return _of_get_opp_desc_node_from_prop(dev, prop);
+}
+
+/* Initializes OPP tables based on new bindings */
+static int _of_init_opp_table_v2(struct device *dev,
+				 const struct property *prop)
+{
+	struct device_node *opp_np, *np;
+	struct device_opp *dev_opp;
+	int ret = 0, count = 0;
+
+	if (!prop->value)
+		return -ENODATA;
+
+	/* Get opp node */
+	opp_np = _of_get_opp_desc_node_from_prop(dev, prop);
+	if (IS_ERR(opp_np))
+		return PTR_ERR(opp_np);
+
+	dev_opp = _managed_opp(opp_np);
+	if (dev_opp) {
+		/* OPPs are already managed */
+		if (!_add_list_dev(dev, dev_opp))
+			ret = -ENOMEM;
+		goto put_opp_np;
+	}
+
+	/* We have opp-list node now, iterate over it and add OPPs */
+	for_each_available_child_of_node(opp_np, np) {
+		count++;
+
+		ret = _opp_add_static_v2(dev, np);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
+				ret);
+			goto free_table;
+		}
+	}
+
+	/* There should be one of more OPP defined */
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_np;
+	}
+
+	dev_opp = _find_device_opp(dev);
+	if (WARN_ON(IS_ERR(dev_opp))) {
+		ret = PTR_ERR(dev_opp);
+		goto free_table;
+	}
+
+	dev_opp->np = opp_np;
+	dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+
+	of_node_put(opp_np);
+	return 0;
+
+free_table:
+	of_free_opp_table(dev);
+put_opp_np:
+	of_node_put(opp_np);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on old-deprecated bindings */
+static int _of_init_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
@@ -881,47 +1392,177 @@ int of_init_opp_table(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_init_opp_table);
 
 /**
- * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * of_init_opp_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Free OPPs created using static entries present in DT.
+ * Register the initial OPP table with the OPP library for given device.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function indirectly 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.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
  */
-void of_free_opp_table(struct device *dev)
+int of_init_opp_table(struct device *dev)
+{
+	const struct property *prop;
+
+	/*
+	 * OPPs have two version of bindings now. The older one is deprecated,
+	 * try for the new binding first.
+	 */
+	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
+	if (!prop) {
+		/*
+		 * Try old-deprecated bindings for backward compatibility with
+		 * older dtbs.
+		 */
+		return _of_init_opp_table_v1(dev);
+	}
+
+	return _of_init_opp_table_v2(dev, prop);
+}
+EXPORT_SYMBOL_GPL(of_init_opp_table);
+
+int of_cpumask_init_opp_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu, ret = 0;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		ret = of_init_opp_table(cpu_dev);
+		if (ret) {
+			pr_err("%s: couldn't find opp table for cpu:%d, %d\n",
+			       __func__, cpu, ret);
+
+			/* Free all other OPPs */
+			of_cpumask_free_opp_table(cpumask);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_cpumask_init_opp_table);
+
+/* Required only for V1 bindings, as v2 can manage it from DT itself */
+int set_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
 {
+	struct device_list_opp *list_dev;
 	struct device_opp *dev_opp;
-	struct dev_pm_opp *opp, *tmp;
+	struct device *dev;
+	int cpu, ret = 0;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(cpu_dev);
 	if (IS_ERR(dev_opp)) {
-		int error = PTR_ERR(dev_opp);
-		if (error != -ENODEV)
-			WARN(1, "%s: dev_opp: %d\n",
-			     IS_ERR_OR_NULL(dev) ?
-					"Invalid device" : dev_name(dev),
-			     error);
-		return;
+		ret = -EINVAL;
+		goto out_rcu_read_unlock;
 	}
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	for_each_cpu(cpu, cpumask) {
+		if (cpu == cpu_dev->id)
+			continue;
 
-	/* Free static OPPs */
-	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
-		if (!opp->dynamic)
-			_opp_remove(dev_opp, opp);
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+
+		list_dev = _add_list_dev(dev, dev_opp);
+		if (!list_dev) {
+			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
 	}
+out_rcu_read_unlock:
+	rcu_read_unlock();
 
-	mutex_unlock(&dev_opp_list_lock);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(of_free_opp_table);
+EXPORT_SYMBOL_GPL(set_cpus_sharing_opps);
+
+/*
+ * Works only for OPP v2 bindings.
+ *
+ * cpumask should be already set to mask of cpu_dev->id.
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+int of_get_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_node *np, *tmp_np;
+	struct device *tcpu_dev;
+	int cpu, ret = 0;
+
+	/* Get OPP descriptor node */
+	np = _of_get_opp_desc_node(cpu_dev);
+	if (IS_ERR(np)) {
+		dev_dbg(cpu_dev, "%s: Couldn't find opp node: %ld\n", __func__,
+			PTR_ERR(np));
+		return -ENOENT;
+	}
+
+	/* OPPs are shared ? */
+	if (!of_property_read_bool(np, "opp-shared"))
+		goto put_cpu_node;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			ret = -ENODEV;
+			goto put_cpu_node;
+		}
+
+		/* Get OPP descriptor node */
+		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		if (IS_ERR(tmp_np)) {
+			dev_err(tcpu_dev, "%s: Couldn't find opp node: %ld\n",
+				__func__, PTR_ERR(tmp_np));
+			ret = PTR_ERR(tmp_np);
+			goto put_cpu_node;
+		}
+
+		/* CPUs are sharing opp node */
+		if (np == tmp_np)
+			cpumask_set_cpu(cpu, cpumask);
+
+		of_node_put(tmp_np);
+	}
+
+put_cpu_node:
+	of_node_put(np);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_get_cpus_sharing_opps);
 #endif
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index f1a5d95e7b20..998fa6b23084 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -73,6 +73,8 @@ extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
 extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
 extern int pm_qos_sysfs_add_flags(struct device *dev);
 extern void pm_qos_sysfs_remove_flags(struct device *dev);
+extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev);
+extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev);
 
 #else /* CONFIG_PM */
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index e56d538d039e..7f3646e459cb 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -883,3 +883,40 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
 }
+
+/**
+ * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace
+ * @dev: Device whose latency tolerance to expose
+ */
+int dev_pm_qos_expose_latency_tolerance(struct device *dev)
+{
+	int ret;
+
+	if (!dev->power.set_latency_tolerance)
+		return -EINVAL;
+
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	ret = pm_qos_sysfs_add_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance);
+
+/**
+ * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace
+ * @dev: Device whose latency tolerance to hide
+ */
+void dev_pm_qos_hide_latency_tolerance(struct device *dev)
+{
+	mutex_lock(&dev_pm_qos_sysfs_mtx);
+	pm_qos_sysfs_remove_latency_tolerance(dev);
+	mutex_unlock(&dev_pm_qos_sysfs_mtx);
+
+	/* Remove the request from user space now */
+	pm_runtime_get_sync(dev);
+	dev_pm_qos_update_user_latency_tolerance(dev,
+		PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT);
+	pm_runtime_put(dev);
+}
+EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance);
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index d2be3f9c211c..a7b46798c81d 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -738,6 +738,17 @@ void pm_qos_sysfs_remove_flags(struct device *dev)
 	sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group);
 }
 
+int pm_qos_sysfs_add_latency_tolerance(struct device *dev)
+{
+	return sysfs_merge_group(&dev->kobj,
+				 &pm_qos_latency_tolerance_attr_group);
+}
+
+void pm_qos_sysfs_remove_latency_tolerance(struct device *dev)
+{
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
+}
+
 void rpm_sysfs_remove(struct device *dev)
 {
 	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);