Merge tag 'pm-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These update PCI and ACPI power management (improved handling of ACPI
  power resources and PCIe link delays, fixes related to corner cases,
  hibernation handling rework), fix and extend the operating performance
  points (OPP) framework, add new cpufreq drivers for Raspberry Pi and
  imx8m chips, update some other cpufreq drivers, clean up assorted
  pieces of PM code and documentation and update tools.

  Specifics:

   - Improve the handling of shared ACPI power resources in the PCI bus
     type layer (Mika Westerberg).

   - Make the PCI layer take link delays required by the PCIe spec into
     account as appropriate and avoid polling devices in D3cold for PME
     (Mika Westerberg).

   - Fix some corner case issues in ACPI device power management and in
     the PCI bus type layer, optimiza and clean up the handling of
     runtime-suspended PCI devices during system-wide transitions to
     sleep states (Rafael Wysocki).

   - Rework hibernation handling in the ACPI core and the PCI bus type
     to resume runtime-suspended devices before hibernation (which
     allows some functional problems to be avoided) and fix some ACPI
     power management issues related to hiberation (Rafael Wysocki).

   - Extend the operating performance points (OPP) framework to support
     a wider range of devices (Rajendra Nayak, Stehpen Boyd).

   - Fix issues related to genpd_virt_devs and issues with platforms
     using the set_opp() callback in the OPP framework (Viresh Kumar,
     Dmitry Osipenko).

   - Add new cpufreq driver for Raspberry Pi (Nicolas Saenz Julienne).

   - Add new cpufreq driver for imx8m and imx7d chips (Leonard Crestez).

   - Fix and clean up the pcc-cpufreq, brcmstb-avs-cpufreq, s5pv210, and
     armada-37xx cpufreq drivers (David Arcari, Florian Fainelli, Paweł
     Chmiel, YueHaibing).

   - Clean up and fix the cpufreq core (Viresh Kumar, Daniel Lezcano).

   - Fix minor issue in the ACPI system sleep support code and export
     one function from it (Lenny Szubowicz, Dexuan Cui).

   - Clean up assorted pieces of PM code and documentation (Kefeng Wang,
     Andy Shevchenko, Bart Van Assche, Greg Kroah-Hartman, Fuqian Huang,
     Geert Uytterhoeven, Mathieu Malaterre, Rafael Wysocki).

   - Update the pm-graph utility to v5.4 (Todd Brandt).

   - Fix and clean up the cpupower utility (Abhishek Goel, Nick Black)"

* tag 'pm-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (57 commits)
  ACPI: PM: Make acpi_sleep_state_supported() non-static
  PM: sleep: Drop dev_pm_skip_next_resume_phases()
  ACPI: PM: Unexport acpi_device_get_power()
  Documentation: ABI: power: Add missing newline at end of file
  ACPI: PM: Drop unused function and function header
  ACPI: PM: Introduce "poweroff" callbacks for ACPI PM domain and LPSS
  ACPI: PM: Simplify and fix PM domain hibernation callbacks
  PCI: PM: Simplify bus-level hibernation callbacks
  PM: ACPI/PCI: Resume all devices during hibernation
  cpufreq: Avoid calling cpufreq_verify_current_freq() from handle_update()
  cpufreq: Consolidate cpufreq_update_current_freq() and __cpufreq_get()
  kernel: power: swap: use kzalloc() instead of kmalloc() followed by memset()
  cpufreq: Don't skip frequency validation for has_target() drivers
  PCI: PM/ACPI: Refresh all stale power state data in pci_pm_complete()
  PCI / ACPI: Add _PR0 dependent devices
  ACPI / PM: Introduce concept of a _PR0 dependent device
  PCI / ACPI: Use cached ACPI device state to get PCI device power state
  ACPI: PM: Allow transitions to D0 to occur in special cases
  ACPI: PM: Avoid evaluating _PS3 on transitions from D3hot to D3cold
  cpufreq: Use has_target() instead of !setpolicy
  ...

6 files changed, 362 insertions, 85 deletions

diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c
index 6116b0fb86d4..433376e819bb 100644
--- a/drivers/acpi/acpi_lpit.c
+++ b/drivers/acpi/acpi_lpit.c
@@ -129,7 +129,7 @@ static void lpit_update_residency(struct lpit_residency_info *info,
 
 static void lpit_process(u64 begin, u64 end)
 {
-	while (begin + sizeof(struct acpi_lpit_native) < end) {
+	while (begin + sizeof(struct acpi_lpit_native) <= end) {
 		struct acpi_lpit_native *lpit_native = (struct acpi_lpit_native *)begin;
 
 		if (!lpit_native->header.type && !lpit_native->header.flags) {
@@ -148,7 +148,6 @@ static void lpit_process(u64 begin, u64 end)
 void acpi_init_lpit(void)
 {
 	acpi_status status;
-	u64 lpit_begin;
 	struct acpi_table_lpit *lpit;
 
 	status = acpi_get_table(ACPI_SIG_LPIT, 0, (struct acpi_table_header **)&lpit);
@@ -156,6 +155,6 @@ void acpi_init_lpit(void)
 	if (ACPI_FAILURE(status))
 		return;
 
-	lpit_begin = (u64)lpit + sizeof(*lpit);
-	lpit_process(lpit_begin, lpit_begin + lpit->header.length);
+	lpit_process((u64)lpit + sizeof(*lpit),
+		     (u64)lpit + lpit->header.length);
 }
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 23484aa877b6..398451839178 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -1061,6 +1061,13 @@ static int acpi_lpss_suspend_noirq(struct device *dev)
 	int ret;
 
 	if (pdata->dev_desc->resume_from_noirq) {
+		/*
+		 * The driver's ->suspend_late callback will be invoked by
+		 * acpi_lpss_do_suspend_late(), with the assumption that the
+		 * driver really wanted to run that code in ->suspend_noirq, but
+		 * it could not run after acpi_dev_suspend() and the driver
+		 * expected the latter to be called in the "late" phase.
+		 */
 		ret = acpi_lpss_do_suspend_late(dev);
 		if (ret)
 			return ret;
@@ -1091,16 +1098,99 @@ static int acpi_lpss_resume_noirq(struct device *dev)
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 	int ret;
 
-	ret = acpi_subsys_resume_noirq(dev);
+	/* Follow acpi_subsys_resume_noirq(). */
+	if (dev_pm_may_skip_resume(dev))
+		return 0;
+
+	if (dev_pm_smart_suspend_and_suspended(dev))
+		pm_runtime_set_active(dev);
+
+	ret = pm_generic_resume_noirq(dev);
 	if (ret)
 		return ret;
 
-	if (!dev_pm_may_skip_resume(dev) && pdata->dev_desc->resume_from_noirq)
-		ret = acpi_lpss_do_resume_early(dev);
+	if (!pdata->dev_desc->resume_from_noirq)
+		return 0;
 
-	return ret;
+	/*
+	 * The driver's ->resume_early callback will be invoked by
+	 * acpi_lpss_do_resume_early(), with the assumption that the driver
+	 * really wanted to run that code in ->resume_noirq, but it could not
+	 * run before acpi_dev_resume() and the driver expected the latter to be
+	 * called in the "early" phase.
+	 */
+	return acpi_lpss_do_resume_early(dev);
+}
+
+static int acpi_lpss_do_restore_early(struct device *dev)
+{
+	int ret = acpi_lpss_resume(dev);
+
+	return ret ? ret : pm_generic_restore_early(dev);
 }
 
+static int acpi_lpss_restore_early(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	return acpi_lpss_do_restore_early(dev);
+}
+
+static int acpi_lpss_restore_noirq(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+	int ret;
+
+	ret = pm_generic_restore_noirq(dev);
+	if (ret)
+		return ret;
+
+	if (!pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	/* This is analogous to what happens in acpi_lpss_resume_noirq(). */
+	return acpi_lpss_do_restore_early(dev);
+}
+
+static int acpi_lpss_do_poweroff_late(struct device *dev)
+{
+	int ret = pm_generic_poweroff_late(dev);
+
+	return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev));
+}
+
+static int acpi_lpss_poweroff_late(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (dev_pm_smart_suspend_and_suspended(dev))
+		return 0;
+
+	if (pdata->dev_desc->resume_from_noirq)
+		return 0;
+
+	return acpi_lpss_do_poweroff_late(dev);
+}
+
+static int acpi_lpss_poweroff_noirq(struct device *dev)
+{
+	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
+
+	if (dev_pm_smart_suspend_and_suspended(dev))
+		return 0;
+
+	if (pdata->dev_desc->resume_from_noirq) {
+		/* This is analogous to the acpi_lpss_suspend_noirq() case. */
+		int ret = acpi_lpss_do_poweroff_late(dev);
+		if (ret)
+			return ret;
+	}
+
+	return pm_generic_poweroff_noirq(dev);
+}
 #endif /* CONFIG_PM_SLEEP */
 
 static int acpi_lpss_runtime_suspend(struct device *dev)
@@ -1134,14 +1224,11 @@ static struct dev_pm_domain acpi_lpss_pm_domain = {
 		.resume_noirq = acpi_lpss_resume_noirq,
 		.resume_early = acpi_lpss_resume_early,
 		.freeze = acpi_subsys_freeze,
-		.freeze_late = acpi_subsys_freeze_late,
-		.freeze_noirq = acpi_subsys_freeze_noirq,
-		.thaw_noirq = acpi_subsys_thaw_noirq,
-		.poweroff = acpi_subsys_suspend,
-		.poweroff_late = acpi_lpss_suspend_late,
-		.poweroff_noirq = acpi_lpss_suspend_noirq,
-		.restore_noirq = acpi_lpss_resume_noirq,
-		.restore_early = acpi_lpss_resume_early,
+		.poweroff = acpi_subsys_poweroff,
+		.poweroff_late = acpi_lpss_poweroff_late,
+		.poweroff_noirq = acpi_lpss_poweroff_noirq,
+		.restore_noirq = acpi_lpss_restore_noirq,
+		.restore_early = acpi_lpss_restore_early,
 #endif
 		.runtime_suspend = acpi_lpss_runtime_suspend,
 		.runtime_resume = acpi_lpss_runtime_resume,
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index e54956ae93d3..28cffaaf9d82 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -45,6 +45,19 @@ const char *acpi_power_state_string(int state)
 	}
 }
 
+static int acpi_dev_pm_explicit_get(struct acpi_device *device, int *state)
+{
+	unsigned long long psc;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(device->handle, "_PSC", NULL, &psc);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	*state = psc;
+	return 0;
+}
+
 /**
  * acpi_device_get_power - Get power state of an ACPI device.
  * @device: Device to get the power state of.
@@ -53,10 +66,16 @@ const char *acpi_power_state_string(int state)
  * This function does not update the device's power.state field, but it may
  * update its parent's power.state field (when the parent's power state is
  * unknown and the device's power state turns out to be D0).
+ *
+ * Also, it does not update power resource reference counters to ensure that
+ * the power state returned by it will be persistent and it may return a power
+ * state shallower than previously set by acpi_device_set_power() for @device
+ * (if that power state depends on any power resources).
  */
 int acpi_device_get_power(struct acpi_device *device, int *state)
 {
 	int result = ACPI_STATE_UNKNOWN;
+	int error;
 
 	if (!device || !state)
 		return -EINVAL;
@@ -73,18 +92,16 @@ int acpi_device_get_power(struct acpi_device *device, int *state)
 	 * if available.
 	 */
 	if (device->power.flags.power_resources) {
-		int error = acpi_power_get_inferred_state(device, &result);
+		error = acpi_power_get_inferred_state(device, &result);
 		if (error)
 			return error;
 	}
 	if (device->power.flags.explicit_get) {
-		acpi_handle handle = device->handle;
-		unsigned long long psc;
-		acpi_status status;
+		int psc;
 
-		status = acpi_evaluate_integer(handle, "_PSC", NULL, &psc);
-		if (ACPI_FAILURE(status))
-			return -ENODEV;
+		error = acpi_dev_pm_explicit_get(device, &psc);
+		if (error)
+			return error;
 
 		/*
 		 * The power resources settings may indicate a power state
@@ -118,7 +135,6 @@ int acpi_device_get_power(struct acpi_device *device, int *state)
 
 	return 0;
 }
-EXPORT_SYMBOL(acpi_device_get_power);
 
 static int acpi_dev_pm_explicit_set(struct acpi_device *adev, int state)
 {
@@ -152,7 +168,8 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 
 	/* Make sure this is a valid target state */
 
-	if (state == device->power.state) {
+	/* There is a special case for D0 addressed below. */
+	if (state > ACPI_STATE_D0 && state == device->power.state) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] already in %s\n",
 				  device->pnp.bus_id,
 				  acpi_power_state_string(state)));
@@ -202,9 +219,15 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 			return -ENODEV;
 		}
 
-		result = acpi_dev_pm_explicit_set(device, state);
-		if (result)
-			goto end;
+		/*
+		 * If the device goes from D3hot to D3cold, _PS3 has been
+		 * evaluated for it already, so skip it in that case.
+		 */
+		if (device->power.state < ACPI_STATE_D3_HOT) {
+			result = acpi_dev_pm_explicit_set(device, state);
+			if (result)
+				goto end;
+		}
 
 		if (device->power.flags.power_resources)
 			result = acpi_power_transition(device, target_state);
@@ -214,6 +237,30 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 			if (result)
 				goto end;
 		}
+
+		if (device->power.state == ACPI_STATE_D0) {
+			int psc;
+
+			/* Nothing to do here if _PSC is not present. */
+			if (!device->power.flags.explicit_get)
+				return 0;
+
+			/*
+			 * The power state of the device was set to D0 last
+			 * time, but that might have happened before a
+			 * system-wide transition involving the platform
+			 * firmware, so it may be necessary to evaluate _PS0
+			 * for the device here.  However, use extra care here
+			 * and evaluate _PSC to check the device's current power
+			 * state, and only invoke _PS0 if the evaluation of _PSC
+			 * is successful and it returns a power state different
+			 * from D0.
+			 */
+			result = acpi_dev_pm_explicit_get(device, &psc);
+			if (result || psc == ACPI_STATE_D0)
+				return 0;
+		}
+
 		result = acpi_dev_pm_explicit_set(device, ACPI_STATE_D0);
 	}
 
@@ -1073,7 +1120,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq);
  * acpi_subsys_resume_noirq - Run the device driver's "noirq" resume callback.
  * @dev: Device to handle.
  */
-int acpi_subsys_resume_noirq(struct device *dev)
+static int acpi_subsys_resume_noirq(struct device *dev)
 {
 	if (dev_pm_may_skip_resume(dev))
 		return 0;
@@ -1088,7 +1135,6 @@ int acpi_subsys_resume_noirq(struct device *dev)
 
 	return pm_generic_resume_noirq(dev);
 }
-EXPORT_SYMBOL_GPL(acpi_subsys_resume_noirq);
 
 /**
  * acpi_subsys_resume_early - Resume device using ACPI.
@@ -1098,12 +1144,11 @@ EXPORT_SYMBOL_GPL(acpi_subsys_resume_noirq);
  * generic early resume procedure for it during system transition into the
  * working state.
  */
-int acpi_subsys_resume_early(struct device *dev)
+static int acpi_subsys_resume_early(struct device *dev)
 {
 	int ret = acpi_dev_resume(dev);
 	return ret ? ret : pm_generic_resume_early(dev);
 }
-EXPORT_SYMBOL_GPL(acpi_subsys_resume_early);
 
 /**
  * acpi_subsys_freeze - Run the device driver's freeze callback.
@@ -1112,65 +1157,81 @@ EXPORT_SYMBOL_GPL(acpi_subsys_resume_early);
 int acpi_subsys_freeze(struct device *dev)
 {
 	/*
-	 * This used to be done in acpi_subsys_prepare() for all devices and
-	 * some drivers may depend on it, so do it here.  Ideally, however,
-	 * runtime-suspended devices should not be touched during freeze/thaw
-	 * transitions.
+	 * Resume all runtime-suspended devices before creating a snapshot
+	 * image of system memory, because the restore kernel generally cannot
+	 * be expected to always handle them consistently and they need to be
+	 * put into the runtime-active metastate during system resume anyway,
+	 * so it is better to ensure that the state saved in the image will be
+	 * always consistent with that.
 	 */
-	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND))
-		pm_runtime_resume(dev);
+	pm_runtime_resume(dev);
 
 	return pm_generic_freeze(dev);
 }
 EXPORT_SYMBOL_GPL(acpi_subsys_freeze);
 
 /**
- * acpi_subsys_freeze_late - Run the device driver's "late" freeze callback.
- * @dev: Device to handle.
+ * acpi_subsys_restore_early - Restore device using ACPI.
+ * @dev: Device to restore.
  */
-int acpi_subsys_freeze_late(struct device *dev)
+int acpi_subsys_restore_early(struct device *dev)
 {
+	int ret = acpi_dev_resume(dev);
+	return ret ? ret : pm_generic_restore_early(dev);
+}
+EXPORT_SYMBOL_GPL(acpi_subsys_restore_early);
 
-	if (dev_pm_smart_suspend_and_suspended(dev))
-		return 0;
+/**
+ * acpi_subsys_poweroff - Run the device driver's poweroff callback.
+ * @dev: Device to handle.
+ *
+ * Follow PCI and resume devices from runtime suspend before running their
+ * system poweroff callbacks, unless the driver can cope with runtime-suspended
+ * devices during system suspend and there are no ACPI-specific reasons for
+ * resuming them.
+ */
+int acpi_subsys_poweroff(struct device *dev)
+{
+	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
+	    acpi_dev_needs_resume(dev, ACPI_COMPANION(dev)))
+		pm_runtime_resume(dev);
 
-	return pm_generic_freeze_late(dev);
+	return pm_generic_poweroff(dev);
 }
-EXPORT_SYMBOL_GPL(acpi_subsys_freeze_late);
+EXPORT_SYMBOL_GPL(acpi_subsys_poweroff);
 
 /**
- * acpi_subsys_freeze_noirq - Run the device driver's "noirq" freeze callback.
+ * acpi_subsys_poweroff_late - Run the device driver's poweroff callback.
  * @dev: Device to handle.
+ *
+ * Carry out the generic late poweroff procedure for @dev and use ACPI to put
+ * it into a low-power state during system transition into a sleep state.
  */
-int acpi_subsys_freeze_noirq(struct device *dev)
+static int acpi_subsys_poweroff_late(struct device *dev)
 {
+	int ret;
 
 	if (dev_pm_smart_suspend_and_suspended(dev))
 		return 0;
 
-	return pm_generic_freeze_noirq(dev);
+	ret = pm_generic_poweroff_late(dev);
+	if (ret)
+		return ret;
+
+	return acpi_dev_suspend(dev, device_may_wakeup(dev));
 }
-EXPORT_SYMBOL_GPL(acpi_subsys_freeze_noirq);
 
 /**
- * acpi_subsys_thaw_noirq - Run the device driver's "noirq" thaw callback.
- * @dev: Device to handle.
+ * acpi_subsys_poweroff_noirq - Run the driver's "noirq" poweroff callback.
+ * @dev: Device to suspend.
  */
-int acpi_subsys_thaw_noirq(struct device *dev)
+static int acpi_subsys_poweroff_noirq(struct device *dev)
 {
-	/*
-	 * If the device is in runtime suspend, the "thaw" code may not work
-	 * correctly with it, so skip the driver callback and make the PM core
-	 * skip all of the subsequent "thaw" callbacks for the device.
-	 */
-	if (dev_pm_smart_suspend_and_suspended(dev)) {
-		dev_pm_skip_next_resume_phases(dev);
+	if (dev_pm_smart_suspend_and_suspended(dev))
 		return 0;
-	}
 
-	return pm_generic_thaw_noirq(dev);
+	return pm_generic_poweroff_noirq(dev);
 }
-EXPORT_SYMBOL_GPL(acpi_subsys_thaw_noirq);
 #endif /* CONFIG_PM_SLEEP */
 
 static struct dev_pm_domain acpi_general_pm_domain = {
@@ -1186,14 +1247,10 @@ static struct dev_pm_domain acpi_general_pm_domain = {
 		.resume_noirq = acpi_subsys_resume_noirq,
 		.resume_early = acpi_subsys_resume_early,
 		.freeze = acpi_subsys_freeze,
-		.freeze_late = acpi_subsys_freeze_late,
-		.freeze_noirq = acpi_subsys_freeze_noirq,
-		.thaw_noirq = acpi_subsys_thaw_noirq,
-		.poweroff = acpi_subsys_suspend,
-		.poweroff_late = acpi_subsys_suspend_late,
-		.poweroff_noirq = acpi_subsys_suspend_noirq,
-		.restore_noirq = acpi_subsys_resume_noirq,
-		.restore_early = acpi_subsys_resume_early,
+		.poweroff = acpi_subsys_poweroff,
+		.poweroff_late = acpi_subsys_poweroff_late,
+		.poweroff_noirq = acpi_subsys_poweroff_noirq,
+		.restore_early = acpi_subsys_restore_early,
 #endif
 	},
 };
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index f6157d4d637a..f4c2fe6be4f2 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -139,8 +139,15 @@ int acpi_power_get_inferred_state(struct acpi_device *device, int *state);
 int acpi_power_on_resources(struct acpi_device *device, int state);
 int acpi_power_transition(struct acpi_device *device, int state);
 
+/* --------------------------------------------------------------------------
+                              Device Power Management
+   -------------------------------------------------------------------------- */
+int acpi_device_get_power(struct acpi_device *device, int *state);
 int acpi_wakeup_device_init(void);
 
+/* --------------------------------------------------------------------------
+                                  Processor
+   -------------------------------------------------------------------------- */
 #ifdef CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC
 void acpi_early_processor_set_pdc(void);
 #else
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index a916417b9e70..fe1e7bc91a5e 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -42,6 +42,11 @@ ACPI_MODULE_NAME("power");
 #define ACPI_POWER_RESOURCE_STATE_ON	0x01
 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF
 
+struct acpi_power_dependent_device {
+	struct device *dev;
+	struct list_head node;
+};
+
 struct acpi_power_resource {
 	struct acpi_device device;
 	struct list_head list_node;
@@ -51,6 +56,7 @@ struct acpi_power_resource {
 	unsigned int ref_count;
 	bool wakeup_enabled;
 	struct mutex resource_lock;
+	struct list_head dependents;
 };
 
 struct acpi_power_resource_entry {
@@ -232,8 +238,121 @@ static int acpi_power_get_list_state(struct list_head *list, int *state)
 	return 0;
 }
 
+static int
+acpi_power_resource_add_dependent(struct acpi_power_resource *resource,
+				  struct device *dev)
+{
+	struct acpi_power_dependent_device *dep;
+	int ret = 0;
+
+	mutex_lock(&resource->resource_lock);
+	list_for_each_entry(dep, &resource->dependents, node) {
+		/* Only add it once */
+		if (dep->dev == dev)
+			goto unlock;
+	}
+
+	dep = kzalloc(sizeof(*dep), GFP_KERNEL);
+	if (!dep) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	dep->dev = dev;
+	list_add_tail(&dep->node, &resource->dependents);
+	dev_dbg(dev, "added power dependency to [%s]\n", resource->name);
+
+unlock:
+	mutex_unlock(&resource->resource_lock);
+	return ret;
+}
+
+static void
+acpi_power_resource_remove_dependent(struct acpi_power_resource *resource,
+				     struct device *dev)
+{
+	struct acpi_power_dependent_device *dep;
+
+	mutex_lock(&resource->resource_lock);
+	list_for_each_entry(dep, &resource->dependents, node) {
+		if (dep->dev == dev) {
+			list_del(&dep->node);
+			kfree(dep);
+			dev_dbg(dev, "removed power dependency to [%s]\n",
+				resource->name);
+			break;
+		}
+	}
+	mutex_unlock(&resource->resource_lock);
+}
+
+/**
+ * acpi_device_power_add_dependent - Add dependent device of this ACPI device
+ * @adev: ACPI device pointer
+ * @dev: Dependent device
+ *
+ * If @adev has non-empty _PR0 the @dev is added as dependent device to all
+ * power resources returned by it. This means that whenever these power
+ * resources are turned _ON the dependent devices get runtime resumed. This
+ * is needed for devices such as PCI to allow its driver to re-initialize
+ * it after it went to D0uninitialized.
+ *
+ * If @adev does not have _PR0 this does nothing.
+ *
+ * Returns %0 in case of success and negative errno otherwise.
+ */
+int acpi_device_power_add_dependent(struct acpi_device *adev,
+				    struct device *dev)
+{
+	struct acpi_power_resource_entry *entry;
+	struct list_head *resources;
+	int ret;
+
+	if (!adev->flags.power_manageable)
+		return 0;
+
+	resources = &adev->power.states[ACPI_STATE_D0].resources;
+	list_for_each_entry(entry, resources, node) {
+		ret = acpi_power_resource_add_dependent(entry->resource, dev);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	list_for_each_entry(entry, resources, node)
+		acpi_power_resource_remove_dependent(entry->resource, dev);
+
+	return ret;
+}
+
+/**
+ * acpi_device_power_remove_dependent - Remove dependent device
+ * @adev: ACPI device pointer
+ * @dev: Dependent device
+ *
+ * Does the opposite of acpi_device_power_add_dependent() and removes the
+ * dependent device if it is found. Can be called to @adev that does not
+ * have _PR0 as well.
+ */
+void acpi_device_power_remove_dependent(struct acpi_device *adev,
+					struct device *dev)
+{
+	struct acpi_power_resource_entry *entry;
+	struct list_head *resources;
+
+	if (!adev->flags.power_manageable)
+		return;
+
+	resources = &adev->power.states[ACPI_STATE_D0].resources;
+	list_for_each_entry_reverse(entry, resources, node)
+		acpi_power_resource_remove_dependent(entry->resource, dev);
+}
+
 static int __acpi_power_on(struct acpi_power_resource *resource)
 {
+	struct acpi_power_dependent_device *dep;
 	acpi_status status = AE_OK;
 
 	status = acpi_evaluate_object(resource->device.handle, "_ON", NULL, NULL);
@@ -243,6 +362,21 @@ static int __acpi_power_on(struct acpi_power_resource *resource)
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n",
 			  resource->name));
 
+	/*
+	 * If there are other dependents on this power resource we need to
+	 * resume them now so that their drivers can re-initialize the
+	 * hardware properly after it went back to D0.
+	 */
+	if (list_empty(&resource->dependents) ||
+	    list_is_singular(&resource->dependents))
+		return 0;
+
+	list_for_each_entry(dep, &resource->dependents, node) {
+		dev_dbg(dep->dev, "runtime resuming because [%s] turned on\n",
+			resource->name);
+		pm_request_resume(dep->dev);
+	}
+
 	return 0;
 }
 
@@ -810,6 +944,7 @@ int acpi_add_power_resource(acpi_handle handle)
 				ACPI_STA_DEFAULT);
 	mutex_init(&resource->resource_lock);
 	INIT_LIST_HEAD(&resource->list_node);
+	INIT_LIST_HEAD(&resource->dependents);
 	resource->name = device->pnp.bus_id;
 	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_POWER_CLASS);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 8ff08e531443..f0fe7c15d657 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -77,7 +77,7 @@ static int acpi_sleep_prepare(u32 acpi_state)
 	return 0;
 }
 
-static bool acpi_sleep_state_supported(u8 sleep_state)
+bool acpi_sleep_state_supported(u8 sleep_state)
 {
 	acpi_status status;
 	u8 type_a, type_b;
@@ -452,14 +452,6 @@ static int acpi_pm_prepare(void)
 	return error;
 }
 
-static int find_powerf_dev(struct device *dev, void *data)
-{
-	struct acpi_device *device = to_acpi_device(dev);
-	const char *hid = acpi_device_hid(device);
-
-	return !strcmp(hid, ACPI_BUTTON_HID_POWERF);
-}
-
 /**
  *	acpi_pm_finish - Instruct the platform to leave a sleep state.
  *
@@ -468,7 +460,7 @@ static int find_powerf_dev(struct device *dev, void *data)
  */
 static void acpi_pm_finish(void)
 {
-	struct device *pwr_btn_dev;
+	struct acpi_device *pwr_btn_adev;
 	u32 acpi_state = acpi_target_sleep_state;
 
 	acpi_ec_unblock_transactions();
@@ -499,11 +491,11 @@ static void acpi_pm_finish(void)
 		return;
 
 	pwr_btn_event_pending = false;
-	pwr_btn_dev = bus_find_device(&acpi_bus_type, NULL, NULL,
-				      find_powerf_dev);
-	if (pwr_btn_dev) {
-		pm_wakeup_event(pwr_btn_dev, 0);
-		put_device(pwr_btn_dev);
+	pwr_btn_adev = acpi_dev_get_first_match_dev(ACPI_BUTTON_HID_POWERF,
+						    NULL, -1);
+	if (pwr_btn_adev) {
+		pm_wakeup_event(&pwr_btn_adev->dev, 0);
+		acpi_dev_put(pwr_btn_adev);
 	}
 }