Merge branches 'acpi-pm' and 'pm-pci'

* acpi-pm:
  ACPI: PM: Make acpi_sleep_state_supported() non-static
  ACPI: PM: Allow transitions to D0 to occur in special cases
  ACPI: PM: Avoid evaluating _PS3 on transitions from D3hot to D3cold
  ACPI / sleep: Switch to use acpi_dev_get_first_match_dev()
  ACPI / LPIT: Correct LPIT end address for lpit_process()

* pm-pci:
  ACPI: PM: Unexport acpi_device_get_power()
  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
  PCI: Do not poll for PME if the device is in D3cold
  PCI: Add missing link delays required by the PCIe spec
  PCI: PM: Replace pci_dev_keep_suspended() with two functions
  PCI: PM: Avoid resuming devices in D3hot during system suspend

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);
 }

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);
 	}
 

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

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);

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);
 	}
 }
 

drivers/pci/pci-acpi.c

@@ -685,12 +685,21 @@ static pci_power_t acpi_pci_get_power_state(struct pci_dev *dev)
 	if (!adev || !acpi_device_power_manageable(adev))
 		return PCI_UNKNOWN;
 
-	if (acpi_device_get_power(adev, &state) || state == ACPI_STATE_UNKNOWN)
+	state = adev->power.state;
+	if (state == ACPI_STATE_UNKNOWN)
 		return PCI_UNKNOWN;
 
 	return state_conv[state];
 }
 
+static void acpi_pci_refresh_power_state(struct pci_dev *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
+
+	if (adev && acpi_device_power_manageable(adev))
+		acpi_device_update_power(adev, NULL);
+}
+
 static int acpi_pci_propagate_wakeup(struct pci_bus *bus, bool enable)
 {
 	while (bus->parent) {
@@ -748,6 +757,7 @@ static const struct pci_platform_pm_ops acpi_pci_platform_pm = {
 	.is_manageable = acpi_pci_power_manageable,
 	.set_state = acpi_pci_set_power_state,
 	.get_state = acpi_pci_get_power_state,
+	.refresh_state = acpi_pci_refresh_power_state,
 	.choose_state = acpi_pci_choose_state,
 	.set_wakeup = acpi_pci_wakeup,
 	.need_resume = acpi_pci_need_resume,
@@ -901,6 +911,7 @@ static void pci_acpi_setup(struct device *dev)
 		device_wakeup_enable(dev);
 
 	acpi_pci_wakeup(pci_dev, false);
+	acpi_device_power_add_dependent(adev, dev);
 }
 
 static void pci_acpi_cleanup(struct device *dev)
@@ -913,6 +924,7 @@ static void pci_acpi_cleanup(struct device *dev)
 
 	pci_acpi_remove_pm_notifier(adev);
 	if (adev->wakeup.flags.valid) {
+		acpi_device_power_remove_dependent(adev, dev);
 		if (pci_dev->bridge_d3)
 			device_wakeup_disable(dev);
 

drivers/pci/pci-driver.c

@@ -678,6 +678,7 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev)
 static int pci_pm_prepare(struct device *dev)
 {
 	struct device_driver *drv = dev->driver;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
 
 	if (drv && drv->pm && drv->pm->prepare) {
 		int error = drv->pm->prepare(dev);
@@ -687,7 +688,15 @@ static int pci_pm_prepare(struct device *dev)
 		if (!error && dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_PREPARE))
 			return 0;
 	}
-	return pci_dev_keep_suspended(to_pci_dev(dev));
+	if (pci_dev_need_resume(pci_dev))
+		return 0;
+
+	/*
+	 * The PME setting needs to be adjusted here in case the direct-complete
+	 * optimization is used with respect to this device.
+	 */
+	pci_dev_adjust_pme(pci_dev);
+	return 1;
 }
 
 static void pci_pm_complete(struct device *dev)
@@ -701,7 +710,14 @@ static void pci_pm_complete(struct device *dev)
 	if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) {
 		pci_power_t pre_sleep_state = pci_dev->current_state;
 
-		pci_update_current_state(pci_dev, pci_dev->current_state);
+		pci_refresh_power_state(pci_dev);
+		/*
+		 * On platforms with ACPI this check may also trigger for
+		 * devices sharing power resources if one of those power
+		 * resources has been activated as a result of a change of the
+		 * power state of another device sharing it.  However, in that
+		 * case it is also better to resume the device, in general.
+		 */
 		if (pci_dev->current_state < pre_sleep_state)
 			pm_request_resume(dev);
 	}
@@ -757,9 +773,11 @@ static int pci_pm_suspend(struct device *dev)
 	 * better to resume the device from runtime suspend here.
 	 */
 	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
-	    !pci_dev_keep_suspended(pci_dev)) {
+	    pci_dev_need_resume(pci_dev)) {
 		pm_runtime_resume(dev);
 		pci_dev->state_saved = false;
+	} else {
+		pci_dev_adjust_pme(pci_dev);
 	}
 
 	if (pm->suspend) {
@@ -1130,10 +1148,13 @@ static int pci_pm_poweroff(struct device *dev)
 
 	/* The reason to do that is the same as in pci_pm_suspend(). */
 	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
-	    !pci_dev_keep_suspended(pci_dev))
+	    pci_dev_need_resume(pci_dev)) {
 		pm_runtime_resume(dev);
+		pci_dev->state_saved = false;
+	} else {
+		pci_dev_adjust_pme(pci_dev);
+	}
 
-	pci_dev->state_saved = false;
 	if (pm->poweroff) {
 		int error;
 

drivers/pci/pci.c

@@ -777,6 +777,12 @@ static inline pci_power_t platform_pci_get_power_state(struct pci_dev *dev)
 	return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN;
 }
 
+static inline void platform_pci_refresh_power_state(struct pci_dev *dev)
+{
+	if (pci_platform_pm && pci_platform_pm->refresh_state)
+		pci_platform_pm->refresh_state(dev);
+}
+
 static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev)
 {
 	return pci_platform_pm ?
@@ -937,6 +943,21 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state)
 	}
 }
 
+/**
+ * pci_refresh_power_state - Refresh the given device's power state data
+ * @dev: Target PCI device.
+ *
+ * Ask the platform to refresh the devices power state information and invoke
+ * pci_update_current_state() to update its current PCI power state.
+ */
+void pci_refresh_power_state(struct pci_dev *dev)
+{
+	if (platform_pci_power_manageable(dev))
+		platform_pci_refresh_power_state(dev);
+
+	pci_update_current_state(dev, dev->current_state);
+}
+
 /**
  * pci_power_up - Put the given device into D0 forcibly
  * @dev: PCI device to power up
@@ -1004,15 +1025,10 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
 	if (state == PCI_D0) {
 		pci_platform_power_transition(dev, PCI_D0);
 		/*
-		 * Mandatory power management transition delays, see
-		 * PCI Express Base Specification Revision 2.0 Section
-		 * 6.6.1: Conventional Reset.  Do not delay for
-		 * devices powered on/off by corresponding bridge,
-		 * because have already delayed for the bridge.
+		 * Mandatory power management transition delays are
+		 * handled in the PCIe portdrv resume hooks.
 		 */
 		if (dev->runtime_d3cold) {
-			if (dev->d3cold_delay && !dev->imm_ready)
-				msleep(dev->d3cold_delay);
 			/*
 			 * When powering on a bridge from D3cold, the
 			 * whole hierarchy may be powered on into
@@ -2065,6 +2081,13 @@ static void pci_pme_list_scan(struct work_struct *work)
 			 */
 			if (bridge && bridge->current_state != PCI_D0)
 				continue;
+			/*
+			 * If the device is in D3cold it should not be
+			 * polled either.
+			 */
+			if (pme_dev->dev->current_state == PCI_D3cold)
+				continue;
+
 			pci_pme_wakeup(pme_dev->dev, NULL);
 		} else {
 			list_del(&pme_dev->list);
@@ -2459,45 +2482,56 @@ bool pci_dev_run_wake(struct pci_dev *dev)
 EXPORT_SYMBOL_GPL(pci_dev_run_wake);
 
 /**
- * pci_dev_keep_suspended - Check if the device can stay in the suspended state.
+ * pci_dev_need_resume - Check if it is necessary to resume the device.
  * @pci_dev: Device to check.
  *
- * Return 'true' if the device is runtime-suspended, it doesn't have to be
+ * Return 'true' if the device is not runtime-suspended or it has to be
  * reconfigured due to wakeup settings difference between system and runtime
- * suspend and the current power state of it is suitable for the upcoming
- * (system) transition.
- *
- * If the device is not configured for system wakeup, disable PME for it before
- * returning 'true' to prevent it from waking up the system unnecessarily.
+ * suspend, or the current power state of it is not suitable for the upcoming
+ * (system-wide) transition.
  */
-bool pci_dev_keep_suspended(struct pci_dev *pci_dev)
+bool pci_dev_need_resume(struct pci_dev *pci_dev)
 {
 	struct device *dev = &pci_dev->dev;
-	bool wakeup = device_may_wakeup(dev);
+	pci_power_t target_state;
 
-	if (!pm_runtime_suspended(dev)
-	    || pci_target_state(pci_dev, wakeup) != pci_dev->current_state
-	    || platform_pci_need_resume(pci_dev))
-		return false;
+	if (!pm_runtime_suspended(dev) || platform_pci_need_resume(pci_dev))
+		return true;
+
+	target_state = pci_target_state(pci_dev, device_may_wakeup(dev));
 
 	/*
-	 * At this point the device is good to go unless it's been configured
-	 * to generate PME at the runtime suspend time, but it is not supposed
-	 * to wake up the system.  In that case, simply disable PME for it
-	 * (it will have to be re-enabled on exit from system resume).
-	 *
-	 * If the device's power state is D3cold and the platform check above
-	 * hasn't triggered, the device's configuration is suitable and we don't
-	 * need to manipulate it at all.
+	 * If the earlier platform check has not triggered, D3cold is just power
+	 * removal on top of D3hot, so no need to resume the device in that
+	 * case.
 	 */
+	return target_state != pci_dev->current_state &&
+		target_state != PCI_D3cold &&
+		pci_dev->current_state != PCI_D3hot;
+}
+
+/**
+ * pci_dev_adjust_pme - Adjust PME setting for a suspended device.
+ * @pci_dev: Device to check.
+ *
+ * If the device is suspended and it is not configured for system wakeup,
+ * disable PME for it to prevent it from waking up the system unnecessarily.
+ *
+ * Note that if the device's power state is D3cold and the platform check in
+ * pci_dev_need_resume() has not triggered, the device's configuration need not
+ * be changed.
+ */
+void pci_dev_adjust_pme(struct pci_dev *pci_dev)
+{
+	struct device *dev = &pci_dev->dev;
+
 	spin_lock_irq(&dev->power.lock);
 
-	if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold &&
-	    !wakeup)
+	if (pm_runtime_suspended(dev) && !device_may_wakeup(dev) &&
+	    pci_dev->current_state < PCI_D3cold)
 		__pci_pme_active(pci_dev, false);
 
 	spin_unlock_irq(&dev->power.lock);
-	return true;
 }
 
 /**
@@ -4568,14 +4602,16 @@ static int pci_pm_reset(struct pci_dev *dev, int probe)
 
 	return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS);
 }
+
 /**
- * pcie_wait_for_link - Wait until link is active or inactive
+ * pcie_wait_for_link_delay - Wait until link is active or inactive
  * @pdev: Bridge device
  * @active: waiting for active or inactive?
+ * @delay: Delay to wait after link has become active (in ms)
  *
  * Use this to wait till link becomes active or inactive.
  */
-bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
+bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay)
 {
 	int timeout = 1000;
 	bool ret;
@@ -4612,13 +4648,25 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
 		timeout -= 10;
 	}
 	if (active && ret)
-		msleep(100);
+		msleep(delay);
 	else if (ret != active)
 		pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n",
 			active ? "set" : "cleared");
 	return ret == active;
 }
 
+/**
+ * pcie_wait_for_link - Wait until link is active or inactive
+ * @pdev: Bridge device
+ * @active: waiting for active or inactive?
+ *
+ * Use this to wait till link becomes active or inactive.
+ */
+bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
+{
+	return pcie_wait_for_link_delay(pdev, active, 100);
+}
+
 void pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	u16 ctrl;

drivers/pci/pci.h

@@ -51,6 +51,8 @@ int pci_bus_error_reset(struct pci_dev *dev);
  *
  * @get_state: queries the platform firmware for a device's current power state
  *
+ * @refresh_state: asks the platform to refresh the device's power state data
+ *
  * @choose_state: returns PCI power state of given device preferred by the
  *		  platform; to be used during system-wide transitions from a
  *		  sleeping state to the working state and vice versa
@@ -69,6 +71,7 @@ struct pci_platform_pm_ops {
 	bool (*is_manageable)(struct pci_dev *dev);
 	int (*set_state)(struct pci_dev *dev, pci_power_t state);
 	pci_power_t (*get_state)(struct pci_dev *dev);
+	void (*refresh_state)(struct pci_dev *dev);
 	pci_power_t (*choose_state)(struct pci_dev *dev);
 	int (*set_wakeup)(struct pci_dev *dev, bool enable);
 	bool (*need_resume)(struct pci_dev *dev);
@@ -76,13 +79,15 @@ struct pci_platform_pm_ops {
 
 int pci_set_platform_pm(const struct pci_platform_pm_ops *ops);
 void pci_update_current_state(struct pci_dev *dev, pci_power_t state);
+void pci_refresh_power_state(struct pci_dev *dev);
 void pci_power_up(struct pci_dev *dev);
 void pci_disable_enabled_device(struct pci_dev *dev);
 int pci_finish_runtime_suspend(struct pci_dev *dev);
 void pcie_clear_root_pme_status(struct pci_dev *dev);
 int __pci_pme_wakeup(struct pci_dev *dev, void *ign);
 void pci_pme_restore(struct pci_dev *dev);
-bool pci_dev_keep_suspended(struct pci_dev *dev);
+bool pci_dev_need_resume(struct pci_dev *dev);
+void pci_dev_adjust_pme(struct pci_dev *dev);
 void pci_dev_complete_resume(struct pci_dev *pci_dev);
 void pci_config_pm_runtime_get(struct pci_dev *dev);
 void pci_config_pm_runtime_put(struct pci_dev *dev);
@@ -493,6 +498,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
 void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
 		      u32 service);
 
+bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay);
 bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
 #ifdef CONFIG_PCIEASPM
 void pcie_aspm_init_link_state(struct pci_dev *pdev);

drivers/pci/pcie/portdrv_core.c

@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
@@ -378,6 +379,67 @@ static int pm_iter(struct device *dev, void *data)
 	return 0;
 }
 
+static int get_downstream_delay(struct pci_bus *bus)
+{
+	struct pci_dev *pdev;
+	int min_delay = 100;
+	int max_delay = 0;
+
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		if (!pdev->imm_ready)
+			min_delay = 0;
+		else if (pdev->d3cold_delay < min_delay)
+			min_delay = pdev->d3cold_delay;
+		if (pdev->d3cold_delay > max_delay)
+			max_delay = pdev->d3cold_delay;
+	}
+
+	return max(min_delay, max_delay);
+}
+
+/*
+ * wait_for_downstream_link - Wait for downstream link to establish
+ * @pdev: PCIe port whose downstream link is waited
+ *
+ * Handle delays according to PCIe 4.0 section 6.6.1 before configuration
+ * access to the downstream component is permitted.
+ *
+ * This blocks PCI core resume of the hierarchy below this port until the
+ * link is trained. Should be called before resuming port services to
+ * prevent pciehp from starting to tear-down the hierarchy too soon.
+ */
+static void wait_for_downstream_link(struct pci_dev *pdev)
+{
+	int delay;
+
+	if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
+	    pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+
+	if (pci_dev_is_disconnected(pdev))
+		return;
+
+	if (!pdev->subordinate || list_empty(&pdev->subordinate->devices) ||
+	    !pdev->bridge_d3)
+		return;
+
+	delay = get_downstream_delay(pdev->subordinate);
+	if (!delay)
+		return;
+
+	dev_dbg(&pdev->dev, "waiting downstream link for %d ms\n", delay);
+
+	/*
+	 * If downstream port does not support speeds greater than 5 GT/s
+	 * need to wait 100ms. For higher speeds (gen3) we need to wait
+	 * first for the data link layer to become active.
+	 */
+	if (pcie_get_speed_cap(pdev) <= PCIE_SPEED_5_0GT)
+		msleep(delay);
+	else
+		pcie_wait_for_link_delay(pdev, true, delay);
+}
+
 /**
  * pcie_port_device_suspend - suspend port services associated with a PCIe port
  * @dev: PCI Express port to handle
@@ -391,6 +453,8 @@ int pcie_port_device_suspend(struct device *dev)
 int pcie_port_device_resume_noirq(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, resume_noirq);
+
+	wait_for_downstream_link(to_pci_dev(dev));
 	return device_for_each_child(dev, &off, pm_iter);
 }
 
@@ -421,6 +485,8 @@ int pcie_port_device_runtime_suspend(struct device *dev)
 int pcie_port_device_runtime_resume(struct device *dev)
 {
 	size_t off = offsetof(struct pcie_port_service_driver, runtime_resume);
+
+	wait_for_downstream_link(to_pci_dev(dev));
 	return device_for_each_child(dev, &off, pm_iter);
 }
 #endif /* PM */

include/acpi/acpi_bus.h

@@ -506,13 +506,16 @@ int acpi_bus_get_status(struct acpi_device *device);
 
 int acpi_bus_set_power(acpi_handle handle, int state);
 const char *acpi_power_state_string(int state);
-int acpi_device_get_power(struct acpi_device *device, int *state);
 int acpi_device_set_power(struct acpi_device *device, int state);
 int acpi_bus_init_power(struct acpi_device *device);
 int acpi_device_fix_up_power(struct acpi_device *device);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 int acpi_device_update_power(struct acpi_device *device, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
+int acpi_device_power_add_dependent(struct acpi_device *adev,
+				    struct device *dev);
+void acpi_device_power_remove_dependent(struct acpi_device *adev,
+					struct device *dev);
 
 #ifdef CONFIG_PM
 bool acpi_bus_can_wakeup(acpi_handle handle);
@@ -651,6 +654,12 @@ static inline int acpi_pm_set_bridge_wakeup(struct device *dev, bool enable)
 }
 #endif
 
+#ifdef CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT
+bool acpi_sleep_state_supported(u8 sleep_state);
+#else
+static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; }
+#endif
+
 #ifdef CONFIG_ACPI_SLEEP
 u32 acpi_target_system_state(void);
 #else