Merge tag 'pm-5.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These add PM QoS support to devfreq and fix a few issues in that
  subsystem, fix two cpuidle issues and do one minor cleanup in there,
  and address an ACPI power management problem related to devices with
  special power management requirements, like fans.

  Specifics:

   - Add PM QoS support, based on the frequency QoS introduced during
     the 5.4 cycle, to devfreq (Leonard Crestez).

   - Fix some assorted devfreq issues (Leonard Crestez).

   - Fix an unintentional cpuidle behavior change (introduced during the
     5.4 cycle) related to the active polling time limit (Marcelo
     Tosatti).

   - Fix a recently introduced cpuidle helper function and do a minor
     cleanup in the cpuidle core (Rafael Wysocki).

   - Avoid adding devices with special power management requirements,
     like fans, to the generic ACPI PM domain (Rafael Wysocki)"

* tag 'pm-5.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpuidle: Drop unnecessary type cast in cpuidle_poll_time()
  cpuidle: Fix cpuidle_driver_state_disabled()
  ACPI: PM: Avoid attaching ACPI PM domain to certain devices
  cpuidle: use first valid target residency as poll time
  PM / devfreq: Use PM QoS for sysfs min/max_freq
  PM / devfreq: Add PM QoS support
  PM / devfreq: Don't fail devfreq_dev_release if not in list
  PM / devfreq: Introduce get_freq_range helper
  PM / devfreq: Set scaling_max_freq to max on OPP notifier error
  PM / devfreq: Fix devfreq_notifier_call returning errno

5 files changed, 235 insertions, 77 deletions

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 08bb9f2f2d23..5e4a8860a9c0 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1314,9 +1314,19 @@ static void acpi_dev_pm_detach(struct device *dev, bool power_off)
  */
 int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
+	/*
+	 * Skip devices whose ACPI companions match the device IDs below,
+	 * because they require special power management handling incompatible
+	 * with the generic ACPI PM domain.
+	 */
+	static const struct acpi_device_id special_pm_ids[] = {
+		{"PNP0C0B", }, /* Generic ACPI fan */
+		{"INT3404", }, /* Fan */
+		{}
+	};
 	struct acpi_device *adev = ACPI_COMPANION(dev);
 
-	if (!adev)
+	if (!adev || !acpi_match_device_ids(adev, special_pm_ids))
 		return 0;
 
 	/*
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 0005be5ea2b4..33d19c8eb027 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -381,7 +381,8 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv,
 		if (dev->states_usage[i].disable)
 			continue;
 
-		limit_ns = (u64)drv->states[i].target_residency_ns;
+		limit_ns = drv->states[i].target_residency_ns;
+		break;
 	}
 
 	dev->poll_limit_ns = limit_ns;
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index c76423aaef4d..ce6a5f80fb83 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -403,6 +403,13 @@ void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx,
 
 	mutex_lock(&cpuidle_lock);
 
+	spin_lock(&cpuidle_driver_lock);
+
+	if (!drv->cpumask) {
+		drv->states[idx].flags |= CPUIDLE_FLAG_UNUSABLE;
+		goto unlock;
+	}
+
 	for_each_cpu(cpu, drv->cpumask) {
 		struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
 
@@ -415,5 +422,8 @@ void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx,
 			dev->states_usage[idx].disable &= ~CPUIDLE_STATE_DISABLED_BY_DRIVER;
 	}
 
+unlock:
+	spin_unlock(&cpuidle_driver_lock);
+
 	mutex_unlock(&cpuidle_lock);
 }
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 425149e8bab0..57f6944d65a6 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -24,11 +24,14 @@
 #include <linux/printk.h>
 #include <linux/hrtimer.h>
 #include <linux/of.h>
+#include <linux/pm_qos.h>
 #include "governor.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/devfreq.h>
 
+#define HZ_PER_KHZ	1000
+
 static struct class *devfreq_class;
 
 /*
@@ -99,6 +102,54 @@ static unsigned long find_available_max_freq(struct devfreq *devfreq)
 }
 
 /**
+ * get_freq_range() - Get the current freq range
+ * @devfreq:	the devfreq instance
+ * @min_freq:	the min frequency
+ * @max_freq:	the max frequency
+ *
+ * This takes into consideration all constraints.
+ */
+static void get_freq_range(struct devfreq *devfreq,
+			   unsigned long *min_freq,
+			   unsigned long *max_freq)
+{
+	unsigned long *freq_table = devfreq->profile->freq_table;
+	s32 qos_min_freq, qos_max_freq;
+
+	lockdep_assert_held(&devfreq->lock);
+
+	/*
+	 * Initialize minimum/maximum frequency from freq table.
+	 * The devfreq drivers can initialize this in either ascending or
+	 * descending order and devfreq core supports both.
+	 */
+	if (freq_table[0] < freq_table[devfreq->profile->max_state - 1]) {
+		*min_freq = freq_table[0];
+		*max_freq = freq_table[devfreq->profile->max_state - 1];
+	} else {
+		*min_freq = freq_table[devfreq->profile->max_state - 1];
+		*max_freq = freq_table[0];
+	}
+
+	/* Apply constraints from PM QoS */
+	qos_min_freq = dev_pm_qos_read_value(devfreq->dev.parent,
+					     DEV_PM_QOS_MIN_FREQUENCY);
+	qos_max_freq = dev_pm_qos_read_value(devfreq->dev.parent,
+					     DEV_PM_QOS_MAX_FREQUENCY);
+	*min_freq = max(*min_freq, (unsigned long)HZ_PER_KHZ * qos_min_freq);
+	if (qos_max_freq != PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE)
+		*max_freq = min(*max_freq,
+				(unsigned long)HZ_PER_KHZ * qos_max_freq);
+
+	/* Apply constraints from OPP interface */
+	*min_freq = max(*min_freq, devfreq->scaling_min_freq);
+	*max_freq = min(*max_freq, devfreq->scaling_max_freq);
+
+	if (*min_freq > *max_freq)
+		*min_freq = *max_freq;
+}
+
+/**
  * devfreq_get_freq_level() - Lookup freq_table for the frequency
  * @devfreq:	the devfreq instance
  * @freq:	the target frequency
@@ -351,16 +402,7 @@ int update_devfreq(struct devfreq *devfreq)
 	err = devfreq->governor->get_target_freq(devfreq, &freq);
 	if (err)
 		return err;
-
-	/*
-	 * Adjust the frequency with user freq, QoS and available freq.
-	 *
-	 * List from the highest priority
-	 * max_freq
-	 * min_freq
-	 */
-	max_freq = min(devfreq->scaling_max_freq, devfreq->max_freq);
-	min_freq = max(devfreq->scaling_min_freq, devfreq->min_freq);
+	get_freq_range(devfreq, &min_freq, &max_freq);
 
 	if (freq < min_freq) {
 		freq = min_freq;
@@ -568,26 +610,69 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 				 void *devp)
 {
 	struct devfreq *devfreq = container_of(nb, struct devfreq, nb);
-	int ret;
+	int err = -EINVAL;
 
 	mutex_lock(&devfreq->lock);
 
 	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->scaling_min_freq) {
-		mutex_unlock(&devfreq->lock);
-		return -EINVAL;
-	}
+	if (!devfreq->scaling_min_freq)
+		goto out;
 
 	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
 	if (!devfreq->scaling_max_freq) {
-		mutex_unlock(&devfreq->lock);
-		return -EINVAL;
+		devfreq->scaling_max_freq = ULONG_MAX;
+		goto out;
 	}
 
-	ret = update_devfreq(devfreq);
+	err = update_devfreq(devfreq);
+
+out:
 	mutex_unlock(&devfreq->lock);
+	if (err)
+		dev_err(devfreq->dev.parent,
+			"failed to update frequency from OPP notifier (%d)\n",
+			err);
 
-	return ret;
+	return NOTIFY_OK;
+}
+
+/**
+ * qos_notifier_call() - Common handler for QoS constraints.
+ * @devfreq:    the devfreq instance.
+ */
+static int qos_notifier_call(struct devfreq *devfreq)
+{
+	int err;
+
+	mutex_lock(&devfreq->lock);
+	err = update_devfreq(devfreq);
+	mutex_unlock(&devfreq->lock);
+	if (err)
+		dev_err(devfreq->dev.parent,
+			"failed to update frequency from PM QoS (%d)\n",
+			err);
+
+	return NOTIFY_OK;
+}
+
+/**
+ * qos_min_notifier_call() - Callback for QoS min_freq changes.
+ * @nb:		Should be devfreq->nb_min
+ */
+static int qos_min_notifier_call(struct notifier_block *nb,
+					 unsigned long val, void *ptr)
+{
+	return qos_notifier_call(container_of(nb, struct devfreq, nb_min));
+}
+
+/**
+ * qos_max_notifier_call() - Callback for QoS max_freq changes.
+ * @nb:		Should be devfreq->nb_max
+ */
+static int qos_max_notifier_call(struct notifier_block *nb,
+					 unsigned long val, void *ptr)
+{
+	return qos_notifier_call(container_of(nb, struct devfreq, nb_max));
 }
 
 /**
@@ -599,16 +684,36 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 static void devfreq_dev_release(struct device *dev)
 {
 	struct devfreq *devfreq = to_devfreq(dev);
+	int err;
 
 	mutex_lock(&devfreq_list_lock);
-	if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) {
-		mutex_unlock(&devfreq_list_lock);
-		dev_warn(&devfreq->dev, "releasing devfreq which doesn't exist\n");
-		return;
-	}
 	list_del(&devfreq->node);
 	mutex_unlock(&devfreq_list_lock);
 
+	err = dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_max,
+					 DEV_PM_QOS_MAX_FREQUENCY);
+	if (err && err != -ENOENT)
+		dev_warn(dev->parent,
+			"Failed to remove max_freq notifier: %d\n", err);
+	err = dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_min,
+					 DEV_PM_QOS_MIN_FREQUENCY);
+	if (err && err != -ENOENT)
+		dev_warn(dev->parent,
+			"Failed to remove min_freq notifier: %d\n", err);
+
+	if (dev_pm_qos_request_active(&devfreq->user_max_freq_req)) {
+		err = dev_pm_qos_remove_request(&devfreq->user_max_freq_req);
+		if (err)
+			dev_warn(dev->parent,
+				"Failed to remove max_freq request: %d\n", err);
+	}
+	if (dev_pm_qos_request_active(&devfreq->user_min_freq_req)) {
+		err = dev_pm_qos_remove_request(&devfreq->user_min_freq_req);
+		if (err)
+			dev_warn(dev->parent,
+				"Failed to remove min_freq request: %d\n", err);
+	}
+
 	if (devfreq->profile->exit)
 		devfreq->profile->exit(devfreq->dev.parent);
 
@@ -660,6 +765,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->dev.parent = dev;
 	devfreq->dev.class = devfreq_class;
 	devfreq->dev.release = devfreq_dev_release;
+	INIT_LIST_HEAD(&devfreq->node);
 	devfreq->profile = profile;
 	strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN);
 	devfreq->previous_freq = profile->initial_freq;
@@ -681,7 +787,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->min_freq = devfreq->scaling_min_freq;
 
 	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
 	if (!devfreq->scaling_max_freq) {
@@ -689,7 +794,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev);
 	atomic_set(&devfreq->suspend_count, 0);
@@ -730,6 +834,28 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 	mutex_unlock(&devfreq->lock);
 
+	err = dev_pm_qos_add_request(dev, &devfreq->user_min_freq_req,
+				     DEV_PM_QOS_MIN_FREQUENCY, 0);
+	if (err < 0)
+		goto err_devfreq;
+	err = dev_pm_qos_add_request(dev, &devfreq->user_max_freq_req,
+				     DEV_PM_QOS_MAX_FREQUENCY,
+				     PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
+	if (err < 0)
+		goto err_devfreq;
+
+	devfreq->nb_min.notifier_call = qos_min_notifier_call;
+	err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_min,
+				      DEV_PM_QOS_MIN_FREQUENCY);
+	if (err)
+		goto err_devfreq;
+
+	devfreq->nb_max.notifier_call = qos_max_notifier_call;
+	err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_max,
+				      DEV_PM_QOS_MAX_FREQUENCY);
+	if (err)
+		goto err_devfreq;
+
 	mutex_lock(&devfreq_list_lock);
 
 	governor = try_then_request_governor(devfreq->governor_name);
@@ -1303,41 +1429,37 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr,
 	unsigned long value;
 	int ret;
 
+	/*
+	 * Protect against theoretical sysfs writes between
+	 * device_add and dev_pm_qos_add_request
+	 */
+	if (!dev_pm_qos_request_active(&df->user_min_freq_req))
+		return -EAGAIN;
+
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
-	mutex_lock(&df->lock);
-
-	if (value) {
-		if (value > df->max_freq) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-	} else {
-		unsigned long *freq_table = df->profile->freq_table;
-
-		/* Get minimum frequency according to sorting order */
-		if (freq_table[0] < freq_table[df->profile->max_state - 1])
-			value = freq_table[0];
-		else
-			value = freq_table[df->profile->max_state - 1];
-	}
+	/* Round down to kHz for PM QoS */
+	ret = dev_pm_qos_update_request(&df->user_min_freq_req,
+					value / HZ_PER_KHZ);
+	if (ret < 0)
+		return ret;
 
-	df->min_freq = value;
-	update_devfreq(df);
-	ret = count;
-unlock:
-	mutex_unlock(&df->lock);
-	return ret;
+	return count;
 }
 
 static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
+	unsigned long min_freq, max_freq;
 
-	return sprintf(buf, "%lu\n", max(df->scaling_min_freq, df->min_freq));
+	mutex_lock(&df->lock);
+	get_freq_range(df, &min_freq, &max_freq);
+	mutex_unlock(&df->lock);
+
+	return sprintf(buf, "%lu\n", min_freq);
 }
 
 static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
@@ -1347,33 +1469,37 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr,
 	unsigned long value;
 	int ret;
 
+	/*
+	 * Protect against theoretical sysfs writes between
+	 * device_add and dev_pm_qos_add_request
+	 */
+	if (!dev_pm_qos_request_active(&df->user_max_freq_req))
+		return -EINVAL;
+
 	ret = sscanf(buf, "%lu", &value);
 	if (ret != 1)
 		return -EINVAL;
 
-	mutex_lock(&df->lock);
-
-	if (value) {
-		if (value < df->min_freq) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-	} else {
-		unsigned long *freq_table = df->profile->freq_table;
+	/*
+	 * PM QoS frequencies are in kHz so we need to convert. Convert by
+	 * rounding upwards so that the acceptable interval never shrinks.
+	 *
+	 * For example if the user writes "666666666" to sysfs this value will
+	 * be converted to 666667 kHz and back to 666667000 Hz before an OPP
+	 * lookup, this ensures that an OPP of 666666666Hz is still accepted.
+	 *
+	 * A value of zero means "no limit".
+	 */
+	if (value)
+		value = DIV_ROUND_UP(value, HZ_PER_KHZ);
+	else
+		value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
 
-		/* Get maximum frequency according to sorting order */
-		if (freq_table[0] < freq_table[df->profile->max_state - 1])
-			value = freq_table[df->profile->max_state - 1];
-		else
-			value = freq_table[0];
-	}
+	ret = dev_pm_qos_update_request(&df->user_max_freq_req, value);
+	if (ret < 0)
+		return ret;
 
-	df->max_freq = value;
-	update_devfreq(df);
-	ret = count;
-unlock:
-	mutex_unlock(&df->lock);
-	return ret;
+	return count;
 }
 static DEVICE_ATTR_RW(min_freq);
 
@@ -1381,8 +1507,13 @@ static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
+	unsigned long min_freq, max_freq;
+
+	mutex_lock(&df->lock);
+	get_freq_range(df, &min_freq, &max_freq);
+	mutex_unlock(&df->lock);
 
-	return sprintf(buf, "%lu\n", min(df->scaling_max_freq, df->max_freq));
+	return sprintf(buf, "%lu\n", max_freq);
 }
 static DEVICE_ATTR_RW(max_freq);
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 2bae9ed3c783..fb376b5b7281 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -13,6 +13,7 @@
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/pm_opp.h>
+#include <linux/pm_qos.h>
 
 #define DEVFREQ_NAME_LEN 16
 
@@ -123,8 +124,8 @@ struct devfreq_dev_profile {
  * @previous_freq:	previously configured frequency value.
  * @data:	Private data of the governor. The devfreq framework does not
  *		touch this.
- * @min_freq:	Limit minimum frequency requested by user (0: none)
- * @max_freq:	Limit maximum frequency requested by user (0: none)
+ * @user_min_freq_req:	PM QoS minimum frequency request from user (via sysfs)
+ * @user_max_freq_req:	PM QoS maximum frequency request from user (via sysfs)
  * @scaling_min_freq:	Limit minimum frequency requested by OPP interface
  * @scaling_max_freq:	Limit maximum frequency requested by OPP interface
  * @stop_polling:	 devfreq polling status of a device.
@@ -136,6 +137,8 @@ struct devfreq_dev_profile {
  * @time_in_state:	Statistics of devfreq states
  * @last_stat_updated:	The last time stat updated
  * @transition_notifier_list: list head of DEVFREQ_TRANSITION_NOTIFIER notifier
+ * @nb_min:		Notifier block for DEV_PM_QOS_MIN_FREQUENCY
+ * @nb_max:		Notifier block for DEV_PM_QOS_MAX_FREQUENCY
  *
  * This structure stores the devfreq information for a give device.
  *
@@ -161,8 +164,8 @@ struct devfreq {
 
 	void *data; /* private data for governors */
 
-	unsigned long min_freq;
-	unsigned long max_freq;
+	struct dev_pm_qos_request user_min_freq_req;
+	struct dev_pm_qos_request user_max_freq_req;
 	unsigned long scaling_min_freq;
 	unsigned long scaling_max_freq;
 	bool stop_polling;
@@ -178,6 +181,9 @@ struct devfreq {
 	unsigned long last_stat_updated;
 
 	struct srcu_notifier_head transition_notifier_list;
+
+	struct notifier_block nb_min;
+	struct notifier_block nb_max;
 };
 
 struct devfreq_freqs {