[V9,1/7] PM / Domains: Add support to select performance-state of domains

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 43fd08e50ae9..5f50d5295cd4 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -237,6 +237,274 @@  static void genpd_update_accounting(struct generic_pm_domain *genpd)
 static inline void genpd_update_accounting(struct generic_pm_domain *genpd) {}
 #endif
 
+/**
+ * dev_pm_genpd_has_performance_state - Checks if power domain does performance
+ * state management.
+ *
+ * @dev: Device whose power domain is getting inquired.
+ *
+ * This can be called by the user drivers, before they start calling
+ * dev_pm_genpd_update_performance_state(), to guarantee that all dependencies
+ * are met and the device's genpd supports performance states.
+ *
+ * It is assumed that the user driver guarantees that the genpd wouldn't be
+ * detached while this routine is getting called.
+ *
+ * Returns "true" if device's genpd supports performance states, "false"
+ * otherwise.
+ */
+bool dev_pm_genpd_has_performance_state(struct device *dev)
+{
+	struct generic_pm_domain *genpd = genpd_lookup_dev(dev);
+
+	return !IS_ERR(genpd) && genpd->dev_get_performance_state;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_has_performance_state);
+
+static int _genpd_reeval_performance_state(struct generic_pm_domain *genpd,
+					   int state, int depth);
+
+/* Returns -ve errors or 0 on success */
+static int _genpd_set_performance_state(struct generic_pm_domain *genpd,
+					int state, int depth)
+{
+	struct generic_pm_domain *master;
+	struct gpd_link *link;
+	int prev = genpd->performance_state, ret;
+
+	if (genpd->genpd_set_performance_state) {
+		ret = genpd->genpd_set_performance_state(genpd, state);
+		if (ret)
+			return ret;
+	}
+
+	/* Propagate to masters of genpd */
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		master = link->master;
+
+		genpd_lock_nested(master, depth + 1);
+
+		link->performance_state = state;
+		ret = _genpd_reeval_performance_state(master, state, depth + 1);
+		if (ret)
+			link->performance_state = prev;
+
+		genpd_unlock(master);
+
+		if (ret)
+			goto err;
+	}
+
+	/*
+	 * The masters are updated now, lets get genpd performance_state in sync
+	 * with those.
+	 */
+	genpd->performance_state = state;
+	return 0;
+
+err:
+	/* Encountered an error, lets rollback */
+	list_for_each_entry_continue_reverse(link, &genpd->slave_links,
+					     slave_node) {
+		master = link->master;
+
+		genpd_lock_nested(master, depth + 1);
+		link->performance_state = prev;
+		if (_genpd_reeval_performance_state(master, prev, depth + 1)) {
+			pr_err("%s: Failed to roll back to %d performance state\n",
+			       master->name, prev);
+		}
+		genpd_unlock(master);
+	}
+
+	if (genpd->genpd_set_performance_state) {
+		if (genpd->genpd_set_performance_state(genpd, prev)) {
+			pr_err("%s: Failed to roll back to %d performance state\n",
+			       genpd->name, prev);
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Re-evaluate performance state of a genpd. Finds the highest requested
+ * performance state by the devices and subdomains within the genpd and then
+ * change genpd's performance state (if required). The request is then
+ * propagated to the masters of the genpd.
+ *
+ * @genpd: PM domain whose state needs to be reevaluated.
+ * @state: Newly requested performance state of the device or subdomain for
+ * which this routine is called.
+ * @depth: nesting count for lockdep.
+ *
+ * Locking rules followed are:
+ *
+ * - Device's state (pd_data->performance_state) should be accessed from within
+ *   its master's lock protected section.
+ *
+ * - Subdomains have a separate state field (link->performance_state) per master
+ *   domain and is accessed only from within master's lock protected section.
+ *
+ * - Subdomain's state (genpd->performance_state) should be accessed from within
+ *   its own lock protected section.
+ *
+ * - The locks are always taken in bottom->up order, i.e. subdomain first,
+ *   followed by its masters.
+ *
+ * Returns -ve errors or 0 on success.
+ */
+static int _genpd_reeval_performance_state(struct generic_pm_domain *genpd,
+					   int state, int depth)
+{
+	struct generic_pm_domain_data *pd_data;
+	struct pm_domain_data *pdd;
+	struct gpd_link *link;
+
+	/* New requested state is same as Max requested state */
+	if (state == genpd->performance_state)
+		return 0;
+
+	/* New requested state is higher than Max requested state */
+	if (state > genpd->performance_state)
+		goto update_state;
+
+	/* Traverse all devices within the domain */
+	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
+		pd_data = to_gpd_data(pdd);
+
+		if (pd_data->performance_state > state)
+			state = pd_data->performance_state;
+	}
+
+	/*
+	 * Traverse all subdomains within the domain. This can be done without
+	 * any additional locks as all link->performance_state fields are
+	 * protected by genpd->lock, which is already taken.
+	 */
+	list_for_each_entry(link, &genpd->master_links, master_node) {
+		if (link->performance_state > state)
+			state = link->performance_state;
+	}
+
+update_state:
+	return _genpd_set_performance_state(genpd, state, depth);
+}
+
+static void __genpd_dev_update_performance_state(struct device *dev, int state)
+{
+	struct generic_pm_domain_data *gpd_data;
+
+	spin_lock_irq(&dev->power.lock);
+
+	if (!dev->power.subsys_data || !dev->power.subsys_data->domain_data) {
+		WARN_ON(1);
+		goto unlock;
+	}
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	gpd_data->performance_state = state;
+
+unlock:
+	spin_unlock_irq(&dev->power.lock);
+}
+
+/**
+ * dev_pm_genpd_update_performance_state - Update performance state of device's
+ * power domain for the target frequency for the device.
+ *
+ * @dev: Device for which the performance-state needs to be adjusted.
+ * @rate: Device's next frequency. This can be set as 0 when the device doesn't
+ * have any performance state constraints left (And so the device wouldn't
+ * participate anymore to find the target performance state of the genpd).
+ *
+ * The user drivers may want to call dev_pm_genpd_has_performance_state() (only
+ * once) before calling this routine (any number of times) to guarantee that all
+ * dependencies are met.
+ *
+ * It is assumed that the user driver guarantees that the genpd wouldn't be
+ * detached while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_update_performance_state(struct device *dev,
+					  unsigned long rate)
+{
+	struct generic_pm_domain *genpd;
+	int ret, state;
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return -ENODEV;
+
+	genpd_lock(genpd);
+
+	if (!genpd_status_on(genpd)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	state = genpd->dev_get_performance_state(dev, rate);
+	if (state < 0) {
+		ret = state;
+		goto unlock;
+	}
+
+	ret = _genpd_reeval_performance_state(genpd, state, 0);
+	if (!ret) {
+		/*
+		 * Since we are passing "state" to
+		 * _genpd_reeval_performance_state() as well, we don't need to
+		 * call __genpd_dev_update_performance_state() before updating
+		 * genpd's state with the above call. Update it only after the
+		 * state of master domain is updated.
+		 */
+		__genpd_dev_update_performance_state(dev, state);
+	}
+
+unlock:
+	genpd_unlock(genpd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_update_performance_state);
+
+static int _genpd_on_update_performance_state(struct generic_pm_domain *genpd,
+					      int depth)
+{
+	int ret, prev = genpd->prev_performance_state;
+
+	if (likely(!prev))
+		return 0;
+
+	ret = _genpd_set_performance_state(genpd, prev, depth);
+	if (ret) {
+		pr_err("%s: Failed to restore performance state to %d (%d)\n",
+		       genpd->name, prev, ret);
+	} else {
+		genpd->prev_performance_state = 0;
+	}
+
+	return ret;
+}
+
+static void _genpd_off_update_performance_state(struct generic_pm_domain *genpd,
+						int depth)
+{
+	int ret, state = genpd->performance_state;
+
+	if (likely(!state))
+		return;
+
+	ret = _genpd_set_performance_state(genpd, 0, depth);
+	if (ret) {
+		pr_err("%s: Failed to set performance state to 0 (%d)\n",
+		       genpd->name, ret);
+	} else {
+		genpd->prev_performance_state = state;
+	}
+}
+
 static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
 	unsigned int state_idx = genpd->state_idx;
@@ -388,6 +656,8 @@  static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 			return ret;
 	}
 
+	_genpd_off_update_performance_state(genpd, depth);
+
 	genpd->status = GPD_STATE_POWER_OFF;
 	genpd_update_accounting(genpd);
 
@@ -437,15 +707,21 @@  static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 		}
 	}
 
-	ret = _genpd_power_on(genpd, true);
+	ret = _genpd_on_update_performance_state(genpd, depth);
 	if (ret)
 		goto err;
 
+	ret = _genpd_power_on(genpd, true);
+	if (ret)
+		goto err_power_on;
+
 	genpd->status = GPD_STATE_ACTIVE;
 	genpd_update_accounting(genpd);
 
 	return 0;
 
+ err_power_on:
+	_genpd_off_update_performance_state(genpd, depth);
  err:
 	list_for_each_entry_continue_reverse(link,
 					&genpd->slave_links,
@@ -807,6 +1083,8 @@  static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
 	if (_genpd_power_off(genpd, false))
 		return;
 
+	_genpd_off_update_performance_state(genpd, depth);
+
 	genpd->status = GPD_STATE_POWER_OFF;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
@@ -852,7 +1130,9 @@  static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 			genpd_unlock(link->master);
 	}
 
-	_genpd_power_on(genpd, false);
+	if (!_genpd_on_update_performance_state(genpd, depth))
+		if (_genpd_power_on(genpd, false))
+			_genpd_off_update_performance_state(genpd, depth);
 
 	genpd->status = GPD_STATE_ACTIVE;
 }
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 84f423d5633e..715cca7ac399 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -64,8 +64,13 @@  struct generic_pm_domain {
 	unsigned int device_count;	/* Number of devices */
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
+	unsigned int performance_state;	/* Max requested performance state */
+	unsigned int prev_performance_state;	/* Performance state before power off */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
+	int (*dev_get_performance_state)(struct device *dev, unsigned long rate);
+	int (*genpd_set_performance_state)(struct generic_pm_domain *genpd,
+					   unsigned int state);
 	struct gpd_dev_ops dev_ops;
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
@@ -102,6 +107,9 @@  struct gpd_link {
 	struct list_head master_node;
 	struct generic_pm_domain *slave;
 	struct list_head slave_node;
+
+	/* Sub-domain's per-master domain performance state */
+	unsigned int performance_state;
 };
 
 struct gpd_timing_data {
@@ -121,6 +129,7 @@  struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
+	unsigned int performance_state;
 	void *data;
 };
 
@@ -148,6 +157,9 @@  extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 extern int pm_genpd_init(struct generic_pm_domain *genpd,
 			 struct dev_power_governor *gov, bool is_off);
 extern int pm_genpd_remove(struct generic_pm_domain *genpd);
+extern bool dev_pm_genpd_has_performance_state(struct device *dev);
+extern int dev_pm_genpd_update_performance_state(struct device *dev,
+						 unsigned long rate);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -188,6 +200,17 @@  static inline int pm_genpd_remove(struct generic_pm_domain *genpd)
 	return -ENOTSUPP;
 }
 
+static inline bool dev_pm_genpd_has_performance_state(struct device *dev)
+{
+	return false;
+}
+
+static inline int dev_pm_genpd_update_performance_state(struct device *dev,
+							unsigned long rate)
+{
+	return -ENOTSUPP;
+}
+
 #define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
 #define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
 #endif