4 files changed, 191 insertions, 70 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 96a6dc9d305c..3d899e8abd58 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/suspend.h>
 #include <linux/export.h>
+#include <linux/cpu.h>
 
 #include "power.h"
 
@@ -128,6 +129,7 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
 #define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 #define genpd_is_active_wakeup(genpd)	(genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP)
+#define genpd_is_cpu_domain(genpd)	(genpd->flags & GENPD_FLAG_CPU_DOMAIN)
 
 static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 		const struct generic_pm_domain *genpd)
@@ -391,11 +393,9 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 	if (unlikely(!genpd->set_performance_state))
 		return -EINVAL;
 
-	if (unlikely(!dev->power.subsys_data ||
-		     !dev->power.subsys_data->domain_data)) {
-		WARN_ON(1);
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
 		return -EINVAL;
-	}
 
 	genpd_lock(genpd);
 
@@ -1396,8 +1396,7 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 
 #endif /* CONFIG_PM_SLEEP */
 
-static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
-					struct gpd_timing_data *td)
+static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev)
 {
 	struct generic_pm_domain_data *gpd_data;
 	int ret;
@@ -1412,9 +1411,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 		goto err_put;
 	}
 
-	if (td)
-		gpd_data->td = *td;
-
 	gpd_data->base.dev = dev;
 	gpd_data->td.constraint_changed = true;
 	gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
@@ -1454,8 +1450,57 @@ static void genpd_free_dev_data(struct device *dev,
 	dev_pm_put_subsys_data(dev);
 }
 
+static void genpd_update_cpumask(struct generic_pm_domain *genpd,
+				 int cpu, bool set, unsigned int depth)
+{
+	struct gpd_link *link;
+
+	if (!genpd_is_cpu_domain(genpd))
+		return;
+
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		struct generic_pm_domain *master = link->master;
+
+		genpd_lock_nested(master, depth + 1);
+		genpd_update_cpumask(master, cpu, set, depth + 1);
+		genpd_unlock(master);
+	}
+
+	if (set)
+		cpumask_set_cpu(cpu, genpd->cpus);
+	else
+		cpumask_clear_cpu(cpu, genpd->cpus);
+}
+
+static void genpd_set_cpumask(struct generic_pm_domain *genpd, int cpu)
+{
+	if (cpu >= 0)
+		genpd_update_cpumask(genpd, cpu, true, 0);
+}
+
+static void genpd_clear_cpumask(struct generic_pm_domain *genpd, int cpu)
+{
+	if (cpu >= 0)
+		genpd_update_cpumask(genpd, cpu, false, 0);
+}
+
+static int genpd_get_cpu(struct generic_pm_domain *genpd, struct device *dev)
+{
+	int cpu;
+
+	if (!genpd_is_cpu_domain(genpd))
+		return -1;
+
+	for_each_possible_cpu(cpu) {
+		if (get_cpu_device(cpu) == dev)
+			return cpu;
+	}
+
+	return -1;
+}
+
 static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
-			    struct gpd_timing_data *td)
+			    struct device *base_dev)
 {
 	struct generic_pm_domain_data *gpd_data;
 	int ret;
@@ -1465,16 +1510,19 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data = genpd_alloc_dev_data(dev, td);
+	gpd_data = genpd_alloc_dev_data(dev);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
+	gpd_data->cpu = genpd_get_cpu(genpd, base_dev);
+
 	ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
 	if (ret)
 		goto out;
 
 	genpd_lock(genpd);
 
+	genpd_set_cpumask(genpd, gpd_data->cpu);
 	dev_pm_domain_set(dev, &genpd->domain);
 
 	genpd->device_count++;
@@ -1502,7 +1550,7 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 	int ret;
 
 	mutex_lock(&gpd_list_lock);
-	ret = genpd_add_device(genpd, dev, NULL);
+	ret = genpd_add_device(genpd, dev, dev);
 	mutex_unlock(&gpd_list_lock);
 
 	return ret;
@@ -1532,6 +1580,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 	genpd->device_count--;
 	genpd->max_off_time_changed = true;
 
+	genpd_clear_cpumask(genpd, gpd_data->cpu);
 	dev_pm_domain_set(dev, NULL);
 
 	list_del_init(&pdd->list_node);
@@ -1686,6 +1735,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 
+static void genpd_free_default_power_state(struct genpd_power_state *states,
+					   unsigned int state_count)
+{
+	kfree(states);
+}
+
 static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
 {
 	struct genpd_power_state *state;
@@ -1696,7 +1751,7 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
 
 	genpd->states = state;
 	genpd->state_count = 1;
-	genpd->free = state;
+	genpd->free_states = genpd_free_default_power_state;
 
 	return 0;
 }
@@ -1762,11 +1817,18 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	if (genpd_is_always_on(genpd) && !genpd_status_on(genpd))
 		return -EINVAL;
 
+	if (genpd_is_cpu_domain(genpd) &&
+	    !zalloc_cpumask_var(&genpd->cpus, GFP_KERNEL))
+		return -ENOMEM;
+
 	/* Use only one "off" state if there were no states declared */
 	if (genpd->state_count == 0) {
 		ret = genpd_set_default_power_state(genpd);
-		if (ret)
+		if (ret) {
+			if (genpd_is_cpu_domain(genpd))
+				free_cpumask_var(genpd->cpus);
 			return ret;
+		}
 	} else if (!gov && genpd->state_count > 1) {
 		pr_warn("%s: no governor for states\n", genpd->name);
 	}
@@ -1812,7 +1874,11 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	list_del(&genpd->gpd_list_node);
 	genpd_unlock(genpd);
 	cancel_work_sync(&genpd->power_off_work);
-	kfree(genpd->free);
+	if (genpd_is_cpu_domain(genpd))
+		free_cpumask_var(genpd->cpus);
+	if (genpd->free_states)
+		genpd->free_states(genpd->states, genpd->state_count);
+
 	pr_debug("%s: removed %s\n", __func__, genpd->name);
 
 	return 0;
@@ -2190,7 +2256,7 @@ int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev)
 		goto out;
 	}
 
-	ret = genpd_add_device(genpd, dev, NULL);
+	ret = genpd_add_device(genpd, dev, dev);
 
 out:
 	mutex_unlock(&gpd_list_lock);
@@ -2274,6 +2340,7 @@ EXPORT_SYMBOL_GPL(of_genpd_remove_last);
 
 static void genpd_release_dev(struct device *dev)
 {
+	of_node_put(dev->of_node);
 	kfree(dev);
 }
 
@@ -2335,14 +2402,14 @@ static void genpd_dev_pm_sync(struct device *dev)
 	genpd_queue_power_off_work(pd);
 }
 
-static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
+static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev,
 				 unsigned int index, bool power_on)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
 	int ret;
 
-	ret = of_parse_phandle_with_args(np, "power-domains",
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
 				"#power-domain-cells", index, &pd_args);
 	if (ret < 0)
 		return ret;
@@ -2354,12 +2421,12 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
 		mutex_unlock(&gpd_list_lock);
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		return driver_deferred_probe_check_state(dev);
+		return driver_deferred_probe_check_state(base_dev);
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	ret = genpd_add_device(pd, dev, NULL);
+	ret = genpd_add_device(pd, dev, base_dev);
 	mutex_unlock(&gpd_list_lock);
 
 	if (ret < 0) {
@@ -2410,7 +2477,7 @@ int genpd_dev_pm_attach(struct device *dev)
 				       "#power-domain-cells") != 1)
 		return 0;
 
-	return __genpd_dev_pm_attach(dev, dev->of_node, 0, true);
+	return __genpd_dev_pm_attach(dev, dev, 0, true);
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 
@@ -2440,10 +2507,10 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	if (!dev->of_node)
 		return NULL;
 
-	/* Deal only with devices using multiple PM domains. */
+	/* Verify that the index is within a valid range. */
 	num_domains = of_count_phandle_with_args(dev->of_node, "power-domains",
 						 "#power-domain-cells");
-	if (num_domains < 2 || index >= num_domains)
+	if (index >= num_domains)
 		return NULL;
 
 	/* Allocate and register device on the genpd bus. */
@@ -2454,15 +2521,16 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	dev_set_name(virt_dev, "genpd:%u:%s", index, dev_name(dev));
 	virt_dev->bus = &genpd_bus_type;
 	virt_dev->release = genpd_release_dev;
+	virt_dev->of_node = of_node_get(dev->of_node);
 
 	ret = device_register(virt_dev);
 	if (ret) {
-		kfree(virt_dev);
+		put_device(virt_dev);
 		return ERR_PTR(ret);
 	}
 
 	/* Try to attach the device to the PM domain at the specified index. */
-	ret = __genpd_dev_pm_attach(virt_dev, dev->of_node, index, false);
+	ret = __genpd_dev_pm_attach(virt_dev, dev, index, false);
 	if (ret < 1) {
 		device_unregister(virt_dev);
 		return ret ? ERR_PTR(ret) : NULL;
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 4d07e38a8247..7912bc957244 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -10,6 +10,9 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
 #include <linux/hrtimer.h>
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/ktime.h>
 
 static int dev_update_qos_constraint(struct device *dev, void *data)
 {
@@ -210,8 +213,10 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
 	struct gpd_link *link;
 
-	if (!genpd->max_off_time_changed)
+	if (!genpd->max_off_time_changed) {
+		genpd->state_idx = genpd->cached_power_down_state_idx;
 		return genpd->cached_power_down_ok;
+	}
 
 	/*
 	 * We have to invalidate the cached results for the masters, so
@@ -236,6 +241,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		genpd->state_idx--;
 	}
 
+	genpd->cached_power_down_state_idx = genpd->state_idx;
 	return genpd->cached_power_down_ok;
 }
 
@@ -244,6 +250,65 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 	return false;
 }
 
+#ifdef CONFIG_CPU_IDLE
+static bool cpu_power_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct cpuidle_device *dev;
+	ktime_t domain_wakeup, next_hrtimer;
+	s64 idle_duration_ns;
+	int cpu, i;
+
+	/* Validate dev PM QoS constraints. */
+	if (!default_power_down_ok(pd))
+		return false;
+
+	if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
+		return true;
+
+	/*
+	 * Find the next wakeup for any of the online CPUs within the PM domain
+	 * and its subdomains. Note, we only need the genpd->cpus, as it already
+	 * contains a mask of all CPUs from subdomains.
+	 */
+	domain_wakeup = ktime_set(KTIME_SEC_MAX, 0);
+	for_each_cpu_and(cpu, genpd->cpus, cpu_online_mask) {
+		dev = per_cpu(cpuidle_devices, cpu);
+		if (dev) {
+			next_hrtimer = READ_ONCE(dev->next_hrtimer);
+			if (ktime_before(next_hrtimer, domain_wakeup))
+				domain_wakeup = next_hrtimer;
+		}
+	}
+
+	/* The minimum idle duration is from now - until the next wakeup. */
+	idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get()));
+	if (idle_duration_ns <= 0)
+		return false;
+
+	/*
+	 * Find the deepest idle state that has its residency value satisfied
+	 * and by also taking into account the power off latency for the state.
+	 * Start at the state picked by the dev PM QoS constraint validation.
+	 */
+	i = genpd->state_idx;
+	do {
+		if (idle_duration_ns >= (genpd->states[i].residency_ns +
+		    genpd->states[i].power_off_latency_ns)) {
+			genpd->state_idx = i;
+			return true;
+		}
+	} while (--i >= 0);
+
+	return false;
+}
+
+struct dev_power_governor pm_domain_cpu_gov = {
+	.suspend_ok = default_suspend_ok,
+	.power_down_ok = cpu_power_down_ok,
+};
+#endif
+
 struct dev_power_governor simple_qos_governor = {
 	.suspend_ok = default_suspend_ok,
 	.power_down_ok = default_power_down_ok,
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index f80d298de3fa..43e863cc0c1b 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -478,7 +478,7 @@ struct dpm_watchdog {
 
 /**
  * dpm_watchdog_handler - Driver suspend / resume watchdog handler.
- * @data: Watchdog object address.
+ * @t: The timer that PM watchdog depends on.
  *
  * Called when a driver has timed out suspending or resuming.
  * There's not much we can do here to recover so panic() to
@@ -706,6 +706,19 @@ static bool is_async(struct device *dev)
 		&& !pm_trace_is_enabled();
 }
 
+static bool dpm_async_fn(struct device *dev, async_func_t func)
+{
+	reinit_completion(&dev->power.completion);
+
+	if (is_async(dev)) {
+		get_device(dev);
+		async_schedule(func, dev);
+		return true;
+	}
+
+	return false;
+}
+
 static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = (struct device *)data;
@@ -732,13 +745,8 @@ void dpm_noirq_resume_devices(pm_message_t state)
 	 * in case the starting of async threads is
 	 * delayed by non-async resuming devices.
 	 */
-	list_for_each_entry(dev, &dpm_noirq_list, power.entry) {
-		reinit_completion(&dev->power.completion);
-		if (is_async(dev)) {
-			get_device(dev);
-			async_schedule_dev(async_resume_noirq, dev);
-		}
-	}
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
+		dpm_async_fn(dev, async_resume_noirq);
 
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
@@ -889,13 +897,8 @@ void dpm_resume_early(pm_message_t state)
 	 * in case the starting of async threads is
 	 * delayed by non-async resuming devices.
 	 */
-	list_for_each_entry(dev, &dpm_late_early_list, power.entry) {
-		reinit_completion(&dev->power.completion);
-		if (is_async(dev)) {
-			get_device(dev);
-			async_schedule_dev(async_resume_early, dev);
-		}
-	}
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
+		dpm_async_fn(dev, async_resume_early);
 
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
@@ -1053,13 +1056,8 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
-	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
-		reinit_completion(&dev->power.completion);
-		if (is_async(dev)) {
-			get_device(dev);
-			async_schedule_dev(async_resume, dev);
-		}
-	}
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
+		dpm_async_fn(dev, async_resume);
 
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
@@ -1373,13 +1371,9 @@ static void async_suspend_noirq(void *data, async_cookie_t cookie)
 
 static int device_suspend_noirq(struct device *dev)
 {
-	reinit_completion(&dev->power.completion);
-
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(async_suspend_noirq, dev);
+	if (dpm_async_fn(dev, async_suspend_noirq))
 		return 0;
-	}
+
 	return __device_suspend_noirq(dev, pm_transition, false);
 }
 
@@ -1576,13 +1570,8 @@ static void async_suspend_late(void *data, async_cookie_t cookie)
 
 static int device_suspend_late(struct device *dev)
 {
-	reinit_completion(&dev->power.completion);
-
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(async_suspend_late, dev);
+	if (dpm_async_fn(dev, async_suspend_late))
 		return 0;
-	}
 
 	return __device_suspend_late(dev, pm_transition, false);
 }
@@ -1747,6 +1736,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.syscore)
 		goto Complete;
 
+	/* Avoid direct_complete to let wakeup_path propagate. */
+	if (device_may_wakeup(dev) || dev->power.wakeup_path)
+		dev->power.direct_complete = false;
+
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
 			pm_runtime_disable(dev);
@@ -1842,13 +1835,8 @@ static void async_suspend(void *data, async_cookie_t cookie)
 
 static int device_suspend(struct device *dev)
 {
-	reinit_completion(&dev->power.completion);
-
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(async_suspend, dev);
+	if (dpm_async_fn(dev, async_suspend))
 		return 0;
-	}
 
 	return __device_suspend(dev, pm_transition, false);
 }
@@ -2069,8 +2057,8 @@ EXPORT_SYMBOL_GPL(__suspend_report_result);
 
 /**
  * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete.
- * @dev: Device to wait for.
  * @subordinate: Device that needs to wait for @dev.
+ * @dev: Device to wait for.
  */
 int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
 {
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index bb1ae175fae1..23c243a4c675 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -804,7 +804,7 @@ void pm_print_active_wakeup_sources(void)
 	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
-			pr_debug("active wakeup source: %s\n", ws->name);
+			pm_pr_dbg("active wakeup source: %s\n", ws->name);
 			active = 1;
 		} else if (!active &&
 			   (!last_activity_ws ||
@@ -815,7 +815,7 @@ void pm_print_active_wakeup_sources(void)
 	}
 
 	if (!active && last_activity_ws)
-		pr_debug("last active wakeup source: %s\n",
+		pm_pr_dbg("last active wakeup source: %s\n",
 			last_activity_ws->name);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
@@ -845,7 +845,7 @@ bool pm_wakeup_pending(void)
 	raw_spin_unlock_irqrestore(&events_lock, flags);
 
 	if (ret) {
-		pr_debug("Wakeup pending, aborting suspend\n");
+		pm_pr_dbg("Wakeup pending, aborting suspend\n");
 		pm_print_active_wakeup_sources();
 	}