Merge cpuidle material depended on by the subsequent changes.

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)
@@ -1452,6 +1454,56 @@ 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_update_cpumask(struct generic_pm_domain *genpd,
+				 struct device *dev, bool set)
+{
+	int cpu;
+
+	if (!genpd_is_cpu_domain(genpd))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		if (get_cpu_device(cpu) == dev) {
+			__genpd_update_cpumask(genpd, cpu, set, 0);
+			return;
+		}
+	}
+}
+
+static void genpd_set_cpumask(struct generic_pm_domain *genpd,
+			      struct device *dev)
+{
+	genpd_update_cpumask(genpd, dev, true);
+}
+
+static void genpd_clear_cpumask(struct generic_pm_domain *genpd,
+				struct device *dev)
+{
+	genpd_update_cpumask(genpd, dev, false);
+}
+
 static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 			    struct gpd_timing_data *td)
 {
@@ -1473,6 +1525,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 
 	genpd_lock(genpd);
 
+	genpd_set_cpumask(genpd, dev);
 	dev_pm_domain_set(dev, &genpd->domain);
 
 	genpd->device_count++;
@@ -1530,6 +1583,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 	genpd->device_count--;
 	genpd->max_off_time_changed = true;
 
+	genpd_clear_cpumask(genpd, dev);
 	dev_pm_domain_set(dev, NULL);
 
 	list_del_init(&pdd->list_node);
@@ -1684,6 +1738,12 @@ 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;
@@ -1694,7 +1754,7 @@ 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;
 }
@@ -1760,11 +1820,18 @@ 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);
 	}
@@ -1810,7 +1877,11 @@ 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;

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,

drivers/cpuidle/cpuidle-exynos.c

@@ -84,7 +84,7 @@ static struct cpuidle_driver exynos_idle_driver = {
 		[1] = {
 			.enter			= exynos_enter_lowpower,
 			.exit_latency		= 300,
-			.target_residency	= 100000,
+			.target_residency	= 10000,
 			.name			= "C1",
 			.desc			= "ARM power down",
 		},

drivers/cpuidle/cpuidle.c

@@ -328,9 +328,23 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		  int index)
 {
+	int ret = 0;
+
+	/*
+	 * Store the next hrtimer, which becomes either next tick or the next
+	 * timer event, whatever expires first. Additionally, to make this data
+	 * useful for consumers outside cpuidle, we rely on that the governor's
+	 * ->select() callback have decided, whether to stop the tick or not.
+	 */
+	WRITE_ONCE(dev->next_hrtimer, tick_nohz_get_next_hrtimer());
+
 	if (cpuidle_state_is_coupled(drv, index))
-		return cpuidle_enter_state_coupled(dev, drv, index);
-	return cpuidle_enter_state(dev, drv, index);
+		ret = cpuidle_enter_state_coupled(dev, drv, index);
+	else
+		ret = cpuidle_enter_state(dev, drv, index);
+
+	WRITE_ONCE(dev->next_hrtimer, 0);
+	return ret;
 }
 
 /**
@@ -511,6 +525,7 @@ static void __cpuidle_device_init(struct cpuidle_device *dev)
 {
 	memset(dev->states_usage, 0, sizeof(dev->states_usage));
 	dev->last_residency = 0;
+	dev->next_hrtimer = 0;
 }
 
 /**

include/linux/cpuidle.h

@@ -83,6 +83,7 @@ struct cpuidle_device {
 	unsigned int		use_deepest_state:1;
 	unsigned int		poll_time_limit:1;
 	unsigned int		cpu;
+	ktime_t			next_hrtimer;
 
 	int			last_residency;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];

include/linux/pm_domain.h

@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
+#include <linux/cpumask.h>
 
 /*
  * Flags to control the behaviour of a genpd.
@@ -42,11 +43,22 @@
  * GENPD_FLAG_ACTIVE_WAKEUP:	Instructs genpd to keep the PM domain powered
  *				on, in case any of its attached devices is used
  *				in the wakeup path to serve system wakeups.
+ *
+ * GENPD_FLAG_CPU_DOMAIN:	Instructs genpd that it should expect to get
+ *				devices attached, which may belong to CPUs or
+ *				possibly have subdomains with CPUs attached.
+ *				This flag enables the genpd backend driver to
+ *				deploy idle power management support for CPUs
+ *				and groups of CPUs. Note that, the backend
+ *				driver must then comply with the so called,
+ *				last-man-standing algorithm, for the CPUs in the
+ *				PM domain.
  */
 #define GENPD_FLAG_PM_CLK	 (1U << 0)
 #define GENPD_FLAG_IRQ_SAFE	 (1U << 1)
 #define GENPD_FLAG_ALWAYS_ON	 (1U << 2)
 #define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3)
+#define GENPD_FLAG_CPU_DOMAIN	 (1U << 4)
 
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
@@ -69,6 +81,7 @@ struct genpd_power_state {
 	s64 residency_ns;
 	struct fwnode_handle *fwnode;
 	ktime_t idle_time;
+	void *data;
 };
 
 struct genpd_lock_ops;
@@ -93,6 +106,7 @@ struct generic_pm_domain {
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
 	unsigned int performance_state;	/* Aggregated max performance state */
+	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
 	struct opp_table *opp_table;	/* OPP table of the genpd */
@@ -104,15 +118,17 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
+	bool cached_power_down_state_idx;
 	int (*attach_dev)(struct generic_pm_domain *domain,
 			  struct device *dev);
 	void (*detach_dev)(struct generic_pm_domain *domain,
 			   struct device *dev);
 	unsigned int flags;		/* Bit field of configs for genpd */
 	struct genpd_power_state *states;
+	void (*free_states)(struct genpd_power_state *states,
+			    unsigned int state_count);
 	unsigned int state_count; /* number of states */
 	unsigned int state_idx; /* state that genpd will go to when off */
-	void *free; /* Free the state that was allocated for default */
 	ktime_t on_time;
 	ktime_t accounting_time;
 	const struct genpd_lock_ops *lock_ops;
@@ -187,6 +203,9 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
+#ifdef CONFIG_CPU_IDLE
+extern struct dev_power_governor pm_domain_cpu_gov;
+#endif
 #else
 
 static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)

include/linux/tick.h

@@ -122,6 +122,7 @@ extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern bool tick_nohz_idle_got_tick(void);
+extern ktime_t tick_nohz_get_next_hrtimer(void);
 extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
 extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
@@ -145,7 +146,11 @@ static inline void tick_nohz_idle_restart_tick(void) { }
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
 static inline bool tick_nohz_idle_got_tick(void) { return false; }
-
+static inline ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	/* Next wake up is the tick period, assume it starts now */
+	return ktime_add(ktime_get(), TICK_NSEC);
+}
 static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
 	*delta_next = TICK_NSEC;

kernel/time/tick-sched.c

@@ -1022,6 +1022,18 @@ bool tick_nohz_idle_got_tick(void)
 	return false;
 }
 
+/**
+ * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
+ * or the tick, whatever that expires first. Note that, if the tick has been
+ * stopped, it returns the next hrtimer.
+ *
+ * Called from power state control code with interrupts disabled
+ */
+ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
+}
+
 /**
  * tick_nohz_get_sleep_length - return the expected length of the current sleep
  * @delta_next: duration until the next event if the tick cannot be stopped