5 files changed, 135 insertions, 52 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index de8587cc119e..c1179edc0f3b 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,17 +21,94 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
+static DEFINE_PER_CPU(struct scale_freq_data *, sft_data);
+static struct cpumask scale_freq_counters_mask;
+static bool scale_freq_invariant;
+
+static bool supports_scale_freq_counters(const struct cpumask *cpus)
+{
+	return cpumask_subset(cpus, &scale_freq_counters_mask);
+}
+
 bool topology_scale_freq_invariant(void)
 {
 	return cpufreq_supports_freq_invariance() ||
-	       arch_freq_counters_available(cpu_online_mask);
+	       supports_scale_freq_counters(cpu_online_mask);
 }
 
-__weak bool arch_freq_counters_available(const struct cpumask *cpus)
+static void update_scale_freq_invariant(bool status)
 {
-	return false;
+	if (scale_freq_invariant == status)
+		return;
+
+	/*
+	 * Task scheduler behavior depends on frequency invariance support,
+	 * either cpufreq or counter driven. If the support status changes as
+	 * a result of counter initialisation and use, retrigger the build of
+	 * scheduling domains to ensure the information is propagated properly.
+	 */
+	if (topology_scale_freq_invariant() == status) {
+		scale_freq_invariant = status;
+		rebuild_sched_domains_energy();
+	}
 }
-DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
+
+void topology_set_scale_freq_source(struct scale_freq_data *data,
+				    const struct cpumask *cpus)
+{
+	struct scale_freq_data *sfd;
+	int cpu;
+
+	/*
+	 * Avoid calling rebuild_sched_domains() unnecessarily if FIE is
+	 * supported by cpufreq.
+	 */
+	if (cpumask_empty(&scale_freq_counters_mask))
+		scale_freq_invariant = topology_scale_freq_invariant();
+
+	for_each_cpu(cpu, cpus) {
+		sfd = per_cpu(sft_data, cpu);
+
+		/* Use ARCH provided counters whenever possible */
+		if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) {
+			per_cpu(sft_data, cpu) = data;
+			cpumask_set_cpu(cpu, &scale_freq_counters_mask);
+		}
+	}
+
+	update_scale_freq_invariant(true);
+}
+EXPORT_SYMBOL_GPL(topology_set_scale_freq_source);
+
+void topology_clear_scale_freq_source(enum scale_freq_source source,
+				      const struct cpumask *cpus)
+{
+	struct scale_freq_data *sfd;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		sfd = per_cpu(sft_data, cpu);
+
+		if (sfd && sfd->source == source) {
+			per_cpu(sft_data, cpu) = NULL;
+			cpumask_clear_cpu(cpu, &scale_freq_counters_mask);
+		}
+	}
+
+	update_scale_freq_invariant(false);
+}
+EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source);
+
+void topology_scale_freq_tick(void)
+{
+	struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data);
+
+	if (sfd)
+		sfd->set_freq_scale();
+}
+
+DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
 
 void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 			     unsigned long max_freq)
@@ -47,13 +124,13 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 	 * want to update the scale factor with information from CPUFREQ.
 	 * Instead the scale factor will be updated from arch_scale_freq_tick.
 	 */
-	if (arch_freq_counters_available(cpus))
+	if (supports_scale_freq_counters(cpus))
 		return;
 
 	scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq;
 
 	for_each_cpu(i, cpus)
-		per_cpu(freq_scale, i) = scale;
+		per_cpu(arch_freq_scale, i) = scale;
 }
 
 DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 9179825ff646..e2cf3b29123e 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -97,6 +97,9 @@ static void deferred_probe_work_func(struct work_struct *work)
 
 		get_device(dev);
 
+		kfree(dev->p->deferred_probe_reason);
+		dev->p->deferred_probe_reason = NULL;
+
 		/*
 		 * Drop the mutex while probing each device; the probe path may
 		 * manipulate the deferred list
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 78c310d3179d..b6a782c31613 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1088,34 +1088,6 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 }
 
 /**
- * resume_needed - Check whether to resume a device before system suspend.
- * @dev: Device to check.
- * @genpd: PM domain the device belongs to.
- *
- * There are two cases in which a device that can wake up the system from sleep
- * states should be resumed by genpd_prepare(): (1) if the device is enabled
- * to wake up the system and it has to remain active for this purpose while the
- * system is in the sleep state and (2) if the device is not enabled to wake up
- * the system from sleep states and it generally doesn't generate wakeup signals
- * by itself (those signals are generated on its behalf by other parts of the
- * system).  In the latter case it may be necessary to reconfigure the device's
- * wakeup settings during system suspend, because it may have been set up to
- * signal remote wakeup from the system's working state as needed by runtime PM.
- * Return 'true' in either of the above cases.
- */
-static bool resume_needed(struct device *dev,
-			  const struct generic_pm_domain *genpd)
-{
-	bool active_wakeup;
-
-	if (!device_can_wakeup(dev))
-		return false;
-
-	active_wakeup = genpd_is_active_wakeup(genpd);
-	return device_may_wakeup(dev) ? active_wakeup : !active_wakeup;
-}
-
-/**
  * genpd_prepare - Start power transition of a device in a PM domain.
  * @dev: Device to start the transition of.
  *
@@ -1135,14 +1107,6 @@ static int genpd_prepare(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	/*
-	 * If a wakeup request is pending for the device, it should be woken up
-	 * at this point and a system wakeup event should be reported if it's
-	 * set up to wake up the system from sleep states.
-	 */
-	if (resume_needed(dev, genpd))
-		pm_runtime_resume(dev);
-
 	genpd_lock(genpd);
 
 	if (genpd->prepared_count++ == 0)
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index a46a7e30881b..fe1dad68aee4 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -305,7 +305,7 @@ static int rpm_get_suppliers(struct device *dev)
 	return 0;
 }
 
-static void rpm_put_suppliers(struct device *dev)
+static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
 {
 	struct device_link *link;
 
@@ -313,10 +313,30 @@ static void rpm_put_suppliers(struct device *dev)
 				device_links_read_lock_held()) {
 
 		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put(link->supplier);
+			pm_runtime_put_noidle(link->supplier);
+
+		if (try_to_suspend)
+			pm_request_idle(link->supplier);
 	}
 }
 
+static void rpm_put_suppliers(struct device *dev)
+{
+	__rpm_put_suppliers(dev, true);
+}
+
+static void rpm_suspend_suppliers(struct device *dev)
+{
+	struct device_link *link;
+	int idx = device_links_read_lock();
+
+	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held())
+		pm_request_idle(link->supplier);
+
+	device_links_read_unlock(idx);
+}
+
 /**
  * __rpm_callback - Run a given runtime PM callback for a given device.
  * @cb: Runtime PM callback to run.
@@ -344,8 +364,10 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 			idx = device_links_read_lock();
 
 			retval = rpm_get_suppliers(dev);
-			if (retval)
+			if (retval) {
+				rpm_put_suppliers(dev);
 				goto fail;
+			}
 
 			device_links_read_unlock(idx);
 		}
@@ -368,9 +390,9 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
 		    || (dev->power.runtime_status == RPM_RESUMING && retval))) {
 			idx = device_links_read_lock();
 
- fail:
-			rpm_put_suppliers(dev);
+			__rpm_put_suppliers(dev, false);
 
+fail:
 			device_links_read_unlock(idx);
 		}
 
@@ -642,8 +664,11 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 		goto out;
 	}
 
+	if (dev->power.irq_safe)
+		goto out;
+
 	/* Maybe the parent is now able to suspend. */
-	if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
+	if (parent && !parent->power.ignore_children) {
 		spin_unlock(&dev->power.lock);
 
 		spin_lock(&parent->power.lock);
@@ -652,6 +677,14 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 		spin_lock(&dev->power.lock);
 	}
+	/* Maybe the suppliers are now able to suspend. */
+	if (dev->power.links_count > 0) {
+		spin_unlock_irq(&dev->power.lock);
+
+		rpm_suspend_suppliers(dev);
+
+		spin_lock_irq(&dev->power.lock);
+	}
 
  out:
 	trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
@@ -1657,8 +1690,8 @@ void pm_runtime_get_suppliers(struct device *dev)
 				device_links_read_lock_held())
 		if (link->flags & DL_FLAG_PM_RUNTIME) {
 			link->supplier_preactivated = true;
-			refcount_inc(&link->rpm_active);
 			pm_runtime_get_sync(link->supplier);
+			refcount_inc(&link->rpm_active);
 		}
 
 	device_links_read_unlock(idx);
@@ -1671,6 +1704,8 @@ void pm_runtime_get_suppliers(struct device *dev)
 void pm_runtime_put_suppliers(struct device *dev)
 {
 	struct device_link *link;
+	unsigned long flags;
+	bool put;
 	int idx;
 
 	idx = device_links_read_lock();
@@ -1679,7 +1714,11 @@ void pm_runtime_put_suppliers(struct device *dev)
 				device_links_read_lock_held())
 		if (link->supplier_preactivated) {
 			link->supplier_preactivated = false;
-			if (refcount_dec_not_one(&link->rpm_active))
+			spin_lock_irqsave(&dev->power.lock, flags);
+			put = pm_runtime_status_suspended(dev) &&
+			      refcount_dec_not_one(&link->rpm_active);
+			spin_unlock_irqrestore(&dev->power.lock, flags);
+			if (put)
 				pm_runtime_put(link->supplier);
 		}
 
diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c
index d638259b829a..924fac493c4f 100644
--- a/drivers/base/power/wakeup_stats.c
+++ b/drivers/base/power/wakeup_stats.c
@@ -137,7 +137,7 @@ static struct device *wakeup_source_device_create(struct device *parent,
 						  struct wakeup_source *ws)
 {
 	struct device *dev = NULL;
-	int retval = -ENODEV;
+	int retval;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev) {
@@ -154,7 +154,7 @@ static struct device *wakeup_source_device_create(struct device *parent,
 	dev_set_drvdata(dev, ws);
 	device_set_pm_not_required(dev);
 
-	retval = kobject_set_name(&dev->kobj, "wakeup%d", ws->id);
+	retval = dev_set_name(dev, "wakeup%d", ws->id);
 	if (retval)
 		goto error;