Merge tag 'pm-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These clean up and rework the PM QoS API, address a suspend-to-idle
  wakeup regression on some ACPI-based platforms, clean up and extend a
  few cpuidle drivers, update multiple cpufreq drivers and cpufreq
  documentation, and fix a number of issues in devfreq and several other
  things all over.

  Specifics:

   - Clean up and rework the PM QoS API to simplify the code and reduce
     the size of it (Rafael Wysocki).

   - Fix a suspend-to-idle wakeup regression on Dell XPS13 9370 and
     similar platforms where the USB plug/unplug events are handled by
     the EC (Rafael Wysocki).

   - CLean up the intel_idle and PSCI cpuidle drivers (Rafael Wysocki,
     Ulf Hansson).

   - Extend the haltpoll cpuidle driver so that it can be forced to run
     on some systems where it refused to load (Maciej Szmigiero).

   - Convert several cpufreq documents to the .rst format and move the
     legacy driver documentation into one common file (Mauro Carvalho
     Chehab, Rafael Wysocki).

   - Update several cpufreq drivers:

        * Extend and fix the imx-cpufreq-dt driver (Anson Huang).

        * Improve the -EPROBE_DEFER handling and fix unwanted CPU
          overclocking on i.MX6ULL in imx6q-cpufreq (Anson Huang,
          Christoph Niedermaier).

        * Add support for Krait based SoCs to the qcom driver (Ansuel
          Smith).

        * Add support for OPP_PLUS to ti-cpufreq (Lokesh Vutla).

        * Add platform specific intermediate callbacks support to
          cpufreq-dt and update the imx6q driver (Peng Fan).

        * Simplify and consolidate some pieces of the intel_pstate
          driver and update its documentation (Rafael Wysocki, Alex
          Hung).

   - Fix several devfreq issues:

        * Remove unneeded extern keyword from a devfreq header file and
          use the DEVFREQ_GOV_UPDATE_INTERNAL event name instead of
          DEVFREQ_GOV_INTERNAL (Chanwoo Choi).

        * Fix the handling of dev_pm_qos_remove_request() result
          (Leonard Crestez).

        * Use constant name for userspace governor (Pierre Kuo).

        * Get rid of doc warnings and fix a typo (Christophe JAILLET).

   - Use built-in RCU list checking in some places in the PM core to
     avoid false-positive RCU usage warnings (Madhuparna Bhowmik).

   - Add explicit READ_ONCE()/WRITE_ONCE() annotations to low-level PM
     QoS routines (Qian Cai).

   - Fix removal of wakeup sources to avoid NULL pointer dereferences in
     a corner case (Neeraj Upadhyay).

   - Clean up the handling of hibernate compat ioctls and fix the
     related documentation (Eric Biggers).

   - Update the idle_inject power capping driver to use variable-length
     arrays instead of zero-length arrays (Gustavo Silva).

   - Fix list format in a PM QoS document (Randy Dunlap).

   - Make the cpufreq stats module use scnprintf() to avoid potential
     buffer overflows (Takashi Iwai).

   - Add pm_runtime_get_if_active() to PM-runtime API (Sakari Ailus).

   - Allow no domain-idle-states DT property in generic PM domains (Ulf
     Hansson).

   - Fix a broken y-axis scale in the intel_pstate_tracer utility (Doug
     Smythies)"

* tag 'pm-5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (78 commits)
  cpufreq: intel_pstate: Simplify intel_pstate_cpu_init()
  tools/power/x86/intel_pstate_tracer: fix a broken y-axis scale
  ACPI: PM: s2idle: Refine active GPEs check
  ACPICA: Allow acpi_any_gpe_status_set() to skip one GPE
  PM: sleep: wakeup: Skip wakeup_source_sysfs_remove() if device is not there
  PM / devfreq: Get rid of some doc warnings
  PM / devfreq: Fix handling dev_pm_qos_remove_request result
  PM / devfreq: Fix a typo in a comment
  PM / devfreq: Change to DEVFREQ_GOV_UPDATE_INTERVAL event name
  PM / devfreq: Remove unneeded extern keyword
  PM / devfreq: Use constant name of userspace governor
  ACPI: PM: s2idle: Fix comment in acpi_s2idle_prepare_late()
  cpufreq: qcom: Add support for krait based socs
  cpufreq: imx6q-cpufreq: Improve the logic of -EPROBE_DEFER handling
  cpufreq: Use scnprintf() for avoiding potential buffer overflow
  cpuidle: psci: Split psci_dt_cpu_init_idle()
  PM / Domains: Allow no domain-idle-states DT property in genpd when parsing
  PM / hibernate: Remove unnecessary compat ioctl overrides
  PM: hibernate: fix docs for ioctls that return loff_t via pointer
  Documentation: intel_pstate: update links for references
  ...

4 files changed, 47 insertions, 20 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 959d6d5eb000..0a01df608849 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2653,7 +2653,7 @@ static int genpd_iterate_idle_states(struct device_node *dn,
 
 	ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
 	if (ret <= 0)
-		return ret;
+		return ret == -ENOENT ? 0 : ret;
 
 	/* Loop over the phandles until all the requested entry is found */
 	of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) {
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 0e99a760aebd..6d1dee7051eb 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -40,6 +40,10 @@
 
 typedef int (*pm_callback_t)(struct device *);
 
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+			device_links_read_lock_held())
+
 /*
  * The entries in the dpm_list list are in a depth first order, simply
  * because children are guaranteed to be discovered after parents, and
@@ -266,7 +270,7 @@ static void dpm_wait_for_suppliers(struct device *dev, bool async)
 	 * callbacks freeing the link objects for the links in the list we're
 	 * walking.
 	 */
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_wait(link->supplier, async);
 
@@ -323,7 +327,7 @@ static void dpm_wait_for_consumers(struct device *dev, bool async)
 	 * continue instead of trying to continue in parallel with its
 	 * unregistration).
 	 */
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.consumers, s_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_wait(link->consumer, async);
 
@@ -1235,7 +1239,7 @@ static void dpm_superior_set_must_resume(struct device *dev)
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		link->supplier->power.must_resume = true;
 
 	device_links_read_unlock(idx);
@@ -1695,7 +1699,7 @@ static void dpm_clear_superiors_direct_complete(struct device *dev)
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node) {
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) {
 		spin_lock_irq(&link->supplier->power.lock);
 		link->supplier->power.direct_complete = false;
 		spin_unlock_irq(&link->supplier->power.lock);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 16134a69bf6f..99c7da112c95 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1087,29 +1087,47 @@ int __pm_runtime_resume(struct device *dev, int rpmflags)
 EXPORT_SYMBOL_GPL(__pm_runtime_resume);
 
 /**
- * pm_runtime_get_if_in_use - Conditionally bump up the device's usage counter.
+ * pm_runtime_get_if_active - Conditionally bump up the device's usage counter.
  * @dev: Device to handle.
  *
  * Return -EINVAL if runtime PM is disabled for the device.
  *
- * If that's not the case and if the device's runtime PM status is RPM_ACTIVE
- * and the runtime PM usage counter is nonzero, increment the counter and
- * return 1.  Otherwise return 0 without changing the counter.
+ * Otherwise, if the device's runtime PM status is RPM_ACTIVE and either
+ * ign_usage_count is true or the device's usage_count is non-zero, increment
+ * the counter and return 1. Otherwise return 0 without changing the counter.
+ *
+ * If ign_usage_count is true, the function can be used to prevent suspending
+ * the device when its runtime PM status is RPM_ACTIVE.
+ *
+ * If ign_usage_count is false, the function can be used to prevent suspending
+ * the device when both its runtime PM status is RPM_ACTIVE and its usage_count
+ * is non-zero.
+ *
+ * The caller is resposible for putting the device's usage count when ther
+ * return value is greater than zero.
  */
-int pm_runtime_get_if_in_use(struct device *dev)
+int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count)
 {
 	unsigned long flags;
 	int retval;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
-	retval = dev->power.disable_depth > 0 ? -EINVAL :
-		dev->power.runtime_status == RPM_ACTIVE
-			&& atomic_inc_not_zero(&dev->power.usage_count);
+	if (dev->power.disable_depth > 0) {
+		retval = -EINVAL;
+	} else if (dev->power.runtime_status != RPM_ACTIVE) {
+		retval = 0;
+	} else if (ign_usage_count) {
+		retval = 1;
+		atomic_inc(&dev->power.usage_count);
+	} else {
+		retval = atomic_inc_not_zero(&dev->power.usage_count);
+	}
 	trace_rpm_usage_rcuidle(dev, 0);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
+
 	return retval;
 }
-EXPORT_SYMBOL_GPL(pm_runtime_get_if_in_use);
+EXPORT_SYMBOL_GPL(pm_runtime_get_if_active);
 
 /**
  * __pm_runtime_set_status - Set runtime PM status of a device.
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 27f3e60608e5..92073ac68473 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -24,6 +24,9 @@ suspend_state_t pm_suspend_target_state;
 #define pm_suspend_target_state	(PM_SUSPEND_ON)
 #endif
 
+#define list_for_each_entry_rcu_locked(pos, head, member) \
+	list_for_each_entry_rcu(pos, head, member, \
+		srcu_read_lock_held(&wakeup_srcu))
 /*
  * If set, the suspend/hibernate code will abort transitions to a sleep state
  * if wakeup events are registered during or immediately before the transition.
@@ -241,7 +244,9 @@ void wakeup_source_unregister(struct wakeup_source *ws)
 {
 	if (ws) {
 		wakeup_source_remove(ws);
-		wakeup_source_sysfs_remove(ws);
+		if (ws->dev)
+			wakeup_source_sysfs_remove(ws);
+
 		wakeup_source_destroy(ws);
 	}
 }
@@ -405,7 +410,7 @@ void device_wakeup_arm_wake_irqs(void)
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
 		dev_pm_arm_wake_irq(ws->wakeirq);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
@@ -421,7 +426,7 @@ void device_wakeup_disarm_wake_irqs(void)
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry)
 		dev_pm_disarm_wake_irq(ws->wakeirq);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
@@ -874,7 +879,7 @@ void pm_print_active_wakeup_sources(void)
 	struct wakeup_source *last_activity_ws = NULL;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		if (ws->active) {
 			pm_pr_dbg("active wakeup source: %s\n", ws->name);
 			active = 1;
@@ -1025,7 +1030,7 @@ void pm_wakep_autosleep_enabled(bool set)
 	int srcuidx;
 
 	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		spin_lock_irq(&ws->lock);
 		if (ws->autosleep_enabled != set) {
 			ws->autosleep_enabled = set;
@@ -1104,7 +1109,7 @@ static void *wakeup_sources_stats_seq_start(struct seq_file *m,
 	}
 
 	*srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+	list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) {
 		if (n-- <= 0)
 			return ws;
 	}