Merge tag 'pm-5.7-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "Additional power management updates.

  These fix a corner-case suspend-to-idle wakeup issue on systems where
  the ACPI SCI is shared with another wakeup source, add a kernel
  command line option to set pm_debug_messages via the kernel command
  line, add a document desctibing system-wide suspend and resume code
  flows, modify cpufreq Kconfig to choose schedutil as the preferred
  governor by default in a couple of cases and do some assorted
  cleanups.

  Specifics:

   - Fix corner-case suspend-to-idle wakeup issue on systems where the
     ACPI SCI is shared with another wakeup source (Hans de Goede).

   - Add document describing system-wide suspend and resume code flows
     to the admin guide (Rafael Wysocki).

   - Add kernel command line option to set pm_debug_messages (Chen Yu).

   - Choose schedutil as the preferred scaling governor by default on
     ARM big.LITTLE systems and on x86 systems using the intel_pstate
     driver in the passive mode (Linus Walleij, Rafael Wysocki).

   - Drop racy and redundant checks from the PM core's device_prepare()
     routine (Rafael Wysocki).

   - Make resume from hibernation take the hibernation_restore() return
     value into account (Dexuan Cui)"

* tag 'pm-5.7-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  platform/x86: intel_int0002_vgpio: Use acpi_register_wakeup_handler()
  ACPI: PM: Add acpi_[un]register_wakeup_handler()
  Documentation: PM: sleep: Document system-wide suspend code flows
  cpufreq: Select schedutil when using big.LITTLE
  PM: sleep: Add pm_debug_messages kernel command line option
  PM: sleep: core: Drop racy and redundant checks from device_prepare()
  PM: hibernate: Propagate the return value of hibernation_restore()
  cpufreq: intel_pstate: Select schedutil as the default governor

Documentation/admin-guide/kernel-parameters.txt

@@ -3720,6 +3720,9 @@
 			Override pmtimer IOPort with a hex value.
 			e.g. pmtmr=0x508
 
+	pm_debug_messages	[SUSPEND,KNL]
+			Enable suspend/resume debug messages during boot up.
+
 	pnp.debug=1	[PNP]
 			Enable PNP debug messages (depends on the
 			CONFIG_PNP_DEBUG_MESSAGES option).  Change at run-time

Documentation/admin-guide/pm/system-wide.rst

@@ -8,3 +8,4 @@ System-Wide Power Management
    :maxdepth: 2
 
    sleep-states
+   suspend-flows

drivers/acpi/sleep.c

@@ -1009,6 +1009,10 @@ static bool acpi_s2idle_wake(void)
 		if (acpi_any_fixed_event_status_set())
 			return true;
 
+		/* Check wakeups from drivers sharing the SCI. */
+		if (acpi_check_wakeup_handlers())
+			return true;
+
 		/*
 		 * If the status bit is set for any enabled GPE other than the
 		 * EC one, the wakeup is regarded as a genuine one.

drivers/acpi/sleep.h

@@ -2,6 +2,7 @@
 
 extern void acpi_enable_wakeup_devices(u8 sleep_state);
 extern void acpi_disable_wakeup_devices(u8 sleep_state);
+extern bool acpi_check_wakeup_handlers(void);
 
 extern struct list_head acpi_wakeup_device_list;
 extern struct mutex acpi_device_lock;

drivers/acpi/wakeup.c

@@ -12,6 +12,15 @@
 #include "internal.h"
 #include "sleep.h"
 
+struct acpi_wakeup_handler {
+	struct list_head list_node;
+	bool (*wakeup)(void *context);
+	void *context;
+};
+
+static LIST_HEAD(acpi_wakeup_handler_head);
+static DEFINE_MUTEX(acpi_wakeup_handler_mutex);
+
 /*
  * We didn't lock acpi_device_lock in the file, because it invokes oops in
  * suspend/resume and isn't really required as this is called in S-state. At
@@ -90,3 +99,75 @@ int __init acpi_wakeup_device_init(void)
 	mutex_unlock(&acpi_device_lock);
 	return 0;
 }
+
+/**
+ * acpi_register_wakeup_handler - Register wakeup handler
+ * @wake_irq: The IRQ through which the device may receive wakeups
+ * @wakeup:   Wakeup-handler to call when the SCI has triggered a wakeup
+ * @context:  Context to pass to the handler when calling it
+ *
+ * Drivers which may share an IRQ with the SCI can use this to register
+ * a handler which returns true when the device they are managing wants
+ * to trigger a wakeup.
+ */
+int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context),
+				 void *context)
+{
+	struct acpi_wakeup_handler *handler;
+
+	/*
+	 * If the device is not sharing its IRQ with the SCI, there is no
+	 * need to register the handler.
+	 */
+	if (!acpi_sci_irq_valid() || wake_irq != acpi_sci_irq)
+		return 0;
+
+	handler = kmalloc(sizeof(*handler), GFP_KERNEL);
+	if (!handler)
+		return -ENOMEM;
+
+	handler->wakeup = wakeup;
+	handler->context = context;
+
+	mutex_lock(&acpi_wakeup_handler_mutex);
+	list_add(&handler->list_node, &acpi_wakeup_handler_head);
+	mutex_unlock(&acpi_wakeup_handler_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_register_wakeup_handler);
+
+/**
+ * acpi_unregister_wakeup_handler - Unregister wakeup handler
+ * @wakeup:   Wakeup-handler passed to acpi_register_wakeup_handler()
+ * @context:  Context passed to acpi_register_wakeup_handler()
+ */
+void acpi_unregister_wakeup_handler(bool (*wakeup)(void *context),
+				    void *context)
+{
+	struct acpi_wakeup_handler *handler;
+
+	mutex_lock(&acpi_wakeup_handler_mutex);
+	list_for_each_entry(handler, &acpi_wakeup_handler_head, list_node) {
+		if (handler->wakeup == wakeup && handler->context == context) {
+			list_del(&handler->list_node);
+			kfree(handler);
+			break;
+		}
+	}
+	mutex_unlock(&acpi_wakeup_handler_mutex);
+}
+EXPORT_SYMBOL_GPL(acpi_unregister_wakeup_handler);
+
+bool acpi_check_wakeup_handlers(void)
+{
+	struct acpi_wakeup_handler *handler;
+
+	/* No need to lock, nothing else is running when we're called. */
+	list_for_each_entry(handler, &acpi_wakeup_handler_head, list_node) {
+		if (handler->wakeup(handler->context))
+			return true;
+	}
+
+	return false;
+}

drivers/base/power/main.c

@@ -1922,10 +1922,6 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	if (dev->power.syscore)
 		return 0;
 
-	WARN_ON(!pm_runtime_enabled(dev) &&
-		dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND |
-					      DPM_FLAG_LEAVE_SUSPENDED));
-
 	/*
 	 * If a device's parent goes into runtime suspend at the wrong time,
 	 * it won't be possible to resume the device.  To prevent this we
@@ -1973,8 +1969,7 @@ static int device_prepare(struct device *dev, pm_message_t state)
 	 */
 	spin_lock_irq(&dev->power.lock);
 	dev->power.direct_complete = state.event == PM_EVENT_SUSPEND &&
-		((pm_runtime_suspended(dev) && ret > 0) ||
-		 dev->power.no_pm_callbacks) &&
+		(ret > 0 || dev->power.no_pm_callbacks) &&
 		!dev_pm_test_driver_flags(dev, DPM_FLAG_NEVER_SKIP);
 	spin_unlock_irq(&dev->power.lock);
 	return 0;

drivers/cpufreq/Kconfig

@@ -37,10 +37,12 @@ config CPU_FREQ_STAT
 choice
 	prompt "Default CPUFreq governor"
 	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
+	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if BIG_LITTLE
+	default CPU_FREQ_DEFAULT_GOV_SCHEDUTIL if X86_INTEL_PSTATE && SMP
 	default CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	help
 	  This option sets which CPUFreq governor shall be loaded at
-	  startup. If in doubt, select 'performance'.
+	  startup. If in doubt, use the default setting.
 
 config CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	bool "performance"

drivers/cpufreq/Kconfig.x86

@@ -8,6 +8,8 @@ config X86_INTEL_PSTATE
 	depends on X86
 	select ACPI_PROCESSOR if ACPI
 	select ACPI_CPPC_LIB if X86_64 && ACPI && SCHED_MC_PRIO
+	select CPU_FREQ_GOV_PERFORMANCE
+	select CPU_FREQ_GOV_SCHEDUTIL if SMP
 	help
 	  This driver provides a P state for Intel core processors.
 	  The driver implements an internal governor and will become

drivers/platform/x86/intel_int0002_vgpio.c

@@ -127,6 +127,14 @@ static irqreturn_t int0002_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static bool int0002_check_wake(void *data)
+{
+	u32 gpe_sts_reg;
+
+	gpe_sts_reg = inl(GPE0A_STS_PORT);
+	return (gpe_sts_reg & GPE0A_PME_B0_STS_BIT);
+}
+
 static struct irq_chip int0002_byt_irqchip = {
 	.name			= DRV_NAME,
 	.irq_ack		= int0002_irq_ack,
@@ -220,6 +228,7 @@ static int int0002_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	acpi_register_wakeup_handler(irq, int0002_check_wake, NULL);
 	device_init_wakeup(dev, true);
 	return 0;
 }
@@ -227,6 +236,7 @@ static int int0002_probe(struct platform_device *pdev)
 static int int0002_remove(struct platform_device *pdev)
 {
 	device_init_wakeup(&pdev->dev, false);
+	acpi_unregister_wakeup_handler(int0002_check_wake, NULL);
 	return 0;
 }
 

include/linux/acpi.h

@@ -488,6 +488,11 @@ void __init acpi_nvs_nosave_s3(void);
 void __init acpi_sleep_no_blacklist(void);
 #endif /* CONFIG_PM_SLEEP */
 
+int acpi_register_wakeup_handler(
+	int wake_irq, bool (*wakeup)(void *context), void *context);
+void acpi_unregister_wakeup_handler(
+	bool (*wakeup)(void *context), void *context);
+
 struct acpi_osc_context {
 	char *uuid_str;			/* UUID string */
 	int rev;

kernel/power/hibernate.c

@@ -678,7 +678,7 @@ static int load_image_and_restore(void)
 	error = swsusp_read(&flags);
 	swsusp_close(FMODE_READ);
 	if (!error)
-		hibernation_restore(flags & SF_PLATFORM_MODE);
+		error = hibernation_restore(flags & SF_PLATFORM_MODE);
 
 	pr_err("Failed to load image, recovering.\n");
 	swsusp_free();

kernel/power/main.c

@@ -535,6 +535,13 @@ static ssize_t pm_debug_messages_store(struct kobject *kobj,
 
 power_attr(pm_debug_messages);
 
+static int __init pm_debug_messages_setup(char *str)
+{
+	pm_debug_messages_on = true;
+	return 1;
+}
+__setup("pm_debug_messages", pm_debug_messages_setup);
+
 /**
  * __pm_pr_dbg - Print a suspend debug message to the kernel log.
  * @defer: Whether or not to use printk_deferred() to print the message.