Merge branches 'pm-cpuidle', 'pm-core' and 'pm-sleep'

Merge cpuidle updates, PM core updates and one hiberation-related
update for 5.17-rc1:

 - Make cpuidle use default_groups in kobj_type (Greg Kroah-Hartman).

 - Fix two comments in cpuidle code (Jason Wang, Yang Li).

 - Simplify locking in pm_runtime_put_suppliers() (Rafael Wysocki).

 - Add safety net to supplier device release in the runtime PM core
   code (Rafael Wysocki).

 - Capture device status before disabling runtime PM for it (Rafael
   Wysocki).

 - Add new macros for declaring PM operations to allow drivers to
   avoid guarding them with CONFIG_PM #ifdefs or __maybe_unused and
   update some drivers to use these macros (Paul Cercueil).

 - Allow ACPI hardware signature to be honoured during restore from
   hibernation (David Woodhouse).

* pm-cpuidle:
  cpuidle: use default_groups in kobj_type
  cpuidle: Fix cpuidle_remove_state_sysfs() kerneldoc comment
  cpuidle: menu: Fix typo in a comment

* pm-core:
  PM: runtime: Simplify locking in pm_runtime_put_suppliers()
  mmc: mxc: Use the new PM macros
  mmc: jz4740: Use the new PM macros
  PM: runtime: Add safety net to supplier device release
  PM: runtime: Capture device status before disabling runtime PM
  PM: core: Add new *_PM_OPS macros, deprecate old ones
  PM: core: Redefine pm_ptr() macro
  r8169: Avoid misuse of pm_ptr() macro

* pm-sleep:
  PM: hibernate: Allow ACPI hardware signature to be honoured

Documentation/admin-guide/kernel-parameters.txt

@@ -225,14 +225,23 @@
 			For broken nForce2 BIOS resulting in XT-PIC timer.
 
 	acpi_sleep=	[HW,ACPI] Sleep options
-			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-				  old_ordering, nonvs, sci_force_enable, nobl }
+			Format: { s3_bios, s3_mode, s3_beep, s4_hwsig,
+				  s4_nohwsig, old_ordering, nonvs,
+				  sci_force_enable, nobl }
 			See Documentation/power/video.rst for information on
 			s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
 			as soon as the kernel's real-mode entry point is called.
+			s4_hwsig causes the kernel to check the ACPI hardware
+			signature during resume from hibernation, and gracefully
+			refuse to resume if it has changed. This complies with
+			the ACPI specification but not with reality, since
+			Windows does not do this and many laptops do change it
+			on docking. So the default behaviour is to allow resume
+			and simply warn when the signature changes, unless the
+			s4_hwsig option is enabled.
 			s4_nohwsig prevents ACPI hardware signature from being
-			used during resume from hibernation.
+			used (or even warned about) during resume.
 			old_ordering causes the ACPI 1.0 ordering of the _PTS
 			control method, with respect to putting devices into
 			low power states, to be enforced (the ACPI 2.0 ordering

Documentation/power/runtime_pm.rst

@@ -265,6 +265,10 @@ defined in include/linux/pm.h:
       RPM_SUSPENDED, which means that each device is initially regarded by the
       PM core as 'suspended', regardless of its real hardware status
 
+  `enum rpm_status last_status;`
+    - the last runtime PM status of the device captured before disabling runtime
+      PM for it (invalid initially and when disable_depth is 0)
+
   `unsigned int runtime_auto;`
     - if set, indicates that the user space has allowed the device driver to
       power manage the device at run time via the /sys/devices/.../power/control
@@ -333,10 +337,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
 
   `int pm_runtime_resume(struct device *dev);`
     - execute the subsystem-level resume callback for the device; returns 0 on
-      success, 1 if the device's runtime PM status was already 'active' or
-      error code on failure, where -EAGAIN means it may be safe to attempt to
-      resume the device again in future, but 'power.runtime_error' should be
-      checked additionally, and -EACCES means that 'power.disable_depth' is
+      success, 1 if the device's runtime PM status is already 'active' (also if
+      'power.disable_depth' is nonzero, but the status was 'active' when it was
+      changing from 0 to 1) or error code on failure, where -EAGAIN means it may
+      be safe to attempt to resume the device again in future, but
+      'power.runtime_error' should be checked additionally, and -EACCES means
+      that the callback could not be run, because 'power.disable_depth' was
       different from 0
 
   `int pm_runtime_resume_and_get(struct device *dev);`

arch/x86/kernel/acpi/sleep.c

@@ -139,8 +139,10 @@ static int __init acpi_sleep_setup(char *str)
 		if (strncmp(str, "s3_beep", 7) == 0)
 			acpi_realmode_flags |= 4;
 #ifdef CONFIG_HIBERNATION
+		if (strncmp(str, "s4_hwsig", 8) == 0)
+			acpi_check_s4_hw_signature(1);
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
-			acpi_no_s4_hw_signature();
+			acpi_check_s4_hw_signature(0);
 #endif
 		if (strncmp(str, "nonvs", 5) == 0)
 			acpi_nvs_nosave();

drivers/acpi/sleep.c

@@ -877,11 +877,11 @@ static inline void acpi_sleep_syscore_init(void) {}
 #ifdef CONFIG_HIBERNATION
 static unsigned long s4_hardware_signature;
 static struct acpi_table_facs *facs;
-static bool nosigcheck;
+static int sigcheck = -1; /* Default behaviour is just to warn */
 
-void __init acpi_no_s4_hw_signature(void)
+void __init acpi_check_s4_hw_signature(int check)
 {
-	nosigcheck = true;
+	sigcheck = check;
 }
 
 static int acpi_hibernation_begin(pm_message_t stage)
@@ -1009,12 +1009,28 @@ static void acpi_sleep_hibernate_setup(void)
 	hibernation_set_ops(old_suspend_ordering ?
 			&acpi_hibernation_ops_old : &acpi_hibernation_ops);
 	sleep_states[ACPI_STATE_S4] = 1;
-	if (nosigcheck)
+	if (!sigcheck)
 		return;
 
 	acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs);
-	if (facs)
+	if (facs) {
+		/*
+		 * s4_hardware_signature is the local variable which is just
+		 * used to warn about mismatch after we're attempting to
+		 * resume (in violation of the ACPI specification.)
+		 */
 		s4_hardware_signature = facs->hardware_signature;
+
+		if (sigcheck > 0) {
+			/*
+			 * If we're actually obeying the ACPI specification
+			 * then the signature is written out as part of the
+			 * swsusp header, in order to allow the boot kernel
+			 * to gracefully decline to resume.
+			 */
+			swsusp_hardware_signature = facs->hardware_signature;
+		}
+	}
 }
 #else /* !CONFIG_HIBERNATION */
 static inline void acpi_sleep_hibernate_setup(void) {}

drivers/base/core.c

@@ -485,8 +485,7 @@ static void device_link_release_fn(struct work_struct *work)
 	/* Ensure that all references to the link object have been dropped. */
 	device_link_synchronize_removal();
 
-	while (refcount_dec_not_one(&link->rpm_active))
-		pm_runtime_put(link->supplier);
+	pm_runtime_release_supplier(link, true);
 
 	put_device(link->consumer);
 	put_device(link->supplier);

drivers/base/power/runtime.c

@@ -305,19 +305,40 @@ static int rpm_get_suppliers(struct device *dev)
 	return 0;
 }
 
+/**
+ * pm_runtime_release_supplier - Drop references to device link's supplier.
+ * @link: Target device link.
+ * @check_idle: Whether or not to check if the supplier device is idle.
+ *
+ * Drop all runtime PM references associated with @link to its supplier device
+ * and if @check_idle is set, check if that device is idle (and so it can be
+ * suspended).
+ */
+void pm_runtime_release_supplier(struct device_link *link, bool check_idle)
+{
+	struct device *supplier = link->supplier;
+
+	/*
+	 * The additional power.usage_count check is a safety net in case
+	 * the rpm_active refcount becomes saturated, in which case
+	 * refcount_dec_not_one() would return true forever, but it is not
+	 * strictly necessary.
+	 */
+	while (refcount_dec_not_one(&link->rpm_active) &&
+	       atomic_read(&supplier->power.usage_count) > 0)
+		pm_runtime_put_noidle(supplier);
+
+	if (check_idle)
+		pm_request_idle(supplier);
+}
+
 static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
 {
 	struct device_link *link;
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
-				device_links_read_lock_held()) {
-
-		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put_noidle(link->supplier);
-
-		if (try_to_suspend)
-			pm_request_idle(link->supplier);
-	}
+				device_links_read_lock_held())
+		pm_runtime_release_supplier(link, try_to_suspend);
 }
 
 static void rpm_put_suppliers(struct device *dev)
@@ -742,13 +763,15 @@ static int rpm_resume(struct device *dev, int rpmflags)
 	trace_rpm_resume_rcuidle(dev, rpmflags);
 
  repeat:
-	if (dev->power.runtime_error)
+	if (dev->power.runtime_error) {
 		retval = -EINVAL;
-	else if (dev->power.disable_depth == 1 && dev->power.is_suspended
-	    && dev->power.runtime_status == RPM_ACTIVE)
-		retval = 1;
-	else if (dev->power.disable_depth > 0)
-		retval = -EACCES;
+	} else if (dev->power.disable_depth > 0) {
+		if (dev->power.runtime_status == RPM_ACTIVE &&
+		    dev->power.last_status == RPM_ACTIVE)
+			retval = 1;
+		else
+			retval = -EACCES;
+	}
 	if (retval)
 		goto out;
 
@@ -1410,8 +1433,10 @@ void __pm_runtime_disable(struct device *dev, bool check_resume)
 	/* Update time accounting before disabling PM-runtime. */
 	update_pm_runtime_accounting(dev);
 
-	if (!dev->power.disable_depth++)
+	if (!dev->power.disable_depth++) {
 		__pm_runtime_barrier(dev);
+		dev->power.last_status = dev->power.runtime_status;
+	}
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1428,23 +1453,23 @@ void pm_runtime_enable(struct device *dev)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	if (dev->power.disable_depth > 0) {
-		dev->power.disable_depth--;
-
-		/* About to enable runtime pm, set accounting_timestamp to now */
-		if (!dev->power.disable_depth)
-			dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
-	} else {
+	if (!dev->power.disable_depth) {
 		dev_warn(dev, "Unbalanced %s!\n", __func__);
+		goto out;
 	}
 
-	WARN(!dev->power.disable_depth &&
-	     dev->power.runtime_status == RPM_SUSPENDED &&
-	     !dev->power.ignore_children &&
-	     atomic_read(&dev->power.child_count) > 0,
-	     "Enabling runtime PM for inactive device (%s) with active children\n",
-	     dev_name(dev));
+	if (--dev->power.disable_depth > 0)
+		goto out;
+
+	dev->power.last_status = RPM_INVALID;
+	dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
+
+	if (dev->power.runtime_status == RPM_SUSPENDED &&
+	    !dev->power.ignore_children &&
+	    atomic_read(&dev->power.child_count) > 0)
+		dev_warn(dev, "Enabling runtime PM for inactive device with active children\n");
 
+out:
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 }
 EXPORT_SYMBOL_GPL(pm_runtime_enable);
@@ -1640,6 +1665,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);
 void pm_runtime_init(struct device *dev)
 {
 	dev->power.runtime_status = RPM_SUSPENDED;
+	dev->power.last_status = RPM_INVALID;
 	dev->power.idle_notification = false;
 
 	dev->power.disable_depth = 1;
@@ -1722,20 +1748,24 @@ 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();
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
 				device_links_read_lock_held())
 		if (link->supplier_preactivated) {
+			bool put;
+
 			link->supplier_preactivated = false;
-			spin_lock_irqsave(&dev->power.lock, flags);
+
+			spin_lock_irq(&dev->power.lock);
+
 			put = pm_runtime_status_suspended(dev) &&
 			      refcount_dec_not_one(&link->rpm_active);
-			spin_unlock_irqrestore(&dev->power.lock, flags);
+
+			spin_unlock_irq(&dev->power.lock);
+
 			if (put)
 				pm_runtime_put(link->supplier);
 		}
@@ -1772,9 +1802,7 @@ void pm_runtime_drop_link(struct device_link *link)
 		return;
 
 	pm_runtime_drop_link_count(link->consumer);
-
-	while (refcount_dec_not_one(&link->rpm_active))
-		pm_runtime_put(link->supplier);
+	pm_runtime_release_supplier(link, true);
 }
 
 static bool pm_runtime_need_not_resume(struct device *dev)

drivers/cpuidle/governors/menu.c

@@ -34,7 +34,7 @@
  * 1) Energy break even point
  * 2) Performance impact
  * 3) Latency tolerance (from pmqos infrastructure)
- * These these three factors are treated independently.
+ * These three factors are treated independently.
  *
  * Energy break even point
  * -----------------------

drivers/cpuidle/sysfs.c

@@ -335,6 +335,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_default_status.attr,
 	NULL
 };
+ATTRIBUTE_GROUPS(cpuidle_state_default);
 
 struct cpuidle_state_kobj {
 	struct cpuidle_state *state;
@@ -448,7 +449,7 @@ static void cpuidle_state_sysfs_release(struct kobject *kobj)
 
 static struct kobj_type ktype_state_cpuidle = {
 	.sysfs_ops = &cpuidle_state_sysfs_ops,
-	.default_attrs = cpuidle_state_default_attrs,
+	.default_groups = cpuidle_state_default_groups,
 	.release = cpuidle_state_sysfs_release,
 };
 
@@ -505,7 +506,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 }
 
 /**
- * cpuidle_remove_driver_sysfs - removes the cpuidle states sysfs attributes
+ * cpuidle_remove_state_sysfs - removes the cpuidle states sysfs attributes
  * @device: the target device
  */
 static void cpuidle_remove_state_sysfs(struct cpuidle_device *device)
@@ -591,10 +592,11 @@ static struct attribute *cpuidle_driver_default_attrs[] = {
 	&attr_driver_name.attr,
 	NULL
 };
+ATTRIBUTE_GROUPS(cpuidle_driver_default);
 
 static struct kobj_type ktype_driver_cpuidle = {
 	.sysfs_ops = &cpuidle_driver_sysfs_ops,
-	.default_attrs = cpuidle_driver_default_attrs,
+	.default_groups = cpuidle_driver_default_groups,
 	.release = cpuidle_driver_sysfs_release,
 };
 

drivers/mmc/host/jz4740_mmc.c

@@ -1103,17 +1103,17 @@ static int jz4740_mmc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int __maybe_unused jz4740_mmc_suspend(struct device *dev)
+static int jz4740_mmc_suspend(struct device *dev)
 {
 	return pinctrl_pm_select_sleep_state(dev);
 }
 
-static int __maybe_unused jz4740_mmc_resume(struct device *dev)
+static int jz4740_mmc_resume(struct device *dev)
 {
 	return pinctrl_select_default_state(dev);
 }
 
-static SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend,
+DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend,
 	jz4740_mmc_resume);
 
 static struct platform_driver jz4740_mmc_driver = {
@@ -1123,7 +1123,7 @@ static struct platform_driver jz4740_mmc_driver = {
 		.name = "jz4740-mmc",
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 		.of_match_table = of_match_ptr(jz4740_mmc_of_match),
-		.pm = pm_ptr(&jz4740_mmc_pm_ops),
+		.pm = pm_sleep_ptr(&jz4740_mmc_pm_ops),
 	},
 };
 

drivers/mmc/host/mxcmmc.c

@@ -1183,7 +1183,6 @@ static int mxcmci_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int mxcmci_suspend(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
@@ -1210,17 +1209,16 @@ static int mxcmci_resume(struct device *dev)
 
 	return ret;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume);
+DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume);
 
 static struct platform_driver mxcmci_driver = {
 	.probe		= mxcmci_probe,
 	.remove		= mxcmci_remove,
 	.driver		= {
 		.name		= DRIVER_NAME,
 		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
-		.pm	= &mxcmci_pm_ops,
+		.pm	= pm_sleep_ptr(&mxcmci_pm_ops),
 		.of_match_table	= mxcmci_of_match,
 	}
 };