Merge branches 'pm-sleep', 'pm-domains' and 'pm-docs'

Merge changes related to system sleep, PM domains changes and power
management documentation changes for 5.18-rc1:

- Fix load_image_and_restore() error path (Ye Bin).

- Fix typos in comments in the system wakeup hadling code (Tom Rix).

- Clean up non-kernel-doc comments in hibernation code (Jiapeng
Chong).

- Fix __setup handler error handling in system-wide suspend and
hibernation core code (Randy Dunlap).

- Add device name to suspend_report_result() (Youngjin Jang).

- Make virtual guests honour ACPI S4 hardware signature by
default (David Woodhouse).

- Block power off of a parent PM domain unless child is in deepest
state (Ulf Hansson).

- Use dev_err_probe() to simplify error handling for generic PM
domains (Ahmad Fatoum).

- Fix sleep-in-atomic bug caused by genpd_debug_remove() (Shawn Guo).

- Document Intel uncore frequency scaling (Srinivas Pandruvada).

* pm-sleep:
PM: hibernate: Honour ACPI hardware signature by default for virtual guests
PM: sleep: Add device name to suspend_report_result()
PM: suspend: fix return value of __setup handler
PM: hibernate: fix __setup handler error handling
PM: hibernate: Clean up non-kernel-doc comments
PM: sleep: wakeup: Fix typos in comments
PM: hibernate: fix load_image_and_restore() error path

* pm-domains:
PM: domains: Fix sleep-in-atomic bug caused by genpd_debug_remove()
PM: domains: use dev_err_probe() to simplify error handling
PM: domains: Prevent power off for parent unless child is in deepest state

* pm-docs:
Documentation: admin-guide: pm: Document uncore frequency scaling

Documentation/admin-guide/pm/intel_uncore_frequency_scaling.rst

···
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+==============================
+Intel Uncore Frequency Scaling
+==============================
+
+:Copyright: |copy| 2022 Intel Corporation
+
+:Author: Srinivas Pandruvada <[e-mail]>
+
+Introduction
+------------
+
+The uncore can consume significant amount of power in Intel's Xeon servers based
+on the workload characteristics. To optimize the total power and improve overall
+performance, SoCs have internal algorithms for scaling uncore frequency. These
+algorithms monitor workload usage of uncore and set a desirable frequency.
+
+It is possible that users have different expectations of uncore performance and
+want to have control over it. The objective is similar to allowing users to set
+the scaling min/max frequencies via cpufreq sysfs to improve CPU performance.
+Users may have some latency sensitive workloads where they do not want any
+change to uncore frequency. Also, users may have workloads which require
+different core and uncore performance at distinct phases and they may want to
+use both cpufreq and the uncore scaling interface to distribute power and
+improve overall performance.
+
+Sysfs Interface
+---------------
+
+To control uncore frequency, a sysfs interface is provided in the directory:
+`/sys/devices/system/cpu/intel_uncore_frequency/`.
+
+There is one directory for each package and die combination as the scope of
+uncore scaling control is per die in multiple die/package SoCs or per
+package for single die per package SoCs. The name represents the
+scope of control. For example: 'package_00_die_00' is for package id 0 and
+die 0.
+
+Each package_*_die_* contains the following attributes:
+
+``initial_max_freq_khz``
+	Out of reset, this attribute represent the maximum possible frequency.
+	This is a read-only attribute. If users adjust max_freq_khz,
+	they can always go back to maximum using the value from this attribute.
+
+``initial_min_freq_khz``
+	Out of reset, this attribute represent the minimum possible frequency.
+	This is a read-only attribute. If users adjust min_freq_khz,
+	they can always go back to minimum using the value from this attribute.
+
+``max_freq_khz``
+	This attribute is used to set the maximum uncore frequency.
+
+``min_freq_khz``
+	This attribute is used to set the minimum uncore frequency.
+
+``current_freq_khz``
+	This attribute is used to get the current uncore frequency.

Documentation/admin-guide/pm/working-state.rst

···
    cpufreq_drivers
    intel_epb
    intel-speed-select
+   intel_uncore_frequency_scaling

arch/x86/kernel/acpi/sleep.c

···
 #include <asm/desc.h>
 #include <asm/cacheflush.h>
 #include <asm/realmode.h>
+#include <asm/hypervisor.h>
 
 #include <linux/ftrace.h>
 #include "../../realmode/rm/wakeup.h"
···
 			acpi_realmode_flags |= 4;
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_hwsig", 8) == 0)
-			acpi_check_s4_hw_signature(1);
+			acpi_check_s4_hw_signature = 1;
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
-			acpi_check_s4_hw_signature(0);
+			acpi_check_s4_hw_signature = 0;
 #endif
 		if (strncmp(str, "nonvs", 5) == 0)
 			acpi_nvs_nosave();
···
 }
 
 __setup("acpi_sleep=", acpi_sleep_setup);
+
+#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HYPERVISOR_GUEST)
+static int __init init_s4_sigcheck(void)
+{
+	/*
+	 * If running on a hypervisor, honour the ACPI specification
+	 * by default and trigger a clean reboot when the hardware
+	 * signature in FACS is changed after hibernation.
+	 */
+	if (acpi_check_s4_hw_signature == -1 &&
+	    !hypervisor_is_type(X86_HYPER_NATIVE))
+		acpi_check_s4_hw_signature = 1;
+
+	return 0;
+}
+/* This must happen before acpi_init() which is a subsys initcall */
+arch_initcall(init_s4_sigcheck);
+#endif

drivers/acpi/sleep.c

···
 #ifdef CONFIG_HIBERNATION
 static unsigned long s4_hardware_signature;
 static struct acpi_table_facs *facs;
-static int sigcheck = -1; /* Default behaviour is just to warn */
-
-void __init acpi_check_s4_hw_signature(int check)
-{
-	sigcheck = check;
-}
+int acpi_check_s4_hw_signature = -1; /* Default behaviour is just to warn */
 
 static int acpi_hibernation_begin(pm_message_t stage)
 {
···
 	hibernation_set_ops(old_suspend_ordering ?
 			&acpi_hibernation_ops_old : &acpi_hibernation_ops);
 	sleep_states[ACPI_STATE_S4] = 1;
-	if (!sigcheck)
+	if (!acpi_check_s4_hw_signature)
 		return;
 
 	acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs);
···
 		 */
 		s4_hardware_signature = facs->hardware_signature;
 
-		if (sigcheck > 0) {
+		if (acpi_check_s4_hw_signature > 0) {
 			/*
 			 * If we're actually obeying the ACPI specification
 			 * then the signature is written out as part of the

drivers/base/power/domain.c

···
 			atomic_read(&genpd->sd_count) > 0)
 		return -EBUSY;
 
+	/*
+	 * The children must be in their deepest (powered-off) states to allow
+	 * the parent to be powered off. Note that, there's no need for
+	 * additional locking, as powering on a child, requires the parent's
+	 * lock to be acquired first.
+	 */
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		struct generic_pm_domain *child = link->child;
+		if (child->state_idx < child->state_count - 1)
+			return -EBUSY;
+	}
+
 	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
 		enum pm_qos_flags_status stat;
 
···
 	if (genpd->suspended_count != genpd->device_count
 	    || atomic_read(&genpd->sd_count) > 0)
 		return;
+
+	/* Check that the children are in their deepest (powered-off) state. */
+	list_for_each_entry(link, &genpd->parent_links, parent_node) {
+		struct generic_pm_domain *child = link->child;
+		if (child->state_idx < child->state_count - 1)
+			return;
+	}
 
 	/* Choose the deepest state when suspending */
 	genpd->state_idx = genpd->state_count - 1;
···
 		kfree(link);
 	}
 
-	genpd_debug_remove(genpd);
 	list_del(&genpd->gpd_list_node);
 	genpd_unlock(genpd);
+	genpd_debug_remove(genpd);
 	cancel_work_sync(&genpd->power_off_work);
 	if (genpd_is_cpu_domain(genpd))
 		free_cpumask_var(genpd->cpus);
···
 	/* Parse genpd OPP table */
 	if (genpd->set_performance_state) {
 		ret = dev_pm_opp_of_add_table(&genpd->dev);
-		if (ret) {
-			if (ret != -EPROBE_DEFER)
-				dev_err(&genpd->dev, "Failed to add OPP table: %d\n",
-					ret);
-			return ret;
-		}
+		if (ret)
+			return dev_err_probe(&genpd->dev, ret, "Failed to add OPP table\n");
 
 		/*
 		 * Save table for faster processing while setting performance
···
 		if (genpd->set_performance_state) {
 			ret = dev_pm_opp_of_add_table_indexed(&genpd->dev, i);
 			if (ret) {
-				if (ret != -EPROBE_DEFER)
-					dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n",
-						i, ret);
+				dev_err_probe(&genpd->dev, ret,
+					      "Failed to add OPP table for index %d\n", i);
 				goto error;
 			}
 
···
 	ret = genpd_add_device(pd, dev, base_dev);
 	mutex_unlock(&gpd_list_lock);
 
-	if (ret < 0) {
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "failed to add to PM domain %s: %d",
-				pd->name, ret);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "failed to add to PM domain %s\n", pd->name);
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;

drivers/base/power/main.c

···
 	trace_device_pm_callback_start(dev, info, state.event);
 	error = cb(dev);
 	trace_device_pm_callback_end(dev, error);
-	suspend_report_result(cb, error);
+	suspend_report_result(dev, cb, error);
 
 	initcall_debug_report(dev, calltime, cb, error);
 
···
 	trace_device_pm_callback_start(dev, info, state.event);
 	error = cb(dev, state);
 	trace_device_pm_callback_end(dev, error);
-	suspend_report_result(cb, error);
+	suspend_report_result(dev, cb, error);
 
 	initcall_debug_report(dev, calltime, cb, error);
 
···
 	device_unlock(dev);
 
 	if (ret < 0) {
-		suspend_report_result(callback, ret);
+		suspend_report_result(dev, callback, ret);
 		pm_runtime_put(dev);
 		return ret;
 	}
···
 }
 EXPORT_SYMBOL_GPL(dpm_suspend_start);
 
-void __suspend_report_result(const char *function, void *fn, int ret)
+void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret)
 {
 	if (ret)
-		pr_err("%s(): %pS returns %d\n", function, fn, ret);
+		dev_err(dev, "%s(): %pS returns %d\n", function, fn, ret);
 }
 EXPORT_SYMBOL_GPL(__suspend_report_result);
 

drivers/base/power/wakeirq.c

···
  *
  * Enables wakeirq conditionally. We need to enable wake-up interrupt
  * lazily on the first rpm_suspend(). This is needed as the consumer device
- * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would
+ * starts in RPM_SUSPENDED state, and the first pm_runtime_get() would
  * otherwise try to disable already disabled wakeirq. The wake-up interrupt
  * starts disabled with IRQ_NOAUTOEN set.
  *

drivers/base/power/wakeup.c

···
  * @ws: Wakeup source to handle.
  *
  * Update the @ws' statistics and, if @ws has just been activated, notify the PM
- * core of the event by incrementing the counter of of wakeup events being
+ * core of the event by incrementing the counter of the wakeup events being
  * processed.
  */
 static void wakeup_source_activate(struct wakeup_source *ws)
···
 
 	/*
 	 * Increment the counter of registered wakeup events and decrement the
-	 * couter of wakeup events in progress simultaneously.
+	 * counter of wakeup events in progress simultaneously.
 	 */
 	cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count);
 	trace_wakeup_source_deactivate(ws->name, cec);

drivers/pci/pci-driver.c

···
 		int error;
 
 		error = drv->suspend(pci_dev, state);
-		suspend_report_result(drv->suspend, error);
+		suspend_report_result(dev, drv->suspend, error);
 		if (error)
 			return error;
 
···
 		int error;
 
 		error = pm->suspend(dev);
-		suspend_report_result(pm->suspend, error);
+		suspend_report_result(dev, pm->suspend, error);
 		if (error)
 			return error;
 
···
 		int error;
 
 		error = pm->suspend_noirq(dev);
-		suspend_report_result(pm->suspend_noirq, error);
+		suspend_report_result(dev, pm->suspend_noirq, error);
 		if (error)
 			return error;
 
···
 		int error;
 
 		error = pm->freeze(dev);
-		suspend_report_result(pm->freeze, error);
+		suspend_report_result(dev, pm->freeze, error);
 		if (error)
 			return error;
 	}
···
 		int error;
 
 		error = pm->freeze_noirq(dev);
-		suspend_report_result(pm->freeze_noirq, error);
+		suspend_report_result(dev, pm->freeze_noirq, error);
 		if (error)
 			return error;
 	}
···
 		int error;
 
 		error = pm->poweroff(dev);
-		suspend_report_result(pm->poweroff, error);
+		suspend_report_result(dev, pm->poweroff, error);
 		if (error)
 			return error;
 	}
···
 		int error;
 
 		error = pm->poweroff_noirq(dev);
-		suspend_report_result(pm->poweroff_noirq, error);
+		suspend_report_result(dev, pm->poweroff_noirq, error);
 		if (error)
 			return error;
 	}

drivers/pnp/driver.c

···
 
 	if (pnp_drv->driver.pm && pnp_drv->driver.pm->suspend) {
 		error = pnp_drv->driver.pm->suspend(dev);
-		suspend_report_result(pnp_drv->driver.pm->suspend, error);
+		suspend_report_result(dev, pnp_drv->driver.pm->suspend, error);
 		if (error)
 			return error;
 	}

drivers/usb/core/hcd-pci.c

···
 				HCD_WAKEUP_PENDING(hcd->shared_hcd))
 			return -EBUSY;
 		retval = hcd->driver->pci_suspend(hcd, do_wakeup);
-		suspend_report_result(hcd->driver->pci_suspend, retval);
+		suspend_report_result(dev, hcd->driver->pci_suspend, retval);
 
 		/* Check again in case wakeup raced with pci_suspend */
 		if ((retval == 0 && do_wakeup && HCD_WAKEUP_PENDING(hcd)) ||
···
 		dev_dbg(dev, "--> PCI %s\n",
 				pci_power_name(pci_dev->current_state));
 	} else {
-		suspend_report_result(pci_prepare_to_sleep, retval);
+		suspend_report_result(dev, pci_prepare_to_sleep, retval);
 		return retval;
 	}
 

include/linux/acpi.h

···
 int acpi_resources_are_enforced(void);
 
 #ifdef CONFIG_HIBERNATION
-void __init acpi_check_s4_hw_signature(int check);
+extern int acpi_check_s4_hw_signature;
 #endif
 
 #ifdef CONFIG_PM_SLEEP

include/linux/pm.h

···
 extern int dpm_suspend(pm_message_t state);
 extern int dpm_prepare(pm_message_t state);
 
-extern void __suspend_report_result(const char *function, void *fn, int ret);
+extern void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret);
 
-#define suspend_report_result(fn, ret)					\
+#define suspend_report_result(dev, fn, ret)				\
 	do {								\
-		__suspend_report_result(__func__, fn, ret);		\
+		__suspend_report_result(__func__, dev, fn, ret);	\
 	} while (0)
 
 extern int device_pm_wait_for_dev(struct device *sub, struct device *dev);
···
 	return 0;
 }
 
-#define suspend_report_result(fn, ret)		do {} while (0)
+#define suspend_report_result(dev, fn, ret)	do {} while (0)
 
 static inline int device_pm_wait_for_dev(struct device *a, struct device *b)
 {

kernel/power/hibernate.c

···
 
 	lock_device_hotplug();
 	error = create_basic_memory_bitmaps();
-	if (error)
+	if (error) {
+		swsusp_close(FMODE_READ | FMODE_EXCL);
 		goto Unlock;
+	}
 
 	error = swsusp_read(&flags);
 	swsusp_close(FMODE_READ | FMODE_EXCL);
···
 	int rc = kstrtouint(str, 0, &resume_delay);
 
 	if (rc)
-		return rc;
+		pr_warn("resumedelay: bad option string '%s'\n", str);
 	return 1;
 }
 

kernel/power/suspend_test.c

···
 	value++;
 	suspend_type = strsep(&value, ",");
 	if (!suspend_type)
-		return 0;
+		return 1;
 
 	repeat = strsep(&value, ",");
 	if (repeat) {
 		if (kstrtou32(repeat, 0, &test_repeat_count_max))
-			return 0;
+			return 1;
 	}
 
 	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
 		if (!strcmp(pm_labels[i], suspend_type)) {
 			test_state_label = pm_labels[i];
-			return 0;
+			return 1;
 		}
 
 	printk(warn_bad_state, suspend_type);
-	return 0;
+	return 1;
 }
 __setup("test_suspend", setup_test_suspend);
 

kernel/power/swap.c

···
 	struct swap_map_page_list *next;
 };
 
-/**
+/*
  *	The swap_map_handle structure is used for handling swap in
  *	a file-alike way
  */
···
 
 static struct swsusp_header *swsusp_header;
 
-/**
+/*
  *	The following functions are used for tracing the allocated
  *	swap pages, so that they can be freed in case of an error.
  */
···
 	return 0;
 }
 
-/**
+/*
  *	alloc_swapdev_block - allocate a swap page and register that it has
  *	been allocated, so that it can be freed in case of an error.
  */
···
 	return 0;
 }
 
-/**
+/*
  *	free_all_swap_pages - free swap pages allocated for saving image data.
  *	It also frees the extents used to register which swap entries had been
  *	allocated.