Resguardo inicial

linux-7.2.3/kernel/power/Kconfig

@@ -0,0 +1,404 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SUSPEND
+	bool "Suspend to RAM and standby"
+	depends on ARCH_SUSPEND_POSSIBLE
+	default y
+	help
+	  Allow the system to enter sleep states in which main memory is
+	  powered and thus its contents are preserved, such as the
+	  suspend-to-RAM state (e.g. the ACPI S3 state).
+
+config SUSPEND_FREEZER
+	bool "Enable freezer for suspend to RAM/standby" \
+		if ARCH_WANTS_FREEZER_CONTROL || BROKEN
+	depends on SUSPEND
+	default y
+	help
+	  This allows you to turn off the freezer for suspend. If this is
+	  done, no tasks are frozen for suspend to RAM/standby.
+
+	  Turning OFF this setting is NOT recommended! If in doubt, say Y.
+
+config SUSPEND_SKIP_SYNC
+	bool "Skip kernel's sys_sync() on suspend to RAM/standby"
+	depends on SUSPEND
+	depends on EXPERT
+	help
+	  Skip the kernel sys_sync() before freezing user processes.
+	  Some systems prefer not to pay this cost on every invocation
+	  of suspend, or they are content with invoking sync() from
+	  user-space before invoking suspend.  There's a run-time switch
+	  at '/sys/power/sync_on_suspend' to configure this behaviour.
+	  This setting changes the default for the run-tim switch. Say Y
+	  to change the default to disable the kernel sys_sync().
+
+config HIBERNATE_CALLBACKS
+	bool
+
+config HIBERNATION
+	bool "Hibernation (aka 'suspend to disk')"
+	depends on SWAP && ARCH_HIBERNATION_POSSIBLE
+	select HIBERNATE_CALLBACKS
+	select CRC32
+	select CRYPTO
+	select CRYPTO_LZO
+	select CRYPTO_LZ4
+	help
+	  Enable the suspend to disk (STD) functionality, which is usually
+	  called "hibernation" in user interfaces.  STD checkpoints the
+	  system and powers it off; and restores that checkpoint on reboot.
+
+	  You can suspend your machine with 'echo disk > /sys/power/state'
+	  after placing resume=/dev/swappartition on the kernel command line
+	  in your bootloader's configuration file.
+
+	  Alternatively, you can use the additional userland tools available
+	  from <http://suspend.sf.net>.
+
+	  In principle it does not require ACPI or APM, although for example
+	  ACPI will be used for the final steps when it is available.  One
+	  of the reasons to use software suspend is that the firmware hooks
+	  for suspend states like suspend-to-RAM (STR) often don't work very
+	  well with Linux.
+
+	  It creates an image which is saved in your active swap. Upon the next
+	  boot, pass the 'resume=/dev/swappartition' argument to the kernel to
+	  have it detect the saved image, restore memory state from it, and
+	  continue to run as before. If you do not want the previous state to
+	  be reloaded, then use the 'noresume' kernel command line argument.
+	  Note, however, that fsck will be run on your filesystems and you will
+	  need to run mkswap against the swap partition used for the suspend.
+
+	  It also works with swap files to a limited extent (for details see
+	  <file:Documentation/power/swsusp-and-swap-files.rst>).
+
+	  Right now you may boot without resuming and resume later but in the
+	  meantime you cannot use the swap partition(s)/file(s) involved in
+	  suspending.  Also in this case you must not use the filesystems
+	  that were mounted before the suspend.  In particular, you MUST NOT
+	  MOUNT any journaled filesystems mounted before the suspend or they
+	  will get corrupted in a nasty way.
+
+	  For more information take a look at <file:Documentation/power/swsusp.rst>.
+
+config HIBERNATION_SNAPSHOT_DEV
+	bool "Userspace snapshot device"
+	depends on HIBERNATION
+	default y
+	help
+	  Device used by the uswsusp tools.
+
+	  Say N if no snapshotting from userspace is needed, this also
+	  reduces the attack surface of the kernel.
+
+	  If in doubt, say Y.
+
+choice
+	prompt "Default compressor"
+	default HIBERNATION_COMP_LZO
+	depends on HIBERNATION
+
+config HIBERNATION_COMP_LZO
+	bool "lzo"
+	depends on CRYPTO_LZO
+
+config HIBERNATION_COMP_LZ4
+	bool "lz4"
+	depends on CRYPTO_LZ4
+
+endchoice
+
+config HIBERNATION_DEF_COMP
+	string
+	default "lzo" if HIBERNATION_COMP_LZO
+	default "lz4" if HIBERNATION_COMP_LZ4
+	help
+	  Default compressor to be used for hibernation.
+
+config PM_STD_PARTITION
+	string "Default resume partition"
+	depends on HIBERNATION
+	default ""
+	help
+	  The default resume partition is the partition that the suspend-
+	  to-disk implementation will look for a suspended disk image.
+
+	  The partition specified here will be different for almost every user.
+	  It should be a valid swap partition (at least for now) that is turned
+	  on before suspending.
+
+	  The partition specified can be overridden by specifying:
+
+		resume=/dev/<other device>
+
+	  which will set the resume partition to the device specified.
+
+	  Note there is currently not a way to specify which device to save the
+	  suspended image to. It will simply pick the first available swap
+	  device.
+
+config PM_SLEEP
+	def_bool y
+	depends on SUSPEND || HIBERNATE_CALLBACKS
+	select PM
+
+config PM_SLEEP_SMP
+	def_bool y
+	depends on SMP
+	depends on ARCH_SUSPEND_POSSIBLE || ARCH_HIBERNATION_POSSIBLE
+	depends on PM_SLEEP
+	select HOTPLUG_CPU
+
+config PM_SLEEP_SMP_NONZERO_CPU
+	def_bool y
+	depends on PM_SLEEP_SMP
+	depends on ARCH_SUSPEND_NONZERO_CPU
+	help
+	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+	will allow nohz_full mask to include CPU0.
+
+config PM_AUTOSLEEP
+	bool "Opportunistic sleep"
+	depends on PM_SLEEP
+	help
+	Allow the kernel to trigger a system transition into a global sleep
+	state automatically whenever there are no active wakeup sources.
+
+config PM_USERSPACE_AUTOSLEEP
+	bool "Userspace opportunistic sleep"
+	depends on PM_SLEEP
+	help
+	Notify kernel of aggressive userspace autosleep power management policy.
+
+	This option changes the behavior of various sleep-sensitive code to deal
+	with frequent userspace-initiated transitions into a global sleep state.
+
+	Saying Y here, disables code paths that most users really should keep
+	enabled. In particular, only enable this if it is very common to be
+	asleep/awake for very short periods of time (<= 2 seconds).
+
+	Only platforms, such as Android, that implement opportunistic sleep from
+	a userspace power manager service should enable this option; and not
+	other machines. Therefore, you should say N here, unless you are
+	extremely certain that this is what you want. The option otherwise has
+	bad, undesirable effects, and should not be enabled just for fun.
+
+
+config PM_WAKELOCKS
+	bool "User space wakeup sources interface"
+	depends on PM_SLEEP
+	help
+	Allow user space to create, activate and deactivate wakeup source
+	objects with the help of a sysfs-based interface.
+
+config PM_WAKELOCKS_LIMIT
+	int "Maximum number of user space wakeup sources (0 = no limit)"
+	range 0 100000
+	default 100
+	depends on PM_WAKELOCKS
+
+config PM_WAKELOCKS_GC
+	bool "Garbage collector for user space wakeup sources"
+	depends on PM_WAKELOCKS
+	default y
+
+config PM_QOS_CPU_SYSTEM_WAKEUP
+	bool "User space interface for CPU system wakeup QoS"
+	depends on CPU_IDLE
+	help
+	  Enable this to allow user space via the cpu_wakeup_latency file to
+	  specify a CPU system wakeup latency limit.
+
+	  This may be particularly useful for platforms supporting multiple low
+	  power states for CPUs during system-wide suspend and s2idle in
+	  particular.
+
+config PM
+	bool "Device power management core functionality"
+	help
+	  Enable functionality allowing I/O devices to be put into energy-saving
+	  (low power) states, for example after a specified period of inactivity
+	  (autosuspended), and woken up in response to a hardware-generated
+	  wake-up event or a driver's request.
+
+	  Hardware support is generally required for this functionality to work
+	  and the bus type drivers of the buses the devices are on are
+	  responsible for the actual handling of device suspend requests and
+	  wake-up events.
+
+config PM_DEBUG
+	bool "Power Management Debug Support"
+	depends on PM
+	help
+	This option enables various debugging support in the Power Management
+	code. This is helpful when debugging and reporting PM bugs, like
+	suspend support.
+
+config PM_ADVANCED_DEBUG
+	bool "Extra PM attributes in sysfs for low-level debugging/testing"
+	depends on PM_DEBUG
+	help
+	Add extra sysfs attributes allowing one to access some Power Management
+	fields of device objects from user space.  If you are not a kernel
+	developer interested in debugging/testing Power Management, say "no".
+
+config PM_TEST_SUSPEND
+	bool "Test suspend/resume and wakealarm during bootup"
+	depends on SUSPEND && PM_DEBUG && RTC_CLASS=y
+	help
+	This option will let you suspend your machine during bootup, and
+	make it wake up a few seconds later using an RTC wakeup alarm.
+	Enable this with a kernel parameter like "test_suspend=mem".
+
+	You probably want to have your system's RTC driver statically
+	linked, ensuring that it's available when this test runs.
+
+config PM_SLEEP_DEBUG
+	def_bool y
+	depends on PM_DEBUG && PM_SLEEP
+
+config DPM_WATCHDOG
+	bool "Device suspend/resume watchdog"
+	depends on PM_DEBUG && PSTORE && EXPERT
+	help
+	  Sets up a watchdog timer to capture drivers that are
+	  locked up attempting to suspend/resume a device.
+	  A detected lockup causes system panic with message
+	  captured in pstore device for inspection in subsequent
+	  boot session.
+
+config DPM_WATCHDOG_TIMEOUT
+	int "Watchdog timeout to panic in seconds"
+	range 1 120
+	default 120
+	depends on DPM_WATCHDOG
+
+config DPM_WATCHDOG_WARNING_TIMEOUT
+	int "Watchdog timeout to warn in seconds"
+	range 1 DPM_WATCHDOG_TIMEOUT
+	default DPM_WATCHDOG_TIMEOUT
+	depends on DPM_WATCHDOG
+	help
+	  If the DPM watchdog warning timeout and main timeout are
+	  different then a non-fatal warning (with a stack trace of
+	  the stuck suspend routine) will be printed when the warning
+	  timeout expires. If the suspend routine gets un-stuck
+	  before the main timeout expires then no other action is
+	  taken. If the routine continues to be stuck and the main
+	  timeout expires then an emergency-level message and stack
+	  trace will be printed and the system will panic.
+
+	  If the warning timeout is equal to the main timeout (the
+	  default) then the warning will never happen and the system
+	  will jump straight to panic when the main timeout expires.
+
+config PM_TRACE
+	bool
+	help
+	  This enables code to save the last PM event point across
+	  reboot. The architecture needs to support this, x86 for
+	  example does by saving things in the RTC, see below.
+
+	  The architecture specific code must provide the extern
+	  functions from <linux/resume-trace.h> as well as the
+	  <asm/resume-trace.h> header with a TRACE_RESUME() macro.
+
+	  The way the information is presented is architecture-
+	  dependent, x86 will print the information during a
+	  late_initcall.
+
+config PM_TRACE_RTC
+	bool "Suspend/resume event tracing"
+	depends on PM_SLEEP_DEBUG
+	depends on X86
+	select PM_TRACE
+	help
+	This enables some cheesy code to save the last PM event point in the
+	RTC across reboots, so that you can debug a machine that just hangs
+	during suspend (or more commonly, during resume).
+
+	To use this debugging feature you should attempt to suspend the
+	machine, reboot it and then run
+
+		dmesg -s 1000000 | grep 'hash matches'
+
+	CAUTION: this option will cause your machine's real-time clock to be
+	set to an invalid time after a resume.
+
+config APM_EMULATION
+	tristate "Advanced Power Management Emulation"
+	depends on SYS_SUPPORTS_APM_EMULATION
+	help
+	  APM is a BIOS specification for saving power using several different
+	  techniques. This is mostly useful for battery powered laptops with
+	  APM compliant BIOSes. If you say Y here, the system time will be
+	  reset after a RESUME operation, the /proc/apm device will provide
+	  battery status information, and user-space programs will receive
+	  notification of APM "events" (e.g. battery status change).
+
+	  In order to use APM, you will need supporting software. For location
+	  and more information, read <file:Documentation/power/apm-acpi.rst>
+	  and the Battery Powered Linux mini-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+	  This driver does not spin down disk drives (see the hdparm(8)
+	  manpage ("man 8 hdparm") for that), and it doesn't turn off
+	  VESA-compliant "green" monitors.
+
+	  Generally, if you don't have a battery in your machine, there isn't
+	  much point in using this driver and you should say N. If you get
+	  random kernel OOPSes or reboots that don't seem to be related to
+	  anything, try disabling/enabling this option (or disabling/enabling
+	  APM in your BIOS).
+
+config PM_CLK
+	def_bool y
+	depends on PM && HAVE_CLK
+
+config PM_GENERIC_DOMAINS
+	bool
+	depends on PM
+
+config WQ_POWER_EFFICIENT_DEFAULT
+	bool "Enable workqueue power-efficient mode by default"
+	depends on PM
+	help
+	  Per-cpu workqueues are generally preferred because they show
+	  better performance thanks to cache locality; unfortunately,
+	  per-cpu workqueues tend to be more power hungry than unbound
+	  workqueues.
+
+	  Enabling workqueue.power_efficient kernel parameter makes the
+	  per-cpu workqueues which were observed to contribute
+	  significantly to power consumption unbound, leading to measurably
+	  lower power usage at the cost of small performance overhead.
+
+	  This config option determines whether workqueue.power_efficient
+	  is enabled by default.
+
+	  If in doubt, say N.
+
+config PM_GENERIC_DOMAINS_SLEEP
+	def_bool y
+	depends on PM_SLEEP && PM_GENERIC_DOMAINS
+
+config PM_GENERIC_DOMAINS_OF
+	def_bool y
+	depends on PM_GENERIC_DOMAINS && OF
+
+config CPU_PM
+	bool
+
+config ENERGY_MODEL
+	bool "Energy Model for devices with DVFS (CPUs, GPUs, etc)"
+	depends on CPU_FREQ || PM_DEVFREQ
+	help
+	  Several subsystems (thermal and/or the task scheduler for example)
+	  can leverage information about the energy consumed by devices to
+	  make smarter decisions. This config option enables the framework
+	  from which subsystems can access the energy models.
+
+	  The exact usage of the energy model is subsystem-dependent.
+
+	  If in doubt, say N.

linux-7.2.3/kernel/power/Makefile

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ifeq ($(CONFIG_DYNAMIC_DEBUG), y)
+CFLAGS_swap.o                   := -DDEBUG
+CFLAGS_snapshot.o               := -DDEBUG
+CFLAGS_energy_model.o           := -DDEBUG
+endif
+
+KASAN_SANITIZE_snapshot.o	:= n
+
+obj-y				+= qos.o
+obj-$(CONFIG_PM)		+= main.o
+obj-$(CONFIG_VT_CONSOLE_SLEEP)	+= console.o
+obj-$(CONFIG_FREEZER)		+= process.o
+obj-$(CONFIG_SUSPEND)		+= suspend.o
+obj-$(CONFIG_PM_TEST_SUSPEND)	+= suspend_test.o
+obj-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o
+obj-$(CONFIG_HIBERNATION_SNAPSHOT_DEV) += user.o
+obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
+obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
+
+obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
+
+obj-$(CONFIG_ENERGY_MODEL)	+= em.o
+em-y				:= energy_model.o
+em-$(CONFIG_NET)		+= em_netlink_autogen.o em_netlink.o

linux-7.2.3/kernel/power/autosleep.c

@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kernel/power/autosleep.c
+ *
+ * Opportunistic sleep support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#include <linux/device.h>
+#include <linux/mutex.h>
+
+#include "power.h"
+
+static suspend_state_t autosleep_state;
+static struct workqueue_struct *autosleep_wq;
+/*
+ * Note: it is only safe to mutex_lock(&autosleep_lock) if a wakeup_source
+ * is active, otherwise a deadlock with try_to_suspend() is possible.
+ * Alternatively mutex_lock_interruptible() can be used.  This will then fail
+ * if an auto_sleep cycle tries to freeze processes.
+ */
+static DEFINE_MUTEX(autosleep_lock);
+static struct wakeup_source *autosleep_ws;
+
+static void try_to_suspend(struct work_struct *work)
+{
+	unsigned int initial_count, final_count;
+
+	if (!pm_get_wakeup_count(&initial_count, true))
+		goto out;
+
+	mutex_lock(&autosleep_lock);
+
+	if (!pm_save_wakeup_count(initial_count) ||
+		system_state != SYSTEM_RUNNING) {
+		mutex_unlock(&autosleep_lock);
+		goto out;
+	}
+
+	if (autosleep_state == PM_SUSPEND_ON) {
+		mutex_unlock(&autosleep_lock);
+		return;
+	}
+	if (autosleep_state >= PM_SUSPEND_MAX)
+		hibernate();
+	else
+		pm_suspend(autosleep_state);
+
+	mutex_unlock(&autosleep_lock);
+
+	if (!pm_get_wakeup_count(&final_count, false))
+		goto out;
+
+	/*
+	 * If the wakeup occurred for an unknown reason, wait to prevent the
+	 * system from trying to suspend and waking up in a tight loop.
+	 */
+	if (final_count == initial_count)
+		schedule_timeout_uninterruptible(HZ / 2);
+
+ out:
+	queue_up_suspend_work();
+}
+
+static DECLARE_WORK(suspend_work, try_to_suspend);
+
+void queue_up_suspend_work(void)
+{
+	if (autosleep_state > PM_SUSPEND_ON)
+		queue_work(autosleep_wq, &suspend_work);
+}
+
+suspend_state_t pm_autosleep_state(void)
+{
+	return autosleep_state;
+}
+
+int pm_autosleep_lock(void)
+{
+	return mutex_lock_interruptible(&autosleep_lock);
+}
+
+void pm_autosleep_unlock(void)
+{
+	mutex_unlock(&autosleep_lock);
+}
+
+int pm_autosleep_set_state(suspend_state_t state)
+{
+
+#ifndef CONFIG_HIBERNATION
+	if (state >= PM_SUSPEND_MAX)
+		return -EINVAL;
+#endif
+
+	__pm_stay_awake(autosleep_ws);
+
+	mutex_lock(&autosleep_lock);
+
+	autosleep_state = state;
+
+	__pm_relax(autosleep_ws);
+
+	if (state > PM_SUSPEND_ON) {
+		pm_wakep_autosleep_enabled(true);
+		queue_up_suspend_work();
+	} else {
+		pm_wakep_autosleep_enabled(false);
+	}
+
+	mutex_unlock(&autosleep_lock);
+	return 0;
+}
+
+int __init pm_autosleep_init(void)
+{
+	autosleep_ws = wakeup_source_register(NULL, "autosleep");
+	if (!autosleep_ws)
+		return -ENOMEM;
+
+	autosleep_wq = alloc_ordered_workqueue("autosleep", 0);
+	if (autosleep_wq)
+		return 0;
+
+	wakeup_source_unregister(autosleep_ws);
+	return -ENOMEM;
+}

linux-7.2.3/kernel/power/console.c

@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Functions for saving/restoring console.
+ *
+ * Originally from swsusp.
+ */
+
+#include <linux/console.h>
+#include <linux/vt_kern.h>
+#include <linux/kbd_kern.h>
+#include <linux/vt.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "power.h"
+
+#define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
+
+static int orig_fgconsole, orig_kmsg;
+static bool vt_switch_done;
+
+static DEFINE_MUTEX(vt_switch_mutex);
+
+struct pm_vt_switch {
+	struct list_head head;
+	struct device *dev;
+	bool required;
+};
+
+static LIST_HEAD(pm_vt_switch_list);
+
+
+/**
+ * pm_vt_switch_required - indicate VT switch at suspend requirements
+ * @dev: device
+ * @required: if true, caller needs VT switch at suspend/resume time
+ *
+ * The different console drivers may or may not require VT switches across
+ * suspend/resume, depending on how they handle restoring video state and
+ * what may be running.
+ *
+ * Drivers can indicate support for switchless suspend/resume, which can
+ * save time and flicker, by using this routine and passing 'false' as
+ * the argument.  If any loaded driver needs VT switching, or the
+ * no_console_suspend argument has been passed on the command line, VT
+ * switches will occur.
+ */
+int pm_vt_switch_required(struct device *dev, bool required)
+{
+	struct pm_vt_switch *entry, *tmp;
+	int ret = 0;
+
+	mutex_lock(&vt_switch_mutex);
+	list_for_each_entry(tmp, &pm_vt_switch_list, head) {
+		if (tmp->dev == dev) {
+			/* already registered, update requirement */
+			tmp->required = required;
+			goto out;
+		}
+	}
+
+	entry = kmalloc_obj(*entry);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto out;
+		}
+
+	entry->required = required;
+	entry->dev = dev;
+
+	list_add(&entry->head, &pm_vt_switch_list);
+out:
+	mutex_unlock(&vt_switch_mutex);
+	return ret;
+}
+EXPORT_SYMBOL(pm_vt_switch_required);
+
+/**
+ * pm_vt_switch_unregister - stop tracking a device's VT switching needs
+ * @dev: device
+ *
+ * Remove @dev from the vt switch list.
+ */
+void pm_vt_switch_unregister(struct device *dev)
+{
+	struct pm_vt_switch *tmp;
+
+	mutex_lock(&vt_switch_mutex);
+	list_for_each_entry(tmp, &pm_vt_switch_list, head) {
+		if (tmp->dev == dev) {
+			list_del(&tmp->head);
+			kfree(tmp);
+			break;
+		}
+	}
+	mutex_unlock(&vt_switch_mutex);
+}
+EXPORT_SYMBOL(pm_vt_switch_unregister);
+
+/*
+ * There are three cases when a VT switch on suspend/resume are required:
+ *   1) no driver has indicated a requirement one way or another, so preserve
+ *      the old behavior
+ *   2) console suspend is disabled, we want to see debug messages across
+ *      suspend/resume
+ *   3) any registered driver indicates it needs a VT switch
+ *
+ * If none of these conditions is present, meaning we have at least one driver
+ * that doesn't need the switch, and none that do, we can avoid it to make
+ * resume look a little prettier (and suspend too, but that's usually hidden,
+ * e.g. when closing the lid on a laptop).
+ */
+static bool pm_vt_switch(void)
+{
+	struct pm_vt_switch *entry;
+	bool ret = true;
+
+	mutex_lock(&vt_switch_mutex);
+	if (list_empty(&pm_vt_switch_list))
+		goto out;
+
+	if (!console_suspend_enabled)
+		goto out;
+
+	list_for_each_entry(entry, &pm_vt_switch_list, head) {
+		if (entry->required)
+			goto out;
+	}
+
+	ret = false;
+out:
+	mutex_unlock(&vt_switch_mutex);
+	return ret;
+}
+
+void pm_prepare_console(void)
+{
+	if (!pm_vt_switch())
+		return;
+
+	orig_fgconsole = vt_move_to_console(SUSPEND_CONSOLE, 1);
+	if (orig_fgconsole < 0)
+		return;
+
+	vt_switch_done = true;
+
+	orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE);
+	return;
+}
+
+void pm_restore_console(void)
+{
+	if (!pm_vt_switch() && !vt_switch_done)
+		return;
+
+	if (orig_fgconsole >= 0) {
+		vt_move_to_console(orig_fgconsole, 0);
+		vt_kmsg_redirect(orig_kmsg);
+	}
+
+	vt_switch_done = false;
+}

linux-7.2.3/kernel/power/em_netlink.c

@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *
+ * Generic netlink for energy model.
+ *
+ * Copyright (c) 2025 Valve Corporation.
+ * Author: Changwoo Min <changwoo@igalia.com>
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/energy_model.h>
+#include <net/sock.h>
+#include <net/genetlink.h>
+#include <uapi/linux/dev_energymodel.h>
+
+#include "em_netlink.h"
+#include "em_netlink_autogen.h"
+
+/*************************** Command encoding ********************************/
+struct dump_ctx {
+	int idx;
+	int start;
+	struct sk_buff *skb;
+	struct netlink_callback *cb;
+};
+
+static int __em_nl_get_pd_size(struct em_perf_domain *pd, void *data)
+{
+	int nr_cpus, msg_sz, cpus_sz;
+	int *tot_msg_sz = data;
+
+	nr_cpus = cpumask_weight(to_cpumask(pd->cpus));
+	cpus_sz = nla_total_size_64bit(sizeof(u64)) * nr_cpus;
+
+	msg_sz = nla_total_size(0) +
+		 /* DEV_ENERGYMODEL_A_PERF_DOMAINS_PERF_DOMAIN */
+		 nla_total_size(sizeof(u32)) +
+		 /* DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID */
+		 nla_total_size_64bit(sizeof(u64)) +
+		 /* DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS */
+		 nla_total_size(cpus_sz);
+		 /* DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS */
+
+	*tot_msg_sz += nlmsg_total_size(genlmsg_msg_size(msg_sz));
+	return 0;
+}
+
+static int __em_nl_get_pd(struct em_perf_domain *pd, void *data)
+{
+	struct sk_buff *msg = data;
+	struct cpumask *cpumask;
+	int cpu;
+
+	if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID,
+			pd->id))
+		goto out_cancel_nest;
+
+	if (nla_put_u64_64bit(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_FLAGS,
+			      pd->flags, DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD))
+		goto out_cancel_nest;
+
+	cpumask = to_cpumask(pd->cpus);
+	for_each_cpu(cpu, cpumask) {
+		if (nla_put_u64_64bit(msg, DEV_ENERGYMODEL_A_PERF_DOMAIN_CPUS,
+				      cpu, DEV_ENERGYMODEL_A_PERF_DOMAIN_PAD))
+			goto out_cancel_nest;
+	}
+
+	return 0;
+
+out_cancel_nest:
+	return -EMSGSIZE;
+}
+
+static int __em_nl_get_pd_for_dump(struct em_perf_domain *pd, void *data)
+{
+	const struct genl_info *info;
+	struct dump_ctx *ctx = data;
+	void *hdr;
+	int ret;
+
+	if (ctx->idx++ < ctx->start)
+		return 0;
+
+	info = genl_info_dump(ctx->cb);
+	hdr = genlmsg_iput(ctx->skb, info);
+	if (!hdr) {
+		genlmsg_cancel(ctx->skb, hdr);
+		return -EMSGSIZE;
+	}
+
+	ret = __em_nl_get_pd(pd, ctx->skb);
+	genlmsg_end(ctx->skb, hdr);
+	return ret;
+}
+
+int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb,
+					      struct genl_info *info)
+{
+	int id, ret = -EMSGSIZE, msg_sz = 0;
+	int cmd = info->genlhdr->cmd;
+	struct em_perf_domain *pd;
+	struct sk_buff *msg;
+	void *hdr;
+
+	if (!info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID])
+		return -EINVAL;
+
+	id = nla_get_u32(info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID]);
+	pd = em_perf_domain_get_by_id(id);
+	if (!pd)
+		return -EINVAL;
+
+	__em_nl_get_pd_size(pd, &msg_sz);
+	msg = genlmsg_new(msg_sz, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put_reply(msg, info, &dev_energymodel_nl_family, 0, cmd);
+	if (!hdr)
+		goto out_free_msg;
+
+	ret = __em_nl_get_pd(pd, msg);
+	if (ret)
+		goto out_cancel_msg;
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+
+out_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+out_free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
+int dev_energymodel_nl_get_perf_domains_dumpit(struct sk_buff *skb,
+						struct netlink_callback *cb)
+{
+	struct dump_ctx ctx = {
+		.idx = 0,
+		.start = cb->args[0],
+		.skb = skb,
+		.cb = cb,
+	};
+
+	return for_each_em_perf_domain(__em_nl_get_pd_for_dump, &ctx);
+}
+
+static struct em_perf_domain *__em_nl_get_pd_table_id(struct nlattr **attrs)
+{
+	struct em_perf_domain *pd;
+	int id;
+
+	if (!attrs[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID])
+		return NULL;
+
+	id = nla_get_u32(attrs[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID]);
+	pd = em_perf_domain_get_by_id(id);
+	return pd;
+}
+
+static int __em_nl_get_pd_table_size(const struct em_perf_domain *pd)
+{
+	int id_sz, ps_sz;
+
+	id_sz = nla_total_size(sizeof(u32));
+		/* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID */
+	ps_sz = nla_total_size(0) +
+		/* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE */
+		nla_total_size_64bit(sizeof(u64)) +
+		/* DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE */
+		nla_total_size_64bit(sizeof(u64)) +
+		/* DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY */
+		nla_total_size_64bit(sizeof(u64)) +
+		/* DEV_ENERGYMODEL_A_PERF_STATE_POWER */
+		nla_total_size_64bit(sizeof(u64)) +
+		/* DEV_ENERGYMODEL_A_PERF_STATE_COST */
+		nla_total_size_64bit(sizeof(u64));
+		/* DEV_ENERGYMODEL_A_PERF_STATE_FLAGS */
+	ps_sz *= pd->nr_perf_states;
+
+	return nlmsg_total_size(genlmsg_msg_size(id_sz + ps_sz));
+}
+
+static
+int __em_nl_get_pd_table(struct sk_buff *msg, const struct em_perf_domain *pd)
+{
+	struct em_perf_state *table, *ps;
+	struct nlattr *entry;
+	int i;
+
+	if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID,
+			pd->id))
+		goto out_err;
+
+	rcu_read_lock();
+	table = em_perf_state_from_pd((struct em_perf_domain *)pd);
+
+	for (i = 0; i < pd->nr_perf_states; i++) {
+		ps = &table[i];
+
+		entry = nla_nest_start(msg,
+				       DEV_ENERGYMODEL_A_PERF_TABLE_PERF_STATE);
+		if (!entry)
+			goto out_unlock_ps;
+
+		if (nla_put_u64_64bit(msg,
+				      DEV_ENERGYMODEL_A_PERF_STATE_PERFORMANCE,
+				      ps->performance,
+				      DEV_ENERGYMODEL_A_PERF_STATE_PAD))
+			goto out_cancel_ps_nest;
+		if (nla_put_u64_64bit(msg,
+				      DEV_ENERGYMODEL_A_PERF_STATE_FREQUENCY,
+				      ps->frequency,
+				      DEV_ENERGYMODEL_A_PERF_STATE_PAD))
+			goto out_cancel_ps_nest;
+		if (nla_put_u64_64bit(msg,
+				      DEV_ENERGYMODEL_A_PERF_STATE_POWER,
+				      ps->power,
+				      DEV_ENERGYMODEL_A_PERF_STATE_PAD))
+			goto out_cancel_ps_nest;
+		if (nla_put_u64_64bit(msg,
+				      DEV_ENERGYMODEL_A_PERF_STATE_COST,
+				      ps->cost,
+				      DEV_ENERGYMODEL_A_PERF_STATE_PAD))
+			goto out_cancel_ps_nest;
+		if (nla_put_u64_64bit(msg,
+				      DEV_ENERGYMODEL_A_PERF_STATE_FLAGS,
+				      ps->flags,
+				      DEV_ENERGYMODEL_A_PERF_STATE_PAD))
+			goto out_cancel_ps_nest;
+
+		nla_nest_end(msg, entry);
+	}
+	rcu_read_unlock();
+	return 0;
+
+out_cancel_ps_nest:
+	nla_nest_cancel(msg, entry);
+out_unlock_ps:
+	rcu_read_unlock();
+out_err:
+	return -EMSGSIZE;
+}
+
+int dev_energymodel_nl_get_perf_table_doit(struct sk_buff *skb,
+					    struct genl_info *info)
+{
+	int cmd = info->genlhdr->cmd;
+	int msg_sz, ret = -EMSGSIZE;
+	struct em_perf_domain *pd;
+	struct sk_buff *msg;
+	void *hdr;
+
+	pd = __em_nl_get_pd_table_id(info->attrs);
+	if (!pd)
+		return -EINVAL;
+
+	msg_sz = __em_nl_get_pd_table_size(pd);
+
+	msg = genlmsg_new(msg_sz, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put_reply(msg, info, &dev_energymodel_nl_family, 0, cmd);
+	if (!hdr)
+		goto out_free_msg;
+
+	ret = __em_nl_get_pd_table(msg, pd);
+	if (ret)
+		goto out_free_msg;
+
+	genlmsg_end(msg, hdr);
+	return genlmsg_reply(msg, info);
+
+out_free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
+
+/**************************** Event encoding *********************************/
+static void __em_notify_pd_table(const struct em_perf_domain *pd, int ntf_type)
+{
+	struct sk_buff *msg;
+	int msg_sz, ret = -EMSGSIZE;
+	void *hdr;
+
+	if (!genl_has_listeners(&dev_energymodel_nl_family, &init_net, DEV_ENERGYMODEL_NLGRP_EVENT))
+		return;
+
+	msg_sz = __em_nl_get_pd_table_size(pd);
+
+	msg = genlmsg_new(msg_sz, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = genlmsg_put(msg, 0, 0, &dev_energymodel_nl_family, 0, ntf_type);
+	if (!hdr)
+		goto out_free_msg;
+
+	ret = __em_nl_get_pd_table(msg, pd);
+	if (ret)
+		goto out_free_msg;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast(&dev_energymodel_nl_family, msg, 0,
+			  DEV_ENERGYMODEL_NLGRP_EVENT, GFP_KERNEL);
+
+	return;
+
+out_free_msg:
+	nlmsg_free(msg);
+}
+
+void em_notify_pd_created(const struct em_perf_domain *pd)
+{
+	__em_notify_pd_table(pd, DEV_ENERGYMODEL_CMD_PERF_DOMAIN_CREATED);
+}
+
+void em_notify_pd_updated(const struct em_perf_domain *pd)
+{
+	__em_notify_pd_table(pd, DEV_ENERGYMODEL_CMD_PERF_DOMAIN_UPDATED);
+}
+
+static int __em_notify_pd_deleted_size(const struct em_perf_domain *pd)
+{
+	int id_sz = nla_total_size(sizeof(u32)); /* DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID */
+
+	return nlmsg_total_size(genlmsg_msg_size(id_sz));
+}
+
+void em_notify_pd_deleted(const struct em_perf_domain *pd)
+{
+	struct sk_buff *msg;
+	void *hdr;
+	int msg_sz;
+
+	if (!genl_has_listeners(&dev_energymodel_nl_family, &init_net,
+				DEV_ENERGYMODEL_NLGRP_EVENT))
+		return;
+
+	msg_sz = __em_notify_pd_deleted_size(pd);
+
+	msg = genlmsg_new(msg_sz, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = genlmsg_put(msg, 0, 0, &dev_energymodel_nl_family, 0,
+			  DEV_ENERGYMODEL_CMD_PERF_DOMAIN_DELETED);
+	if (!hdr)
+		goto out_free_msg;
+
+	if (nla_put_u32(msg, DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID,
+			pd->id))
+		goto out_free_msg;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast(&dev_energymodel_nl_family, msg, 0,
+			  DEV_ENERGYMODEL_NLGRP_EVENT, GFP_KERNEL);
+
+	return;
+
+out_free_msg:
+	nlmsg_free(msg);
+}
+
+/**************************** Initialization *********************************/
+static int __init em_netlink_init(void)
+{
+	return genl_register_family(&dev_energymodel_nl_family);
+}
+postcore_initcall(em_netlink_init);

linux-7.2.3/kernel/power/em_netlink.h

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *
+ * Generic netlink for energy model.
+ *
+ * Copyright (c) 2025 Valve Corporation.
+ * Author: Changwoo Min <changwoo@igalia.com>
+ */
+#ifndef _EM_NETLINK_H
+#define _EM_NETLINK_H
+
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_NET)
+int for_each_em_perf_domain(int (*cb)(struct em_perf_domain*, void *),
+			    void *data);
+struct em_perf_domain *em_perf_domain_get_by_id(int id);
+void em_notify_pd_created(const struct em_perf_domain *pd);
+void em_notify_pd_deleted(const struct em_perf_domain *pd);
+void em_notify_pd_updated(const struct em_perf_domain *pd);
+#else
+static inline
+int for_each_em_perf_domain(int (*cb)(struct em_perf_domain*, void *),
+			    void *data)
+{
+	return -EINVAL;
+}
+static inline
+struct em_perf_domain *em_perf_domain_get_by_id(int id)
+{
+	return NULL;
+}
+
+static inline void em_notify_pd_created(const struct em_perf_domain *pd) {}
+
+static inline void em_notify_pd_deleted(const struct em_perf_domain *pd) {}
+
+static inline void em_notify_pd_updated(const struct em_perf_domain *pd) {}
+#endif
+
+#endif /* _EM_NETLINK_H */

linux-7.2.3/kernel/power/em_netlink_autogen.c

@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/dev-energymodel.yaml */
+/* YNL-GEN kernel source */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "em_netlink_autogen.h"
+
+#include <uapi/linux/dev_energymodel.h>
+
+/* DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS - do */
+static const struct nla_policy dev_energymodel_get_perf_domains_nl_policy[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID + 1] = {
+	[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID] = { .type = NLA_U32, },
+};
+
+/* DEV_ENERGYMODEL_CMD_GET_PERF_TABLE - do */
+static const struct nla_policy dev_energymodel_get_perf_table_nl_policy[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID + 1] = {
+	[DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID] = { .type = NLA_U32, },
+};
+
+/* Ops table for dev_energymodel */
+static const struct genl_split_ops dev_energymodel_nl_ops[] = {
+	{
+		.cmd		= DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS,
+		.doit		= dev_energymodel_nl_get_perf_domains_doit,
+		.policy		= dev_energymodel_get_perf_domains_nl_policy,
+		.maxattr	= DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= DEV_ENERGYMODEL_CMD_GET_PERF_DOMAINS,
+		.dumpit	= dev_energymodel_nl_get_perf_domains_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= DEV_ENERGYMODEL_CMD_GET_PERF_TABLE,
+		.doit		= dev_energymodel_nl_get_perf_table_doit,
+		.policy		= dev_energymodel_get_perf_table_nl_policy,
+		.maxattr	= DEV_ENERGYMODEL_A_PERF_TABLE_PERF_DOMAIN_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+};
+
+static const struct genl_multicast_group dev_energymodel_nl_mcgrps[] = {
+	[DEV_ENERGYMODEL_NLGRP_EVENT] = { "event", },
+};
+
+struct genl_family dev_energymodel_nl_family __ro_after_init = {
+	.name		= DEV_ENERGYMODEL_FAMILY_NAME,
+	.version	= DEV_ENERGYMODEL_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= dev_energymodel_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(dev_energymodel_nl_ops),
+	.mcgrps		= dev_energymodel_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(dev_energymodel_nl_mcgrps),
+};

linux-7.2.3/kernel/power/em_netlink_autogen.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/dev-energymodel.yaml */
+/* YNL-GEN kernel header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#ifndef _LINUX_DEV_ENERGYMODEL_GEN_H
+#define _LINUX_DEV_ENERGYMODEL_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/dev_energymodel.h>
+
+int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb,
+					     struct genl_info *info);
+int dev_energymodel_nl_get_perf_domains_dumpit(struct sk_buff *skb,
+					       struct netlink_callback *cb);
+int dev_energymodel_nl_get_perf_table_doit(struct sk_buff *skb,
+					   struct genl_info *info);
+
+enum {
+	DEV_ENERGYMODEL_NLGRP_EVENT,
+};
+
+extern struct genl_family dev_energymodel_nl_family;
+
+#endif /* _LINUX_DEV_ENERGYMODEL_GEN_H */

linux-7.2.3/kernel/power/power.h

@@ -0,0 +1,354 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/suspend.h>
+#include <linux/suspend_ioctls.h>
+#include <linux/utsname.h>
+#include <linux/freezer.h>
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/crypto.h>
+
+struct swsusp_info {
+	struct new_utsname	uts;
+	u32			version_code;
+	unsigned long		num_physpages;
+	int			cpus;
+	unsigned long		image_pages;
+	unsigned long		pages;
+	unsigned long		size;
+} __aligned(PAGE_SIZE);
+
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern int pm_sleep_fs_sync(void);
+extern bool filesystem_freeze_enabled;
+#endif
+
+#ifdef CONFIG_HIBERNATION
+/* kernel/power/snapshot.c */
+extern void __init hibernate_reserved_size_init(void);
+extern void __init hibernate_image_size_init(void);
+
+#ifdef CONFIG_ARCH_HIBERNATION_HEADER
+/* Maximum size of architecture specific data in a hibernation header */
+#define MAX_ARCH_HEADER_SIZE	(sizeof(struct new_utsname) + 4)
+
+static inline int init_header_complete(struct swsusp_info *info)
+{
+	return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE);
+}
+
+static inline const char *check_image_kernel(struct swsusp_info *info)
+{
+	return arch_hibernation_header_restore(info) ?
+			"architecture specific data" : NULL;
+}
+#endif /* CONFIG_ARCH_HIBERNATION_HEADER */
+
+/*
+ * Keep some memory free so that I/O operations can succeed without paging
+ * [Might this be more than 4 MB?]
+ */
+#define PAGES_FOR_IO	((4096 * 1024) >> PAGE_SHIFT)
+
+/*
+ * Keep 1 MB of memory free so that device drivers can allocate some pages in
+ * their .suspend() routines without breaking the suspend to disk.
+ */
+#define SPARE_PAGES	((1024 * 1024) >> PAGE_SHIFT)
+
+asmlinkage int swsusp_save(void);
+
+/* kernel/power/hibernate.c */
+extern bool freezer_test_done;
+extern char hib_comp_algo[CRYPTO_MAX_ALG_NAME];
+
+/* kernel/power/swap.c */
+extern unsigned int swsusp_header_flags;
+
+extern int hibernation_snapshot(int platform_mode);
+extern int hibernation_restore(int platform_mode);
+extern int hibernation_platform_enter(void);
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+/* kernel/power/snapshot.c */
+extern void enable_restore_image_protection(void);
+#else
+static inline void enable_restore_image_protection(void) {}
+#endif /* CONFIG_STRICT_KERNEL_RWX */
+
+extern bool hibernation_in_progress(void);
+
+#else /* !CONFIG_HIBERNATION */
+
+static inline void hibernate_reserved_size_init(void) {}
+static inline void hibernate_image_size_init(void) {}
+
+static inline bool hibernation_in_progress(void) { return false; }
+#endif /* !CONFIG_HIBERNATION */
+
+#define power_attr(_name) \
+static struct kobj_attribute _name##_attr = {	\
+	.attr	= {				\
+		.name = __stringify(_name),	\
+		.mode = 0644,			\
+	},					\
+	.show	= _name##_show,			\
+	.store	= _name##_store,		\
+}
+
+#define power_attr_ro(_name) \
+static struct kobj_attribute _name##_attr = {	\
+	.attr	= {				\
+		.name = __stringify(_name),	\
+		.mode = S_IRUGO,		\
+	},					\
+	.show	= _name##_show,			\
+}
+
+/* Preferred image size in bytes (default 500 MB) */
+extern unsigned long image_size;
+/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */
+extern unsigned long reserved_size;
+extern int in_suspend;
+extern dev_t swsusp_resume_device;
+extern sector_t swsusp_resume_block;
+
+extern int create_basic_memory_bitmaps(void);
+extern void free_basic_memory_bitmaps(void);
+extern int hibernate_preallocate_memory(void);
+
+extern void clear_or_poison_free_pages(void);
+
+/*
+ *	Auxiliary structure used for reading the snapshot image data and
+ *	metadata from and writing them to the list of page backup entries
+ *	(PBEs) which is the main data structure of swsusp.
+ *
+ *	Using struct snapshot_handle we can transfer the image, including its
+ *	metadata, as a continuous sequence of bytes with the help of
+ *	snapshot_read_next() and snapshot_write_next().
+ *
+ *	The code that writes the image to a storage or transfers it to
+ *	the user land is required to use snapshot_read_next() for this
+ *	purpose and it should not make any assumptions regarding the internal
+ *	structure of the image.  Similarly, the code that reads the image from
+ *	a storage or transfers it from the user land is required to use
+ *	snapshot_write_next().
+ *
+ *	This may allow us to change the internal structure of the image
+ *	in the future with considerably less effort.
+ */
+
+struct snapshot_handle {
+	unsigned int	cur;	/* number of the block of PAGE_SIZE bytes the
+				 * next operation will refer to (ie. current)
+				 */
+	void		*buffer;	/* address of the block to read from
+					 * or write to
+					 */
+	int		sync_read;	/* Set to one to notify the caller of
+					 * snapshot_write_next() that it may
+					 * need to call wait_on_bio_chain()
+					 */
+};
+
+/* This macro returns the address from/to which the caller of
+ * snapshot_read_next()/snapshot_write_next() is allowed to
+ * read/write data after the function returns
+ */
+#define data_of(handle)	((handle).buffer)
+
+extern unsigned int snapshot_additional_pages(struct zone *zone);
+extern unsigned long snapshot_get_image_size(void);
+extern int snapshot_read_next(struct snapshot_handle *handle);
+extern int snapshot_write_next(struct snapshot_handle *handle);
+int snapshot_write_finalize(struct snapshot_handle *handle);
+extern int snapshot_image_loaded(struct snapshot_handle *handle);
+
+extern bool hibernate_acquire(void);
+extern void hibernate_release(void);
+
+extern sector_t alloc_swapdev_block(int swap);
+extern void free_all_swap_pages(int swap);
+extern int swsusp_swap_in_use(void);
+
+/*
+ * Flags that can be passed from the hibernatig hernel to the "boot" kernel in
+ * the image header.
+ */
+#define SF_COMPRESSION_ALG_LZO	0 /* dummy, details given  below */
+#define SF_PLATFORM_MODE	1
+#define SF_NOCOMPRESS_MODE	2
+#define SF_CRC32_MODE	        4
+#define SF_HW_SIG		8
+
+/*
+ * Bit to indicate the compression algorithm to be used(for LZ4). The same
+ * could be checked while saving/loading image to/from disk to use the
+ * corresponding algorithms.
+ *
+ * By default, LZO compression is enabled if SF_CRC32_MODE is set. Use
+ * SF_COMPRESSION_ALG_LZ4 to override this behaviour and use LZ4.
+ *
+ * SF_CRC32_MODE, SF_COMPRESSION_ALG_LZO(dummy) -> Compression, LZO
+ * SF_CRC32_MODE, SF_COMPRESSION_ALG_LZ4 -> Compression, LZ4
+ */
+#define SF_COMPRESSION_ALG_LZ4	16
+
+/* kernel/power/hibernate.c */
+int swsusp_check(bool exclusive);
+extern void swsusp_free(void);
+extern int swsusp_read(unsigned int *flags_p);
+extern int swsusp_write(unsigned int flags);
+void swsusp_close(void);
+#ifdef CONFIG_SUSPEND
+extern int swsusp_unmark(void);
+#else
+static inline int swsusp_unmark(void) { return 0; }
+#endif
+
+struct __kernel_old_timeval;
+/* kernel/power/swsusp.c */
+extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *);
+
+#ifdef CONFIG_SUSPEND
+/* kernel/power/suspend.c */
+extern const char * const pm_labels[];
+extern const char *pm_states[];
+extern const char *mem_sleep_states[];
+
+extern int suspend_devices_and_enter(suspend_state_t state);
+#else /* !CONFIG_SUSPEND */
+#define mem_sleep_current	PM_SUSPEND_ON
+
+static inline int suspend_devices_and_enter(suspend_state_t state)
+{
+	return -ENOSYS;
+}
+#endif /* !CONFIG_SUSPEND */
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+/* kernel/power/suspend_test.c */
+extern void suspend_test_start(void);
+extern void suspend_test_finish(const char *label);
+#else /* !CONFIG_PM_TEST_SUSPEND */
+static inline void suspend_test_start(void) {}
+static inline void suspend_test_finish(const char *label) {}
+#endif /* !CONFIG_PM_TEST_SUSPEND */
+
+#ifdef CONFIG_PM_SLEEP
+/* kernel/power/main.c */
+extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
+extern int pm_notifier_call_chain(unsigned long val);
+#endif
+
+#ifdef CONFIG_HIGHMEM
+int restore_highmem(void);
+#else
+static inline unsigned int count_highmem_pages(void) { return 0; }
+static inline int restore_highmem(void) { return 0; }
+#endif
+
+/*
+ * Suspend test levels
+ */
+enum {
+	/* keep first */
+	TEST_NONE,
+	TEST_CORE,
+	TEST_CPUS,
+	TEST_PLATFORM,
+	TEST_DEVICES,
+	TEST_FREEZER,
+	/* keep last */
+	__TEST_AFTER_LAST
+};
+
+#define TEST_FIRST	TEST_NONE
+#define TEST_MAX	(__TEST_AFTER_LAST - 1)
+
+#ifdef CONFIG_PM_SLEEP_DEBUG
+extern int pm_test_level;
+#else
+#define pm_test_level	(TEST_NONE)
+#endif
+
+#ifdef CONFIG_SUSPEND_FREEZER
+static inline int suspend_freeze_processes(void)
+{
+	int error;
+
+	error = freeze_processes();
+	/*
+	 * freeze_processes() automatically thaws every task if freezing
+	 * fails. So we need not do anything extra upon error.
+	 */
+	if (error)
+		return error;
+
+	error = freeze_kernel_threads();
+	/*
+	 * freeze_kernel_threads() thaws only kernel threads upon freezing
+	 * failure. So we have to thaw the userspace tasks ourselves.
+	 */
+	if (error)
+		thaw_processes();
+
+	return error;
+}
+
+static inline void suspend_thaw_processes(void)
+{
+	thaw_processes();
+}
+#else
+static inline int suspend_freeze_processes(void)
+{
+	return 0;
+}
+
+static inline void suspend_thaw_processes(void)
+{
+}
+#endif
+
+#ifdef CONFIG_PM_AUTOSLEEP
+
+/* kernel/power/autosleep.c */
+extern int pm_autosleep_init(void);
+extern int pm_autosleep_lock(void);
+extern void pm_autosleep_unlock(void);
+extern suspend_state_t pm_autosleep_state(void);
+extern int pm_autosleep_set_state(suspend_state_t state);
+
+#else /* !CONFIG_PM_AUTOSLEEP */
+
+static inline int pm_autosleep_init(void) { return 0; }
+static inline int pm_autosleep_lock(void) { return 0; }
+static inline void pm_autosleep_unlock(void) {}
+static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; }
+
+#endif /* !CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+
+/* kernel/power/wakelock.c */
+extern ssize_t pm_show_wakelocks(char *buf, bool show_active);
+extern int pm_wake_lock(const char *buf);
+extern int pm_wake_unlock(const char *buf);
+
+#endif /* !CONFIG_PM_WAKELOCKS */
+
+static inline int pm_sleep_disable_secondary_cpus(void)
+{
+	cpuidle_pause();
+	return suspend_disable_secondary_cpus();
+}
+
+static inline void pm_sleep_enable_secondary_cpus(void)
+{
+	suspend_enable_secondary_cpus();
+	cpuidle_resume();
+}
+
+void dpm_save_errno(int err);

linux-7.2.3/kernel/power/poweroff.c

@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * poweroff.c - sysrq handler to gracefully power down machine.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sysrq.h>
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <linux/workqueue.h>
+#include <linux/reboot.h>
+#include <linux/cpumask.h>
+
+/*
+ * When the user hits Sys-Rq o to power down the machine this is the
+ * callback we use.
+ */
+
+static void do_poweroff(struct work_struct *dummy)
+{
+	kernel_power_off();
+}
+
+static DECLARE_WORK(poweroff_work, do_poweroff);
+
+static void handle_poweroff(u8 key)
+{
+	/* run sysrq poweroff on boot cpu */
+	schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
+}
+
+static const struct sysrq_key_op	sysrq_poweroff_op = {
+	.handler        = handle_poweroff,
+	.help_msg       = "poweroff(o)",
+	.action_msg     = "Power Off",
+	.enable_mask	= SYSRQ_ENABLE_BOOT,
+};
+
+static int __init pm_sysrq_init(void)
+{
+	register_sysrq_key('o', &sysrq_poweroff_op);
+	return 0;
+}
+
+subsys_initcall(pm_sysrq_init);

linux-7.2.3/kernel/power/process.c

@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/power/process.c - Functions for starting/stopping processes on
+ *                           suspend transitions.
+ *
+ * Originally from swsusp.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/oom.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/syscalls.h>
+#include <linux/freezer.h>
+#include <linux/delay.h>
+#include <linux/workqueue.h>
+#include <linux/kmod.h>
+#include <trace/events/power.h>
+#include <linux/cpuset.h>
+
+/*
+ * Timeout for stopping processes
+ */
+unsigned int __read_mostly freeze_timeout_msecs = 20 * MSEC_PER_SEC;
+
+static int try_to_freeze_tasks(bool user_only)
+{
+	const char *what = user_only ? "user space processes" :
+					"remaining freezable tasks";
+	struct task_struct *g, *p;
+	unsigned long end_time;
+	unsigned int todo;
+	bool wq_busy = false;
+	ktime_t start, end, elapsed;
+	unsigned int elapsed_msecs;
+	bool wakeup = false;
+	int sleep_usecs = USEC_PER_MSEC;
+
+	pr_info("Freezing %s\n", what);
+
+	start = ktime_get_boottime();
+
+	end_time = jiffies + msecs_to_jiffies(freeze_timeout_msecs);
+
+	if (!user_only)
+		freeze_workqueues_begin();
+
+	while (true) {
+		todo = 0;
+		read_lock(&tasklist_lock);
+		for_each_process_thread(g, p) {
+			if (p == current || !freeze_task(p))
+				continue;
+
+			todo++;
+		}
+		read_unlock(&tasklist_lock);
+
+		if (!user_only) {
+			wq_busy = freeze_workqueues_busy();
+			todo += wq_busy;
+		}
+
+		if (!todo || time_after(jiffies, end_time))
+			break;
+
+		if (pm_wakeup_pending()) {
+			wakeup = true;
+			break;
+		}
+
+		/*
+		 * We need to retry, but first give the freezing tasks some
+		 * time to enter the refrigerator.  Start with an initial
+		 * 1 ms sleep followed by exponential backoff until 8 ms.
+		 */
+		usleep_range(sleep_usecs / 2, sleep_usecs);
+		if (sleep_usecs < 8 * USEC_PER_MSEC)
+			sleep_usecs *= 2;
+	}
+
+	end = ktime_get_boottime();
+	elapsed = ktime_sub(end, start);
+	elapsed_msecs = ktime_to_ms(elapsed);
+
+	if (todo) {
+		pr_err("Freezing %s %s after %d.%03d seconds "
+		       "(%d tasks refusing to freeze, wq_busy=%d):\n", what,
+		       wakeup ? "aborted" : "failed",
+		       elapsed_msecs / 1000, elapsed_msecs % 1000,
+		       todo - wq_busy, wq_busy);
+
+		if (wq_busy)
+			show_freezable_workqueues();
+
+		if (!wakeup || pm_debug_messages_on) {
+			read_lock(&tasklist_lock);
+			for_each_process_thread(g, p) {
+				if (p != current && freezing(p) && !frozen(p))
+					sched_show_task(p);
+			}
+			read_unlock(&tasklist_lock);
+		}
+	} else {
+		pr_info("Freezing %s completed (elapsed %d.%03d seconds)\n",
+			what, elapsed_msecs / 1000, elapsed_msecs % 1000);
+	}
+
+	return todo ? -EBUSY : 0;
+}
+
+/**
+ * freeze_processes - Signal user space processes to enter the refrigerator.
+ * The current thread will not be frozen.  The same process that calls
+ * freeze_processes must later call thaw_processes.
+ *
+ * On success, returns 0.  On failure, -errno and system is fully thawed.
+ */
+int freeze_processes(void)
+{
+	int error;
+
+	error = __usermodehelper_disable(UMH_FREEZING);
+	if (error)
+		return error;
+
+	/* Make sure this task doesn't get frozen */
+	current->flags |= PF_SUSPEND_TASK;
+
+	if (!pm_freezing)
+		static_branch_inc(&freezer_active);
+
+	pm_wakeup_clear(0);
+	pm_freezing = true;
+	error = try_to_freeze_tasks(true);
+	if (!error)
+		__usermodehelper_set_disable_depth(UMH_DISABLED);
+
+	BUG_ON(in_atomic());
+
+	/*
+	 * Now that the whole userspace is frozen we need to disable
+	 * the OOM killer to disallow any further interference with
+	 * killable tasks. There is no guarantee oom victims will
+	 * ever reach a point they go away we have to wait with a timeout.
+	 */
+	if (!error && !oom_killer_disable(msecs_to_jiffies(freeze_timeout_msecs)))
+		error = -EBUSY;
+
+	if (error)
+		thaw_processes();
+	return error;
+}
+
+/**
+ * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator.
+ *
+ * On success, returns 0.  On failure, -errno and only the kernel threads are
+ * thawed, so as to give a chance to the caller to do additional cleanups
+ * (if any) before thawing the userspace tasks. So, it is the responsibility
+ * of the caller to thaw the userspace tasks, when the time is right.
+ */
+int freeze_kernel_threads(void)
+{
+	int error;
+
+	pm_nosig_freezing = true;
+	error = try_to_freeze_tasks(false);
+
+	BUG_ON(in_atomic());
+
+	if (error)
+		thaw_kernel_threads();
+	return error;
+}
+
+void thaw_processes(void)
+{
+	struct task_struct *g, *p;
+	struct task_struct *curr = current;
+
+	trace_suspend_resume(TPS("thaw_processes"), 0, true);
+	if (pm_freezing)
+		static_branch_dec(&freezer_active);
+	pm_freezing = false;
+	pm_nosig_freezing = false;
+
+	oom_killer_enable();
+
+	pr_info("Restarting tasks: Starting\n");
+
+	__usermodehelper_set_disable_depth(UMH_FREEZING);
+	thaw_workqueues();
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		/* No other threads should have PF_SUSPEND_TASK set */
+		WARN_ON((p != curr) && (p->flags & PF_SUSPEND_TASK));
+		__thaw_task(p);
+	}
+	read_unlock(&tasklist_lock);
+
+	WARN_ON(!(curr->flags & PF_SUSPEND_TASK));
+	curr->flags &= ~PF_SUSPEND_TASK;
+
+	usermodehelper_enable();
+
+	schedule();
+	pr_info("Restarting tasks: Done\n");
+	trace_suspend_resume(TPS("thaw_processes"), 0, false);
+}
+
+void thaw_kernel_threads(void)
+{
+	struct task_struct *g, *p;
+
+	pm_nosig_freezing = false;
+	pr_info("Restarting kernel threads ...\n");
+
+	thaw_workqueues();
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		if (p->flags & PF_KTHREAD)
+			__thaw_task(p);
+	}
+	read_unlock(&tasklist_lock);
+
+	schedule();
+	pr_info("Done restarting kernel threads.\n");
+}

linux-7.2.3/kernel/power/qos.c

@@ -0,0 +1,794 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Power Management Quality of Service (PM QoS) support base.
+ *
+ * Copyright (C) 2020 Intel Corporation
+ *
+ * Authors:
+ *	Mark Gross <mgross@linux.intel.com>
+ *	Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * Provided here is an interface for specifying PM QoS dependencies.  It allows
+ * entities depending on QoS constraints to register their requests which are
+ * aggregated as appropriate to produce effective constraints (target values)
+ * that can be monitored by entities needing to respect them, either by polling
+ * or through a built-in notification mechanism.
+ *
+ * In addition to the basic functionality, more specific interfaces for managing
+ * global CPU latency QoS requests and frequency QoS requests are provided.
+ */
+
+/*#define DEBUG*/
+
+#include <linux/pm_qos.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/string.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <trace/events/power.h>
+
+/*
+ * locking rule: all changes to constraints or notifiers lists
+ * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock
+ * held, taken with _irqsave.  One lock to rule them all
+ */
+static DEFINE_SPINLOCK(pm_qos_lock);
+
+/**
+ * pm_qos_read_value - Return the current effective constraint value.
+ * @c: List of PM QoS constraint requests.
+ */
+s32 pm_qos_read_value(struct pm_qos_constraints *c)
+{
+	return READ_ONCE(c->target_value);
+}
+
+static int pm_qos_get_value(struct pm_qos_constraints *c)
+{
+	if (plist_head_empty(&c->list))
+		return c->no_constraint_value;
+
+	switch (c->type) {
+	case PM_QOS_MIN:
+		return plist_first(&c->list)->prio;
+
+	case PM_QOS_MAX:
+		return plist_last(&c->list)->prio;
+
+	default:
+		WARN(1, "Unknown PM QoS type in %s\n", __func__);
+		return PM_QOS_DEFAULT_VALUE;
+	}
+}
+
+static void pm_qos_set_value(struct pm_qos_constraints *c, s32 value)
+{
+	WRITE_ONCE(c->target_value, value);
+}
+
+/**
+ * pm_qos_update_target - Update a list of PM QoS constraint requests.
+ * @c: List of PM QoS requests.
+ * @node: Target list entry.
+ * @action: Action to carry out (add, update or remove).
+ * @value: New request value for the target list entry.
+ *
+ * Update the given list of PM QoS constraint requests, @c, by carrying an
+ * @action involving the @node list entry and @value on it.
+ *
+ * The recognized values of @action are PM_QOS_ADD_REQ (store @value in @node
+ * and add it to the list), PM_QOS_UPDATE_REQ (remove @node from the list, store
+ * @value in it and add it to the list again), and PM_QOS_REMOVE_REQ (remove
+ * @node from the list, ignore @value).
+ *
+ * Return: 1 if the aggregate constraint value has changed, 0  otherwise.
+ */
+int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
+			 enum pm_qos_req_action action, int value)
+{
+	int prev_value, curr_value, new_value;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pm_qos_lock, flags);
+
+	prev_value = pm_qos_get_value(c);
+	if (value == PM_QOS_DEFAULT_VALUE)
+		new_value = c->default_value;
+	else
+		new_value = value;
+
+	switch (action) {
+	case PM_QOS_REMOVE_REQ:
+		plist_del(node, &c->list);
+		break;
+	case PM_QOS_UPDATE_REQ:
+		/*
+		 * To change the list, atomically remove, reinit with new value
+		 * and add, then see if the aggregate has changed.
+		 */
+		plist_del(node, &c->list);
+		fallthrough;
+	case PM_QOS_ADD_REQ:
+		plist_node_init(node, new_value);
+		plist_add(node, &c->list);
+		break;
+	default:
+		/* no action */
+		;
+	}
+
+	curr_value = pm_qos_get_value(c);
+	pm_qos_set_value(c, curr_value);
+
+	spin_unlock_irqrestore(&pm_qos_lock, flags);
+
+	trace_pm_qos_update_target(action, prev_value, curr_value);
+
+	if (prev_value == curr_value)
+		return 0;
+
+	if (c->notifiers)
+		blocking_notifier_call_chain(c->notifiers, curr_value, NULL);
+
+	return 1;
+}
+
+/**
+ * pm_qos_flags_remove_req - Remove device PM QoS flags request.
+ * @pqf: Device PM QoS flags set to remove the request from.
+ * @req: Request to remove from the set.
+ */
+static void pm_qos_flags_remove_req(struct pm_qos_flags *pqf,
+				    struct pm_qos_flags_request *req)
+{
+	s32 val = 0;
+
+	list_del(&req->node);
+	list_for_each_entry(req, &pqf->list, node)
+		val |= req->flags;
+
+	pqf->effective_flags = val;
+}
+
+/**
+ * pm_qos_update_flags - Update a set of PM QoS flags.
+ * @pqf: Set of PM QoS flags to update.
+ * @req: Request to add to the set, to modify, or to remove from the set.
+ * @action: Action to take on the set.
+ * @val: Value of the request to add or modify.
+ *
+ * Return: 1 if the aggregate constraint value has changed, 0 otherwise.
+ */
+bool pm_qos_update_flags(struct pm_qos_flags *pqf,
+			 struct pm_qos_flags_request *req,
+			 enum pm_qos_req_action action, s32 val)
+{
+	unsigned long irqflags;
+	s32 prev_value, curr_value;
+
+	spin_lock_irqsave(&pm_qos_lock, irqflags);
+
+	prev_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags;
+
+	switch (action) {
+	case PM_QOS_REMOVE_REQ:
+		pm_qos_flags_remove_req(pqf, req);
+		break;
+	case PM_QOS_UPDATE_REQ:
+		pm_qos_flags_remove_req(pqf, req);
+		fallthrough;
+	case PM_QOS_ADD_REQ:
+		req->flags = val;
+		INIT_LIST_HEAD(&req->node);
+		list_add_tail(&req->node, &pqf->list);
+		pqf->effective_flags |= val;
+		break;
+	default:
+		/* no action */
+		;
+	}
+
+	curr_value = list_empty(&pqf->list) ? 0 : pqf->effective_flags;
+
+	spin_unlock_irqrestore(&pm_qos_lock, irqflags);
+
+	trace_pm_qos_update_flags(action, prev_value, curr_value);
+
+	return prev_value != curr_value;
+}
+
+#ifdef CONFIG_CPU_IDLE
+/* Definitions related to the CPU latency QoS. */
+
+static struct pm_qos_constraints cpu_latency_constraints = {
+	.list = PLIST_HEAD_INIT(cpu_latency_constraints.list),
+	.target_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.no_constraint_value = PM_QOS_CPU_LATENCY_DEFAULT_VALUE,
+	.type = PM_QOS_MIN,
+};
+
+static inline bool cpu_latency_qos_value_invalid(s32 value)
+{
+	return value < 0 && value != PM_QOS_DEFAULT_VALUE;
+}
+
+/**
+ * cpu_latency_qos_limit - Return current system-wide CPU latency QoS limit.
+ */
+s32 cpu_latency_qos_limit(void)
+{
+	return pm_qos_read_value(&cpu_latency_constraints);
+}
+
+/**
+ * cpu_latency_qos_request_active - Check the given PM QoS request.
+ * @req: PM QoS request to check.
+ *
+ * Return: 'true' if @req has been added to the CPU latency QoS list, 'false'
+ * otherwise.
+ */
+bool cpu_latency_qos_request_active(struct pm_qos_request *req)
+{
+	return req->qos == &cpu_latency_constraints;
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_request_active);
+
+static void cpu_latency_qos_apply(struct pm_qos_request *req,
+				  enum pm_qos_req_action action, s32 value)
+{
+	int ret = pm_qos_update_target(req->qos, &req->node, action, value);
+	if (ret > 0)
+		wake_up_all_idle_cpus();
+}
+
+/**
+ * cpu_latency_qos_add_request - Add new CPU latency QoS request.
+ * @req: Pointer to a preallocated handle.
+ * @value: Requested constraint value.
+ *
+ * Use @value to initialize the request handle pointed to by @req, insert it as
+ * a new entry to the CPU latency QoS list and recompute the effective QoS
+ * constraint for that list.
+ *
+ * Callers need to save the handle for later use in updates and removal of the
+ * QoS request represented by it.
+ */
+void cpu_latency_qos_add_request(struct pm_qos_request *req, s32 value)
+{
+	if (!req || cpu_latency_qos_value_invalid(value))
+		return;
+
+	if (cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for already added request\n", __func__);
+		return;
+	}
+
+	trace_pm_qos_add_request(value);
+
+	req->qos = &cpu_latency_constraints;
+	cpu_latency_qos_apply(req, PM_QOS_ADD_REQ, value);
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_add_request);
+
+/**
+ * cpu_latency_qos_update_request - Modify existing CPU latency QoS request.
+ * @req : QoS request to update.
+ * @new_value: New requested constraint value.
+ *
+ * Use @new_value to update the QoS request represented by @req in the CPU
+ * latency QoS list along with updating the effective constraint value for that
+ * list.
+ */
+void cpu_latency_qos_update_request(struct pm_qos_request *req, s32 new_value)
+{
+	if (!req || cpu_latency_qos_value_invalid(new_value))
+		return;
+
+	if (!cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for unknown object\n", __func__);
+		return;
+	}
+
+	trace_pm_qos_update_request(new_value);
+
+	if (new_value == req->node.prio)
+		return;
+
+	cpu_latency_qos_apply(req, PM_QOS_UPDATE_REQ, new_value);
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_update_request);
+
+/**
+ * cpu_latency_qos_remove_request - Remove existing CPU latency QoS request.
+ * @req: QoS request to remove.
+ *
+ * Remove the CPU latency QoS request represented by @req from the CPU latency
+ * QoS list along with updating the effective constraint value for that list.
+ */
+void cpu_latency_qos_remove_request(struct pm_qos_request *req)
+{
+	if (!req)
+		return;
+
+	if (!cpu_latency_qos_request_active(req)) {
+		WARN(1, KERN_ERR "%s called for unknown object\n", __func__);
+		return;
+	}
+
+	trace_pm_qos_remove_request(PM_QOS_DEFAULT_VALUE);
+
+	cpu_latency_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+	memset(req, 0, sizeof(*req));
+}
+EXPORT_SYMBOL_GPL(cpu_latency_qos_remove_request);
+
+/* User space interface to the CPU latency QoS via misc device. */
+
+static int cpu_latency_qos_open(struct inode *inode, struct file *filp)
+{
+	struct pm_qos_request *req;
+
+	req = kzalloc_obj(*req);
+	if (!req)
+		return -ENOMEM;
+
+	cpu_latency_qos_add_request(req, PM_QOS_DEFAULT_VALUE);
+	filp->private_data = req;
+
+	return 0;
+}
+
+static int cpu_latency_qos_release(struct inode *inode, struct file *filp)
+{
+	struct pm_qos_request *req = filp->private_data;
+
+	filp->private_data = NULL;
+
+	cpu_latency_qos_remove_request(req);
+	kfree(req);
+
+	return 0;
+}
+
+static ssize_t cpu_latency_qos_read(struct file *filp, char __user *buf,
+				    size_t count, loff_t *f_pos)
+{
+	struct pm_qos_request *req = filp->private_data;
+	unsigned long flags;
+	s32 value;
+
+	if (!req || !cpu_latency_qos_request_active(req))
+		return -EINVAL;
+
+	spin_lock_irqsave(&pm_qos_lock, flags);
+	value = pm_qos_get_value(&cpu_latency_constraints);
+	spin_unlock_irqrestore(&pm_qos_lock, flags);
+
+	return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
+}
+
+static ssize_t cpu_latency_qos_write(struct file *filp, const char __user *buf,
+				     size_t count, loff_t *f_pos)
+{
+	s32 value;
+
+	if (count == sizeof(s32)) {
+		if (copy_from_user(&value, buf, sizeof(s32)))
+			return -EFAULT;
+	} else {
+		int ret;
+
+		ret = kstrtos32_from_user(buf, count, 16, &value);
+		if (ret)
+			return ret;
+	}
+
+	cpu_latency_qos_update_request(filp->private_data, value);
+
+	return count;
+}
+
+static const struct file_operations cpu_latency_qos_fops = {
+	.write = cpu_latency_qos_write,
+	.read = cpu_latency_qos_read,
+	.open = cpu_latency_qos_open,
+	.release = cpu_latency_qos_release,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice cpu_latency_qos_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "cpu_dma_latency",
+	.fops = &cpu_latency_qos_fops,
+};
+
+#ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP
+/* The CPU system wakeup latency QoS. */
+static struct pm_qos_constraints cpu_wakeup_latency_constraints = {
+	.list = PLIST_HEAD_INIT(cpu_wakeup_latency_constraints.list),
+	.target_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT,
+	.default_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT,
+	.no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT,
+	.type = PM_QOS_MIN,
+};
+
+/**
+ * cpu_wakeup_latency_qos_limit - Current CPU system wakeup latency QoS limit.
+ *
+ * Returns the current CPU system wakeup latency QoS limit that may have been
+ * requested by user space.
+ */
+s32 cpu_wakeup_latency_qos_limit(void)
+{
+	return pm_qos_read_value(&cpu_wakeup_latency_constraints);
+}
+
+static int cpu_wakeup_latency_qos_open(struct inode *inode, struct file *filp)
+{
+	struct pm_qos_request *req;
+
+	req = kzalloc_obj(*req);
+	if (!req)
+		return -ENOMEM;
+
+	req->qos = &cpu_wakeup_latency_constraints;
+	pm_qos_update_target(req->qos, &req->node, PM_QOS_ADD_REQ,
+			     PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
+	filp->private_data = req;
+
+	return 0;
+}
+
+static int cpu_wakeup_latency_qos_release(struct inode *inode,
+					  struct file *filp)
+{
+	struct pm_qos_request *req = filp->private_data;
+
+	filp->private_data = NULL;
+	pm_qos_update_target(req->qos, &req->node, PM_QOS_REMOVE_REQ,
+			     PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
+	kfree(req);
+
+	return 0;
+}
+
+static ssize_t cpu_wakeup_latency_qos_read(struct file *filp, char __user *buf,
+					   size_t count, loff_t *f_pos)
+{
+	s32 value = pm_qos_read_value(&cpu_wakeup_latency_constraints);
+
+	return simple_read_from_buffer(buf, count, f_pos, &value, sizeof(s32));
+}
+
+static ssize_t cpu_wakeup_latency_qos_write(struct file *filp,
+					    const char __user *buf,
+					    size_t count, loff_t *f_pos)
+{
+	struct pm_qos_request *req = filp->private_data;
+	s32 value;
+
+	if (count == sizeof(s32)) {
+		if (copy_from_user(&value, buf, sizeof(s32)))
+			return -EFAULT;
+	} else {
+		int ret;
+
+		ret = kstrtos32_from_user(buf, count, 16, &value);
+		if (ret)
+			return ret;
+	}
+
+	if (value < 0)
+		return -EINVAL;
+
+	pm_qos_update_target(req->qos, &req->node, PM_QOS_UPDATE_REQ, value);
+
+	return count;
+}
+
+static const struct file_operations cpu_wakeup_latency_qos_fops = {
+	.open = cpu_wakeup_latency_qos_open,
+	.release = cpu_wakeup_latency_qos_release,
+	.read = cpu_wakeup_latency_qos_read,
+	.write = cpu_wakeup_latency_qos_write,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice cpu_wakeup_latency_qos_miscdev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "cpu_wakeup_latency",
+	.fops = &cpu_wakeup_latency_qos_fops,
+};
+#endif /* CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP */
+
+static int __init cpu_latency_qos_init(void)
+{
+	int ret;
+
+	ret = misc_register(&cpu_latency_qos_miscdev);
+	if (ret < 0) {
+		pr_err("%s: %s setup failed\n", __func__,
+		       cpu_latency_qos_miscdev.name);
+		return ret;
+	}
+
+#ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP
+	ret = misc_register(&cpu_wakeup_latency_qos_miscdev);
+	if (ret < 0) {
+		pr_err("%s: %s setup failed\n", __func__,
+		       cpu_wakeup_latency_qos_miscdev.name);
+		misc_deregister(&cpu_latency_qos_miscdev);
+		return ret;
+	}
+#endif
+
+	return 0;
+}
+late_initcall(cpu_latency_qos_init);
+#endif /* CONFIG_CPU_IDLE */
+
+/* Definitions related to the frequency QoS below. */
+
+static inline bool freq_qos_value_invalid(s32 value)
+{
+	return value < 0 && value != PM_QOS_DEFAULT_VALUE;
+}
+
+/**
+ * freq_constraints_init - Initialize frequency QoS constraints.
+ * @qos: Frequency QoS constraints to initialize.
+ */
+void freq_constraints_init(struct freq_constraints *qos)
+{
+	struct pm_qos_constraints *c;
+
+	c = &qos->min_freq;
+	plist_head_init(&c->list);
+	c->target_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+	c->default_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+	c->no_constraint_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+	c->type = PM_QOS_MAX;
+	c->notifiers = &qos->min_freq_notifiers;
+	BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers);
+
+	c = &qos->max_freq;
+	plist_head_init(&c->list);
+	c->target_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+	c->default_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+	c->no_constraint_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+	c->type = PM_QOS_MIN;
+	c->notifiers = &qos->max_freq_notifiers;
+	BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers);
+}
+
+/**
+ * freq_qos_read_value - Get frequency QoS constraint for a given list.
+ * @qos: Constraints to evaluate.
+ * @type: QoS request type.
+ */
+s32 freq_qos_read_value(struct freq_constraints *qos,
+			enum freq_qos_req_type type)
+{
+	s32 ret;
+
+	switch (type) {
+	case FREQ_QOS_MIN:
+		ret = IS_ERR_OR_NULL(qos) ?
+			FREQ_QOS_MIN_DEFAULT_VALUE :
+			pm_qos_read_value(&qos->min_freq);
+		break;
+	case FREQ_QOS_MAX:
+		ret = IS_ERR_OR_NULL(qos) ?
+			FREQ_QOS_MAX_DEFAULT_VALUE :
+			pm_qos_read_value(&qos->max_freq);
+		break;
+	default:
+		WARN_ON(1);
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * freq_qos_apply - Add/modify/remove frequency QoS request.
+ * @req: Constraint request to apply.
+ * @action: Action to perform (add/update/remove).
+ * @value: Value to assign to the QoS request.
+ *
+ * This is only meant to be called from inside pm_qos, not drivers.
+ */
+int freq_qos_apply(struct freq_qos_request *req,
+			  enum pm_qos_req_action action, s32 value)
+{
+	int ret;
+
+	switch(req->type) {
+	case FREQ_QOS_MIN:
+		ret = pm_qos_update_target(&req->qos->min_freq, &req->pnode,
+					   action, value);
+		break;
+	case FREQ_QOS_MAX:
+		ret = pm_qos_update_target(&req->qos->max_freq, &req->pnode,
+					   action, value);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/**
+ * freq_qos_add_request - Insert new frequency QoS request into a given list.
+ * @qos: Constraints to update.
+ * @req: Preallocated request object.
+ * @type: Request type.
+ * @value: Request value.
+ *
+ * Insert a new entry into the @qos list of requests, recompute the effective
+ * QoS constraint value for that list and initialize the @req object.  The
+ * caller needs to save that object for later use in updates and removal.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_add_request(struct freq_constraints *qos,
+			 struct freq_qos_request *req,
+			 enum freq_qos_req_type type, s32 value)
+{
+	int ret;
+
+	if (IS_ERR_OR_NULL(qos) || !req || freq_qos_value_invalid(value))
+		return -EINVAL;
+
+	if (WARN(freq_qos_request_active(req),
+		 "%s() called for active request\n", __func__))
+		return -EINVAL;
+
+	req->qos = qos;
+	req->type = type;
+	ret = freq_qos_apply(req, PM_QOS_ADD_REQ, value);
+	if (ret < 0) {
+		req->qos = NULL;
+		req->type = 0;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_add_request);
+
+/**
+ * freq_qos_update_request - Modify existing frequency QoS request.
+ * @req: Request to modify.
+ * @new_value: New request value.
+ *
+ * Update an existing frequency QoS request along with the effective constraint
+ * value for the list of requests it belongs to.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_update_request(struct freq_qos_request *req, s32 new_value)
+{
+	if (!req || freq_qos_value_invalid(new_value))
+		return -EINVAL;
+
+	if (WARN(!freq_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	if (req->pnode.prio == new_value)
+		return 0;
+
+	return freq_qos_apply(req, PM_QOS_UPDATE_REQ, new_value);
+}
+EXPORT_SYMBOL_GPL(freq_qos_update_request);
+
+/**
+ * freq_qos_remove_request - Remove frequency QoS request from its list.
+ * @req: Request to remove.
+ *
+ * Remove the given frequency QoS request from the list of constraints it
+ * belongs to and recompute the effective constraint value for that list.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_remove_request(struct freq_qos_request *req)
+{
+	int ret;
+
+	if (!req)
+		return -EINVAL;
+
+	if (WARN(!freq_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	ret = freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+	req->qos = NULL;
+	req->type = 0;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_remove_request);
+
+/**
+ * freq_qos_add_notifier - Add frequency QoS change notifier.
+ * @qos: List of requests to add the notifier to.
+ * @type: Request type.
+ * @notifier: Notifier block to add.
+ */
+int freq_qos_add_notifier(struct freq_constraints *qos,
+			  enum freq_qos_req_type type,
+			  struct notifier_block *notifier)
+{
+	int ret;
+
+	if (IS_ERR_OR_NULL(qos) || !notifier)
+		return -EINVAL;
+
+	switch (type) {
+	case FREQ_QOS_MIN:
+		ret = blocking_notifier_chain_register(qos->min_freq.notifiers,
+						       notifier);
+		break;
+	case FREQ_QOS_MAX:
+		ret = blocking_notifier_chain_register(qos->max_freq.notifiers,
+						       notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_add_notifier);
+
+/**
+ * freq_qos_remove_notifier - Remove frequency QoS change notifier.
+ * @qos: List of requests to remove the notifier from.
+ * @type: Request type.
+ * @notifier: Notifier block to remove.
+ */
+int freq_qos_remove_notifier(struct freq_constraints *qos,
+			     enum freq_qos_req_type type,
+			     struct notifier_block *notifier)
+{
+	int ret;
+
+	if (IS_ERR_OR_NULL(qos) || !notifier)
+		return -EINVAL;
+
+	switch (type) {
+	case FREQ_QOS_MIN:
+		ret = blocking_notifier_chain_unregister(qos->min_freq.notifiers,
+							 notifier);
+		break;
+	case FREQ_QOS_MAX:
+		ret = blocking_notifier_chain_unregister(qos->max_freq.notifiers,
+							 notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_remove_notifier);

linux-7.2.3/kernel/power/suspend.c

@@ -0,0 +1,649 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kernel/power/suspend.c - Suspend to RAM and standby functionality.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+ */
+
+#define pr_fmt(fmt) "PM: " fmt
+
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/gfp.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/suspend.h>
+#include <linux/syscore_ops.h>
+#include <linux/swait.h>
+#include <linux/ftrace.h>
+#include <trace/events/power.h>
+#include <linux/compiler.h>
+#include <linux/moduleparam.h>
+#include <linux/fs.h>
+
+#include "power.h"
+
+const char * const pm_labels[] = {
+	[PM_SUSPEND_TO_IDLE] = "freeze",
+	[PM_SUSPEND_STANDBY] = "standby",
+	[PM_SUSPEND_MEM] = "mem",
+};
+const char *pm_states[PM_SUSPEND_MAX];
+static const char * const mem_sleep_labels[] = {
+	[PM_SUSPEND_TO_IDLE] = "s2idle",
+	[PM_SUSPEND_STANDBY] = "shallow",
+	[PM_SUSPEND_MEM] = "deep",
+};
+const char *mem_sleep_states[PM_SUSPEND_MAX];
+
+suspend_state_t mem_sleep_current = PM_SUSPEND_TO_IDLE;
+suspend_state_t mem_sleep_default = PM_SUSPEND_MAX;
+suspend_state_t pm_suspend_target_state;
+EXPORT_SYMBOL_GPL(pm_suspend_target_state);
+
+unsigned int pm_suspend_global_flags;
+EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
+
+static const struct platform_suspend_ops *suspend_ops;
+static const struct platform_s2idle_ops *s2idle_ops;
+static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head);
+
+enum s2idle_states __read_mostly s2idle_state;
+static DEFINE_RAW_SPINLOCK(s2idle_lock);
+
+/**
+ * pm_suspend_default_s2idle - Check if suspend-to-idle is the default suspend.
+ *
+ * Return 'true' if suspend-to-idle has been selected as the default system
+ * suspend method.
+ */
+bool pm_suspend_default_s2idle(void)
+{
+	return mem_sleep_current == PM_SUSPEND_TO_IDLE;
+}
+EXPORT_SYMBOL_GPL(pm_suspend_default_s2idle);
+
+void s2idle_set_ops(const struct platform_s2idle_ops *ops)
+{
+	unsigned int sleep_flags;
+
+	sleep_flags = lock_system_sleep();
+	s2idle_ops = ops;
+	unlock_system_sleep(sleep_flags);
+}
+
+static void s2idle_begin(void)
+{
+	s2idle_state = S2IDLE_STATE_NONE;
+}
+
+static void s2idle_enter(void)
+{
+	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, true);
+
+	/*
+	 * The correctness of the code below depends on the number of online
+	 * CPUs being stable, but CPUs cannot be taken offline or put online
+	 * while it is running.
+	 *
+	 * The s2idle_lock must be acquired before the pending wakeup check to
+	 * prevent pm_system_wakeup() from running as a whole between that check
+	 * and the subsequent s2idle_state update in which case a wakeup event
+	 * would get lost.
+	 */
+	raw_spin_lock_irq(&s2idle_lock);
+	if (pm_wakeup_pending())
+		goto out;
+
+	s2idle_state = S2IDLE_STATE_ENTER;
+	raw_spin_unlock_irq(&s2idle_lock);
+
+	/* Push all the CPUs into the idle loop. */
+	wake_up_all_idle_cpus();
+	/* Make the current CPU wait so it can enter the idle loop too. */
+	swait_event_exclusive(s2idle_wait_head,
+		    s2idle_state == S2IDLE_STATE_WAKE);
+
+	/*
+	 * Kick all CPUs to ensure that they resume their timers and restore
+	 * consistent system state.
+	 */
+	wake_up_all_idle_cpus();
+
+	raw_spin_lock_irq(&s2idle_lock);
+
+ out:
+	s2idle_state = S2IDLE_STATE_NONE;
+	raw_spin_unlock_irq(&s2idle_lock);
+
+	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_TO_IDLE, false);
+}
+
+static void s2idle_loop(void)
+{
+	pm_pr_dbg("suspend-to-idle\n");
+
+	/*
+	 * Suspend-to-idle equals:
+	 * frozen processes + suspended devices + idle processors.
+	 * Thus s2idle_enter() should be called right after all devices have
+	 * been suspended.
+	 *
+	 * Wakeups during the noirq suspend of devices may be spurious, so try
+	 * to avoid them upfront.
+	 */
+	for (;;) {
+		if (s2idle_ops && s2idle_ops->wake) {
+			if (s2idle_ops->wake())
+				break;
+		} else if (pm_wakeup_pending()) {
+			break;
+		}
+
+		if (s2idle_ops && s2idle_ops->check)
+			s2idle_ops->check();
+
+		s2idle_enter();
+	}
+
+	pm_pr_dbg("resume from suspend-to-idle\n");
+}
+
+void s2idle_wake(void)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&s2idle_lock, flags);
+	if (s2idle_state > S2IDLE_STATE_NONE) {
+		s2idle_state = S2IDLE_STATE_WAKE;
+		swake_up_one(&s2idle_wait_head);
+	}
+	raw_spin_unlock_irqrestore(&s2idle_lock, flags);
+}
+EXPORT_SYMBOL_GPL(s2idle_wake);
+
+static bool valid_state(suspend_state_t state)
+{
+	/*
+	 * The PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states require low-level
+	 * support and need to be valid to the low-level implementation.
+	 *
+	 * No ->valid() or ->enter() callback implies that none are valid.
+	 */
+	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state) &&
+		suspend_ops->enter;
+}
+
+void __init pm_states_init(void)
+{
+	/* "mem" and "freeze" are always present in /sys/power/state. */
+	pm_states[PM_SUSPEND_MEM] = pm_labels[PM_SUSPEND_MEM];
+	pm_states[PM_SUSPEND_TO_IDLE] = pm_labels[PM_SUSPEND_TO_IDLE];
+	/*
+	 * Suspend-to-idle should be supported even without any suspend_ops,
+	 * initialize mem_sleep_states[] accordingly here.
+	 */
+	mem_sleep_states[PM_SUSPEND_TO_IDLE] = mem_sleep_labels[PM_SUSPEND_TO_IDLE];
+}
+
+static int __init mem_sleep_default_setup(char *str)
+{
+	suspend_state_t state;
+
+	for (state = PM_SUSPEND_TO_IDLE; state <= PM_SUSPEND_MEM; state++)
+		if (mem_sleep_labels[state] &&
+		    !strcmp(str, mem_sleep_labels[state])) {
+			mem_sleep_default = state;
+			mem_sleep_current = state;
+			break;
+		}
+
+	return 1;
+}
+__setup("mem_sleep_default=", mem_sleep_default_setup);
+
+/**
+ * suspend_set_ops - Set the global suspend method table.
+ * @ops: Suspend operations to use.
+ */
+void suspend_set_ops(const struct platform_suspend_ops *ops)
+{
+	unsigned int sleep_flags;
+
+	sleep_flags = lock_system_sleep();
+
+	suspend_ops = ops;
+
+	if (valid_state(PM_SUSPEND_STANDBY)) {
+		mem_sleep_states[PM_SUSPEND_STANDBY] = mem_sleep_labels[PM_SUSPEND_STANDBY];
+		pm_states[PM_SUSPEND_STANDBY] = pm_labels[PM_SUSPEND_STANDBY];
+		if (mem_sleep_default == PM_SUSPEND_STANDBY)
+			mem_sleep_current = PM_SUSPEND_STANDBY;
+	}
+	if (valid_state(PM_SUSPEND_MEM)) {
+		mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
+		if (mem_sleep_default >= PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_MEM;
+	}
+
+	unlock_system_sleep(sleep_flags);
+}
+EXPORT_SYMBOL_GPL(suspend_set_ops);
+
+/**
+ * suspend_valid_only_mem - Generic memory-only valid callback.
+ * @state: Target system sleep state.
+ *
+ * Platform drivers that implement mem suspend only and only need to check for
+ * that in their .valid() callback can use this instead of rolling their own
+ * .valid() callback.
+ */
+int suspend_valid_only_mem(suspend_state_t state)
+{
+	return state == PM_SUSPEND_MEM;
+}
+EXPORT_SYMBOL_GPL(suspend_valid_only_mem);
+
+static bool sleep_state_supported(suspend_state_t state)
+{
+	return state == PM_SUSPEND_TO_IDLE ||
+	       (valid_state(state) && !cxl_mem_active());
+}
+
+static int platform_suspend_prepare(suspend_state_t state)
+{
+	return state != PM_SUSPEND_TO_IDLE && suspend_ops->prepare ?
+		suspend_ops->prepare() : 0;
+}
+
+static int platform_suspend_prepare_late(suspend_state_t state)
+{
+	return state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->prepare ?
+		s2idle_ops->prepare() : 0;
+}
+
+static int platform_suspend_prepare_noirq(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_TO_IDLE)
+		return s2idle_ops && s2idle_ops->prepare_late ?
+			s2idle_ops->prepare_late() : 0;
+
+	return suspend_ops->prepare_late ? suspend_ops->prepare_late() : 0;
+}
+
+static void platform_resume_noirq(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_TO_IDLE) {
+		if (s2idle_ops && s2idle_ops->restore_early)
+			s2idle_ops->restore_early();
+	} else if (suspend_ops->wake) {
+		suspend_ops->wake();
+	}
+}
+
+static void platform_resume_early(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->restore)
+		s2idle_ops->restore();
+}
+
+static void platform_resume_finish(suspend_state_t state)
+{
+	if (state != PM_SUSPEND_TO_IDLE && suspend_ops->finish)
+		suspend_ops->finish();
+}
+
+static int platform_suspend_begin(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->begin)
+		return s2idle_ops->begin();
+	else if (suspend_ops && suspend_ops->begin)
+		return suspend_ops->begin(state);
+	else
+		return 0;
+}
+
+static void platform_resume_end(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_TO_IDLE && s2idle_ops && s2idle_ops->end)
+		s2idle_ops->end();
+	else if (suspend_ops && suspend_ops->end)
+		suspend_ops->end();
+}
+
+static void platform_recover(suspend_state_t state)
+{
+	if (state != PM_SUSPEND_TO_IDLE && suspend_ops->recover)
+		suspend_ops->recover();
+}
+
+static bool platform_suspend_again(suspend_state_t state)
+{
+	return state != PM_SUSPEND_TO_IDLE && suspend_ops->suspend_again ?
+		suspend_ops->suspend_again() : false;
+}
+
+#ifdef CONFIG_PM_DEBUG
+static unsigned int pm_test_delay = 5;
+module_param(pm_test_delay, uint, 0644);
+MODULE_PARM_DESC(pm_test_delay,
+		 "Number of seconds to wait before resuming from suspend test");
+#endif
+
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+	int i;
+
+	if (pm_test_level == level) {
+		pr_info("suspend debug: Waiting for %d second(s).\n",
+				pm_test_delay);
+		for (i = 0; i < pm_test_delay && !pm_wakeup_pending(); i++) {
+			if (level > TEST_CORE)
+				msleep(1000);
+			else
+				mdelay(1000);
+		}
+		return 1;
+	}
+#endif /* !CONFIG_PM_DEBUG */
+	return 0;
+}
+
+/**
+ * suspend_prepare - Prepare for entering system sleep state.
+ * @state: Target system sleep state.
+ *
+ * Common code run for every system sleep state that can be entered (except for
+ * hibernation).  Run suspend notifiers, allocate the "suspend" console and
+ * freeze processes.
+ */
+static int suspend_prepare(suspend_state_t state)
+{
+	int error;
+
+	if (!sleep_state_supported(state))
+		return -EPERM;
+
+	pm_prepare_console();
+
+	error = pm_notifier_call_chain_robust(PM_SUSPEND_PREPARE, PM_POST_SUSPEND);
+	if (error)
+		goto Restore;
+
+	filesystems_freeze(filesystem_freeze_enabled);
+	trace_suspend_resume(TPS("freeze_processes"), 0, true);
+	error = suspend_freeze_processes();
+	trace_suspend_resume(TPS("freeze_processes"), 0, false);
+	if (!error)
+		return 0;
+
+	dpm_save_failed_step(SUSPEND_FREEZE);
+	filesystems_thaw();
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+ Restore:
+	pm_restore_console();
+	return error;
+}
+
+/* default implementation */
+void __weak arch_suspend_disable_irqs(void)
+{
+	local_irq_disable();
+}
+
+/* default implementation */
+void __weak arch_suspend_enable_irqs(void)
+{
+	local_irq_enable();
+}
+
+/**
+ * suspend_enter - Make the system enter the given sleep state.
+ * @state: System sleep state to enter.
+ * @wakeup: Returns information that the sleep state should not be re-entered.
+ *
+ * This function should be called after devices have been suspended.
+ */
+static int suspend_enter(suspend_state_t state, bool *wakeup)
+{
+	int error;
+
+	error = platform_suspend_prepare(state);
+	if (error)
+		goto Platform_finish;
+
+	error = dpm_suspend_late(PMSG_SUSPEND);
+	if (error) {
+		pr_err("late suspend of devices failed\n");
+		goto Platform_finish;
+	}
+	error = platform_suspend_prepare_late(state);
+	if (error)
+		goto Devices_early_resume;
+
+	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	if (error) {
+		pr_err("noirq suspend of devices failed\n");
+		goto Platform_early_resume;
+	}
+	error = platform_suspend_prepare_noirq(state);
+	if (error)
+		goto Platform_wake;
+
+	if (suspend_test(TEST_PLATFORM))
+		goto Platform_wake;
+
+	if (state == PM_SUSPEND_TO_IDLE) {
+		s2idle_loop();
+		goto Platform_wake;
+	}
+
+	error = pm_sleep_disable_secondary_cpus();
+	if (error || suspend_test(TEST_CPUS))
+		goto Enable_cpus;
+
+	arch_suspend_disable_irqs();
+	BUG_ON(!irqs_disabled());
+
+	system_state = SYSTEM_SUSPEND;
+
+	error = syscore_suspend();
+	if (!error) {
+		*wakeup = pm_wakeup_pending();
+		if (!(suspend_test(TEST_CORE) || *wakeup)) {
+			trace_suspend_resume(TPS("machine_suspend"),
+				state, true);
+			error = suspend_ops->enter(state);
+			trace_suspend_resume(TPS("machine_suspend"),
+				state, false);
+		} else if (*wakeup) {
+			error = -EBUSY;
+		}
+		syscore_resume();
+	}
+
+	system_state = SYSTEM_RUNNING;
+
+	arch_suspend_enable_irqs();
+	BUG_ON(irqs_disabled());
+
+ Enable_cpus:
+	pm_sleep_enable_secondary_cpus();
+
+ Platform_wake:
+	platform_resume_noirq(state);
+	dpm_resume_noirq(PMSG_RESUME);
+
+ Platform_early_resume:
+	platform_resume_early(state);
+
+ Devices_early_resume:
+	dpm_resume_early(PMSG_RESUME);
+
+ Platform_finish:
+	platform_resume_finish(state);
+	return error;
+}
+
+/**
+ * suspend_devices_and_enter - Suspend devices and enter system sleep state.
+ * @state: System sleep state to enter.
+ */
+int suspend_devices_and_enter(suspend_state_t state)
+{
+	int error;
+	bool wakeup = false;
+
+	if (!sleep_state_supported(state))
+		return -ENOSYS;
+
+	pm_suspend_target_state = state;
+
+	if (state == PM_SUSPEND_TO_IDLE)
+		pm_set_suspend_no_platform();
+
+	error = platform_suspend_begin(state);
+	if (error)
+		goto Close;
+
+	console_suspend_all();
+	suspend_test_start();
+	error = dpm_suspend_start(PMSG_SUSPEND);
+	if (error) {
+		pr_err("Some devices failed to suspend, or early wake event detected\n");
+		goto Recover_platform;
+	}
+	suspend_test_finish("suspend devices");
+	if (suspend_test(TEST_DEVICES))
+		goto Recover_platform;
+
+	do {
+		error = suspend_enter(state, &wakeup);
+	} while (!error && !wakeup && platform_suspend_again(state));
+
+ Resume_devices:
+	suspend_test_start();
+	dpm_resume_end(PMSG_RESUME);
+	suspend_test_finish("resume devices");
+	trace_suspend_resume(TPS("console_resume_all"), state, true);
+	console_resume_all();
+	trace_suspend_resume(TPS("console_resume_all"), state, false);
+
+ Close:
+	platform_resume_end(state);
+	pm_suspend_target_state = PM_SUSPEND_ON;
+	return error;
+
+ Recover_platform:
+	platform_recover(state);
+	goto Resume_devices;
+}
+
+/**
+ * suspend_finish - Clean up before finishing the suspend sequence.
+ *
+ * Call platform code to clean up, restart processes, and free the console that
+ * we've allocated. This routine is not called for hibernation.
+ */
+static void suspend_finish(void)
+{
+	suspend_thaw_processes();
+	filesystems_thaw();
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+	pm_restore_console();
+}
+
+/**
+ * enter_state - Do common work needed to enter system sleep state.
+ * @state: System sleep state to enter.
+ *
+ * Make sure that no one else is trying to put the system into a sleep state.
+ * Fail if that's not the case.  Otherwise, prepare for system suspend, make the
+ * system enter the given sleep state and clean up after wakeup.
+ */
+static int enter_state(suspend_state_t state)
+{
+	int error;
+
+	trace_suspend_resume(TPS("suspend_enter"), state, true);
+	if (state == PM_SUSPEND_TO_IDLE) {
+#ifdef CONFIG_PM_DEBUG
+		if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
+			pr_warn("Unsupported test mode for suspend to idle, please choose none/freezer/devices/platform.\n");
+			return -EAGAIN;
+		}
+#endif
+	} else if (!valid_state(state)) {
+		return -EINVAL;
+	}
+	if (!mutex_trylock(&system_transition_mutex))
+		return -EBUSY;
+
+	if (state == PM_SUSPEND_TO_IDLE)
+		s2idle_begin();
+
+	if (sync_on_suspend_enabled) {
+		trace_suspend_resume(TPS("sync_filesystems"), 0, true);
+
+		error = pm_sleep_fs_sync();
+		if (error)
+			goto Unlock;
+
+		trace_suspend_resume(TPS("sync_filesystems"), 0, false);
+	}
+
+	pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
+	pm_suspend_clear_flags();
+	error = suspend_prepare(state);
+	if (error)
+		goto Unlock;
+
+	if (suspend_test(TEST_FREEZER))
+		goto Finish;
+
+	trace_suspend_resume(TPS("suspend_enter"), state, false);
+	pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]);
+	error = suspend_devices_and_enter(state);
+
+ Finish:
+	events_check_enabled = false;
+	pm_pr_dbg("Finishing wakeup.\n");
+	suspend_finish();
+ Unlock:
+	mutex_unlock(&system_transition_mutex);
+	return error;
+}
+
+/**
+ * pm_suspend - Externally visible function for suspending the system.
+ * @state: System sleep state to enter.
+ *
+ * Check if the value of @state represents one of the supported states,
+ * execute enter_state() and update system suspend statistics.
+ */
+int pm_suspend(suspend_state_t state)
+{
+	int error;
+
+	if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
+		return -EINVAL;
+
+	pr_info("suspend entry (%s)\n", mem_sleep_labels[state]);
+	error = enter_state(state);
+	dpm_save_errno(error);
+	pr_info("suspend exit\n");
+	return error;
+}
+EXPORT_SYMBOL(pm_suspend);

linux-7.2.3/kernel/power/suspend_test.c

@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * kernel/power/suspend_test.c - Suspend to RAM and standby test facility.
+ *
+ * Copyright (c) 2009 Pavel Machek <pavel@ucw.cz>
+ */
+
+#include <linux/init.h>
+#include <linux/rtc.h>
+
+#include "power.h"
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending.  Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS	10
+
+static unsigned long suspend_test_start_time;
+static u32 test_repeat_count_max = 1;
+static u32 test_repeat_count_current;
+
+void suspend_test_start(void)
+{
+	/* FIXME Use better timebase than "jiffies", ideally a clocksource.
+	 * What we want is a hardware counter that will work correctly even
+	 * during the irqs-are-off stages of the suspend/resume cycle...
+	 */
+	suspend_test_start_time = jiffies;
+}
+
+void suspend_test_finish(const char *label)
+{
+	long nj = jiffies - suspend_test_start_time;
+	unsigned msec;
+
+	msec = jiffies_to_msecs(abs(nj));
+	pr_info("PM: %s took %d.%03d seconds\n", label,
+			msec / 1000, msec % 1000);
+
+	/* Warning on suspend means the RTC alarm period needs to be
+	 * larger -- the system was sooo slooowwww to suspend that the
+	 * alarm (should have) fired before the system went to sleep!
+	 *
+	 * Warning on either suspend or resume also means the system
+	 * has some performance issues.  The stack dump of a WARN_ON
+	 * is more likely to get the right attention than a printk...
+	 */
+	WARN(msec > (TEST_SUSPEND_SECONDS * 1000),
+	     "Component: %s, time: %u\n", label, msec);
+}
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system.  RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+	static char err_readtime[] __initdata =
+		KERN_ERR "PM: can't read %s time, err %d\n";
+	static char err_wakealarm [] __initdata =
+		KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+	static char err_suspend[] __initdata =
+		KERN_ERR "PM: suspend test failed, error %d\n";
+	static char info_test[] __initdata =
+		KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+	time64_t		now;
+	struct rtc_wkalrm	alm;
+	int			status;
+
+	/* this may fail if the RTC hasn't been initialized */
+repeat:
+	status = rtc_read_time(rtc, &alm.time);
+	if (status < 0) {
+		printk(err_readtime, dev_name(&rtc->dev), status);
+		return;
+	}
+	now = rtc_tm_to_time64(&alm.time);
+
+	memset(&alm, 0, sizeof alm);
+	rtc_time64_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+	alm.enabled = true;
+
+	status = rtc_set_alarm(rtc, &alm);
+	if (status < 0) {
+		printk(err_wakealarm, dev_name(&rtc->dev), status);
+		return;
+	}
+
+	if (state == PM_SUSPEND_MEM) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+		if (status == -ENODEV)
+			state = PM_SUSPEND_STANDBY;
+	}
+	if (state == PM_SUSPEND_STANDBY) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+		if (status < 0)
+			state = PM_SUSPEND_TO_IDLE;
+	}
+	if (state == PM_SUSPEND_TO_IDLE) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+	}
+
+	if (status < 0)
+		printk(err_suspend, status);
+
+	test_repeat_count_current++;
+	if (test_repeat_count_current < test_repeat_count_max)
+		goto repeat;
+
+	/* Some platforms can't detect that the alarm triggered the
+	 * wakeup, or (accordingly) disable it after it afterwards.
+	 * It's supposed to give oneshot behavior; cope.
+	 */
+	alm.enabled = false;
+	rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, const void *data)
+{
+	struct rtc_device *candidate = to_rtc_device(dev);
+
+	if (!test_bit(RTC_FEATURE_ALARM, candidate->features))
+		return 0;
+	if (!device_may_wakeup(candidate->dev.parent))
+		return 0;
+
+	return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time.  They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static const char *test_state_label __initdata;
+
+static char warn_bad_state[] __initdata =
+	KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+	int i;
+	char *repeat;
+	char *suspend_type;
+
+	/* example : "=mem[,N]" ==> "mem[,N]" */
+	value++;
+	suspend_type = strsep(&value, ",");
+	if (!suspend_type)
+		return 1;
+
+	repeat = strsep(&value, ",");
+	if (repeat) {
+		if (kstrtou32(repeat, 0, &test_repeat_count_max))
+			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 1;
+		}
+
+	printk(warn_bad_state, suspend_type);
+	return 1;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+	static char		warn_no_rtc[] __initdata =
+		KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+	struct rtc_device	*rtc = NULL;
+	struct device		*dev;
+	suspend_state_t test_state;
+
+	/* PM is initialized by now; is that state testable? */
+	if (!test_state_label)
+		return 0;
+
+	for (test_state = PM_SUSPEND_MIN; test_state < PM_SUSPEND_MAX; test_state++) {
+		const char *state_label = pm_states[test_state];
+
+		if (state_label && !strcmp(test_state_label, state_label))
+			break;
+	}
+	if (test_state == PM_SUSPEND_MAX) {
+		printk(warn_bad_state, test_state_label);
+		return 0;
+	}
+
+	/* RTCs have initialized by now too ... can we use one? */
+	dev = class_find_device(&rtc_class, NULL, NULL, has_wakealarm);
+	if (dev) {
+		rtc = rtc_class_open(dev_name(dev));
+		put_device(dev);
+	}
+	if (!rtc) {
+		printk(warn_no_rtc);
+		return 0;
+	}
+
+	/* go for it */
+	test_wakealarm(rtc, test_state);
+	rtc_class_close(rtc);
+	return 0;
+}
+late_initcall(test_suspend);

linux-7.2.3/kernel/power/user.c

@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/kernel/power/user.c
+ *
+ * This file provides the user space interface for software suspend/resume.
+ *
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#include <linux/suspend.h>
+#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/device.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/pm.h>
+#include <linux/fs.h>
+#include <linux/compat.h>
+#include <linux/console.h>
+#include <linux/cpu.h>
+#include <linux/freezer.h>
+
+#include <linux/uaccess.h>
+
+#include "power.h"
+
+static bool need_wait;
+
+static struct snapshot_data {
+	struct snapshot_handle handle;
+	int swap;
+	int mode;
+	bool frozen;
+	bool ready;
+	bool platform_support;
+	bool free_bitmaps;
+	dev_t dev;
+} snapshot_state;
+
+int is_hibernate_resume_dev(dev_t dev)
+{
+	return hibernation_available() && snapshot_state.dev == dev;
+}
+
+static int snapshot_open(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+	unsigned int sleep_flags;
+	int error;
+
+	if (!hibernation_available())
+		return -EPERM;
+
+	sleep_flags = lock_system_sleep();
+
+	if (!hibernate_acquire()) {
+		error = -EBUSY;
+		goto Unlock;
+	}
+
+	if ((filp->f_flags & O_ACCMODE) == O_RDWR) {
+		hibernate_release();
+		error = -ENOSYS;
+		goto Unlock;
+	}
+	nonseekable_open(inode, filp);
+	data = &snapshot_state;
+	filp->private_data = data;
+	memset(&data->handle, 0, sizeof(struct snapshot_handle));
+	if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
+		/* Hibernating.  The image device should be accessible. */
+		data->swap = pin_hibernation_swap_type(swsusp_resume_device, 0);
+		data->mode = O_RDONLY;
+		data->free_bitmaps = false;
+		error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
+	} else {
+		/*
+		 * Resuming.  We may need to wait for the image device to
+		 * appear.
+		 */
+		need_wait = true;
+
+		data->swap = -1;
+		data->mode = O_WRONLY;
+		error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE);
+		if (!error) {
+			error = create_basic_memory_bitmaps();
+			data->free_bitmaps = !error;
+		}
+	}
+	if (error) {
+		unpin_hibernation_swap_type(data->swap);
+		hibernate_release();
+	}
+
+	data->frozen = false;
+	data->ready = false;
+	data->platform_support = false;
+	data->dev = 0;
+
+ Unlock:
+	unlock_system_sleep(sleep_flags);
+
+	return error;
+}
+
+static int snapshot_release(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+	unsigned int sleep_flags;
+
+	sleep_flags = lock_system_sleep();
+
+	swsusp_free();
+	data = filp->private_data;
+	data->dev = 0;
+	free_all_swap_pages(data->swap);
+	unpin_hibernation_swap_type(data->swap);
+	if (data->frozen) {
+		pm_restore_gfp_mask();
+		free_basic_memory_bitmaps();
+		thaw_processes();
+	} else if (data->free_bitmaps) {
+		free_basic_memory_bitmaps();
+	}
+	pm_notifier_call_chain(data->mode == O_RDONLY ?
+			PM_POST_HIBERNATION : PM_POST_RESTORE);
+	hibernate_release();
+
+	unlock_system_sleep(sleep_flags);
+
+	return 0;
+}
+
+static ssize_t snapshot_read(struct file *filp, char __user *buf,
+                             size_t count, loff_t *offp)
+{
+	loff_t pg_offp = *offp & ~PAGE_MASK;
+	struct snapshot_data *data;
+	unsigned int sleep_flags;
+	ssize_t res;
+
+	sleep_flags = lock_system_sleep();
+
+	data = filp->private_data;
+	if (!data->ready) {
+		res = -ENODATA;
+		goto Unlock;
+	}
+	if (!pg_offp) { /* on page boundary? */
+		res = snapshot_read_next(&data->handle);
+		if (res <= 0)
+			goto Unlock;
+	} else {
+		res = PAGE_SIZE - pg_offp;
+	}
+
+	res = simple_read_from_buffer(buf, count, &pg_offp,
+			data_of(data->handle), res);
+	if (res > 0)
+		*offp += res;
+
+ Unlock:
+	unlock_system_sleep(sleep_flags);
+
+	return res;
+}
+
+static ssize_t snapshot_write(struct file *filp, const char __user *buf,
+                              size_t count, loff_t *offp)
+{
+	loff_t pg_offp = *offp & ~PAGE_MASK;
+	struct snapshot_data *data;
+	unsigned long sleep_flags;
+	ssize_t res;
+
+	if (need_wait) {
+		wait_for_device_probe();
+		need_wait = false;
+	}
+
+	sleep_flags = lock_system_sleep();
+
+	data = filp->private_data;
+
+	if (!pg_offp) {
+		res = snapshot_write_next(&data->handle);
+		if (res <= 0)
+			goto unlock;
+	} else {
+		res = PAGE_SIZE;
+	}
+
+	if (!data_of(data->handle)) {
+		res = -EINVAL;
+		goto unlock;
+	}
+
+	res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
+			buf, count);
+	if (res > 0)
+		*offp += res;
+unlock:
+	unlock_system_sleep(sleep_flags);
+
+	return res;
+}
+
+struct compat_resume_swap_area {
+	compat_loff_t offset;
+	u32 dev;
+} __packed;
+
+static int snapshot_set_swap_area(struct snapshot_data *data,
+		void __user *argp)
+{
+	sector_t offset;
+	dev_t swdev;
+
+	if (swsusp_swap_in_use())
+		return -EPERM;
+
+	if (in_compat_syscall()) {
+		struct compat_resume_swap_area swap_area;
+
+		if (copy_from_user(&swap_area, argp, sizeof(swap_area)))
+			return -EFAULT;
+		swdev = new_decode_dev(swap_area.dev);
+		offset = swap_area.offset;
+	} else {
+		struct resume_swap_area swap_area;
+
+		if (copy_from_user(&swap_area, argp, sizeof(swap_area)))
+			return -EFAULT;
+		swdev = new_decode_dev(swap_area.dev);
+		offset = swap_area.offset;
+	}
+
+	/*
+	 * Unpin the swap device if a swap area was already
+	 * set by SNAPSHOT_SET_SWAP_AREA.
+	 */
+	unpin_hibernation_swap_type(data->swap);
+
+	/*
+	 * User space encodes device types as two-byte values,
+	 * so we need to recode them
+	 */
+	data->swap = pin_hibernation_swap_type(swdev, offset);
+	if (data->swap < 0)
+		return swdev ? -ENODEV : -EINVAL;
+	data->dev = swdev;
+	return 0;
+}
+
+static long snapshot_ioctl(struct file *filp, unsigned int cmd,
+							unsigned long arg)
+{
+	int error = 0;
+	struct snapshot_data *data;
+	loff_t size;
+	sector_t offset;
+
+	if (need_wait) {
+		wait_for_device_probe();
+		need_wait = false;
+	}
+
+	if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC)
+		return -ENOTTY;
+	if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR)
+		return -ENOTTY;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!mutex_trylock(&system_transition_mutex))
+		return -EBUSY;
+
+	lock_device_hotplug();
+	data = filp->private_data;
+
+	switch (cmd) {
+
+	case SNAPSHOT_FREEZE:
+		if (data->frozen)
+			break;
+
+		error = pm_sleep_fs_sync();
+		if (error)
+			break;
+
+		error = freeze_processes();
+		if (error)
+			break;
+
+		error = create_basic_memory_bitmaps();
+		if (error)
+			thaw_processes();
+		else
+			data->frozen = true;
+
+		break;
+
+	case SNAPSHOT_UNFREEZE:
+		if (!data->frozen || data->ready)
+			break;
+		pm_restore_gfp_mask();
+		free_basic_memory_bitmaps();
+		data->free_bitmaps = false;
+		thaw_processes();
+		data->frozen = false;
+		break;
+
+	case SNAPSHOT_CREATE_IMAGE:
+		if (data->mode != O_RDONLY || !data->frozen  || data->ready) {
+			error = -EPERM;
+			break;
+		}
+		pm_restore_gfp_mask();
+		error = hibernation_snapshot(data->platform_support);
+		if (!error) {
+			error = put_user(in_suspend, (int __user *)arg);
+			data->ready = !freezer_test_done && !error;
+			freezer_test_done = false;
+		}
+		break;
+
+	case SNAPSHOT_ATOMIC_RESTORE:
+		error = snapshot_write_finalize(&data->handle);
+		if (error)
+			break;
+		if (data->mode != O_WRONLY || !data->frozen) {
+			error = -EPERM;
+			break;
+		}
+		if (!snapshot_image_loaded(&data->handle)) {
+			error = -ENODATA;
+			break;
+		}
+		error = hibernation_restore(data->platform_support);
+		break;
+
+	case SNAPSHOT_FREE:
+		swsusp_free();
+		memset(&data->handle, 0, sizeof(struct snapshot_handle));
+		data->ready = false;
+		/*
+		 * It is necessary to thaw kernel threads here, because
+		 * SNAPSHOT_CREATE_IMAGE may be invoked directly after
+		 * SNAPSHOT_FREE.  In that case, if kernel threads were not
+		 * thawed, the preallocation of memory carried out by
+		 * hibernation_snapshot() might run into problems (i.e. it
+		 * might fail or even deadlock).
+		 */
+		thaw_kernel_threads();
+		break;
+
+	case SNAPSHOT_PREF_IMAGE_SIZE:
+		image_size = arg;
+		break;
+
+	case SNAPSHOT_GET_IMAGE_SIZE:
+		if (!data->ready) {
+			error = -ENODATA;
+			break;
+		}
+		size = snapshot_get_image_size();
+		size <<= PAGE_SHIFT;
+		error = put_user(size, (loff_t __user *)arg);
+		break;
+
+	case SNAPSHOT_AVAIL_SWAP_SIZE:
+		size = count_swap_pages(data->swap, 1);
+		size <<= PAGE_SHIFT;
+		error = put_user(size, (loff_t __user *)arg);
+		break;
+
+	case SNAPSHOT_ALLOC_SWAP_PAGE:
+		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
+			error = -ENODEV;
+			break;
+		}
+		offset = alloc_swapdev_block(data->swap);
+		if (offset) {
+			offset <<= PAGE_SHIFT;
+			error = put_user(offset, (loff_t __user *)arg);
+		} else {
+			error = -ENOSPC;
+		}
+		break;
+
+	case SNAPSHOT_FREE_SWAP_PAGES:
+		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
+			error = -ENODEV;
+			break;
+		}
+		free_all_swap_pages(data->swap);
+		break;
+
+	case SNAPSHOT_S2RAM:
+		if (!data->frozen) {
+			error = -EPERM;
+			break;
+		}
+		/*
+		 * Tasks are frozen and the notifiers have been called with
+		 * PM_HIBERNATION_PREPARE
+		 */
+		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+		data->ready = false;
+		break;
+
+	case SNAPSHOT_PLATFORM_SUPPORT:
+		data->platform_support = !!arg;
+		break;
+
+	case SNAPSHOT_POWER_OFF:
+		if (data->platform_support)
+			error = hibernation_platform_enter();
+		break;
+
+	case SNAPSHOT_SET_SWAP_AREA:
+		error = snapshot_set_swap_area(data, (void __user *)arg);
+		break;
+
+	default:
+		error = -ENOTTY;
+
+	}
+
+	unlock_device_hotplug();
+	mutex_unlock(&system_transition_mutex);
+
+	return error;
+}
+
+#ifdef CONFIG_COMPAT
+static long
+snapshot_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	BUILD_BUG_ON(sizeof(loff_t) != sizeof(compat_loff_t));
+
+	switch (cmd) {
+	case SNAPSHOT_GET_IMAGE_SIZE:
+	case SNAPSHOT_AVAIL_SWAP_SIZE:
+	case SNAPSHOT_ALLOC_SWAP_PAGE:
+	case SNAPSHOT_CREATE_IMAGE:
+	case SNAPSHOT_SET_SWAP_AREA:
+		return snapshot_ioctl(file, cmd,
+				      (unsigned long) compat_ptr(arg));
+	default:
+		return snapshot_ioctl(file, cmd, arg);
+	}
+}
+#endif /* CONFIG_COMPAT */
+
+static const struct file_operations snapshot_fops = {
+	.open = snapshot_open,
+	.release = snapshot_release,
+	.read = snapshot_read,
+	.write = snapshot_write,
+	.unlocked_ioctl = snapshot_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = snapshot_compat_ioctl,
+#endif
+};
+
+static struct miscdevice snapshot_device = {
+	.minor = SNAPSHOT_MINOR,
+	.name = "snapshot",
+	.fops = &snapshot_fops,
+};
+
+static int __init snapshot_device_init(void)
+{
+	return misc_register(&snapshot_device);
+};
+
+device_initcall(snapshot_device_init);

linux-7.2.3/kernel/power/wakelock.c

@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kernel/power/wakelock.c
+ *
+ * User space wakeup sources support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This code is based on the analogous interface allowing user space to
+ * manipulate wakelocks on Android.
+ */
+
+#include <linux/capability.h>
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+#include "power.h"
+
+static DEFINE_MUTEX(wakelocks_lock);
+
+struct wakelock {
+	char			*name;
+	struct rb_node		node;
+	struct wakeup_source	*ws;
+#ifdef CONFIG_PM_WAKELOCKS_GC
+	struct list_head	lru;
+#endif
+};
+
+static struct rb_root wakelocks_tree = RB_ROOT;
+
+ssize_t pm_show_wakelocks(char *buf, bool show_active)
+{
+	struct rb_node *node;
+	struct wakelock *wl;
+	int len = 0;
+
+	mutex_lock(&wakelocks_lock);
+
+	for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) {
+		wl = rb_entry(node, struct wakelock, node);
+		if (wl->ws->active == show_active)
+			len += sysfs_emit_at(buf, len, "%s ", wl->name);
+	}
+
+	if (len > 0)
+		--len;
+
+	len += sysfs_emit_at(buf, len, "\n");
+
+	mutex_unlock(&wakelocks_lock);
+	return len;
+}
+
+#if CONFIG_PM_WAKELOCKS_LIMIT > 0
+static unsigned int number_of_wakelocks;
+
+static inline bool wakelocks_limit_exceeded(void)
+{
+	return number_of_wakelocks > CONFIG_PM_WAKELOCKS_LIMIT;
+}
+
+static inline void increment_wakelocks_number(void)
+{
+	number_of_wakelocks++;
+}
+
+static inline void decrement_wakelocks_number(void)
+{
+	number_of_wakelocks--;
+}
+#else /* CONFIG_PM_WAKELOCKS_LIMIT = 0 */
+static inline bool wakelocks_limit_exceeded(void) { return false; }
+static inline void increment_wakelocks_number(void) {}
+static inline void decrement_wakelocks_number(void) {}
+#endif /* CONFIG_PM_WAKELOCKS_LIMIT */
+
+#ifdef CONFIG_PM_WAKELOCKS_GC
+#define WL_GC_COUNT_MAX	100
+#define WL_GC_TIME_SEC	300
+
+static void __wakelocks_gc(struct work_struct *work);
+static LIST_HEAD(wakelocks_lru_list);
+static DECLARE_WORK(wakelock_work, __wakelocks_gc);
+static unsigned int wakelocks_gc_count;
+
+static inline void wakelocks_lru_add(struct wakelock *wl)
+{
+	list_add(&wl->lru, &wakelocks_lru_list);
+}
+
+static inline void wakelocks_lru_most_recent(struct wakelock *wl)
+{
+	list_move(&wl->lru, &wakelocks_lru_list);
+}
+
+static void __wakelocks_gc(struct work_struct *work)
+{
+	struct wakelock *wl, *aux;
+	ktime_t now;
+
+	mutex_lock(&wakelocks_lock);
+
+	now = ktime_get();
+	list_for_each_entry_safe_reverse(wl, aux, &wakelocks_lru_list, lru) {
+		u64 idle_time_ns;
+		bool active;
+
+		spin_lock_irq(&wl->ws->lock);
+		idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws->last_time));
+		active = wl->ws->active;
+		spin_unlock_irq(&wl->ws->lock);
+
+		if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC))
+			break;
+
+		if (!active) {
+			wakeup_source_unregister(wl->ws);
+			rb_erase(&wl->node, &wakelocks_tree);
+			list_del(&wl->lru);
+			kfree(wl->name);
+			kfree(wl);
+			decrement_wakelocks_number();
+		}
+	}
+	wakelocks_gc_count = 0;
+
+	mutex_unlock(&wakelocks_lock);
+}
+
+static void wakelocks_gc(void)
+{
+	if (++wakelocks_gc_count <= WL_GC_COUNT_MAX)
+		return;
+
+	schedule_work(&wakelock_work);
+}
+#else /* !CONFIG_PM_WAKELOCKS_GC */
+static inline void wakelocks_lru_add(struct wakelock *wl) {}
+static inline void wakelocks_lru_most_recent(struct wakelock *wl) {}
+static inline void wakelocks_gc(void) {}
+#endif /* !CONFIG_PM_WAKELOCKS_GC */
+
+static struct wakelock *wakelock_lookup_add(const char *name, size_t len,
+					    bool add_if_not_found)
+{
+	struct rb_node **node = &wakelocks_tree.rb_node;
+	struct rb_node *parent = *node;
+	struct wakelock *wl;
+
+	while (*node) {
+		int diff;
+
+		parent = *node;
+		wl = rb_entry(*node, struct wakelock, node);
+		diff = strncmp(name, wl->name, len);
+		if (diff == 0) {
+			if (wl->name[len])
+				diff = -1;
+			else
+				return wl;
+		}
+		if (diff < 0)
+			node = &(*node)->rb_left;
+		else
+			node = &(*node)->rb_right;
+	}
+	if (!add_if_not_found)
+		return ERR_PTR(-EINVAL);
+
+	if (wakelocks_limit_exceeded())
+		return ERR_PTR(-ENOSPC);
+
+	/* Not found, we have to add a new one. */
+	wl = kzalloc_obj(*wl);
+	if (!wl)
+		return ERR_PTR(-ENOMEM);
+
+	wl->name = kstrndup(name, len, GFP_KERNEL);
+	if (!wl->name) {
+		kfree(wl);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	wl->ws = wakeup_source_register(NULL, wl->name);
+	if (!wl->ws) {
+		kfree(wl->name);
+		kfree(wl);
+		return ERR_PTR(-ENOMEM);
+	}
+	wl->ws->last_time = ktime_get();
+
+	rb_link_node(&wl->node, parent, node);
+	rb_insert_color(&wl->node, &wakelocks_tree);
+	wakelocks_lru_add(wl);
+	increment_wakelocks_number();
+	return wl;
+}
+
+int pm_wake_lock(const char *buf)
+{
+	const char *str = buf;
+	struct wakelock *wl;
+	u64 timeout_ns = 0;
+	size_t len;
+	int ret = 0;
+
+	if (!capable(CAP_BLOCK_SUSPEND))
+		return -EPERM;
+
+	while (*str && !isspace(*str))
+		str++;
+
+	len = str - buf;
+	if (!len)
+		return -EINVAL;
+
+	if (*str && *str != '\n') {
+		/* Find out if there's a valid timeout string appended. */
+		ret = kstrtou64(skip_spaces(str), 10, &timeout_ns);
+		if (ret)
+			return -EINVAL;
+	}
+
+	mutex_lock(&wakelocks_lock);
+
+	wl = wakelock_lookup_add(buf, len, true);
+	if (IS_ERR(wl)) {
+		ret = PTR_ERR(wl);
+		goto out;
+	}
+	if (timeout_ns) {
+		u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1;
+
+		do_div(timeout_ms, NSEC_PER_MSEC);
+		__pm_wakeup_event(wl->ws, timeout_ms);
+	} else {
+		__pm_stay_awake(wl->ws);
+	}
+
+	wakelocks_lru_most_recent(wl);
+
+ out:
+	mutex_unlock(&wakelocks_lock);
+	return ret;
+}
+
+int pm_wake_unlock(const char *buf)
+{
+	struct wakelock *wl;
+	size_t len;
+	int ret = 0;
+
+	if (!capable(CAP_BLOCK_SUSPEND))
+		return -EPERM;
+
+	len = strlen(buf);
+	if (!len)
+		return -EINVAL;
+
+	if (buf[len-1] == '\n')
+		len--;
+
+	if (!len)
+		return -EINVAL;
+
+	mutex_lock(&wakelocks_lock);
+
+	wl = wakelock_lookup_add(buf, len, false);
+	if (IS_ERR(wl)) {
+		ret = PTR_ERR(wl);
+		goto out;
+	}
+	__pm_relax(wl->ws);
+
+	wakelocks_lru_most_recent(wl);
+	wakelocks_gc();
+
+ out:
+	mutex_unlock(&wakelocks_lock);
+	return ret;
+}