Initial commit: Linux kernel 4.19 for Unplugged OS

kernel/power/Kconfig

@@ -0,0 +1,315 @@
+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.  Say Y if that's your case.
+
+config HIBERNATE_CALLBACKS
+	bool
+
+config HIBERNATION
+	bool "Hibernation (aka 'suspend to disk')"
+	depends on SWAP && ARCH_HIBERNATION_POSSIBLE
+	select HIBERNATE_CALLBACKS
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
+	select CRC32
+	---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.txt>).
+
+	  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.txt>.
+
+config ARCH_SAVE_PAGE_KEYS
+	bool
+
+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
+	select SRCU
+
+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_AUTOSLEEP
+	bool "Opportunistic sleep"
+	depends on PM_SLEEP
+	default n
+	---help---
+	Allow the kernel to trigger a system transition into a global sleep
+	state automatically whenever there are no active wakeup sources.
+
+config PM_WAKELOCKS
+	bool "User space wakeup sources interface"
+	depends on PM_SLEEP
+	default n
+	---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
+	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 in seconds"
+	range 1 120
+	default 120
+	depends on DPM_WATCHDOG
+
+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.txt>
+	  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
+	default n
+	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 CPUs"
+	depends on SMP
+	depends on CPU_FREQ
+	default n
+	help
+	  Several subsystems (thermal and/or the task scheduler for example)
+	  can leverage information about the energy consumed by CPUs 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.

kernel/power/Makefile

@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+
+ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
+
+KASAN_SANITIZE_snapshot.o	:= n
+
+obj-y				+= qos.o
+obj-$(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-$(CONFIG_HIBERNATION)	+= hibernate.o snapshot.o swap.o user.o
+obj-$(CONFIG_PM_AUTOSLEEP)	+= autosleep.o
+obj-$(CONFIG_PM_WAKELOCKS)	+= wakelock.o
+
+obj-$(CONFIG_MAGIC_SYSRQ)	+= poweroff.o
+
+obj-$(CONFIG_ENERGY_MODEL)	+= energy_model.o
+obj-$(CONFIG_SUSPEND)		+= wakeup_reason.o

kernel/power/autosleep.c

@@ -0,0 +1,129 @@
+// 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 <linux/pm_wakeup.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 occured 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;
+}

kernel/power/console.c

@@ -0,0 +1,152 @@
+// 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 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.
+ */
+void pm_vt_switch_required(struct device *dev, bool required)
+{
+	struct pm_vt_switch *entry, *tmp;
+
+	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(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		goto out;
+
+	entry->required = required;
+	entry->dev = dev;
+
+	list_add(&entry->head, &pm_vt_switch_list);
+out:
+	mutex_unlock(&vt_switch_mutex);
+}
+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;
+
+	orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE);
+	return;
+}
+
+void pm_restore_console(void)
+{
+	if (!pm_vt_switch())
+		return;
+
+	if (orig_fgconsole >= 0) {
+		vt_move_to_console(orig_fgconsole, 0);
+		vt_kmsg_redirect(orig_kmsg);
+	}
+}

kernel/power/energy_model.c

@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Energy Model of CPUs
+ *
+ * Copyright (c) 2018, Arm ltd.
+ * Written by: Quentin Perret, Arm ltd.
+ */
+
+#define pr_fmt(fmt) "energy_model: " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/energy_model.h>
+#include <linux/sched/topology.h>
+#include <linux/slab.h>
+
+/* Mapping of each CPU to the performance domain to which it belongs. */
+static DEFINE_PER_CPU(struct em_perf_domain *, em_data);
+
+/*
+ * Mutex serializing the registrations of performance domains and letting
+ * callbacks defined by drivers sleep.
+ */
+static DEFINE_MUTEX(em_pd_mutex);
+
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *rootdir;
+
+static void em_debug_create_cs(struct em_cap_state *cs, struct dentry *pd)
+{
+	struct dentry *d;
+	char name[24];
+
+	snprintf(name, sizeof(name), "cs:%lu", cs->frequency);
+
+	/* Create per-cs directory */
+	d = debugfs_create_dir(name, pd);
+	debugfs_create_ulong("frequency", 0444, d, &cs->frequency);
+	debugfs_create_ulong("power", 0444, d, &cs->power);
+	debugfs_create_ulong("cost", 0444, d, &cs->cost);
+}
+
+static int em_debug_cpus_show(struct seq_file *s, void *unused)
+{
+	seq_printf(s, "%*pbl\n", cpumask_pr_args(to_cpumask(s->private)));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
+
+static void em_debug_create_pd(struct em_perf_domain *pd, int cpu)
+{
+	struct dentry *d;
+	char name[8];
+	int i;
+
+	snprintf(name, sizeof(name), "pd%d", cpu);
+
+	/* Create the directory of the performance domain */
+	d = debugfs_create_dir(name, rootdir);
+
+	debugfs_create_file("cpus", 0444, d, pd->cpus, &em_debug_cpus_fops);
+
+	/* Create a sub-directory for each capacity state */
+	for (i = 0; i < pd->nr_cap_states; i++)
+		em_debug_create_cs(&pd->table[i], d);
+}
+
+static int __init em_debug_init(void)
+{
+	/* Create /sys/kernel/debug/energy_model directory */
+	rootdir = debugfs_create_dir("energy_model", NULL);
+
+	return 0;
+}
+core_initcall(em_debug_init);
+#else /* CONFIG_DEBUG_FS */
+static void em_debug_create_pd(struct em_perf_domain *pd, int cpu) {}
+#endif
+static struct em_perf_domain *em_create_pd(cpumask_t *span, int nr_states,
+						struct em_data_callback *cb)
+{
+	unsigned long opp_eff, prev_opp_eff = ULONG_MAX;
+	unsigned long power, freq, prev_freq = 0;
+	int i, ret, cpu = cpumask_first(span);
+	struct em_cap_state *table;
+	struct em_perf_domain *pd;
+	u64 fmax;
+
+	if (!cb->active_power)
+		return NULL;
+
+	pd = kzalloc(sizeof(*pd) + cpumask_size(), GFP_KERNEL);
+	if (!pd)
+		return NULL;
+
+	table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL);
+	if (!table)
+		goto free_pd;
+
+	/* Build the list of capacity states for this performance domain */
+	for (i = 0, freq = 0; i < nr_states; i++, freq++) {
+		/*
+		 * active_power() is a driver callback which ceils 'freq' to
+		 * lowest capacity state of 'cpu' above 'freq' and updates
+		 * 'power' and 'freq' accordingly.
+		 */
+		ret = cb->active_power(&power, &freq, cpu);
+		if (ret) {
+			pr_err("pd%d: invalid cap. state: %d\n", cpu, ret);
+			goto free_cs_table;
+		}
+
+		/*
+		 * We expect the driver callback to increase the frequency for
+		 * higher capacity states.
+		 */
+		if (freq <= prev_freq) {
+			pr_err("pd%d: non-increasing freq: %lu\n", cpu, freq);
+			goto free_cs_table;
+		}
+
+		/*
+		 * The power returned by active_state() is expected to be
+		 * positive, in milli-watts and to fit into 16 bits.
+		 */
+		if (!power || power > EM_CPU_MAX_POWER) {
+			pr_err("pd%d: invalid power: %lu\n", cpu, power);
+			goto free_cs_table;
+		}
+
+		table[i].power = power;
+		table[i].frequency = prev_freq = freq;
+
+		/*
+		 * The hertz/watts efficiency ratio should decrease as the
+		 * frequency grows on sane platforms. But this isn't always
+		 * true in practice so warn the user if a higher OPP is more
+		 * power efficient than a lower one.
+		 */
+		opp_eff = freq / power;
+		if (opp_eff >= prev_opp_eff)
+			pr_warn("pd%d: hertz/watts ratio non-monotonically decreasing: em_cap_state %d >= em_cap_state%d\n",
+					cpu, i, i - 1);
+		prev_opp_eff = opp_eff;
+	}
+
+	/* Compute the cost of each capacity_state. */
+	fmax = (u64) table[nr_states - 1].frequency;
+	for (i = 0; i < nr_states; i++) {
+		table[i].cost = div64_u64(fmax * table[i].power,
+					  table[i].frequency);
+	}
+
+	pd->table = table;
+	pd->nr_cap_states = nr_states;
+	cpumask_copy(to_cpumask(pd->cpus), span);
+
+	em_debug_create_pd(pd, cpu);
+
+	return pd;
+
+free_cs_table:
+	kfree(table);
+free_pd:
+	kfree(pd);
+
+	return NULL;
+}
+
+/**
+ * em_cpu_get() - Return the performance domain for a CPU
+ * @cpu : CPU to find the performance domain for
+ *
+ * Return: the performance domain to which 'cpu' belongs, or NULL if it doesn't
+ * exist.
+ */
+struct em_perf_domain *em_cpu_get(int cpu)
+{
+	return READ_ONCE(per_cpu(em_data, cpu));
+}
+EXPORT_SYMBOL_GPL(em_cpu_get);
+
+/**
+ * em_register_perf_domain() - Register the Energy Model of a performance domain
+ * @span	: Mask of CPUs in the performance domain
+ * @nr_states	: Number of capacity states to register
+ * @cb		: Callback functions providing the data of the Energy Model
+ *
+ * Create Energy Model tables for a performance domain using the callbacks
+ * defined in cb.
+ *
+ * If multiple clients register the same performance domain, all but the first
+ * registration will be ignored.
+ *
+ * Return 0 on success
+ */
+int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
+						struct em_data_callback *cb)
+{
+	unsigned long cap, prev_cap = 0;
+	struct em_perf_domain *pd;
+	int cpu, ret = 0;
+
+	if (!span || !nr_states || !cb)
+		return -EINVAL;
+
+	/*
+	 * Use a mutex to serialize the registration of performance domains and
+	 * let the driver-defined callback functions sleep.
+	 */
+	mutex_lock(&em_pd_mutex);
+
+	for_each_cpu(cpu, span) {
+		/* Make sure we don't register again an existing domain. */
+		if (READ_ONCE(per_cpu(em_data, cpu))) {
+			ret = -EEXIST;
+			goto unlock;
+		}
+
+		/*
+		 * All CPUs of a domain must have the same micro-architecture
+		 * since they all share the same table.
+		 */
+		cap = arch_scale_cpu_capacity(NULL, cpu);
+		if (prev_cap && prev_cap != cap) {
+			pr_err("CPUs of %*pbl must have the same capacity\n",
+							cpumask_pr_args(span));
+			ret = -EINVAL;
+			goto unlock;
+		}
+		prev_cap = cap;
+	}
+
+	/* Create the performance domain and add it to the Energy Model. */
+	pd = em_create_pd(span, nr_states, cb);
+	if (!pd) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	for_each_cpu(cpu, span) {
+		/*
+		 * The per-cpu array can be read concurrently from em_cpu_get().
+		 * The barrier enforces the ordering needed to make sure readers
+		 * can only access well formed em_perf_domain structs.
+		 */
+		smp_store_release(per_cpu_ptr(&em_data, cpu), pd);
+	}
+
+	pr_debug("Created perf domain %*pbl\n", cpumask_pr_args(span));
+unlock:
+	mutex_unlock(&em_pd_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(em_register_perf_domain);

kernel/power/main.c

@@ -0,0 +1,918 @@
+/*
+ * kernel/power/main.c - PM subsystem core functionality.
+ *
+ * Copyright (c) 2003 Patrick Mochel
+ * Copyright (c) 2003 Open Source Development Lab
+ *
+ * This file is released under the GPLv2
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/pm-trace.h>
+#include <linux/workqueue.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/suspend.h>
+
+#include "power.h"
+
+#ifdef CONFIG_PM_SLEEP
+
+void lock_system_sleep(void)
+{
+	current->flags |= PF_FREEZER_SKIP;
+	mutex_lock(&system_transition_mutex);
+}
+EXPORT_SYMBOL_GPL(lock_system_sleep);
+
+void unlock_system_sleep(void)
+{
+	/*
+	 * Don't use freezer_count() because we don't want the call to
+	 * try_to_freeze() here.
+	 *
+	 * Reason:
+	 * Fundamentally, we just don't need it, because freezing condition
+	 * doesn't come into effect until we release the
+	 * system_transition_mutex lock, since the freezer always works with
+	 * system_transition_mutex held.
+	 *
+	 * More importantly, in the case of hibernation,
+	 * unlock_system_sleep() gets called in snapshot_read() and
+	 * snapshot_write() when the freezing condition is still in effect.
+	 * Which means, if we use try_to_freeze() here, it would make them
+	 * enter the refrigerator, thus causing hibernation to lockup.
+	 */
+	current->flags &= ~PF_FREEZER_SKIP;
+	mutex_unlock(&system_transition_mutex);
+}
+EXPORT_SYMBOL_GPL(unlock_system_sleep);
+
+/* Routines for PM-transition notifications */
+
+static BLOCKING_NOTIFIER_HEAD(pm_chain_head);
+
+int register_pm_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&pm_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(register_pm_notifier);
+
+int unregister_pm_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&pm_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_pm_notifier);
+
+int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls)
+{
+	int ret;
+
+	ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL,
+						nr_to_call, nr_calls);
+
+	return notifier_to_errno(ret);
+}
+int pm_notifier_call_chain(unsigned long val)
+{
+	return __pm_notifier_call_chain(val, -1, NULL);
+}
+
+/* If set, devices may be suspended and resumed asynchronously. */
+int pm_async_enabled = 1;
+
+static ssize_t pm_async_show(struct kobject *kobj, struct kobj_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%d\n", pm_async_enabled);
+}
+
+static ssize_t pm_async_store(struct kobject *kobj, struct kobj_attribute *attr,
+			      const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	if (val > 1)
+		return -EINVAL;
+
+	pm_async_enabled = val;
+	return n;
+}
+
+power_attr(pm_async);
+
+#ifdef CONFIG_SUSPEND
+static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr,
+			      char *buf)
+{
+	char *s = buf;
+	suspend_state_t i;
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (mem_sleep_states[i]) {
+			const char *label = mem_sleep_states[i];
+
+			if (mem_sleep_current == i)
+				s += sprintf(s, "[%s] ", label);
+			else
+				s += sprintf(s, "%s ", label);
+		}
+
+	/* Convert the last space to a newline if needed. */
+	if (s != buf)
+		*(s-1) = '\n';
+
+	return (s - buf);
+}
+
+static suspend_state_t decode_suspend_state(const char *buf, size_t n)
+{
+	suspend_state_t state;
+	char *p;
+	int len;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	for (state = PM_SUSPEND_MIN; state < PM_SUSPEND_MAX; state++) {
+		const char *label = mem_sleep_states[state];
+
+		if (label && len == strlen(label) && !strncmp(buf, label, len))
+			return state;
+	}
+
+	return PM_SUSPEND_ON;
+}
+
+static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	suspend_state_t state;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	state = decode_suspend_state(buf, n);
+	if (state < PM_SUSPEND_MAX && state > PM_SUSPEND_ON)
+		mem_sleep_current = state;
+	else
+		error = -EINVAL;
+
+ out:
+	pm_autosleep_unlock();
+	return error ? error : n;
+}
+
+power_attr(mem_sleep);
+#endif /* CONFIG_SUSPEND */
+
+#ifdef CONFIG_PM_SLEEP_DEBUG
+int pm_test_level = TEST_NONE;
+
+static const char * const pm_tests[__TEST_AFTER_LAST] = {
+	[TEST_NONE] = "none",
+	[TEST_CORE] = "core",
+	[TEST_CPUS] = "processors",
+	[TEST_PLATFORM] = "platform",
+	[TEST_DEVICES] = "devices",
+	[TEST_FREEZER] = "freezer",
+};
+
+static ssize_t pm_test_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	char *s = buf;
+	int level;
+
+	for (level = TEST_FIRST; level <= TEST_MAX; level++)
+		if (pm_tests[level]) {
+			if (level == pm_test_level)
+				s += sprintf(s, "[%s] ", pm_tests[level]);
+			else
+				s += sprintf(s, "%s ", pm_tests[level]);
+		}
+
+	if (s != buf)
+		/* convert the last space to a newline */
+		*(s-1) = '\n';
+
+	return (s - buf);
+}
+
+static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
+				const char *buf, size_t n)
+{
+	const char * const *s;
+	int level;
+	char *p;
+	int len;
+	int error = -EINVAL;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	lock_system_sleep();
+
+	level = TEST_FIRST;
+	for (s = &pm_tests[level]; level <= TEST_MAX; s++, level++)
+		if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
+			pm_test_level = level;
+			error = 0;
+			break;
+		}
+
+	unlock_system_sleep();
+
+	return error ? error : n;
+}
+
+power_attr(pm_test);
+#endif /* CONFIG_PM_SLEEP_DEBUG */
+
+static char *suspend_step_name(enum suspend_stat_step step)
+{
+	switch (step) {
+	case SUSPEND_FREEZE:
+		return "freeze";
+	case SUSPEND_PREPARE:
+		return "prepare";
+	case SUSPEND_SUSPEND:
+		return "suspend";
+	case SUSPEND_SUSPEND_NOIRQ:
+		return "suspend_noirq";
+	case SUSPEND_RESUME_NOIRQ:
+		return "resume_noirq";
+	case SUSPEND_RESUME:
+		return "resume";
+	default:
+		return "";
+	}
+}
+
+#define suspend_attr(_name)					\
+static ssize_t _name##_show(struct kobject *kobj,		\
+		struct kobj_attribute *attr, char *buf)		\
+{								\
+	return sprintf(buf, "%d\n", suspend_stats._name);	\
+}								\
+static struct kobj_attribute _name = __ATTR_RO(_name)
+
+suspend_attr(success);
+suspend_attr(fail);
+suspend_attr(failed_freeze);
+suspend_attr(failed_prepare);
+suspend_attr(failed_suspend);
+suspend_attr(failed_suspend_late);
+suspend_attr(failed_suspend_noirq);
+suspend_attr(failed_resume);
+suspend_attr(failed_resume_early);
+suspend_attr(failed_resume_noirq);
+
+static ssize_t last_failed_dev_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	int index;
+	char *last_failed_dev = NULL;
+
+	index = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+	index %= REC_FAILED_NUM;
+	last_failed_dev = suspend_stats.failed_devs[index];
+
+	return sprintf(buf, "%s\n", last_failed_dev);
+}
+static struct kobj_attribute last_failed_dev = __ATTR_RO(last_failed_dev);
+
+static ssize_t last_failed_errno_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	int index;
+	int last_failed_errno;
+
+	index = suspend_stats.last_failed_errno + REC_FAILED_NUM - 1;
+	index %= REC_FAILED_NUM;
+	last_failed_errno = suspend_stats.errno[index];
+
+	return sprintf(buf, "%d\n", last_failed_errno);
+}
+static struct kobj_attribute last_failed_errno = __ATTR_RO(last_failed_errno);
+
+static ssize_t last_failed_step_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	int index;
+	enum suspend_stat_step step;
+	char *last_failed_step = NULL;
+
+	index = suspend_stats.last_failed_step + REC_FAILED_NUM - 1;
+	index %= REC_FAILED_NUM;
+	step = suspend_stats.failed_steps[index];
+	last_failed_step = suspend_step_name(step);
+
+	return sprintf(buf, "%s\n", last_failed_step);
+}
+static struct kobj_attribute last_failed_step = __ATTR_RO(last_failed_step);
+
+static struct attribute *suspend_attrs[] = {
+	&success.attr,
+	&fail.attr,
+	&failed_freeze.attr,
+	&failed_prepare.attr,
+	&failed_suspend.attr,
+	&failed_suspend_late.attr,
+	&failed_suspend_noirq.attr,
+	&failed_resume.attr,
+	&failed_resume_early.attr,
+	&failed_resume_noirq.attr,
+	&last_failed_dev.attr,
+	&last_failed_errno.attr,
+	&last_failed_step.attr,
+	NULL,
+};
+
+static struct attribute_group suspend_attr_group = {
+	.name = "suspend_stats",
+	.attrs = suspend_attrs,
+};
+
+#ifdef CONFIG_DEBUG_FS
+static int suspend_stats_show(struct seq_file *s, void *unused)
+{
+	int i, index, last_dev, last_errno, last_step;
+
+	last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+	last_dev %= REC_FAILED_NUM;
+	last_errno = suspend_stats.last_failed_errno + REC_FAILED_NUM - 1;
+	last_errno %= REC_FAILED_NUM;
+	last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1;
+	last_step %= REC_FAILED_NUM;
+	seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n"
+			"%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n",
+			"success", suspend_stats.success,
+			"fail", suspend_stats.fail,
+			"failed_freeze", suspend_stats.failed_freeze,
+			"failed_prepare", suspend_stats.failed_prepare,
+			"failed_suspend", suspend_stats.failed_suspend,
+			"failed_suspend_late",
+				suspend_stats.failed_suspend_late,
+			"failed_suspend_noirq",
+				suspend_stats.failed_suspend_noirq,
+			"failed_resume", suspend_stats.failed_resume,
+			"failed_resume_early",
+				suspend_stats.failed_resume_early,
+			"failed_resume_noirq",
+				suspend_stats.failed_resume_noirq);
+	seq_printf(s,	"failures:\n  last_failed_dev:\t%-s\n",
+			suspend_stats.failed_devs[last_dev]);
+	for (i = 1; i < REC_FAILED_NUM; i++) {
+		index = last_dev + REC_FAILED_NUM - i;
+		index %= REC_FAILED_NUM;
+		seq_printf(s, "\t\t\t%-s\n",
+			suspend_stats.failed_devs[index]);
+	}
+	seq_printf(s,	"  last_failed_errno:\t%-d\n",
+			suspend_stats.errno[last_errno]);
+	for (i = 1; i < REC_FAILED_NUM; i++) {
+		index = last_errno + REC_FAILED_NUM - i;
+		index %= REC_FAILED_NUM;
+		seq_printf(s, "\t\t\t%-d\n",
+			suspend_stats.errno[index]);
+	}
+	seq_printf(s,	"  last_failed_step:\t%-s\n",
+			suspend_step_name(
+				suspend_stats.failed_steps[last_step]));
+	for (i = 1; i < REC_FAILED_NUM; i++) {
+		index = last_step + REC_FAILED_NUM - i;
+		index %= REC_FAILED_NUM;
+		seq_printf(s, "\t\t\t%-s\n",
+			suspend_step_name(
+				suspend_stats.failed_steps[index]));
+	}
+
+	return 0;
+}
+
+static int suspend_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, suspend_stats_show, NULL);
+}
+
+static const struct file_operations suspend_stats_operations = {
+	.open           = suspend_stats_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = single_release,
+};
+
+static int __init pm_debugfs_init(void)
+{
+	debugfs_create_file("suspend_stats", S_IFREG | S_IRUGO,
+			NULL, NULL, &suspend_stats_operations);
+	return 0;
+}
+
+late_initcall(pm_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_SLEEP_DEBUG
+/*
+ * pm_print_times: print time taken by devices to suspend and resume.
+ *
+ * show() returns whether printing of suspend and resume times is enabled.
+ * store() accepts 0 or 1.  0 disables printing and 1 enables it.
+ */
+bool pm_print_times_enabled;
+
+static ssize_t pm_print_times_show(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", pm_print_times_enabled);
+}
+
+static ssize_t pm_print_times_store(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	if (val > 1)
+		return -EINVAL;
+
+	pm_print_times_enabled = !!val;
+	return n;
+}
+
+power_attr(pm_print_times);
+
+static inline void pm_print_times_init(void)
+{
+	pm_print_times_enabled = !!initcall_debug;
+}
+
+static ssize_t pm_wakeup_irq_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf)
+{
+	return pm_wakeup_irq ? sprintf(buf, "%u\n", pm_wakeup_irq) : -ENODATA;
+}
+
+power_attr_ro(pm_wakeup_irq);
+
+bool pm_debug_messages_on __read_mostly;
+
+static ssize_t pm_debug_messages_show(struct kobject *kobj,
+				      struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", pm_debug_messages_on);
+}
+
+static ssize_t pm_debug_messages_store(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	if (val > 1)
+		return -EINVAL;
+
+	pm_debug_messages_on = !!val;
+	return n;
+}
+
+power_attr(pm_debug_messages);
+
+/**
+ * __pm_pr_dbg - Print a suspend debug message to the kernel log.
+ * @defer: Whether or not to use printk_deferred() to print the message.
+ * @fmt: Message format.
+ *
+ * The message will be emitted if enabled through the pm_debug_messages
+ * sysfs attribute.
+ */
+void __pm_pr_dbg(bool defer, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	if (!pm_debug_messages_on)
+		return;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (defer)
+		printk_deferred(KERN_DEBUG "PM: %pV", &vaf);
+	else
+		printk(KERN_DEBUG "PM: %pV", &vaf);
+
+	va_end(args);
+}
+
+#else /* !CONFIG_PM_SLEEP_DEBUG */
+static inline void pm_print_times_init(void) {}
+#endif /* CONFIG_PM_SLEEP_DEBUG */
+
+struct kobject *power_kobj;
+EXPORT_SYMBOL_GPL(power_kobj);
+
+/**
+ * state - control system sleep states.
+ *
+ * show() returns available sleep state labels, which may be "mem", "standby",
+ * "freeze" and "disk" (hibernation).
+ * See Documentation/admin-guide/pm/sleep-states.rst for a description of
+ * what they mean.
+ *
+ * store() accepts one of those strings, translates it into the proper
+ * enumerated value, and initiates a suspend transition.
+ */
+static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
+			  char *buf)
+{
+	char *s = buf;
+#ifdef CONFIG_SUSPEND
+	suspend_state_t i;
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (pm_states[i])
+			s += sprintf(s,"%s ", pm_states[i]);
+
+#endif
+	if (hibernation_available())
+		s += sprintf(s, "disk ");
+	if (s != buf)
+		/* convert the last space to a newline */
+		*(s-1) = '\n';
+	return (s - buf);
+}
+
+static suspend_state_t decode_state(const char *buf, size_t n)
+{
+#ifdef CONFIG_SUSPEND
+	suspend_state_t state;
+#endif
+	char *p;
+	int len;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	/* Check hibernation first. */
+	if (len == 4 && !strncmp(buf, "disk", len))
+		return PM_SUSPEND_MAX;
+
+#ifdef CONFIG_SUSPEND
+	for (state = PM_SUSPEND_MIN; state < PM_SUSPEND_MAX; state++) {
+		const char *label = pm_states[state];
+
+		if (label && len == strlen(label) && !strncmp(buf, label, len))
+			return state;
+	}
+#endif
+
+	return PM_SUSPEND_ON;
+}
+
+static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
+			   const char *buf, size_t n)
+{
+	suspend_state_t state;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	state = decode_state(buf, n);
+	if (state < PM_SUSPEND_MAX) {
+		if (state == PM_SUSPEND_MEM)
+			state = mem_sleep_current;
+
+		error = pm_suspend(state);
+	} else if (state == PM_SUSPEND_MAX) {
+		error = hibernate();
+	} else {
+		error = -EINVAL;
+	}
+
+ out:
+	pm_autosleep_unlock();
+	return error ? error : n;
+}
+
+power_attr(state);
+
+#ifdef CONFIG_PM_SLEEP
+/*
+ * The 'wakeup_count' attribute, along with the functions defined in
+ * drivers/base/power/wakeup.c, provides a means by which wakeup events can be
+ * handled in a non-racy way.
+ *
+ * If a wakeup event occurs when the system is in a sleep state, it simply is
+ * woken up.  In turn, if an event that would wake the system up from a sleep
+ * state occurs when it is undergoing a transition to that sleep state, the
+ * transition should be aborted.  Moreover, if such an event occurs when the
+ * system is in the working state, an attempt to start a transition to the
+ * given sleep state should fail during certain period after the detection of
+ * the event.  Using the 'state' attribute alone is not sufficient to satisfy
+ * these requirements, because a wakeup event may occur exactly when 'state'
+ * is being written to and may be delivered to user space right before it is
+ * frozen, so the event will remain only partially processed until the system is
+ * woken up by another event.  In particular, it won't cause the transition to
+ * a sleep state to be aborted.
+ *
+ * This difficulty may be overcome if user space uses 'wakeup_count' before
+ * writing to 'state'.  It first should read from 'wakeup_count' and store
+ * the read value.  Then, after carrying out its own preparations for the system
+ * transition to a sleep state, it should write the stored value to
+ * 'wakeup_count'.  If that fails, at least one wakeup event has occurred since
+ * 'wakeup_count' was read and 'state' should not be written to.  Otherwise, it
+ * is allowed to write to 'state', but the transition will be aborted if there
+ * are any wakeup events detected after 'wakeup_count' was written to.
+ */
+
+static ssize_t wakeup_count_show(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				char *buf)
+{
+	unsigned int val;
+
+	return pm_get_wakeup_count(&val, true) ?
+		sprintf(buf, "%u\n", val) : -EINTR;
+}
+
+static ssize_t wakeup_count_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t n)
+{
+	unsigned int val;
+	int error;
+
+	error = pm_autosleep_lock();
+	if (error)
+		return error;
+
+	if (pm_autosleep_state() > PM_SUSPEND_ON) {
+		error = -EBUSY;
+		goto out;
+	}
+
+	error = -EINVAL;
+	if (sscanf(buf, "%u", &val) == 1) {
+		if (pm_save_wakeup_count(val))
+			error = n;
+		else
+			pm_print_active_wakeup_sources();
+	}
+
+ out:
+	pm_autosleep_unlock();
+	return error;
+}
+
+power_attr(wakeup_count);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t autosleep_show(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      char *buf)
+{
+	suspend_state_t state = pm_autosleep_state();
+
+	if (state == PM_SUSPEND_ON)
+		return sprintf(buf, "off\n");
+
+#ifdef CONFIG_SUSPEND
+	if (state < PM_SUSPEND_MAX)
+		return sprintf(buf, "%s\n", pm_states[state] ?
+					pm_states[state] : "error");
+#endif
+#ifdef CONFIG_HIBERNATION
+	return sprintf(buf, "disk\n");
+#else
+	return sprintf(buf, "error");
+#endif
+}
+
+static ssize_t autosleep_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	suspend_state_t state = decode_state(buf, n);
+	int error;
+
+	if (state == PM_SUSPEND_ON
+	    && strcmp(buf, "off") && strcmp(buf, "off\n"))
+		return -EINVAL;
+
+	if (state == PM_SUSPEND_MEM)
+		state = mem_sleep_current;
+
+	error = pm_autosleep_set_state(state);
+	return error ? error : n;
+}
+
+power_attr(autosleep);
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+static ssize_t wake_lock_show(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      char *buf)
+{
+	return pm_show_wakelocks(buf, true);
+}
+
+static ssize_t wake_lock_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t n)
+{
+	int error = pm_wake_lock(buf);
+	return error ? error : n;
+}
+
+power_attr(wake_lock);
+
+static ssize_t wake_unlock_show(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				char *buf)
+{
+	return pm_show_wakelocks(buf, false);
+}
+
+static ssize_t wake_unlock_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t n)
+{
+	int error = pm_wake_unlock(buf);
+	return error ? error : n;
+}
+
+power_attr(wake_unlock);
+
+#endif /* CONFIG_PM_WAKELOCKS */
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_TRACE
+int pm_trace_enabled;
+
+static ssize_t pm_trace_show(struct kobject *kobj, struct kobj_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%d\n", pm_trace_enabled);
+}
+
+static ssize_t
+pm_trace_store(struct kobject *kobj, struct kobj_attribute *attr,
+	       const char *buf, size_t n)
+{
+	int val;
+
+	if (sscanf(buf, "%d", &val) == 1) {
+		pm_trace_enabled = !!val;
+		if (pm_trace_enabled) {
+			pr_warn("PM: Enabling pm_trace changes system date and time during resume.\n"
+				"PM: Correct system time has to be restored manually after resume.\n");
+		}
+		return n;
+	}
+	return -EINVAL;
+}
+
+power_attr(pm_trace);
+
+static ssize_t pm_trace_dev_match_show(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       char *buf)
+{
+	return show_trace_dev_match(buf, PAGE_SIZE);
+}
+
+power_attr_ro(pm_trace_dev_match);
+
+#endif /* CONFIG_PM_TRACE */
+
+#ifdef CONFIG_FREEZER
+static ssize_t pm_freeze_timeout_show(struct kobject *kobj,
+				      struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", freeze_timeout_msecs);
+}
+
+static ssize_t pm_freeze_timeout_store(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	freeze_timeout_msecs = val;
+	return n;
+}
+
+power_attr(pm_freeze_timeout);
+
+#endif	/* CONFIG_FREEZER*/
+
+static struct attribute * g[] = {
+	&state_attr.attr,
+#ifdef CONFIG_PM_TRACE
+	&pm_trace_attr.attr,
+	&pm_trace_dev_match_attr.attr,
+#endif
+#ifdef CONFIG_PM_SLEEP
+	&pm_async_attr.attr,
+	&wakeup_count_attr.attr,
+#ifdef CONFIG_SUSPEND
+	&mem_sleep_attr.attr,
+#endif
+#ifdef CONFIG_PM_AUTOSLEEP
+	&autosleep_attr.attr,
+#endif
+#ifdef CONFIG_PM_WAKELOCKS
+	&wake_lock_attr.attr,
+	&wake_unlock_attr.attr,
+#endif
+#ifdef CONFIG_PM_SLEEP_DEBUG
+	&pm_test_attr.attr,
+	&pm_print_times_attr.attr,
+	&pm_wakeup_irq_attr.attr,
+	&pm_debug_messages_attr.attr,
+#endif
+#endif
+#ifdef CONFIG_FREEZER
+	&pm_freeze_timeout_attr.attr,
+#endif
+	NULL,
+};
+
+static const struct attribute_group attr_group = {
+	.attrs = g,
+};
+
+static const struct attribute_group *attr_groups[] = {
+	&attr_group,
+#ifdef CONFIG_PM_SLEEP
+	&suspend_attr_group,
+#endif
+	NULL,
+};
+
+struct workqueue_struct *pm_wq;
+EXPORT_SYMBOL_GPL(pm_wq);
+
+static int __init pm_start_workqueue(void)
+{
+	pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
+
+	return pm_wq ? 0 : -ENOMEM;
+}
+
+static int __init pm_init(void)
+{
+	int error = pm_start_workqueue();
+	if (error)
+		return error;
+	hibernate_image_size_init();
+	hibernate_reserved_size_init();
+	pm_states_init();
+	power_kobj = kobject_create_and_add("power", NULL);
+	if (!power_kobj)
+		return -ENOMEM;
+	error = sysfs_create_groups(power_kobj, attr_groups);
+	if (error)
+		return error;
+	pm_print_times_init();
+	return pm_autosleep_init();
+}
+
+core_initcall(pm_init);

kernel/power/power.h

@@ -0,0 +1,315 @@
+/* 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>
+
+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);
+
+#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)
+
+extern int arch_hibernation_header_save(void *addr, unsigned int max_size);
+extern int arch_hibernation_header_restore(void *addr);
+
+static inline int init_header_complete(struct swsusp_info *info)
+{
+	return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE);
+}
+
+static inline char *check_image_kernel(struct swsusp_info *info)
+{
+	return arch_hibernation_header_restore(info) ?
+			"architecture specific data" : NULL;
+}
+#endif /* CONFIG_ARCH_HIBERNATION_HEADER */
+
+extern int hibernate_resume_nonboot_cpu_disable(void);
+
+/*
+ * 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 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 */
+
+#else /* !CONFIG_HIBERNATION */
+
+static inline void hibernate_reserved_size_init(void) {}
+static inline void hibernate_image_size_init(void) {}
+#endif /* !CONFIG_HIBERNATION */
+
+extern int pfn_is_nosave(unsigned long);
+
+#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_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);
+extern void snapshot_write_finalize(struct snapshot_handle *handle);
+extern int snapshot_image_loaded(struct snapshot_handle *handle);
+
+/* If unset, the snapshot device cannot be open. */
+extern atomic_t snapshot_device_available;
+
+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_PLATFORM_MODE	1
+#define SF_NOCOMPRESS_MODE	2
+#define SF_CRC32_MODE	        4
+
+/* kernel/power/hibernate.c */
+extern int swsusp_check(void);
+extern void swsusp_free(void);
+extern int swsusp_read(unsigned int *flags_p);
+extern int swsusp_write(unsigned int flags);
+extern void swsusp_close(fmode_t);
+#ifdef CONFIG_SUSPEND
+extern int swsusp_unmark(void);
+#endif
+
+struct 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(unsigned long val, int nr_to_call,
+				    int *nr_calls);
+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 */

kernel/power/poweroff.c

@@ -0,0 +1,46 @@
+/*
+ * poweroff.c - sysrq handler to gracefully power down machine.
+ *
+ * This file is released under the GPL v2
+ */
+
+#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(int key)
+{
+	/* run sysrq poweroff on boot cpu */
+	schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
+}
+
+static 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);

kernel/power/process.c

@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * drivers/power/process.c - Functions for starting/stopping processes on 
+ *                           suspend transitions.
+ *
+ * Originally from swsusp.
+ */
+
+
+#undef DEBUG
+
+#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)
+{
+	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;
+
+	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;
+
+			if (!freezer_should_skip(p))
+				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 (wakeup) {
+		pr_cont("\n");
+		pr_err("Freezing of tasks aborted after %d.%03d seconds",
+		       elapsed_msecs / 1000, elapsed_msecs % 1000);
+	} else if (todo) {
+		pr_cont("\n");
+		pr_err("Freezing of tasks failed after %d.%03d seconds"
+		       " (%d tasks refusing to freeze, wq_busy=%d):\n",
+		       elapsed_msecs / 1000, elapsed_msecs % 1000,
+		       todo - wq_busy, wq_busy);
+
+		if (wq_busy)
+			show_workqueue_state();
+
+		read_lock(&tasklist_lock);
+		for_each_process_thread(g, p) {
+			if (p != current && !freezer_should_skip(p)
+			    && freezing(p) && !frozen(p))
+				sched_show_task(p);
+		}
+		read_unlock(&tasklist_lock);
+	} else {
+		pr_cont("(elapsed %d.%03d seconds) ", 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)
+		atomic_inc(&system_freezing_cnt);
+
+	pm_wakeup_clear(true);
+	pr_info("Freezing user space processes ... ");
+	pm_freezing = true;
+	error = try_to_freeze_tasks(true);
+	if (!error) {
+		__usermodehelper_set_disable_depth(UMH_DISABLED);
+		pr_cont("done.");
+	}
+	pr_cont("\n");
+	BUG_ON(in_atomic());
+
+	/*
+	 * Now that the whole userspace is frozen we need to disbale
+	 * 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;
+
+	pr_info("Freezing remaining freezable tasks ... ");
+
+	pm_nosig_freezing = true;
+	error = try_to_freeze_tasks(false);
+	if (!error)
+		pr_cont("done.");
+
+	pr_cont("\n");
+	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)
+		atomic_dec(&system_freezing_cnt);
+	pm_freezing = false;
+	pm_nosig_freezing = false;
+
+	oom_killer_enable();
+
+	pr_info("Restarting tasks ... ");
+
+	__usermodehelper_set_disable_depth(UMH_FREEZING);
+	thaw_workqueues();
+
+	cpuset_wait_for_hotplug();
+
+	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_cont("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 ... ");
+
+	thaw_workqueues();
+
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
+		if (p->flags & (PF_KTHREAD | PF_WQ_WORKER))
+			__thaw_task(p);
+	}
+	read_unlock(&tasklist_lock);
+
+	schedule();
+	pr_cont("done.\n");
+}

kernel/power/suspend.c

@@ -0,0 +1,710 @@
+/*
+ * 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.
+ *
+ * This file is released under the GPLv2.
+ */
+
+#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/syscalls.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/wakeup_reason.h>
+
+#include "power.h"
+
+#define MTK_SOLUTION 1
+
+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);
+
+bool pm_suspend_via_s2idle(void)
+{
+	return mem_sleep_current == PM_SUSPEND_TO_IDLE;
+}
+EXPORT_SYMBOL_GPL(pm_suspend_via_s2idle);
+
+void s2idle_set_ops(const struct platform_s2idle_ops *ops)
+{
+	lock_system_sleep();
+	s2idle_ops = ops;
+	unlock_system_sleep();
+}
+EXPORT_SYMBOL_GPL(s2idle_set_ops);
+
+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);
+
+	raw_spin_lock_irq(&s2idle_lock);
+	if (pm_wakeup_pending())
+		goto out;
+
+	s2idle_state = S2IDLE_STATE_ENTER;
+	raw_spin_unlock_irq(&s2idle_lock);
+
+	get_online_cpus();
+	cpuidle_resume();
+
+	/* 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);
+
+	cpuidle_pause();
+	put_online_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");
+
+	for (;;) {
+		int error;
+
+		dpm_noirq_begin();
+
+		/*
+		 * 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 prevent them from terminating the loop right away.
+		 */
+		error = dpm_noirq_suspend_devices(PMSG_SUSPEND);
+		if (!error)
+			s2idle_enter();
+		else if (error == -EBUSY && pm_wakeup_pending())
+			error = 0;
+
+		if (!error && s2idle_ops && s2idle_ops->wake)
+			s2idle_ops->wake();
+
+		dpm_noirq_resume_devices(PMSG_RESUME);
+
+		dpm_noirq_end();
+
+		if (error)
+			break;
+
+		if (s2idle_ops && s2idle_ops->sync)
+			s2idle_ops->sync();
+
+		if (pm_wakeup_pending())
+			break;
+
+		pm_wakeup_clear(false);
+		clear_wakeup_reasons();
+	}
+
+	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)
+{
+	/*
+	 * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level
+	 * support and need to be valid to the low level
+	 * implementation, no valid callback implies that none are valid.
+	 */
+	return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
+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;
+			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)
+{
+	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();
+}
+EXPORT_SYMBOL_GPL(suspend_set_ops);
+
+/**
+ * suspend_valid_only_mem - Generic memory-only valid callback.
+ *
+ * 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 || (suspend_ops && suspend_ops->enter);
+}
+
+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)
+{
+	return state != PM_SUSPEND_TO_IDLE && suspend_ops->prepare_late ?
+		suspend_ops->prepare_late() : 0;
+}
+
+static void platform_resume_noirq(suspend_state_t state)
+{
+	if (state != PM_SUSPEND_TO_IDLE && 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
+	if (pm_test_level == level) {
+		pr_info("suspend debug: Waiting for %d second(s).\n",
+				pm_test_delay);
+		mdelay(pm_test_delay * 1000);
+		return 1;
+	}
+#endif /* !CONFIG_PM_DEBUG */
+	return 0;
+}
+
+/**
+ * suspend_prepare - Prepare for entering 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, nr_calls = 0;
+
+	if (!sleep_state_supported(state))
+		return -EPERM;
+
+	pm_prepare_console();
+
+	error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
+	if (error) {
+		nr_calls--;
+		goto Finish;
+	}
+
+	trace_suspend_resume(TPS("freeze_processes"), 0, true);
+	error = suspend_freeze_processes();
+	trace_suspend_resume(TPS("freeze_processes"), 0, false);
+	if (!error)
+		return 0;
+
+	log_suspend_abort_reason("One or more tasks refusing to freeze");
+	suspend_stats.failed_freeze++;
+	dpm_save_failed_step(SUSPEND_FREEZE);
+ Finish:
+	__pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL);
+	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, last_dev;
+
+	error = platform_suspend_prepare(state);
+	if (error)
+		goto Platform_finish;
+
+	error = dpm_suspend_late(PMSG_SUSPEND);
+	if (error) {
+		last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+		last_dev %= REC_FAILED_NUM;
+		pr_err("late suspend of devices failed\n");
+		log_suspend_abort_reason("late suspend of %s device failed",
+					 suspend_stats.failed_devs[last_dev]);
+		goto Platform_finish;
+	}
+	error = platform_suspend_prepare_late(state);
+	if (error)
+		goto Devices_early_resume;
+
+	if (state == PM_SUSPEND_TO_IDLE && pm_test_level != TEST_PLATFORM) {
+		s2idle_loop();
+		goto Platform_early_resume;
+	}
+
+	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	if (error) {
+		last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+		last_dev %= REC_FAILED_NUM;
+		pr_err("noirq suspend of devices failed\n");
+		log_suspend_abort_reason("noirq suspend of %s device failed",
+					 suspend_stats.failed_devs[last_dev]);
+		goto Platform_early_resume;
+	}
+	error = platform_suspend_prepare_noirq(state);
+	if (error)
+		goto Platform_wake;
+
+	if (suspend_test(TEST_PLATFORM))
+		goto Platform_wake;
+
+	error = disable_nonboot_cpus();
+	if (error || suspend_test(TEST_CPUS)) {
+		log_suspend_abort_reason("Disabling non-boot cpus failed");
+		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:
+	enable_nonboot_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;
+
+	error = platform_suspend_begin(state);
+	if (error)
+		goto Close;
+
+	suspend_console();
+	suspend_test_start();
+	error = dpm_suspend_start(PMSG_SUSPEND);
+	if (error) {
+		pr_err("Some devices failed to suspend, or early wake event detected\n");
+		log_suspend_abort_reason(
+				"Some devices failed to suspend, or early wake event detected");
+		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("resume_console"), state, true);
+	resume_console();
+	trace_suspend_resume(TPS("resume_console"), 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();
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+	pm_restore_console();
+}
+
+#if MTK_SOLUTION
+
+#define SYS_SYNC_TIMEOUT 2000
+
+static int sys_sync_ongoing;
+
+static void suspend_sys_sync(struct work_struct *work);
+static struct workqueue_struct *suspend_sys_sync_work_queue;
+DECLARE_WORK(suspend_sys_sync_work, suspend_sys_sync);
+
+static void suspend_sys_sync(struct work_struct *work)
+{
+	pr_debug("++\n");
+	ksys_sync();
+	sys_sync_ongoing = 0;
+	pr_debug("--\n");
+}
+
+int suspend_syssync_enqueue(void)
+{
+	int timeout = 0;
+
+	if (suspend_sys_sync_work_queue == NULL) {
+		suspend_sys_sync_work_queue =
+			create_singlethread_workqueue("fs_suspend_syssync");
+		if (suspend_sys_sync_work_queue == NULL) {
+			pr_info("fs_suspend_syssync workqueue create failed\n");
+			return -EBUSY;
+		}
+	}
+
+	while (timeout < SYS_SYNC_TIMEOUT) {
+		if (!sys_sync_ongoing)
+			break;
+		msleep(100);
+		timeout += 100;
+	}
+
+	if (!sys_sync_ongoing) {
+		sys_sync_ongoing = 1;
+		queue_work(suspend_sys_sync_work_queue, &suspend_sys_sync_work);
+		while (timeout < SYS_SYNC_TIMEOUT) {
+			if (!sys_sync_ongoing)
+				return 0;
+			msleep(100);
+			timeout += 100;
+		}
+	}
+
+	return -EBUSY;
+}
+
+
+#endif
+
+
+/**
+ * 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();
+
+#ifndef CONFIG_SUSPEND_SKIP_SYNC
+	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
+	pr_info("Syncing filesystems ... ");
+#if MTK_SOLUTION
+	error = suspend_syssync_enqueue();
+	if (error) {
+		pr_info("sys_sync timeout.\n");
+		goto Unlock;
+	}
+#else
+	ksys_sync();
+#endif
+	pr_cont("done.\n");
+	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
+#endif
+
+	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]);
+	pm_restrict_gfp_mask();
+	error = suspend_devices_and_enter(state);
+	pm_restore_gfp_mask();
+
+ 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);
+	if (error) {
+		suspend_stats.fail++;
+		dpm_save_failed_errno(error);
+	} else {
+		suspend_stats.success++;
+	}
+	pr_info("suspend exit\n");
+	return error;
+}
+EXPORT_SYMBOL(pm_suspend);

kernel/power/suspend_test.c

@@ -0,0 +1,220 @@
+/*
+ * kernel/power/suspend_test.c - Suspend to RAM and standby test facility.
+ *
+ * Copyright (c) 2009 Pavel Machek <pavel@ucw.cz>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#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";
+
+	unsigned long		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;
+	}
+	rtc_tm_to_time(&alm.time, &now);
+
+	memset(&alm, 0, sizeof alm);
+	rtc_time_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 (!candidate->ops->set_alarm)
+		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 0;
+
+	repeat = strsep(&value, ",");
+	if (repeat) {
+		if (kstrtou32(repeat, 0, &test_repeat_count_max))
+			return 0;
+	}
+
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+		if (!strcmp(pm_labels[i], suspend_type)) {
+			test_state_label = pm_labels[i];
+			return 0;
+		}
+
+	printk(warn_bad_state, suspend_type);
+	return 0;
+}
+__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);

kernel/power/user.c

@@ -0,0 +1,485 @@
+/*
+ * 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>
+ *
+ * This file is released under the GPLv2.
+ *
+ */
+
+#include <linux/suspend.h>
+#include <linux/syscalls.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"
+
+
+#define SNAPSHOT_MINOR	231
+
+static struct snapshot_data {
+	struct snapshot_handle handle;
+	int swap;
+	int mode;
+	bool frozen;
+	bool ready;
+	bool platform_support;
+	bool free_bitmaps;
+} snapshot_state;
+
+atomic_t snapshot_device_available = ATOMIC_INIT(1);
+
+static int snapshot_open(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+	int error, nr_calls = 0;
+
+	if (!hibernation_available())
+		return -EPERM;
+
+	lock_system_sleep();
+
+	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
+		error = -EBUSY;
+		goto Unlock;
+	}
+
+	if ((filp->f_flags & O_ACCMODE) == O_RDWR) {
+		atomic_inc(&snapshot_device_available);
+		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 = swsusp_resume_device ?
+			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
+		data->mode = O_RDONLY;
+		data->free_bitmaps = false;
+		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
+		if (error)
+			__pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL);
+	} else {
+		/*
+		 * Resuming.  We may need to wait for the image device to
+		 * appear.
+		 */
+		wait_for_device_probe();
+
+		data->swap = -1;
+		data->mode = O_WRONLY;
+		error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
+		if (!error) {
+			error = create_basic_memory_bitmaps();
+			data->free_bitmaps = !error;
+		} else
+			nr_calls--;
+
+		if (error)
+			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
+	}
+	if (error)
+		atomic_inc(&snapshot_device_available);
+
+	data->frozen = false;
+	data->ready = false;
+	data->platform_support = false;
+
+ Unlock:
+	unlock_system_sleep();
+
+	return error;
+}
+
+static int snapshot_release(struct inode *inode, struct file *filp)
+{
+	struct snapshot_data *data;
+
+	lock_system_sleep();
+
+	swsusp_free();
+	data = filp->private_data;
+	free_all_swap_pages(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);
+	atomic_inc(&snapshot_device_available);
+
+	unlock_system_sleep();
+
+	return 0;
+}
+
+static ssize_t snapshot_read(struct file *filp, char __user *buf,
+                             size_t count, loff_t *offp)
+{
+	struct snapshot_data *data;
+	ssize_t res;
+	loff_t pg_offp = *offp & ~PAGE_MASK;
+
+	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();
+
+	return res;
+}
+
+static ssize_t snapshot_write(struct file *filp, const char __user *buf,
+                              size_t count, loff_t *offp)
+{
+	struct snapshot_data *data;
+	ssize_t res;
+	loff_t pg_offp = *offp & ~PAGE_MASK;
+
+	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 - pg_offp;
+	}
+
+	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();
+
+	return res;
+}
+
+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 (_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;
+
+		printk("Syncing filesystems ... ");
+		ksys_sync();
+		printk("done.\n");
+
+		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:
+		snapshot_write_finalize(&data->handle);
+		if (data->mode != O_WRONLY || !data->frozen ||
+		    !snapshot_image_loaded(&data->handle)) {
+			error = -EPERM;
+			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:
+		if (swsusp_swap_in_use()) {
+			error = -EPERM;
+		} else {
+			struct resume_swap_area swap_area;
+			dev_t swdev;
+
+			error = copy_from_user(&swap_area, (void __user *)arg,
+					sizeof(struct resume_swap_area));
+			if (error) {
+				error = -EFAULT;
+				break;
+			}
+
+			/*
+			 * User space encodes device types as two-byte values,
+			 * so we need to recode them
+			 */
+			swdev = new_decode_dev(swap_area.dev);
+			if (swdev) {
+				offset = swap_area.offset;
+				data->swap = swap_type_of(swdev, offset, NULL);
+				if (data->swap < 0)
+					error = -ENODEV;
+			} else {
+				data->swap = -1;
+				error = -EINVAL;
+			}
+		}
+		break;
+
+	default:
+		error = -ENOTTY;
+
+	}
+
+	unlock_device_hotplug();
+	mutex_unlock(&system_transition_mutex);
+
+	return error;
+}
+
+#ifdef CONFIG_COMPAT
+
+struct compat_resume_swap_area {
+	compat_loff_t offset;
+	u32 dev;
+} __packed;
+
+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: {
+		compat_loff_t __user *uoffset = compat_ptr(arg);
+		loff_t offset;
+		mm_segment_t old_fs;
+		int err;
+
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		err = snapshot_ioctl(file, cmd, (unsigned long) &offset);
+		set_fs(old_fs);
+		if (!err && put_user(offset, uoffset))
+			err = -EFAULT;
+		return err;
+	}
+
+	case SNAPSHOT_CREATE_IMAGE:
+		return snapshot_ioctl(file, cmd,
+				      (unsigned long) compat_ptr(arg));
+
+	case SNAPSHOT_SET_SWAP_AREA: {
+		struct compat_resume_swap_area __user *u_swap_area =
+			compat_ptr(arg);
+		struct resume_swap_area swap_area;
+		mm_segment_t old_fs;
+		int err;
+
+		err = get_user(swap_area.offset, &u_swap_area->offset);
+		err |= get_user(swap_area.dev, &u_swap_area->dev);
+		if (err)
+			return -EFAULT;
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		err = snapshot_ioctl(file, SNAPSHOT_SET_SWAP_AREA,
+				     (unsigned long) &swap_area);
+		set_fs(old_fs);
+		return err;
+	}
+
+	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,
+	.llseek = no_llseek,
+	.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);

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;
+	char *str = buf;
+	char *end = buf + PAGE_SIZE;
+
+	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)
+			str += scnprintf(str, end - str, "%s ", wl->name);
+	}
+	if (str > buf)
+		str--;
+
+	str += scnprintf(str, end - str, "\n");
+
+	mutex_unlock(&wakelocks_lock);
+	return (str - buf);
+}
+
+#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(sizeof(*wl), GFP_KERNEL);
+	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;
+}

kernel/power/wakeup_reason.c

@@ -0,0 +1,436 @@
+/*
+ * kernel/power/wakeup_reason.c
+ *
+ * Logs the reasons which caused the kernel to resume from
+ * the suspend mode.
+ *
+ * Copyright (C) 2020 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/wakeup_reason.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+#include <linux/slab.h>
+
+/*
+ * struct wakeup_irq_node - stores data and relationships for IRQs logged as
+ * either base or nested wakeup reasons during suspend/resume flow.
+ * @siblings - for membership on leaf or parent IRQ lists
+ * @irq      - the IRQ number
+ * @irq_name - the name associated with the IRQ, or a default if none
+ */
+struct wakeup_irq_node {
+	struct list_head siblings;
+	int irq;
+	const char *irq_name;
+};
+
+enum wakeup_reason_flag {
+	RESUME_NONE = 0,
+	RESUME_IRQ,
+	RESUME_ABORT,
+	RESUME_ABNORMAL,
+};
+
+static DEFINE_SPINLOCK(wakeup_reason_lock);
+
+static LIST_HEAD(leaf_irqs);   /* kept in ascending IRQ sorted order */
+static LIST_HEAD(parent_irqs); /* unordered */
+
+static struct kmem_cache *wakeup_irq_nodes_cache;
+
+static const char *default_irq_name = "(unnamed)";
+
+static struct kobject *kobj;
+
+static bool capture_reasons;
+static int wakeup_reason;
+static char non_irq_wake_reason[MAX_SUSPEND_ABORT_LEN];
+
+static ktime_t last_monotime; /* monotonic time before last suspend */
+static ktime_t curr_monotime; /* monotonic time after last suspend */
+static ktime_t last_stime; /* monotonic boottime offset before last suspend */
+static ktime_t curr_stime; /* monotonic boottime offset after last suspend */
+
+static void init_node(struct wakeup_irq_node *p, int irq)
+{
+	struct irq_desc *desc;
+
+	INIT_LIST_HEAD(&p->siblings);
+
+	p->irq = irq;
+	desc = irq_to_desc(irq);
+	if (desc && desc->action && desc->action->name)
+		p->irq_name = desc->action->name;
+	else
+		p->irq_name = default_irq_name;
+}
+
+static struct wakeup_irq_node *create_node(int irq)
+{
+	struct wakeup_irq_node *result;
+
+	result = kmem_cache_alloc(wakeup_irq_nodes_cache, GFP_ATOMIC);
+	if (unlikely(!result))
+		pr_warn("Failed to log wakeup IRQ %d\n", irq);
+	else
+		init_node(result, irq);
+
+	return result;
+}
+
+static void delete_list(struct list_head *head)
+{
+	struct wakeup_irq_node *n;
+
+	while (!list_empty(head)) {
+		n = list_first_entry(head, struct wakeup_irq_node, siblings);
+		list_del(&n->siblings);
+		kmem_cache_free(wakeup_irq_nodes_cache, n);
+	}
+}
+
+static bool add_sibling_node_sorted(struct list_head *head, int irq)
+{
+	struct wakeup_irq_node *n = NULL;
+	struct list_head *predecessor = head;
+
+	if (unlikely(WARN_ON(!head)))
+		return NULL;
+
+	if (!list_empty(head))
+		list_for_each_entry(n, head, siblings) {
+			if (n->irq < irq)
+				predecessor = &n->siblings;
+			else if (n->irq == irq)
+				return true;
+			else
+				break;
+		}
+
+	n = create_node(irq);
+	if (n) {
+		list_add(&n->siblings, predecessor);
+		return true;
+	}
+
+	return false;
+}
+
+static struct wakeup_irq_node *find_node_in_list(struct list_head *head,
+						 int irq)
+{
+	struct wakeup_irq_node *n;
+
+	if (unlikely(WARN_ON(!head)))
+		return NULL;
+
+	list_for_each_entry(n, head, siblings)
+		if (n->irq == irq)
+			return n;
+
+	return NULL;
+}
+
+void log_irq_wakeup_reason(int irq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&wakeup_reason_lock, flags);
+	if (wakeup_reason == RESUME_ABNORMAL || wakeup_reason == RESUME_ABORT) {
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return;
+	}
+
+	if (!capture_reasons) {
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return;
+	}
+
+	if (find_node_in_list(&parent_irqs, irq) == NULL)
+		add_sibling_node_sorted(&leaf_irqs, irq);
+
+	wakeup_reason = RESUME_IRQ;
+	spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+}
+
+void log_threaded_irq_wakeup_reason(int irq, int parent_irq)
+{
+	struct wakeup_irq_node *parent;
+	unsigned long flags;
+
+	/*
+	 * Intentionally unsynchronized.  Calls that come in after we have
+	 * resumed should have a fast exit path since there's no work to be
+	 * done, any any coherence issue that could cause a wrong value here is
+	 * both highly improbable - given the set/clear timing - and very low
+	 * impact (parent IRQ gets logged instead of the specific child).
+	 */
+	if (!capture_reasons)
+		return;
+
+	spin_lock_irqsave(&wakeup_reason_lock, flags);
+
+	if (wakeup_reason == RESUME_ABNORMAL || wakeup_reason == RESUME_ABORT) {
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return;
+	}
+
+	if (!capture_reasons || (find_node_in_list(&leaf_irqs, irq) != NULL)) {
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return;
+	}
+
+	parent = find_node_in_list(&parent_irqs, parent_irq);
+	if (parent != NULL)
+		add_sibling_node_sorted(&leaf_irqs, irq);
+	else {
+		parent = find_node_in_list(&leaf_irqs, parent_irq);
+		if (parent != NULL) {
+			list_del_init(&parent->siblings);
+			list_add_tail(&parent->siblings, &parent_irqs);
+			add_sibling_node_sorted(&leaf_irqs, irq);
+		}
+	}
+
+	spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+}
+EXPORT_SYMBOL_GPL(log_threaded_irq_wakeup_reason);
+
+static void __log_abort_or_abnormal_wake(bool abort, const char *fmt,
+					 va_list args)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&wakeup_reason_lock, flags);
+
+	/* Suspend abort or abnormal wake reason has already been logged. */
+	if (wakeup_reason != RESUME_NONE) {
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return;
+	}
+
+	if (abort)
+		wakeup_reason = RESUME_ABORT;
+	else
+		wakeup_reason = RESUME_ABNORMAL;
+
+	vsnprintf(non_irq_wake_reason, MAX_SUSPEND_ABORT_LEN, fmt, args);
+
+	spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+}
+
+void log_suspend_abort_reason(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	__log_abort_or_abnormal_wake(true, fmt, args);
+	va_end(args);
+}
+
+void log_abnormal_wakeup_reason(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	__log_abort_or_abnormal_wake(false, fmt, args);
+	va_end(args);
+}
+
+void clear_wakeup_reasons(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&wakeup_reason_lock, flags);
+
+	delete_list(&leaf_irqs);
+	delete_list(&parent_irqs);
+	wakeup_reason = RESUME_NONE;
+	capture_reasons = true;
+
+	spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+}
+
+static void print_wakeup_sources(void)
+{
+	struct wakeup_irq_node *n;
+	unsigned long flags;
+
+	spin_lock_irqsave(&wakeup_reason_lock, flags);
+
+	capture_reasons = false;
+
+	if (wakeup_reason == RESUME_ABORT) {
+		pr_info("Abort: %s\n", non_irq_wake_reason);
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return;
+	}
+
+	if (wakeup_reason == RESUME_IRQ && !list_empty(&leaf_irqs))
+		list_for_each_entry(n, &leaf_irqs, siblings)
+			pr_info("Resume caused by IRQ %d, %s\n", n->irq,
+				n->irq_name);
+	else if (wakeup_reason == RESUME_ABNORMAL)
+		pr_info("Resume caused by %s\n", non_irq_wake_reason);
+	else
+		pr_info("Resume cause unknown\n");
+
+	spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+}
+
+static ssize_t last_resume_reason_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *buf)
+{
+	ssize_t buf_offset = 0;
+	struct wakeup_irq_node *n;
+	unsigned long flags;
+
+	spin_lock_irqsave(&wakeup_reason_lock, flags);
+
+	if (wakeup_reason == RESUME_ABORT) {
+		buf_offset = scnprintf(buf, PAGE_SIZE, "Abort: %s",
+				       non_irq_wake_reason);
+		spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+		return buf_offset;
+	}
+
+	if (wakeup_reason == RESUME_IRQ && !list_empty(&leaf_irqs))
+		list_for_each_entry(n, &leaf_irqs, siblings)
+			buf_offset += scnprintf(buf + buf_offset,
+						PAGE_SIZE - buf_offset,
+						"%d %s\n", n->irq, n->irq_name);
+	else if (wakeup_reason == RESUME_ABNORMAL)
+		buf_offset = scnprintf(buf, PAGE_SIZE, "-1 %s",
+				       non_irq_wake_reason);
+
+	spin_unlock_irqrestore(&wakeup_reason_lock, flags);
+
+	return buf_offset;
+}
+
+static ssize_t last_suspend_time_show(struct kobject *kobj,
+			struct kobj_attribute *attr, char *buf)
+{
+	struct timespec64 sleep_time;
+	struct timespec64 total_time;
+	struct timespec64 suspend_resume_time;
+
+	/*
+	 * total_time is calculated from monotonic bootoffsets because
+	 * unlike CLOCK_MONOTONIC it include the time spent in suspend state.
+	 */
+	total_time = ktime_to_timespec64(ktime_sub(curr_stime, last_stime));
+
+	/*
+	 * suspend_resume_time is calculated as monotonic (CLOCK_MONOTONIC)
+	 * time interval before entering suspend and post suspend.
+	 */
+	suspend_resume_time =
+		ktime_to_timespec64(ktime_sub(curr_monotime, last_monotime));
+
+	/* sleep_time = total_time - suspend_resume_time */
+	sleep_time = timespec64_sub(total_time, suspend_resume_time);
+
+	/* Export suspend_resume_time and sleep_time in pair here. */
+	return sprintf(buf, "%llu.%09lu %llu.%09lu\n",
+		       (unsigned long long)suspend_resume_time.tv_sec,
+		       suspend_resume_time.tv_nsec,
+		       (unsigned long long)sleep_time.tv_sec,
+		       sleep_time.tv_nsec);
+}
+
+static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason);
+static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time);
+
+static struct attribute *attrs[] = {
+	&resume_reason.attr,
+	&suspend_time.attr,
+	NULL,
+};
+static struct attribute_group attr_group = {
+	.attrs = attrs,
+};
+
+/* Detects a suspend and clears all the previous wake up reasons*/
+static int wakeup_reason_pm_event(struct notifier_block *notifier,
+		unsigned long pm_event, void *unused)
+{
+	switch (pm_event) {
+	case PM_SUSPEND_PREPARE:
+		/* monotonic time since boot */
+		last_monotime = ktime_get();
+		/* monotonic time since boot including the time spent in suspend */
+		last_stime = ktime_get_boottime();
+		clear_wakeup_reasons();
+		break;
+	case PM_POST_SUSPEND:
+		/* monotonic time since boot */
+		curr_monotime = ktime_get();
+		/* monotonic time since boot including the time spent in suspend */
+		curr_stime = ktime_get_boottime();
+		print_wakeup_sources();
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block wakeup_reason_pm_notifier_block = {
+	.notifier_call = wakeup_reason_pm_event,
+};
+
+static int __init wakeup_reason_init(void)
+{
+	if (register_pm_notifier(&wakeup_reason_pm_notifier_block)) {
+		pr_warn("[%s] failed to register PM notifier\n", __func__);
+		goto fail;
+	}
+
+	kobj = kobject_create_and_add("wakeup_reasons", kernel_kobj);
+	if (!kobj) {
+		pr_warn("[%s] failed to create a sysfs kobject\n", __func__);
+		goto fail_unregister_pm_notifier;
+	}
+
+	if (sysfs_create_group(kobj, &attr_group)) {
+		pr_warn("[%s] failed to create a sysfs group\n", __func__);
+		goto fail_kobject_put;
+	}
+
+	wakeup_irq_nodes_cache =
+		kmem_cache_create("wakeup_irq_node_cache",
+				  sizeof(struct wakeup_irq_node), 0, 0, NULL);
+	if (!wakeup_irq_nodes_cache)
+		goto fail_remove_group;
+
+	return 0;
+
+fail_remove_group:
+	sysfs_remove_group(kobj, &attr_group);
+fail_kobject_put:
+	kobject_put(kobj);
+fail_unregister_pm_notifier:
+	unregister_pm_notifier(&wakeup_reason_pm_notifier_block);
+fail:
+	return 1;
+}
+
+late_initcall(wakeup_reason_init);