Merge tag 'pm-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These add support for new processors (Sierra Forest, Grand Ridge and
  Meteor Lake) to the intel_idle driver, make intel_pstate run on
  Emerald Rapids without HWP support and adjust it to utilize EPP values
  supplied by the platform firmware, fix issues, clean up code and
  improve documentation.

  The most significant fix addresses deadlocks in the core system-wide
  resume code that occur if async_schedule_dev() attempts to run its
  argument function synchronously (for example, due to a memory
  allocation failure). It rearranges the code in question which may
  increase the system resume time in some cases, but this basically is a
  removal of a premature optimization. That optimization will be added
  back later, but properly this time.

  Specifics:

   - Add support for the Sierra Forest, Grand Ridge and Meteorlake SoCs
     to the intel_idle cpuidle driver (Artem Bityutskiy, Zhang Rui)

   - Do not enable interrupts when entering idle in the haltpoll cpuidle
     driver (Borislav Petkov)

   - Add Emerald Rapids support in no-HWP mode to the intel_pstate
     cpufreq driver (Zhenguo Yao)

   - Use EPP values programmed by the platform firmware as balanced
     performance ones by default in intel_pstate (Srinivas Pandruvada)

   - Add a missing function return value check to the SCMI cpufreq
     driver to avoid unexpected behavior (Alexandra Diupina)

   - Fix parameter type warning in the armada-8k cpufreq driver (Gregory
     CLEMENT)

   - Rework trans_stat_show() in the devfreq core code to avoid buffer
     overflows (Christian Marangi)

   - Synchronize devfreq_monitor_[start/stop] so as to prevent a timer
     list corruption from occurring when devfreq governors are switched
     frequently (Mukesh Ojha)

   - Fix possible deadlocks in the core system-wide PM code that occur
     if device-handling functions cannot be executed asynchronously
     during resume from system-wide suspend (Rafael J. Wysocki)

   - Clean up unnecessary local variable initializations in multiple
     places in the hibernation code (Wang chaodong, Li zeming)

   - Adjust core hibernation code to avoid missing wakeup events that
     occur after saving an image to persistent storage (Chris Feng)

   - Update hibernation code to enforce correct ordering during image
     compression and decompression (Hongchen Zhang)

   - Use kmap_local_page() instead of kmap_atomic() in copy_data_page()
     during hibernation and restore (Chen Haonan)

   - Adjust documentation and code comments to reflect recent tasks
     freezer changes (Kevin Hao)

   - Repair excess function parameter description warning in the
     hibernation image-saving code (Randy Dunlap)

   - Fix _set_required_opps when opp is NULL (Bryan O'Donoghue)

   - Use device_get_match_data() in the OPP code for TI (Rob Herring)

   - Clean up OPP level and other parts and call dev_pm_opp_set_opp()
     recursively for required OPPs (Viresh Kumar)"

* tag 'pm-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (35 commits)
  OPP: Rename 'rate_clk_single'
  OPP: Pass rounded rate to _set_opp()
  OPP: Relocate dev_pm_opp_sync_regulators()
  PM: sleep: Fix possible deadlocks in core system-wide PM code
  OPP: Move dev_pm_opp_icc_bw to internal opp.h
  async: Introduce async_schedule_dev_nocall()
  async: Split async_schedule_node_domain()
  cpuidle: haltpoll: Do not enable interrupts when entering idle
  OPP: Fix _set_required_opps when opp is NULL
  OPP: The level field is always of unsigned int type
  PM: hibernate: Repair excess function parameter description warning
  PM: sleep: Remove obsolete comment from unlock_system_sleep()
  cpufreq: intel_pstate: Add Emerald Rapids support in no-HWP mode
  Documentation: PM: Adjust freezing-of-tasks.rst to the freezer changes
  PM: hibernate: Use kmap_local_page() in copy_data_page()
  intel_idle: add Sierra Forest SoC support
  intel_idle: add Grand Ridge SoC support
  PM / devfreq: Synchronize devfreq_monitor_[start/stop]
  cpufreq: armada-8k: Fix parameter type warning
  PM: hibernate: Enforce ordering during image compression/decompression
  ...

21 files changed, 658 insertions, 395 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index 5e6b74f30406..1e7e0bb4c14e 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -52,6 +52,9 @@ Description:
 
 			echo 0 > /sys/class/devfreq/.../trans_stat
 
+		If the transition table is bigger than PAGE_SIZE, reading
+		this will return an -EFBIG error.
+
 What:		/sys/class/devfreq/.../available_frequencies
 Date:		October 2012
 Contact:	Nishanth Menon <nm@ti.com>
diff --git a/Documentation/power/freezing-of-tasks.rst b/Documentation/power/freezing-of-tasks.rst
index 53b6a56c4635..df9755bfbd94 100644
--- a/Documentation/power/freezing-of-tasks.rst
+++ b/Documentation/power/freezing-of-tasks.rst
@@ -14,27 +14,28 @@ architectures).
 II. How does it work?
 =====================
 
-There are three per-task flags used for that, PF_NOFREEZE, PF_FROZEN
-and PF_FREEZER_SKIP (the last one is auxiliary).  The tasks that have
-PF_NOFREEZE unset (all user space processes and some kernel threads) are
-regarded as 'freezable' and treated in a special way before the system enters a
-suspend state as well as before a hibernation image is created (in what follows
-we only consider hibernation, but the description also applies to suspend).
+There is one per-task flag (PF_NOFREEZE) and three per-task states
+(TASK_FROZEN, TASK_FREEZABLE and __TASK_FREEZABLE_UNSAFE) used for that.
+The tasks that have PF_NOFREEZE unset (all user space tasks and some kernel
+threads) are regarded as 'freezable' and treated in a special way before the
+system enters a sleep state as well as before a hibernation image is created
+(hibernation is directly covered by what follows, but the description applies
+to system-wide suspend too).
 
 Namely, as the first step of the hibernation procedure the function
 freeze_processes() (defined in kernel/power/process.c) is called.  A system-wide
-variable system_freezing_cnt (as opposed to a per-task flag) is used to indicate
-whether the system is to undergo a freezing operation. And freeze_processes()
-sets this variable.  After this, it executes try_to_freeze_tasks() that sends a
-fake signal to all user space processes, and wakes up all the kernel threads.
-All freezable tasks must react to that by calling try_to_freeze(), which
-results in a call to __refrigerator() (defined in kernel/freezer.c), which sets
-the task's PF_FROZEN flag, changes its state to TASK_UNINTERRUPTIBLE and makes
-it loop until PF_FROZEN is cleared for it. Then, we say that the task is
-'frozen' and therefore the set of functions handling this mechanism is referred
-to as 'the freezer' (these functions are defined in kernel/power/process.c,
-kernel/freezer.c & include/linux/freezer.h). User space processes are generally
-frozen before kernel threads.
+static key freezer_active (as opposed to a per-task flag or state) is used to
+indicate whether the system is to undergo a freezing operation. And
+freeze_processes() sets this static key.  After this, it executes
+try_to_freeze_tasks() that sends a fake signal to all user space processes, and
+wakes up all the kernel threads. All freezable tasks must react to that by
+calling try_to_freeze(), which results in a call to __refrigerator() (defined
+in kernel/freezer.c), which changes the task's state to TASK_FROZEN, and makes
+it loop until it is woken by an explicit TASK_FROZEN wakeup. Then, that task
+is regarded as 'frozen' and so the set of functions handling this mechanism is
+referred to as 'the freezer' (these functions are defined in
+kernel/power/process.c, kernel/freezer.c & include/linux/freezer.h). User space
+tasks are generally frozen before kernel threads.
 
 __refrigerator() must not be called directly.  Instead, use the
 try_to_freeze() function (defined in include/linux/freezer.h), that checks
@@ -43,31 +44,40 @@ if the task is to be frozen and makes the task enter __refrigerator().
 For user space processes try_to_freeze() is called automatically from the
 signal-handling code, but the freezable kernel threads need to call it
 explicitly in suitable places or use the wait_event_freezable() or
-wait_event_freezable_timeout() macros (defined in include/linux/freezer.h)
-that combine interruptible sleep with checking if the task is to be frozen and
-calling try_to_freeze().  The main loop of a freezable kernel thread may look
+wait_event_freezable_timeout() macros (defined in include/linux/wait.h)
+that put the task to sleep (TASK_INTERRUPTIBLE) or freeze it (TASK_FROZEN) if
+freezer_active is set. The main loop of a freezable kernel thread may look
 like the following one::
 
 	set_freezable();
-	do {
-		hub_events();
-		wait_event_freezable(khubd_wait,
-				!list_empty(&hub_event_list) ||
-				kthread_should_stop());
-	} while (!kthread_should_stop() || !list_empty(&hub_event_list));
-
-(from drivers/usb/core/hub.c::hub_thread()).
-
-If a freezable kernel thread fails to call try_to_freeze() after the freezer has
-initiated a freezing operation, the freezing of tasks will fail and the entire
-hibernation operation will be cancelled.  For this reason, freezable kernel
-threads must call try_to_freeze() somewhere or use one of the
+
+	while (true) {
+		struct task_struct *tsk = NULL;
+
+		wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL);
+		spin_lock_irq(&oom_reaper_lock);
+		if (oom_reaper_list != NULL) {
+			tsk = oom_reaper_list;
+			oom_reaper_list = tsk->oom_reaper_list;
+		}
+		spin_unlock_irq(&oom_reaper_lock);
+
+		if (tsk)
+			oom_reap_task(tsk);
+	}
+
+(from mm/oom_kill.c::oom_reaper()).
+
+If a freezable kernel thread is not put to the frozen state after the freezer
+has initiated a freezing operation, the freezing of tasks will fail and the
+entire system-wide transition will be cancelled.  For this reason, freezable
+kernel threads must call try_to_freeze() somewhere or use one of the
 wait_event_freezable() and wait_event_freezable_timeout() macros.
 
 After the system memory state has been restored from a hibernation image and
 devices have been reinitialized, the function thaw_processes() is called in
-order to clear the PF_FROZEN flag for each frozen task.  Then, the tasks that
-have been frozen leave __refrigerator() and continue running.
+order to wake up each frozen task.  Then, the tasks that have been frozen leave
+__refrigerator() and continue running.
 
 
 Rationale behind the functions dealing with freezing and thawing of tasks
@@ -96,7 +106,8 @@ III. Which kernel threads are freezable?
 Kernel threads are not freezable by default.  However, a kernel thread may clear
 PF_NOFREEZE for itself by calling set_freezable() (the resetting of PF_NOFREEZE
 directly is not allowed).  From this point it is regarded as freezable
-and must call try_to_freeze() in a suitable place.
+and must call try_to_freeze() or variants of wait_event_freezable() in a
+suitable place.
 
 IV. Why do we do that?
 ======================
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index f85f3515c258..9c5a5f4dba5a 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev)
 }
 
 /**
- * device_resume_noirq - Execute a "noirq resume" callback for given device.
+ * __device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
@@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev)
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static int device_resume_noirq(struct device *dev, pm_message_t state, bool async)
+static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -655,7 +655,13 @@ Skip:
 Out:
 	complete_all(&dev->power.completion);
 	TRACE_RESUME(error);
-	return error;
+
+	if (error) {
+		suspend_stats.failed_resume_noirq++;
+		dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
+	}
 }
 
 static bool is_async(struct device *dev)
@@ -668,11 +674,15 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
 	reinit_completion(&dev->power.completion);
 
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(func, dev);
+	if (!is_async(dev))
+		return false;
+
+	get_device(dev);
+
+	if (async_schedule_dev_nocall(func, dev))
 		return true;
-	}
+
+	put_device(dev);
 
 	return false;
 }
@@ -680,15 +690,19 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
-	int error;
-
-	error = device_resume_noirq(dev, pm_transition, true);
-	if (error)
-		pm_dev_err(dev, pm_transition, " async", error);
 
+	__device_resume_noirq(dev, pm_transition, true);
 	put_device(dev);
 }
 
+static void device_resume_noirq(struct device *dev)
+{
+	if (dpm_async_fn(dev, async_resume_noirq))
+		return;
+
+	__device_resume_noirq(dev, pm_transition, false);
+}
+
 static void dpm_noirq_resume_devices(pm_message_t state)
 {
 	struct device *dev;
@@ -698,14 +712,6 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
-	/*
-	 * Advanced the async threads upfront,
-	 * in case the starting of async threads is
-	 * delayed by non-async resuming devices.
-	 */
-	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
-		dpm_async_fn(dev, async_resume_noirq);
-
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
 		get_device(dev);
@@ -713,17 +719,7 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		if (!is_async(dev)) {
-			int error;
-
-			error = device_resume_noirq(dev, state, false);
-			if (error) {
-				suspend_stats.failed_resume_noirq++;
-				dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
-				dpm_save_failed_dev(dev_name(dev));
-				pm_dev_err(dev, state, " noirq", error);
-			}
-		}
+		device_resume_noirq(dev);
 
 		put_device(dev);
 
@@ -751,14 +747,14 @@ void dpm_resume_noirq(pm_message_t state)
 }
 
 /**
- * device_resume_early - Execute an "early resume" callback for given device.
+ * __device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  *
  * Runtime PM is disabled for @dev while this function is being executed.
  */
-static int device_resume_early(struct device *dev, pm_message_t state, bool async)
+static void __device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -811,21 +807,31 @@ Out:
 
 	pm_runtime_enable(dev);
 	complete_all(&dev->power.completion);
-	return error;
+
+	if (error) {
+		suspend_stats.failed_resume_early++;
+		dpm_save_failed_step(SUSPEND_RESUME_EARLY);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async early" : " early", error);
+	}
 }
 
 static void async_resume_early(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
-	int error;
-
-	error = device_resume_early(dev, pm_transition, true);
-	if (error)
-		pm_dev_err(dev, pm_transition, " async", error);
 
+	__device_resume_early(dev, pm_transition, true);
 	put_device(dev);
 }
 
+static void device_resume_early(struct device *dev)
+{
+	if (dpm_async_fn(dev, async_resume_early))
+		return;
+
+	__device_resume_early(dev, pm_transition, false);
+}
+
 /**
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
@@ -839,14 +845,6 @@ void dpm_resume_early(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
-	/*
-	 * Advanced the async threads upfront,
-	 * in case the starting of async threads is
-	 * delayed by non-async resuming devices.
-	 */
-	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
-		dpm_async_fn(dev, async_resume_early);
-
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
 		get_device(dev);
@@ -854,17 +852,7 @@ void dpm_resume_early(pm_message_t state)
 
 		mutex_unlock(&dpm_list_mtx);
 
-		if (!is_async(dev)) {
-			int error;
-
-			error = device_resume_early(dev, state, false);
-			if (error) {
-				suspend_stats.failed_resume_early++;
-				dpm_save_failed_step(SUSPEND_RESUME_EARLY);
-				dpm_save_failed_dev(dev_name(dev));
-				pm_dev_err(dev, state, " early", error);
-			}
-		}
+		device_resume_early(dev);
 
 		put_device(dev);
 
@@ -888,12 +876,12 @@ void dpm_resume_start(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_resume_start);
 
 /**
- * device_resume - Execute "resume" callbacks for given device.
+ * __device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  */
-static int device_resume(struct device *dev, pm_message_t state, bool async)
+static void __device_resume(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -975,20 +963,30 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 
 	TRACE_RESUME(error);
 
-	return error;
+	if (error) {
+		suspend_stats.failed_resume++;
+		dpm_save_failed_step(SUSPEND_RESUME);
+		dpm_save_failed_dev(dev_name(dev));
+		pm_dev_err(dev, state, async ? " async" : "", error);
+	}
 }
 
 static void async_resume(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
-	int error;
 
-	error = device_resume(dev, pm_transition, true);
-	if (error)
-		pm_dev_err(dev, pm_transition, " async", error);
+	__device_resume(dev, pm_transition, true);
 	put_device(dev);
 }
 
+static void device_resume(struct device *dev)
+{
+	if (dpm_async_fn(dev, async_resume))
+		return;
+
+	__device_resume(dev, pm_transition, false);
+}
+
 /**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
@@ -1008,27 +1006,17 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
-	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
-		dpm_async_fn(dev, async_resume);
-
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
+
 		get_device(dev);
-		if (!is_async(dev)) {
-			int error;
 
-			mutex_unlock(&dpm_list_mtx);
+		mutex_unlock(&dpm_list_mtx);
+
+		device_resume(dev);
 
-			error = device_resume(dev, state, false);
-			if (error) {
-				suspend_stats.failed_resume++;
-				dpm_save_failed_step(SUSPEND_RESUME);
-				dpm_save_failed_dev(dev_name(dev));
-				pm_dev_err(dev, state, "", error);
-			}
+		mutex_lock(&dpm_list_mtx);
 
-			mutex_lock(&dpm_list_mtx);
-		}
 		if (!list_empty(&dev->power.entry))
 			list_move_tail(&dev->power.entry, &dpm_prepared_list);
 
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
index 8afefdea4d80..ce5a5641b6dd 100644
--- a/drivers/cpufreq/armada-8k-cpufreq.c
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -57,7 +57,7 @@ static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk,
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 		if (IS_ERR(clk)) {
 			pr_warn("Cannot get clock for CPU %d\n", cpu);
 		} else {
@@ -165,7 +165,7 @@ static int __init armada_8k_cpufreq_init(void)
 			continue;
 		}
 
-		clk = clk_get(cpu_dev, 0);
+		clk = clk_get(cpu_dev, NULL);
 
 		if (IS_ERR(clk)) {
 			pr_err("Cannot get clock for CPU %d\n", cpu);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a534a1f7f1ee..3c69040920b8 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1692,13 +1692,6 @@ static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
 	cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 
 	/*
-	 * If this CPU gen doesn't call for change in balance_perf
-	 * EPP return.
-	 */
-	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
-		return;
-
-	/*
 	 * If the EPP is set by firmware, which means that firmware enabled HWP
 	 * - Is equal or less than 0x80 (default balance_perf EPP)
 	 * - But less performance oriented than performance EPP
@@ -1711,6 +1704,13 @@ static void intel_pstate_update_epp_defaults(struct cpudata *cpudata)
 	}
 
 	/*
+	 * If this CPU gen doesn't call for change in balance_perf
+	 * EPP return.
+	 */
+	if (epp_values[EPP_INDEX_BALANCE_PERFORMANCE] == HWP_EPP_BALANCE_PERFORMANCE)
+		return;
+
+	/*
 	 * Use hard coded value per gen to update the balance_perf
 	 * and default EPP.
 	 */
@@ -2406,6 +2406,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(ICELAKE_X,		core_funcs),
 	X86_MATCH(TIGERLAKE,		core_funcs),
 	X86_MATCH(SAPPHIRERAPIDS_X,	core_funcs),
+	X86_MATCH(EMERALDRAPIDS_X,      core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index c8a7ccc42c16..4ee23f4ebf4a 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -334,8 +334,11 @@ static int scmi_cpufreq_probe(struct scmi_device *sdev)
 
 #ifdef CONFIG_COMMON_CLK
 	/* dummy clock provider as needed by OPP if clocks property is used */
-	if (of_property_present(dev->of_node, "#clock-cells"))
-		devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+	if (of_property_present(dev->of_node, "#clock-cells")) {
+		ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+		if (ret)
+			return dev_err_probe(dev, ret, "%s: registering clock provider failed\n", __func__);
+	}
 #endif
 
 	ret = cpufreq_register_driver(&scmi_cpufreq_driver);
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
index e66df22f9695..d8515d5c0853 100644
--- a/drivers/cpuidle/cpuidle-haltpoll.c
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -25,13 +25,12 @@ MODULE_PARM_DESC(force, "Load unconditionally");
 static struct cpuidle_device __percpu *haltpoll_cpuidle_devices;
 static enum cpuhp_state haltpoll_hp_state;
 
-static int default_enter_idle(struct cpuidle_device *dev,
-			      struct cpuidle_driver *drv, int index)
+static __cpuidle int default_enter_idle(struct cpuidle_device *dev,
+					struct cpuidle_driver *drv, int index)
 {
-	if (current_clr_polling_and_test()) {
-		local_irq_enable();
+	if (current_clr_polling_and_test())
 		return index;
-	}
+
 	arch_cpu_idle();
 	return index;
 }
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index b3a68d5833bd..98657d3b9435 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -461,10 +461,14 @@ static void devfreq_monitor(struct work_struct *work)
 	if (err)
 		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
 
+	if (devfreq->stop_polling)
+		goto out;
+
 	queue_delayed_work(devfreq_wq, &devfreq->work,
 				msecs_to_jiffies(devfreq->profile->polling_ms));
-	mutex_unlock(&devfreq->lock);
 
+out:
+	mutex_unlock(&devfreq->lock);
 	trace_devfreq_monitor(devfreq);
 }
 
@@ -483,6 +487,10 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 	if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN))
 		return;
 
+	mutex_lock(&devfreq->lock);
+	if (delayed_work_pending(&devfreq->work))
+		goto out;
+
 	switch (devfreq->profile->timer) {
 	case DEVFREQ_TIMER_DEFERRABLE:
 		INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
@@ -491,12 +499,16 @@ void devfreq_monitor_start(struct devfreq *devfreq)
 		INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
 		break;
 	default:
-		return;
+		goto out;
 	}
 
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
+
+out:
+	devfreq->stop_polling = false;
+	mutex_unlock(&devfreq->lock);
 }
 EXPORT_SYMBOL(devfreq_monitor_start);
 
@@ -513,6 +525,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq)
 	if (IS_SUPPORTED_FLAG(devfreq->governor->flags, IRQ_DRIVEN))
 		return;
 
+	mutex_lock(&devfreq->lock);
+	if (devfreq->stop_polling) {
+		mutex_unlock(&devfreq->lock);
+		return;
+	}
+
+	devfreq->stop_polling = true;
+	mutex_unlock(&devfreq->lock);
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_stop);
@@ -1688,7 +1708,7 @@ static ssize_t trans_stat_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct devfreq *df = to_devfreq(dev);
-	ssize_t len;
+	ssize_t len = 0;
 	int i, j;
 	unsigned int max_state;
 
@@ -1697,7 +1717,7 @@ static ssize_t trans_stat_show(struct device *dev,
 	max_state = df->max_state;
 
 	if (max_state == 0)
-		return sprintf(buf, "Not Supported.\n");
+		return sysfs_emit(buf, "Not Supported.\n");
 
 	mutex_lock(&df->lock);
 	if (!df->stop_polling &&
@@ -1707,31 +1727,49 @@ static ssize_t trans_stat_show(struct device *dev,
 	}
 	mutex_unlock(&df->lock);
 
-	len = sprintf(buf, "     From  :   To\n");
-	len += sprintf(buf + len, "           :");
-	for (i = 0; i < max_state; i++)
-		len += sprintf(buf + len, "%10lu",
-				df->freq_table[i]);
+	len += sysfs_emit_at(buf, len, "     From  :   To\n");
+	len += sysfs_emit_at(buf, len, "           :");
+	for (i = 0; i < max_state; i++) {
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10lu",
+				     df->freq_table[i]);
+	}
 
-	len += sprintf(buf + len, "   time(ms)\n");
+	if (len >= PAGE_SIZE - 1)
+		return PAGE_SIZE - 1;
+	len += sysfs_emit_at(buf, len, "   time(ms)\n");
 
 	for (i = 0; i < max_state; i++) {
-		if (df->freq_table[i] == df->previous_freq)
-			len += sprintf(buf + len, "*");
+		if (len >= PAGE_SIZE - 1)
+			break;
+		if (df->freq_table[2] == df->previous_freq)
+			len += sysfs_emit_at(buf, len, "*");
 		else
-			len += sprintf(buf + len, " ");
-
-		len += sprintf(buf + len, "%10lu:", df->freq_table[i]);
-		for (j = 0; j < max_state; j++)
-			len += sprintf(buf + len, "%10u",
+			len += sysfs_emit_at(buf, len, " ");
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10lu:", df->freq_table[i]);
+		for (j = 0; j < max_state; j++) {
+			if (len >= PAGE_SIZE - 1)
+				break;
+			len += sysfs_emit_at(buf, len, "%10u",
 				df->stats.trans_table[(i * max_state) + j]);
+		}
+		if (len >= PAGE_SIZE - 1)
+			break;
+		len += sysfs_emit_at(buf, len, "%10llu\n", (u64)
+				     jiffies64_to_msecs(df->stats.time_in_state[i]));
+	}
 
-		len += sprintf(buf + len, "%10llu\n", (u64)
-			jiffies64_to_msecs(df->stats.time_in_state[i]));
+	if (len < PAGE_SIZE - 1)
+		len += sysfs_emit_at(buf, len, "Total transition : %u\n",
+				     df->stats.total_trans);
+	if (len >= PAGE_SIZE - 1) {
+		pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n");
+		return -EFBIG;
 	}
 
-	len += sprintf(buf + len, "Total transition : %u\n",
-					df->stats.total_trans);
 	return len;
 }
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3e01a6b23e75..bcf1198e8991 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -918,6 +918,35 @@ static struct cpuidle_state adl_l_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state mtl_l_cstates[] __initdata = {
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 420,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C10",
+		.desc = "MWAIT 0x60",
+		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 310,
+		.target_residency = 930,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static struct cpuidle_state gmt_cstates[] __initdata = {
 	{
 		.name = "C1",
@@ -1237,6 +1266,72 @@ static struct cpuidle_state snr_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+static struct cpuidle_state grr_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 10,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6S",
+		.desc = "MWAIT 0x22",
+		.flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 140,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
+static struct cpuidle_state srf_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 1,
+		.target_residency = 1,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 2,
+		.target_residency = 10,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6S",
+		.desc = "MWAIT 0x22",
+		.flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 270,
+		.target_residency = 700,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6SP",
+		.desc = "MWAIT 0x23",
+		.flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 310,
+		.target_residency = 900,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static const struct idle_cpu idle_cpu_nehalem __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
@@ -1344,6 +1439,10 @@ static const struct idle_cpu idle_cpu_adl_l __initconst = {
 	.state_table = adl_l_cstates,
 };
 
+static const struct idle_cpu idle_cpu_mtl_l __initconst = {
+	.state_table = mtl_l_cstates,
+};
+
 static const struct idle_cpu idle_cpu_gmt __initconst = {
 	.state_table = gmt_cstates,
 };
@@ -1382,6 +1481,18 @@ static const struct idle_cpu idle_cpu_snr __initconst = {
 	.use_acpi = true,
 };
 
+static const struct idle_cpu idle_cpu_grr __initconst = {
+	.state_table = grr_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
+static const struct idle_cpu idle_cpu_srf __initconst = {
+	.state_table = srf_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&idle_cpu_nhx),
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&idle_cpu_nehalem),
@@ -1418,6 +1529,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&idle_cpu_icx),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&idle_cpu_adl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&idle_cpu_adl_l),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&idle_cpu_mtl_l),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&idle_cpu_gmt),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&idle_cpu_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&idle_cpu_spr),
@@ -1427,6 +1539,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&idle_cpu_bxt),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&idle_cpu_dnv),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&idle_cpu_snr),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT,	&idle_cpu_grr),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	&idle_cpu_srf),
 	{}
 };
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 84f345c69ea5..c4e0432ae42a 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -201,7 +201,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq_indexed);
  * @opp:	opp for which level value has to be returned for
  *
  * Return: level read from device tree corresponding to the opp, else
- * return 0.
+ * return U32_MAX.
  */
 unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp)
 {
@@ -221,7 +221,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_level);
  * @index:	index of the required opp
  *
  * Return: performance state read from device tree corresponding to the
- * required opp, else return 0.
+ * required opp, else return U32_MAX.
  */
 unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp,
 					    unsigned int index)
@@ -808,6 +808,16 @@ struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 	struct dev_pm_opp *opp;
 
 	opp = _find_key_ceil(dev, &temp, 0, true, _read_level, NULL);
+	if (IS_ERR(opp))
+		return opp;
+
+	/* False match */
+	if (temp == OPP_LEVEL_UNSET) {
+		dev_err(dev, "%s: OPP levels aren't available\n", __func__);
+		dev_pm_opp_put(opp);
+		return ERR_PTR(-ENODEV);
+	}
+
 	*level = temp;
 	return opp;
 }
@@ -832,9 +842,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
  * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-					       unsigned long *level)
+					       unsigned int *level)
 {
-	return _find_key_floor(dev, level, 0, true, _read_level, NULL);
+	unsigned long temp = *level;
+	struct dev_pm_opp *opp;
+
+	opp = _find_key_floor(dev, &temp, 0, true, _read_level, NULL);
+	*level = temp;
+	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_floor);
 
@@ -948,7 +963,7 @@ _opp_config_clk_single(struct device *dev, struct opp_table *opp_table,
 		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
 			ret);
 	} else {
-		opp_table->rate_clk_single = freq;
+		opp_table->current_rate_single_clk = freq;
 	}
 
 	return ret;
@@ -1046,40 +1061,23 @@ static int _set_opp_bw(const struct opp_table *opp_table,
 	return 0;
 }
 
-static int _set_performance_state(struct device *dev, struct device *pd_dev,
-				  struct dev_pm_opp *opp, int i)
+/* This is only called for PM domain for now */
+static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
+			      struct dev_pm_opp *opp, bool up)
 {
-	unsigned int pstate = likely(opp) ? opp->required_opps[i]->level: 0;
-	int ret;
+	struct device **devs = opp_table->required_devs;
+	struct dev_pm_opp *required_opp;
+	int index, target, delta, ret;
 
-	if (!pd_dev)
+	if (!devs)
 		return 0;
 
-	ret = dev_pm_domain_set_performance_state(pd_dev, pstate);
-	if (ret) {
-		dev_err(dev, "Failed to set performance state of %s: %d (%d)\n",
-			dev_name(pd_dev), pstate, ret);
-	}
-
-	return ret;
-}
-
-static int _opp_set_required_opps_generic(struct device *dev,
-	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
-{
-	dev_err(dev, "setting required-opps isn't supported for non-genpd devices\n");
-	return -ENOENT;
-}
-
-static int _opp_set_required_opps_genpd(struct device *dev,
-	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
-{
-	struct device **genpd_virt_devs =
-		opp_table->genpd_virt_devs ? opp_table->genpd_virt_devs : &dev;
-	int index, target, delta, ret;
+	/* required-opps not fully initialized yet */
+	if (lazy_linking_pending(opp_table))
+		return -EBUSY;
 
 	/* Scaling up? Set required OPPs in normal order, else reverse */
-	if (!scaling_down) {
+	if (up) {
 		index = 0;
 		target = opp_table->required_opp_count;
 		delta = 1;
@@ -1090,9 +1088,13 @@ static int _opp_set_required_opps_genpd(struct device *dev,
 	}
 
 	while (index != target) {
-		ret = _set_performance_state(dev, genpd_virt_devs[index], opp, index);
-		if (ret)
-			return ret;
+		if (devs[index]) {
+			required_opp = opp ? opp->required_opps[index] : NULL;
+
+			ret = dev_pm_opp_set_opp(devs[index], required_opp);
+			if (ret)
+				return ret;
+		}
 
 		index += delta;
 	}
@@ -1100,34 +1102,6 @@ static int _opp_set_required_opps_genpd(struct device *dev,
 	return 0;
 }
 
-/* This is only called for PM domain for now */
-static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
-			      struct dev_pm_opp *opp, bool up)
-{
-	/* required-opps not fully initialized yet */
-	if (lazy_linking_pending(opp_table))
-		return -EBUSY;
-
-	if (opp_table->set_required_opps)
-		return opp_table->set_required_opps(dev, opp_table, opp, up);
-
-	return 0;
-}
-
-/* Update set_required_opps handler */
-void _update_set_required_opps(struct opp_table *opp_table)
-{
-	/* Already set */
-	if (opp_table->set_required_opps)
-		return;
-
-	/* All required OPPs will belong to genpd or none */
-	if (opp_table->required_opp_tables[0]->is_genpd)
-		opp_table->set_required_opps = _opp_set_required_opps_genpd;
-	else
-		opp_table->set_required_opps = _opp_set_required_opps_generic;
-}
-
 static int _set_opp_level(struct device *dev, struct opp_table *opp_table,
 			  struct dev_pm_opp *opp)
 {
@@ -1135,7 +1109,7 @@ static int _set_opp_level(struct device *dev, struct opp_table *opp_table,
 	int ret = 0;
 
 	if (opp) {
-		if (!opp->level)
+		if (opp->level == OPP_LEVEL_UNSET)
 			return 0;
 
 		level = opp->level;
@@ -1378,12 +1352,12 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		 * value of the frequency. In such a case, do not abort but
 		 * configure the hardware to the desired frequency forcefully.
 		 */
-		forced = opp_table->rate_clk_single != target_freq;
+		forced = opp_table->current_rate_single_clk != freq;
 	}
 
-	ret = _set_opp(dev, opp_table, opp, &target_freq, forced);
+	ret = _set_opp(dev, opp_table, opp, &freq, forced);
 
-	if (target_freq)
+	if (freq)
 		dev_pm_opp_put(opp);
 
 put_opp_table:
@@ -1867,6 +1841,8 @@ struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table)
 
 	INIT_LIST_HEAD(&opp->node);
 
+	opp->level = OPP_LEVEL_UNSET;
+
 	return opp;
 }
 
@@ -2388,19 +2364,13 @@ static void _opp_detach_genpd(struct opp_table *opp_table)
 {
 	int index;
 
-	if (!opp_table->genpd_virt_devs)
-		return;
-
 	for (index = 0; index < opp_table->required_opp_count; index++) {
-		if (!opp_table->genpd_virt_devs[index])
+		if (!opp_table->required_devs[index])
 			continue;
 
-		dev_pm_domain_detach(opp_table->genpd_virt_devs[index], false);
-		opp_table->genpd_virt_devs[index] = NULL;
+		dev_pm_domain_detach(opp_table->required_devs[index], false);
+		opp_table->required_devs[index] = NULL;
 	}
-
-	kfree(opp_table->genpd_virt_devs);
-	opp_table->genpd_virt_devs = NULL;
 }
 
 /*
@@ -2427,14 +2397,20 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 	int index = 0, ret = -EINVAL;
 	const char * const *name = names;
 
-	if (opp_table->genpd_virt_devs)
-		return 0;
+	if (!opp_table->required_devs) {
+		dev_err(dev, "Required OPPs not available, can't attach genpd\n");
+		return -EINVAL;
+	}
 
-	opp_table->genpd_virt_devs = kcalloc(opp_table->required_opp_count,
-					     sizeof(*opp_table->genpd_virt_devs),
-					     GFP_KERNEL);
-	if (!opp_table->genpd_virt_devs)
-		return -ENOMEM;
+	/* Genpd core takes care of propagation to parent genpd */
+	if (opp_table->is_genpd) {
+		dev_err(dev, "%s: Operation not supported for genpds\n", __func__);
+		return -EOPNOTSUPP;
+	}
+
+	/* Checking only the first one is enough ? */
+	if (opp_table->required_devs[0])
+		return 0;
 
 	while (*name) {
 		if (index >= opp_table->required_opp_count) {
@@ -2450,13 +2426,25 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 			goto err;
 		}
 
-		opp_table->genpd_virt_devs[index] = virt_dev;
+		/*
+		 * Add the virtual genpd device as a user of the OPP table, so
+		 * we can call dev_pm_opp_set_opp() on it directly.
+		 *
+		 * This will be automatically removed when the OPP table is
+		 * removed, don't need to handle that here.
+		 */
+		if (!_add_opp_dev(virt_dev, opp_table->required_opp_tables[index])) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		opp_table->required_devs[index] = virt_dev;
 		index++;
 		name++;
 	}
 
 	if (virt_devs)
-		*virt_devs = opp_table->genpd_virt_devs;
+		*virt_devs = opp_table->required_devs;
 
 	return 0;
 
@@ -2466,10 +2454,50 @@ err:
 
 }
 
+static int _opp_set_required_devs(struct opp_table *opp_table,
+				  struct device *dev,
+				  struct device **required_devs)
+{
+	int i;
+
+	if (!opp_table->required_devs) {
+		dev_err(dev, "Required OPPs not available, can't set required devs\n");
+		return -EINVAL;
+	}
+
+	/* Another device that shares the OPP table has set the required devs ? */
+	if (opp_table->required_devs[0])
+		return 0;
+
+	for (i = 0; i < opp_table->required_opp_count; i++) {
+		/* Genpd core takes care of propagation to parent genpd */
+		if (required_devs[i] && opp_table->is_genpd &&
+		    opp_table->required_opp_tables[i]->is_genpd) {
+			dev_err(dev, "%s: Operation not supported for genpds\n", __func__);
+			return -EOPNOTSUPP;
+		}
+
+		opp_table->required_devs[i] = required_devs[i];
+	}
+
+	return 0;
+}
+
+static void _opp_put_required_devs(struct opp_table *opp_table)
+{
+	int i;
+
+	for (i = 0; i < opp_table->required_opp_count; i++)
+		opp_table->required_devs[i] = NULL;
+}
+
 static void _opp_clear_config(struct opp_config_data *data)
 {
-	if (data->flags & OPP_CONFIG_GENPD)
+	if (data->flags & OPP_CONFIG_REQUIRED_DEVS)
+		_opp_put_required_devs(data->opp_table);
+	else if (data->flags & OPP_CONFIG_GENPD)
 		_opp_detach_genpd(data->opp_table);
+
 	if (data->flags & OPP_CONFIG_REGULATOR)
 		_opp_put_regulators(data->opp_table);
 	if (data->flags & OPP_CONFIG_SUPPORTED_HW)
@@ -2583,12 +2611,22 @@ int dev_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config)
 
 	/* Attach genpds */
 	if (config->genpd_names) {
+		if (config->required_devs)
+			goto err;
+
 		ret = _opp_attach_genpd(opp_table, dev, config->genpd_names,
 					config->virt_devs);
 		if (ret)
 			goto err;
 
 		data->flags |= OPP_CONFIG_GENPD;
+	} else if (config->required_devs) {
+		ret = _opp_set_required_devs(opp_table, dev,
+					     config->required_devs);
+		if (ret)
+			goto err;
+
+		data->flags |= OPP_CONFIG_REQUIRED_DEVS;
 	}
 
 	ret = xa_alloc(&opp_configs, &id, data, XA_LIMIT(1, INT_MAX),
@@ -2975,6 +3013,47 @@ put_table:
 EXPORT_SYMBOL_GPL(dev_pm_opp_adjust_voltage);
 
 /**
+ * dev_pm_opp_sync_regulators() - Sync state of voltage regulators
+ * @dev:	device for which we do this operation
+ *
+ * Sync voltage state of the OPP table regulators.
+ *
+ * Return: 0 on success or a negative error value.
+ */
+int dev_pm_opp_sync_regulators(struct device *dev)
+{
+	struct opp_table *opp_table;
+	struct regulator *reg;
+	int i, ret = 0;
+
+	/* Device may not have OPP table */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return 0;
+
+	/* Regulator may not be required for the device */
+	if (unlikely(!opp_table->regulators))
+		goto put_table;
+
+	/* Nothing to sync if voltage wasn't changed */
+	if (!opp_table->enabled)
+		goto put_table;
+
+	for (i = 0; i < opp_table->regulator_count; i++) {
+		reg = opp_table->regulators[i];
+		ret = regulator_sync_voltage(reg);
+		if (ret)
+			break;
+	}
+put_table:
+	/* Drop reference taken by _find_opp_table() */
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_sync_regulators);
+
+/**
  * dev_pm_opp_enable() - Enable a specific OPP
  * @dev:	device for which we do this operation
  * @freq:	OPP frequency to enable
@@ -3097,44 +3176,3 @@ void dev_pm_opp_remove_table(struct device *dev)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table);
-
-/**
- * dev_pm_opp_sync_regulators() - Sync state of voltage regulators
- * @dev:	device for which we do this operation
- *
- * Sync voltage state of the OPP table regulators.
- *
- * Return: 0 on success or a negative error value.
- */
-int dev_pm_opp_sync_regulators(struct device *dev)
-{
-	struct opp_table *opp_table;
-	struct regulator *reg;
-	int i, ret = 0;
-
-	/* Device may not have OPP table */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table))
-		return 0;
-
-	/* Regulator may not be required for the device */
-	if (unlikely(!opp_table->regulators))
-		goto put_table;
-
-	/* Nothing to sync if voltage wasn't changed */
-	if (!opp_table->enabled)
-		goto put_table;
-
-	for (i = 0; i < opp_table->regulator_count; i++) {
-		reg = opp_table->regulators[i];
-		ret = regulator_sync_voltage(reg);
-		if (ret)
-			break;
-	}
-put_table:
-	/* Drop reference taken by _find_opp_table() */
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_sync_regulators);
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 81fa27599d58..f9f0b22bccbb 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -165,7 +165,7 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	struct opp_table **required_opp_tables;
 	struct device_node *required_np, *np;
 	bool lazy = false;
-	int count, i;
+	int count, i, size;
 
 	/* Traversing the first OPP node is all we need */
 	np = of_get_next_available_child(opp_np, NULL);
@@ -179,12 +179,13 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	if (count <= 0)
 		goto put_np;
 
-	required_opp_tables = kcalloc(count, sizeof(*required_opp_tables),
-				      GFP_KERNEL);
+	size = sizeof(*required_opp_tables) + sizeof(*opp_table->required_devs);
+	required_opp_tables = kcalloc(count, size, GFP_KERNEL);
 	if (!required_opp_tables)
 		goto put_np;
 
 	opp_table->required_opp_tables = required_opp_tables;
+	opp_table->required_devs = (void *)(required_opp_tables + count);
 	opp_table->required_opp_count = count;
 
 	for (i = 0; i < count; i++) {
@@ -208,8 +209,6 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 		mutex_lock(&opp_table_lock);
 		list_add(&opp_table->lazy, &lazy_opp_tables);
 		mutex_unlock(&opp_table_lock);
-	} else {
-		_update_set_required_opps(opp_table);
 	}
 
 	goto put_np;
@@ -296,7 +295,7 @@ void _of_clear_opp(struct opp_table *opp_table, struct dev_pm_opp *opp)
 	of_node_put(opp->np);
 }
 
-static int _link_required_opps(struct dev_pm_opp *opp,
+static int _link_required_opps(struct dev_pm_opp *opp, struct opp_table *opp_table,
 			       struct opp_table *required_table, int index)
 {
 	struct device_node *np;
@@ -314,6 +313,39 @@ static int _link_required_opps(struct dev_pm_opp *opp,
 		return -ENODEV;
 	}
 
+	/*
+	 * There are two genpd (as required-opp) cases that we need to handle,
+	 * devices with a single genpd and ones with multiple genpds.
+	 *
+	 * The single genpd case requires special handling as we need to use the
+	 * same `dev` structure (instead of a virtual one provided by genpd
+	 * core) for setting the performance state.
+	 *
+	 * It doesn't make sense for a device's DT entry to have both
+	 * "opp-level" and single "required-opps" entry pointing to a genpd's
+	 * OPP, as that would make the OPP core call
+	 * dev_pm_domain_set_performance_state() for two different values for
+	 * the same device structure. Lets treat single genpd configuration as a
+	 * case where the OPP's level is directly available without required-opp
+	 * link in the DT.
+	 *
+	 * Just update the `level` with the right value, which
+	 * dev_pm_opp_set_opp() will take care of in the normal path itself.
+	 *
+	 * There is another case though, where a genpd's OPP table has
+	 * required-opps set to a parent genpd. The OPP core expects the user to
+	 * set the respective required `struct device` pointer via
+	 * dev_pm_opp_set_config().
+	 */
+	if (required_table->is_genpd && opp_table->required_opp_count == 1 &&
+	    !opp_table->required_devs[0]) {
+		/* Genpd core takes care of propagation to parent genpd */
+		if (!opp_table->is_genpd) {
+			if (!WARN_ON(opp->level != OPP_LEVEL_UNSET))
+				opp->level = opp->required_opps[0]->level;
+		}
+	}
+
 	return 0;
 }
 
@@ -338,7 +370,7 @@ static int _of_opp_alloc_required_opps(struct opp_table *opp_table,
 		if (IS_ERR_OR_NULL(required_table))
 			continue;
 
-		ret = _link_required_opps(opp, required_table, i);
+		ret = _link_required_opps(opp, opp_table, required_table, i);
 		if (ret)
 			goto free_required_opps;
 	}
@@ -359,7 +391,7 @@ static int lazy_link_required_opps(struct opp_table *opp_table,
 	int ret;
 
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
-		ret = _link_required_opps(opp, new_table, index);
+		ret = _link_required_opps(opp, opp_table, new_table, index);
 		if (ret)
 			return ret;
 	}
@@ -422,7 +454,6 @@ static void lazy_link_required_opp_table(struct opp_table *new_table)
 
 		/* All required opp-tables found, remove from lazy list */
 		if (!lazy) {
-			_update_set_required_opps(opp_table);
 			list_del_init(&opp_table->lazy);
 
 			list_for_each_entry(opp, &opp_table->opp_list, node)
@@ -1393,8 +1424,14 @@ int of_get_required_opp_performance_state(struct device_node *np, int index)
 
 	opp = _find_opp_of_np(opp_table, required_np);
 	if (opp) {
-		pstate = opp->level;
+		if (opp->level == OPP_LEVEL_UNSET) {
+			pr_err("%s: OPP levels aren't available for %pOF\n",
+			       __func__, np);
+		} else {
+			pstate = opp->level;
+		}
 		dev_pm_opp_put(opp);
+
 	}
 
 	dev_pm_opp_put_opp_table(opp_table);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 08366f90f16b..cff1fabd1ae3 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -35,6 +35,7 @@ extern struct list_head opp_tables;
 #define OPP_CONFIG_PROP_NAME		BIT(3)
 #define OPP_CONFIG_SUPPORTED_HW		BIT(4)
 #define OPP_CONFIG_GENPD		BIT(5)
+#define OPP_CONFIG_REQUIRED_DEVS	BIT(6)
 
 /**
  * struct opp_config_data - data for set config operations
@@ -49,6 +50,18 @@ struct opp_config_data {
 	unsigned int flags;
 };
 
+/**
+ * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
+ * @avg:	Average bandwidth corresponding to this OPP (in icc units)
+ * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
+ *
+ * This structure stores the bandwidth values for a single interconnect path.
+ */
+struct dev_pm_opp_icc_bw {
+	u32 avg;
+	u32 peak;
+};
+
 /*
  * Internal data structure organization with the OPP layer library is as
  * follows:
@@ -157,12 +170,12 @@ enum opp_table_access {
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
  * @parsed_static_opps: Count of devices for which OPPs are initialized from DT.
  * @shared_opp: OPP is shared between multiple devices.
- * @rate_clk_single: Currently configured frequency for single clk.
+ * @current_rate_single_clk: Currently configured frequency for single clk.
  * @current_opp: Currently configured OPP for the table.
  * @suspend_opp: Pointer to OPP to be used during device suspend.
- * @genpd_virt_devs: List of virtual devices for multiple genpd support.
  * @required_opp_tables: List of device OPP tables that are required by OPPs in
  *		this table.
+ * @required_devs: List of devices for required OPP tables.
  * @required_opp_count: Number of required devices.
  * @supported_hw: Array of version number to support.
  * @supported_hw_count: Number of elements in supported_hw array.
@@ -180,7 +193,6 @@ enum opp_table_access {
  * @path_count: Number of interconnect paths
  * @enabled: Set to true if the device's resources are enabled/configured.
  * @is_genpd: Marks if the OPP table belongs to a genpd.
- * @set_required_opps: Helper responsible to set required OPPs.
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -207,12 +219,12 @@ struct opp_table {
 
 	unsigned int parsed_static_opps;
 	enum opp_table_access shared_opp;
-	unsigned long rate_clk_single;
+	unsigned long current_rate_single_clk;
 	struct dev_pm_opp *current_opp;
 	struct dev_pm_opp *suspend_opp;
 
-	struct device **genpd_virt_devs;
 	struct opp_table **required_opp_tables;
+	struct device **required_devs;
 	unsigned int required_opp_count;
 
 	unsigned int *supported_hw;
@@ -229,8 +241,6 @@ struct opp_table {
 	unsigned int path_count;
 	bool enabled;
 	bool is_genpd;
-	int (*set_required_opps)(struct device *dev,
-		struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down);
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
diff --git a/drivers/opp/ti-opp-supply.c b/drivers/opp/ti-opp-supply.c
index 8f3f13fbbb25..e3b97cd1fbbf 100644
--- a/drivers/opp/ti-opp-supply.c
+++ b/drivers/opp/ti-opp-supply.c
@@ -18,6 +18,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 
@@ -373,23 +374,15 @@ static int ti_opp_supply_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device *cpu_dev = get_cpu_device(0);
-	const struct of_device_id *match;
 	const struct ti_opp_supply_of_data *of_data;
 	int ret = 0;
 
-	match = of_match_device(ti_opp_supply_of_match, dev);
-	if (!match) {
-		/* We do not expect this to happen */
-		dev_err(dev, "%s: Unable to match device\n", __func__);
-		return -ENODEV;
-	}
-	if (!match->data) {
+	of_data = device_get_match_data(dev);
+	if (!of_data) {
 		/* Again, unlikely.. but mistakes do happen */
 		dev_err(dev, "%s: Bad data in match\n", __func__);
 		return -EINVAL;
 	}
-	of_data = match->data;
-
 	dev_set_drvdata(dev, (void *)of_data);
 
 	/* If we need optimized voltage */
diff --git a/include/linux/async.h b/include/linux/async.h
index cce4ad31e8fc..33c9ff4afb49 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, struct device *dev)
 	return async_schedule_node(func, dev, dev_to_node(dev));
 }
 
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev);
+
 /**
  * async_schedule_dev_domain - A device specific version of async_schedule_domain
  * @func: function to execute asynchronously
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index ccd97bcef269..76dcb7f37bcd 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -45,18 +45,6 @@ struct dev_pm_opp_supply {
 	unsigned long u_watt;
 };
 
-/**
- * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
- * @avg:	Average bandwidth corresponding to this OPP (in icc units)
- * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
- *
- * This structure stores the bandwidth values for a single interconnect path.
- */
-struct dev_pm_opp_icc_bw {
-	u32 avg;
-	u32 peak;
-};
-
 typedef int (*config_regulators_t)(struct device *dev,
 			struct dev_pm_opp *old_opp, struct dev_pm_opp *new_opp,
 			struct regulator **regulators, unsigned int count);
@@ -74,8 +62,10 @@ typedef int (*config_clks_t)(struct device *dev, struct opp_table *opp_table,
  * @supported_hw_count: Number of elements in the array.
  * @regulator_names: Array of pointers to the names of the regulator, NULL terminated.
  * @genpd_names: Null terminated array of pointers containing names of genpd to
- *		 attach.
- * @virt_devs: Pointer to return the array of virtual devices.
+ *		attach. Mutually exclusive with required_devs.
+ * @virt_devs: Pointer to return the array of genpd virtual devices. Mutually
+ *		exclusive with required_devs.
+ * @required_devs: Required OPP devices. Mutually exclusive with genpd_names/virt_devs.
  *
  * This structure contains platform specific OPP configurations for the device.
  */
@@ -90,11 +80,15 @@ struct dev_pm_opp_config {
 	const char * const *regulator_names;
 	const char * const *genpd_names;
 	struct device ***virt_devs;
+	struct device **required_devs;
 };
 
+#define OPP_LEVEL_UNSET			U32_MAX
+
 /**
  * struct dev_pm_opp_data - The data to use to initialize an OPP.
- * @level: The performance level for the OPP.
+ * @level: The performance level for the OPP. Set level to OPP_LEVEL_UNSET if
+ * level field isn't used.
  * @freq: The clock rate in Hz for the OPP.
  * @u_volt: The voltage in uV for the OPP.
  */
@@ -157,7 +151,7 @@ struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 					      unsigned int *level);
 
 struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-					       unsigned long *level);
+					       unsigned int *level);
 
 struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev,
 					   unsigned int *bw, int index);
@@ -324,7 +318,7 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 }
 
 static inline struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-							     unsigned long *level)
+							     unsigned int *level)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
diff --git a/kernel/async.c b/kernel/async.c
index b2c4ba5686ee..673bba6bdf3a 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -145,6 +145,39 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
+static async_cookie_t __async_schedule_node_domain(async_func_t func,
+						   void *data, int node,
+						   struct async_domain *domain,
+						   struct async_entry *entry)
+{
+	async_cookie_t newcookie;
+	unsigned long flags;
+
+	INIT_LIST_HEAD(&entry->domain_list);
+	INIT_LIST_HEAD(&entry->global_list);
+	INIT_WORK(&entry->work, async_run_entry_fn);
+	entry->func = func;
+	entry->data = data;
+	entry->domain = domain;
+
+	spin_lock_irqsave(&async_lock, flags);
+
+	/* allocate cookie and queue */
+	newcookie = entry->cookie = next_cookie++;
+
+	list_add_tail(&entry->domain_list, &domain->pending);
+	if (domain->registered)
+		list_add_tail(&entry->global_list, &async_global_pending);
+
+	atomic_inc(&entry_count);
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* schedule for execution */
+	queue_work_node(node, system_unbound_wq, &entry->work);
+
+	return newcookie;
+}
+
 /**
  * async_schedule_node_domain - NUMA specific version of async_schedule_domain
  * @func: function to execute asynchronously
@@ -186,29 +219,8 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
 		func(data, newcookie);
 		return newcookie;
 	}
-	INIT_LIST_HEAD(&entry->domain_list);
-	INIT_LIST_HEAD(&entry->global_list);
-	INIT_WORK(&entry->work, async_run_entry_fn);
-	entry->func = func;
-	entry->data = data;
-	entry->domain = domain;
-
-	spin_lock_irqsave(&async_lock, flags);
-
-	/* allocate cookie and queue */
-	newcookie = entry->cookie = next_cookie++;
-
-	list_add_tail(&entry->domain_list, &domain->pending);
-	if (domain->registered)
-		list_add_tail(&entry->global_list, &async_global_pending);
-
-	atomic_inc(&entry_count);
-	spin_unlock_irqrestore(&async_lock, flags);
-
-	/* schedule for execution */
-	queue_work_node(node, system_unbound_wq, &entry->work);
 
-	return newcookie;
+	return __async_schedule_node_domain(func, data, node, domain, entry);
 }
 EXPORT_SYMBOL_GPL(async_schedule_node_domain);
 
@@ -232,6 +244,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
 EXPORT_SYMBOL_GPL(async_schedule_node);
 
 /**
+ * async_schedule_dev_nocall - A simplified variant of async_schedule_dev()
+ * @func: function to execute asynchronously
+ * @dev: device argument to be passed to function
+ *
+ * @dev is used as both the argument for the function and to provide NUMA
+ * context for where to run the function.
+ *
+ * If the asynchronous execution of @func is scheduled successfully, return
+ * true. Otherwise, do nothing and return false, unlike async_schedule_dev()
+ * that will run the function synchronously then.
+ */
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev)
+{
+	struct async_entry *entry;
+
+	entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL);
+
+	/* Give up if there is no memory or too much work. */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		return false;
+	}
+
+	__async_schedule_node_domain(func, dev, dev_to_node(dev),
+				     &async_dfl_domain, entry);
+	return true;
+}
+
+/**
  * async_synchronize_full - synchronize all asynchronous function calls
  *
  * This function waits until all asynchronous function calls have been done.
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index dee341ae4ace..4b0b7cf2e019 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -642,9 +642,9 @@ int hibernation_platform_enter(void)
  */
 static void power_down(void)
 {
-#ifdef CONFIG_SUSPEND
 	int error;
 
+#ifdef CONFIG_SUSPEND
 	if (hibernation_mode == HIBERNATION_SUSPEND) {
 		error = suspend_devices_and_enter(mem_sleep_current);
 		if (error) {
@@ -667,7 +667,13 @@ static void power_down(void)
 		kernel_restart(NULL);
 		break;
 	case HIBERNATION_PLATFORM:
-		hibernation_platform_enter();
+		error = hibernation_platform_enter();
+		if (error == -EAGAIN || error == -EBUSY) {
+			swsusp_unmark();
+			events_check_enabled = false;
+			pr_info("Wakeup event detected during hibernation, rolling back.\n");
+			return;
+		}
 		fallthrough;
 	case HIBERNATION_SHUTDOWN:
 		if (kernel_can_power_off())
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f6425ae3e8b0..b1ae9b677d03 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -60,22 +60,6 @@ EXPORT_SYMBOL_GPL(lock_system_sleep);
 
 void unlock_system_sleep(unsigned int flags)
 {
-	/*
-	 * 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.
-	 */
 	if (!(flags & PF_NOFREEZE))
 		current->flags &= ~PF_NOFREEZE;
 	mutex_unlock(&system_transition_mutex);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 17fd9aaaf084..8499a39c62f4 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,6 +175,8 @@ extern int swsusp_write(unsigned int flags);
 void swsusp_close(void);
 #ifdef CONFIG_SUSPEND
 extern int swsusp_unmark(void);
+#else
+static inline int swsusp_unmark(void) { return 0; }
 #endif
 
 struct __kernel_old_timeval;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 50a15408c3fc..5c96ff067c64 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1119,7 +1119,7 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 int create_basic_memory_bitmaps(void)
 {
 	struct memory_bitmap *bm1, *bm2;
-	int error = 0;
+	int error;
 
 	if (forbidden_pages_map && free_pages_map)
 		return 0;
@@ -1487,11 +1487,11 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 	s_page = pfn_to_page(src_pfn);
 	d_page = pfn_to_page(dst_pfn);
 	if (PageHighMem(s_page)) {
-		src = kmap_atomic(s_page);
-		dst = kmap_atomic(d_page);
+		src = kmap_local_page(s_page);
+		dst = kmap_local_page(d_page);
 		zeros_only = do_copy_page(dst, src);
-		kunmap_atomic(dst);
-		kunmap_atomic(src);
+		kunmap_local(dst);
+		kunmap_local(src);
 	} else {
 		if (PageHighMem(d_page)) {
 			/*
@@ -1499,9 +1499,9 @@ static bool copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 			 * data modified by kmap_atomic()
 			 */
 			zeros_only = safe_copy_page(buffer, s_page);
-			dst = kmap_atomic(d_page);
+			dst = kmap_local_page(d_page);
 			copy_page(dst, buffer);
-			kunmap_atomic(dst);
+			kunmap_local(dst);
 		} else {
 			zeros_only = safe_copy_page(page_address(d_page), s_page);
 		}
@@ -2778,7 +2778,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 int snapshot_write_next(struct snapshot_handle *handle)
 {
 	static struct chain_allocator ca;
-	int error = 0;
+	int error;
 
 next:
 	/* Check if we have already loaded the entire image */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a2cb0babb5ec..6053ddddaf65 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -451,7 +451,7 @@ err_close:
 static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		struct hib_bio_batch *hb)
 {
-	int error = 0;
+	int error;
 	sector_t offset;
 
 	if (!handle->cur)
@@ -606,11 +606,11 @@ static int crc32_threadfn(void *data)
 	unsigned i;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -619,7 +619,7 @@ static int crc32_threadfn(void *data)
 		for (i = 0; i < d->run_threads; i++)
 			*d->crc32 = crc32_le(*d->crc32,
 			                     d->unc[i], *d->unc_len[i]);
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -649,12 +649,12 @@ static int lzo_compress_threadfn(void *data)
 	struct cmp_data *d = data;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
 			d->ret = -1;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -663,7 +663,7 @@ static int lzo_compress_threadfn(void *data)
 		d->ret = lzo1x_1_compress(d->unc, d->unc_len,
 		                          d->cmp + LZO_HEADER, &d->cmp_len,
 		                          d->wrk);
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -798,7 +798,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 
 			data[thr].unc_len = off;
 
-			atomic_set(&data[thr].ready, 1);
+			atomic_set_release(&data[thr].ready, 1);
 			wake_up(&data[thr].go);
 		}
 
@@ -806,12 +806,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			break;
 
 		crc->run_threads = thr;
-		atomic_set(&crc->ready, 1);
+		atomic_set_release(&crc->ready, 1);
 		wake_up(&crc->go);
 
 		for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
 			wait_event(data[thr].done,
-			           atomic_read(&data[thr].stop));
+				atomic_read_acquire(&data[thr].stop));
 			atomic_set(&data[thr].stop, 0);
 
 			ret = data[thr].ret;
@@ -850,7 +850,7 @@ static int save_image_lzo(struct swap_map_handle *handle,
 			}
 		}
 
-		wait_event(crc->done, atomic_read(&crc->stop));
+		wait_event(crc->done, atomic_read_acquire(&crc->stop));
 		atomic_set(&crc->stop, 0);
 	}
 
@@ -1132,12 +1132,12 @@ static int lzo_decompress_threadfn(void *data)
 	struct dec_data *d = data;
 
 	while (1) {
-		wait_event(d->go, atomic_read(&d->ready) ||
+		wait_event(d->go, atomic_read_acquire(&d->ready) ||
 		                  kthread_should_stop());
 		if (kthread_should_stop()) {
 			d->thr = NULL;
 			d->ret = -1;
-			atomic_set(&d->stop, 1);
+			atomic_set_release(&d->stop, 1);
 			wake_up(&d->done);
 			break;
 		}
@@ -1150,7 +1150,7 @@ static int lzo_decompress_threadfn(void *data)
 			flush_icache_range((unsigned long)d->unc,
 					   (unsigned long)d->unc + d->unc_len);
 
-		atomic_set(&d->stop, 1);
+		atomic_set_release(&d->stop, 1);
 		wake_up(&d->done);
 	}
 	return 0;
@@ -1335,7 +1335,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		}
 
 		if (crc->run_threads) {
-			wait_event(crc->done, atomic_read(&crc->stop));
+			wait_event(crc->done, atomic_read_acquire(&crc->stop));
 			atomic_set(&crc->stop, 0);
 			crc->run_threads = 0;
 		}
@@ -1371,7 +1371,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 					pg = 0;
 			}
 
-			atomic_set(&data[thr].ready, 1);
+			atomic_set_release(&data[thr].ready, 1);
 			wake_up(&data[thr].go);
 		}
 
@@ -1390,7 +1390,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 		for (run_threads = thr, thr = 0; thr < run_threads; thr++) {
 			wait_event(data[thr].done,
-			           atomic_read(&data[thr].stop));
+				atomic_read_acquire(&data[thr].stop));
 			atomic_set(&data[thr].stop, 0);
 
 			ret = data[thr].ret;
@@ -1421,7 +1421,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 				ret = snapshot_write_next(snapshot);
 				if (ret <= 0) {
 					crc->run_threads = thr + 1;
-					atomic_set(&crc->ready, 1);
+					atomic_set_release(&crc->ready, 1);
 					wake_up(&crc->go);
 					goto out_finish;
 				}
@@ -1429,13 +1429,13 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		}
 
 		crc->run_threads = thr;
-		atomic_set(&crc->ready, 1);
+		atomic_set_release(&crc->ready, 1);
 		wake_up(&crc->go);
 	}
 
 out_finish:
 	if (crc->run_threads) {
-		wait_event(crc->done, atomic_read(&crc->stop));
+		wait_event(crc->done, atomic_read_acquire(&crc->stop));
 		atomic_set(&crc->stop, 0);
 	}
 	stop = ktime_get();
@@ -1566,7 +1566,6 @@ put:
 
 /**
  * swsusp_close - close resume device.
- * @exclusive: Close the resume device which is exclusively opened.
  */
 
 void swsusp_close(void)