Merge tag 'pm-6.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These restore the asynchronous device resume optimization removed by
  the previous PM merge, make the intel_pstate driver work better on
  Meteor Lake systems, optimize the PM QoS core code slightly and fix up
  typos in admin-guide.

  Specifics:

   - Restore the system-wide asynchronous device resume optimization
     removed by a recent concurrency fix (Rafael J. Wysocki)

   - Make the intel_pstate cpufreq driver allow Meteor Lake systems to
     run at somewhat higher frequencies (Srinivas Pandruvada)

   - Make the PM QoS core code use kcalloc() for array allocation (Erick
     Archer)

   - Fix two PM-related typos in admin-guide (Erwan Velu)"

* tag 'pm-6.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM: sleep: Restore asynchronous device resume optimization
  Documentation: admin-guide: PM: Fix two typos
  cpufreq: intel_pstate: Update hybrid scaling factor for Meteor Lake
  PM: QoS: Use kcalloc() instead of kzalloc()

6 files changed, 86 insertions, 59 deletions

diff --git a/Documentation/admin-guide/acpi/cppc_sysfs.rst b/Documentation/admin-guide/acpi/cppc_sysfs.rst
index e53d76365aa7..36981c667823 100644
--- a/Documentation/admin-guide/acpi/cppc_sysfs.rst
+++ b/Documentation/admin-guide/acpi/cppc_sysfs.rst
@@ -75,4 +75,4 @@ taking two different snapshots of feedback counters at time T1 and T2.
   delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
   reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
 
-  delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
+  delivered_perf = (reference_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 1cf40f69278c..9eb26014d34b 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -361,7 +361,7 @@ Global Attributes
 
 ``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to
 control its functionality at the system level.  They are located in the
-``/sys/devices/system/cpu/amd-pstate/`` directory and affect all CPUs.
+``/sys/devices/system/cpu/amd_pstate/`` directory and affect all CPUs.
 
 ``status``
 	Operation mode of the driver: "active", "passive" or "disable".
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9c5a5f4dba5a..fadcd0379dc2 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 void __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;
@@ -674,16 +674,22 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
 	reinit_completion(&dev->power.completion);
 
-	if (!is_async(dev))
-		return false;
-
-	get_device(dev);
+	if (is_async(dev)) {
+		dev->power.async_in_progress = true;
 
-	if (async_schedule_dev_nocall(func, dev))
-		return true;
+		get_device(dev);
 
-	put_device(dev);
+		if (async_schedule_dev_nocall(func, dev))
+			return true;
 
+		put_device(dev);
+	}
+	/*
+	 * Because async_schedule_dev_nocall() above has returned false or it
+	 * has not been called at all, func() is not running and it is safe to
+	 * update the async_in_progress flag without extra synchronization.
+	 */
+	dev->power.async_in_progress = false;
 	return false;
 }
 
@@ -691,18 +697,10 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_noirq(dev, pm_transition, true);
+	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;
@@ -712,18 +710,28 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	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);
 		list_move_tail(&dev->power.entry, &dpm_late_early_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_noirq(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_noirq(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -747,14 +755,14 @@ 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 void __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;
@@ -820,18 +828,10 @@ static void async_resume_early(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_early(dev, pm_transition, true);
+	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.
@@ -845,18 +845,28 @@ void dpm_resume_early(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	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);
 		list_move_tail(&dev->power.entry, &dpm_suspended_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_early(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_early(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -876,12 +886,12 @@ 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 void __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;
@@ -975,18 +985,10 @@ static void async_resume(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume(dev, pm_transition, true);
+	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.
@@ -1006,16 +1008,25 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	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);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			mutex_unlock(&dpm_list_mtx);
 
-		device_resume(dev);
+			device_resume(dev, state, false);
 
-		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/base/power/qos.c b/drivers/base/power/qos.c
index 8e93167f1783..bd77f6734f14 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -201,7 +201,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	if (!qos)
 		return -ENOMEM;
 
-	n = kzalloc(3 * sizeof(*n), GFP_KERNEL);
+	n = kcalloc(3, sizeof(*n), GFP_KERNEL);
 	if (!n) {
 		kfree(qos);
 		return -ENOMEM;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 3c69040920b8..2ca70b0b5fdc 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -302,7 +302,10 @@ static bool hwp_forced __read_mostly;
 
 static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
-#define HYBRID_SCALING_FACTOR	78741
+#define HYBRID_SCALING_FACTOR		78741
+#define HYBRID_SCALING_FACTOR_MTL	80000
+
+static int hybrid_scaling_factor = HYBRID_SCALING_FACTOR;
 
 static inline int core_get_scaling(void)
 {
@@ -422,7 +425,7 @@ static int intel_pstate_cppc_get_scaling(int cpu)
 	 */
 	if (!ret && cppc_perf.nominal_perf && cppc_perf.nominal_freq &&
 	    cppc_perf.nominal_perf * 100 != cppc_perf.nominal_freq)
-		return HYBRID_SCALING_FACTOR;
+		return hybrid_scaling_factor;
 
 	return core_get_scaling();
 }
@@ -1968,7 +1971,7 @@ static int hwp_get_cpu_scaling(int cpu)
 	smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
 	/* P-cores have a smaller perf level-to-freqency scaling factor. */
 	if (cpu_type == 0x40)
-		return HYBRID_SCALING_FACTOR;
+		return hybrid_scaling_factor;
 
 	/* Use default core scaling for E-cores */
 	if (cpu_type == 0x20)
@@ -3399,6 +3402,11 @@ static const struct x86_cpu_id intel_epp_balance_perf[] = {
 	{}
 };
 
+static const struct x86_cpu_id intel_hybrid_scaling_factor[] = {
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL),
+	{}
+};
+
 static int __init intel_pstate_init(void)
 {
 	static struct cpudata **_all_cpu_data;
@@ -3489,9 +3497,16 @@ hwp_cpu_matched:
 
 	if (hwp_active) {
 		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf);
+		const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor);
 
 		if (id)
 			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data;
+
+		if (hybrid_id) {
+			hybrid_scaling_factor = hybrid_id->driver_data;
+			pr_debug("hybrid scaling factor: %d\n", hybrid_scaling_factor);
+		}
+
 	}
 
 	mutex_lock(&intel_pstate_driver_lock);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 92a4f69de0e8..a2f3e53a8196 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -681,6 +681,7 @@ struct dev_pm_info {
 	bool			wakeup_path:1;
 	bool			syscore:1;
 	bool			no_pm_callbacks:1;	/* Owned by the PM core */
+	bool			async_in_progress:1;	/* Owned by the PM core */
 	unsigned int		must_resume:1;	/* Owned by the PM core */
 	unsigned int		may_skip_resume:1;	/* Set by subsystems */
 #else