Merge tag 'pm-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "The most signigicant change here is the addition of a new cpufreq
  'P-state' driver for AMD processors as a better replacement for the
  venerable acpi-cpufreq driver.

  There are also other cpufreq updates (in the core, intel_pstate, ARM
  drivers), PM core updates (mostly related to adding new macros for
  declaring PM operations which should make the lives of driver
  developers somewhat easier), and a bunch of assorted fixes and
  cleanups.

  Summary:

   - Add new P-state driver for AMD processors (Huang Rui).

   - Fix initialization of min and max frequency QoS requests in the
     cpufreq core (Rafael Wysocki).

   - Fix EPP handling on Alder Lake in intel_pstate (Srinivas
     Pandruvada).

   - Make intel_pstate update cpuinfo.max_freq when notified of HWP
     capabilities changes and drop a redundant function call from that
     driver (Rafael Wysocki).

   - Improve IRQ support in the Qcom cpufreq driver (Ard Biesheuvel,
     Stephen Boyd, Vladimir Zapolskiy).

   - Fix double devm_remap() in the Mediatek cpufreq driver (Hector
     Yuan).

   - Introduce thermal pressure helpers for cpufreq CPU cooling (Lukasz
     Luba).

   - Make cpufreq use default_groups in kobj_type (Greg Kroah-Hartman).

   - Make cpuidle use default_groups in kobj_type (Greg Kroah-Hartman).

   - Fix two comments in cpuidle code (Jason Wang, Yang Li).

   - Allow model-specific normal EPB value to be used in the intel_epb
     sysfs attribute handling code (Srinivas Pandruvada).

   - Simplify locking in pm_runtime_put_suppliers() (Rafael Wysocki).

   - Add safety net to supplier device release in the runtime PM core
     code (Rafael Wysocki).

   - Capture device status before disabling runtime PM for it (Rafael
     Wysocki).

   - Add new macros for declaring PM operations to allow drivers to
     avoid guarding them with CONFIG_PM #ifdefs or __maybe_unused and
     update some drivers to use these macros (Paul Cercueil).

   - Allow ACPI hardware signature to be honoured during restore from
     hibernation (David Woodhouse).

   - Update outdated operating performance points (OPP) documentation
     (Tang Yizhou).

   - Reduce log severity for informative message regarding frequency
     transition failures in devfreq (Tzung-Bi Shih).

   - Add DRAM frequency controller devfreq driver for Allwinner sunXi
     SoCs (Samuel Holland).

   - Add missing COMMON_CLK dependency to sun8i devfreq driver (Arnd
     Bergmann).

   - Add support for new layout of Psys PowerLimit Register on SPR to
     the Intel RAPL power capping driver (Zhang Rui).

   - Fix typo in a comment in idle_inject.c (Jason Wang).

   - Remove unused function definition from the DTPM (Dynamit Thermal
     Power Management) power capping framework (Daniel Lezcano).

   - Reduce DTPM trace verbosity (Daniel Lezcano)"

* tag 'pm-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (53 commits)
  x86, sched: Fix undefined reference to init_freq_invariance_cppc() build error
  cpufreq: amd-pstate: Fix Kconfig dependencies for AMD P-State
  cpufreq: amd-pstate: Fix struct amd_cpudata kernel-doc comment
  cpuidle: use default_groups in kobj_type
  x86: intel_epb: Allow model specific normal EPB value
  MAINTAINERS: Add AMD P-State driver maintainer entry
  Documentation: amd-pstate: Add AMD P-State driver introduction
  cpufreq: amd-pstate: Add AMD P-State performance attributes
  cpufreq: amd-pstate: Add AMD P-State frequencies attributes
  cpufreq: amd-pstate: Add boost mode support for AMD P-State
  cpufreq: amd-pstate: Add trace for AMD P-State module
  cpufreq: amd-pstate: Introduce the support for the processors with shared memory solution
  cpufreq: amd-pstate: Add fast switch function for AMD P-State
  cpufreq: amd-pstate: Introduce a new AMD P-State driver to support future processors
  ACPI: CPPC: Add CPPC enable register function
  ACPI: CPPC: Check present CPUs for determining _CPC is valid
  ACPI: CPPC: Implement support for SystemIO registers
  x86/msr: Add AMD CPPC MSR definitions
  x86/cpufeatures: Add AMD Collaborative Processor Performance Control feature flag
  cpufreq: use default_groups in kobj_type
  ...

3 files changed, 102 insertions, 41 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index ff16a36a908b..976154140f0b 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -22,6 +22,7 @@
 static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
 static struct cpumask scale_freq_counters_mask;
 static bool scale_freq_invariant;
+static DEFINE_PER_CPU(u32, freq_factor) = 1;
 
 static bool supports_scale_freq_counters(const struct cpumask *cpus)
 {
@@ -155,15 +156,49 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
 
 DEFINE_PER_CPU(unsigned long, thermal_pressure);
 
-void topology_set_thermal_pressure(const struct cpumask *cpus,
-			       unsigned long th_pressure)
+/**
+ * topology_update_thermal_pressure() - Update thermal pressure for CPUs
+ * @cpus        : The related CPUs for which capacity has been reduced
+ * @capped_freq : The maximum allowed frequency that CPUs can run at
+ *
+ * Update the value of thermal pressure for all @cpus in the mask. The
+ * cpumask should include all (online+offline) affected CPUs, to avoid
+ * operating on stale data when hot-plug is used for some CPUs. The
+ * @capped_freq reflects the currently allowed max CPUs frequency due to
+ * thermal capping. It might be also a boost frequency value, which is bigger
+ * than the internal 'freq_factor' max frequency. In such case the pressure
+ * value should simply be removed, since this is an indication that there is
+ * no thermal throttling. The @capped_freq must be provided in kHz.
+ */
+void topology_update_thermal_pressure(const struct cpumask *cpus,
+				      unsigned long capped_freq)
 {
+	unsigned long max_capacity, capacity, th_pressure;
+	u32 max_freq;
 	int cpu;
 
+	cpu = cpumask_first(cpus);
+	max_capacity = arch_scale_cpu_capacity(cpu);
+	max_freq = per_cpu(freq_factor, cpu);
+
+	/* Convert to MHz scale which is used in 'freq_factor' */
+	capped_freq /= 1000;
+
+	/*
+	 * Handle properly the boost frequencies, which should simply clean
+	 * the thermal pressure value.
+	 */
+	if (max_freq <= capped_freq)
+		capacity = max_capacity;
+	else
+		capacity = mult_frac(max_capacity, capped_freq, max_freq);
+
+	th_pressure = max_capacity - capacity;
+
 	for_each_cpu(cpu, cpus)
 		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
 }
-EXPORT_SYMBOL_GPL(topology_set_thermal_pressure);
+EXPORT_SYMBOL_GPL(topology_update_thermal_pressure);
 
 static ssize_t cpu_capacity_show(struct device *dev,
 				 struct device_attribute *attr,
@@ -217,7 +252,6 @@ static void update_topology_flags_workfn(struct work_struct *work)
 	update_topology = 0;
 }
 
-static DEFINE_PER_CPU(u32, freq_factor) = 1;
 static u32 *raw_capacity;
 
 static int free_raw_capacity(void)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index fd034d742447..b191bd17de89 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -485,8 +485,7 @@ static void device_link_release_fn(struct work_struct *work)
 	/* Ensure that all references to the link object have been dropped. */
 	device_link_synchronize_removal();
 
-	while (refcount_dec_not_one(&link->rpm_active))
-		pm_runtime_put(link->supplier);
+	pm_runtime_release_supplier(link, true);
 
 	put_device(link->consumer);
 	put_device(link->supplier);
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index d504cd4ab3cb..2f3cce17219b 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -305,19 +305,40 @@ static int rpm_get_suppliers(struct device *dev)
 	return 0;
 }
 
+/**
+ * pm_runtime_release_supplier - Drop references to device link's supplier.
+ * @link: Target device link.
+ * @check_idle: Whether or not to check if the supplier device is idle.
+ *
+ * Drop all runtime PM references associated with @link to its supplier device
+ * and if @check_idle is set, check if that device is idle (and so it can be
+ * suspended).
+ */
+void pm_runtime_release_supplier(struct device_link *link, bool check_idle)
+{
+	struct device *supplier = link->supplier;
+
+	/*
+	 * The additional power.usage_count check is a safety net in case
+	 * the rpm_active refcount becomes saturated, in which case
+	 * refcount_dec_not_one() would return true forever, but it is not
+	 * strictly necessary.
+	 */
+	while (refcount_dec_not_one(&link->rpm_active) &&
+	       atomic_read(&supplier->power.usage_count) > 0)
+		pm_runtime_put_noidle(supplier);
+
+	if (check_idle)
+		pm_request_idle(supplier);
+}
+
 static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
 {
 	struct device_link *link;
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
-				device_links_read_lock_held()) {
-
-		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put_noidle(link->supplier);
-
-		if (try_to_suspend)
-			pm_request_idle(link->supplier);
-	}
+				device_links_read_lock_held())
+		pm_runtime_release_supplier(link, try_to_suspend);
 }
 
 static void rpm_put_suppliers(struct device *dev)
@@ -742,13 +763,15 @@ static int rpm_resume(struct device *dev, int rpmflags)
 	trace_rpm_resume_rcuidle(dev, rpmflags);
 
  repeat:
-	if (dev->power.runtime_error)
+	if (dev->power.runtime_error) {
 		retval = -EINVAL;
-	else if (dev->power.disable_depth == 1 && dev->power.is_suspended
-	    && dev->power.runtime_status == RPM_ACTIVE)
-		retval = 1;
-	else if (dev->power.disable_depth > 0)
-		retval = -EACCES;
+	} else if (dev->power.disable_depth > 0) {
+		if (dev->power.runtime_status == RPM_ACTIVE &&
+		    dev->power.last_status == RPM_ACTIVE)
+			retval = 1;
+		else
+			retval = -EACCES;
+	}
 	if (retval)
 		goto out;
 
@@ -1410,8 +1433,10 @@ void __pm_runtime_disable(struct device *dev, bool check_resume)
 	/* Update time accounting before disabling PM-runtime. */
 	update_pm_runtime_accounting(dev);
 
-	if (!dev->power.disable_depth++)
+	if (!dev->power.disable_depth++) {
 		__pm_runtime_barrier(dev);
+		dev->power.last_status = dev->power.runtime_status;
+	}
 
  out:
 	spin_unlock_irq(&dev->power.lock);
@@ -1428,23 +1453,23 @@ void pm_runtime_enable(struct device *dev)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	if (dev->power.disable_depth > 0) {
-		dev->power.disable_depth--;
-
-		/* About to enable runtime pm, set accounting_timestamp to now */
-		if (!dev->power.disable_depth)
-			dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
-	} else {
+	if (!dev->power.disable_depth) {
 		dev_warn(dev, "Unbalanced %s!\n", __func__);
+		goto out;
 	}
 
-	WARN(!dev->power.disable_depth &&
-	     dev->power.runtime_status == RPM_SUSPENDED &&
-	     !dev->power.ignore_children &&
-	     atomic_read(&dev->power.child_count) > 0,
-	     "Enabling runtime PM for inactive device (%s) with active children\n",
-	     dev_name(dev));
+	if (--dev->power.disable_depth > 0)
+		goto out;
+
+	dev->power.last_status = RPM_INVALID;
+	dev->power.accounting_timestamp = ktime_get_mono_fast_ns();
+
+	if (dev->power.runtime_status == RPM_SUSPENDED &&
+	    !dev->power.ignore_children &&
+	    atomic_read(&dev->power.child_count) > 0)
+		dev_warn(dev, "Enabling runtime PM for inactive device with active children\n");
 
+out:
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 }
 EXPORT_SYMBOL_GPL(pm_runtime_enable);
@@ -1640,6 +1665,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend);
 void pm_runtime_init(struct device *dev)
 {
 	dev->power.runtime_status = RPM_SUSPENDED;
+	dev->power.last_status = RPM_INVALID;
 	dev->power.idle_notification = false;
 
 	dev->power.disable_depth = 1;
@@ -1722,8 +1748,6 @@ void pm_runtime_get_suppliers(struct device *dev)
 void pm_runtime_put_suppliers(struct device *dev)
 {
 	struct device_link *link;
-	unsigned long flags;
-	bool put;
 	int idx;
 
 	idx = device_links_read_lock();
@@ -1731,11 +1755,17 @@ void pm_runtime_put_suppliers(struct device *dev)
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
 				device_links_read_lock_held())
 		if (link->supplier_preactivated) {
+			bool put;
+
 			link->supplier_preactivated = false;
-			spin_lock_irqsave(&dev->power.lock, flags);
+
+			spin_lock_irq(&dev->power.lock);
+
 			put = pm_runtime_status_suspended(dev) &&
 			      refcount_dec_not_one(&link->rpm_active);
-			spin_unlock_irqrestore(&dev->power.lock, flags);
+
+			spin_unlock_irq(&dev->power.lock);
+
 			if (put)
 				pm_runtime_put(link->supplier);
 		}
@@ -1772,9 +1802,7 @@ void pm_runtime_drop_link(struct device_link *link)
 		return;
 
 	pm_runtime_drop_link_count(link->consumer);
-
-	while (refcount_dec_not_one(&link->rpm_active))
-		pm_runtime_put(link->supplier);
+	pm_runtime_release_supplier(link, true);
 }
 
 static bool pm_runtime_need_not_resume(struct device *dev)