Merge tag 'pm-5.10-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "First of all, the adaptive voltage scaling (AVS) drivers go to new
  platform-specific locations as planned (this part was reported to have
  merge conflicts against the new arm-soc updates in linux-next).

  In addition to that, there are some fixes (intel_idle, intel_pstate,
  RAPL, acpi_cpufreq), the addition of on/off notifiers and idle state
  accounting support to the generic power domains (genpd) code and some
  janitorial changes all over.

  Specifics:

   - Move the AVS drivers to new platform-specific locations and get rid
     of the drivers/power/avs directory (Ulf Hansson).

   - Add on/off notifiers and idle state accounting support to the
     generic power domains (genpd) framework (Ulf Hansson, Lina Iyer).

   - Ulf will maintain the PM domain part of cpuidle-psci (Ulf Hansson).

   - Make intel_idle disregard ACPI _CST if it cannot use the data
     returned by that method (Mel Gorman).

   - Modify intel_pstate to avoid leaving useless sysfs directory
     structure behind if it cannot be registered (Chen Yu).

   - Fix domain detection in the RAPL power capping driver and prevent
     it from failing to enumerate the Psys RAPL domain (Zhang Rui).

   - Allow acpi-cpufreq to use ACPI _PSD information with Family 19 and
     later AMD chips (Wei Huang).

   - Update the driver assumptions comment in intel_idle and fix a
     kerneldoc comment in the runtime PM framework (Alexander Monakov,
     Bean Huo).

   - Avoid unnecessary resets of the cached frequency in the schedutil
     cpufreq governor to reduce overhead (Wei Wang).

   - Clean up the cpufreq core a bit (Viresh Kumar).

   - Make assorted minor janitorial changes (Daniel Lezcano, Geert
     Uytterhoeven, Hubert Jasudowicz, Tom Rix).

   - Clean up and optimize the cpupower utility somewhat (Colin Ian
     King, Martin Kaistra)"

* tag 'pm-5.10-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (23 commits)
  PM: sleep: remove unreachable break
  PM: AVS: Drop the avs directory and the corresponding Kconfig
  PM: AVS: qcom-cpr: Move the driver to the qcom specific drivers
  PM: runtime: Fix typo in pm_runtime_set_active() helper comment
  PM: domains: Fix build error for genpd notifiers
  powercap: Fix typo in Kconfig "Plance" -> "Plane"
  cpufreq: schedutil: restore cached freq when next_f is not changed
  acpi-cpufreq: Honor _PSD table setting on new AMD CPUs
  PM: AVS: smartreflex Move driver to soc specific drivers
  PM: AVS: rockchip-io: Move the driver to the rockchip specific drivers
  PM: domains: enable domain idle state accounting
  PM: domains: Add curly braces to delimit comment + statement block
  PM: domains: Add support for PM domain on/off notifiers for genpd
  powercap/intel_rapl: enumerate Psys RAPL domain together with package RAPL domain
  powercap/intel_rapl: Fix domain detection
  intel_idle: Ignore _CST if control cannot be taken from the platform
  cpuidle: Remove pointless stub
  intel_idle: mention assumption that WBINVD is not needed
  MAINTAINERS: Add section for cpuidle-psci PM domain
  cpufreq: intel_pstate: Delete intel_pstate sysfs if failed to register the driver
  ...

Author: torvalds

MAINTAINERS

@@ -4585,6 +4585,14 @@ L:	linux-arm-kernel@lists.infradead.org
 S:	Supported
 F:	drivers/cpuidle/cpuidle-psci.c
 
+CPUIDLE DRIVER - ARM PSCI PM DOMAIN
+M:	Ulf Hansson <ulf.hansson@linaro.org>
+L:	linux-pm@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+S:	Supported
+F:	drivers/cpuidle/cpuidle-psci.h
+F:	drivers/cpuidle/cpuidle-psci-domain.c
+
 CRAMFS FILESYSTEM
 M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Maintained
@@ -5398,11 +5406,11 @@ F:	include/linux/debugfs.h
 F:	include/linux/kobj*
 F:	lib/kobj*
 
-DRIVERS FOR ADAPTIVE VOLTAGE SCALING (AVS)
+DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS)
 M:	Nishanth Menon <nm@ti.com>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
-F:	drivers/power/avs/
+F:	drivers/soc/ti/smartreflex.c
 F:	include/linux/power/smartreflex.h
 
 DRM DRIVER FOR ALLWINNER DE2 AND DE3 ENGINE
@@ -14459,7 +14467,7 @@ L:	linux-pm@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/power/avs/qcom,cpr.txt
-F:	drivers/power/avs/qcom-cpr.c
+F:	drivers/soc/qcom/cpr.c
 
 QUALCOMM CPUFREQ DRIVER MSM8996/APQ8096
 M:	Ilia Lin <ilia.lin@kernel.org>

arch/arm/plat-omap/Kconfig

@@ -23,7 +23,7 @@ config OMAP_DEBUG_LEDS
 
 config POWER_AVS_OMAP
 	bool "AVS(Adaptive Voltage Scaling) support for OMAP IP versions 1&2"
-	depends on POWER_AVS && (ARCH_OMAP3 || ARCH_OMAP4) && PM
+	depends on (ARCH_OMAP3 || ARCH_OMAP4) && PM
 	select POWER_SUPPLY
 	help
 	  Say Y to enable AVS(Adaptive Voltage Scaling)

drivers/base/power/domain.c

@@ -415,26 +415,45 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 	s64 elapsed_ns;
 	int ret;
 
+	/* Notify consumers that we are about to power on. */
+	ret = raw_notifier_call_chain_robust(&genpd->power_notifiers,
+					     GENPD_NOTIFY_PRE_ON,
+					     GENPD_NOTIFY_OFF, NULL);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		return ret;
+
 	if (!genpd->power_on)
-		return 0;
+		goto out;
 
-	if (!timed)
-		return genpd->power_on(genpd);
+	if (!timed) {
+		ret = genpd->power_on(genpd);
+		if (ret)
+			goto err;
+
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_on(genpd);
 	if (ret)
-		return ret;
+		goto err;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns)
-		return ret;
+		goto out;
 
 	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
+	return 0;
+err:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return ret;
 }
 
@@ -445,27 +464,46 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 	s64 elapsed_ns;
 	int ret;
 
+	/* Notify consumers that we are about to power off. */
+	ret = raw_notifier_call_chain_robust(&genpd->power_notifiers,
+					     GENPD_NOTIFY_PRE_OFF,
+					     GENPD_NOTIFY_ON, NULL);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		return ret;
+
 	if (!genpd->power_off)
-		return 0;
+		goto out;
+
+	if (!timed) {
+		ret = genpd->power_off(genpd);
+		if (ret)
+			goto busy;
 
-	if (!timed)
-		return genpd->power_off(genpd);
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_off(genpd);
 	if (ret)
-		return ret;
+		goto busy;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns)
-		return 0;
+		goto out;
 
 	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "off", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return 0;
+busy:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
+	return ret;
 }
 
 /**
@@ -550,11 +588,14 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 		return -EBUSY;
 
 	ret = _genpd_power_off(genpd, true);
-	if (ret)
+	if (ret) {
+		genpd->states[genpd->state_idx].rejected++;
 		return ret;
+	}
 
 	genpd->status = GENPD_STATE_OFF;
 	genpd_update_accounting(genpd);
+	genpd->states[genpd->state_idx].usage++;
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
 		genpd_sd_counter_dec(link->parent);
@@ -1270,13 +1311,14 @@ static int genpd_restore_noirq(struct device *dev)
 	 * first time for the given domain in the present cycle.
 	 */
 	genpd_lock(genpd);
-	if (genpd->suspended_count++ == 0)
+	if (genpd->suspended_count++ == 0) {
 		/*
 		 * The boot kernel might put the domain into arbitrary state,
 		 * so make it appear as powered off to genpd_sync_power_on(),
 		 * so that it tries to power it on in case it was really off.
 		 */
 		genpd->status = GENPD_STATE_OFF;
+	}
 
 	genpd_sync_power_on(genpd, true, 0);
 	genpd_unlock(genpd);
@@ -1592,6 +1634,101 @@ int pm_genpd_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_device);
 
+/**
+ * dev_pm_genpd_add_notifier - Add a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that should be associated with the notifier
+ * @nb: The notifier block to register
+ *
+ * Users may call this function to add a genpd power on/off notifier for an
+ * attached @dev. Only one notifier per device is allowed. The notifier is
+ * sent when genpd is powering on/off the PM domain.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (gpd_data->power_nb)
+		return -EEXIST;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_register(&genpd->power_notifiers, nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to add notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = nb;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_add_notifier);
+
+/**
+ * dev_pm_genpd_remove_notifier - Remove a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that is associated with the notifier
+ *
+ * Users may call this function to remove a genpd power on/off notifier for an
+ * attached @dev.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_remove_notifier(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (!gpd_data->power_nb)
+		return -ENODEV;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_unregister(&genpd->power_notifiers,
+					    gpd_data->power_nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to remove notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_remove_notifier);
+
 static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 			       struct generic_pm_domain *subdomain)
 {
@@ -1762,6 +1899,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_LIST_HEAD(&genpd->parent_links);
 	INIT_LIST_HEAD(&genpd->child_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
+	RAW_INIT_NOTIFIER_HEAD(&genpd->power_notifiers);
 	genpd_lock_init(genpd);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
@@ -2923,7 +3061,7 @@ static int idle_states_show(struct seq_file *s, void *data)
 	if (ret)
 		return -ERESTARTSYS;
 
-	seq_puts(s, "State          Time Spent(ms)\n");
+	seq_puts(s, "State          Time Spent(ms) Usage          Rejected\n");
 
 	for (i = 0; i < genpd->state_count; i++) {
 		ktime_t delta = 0;
@@ -2935,7 +3073,8 @@ static int idle_states_show(struct seq_file *s, void *data)
 
 		msecs = ktime_to_ms(
 			ktime_add(genpd->states[i].idle_time, delta));
-		seq_printf(s, "S%-13i %lld\n", i, msecs);
+		seq_printf(s, "S%-13i %-14lld %-14llu %llu\n", i, msecs,
+			      genpd->states[i].usage, genpd->states[i].rejected);
 	}
 
 	genpd_unlock(genpd);

drivers/base/power/main.c

@@ -363,7 +363,6 @@ static pm_callback_t pm_op(const struct dev_pm_ops *ops, pm_message_t state)
 	case PM_EVENT_THAW:
 	case PM_EVENT_RECOVER:
 		return ops->thaw;
-		break;
 	case PM_EVENT_RESTORE:
 		return ops->restore;
 #endif /* CONFIG_HIBERNATE_CALLBACKS */

drivers/cpufreq/acpi-cpufreq.c

@@ -691,7 +691,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
 	}
 
-	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
+	if (check_amd_hwpstate_cpu(cpu) && boot_cpu_data.x86 < 0x19 &&
+	    !acpi_pstate_strict) {
 		cpumask_clear(policy->cpus);
 		cpumask_set_cpu(cpu, policy->cpus);
 		cpumask_copy(data->freqdomain_cpus,

drivers/cpufreq/cpufreq.c

@@ -1454,23 +1454,22 @@ static int cpufreq_online(unsigned int cpu)
 	 */
 	if ((cpufreq_driver->flags & CPUFREQ_NEED_INITIAL_FREQ_CHECK)
 	    && has_target()) {
+		unsigned int old_freq = policy->cur;
+
 		/* Are we running at unknown frequency ? */
-		ret = cpufreq_frequency_table_get_index(policy, policy->cur);
+		ret = cpufreq_frequency_table_get_index(policy, old_freq);
 		if (ret == -EINVAL) {
-			/* Warn user and fix it */
-			pr_warn("%s: CPU%d: Running at unlisted freq: %u KHz\n",
-				__func__, policy->cpu, policy->cur);
-			ret = __cpufreq_driver_target(policy, policy->cur - 1,
-				CPUFREQ_RELATION_L);
+			ret = __cpufreq_driver_target(policy, old_freq - 1,
+						      CPUFREQ_RELATION_L);
 
 			/*
 			 * Reaching here after boot in a few seconds may not
 			 * mean that system will remain stable at "unknown"
 			 * frequency for longer duration. Hence, a BUG_ON().
 			 */
 			BUG_ON(ret);
-			pr_warn("%s: CPU%d: Unlisted initial frequency changed to: %u KHz\n",
-				__func__, policy->cpu, policy->cur);
+			pr_info("%s: CPU%d: Running at unlisted initial frequency: %u KHz, changing to: %u KHz\n",
+				__func__, policy->cpu, old_freq, policy->cur);
 		}
 	}
 

drivers/cpufreq/intel_pstate.c

@@ -1420,6 +1420,24 @@ static void __init intel_pstate_sysfs_expose_params(void)
 	}
 }
 
+static void __init intel_pstate_sysfs_remove(void)
+{
+	if (!intel_pstate_kobject)
+		return;
+
+	sysfs_remove_group(intel_pstate_kobject, &intel_pstate_attr_group);
+
+	if (!per_cpu_limits) {
+		sysfs_remove_file(intel_pstate_kobject, &max_perf_pct.attr);
+		sysfs_remove_file(intel_pstate_kobject, &min_perf_pct.attr);
+
+		if (x86_match_cpu(intel_pstate_cpu_ee_disable_ids))
+			sysfs_remove_file(intel_pstate_kobject, &energy_efficiency.attr);
+	}
+
+	kobject_put(intel_pstate_kobject);
+}
+
 static void intel_pstate_sysfs_expose_hwp_dynamic_boost(void)
 {
 	int rc;
@@ -3063,8 +3081,10 @@ static int __init intel_pstate_init(void)
 	mutex_lock(&intel_pstate_driver_lock);
 	rc = intel_pstate_register_driver(default_driver);
 	mutex_unlock(&intel_pstate_driver_lock);
-	if (rc)
+	if (rc) {
+		intel_pstate_sysfs_remove();
 		return rc;
+	}
 
 	if (hwp_active) {
 		const struct x86_cpu_id *id;