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
  ...

21 files changed, 236 insertions, 146 deletions

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 05bb4d4401b2..743268996336 100644
--- a/drivers/base/power/domain.c
+++ b/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);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 205a06752ca9..c7ac49042cee 100644
--- a/drivers/base/power/main.c
+++ b/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 */
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index e4ff681faaaa..1e4fbb002a31 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/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,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 1877f5e2e5b0..f4b60663efe6 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1454,14 +1454,13 @@ 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
@@ -1469,8 +1468,8 @@ static int cpufreq_online(unsigned int cpu)
 			 * 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);
 		}
 	}
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9a515c460a00..3c1455518738 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/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 @@ hwp_cpu_matched:
 	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;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 9a810e4a7946..56f5b8077cba 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -8,7 +8,7 @@
  */
 
 /*
- * intel_idle is a cpuidle driver that loads on specific Intel processors
+ * intel_idle is a cpuidle driver that loads on all Intel CPUs with MWAIT
  * in lieu of the legacy ACPI processor_idle driver.  The intent is to
  * make Linux more efficient on these processors, as intel_idle knows
  * more than ACPI, as well as make Linux more immune to ACPI BIOS bugs.
@@ -20,7 +20,11 @@
  * All CPUs have same idle states as boot CPU
  *
  * Chipset BM_STS (bus master status) bit is a NOP
- *	for preventing entry into deep C-stats
+ *	for preventing entry into deep C-states
+ *
+ * CPU will flush caches as needed when entering a C-state via MWAIT
+ *	(in contrast to entering ACPI C3, in which case the WBINVD
+ *	instruction needs to be executed to flush the caches)
  */
 
 /*
@@ -1212,14 +1216,13 @@ static bool __init intel_idle_acpi_cst_extract(void)
 		if (!intel_idle_cst_usable())
 			continue;
 
-		if (!acpi_processor_claim_cst_control()) {
-			acpi_state_table.count = 0;
-			return false;
-		}
+		if (!acpi_processor_claim_cst_control())
+			break;
 
 		return true;
 	}
 
+	acpi_state_table.count = 0;
 	pr_debug("ACPI _CST not found or not usable\n");
 	return false;
 }
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index ff0350ca3b74..696bf77a7042 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-source "drivers/power/avs/Kconfig"
 source "drivers/power/reset/Kconfig"
 source "drivers/power/supply/Kconfig"
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index b7c2e372186b..effbf0377f32 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_POWER_AVS)		+= avs/
 obj-$(CONFIG_POWER_RESET)	+= reset/
 obj-$(CONFIG_POWER_SUPPLY)	+= supply/
diff --git a/drivers/power/avs/Kconfig b/drivers/power/avs/Kconfig
deleted file mode 100644
index cdb4237bfd02..000000000000
--- a/drivers/power/avs/Kconfig
+++ /dev/null
@@ -1,37 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig POWER_AVS
-	bool "Adaptive Voltage Scaling class support"
-	help
-	  AVS is a power management technique which finely controls the
-	  operating voltage of a device in order to optimize (i.e. reduce)
-	  its power consumption.
-	  At a given operating point the voltage is adapted depending on
-	  static factors (chip manufacturing process) and dynamic factors
-	  (temperature depending performance).
-	  AVS is also called SmartReflex on OMAP devices.
-
-	  Say Y here to enable Adaptive Voltage Scaling class support.
-
-config QCOM_CPR
-	tristate "QCOM Core Power Reduction (CPR) support"
-	depends on POWER_AVS && HAS_IOMEM
-	select PM_OPP
-	select REGMAP
-	help
-	  Say Y here to enable support for the CPR hardware found on Qualcomm
-	  SoCs like QCS404.
-
-	  This driver populates CPU OPPs tables and makes adjustments to the
-	  tables based on feedback from the CPR hardware. If you want to do
-	  CPUfrequency scaling say Y here.
-
-	  To compile this driver as a module, choose M here: the module will
-	  be called qcom-cpr
-
-config ROCKCHIP_IODOMAIN
-	tristate "Rockchip IO domain support"
-	depends on POWER_AVS && ARCH_ROCKCHIP && OF
-	help
-	  Say y here to enable support io domains on Rockchip SoCs. It is
-	  necessary for the io domain setting of the SoC to match the
-	  voltage supplied by the regulators.
diff --git a/drivers/power/avs/Makefile b/drivers/power/avs/Makefile
deleted file mode 100644
index 9007d05853e2..000000000000
--- a/drivers/power/avs/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_POWER_AVS_OMAP)		+= smartreflex.o
-obj-$(CONFIG_QCOM_CPR)			+= qcom-cpr.o
-obj-$(CONFIG_ROCKCHIP_IODOMAIN)		+= rockchip-io-domain.o
diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index ebc4d4578339..bc228725346b 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -30,7 +30,7 @@ config INTEL_RAPL
 
 	  In RAPL, the platform level settings are divided into domains for
 	  fine grained control. These domains include processor package, DRAM
-	  controller, CPU core (Power Plance 0), graphics uncore (Power Plane
+	  controller, CPU core (Power Plane 0), graphics uncore (Power Plane
 	  1), etc.
 
 config IDLE_INJECT
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 983d75bd5bd1..0b2830efc574 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -544,7 +544,14 @@ static void rapl_init_domains(struct rapl_package *rp)
 			continue;
 
 		rd->rp = rp;
-		rd->name = rapl_domain_names[i];
+
+		if (i == RAPL_DOMAIN_PLATFORM && rp->id > 0) {
+			snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "psys-%d",
+				cpu_data(rp->lead_cpu).phys_proc_id);
+		} else
+			snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "%s",
+				rapl_domain_names[i]);
+
 		rd->id = i;
 		rd->rpl[0].prim_id = PL1_ENABLE;
 		rd->rpl[0].name = pl1_name;
@@ -1112,13 +1119,17 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
 	}
 	/* now register domains as children of the socket/package */
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
+		struct powercap_zone *parent = rp->power_zone;
+
 		if (rd->id == RAPL_DOMAIN_PACKAGE)
 			continue;
+		if (rd->id == RAPL_DOMAIN_PLATFORM)
+			parent = NULL;
 		/* number of power limits per domain varies */
 		nr_pl = find_nr_power_limit(rd);
 		power_zone = powercap_register_zone(&rd->power_zone,
 						    rp->priv->control_type,
-						    rd->name, rp->power_zone,
+						    rd->name, parent,
 						    &zone_ops[rd->id], nr_pl,
 						    &constraint_ops);
 
@@ -1145,67 +1156,6 @@ err_cleanup:
 	return ret;
 }
 
-int rapl_add_platform_domain(struct rapl_if_priv *priv)
-{
-	struct rapl_domain *rd;
-	struct powercap_zone *power_zone;
-	struct reg_action ra;
-	int ret;
-
-	ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS];
-	ra.mask = ~0;
-	ret = priv->read_raw(0, &ra);
-	if (ret || !ra.value)
-		return -ENODEV;
-
-	ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT];
-	ra.mask = ~0;
-	ret = priv->read_raw(0, &ra);
-	if (ret || !ra.value)
-		return -ENODEV;
-
-	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
-	if (!rd)
-		return -ENOMEM;
-
-	rd->name = rapl_domain_names[RAPL_DOMAIN_PLATFORM];
-	rd->id = RAPL_DOMAIN_PLATFORM;
-	rd->regs[RAPL_DOMAIN_REG_LIMIT] =
-	    priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT];
-	rd->regs[RAPL_DOMAIN_REG_STATUS] =
-	    priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS];
-	rd->rpl[0].prim_id = PL1_ENABLE;
-	rd->rpl[0].name = pl1_name;
-	rd->rpl[1].prim_id = PL2_ENABLE;
-	rd->rpl[1].name = pl2_name;
-	rd->rp = rapl_find_package_domain(0, priv);
-
-	power_zone = powercap_register_zone(&rd->power_zone, priv->control_type,
-					    "psys", NULL,
-					    &zone_ops[RAPL_DOMAIN_PLATFORM],
-					    2, &constraint_ops);
-
-	if (IS_ERR(power_zone)) {
-		kfree(rd);
-		return PTR_ERR(power_zone);
-	}
-
-	priv->platform_rapl_domain = rd;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rapl_add_platform_domain);
-
-void rapl_remove_platform_domain(struct rapl_if_priv *priv)
-{
-	if (priv->platform_rapl_domain) {
-		powercap_unregister_zone(priv->control_type,
-				 &priv->platform_rapl_domain->power_zone);
-		kfree(priv->platform_rapl_domain);
-	}
-}
-EXPORT_SYMBOL_GPL(rapl_remove_platform_domain);
-
 static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 {
 	struct reg_action ra;
@@ -1215,11 +1165,9 @@ static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 	case RAPL_DOMAIN_PP0:
 	case RAPL_DOMAIN_PP1:
 	case RAPL_DOMAIN_DRAM:
+	case RAPL_DOMAIN_PLATFORM:
 		ra.reg = rp->priv->regs[domain][RAPL_DOMAIN_REG_STATUS];
 		break;
-	case RAPL_DOMAIN_PLATFORM:
-		/* PSYS(PLATFORM) is not a CPU domain, so avoid printng error */
-		return -EINVAL;
 	default:
 		pr_err("invalid domain id %d\n", domain);
 		return -EINVAL;
@@ -1228,7 +1176,7 @@ static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 	 * values, otherwise skip it.
 	 */
 
-	ra.mask = ~0;
+	ra.mask = ENERGY_STATUS_MASK;
 	if (rp->priv->read_raw(cpu, &ra) || !ra.value)
 		return -ENODEV;
 
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index d2a2627507a9..1646808d354c 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -44,6 +44,7 @@ static struct rapl_if_priv rapl_msr_priv = {
 	.regs[RAPL_DOMAIN_PLATFORM] = {
 		MSR_PLATFORM_POWER_LIMIT, MSR_PLATFORM_ENERGY_STATUS, 0, 0, 0},
 	.limits[RAPL_DOMAIN_PACKAGE] = 2,
+	.limits[RAPL_DOMAIN_PLATFORM] = 2,
 };
 
 /* Handles CPU hotplug on multi-socket systems.
@@ -157,9 +158,6 @@ static int rapl_msr_probe(struct platform_device *pdev)
 		goto out;
 	rapl_msr_priv.pcap_rapl_online = ret;
 
-	/* Don't bail out if PSys is not supported */
-	rapl_add_platform_domain(&rapl_msr_priv);
-
 	return 0;
 
 out:
@@ -171,7 +169,6 @@ out:
 static int rapl_msr_remove(struct platform_device *pdev)
 {
 	cpuhp_remove_state(rapl_msr_priv.pcap_rapl_online);
-	rapl_remove_platform_domain(&rapl_msr_priv);
 	powercap_unregister_control_type(rapl_msr_priv.control_type);
 	return 0;
 }
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 3dc3e3d61ea3..6a3b69b43ad5 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -26,6 +26,22 @@ config QCOM_COMMAND_DB
 	  resource on a RPM-hardened platform must use this database to get
 	  SoC specific identifier and information for the shared resources.
 
+config QCOM_CPR
+	tristate "QCOM Core Power Reduction (CPR) support"
+	depends on ARCH_QCOM && HAS_IOMEM
+	select PM_OPP
+	select REGMAP
+	help
+	  Say Y here to enable support for the CPR hardware found on Qualcomm
+	  SoCs like QCS404.
+
+	  This driver populates CPU OPPs tables and makes adjustments to the
+	  tables based on feedback from the CPR hardware. If you want to do
+	  CPUfrequency scaling say Y here.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called qcom-cpr
+
 config QCOM_GENI_SE
 	tristate "QCOM GENI Serial Engine Driver"
 	depends on ARCH_QCOM || COMPILE_TEST
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 93392d9dc7f7..ad675a6593d0 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -3,6 +3,7 @@ CFLAGS_rpmh-rsc.o := -I$(src)
 obj-$(CONFIG_QCOM_AOSS_QMP) +=	qcom_aoss.o
 obj-$(CONFIG_QCOM_GENI_SE) +=	qcom-geni-se.o
 obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
+obj-$(CONFIG_QCOM_CPR)		+= cpr.o
 obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
 obj-$(CONFIG_QCOM_MDT_LOADER)	+= mdt_loader.o
 obj-$(CONFIG_QCOM_OCMEM)	+= ocmem.o
diff --git a/drivers/power/avs/qcom-cpr.c b/drivers/soc/qcom/cpr.c
index b24cc77d1889..b24cc77d1889 100644
--- a/drivers/power/avs/qcom-cpr.c
+++ b/drivers/soc/qcom/cpr.c
diff --git a/drivers/soc/rockchip/Kconfig b/drivers/soc/rockchip/Kconfig
index b71b73bf5fc5..2c13bf4dd5db 100644
--- a/drivers/soc/rockchip/Kconfig
+++ b/drivers/soc/rockchip/Kconfig
@@ -14,6 +14,14 @@ config ROCKCHIP_GRF
 	  In a lot of cases there also need to be default settings initialized
 	  to make some of them conform to expectations of the kernel.
 
+config ROCKCHIP_IODOMAIN
+	tristate "Rockchip IO domain support"
+	depends on OF
+	help
+	  Say y here to enable support io domains on Rockchip SoCs. It is
+	  necessary for the io domain setting of the SoC to match the
+	  voltage supplied by the regulators.
+
 config ROCKCHIP_PM_DOMAINS
         bool "Rockchip generic power domain"
         depends on PM
diff --git a/drivers/soc/rockchip/Makefile b/drivers/soc/rockchip/Makefile
index afca0a4c4b72..875032f7344e 100644
--- a/drivers/soc/rockchip/Makefile
+++ b/drivers/soc/rockchip/Makefile
@@ -3,4 +3,5 @@
 # Rockchip Soc drivers
 #
 obj-$(CONFIG_ROCKCHIP_GRF) += grf.o
+obj-$(CONFIG_ROCKCHIP_IODOMAIN) += io-domain.o
 obj-$(CONFIG_ROCKCHIP_PM_DOMAINS) += pm_domains.o
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/soc/rockchip/io-domain.c
index eece97f97ef8..eece97f97ef8 100644
--- a/drivers/power/avs/rockchip-io-domain.c
+++ b/drivers/soc/rockchip/io-domain.c
diff --git a/drivers/soc/ti/Makefile b/drivers/soc/ti/Makefile
index 1110e5c98685..5463431ec96c 100644
--- a/drivers/soc/ti/Makefile
+++ b/drivers/soc/ti/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_TI_SCI_PM_DOMAINS)		+= ti_sci_pm_domains.o
 obj-$(CONFIG_TI_SCI_INTA_MSI_DOMAIN)	+= ti_sci_inta_msi.o
 obj-$(CONFIG_TI_K3_RINGACC)		+= k3-ringacc.o
 obj-$(CONFIG_TI_K3_SOCINFO)		+= k3-socinfo.o
+obj-$(CONFIG_POWER_AVS_OMAP)		+= smartreflex.o
diff --git a/drivers/power/avs/smartreflex.c b/drivers/soc/ti/smartreflex.c
index 5376f3d22f31..5376f3d22f31 100644
--- a/drivers/power/avs/smartreflex.c
+++ b/drivers/soc/ti/smartreflex.c