Merge tag 'pm-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These address some PCI device power management issues, add new
  hardware support to the RAPL power capping driver, add HWP guaranteed
  performance change notification support to the intel_pstate driver,
  replace deprecated CPU-hotplug functions in a few places, update CPU
  PM notifiers to use raw spinlocks, update the PM domains framework
  (new DT property support, Kconfig fix), do a couple of cleanups in
  code related to system sleep, and improve the energy model and the
  schedutil cpufreq governor.

  Specifics:

   - Address 3 PCI device power management issues (Rafael Wysocki).

   - Add Power Limit4 support for Alder Lake to the Intel RAPL power
     capping driver (Sumeet Pawnikar).

   - Add HWP guaranteed performance change notification support to the
     intel_pstate driver (Srinivas Pandruvada).

   - Replace deprecated CPU-hotplug functions in code related to power
     management (Sebastian Andrzej Siewior).

   - Update CPU PM notifiers to use raw spinlocks (Valentin Schneider).

   - Add support for 'required-opps' DT property to the generic power
     domains (genpd) framework and use this property for I2C on ARM64
     sc7180 (Rajendra Nayak).

   - Fix Kconfig issue related to genpd (Geert Uytterhoeven).

   - Increase energy calculation precision in the Energy Model (Lukasz
     Luba).

   - Fix kobject deletion in the exit code of the schedutil cpufreq
     governor (Kevin Hao).

   - Unmark some functions as kernel-doc in the PM core to avoid
     false-positive documentation build warnings (Randy Dunlap).

   - Check RTC features instead of ops in suspend_test Alexandre
     Belloni)"

* tag 'pm-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PM: domains: Fix domain attach for CONFIG_PM_OPP=n
  powercap: Add Power Limit4 support for Alder Lake SoC
  cpufreq: intel_pstate: Process HWP Guaranteed change notification
  thermal: intel: Allow processing of HWP interrupt
  notifier: Remove atomic_notifier_call_chain_robust()
  PM: cpu: Make notifier chain use a raw_spinlock_t
  PM: sleep: unmark 'state' functions as kernel-doc
  arm64: dts: sc7180: Add required-opps for i2c
  PM: domains: Add support for 'required-opps' to set default perf state
  opp: Don't print an error if required-opps is missing
  cpufreq: schedutil: Use kobject release() method to free sugov_tunables
  PM: EM: Increase energy calculation precision
  PM: sleep: check RTC features instead of ops in suspend_test
  PM: sleep: s2idle: Replace deprecated CPU-hotplug functions
  cpufreq: Replace deprecated CPU-hotplug functions
  powercap: intel_rapl: Replace deprecated CPU-hotplug functions
  PCI: PM: Enable PME if it can be signaled from D3cold
  PCI: PM: Avoid forcing PCI_D0 for wakeup reasons inconsistently
  PCI: Use pci_update_current_state() in pci_enable_device_flags()

arch/arm64/boot/dts/qcom/sc7180.dtsi

@@ -786,6 +786,8 @@ i2c0: i2c@880000 {
 						<&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -838,6 +840,8 @@ i2c1: i2c@884000 {
 						<&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -890,6 +894,8 @@ i2c2: i2c@888000 {
 						<&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -924,6 +930,8 @@ i2c3: i2c@88c000 {
 						<&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -976,6 +984,8 @@ i2c4: i2c@890000 {
 						<&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1010,6 +1020,8 @@ i2c5: i2c@894000 {
 						<&aggre1_noc MASTER_QUP_0 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1075,6 +1087,8 @@ i2c6: i2c@a80000 {
 						<&aggre2_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1127,6 +1141,8 @@ i2c7: i2c@a84000 {
 						<&aggre2_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1161,6 +1177,8 @@ i2c8: i2c@a88000 {
 						<&aggre2_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1213,6 +1231,8 @@ i2c9: i2c@a8c000 {
 						<&aggre2_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1247,6 +1267,8 @@ i2c10: i2c@a90000 {
 						<&aggre2_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 
@@ -1299,6 +1321,8 @@ i2c11: i2c@a94000 {
 						<&aggre2_noc MASTER_QUP_1 0 &mc_virt SLAVE_EBI1 0>;
 				interconnect-names = "qup-core", "qup-config",
 							"qup-memory";
+				power-domains = <&rpmhpd SC7180_CX>;
+				required-opps = <&rpmhpd_opp_low_svs>;
 				status = "disabled";
 			};
 

drivers/base/power/domain.c

@@ -2604,6 +2604,12 @@ static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 
 	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
 
+	/* Drop the default performance state */
+	if (dev_gpd_data(dev)->default_pstate) {
+		dev_pm_genpd_set_performance_state(dev, 0);
+		dev_gpd_data(dev)->default_pstate = 0;
+	}
+
 	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = genpd_remove_device(pd, dev);
 		if (ret != -EAGAIN)
@@ -2643,6 +2649,7 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev,
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
+	int pstate;
 	int ret;
 
 	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
@@ -2681,10 +2688,29 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev,
 		genpd_unlock(pd);
 	}
 
-	if (ret)
+	if (ret) {
 		genpd_remove_device(pd, dev);
+		return -EPROBE_DEFER;
+	}
 
-	return ret ? -EPROBE_DEFER : 1;
+	/* Set the default performance state */
+	pstate = of_get_required_opp_performance_state(dev->of_node, index);
+	if (pstate < 0 && pstate != -ENODEV && pstate != -EOPNOTSUPP) {
+		ret = pstate;
+		goto err;
+	} else if (pstate > 0) {
+		ret = dev_pm_genpd_set_performance_state(dev, pstate);
+		if (ret)
+			goto err;
+		dev_gpd_data(dev)->default_pstate = pstate;
+	}
+	return 1;
+
+err:
+	dev_err(dev, "failed to set required performance state for power-domain %s: %d\n",
+		pd->name, ret);
+	genpd_remove_device(pd, dev);
+	return ret;
 }
 
 /**

drivers/cpufreq/acpi-cpufreq.c

@@ -163,9 +163,9 @@ static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
 	if (ret || val > 1)
 		return -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 	set_boost(policy, val);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return count;
 }

drivers/cpufreq/cpufreq.c

@@ -2654,18 +2654,18 @@ int cpufreq_boost_trigger_state(int state)
 	cpufreq_driver->boost_enabled = state;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_active_policy(policy) {
 		ret = cpufreq_driver->set_boost(policy, state);
 		if (ret)
 			goto err_reset_state;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 
 err_reset_state:
-	put_online_cpus();
+	cpus_read_unlock();
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	cpufreq_driver->boost_enabled = !state;

drivers/cpufreq/cpufreq_ondemand.c

@@ -418,7 +418,7 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 	default_powersave_bias = powersave_bias;
 	cpumask_clear(&done);
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct cpufreq_policy *policy;
 		struct policy_dbs_info *policy_dbs;
@@ -442,7 +442,7 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 		od_tuners = dbs_data->tuners;
 		od_tuners->powersave_bias = default_powersave_bias;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 void od_register_powersave_bias_handler(unsigned int (*f)

drivers/cpufreq/intel_pstate.c

@@ -32,6 +32,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 #include <asm/intel-family.h>
+#include "../drivers/thermal/intel/thermal_interrupt.h"
 
 #define INTEL_PSTATE_SAMPLING_INTERVAL	(10 * NSEC_PER_MSEC)
 
@@ -219,6 +220,7 @@ struct global_params {
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
  * @suspended:		Whether or not the driver has been suspended.
+ * @hwp_notify_work:	workqueue for HWP notifications.
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -257,6 +259,7 @@ struct cpudata {
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
 	bool suspended;
+	struct delayed_work hwp_notify_work;
 };
 
 static struct cpudata **all_cpu_data;
@@ -1625,6 +1628,40 @@ static void intel_pstate_sysfs_hide_hwp_dynamic_boost(void)
 
 /************************** sysfs end ************************/
 
+static void intel_pstate_notify_work(struct work_struct *work)
+{
+	mutex_lock(&intel_pstate_driver_lock);
+	cpufreq_update_policy(smp_processor_id());
+	wrmsrl(MSR_HWP_STATUS, 0);
+	mutex_unlock(&intel_pstate_driver_lock);
+}
+
+void notify_hwp_interrupt(void)
+{
+	unsigned int this_cpu = smp_processor_id();
+	struct cpudata *cpudata;
+	u64 value;
+
+	if (!hwp_active || !boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
+		return;
+
+	rdmsrl(MSR_HWP_STATUS, value);
+	if (!(value & 0x01))
+		return;
+
+	cpudata = all_cpu_data[this_cpu];
+	schedule_delayed_work_on(this_cpu, &cpudata->hwp_notify_work, msecs_to_jiffies(10));
+}
+
+static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata)
+{
+	/* Enable HWP notification interrupt for guaranteed performance change */
+	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) {
+		INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work);
+		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01);
+	}
+}
+
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
@@ -1634,6 +1671,8 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 	if (cpudata->epp_default == -EINVAL)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
+
+	intel_pstate_enable_hwp_interrupt(cpudata);
 }
 
 static int atom_get_min_pstate(void)
@@ -2969,7 +3008,7 @@ static void intel_pstate_driver_cleanup(void)
 {
 	unsigned int cpu;
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		if (all_cpu_data[cpu]) {
 			if (intel_pstate_driver == &intel_pstate)
@@ -2979,7 +3018,7 @@ static void intel_pstate_driver_cleanup(void)
 			all_cpu_data[cpu] = NULL;
 		}
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	intel_pstate_driver = NULL;
 }

drivers/cpufreq/powernow-k8.c

@@ -1180,7 +1180,7 @@ static int powernowk8_init(void)
 	if (!x86_match_cpu(powernow_k8_ids))
 		return -ENODEV;
 
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(i) {
 		smp_call_function_single(i, check_supported_cpu, &ret, 1);
 		if (!ret)
@@ -1188,10 +1188,10 @@ static int powernowk8_init(void)
 	}
 
 	if (supported_cpus != num_online_cpus()) {
-		put_online_cpus();
+		cpus_read_unlock();
 		return -ENODEV;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	ret = cpufreq_register_driver(&cpufreq_amd64_driver);
 	if (ret)

drivers/cpufreq/powernv-cpufreq.c

@@ -918,7 +918,7 @@ static void powernv_cpufreq_work_fn(struct work_struct *work)
 	unsigned int cpu;
 	cpumask_t mask;
 
-	get_online_cpus();
+	cpus_read_lock();
 	cpumask_and(&mask, &chip->mask, cpu_online_mask);
 	smp_call_function_any(&mask,
 			      powernv_cpufreq_throttle_check, NULL, 0);
@@ -939,7 +939,7 @@ static void powernv_cpufreq_work_fn(struct work_struct *work)
 		cpufreq_cpu_put(policy);
 	}
 out:
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 static int powernv_cpufreq_occ_msg(struct notifier_block *nb,

drivers/opp/of.c

@@ -95,15 +95,7 @@ static struct dev_pm_opp *_find_opp_of_np(struct opp_table *opp_table,
 static struct device_node *of_parse_required_opp(struct device_node *np,
 						 int index)
 {
-	struct device_node *required_np;
-
-	required_np = of_parse_phandle(np, "required-opps", index);
-	if (unlikely(!required_np)) {
-		pr_err("%s: Unable to parse required-opps: %pOF, index: %d\n",
-		       __func__, np, index);
-	}
-
-	return required_np;
+	return of_parse_phandle(np, "required-opps", index);
 }
 
 /* The caller must call dev_pm_opp_put_opp_table() after the table is used */
@@ -1328,7 +1320,7 @@ int of_get_required_opp_performance_state(struct device_node *np, int index)
 
 	required_np = of_parse_required_opp(np, index);
 	if (!required_np)
-		return -EINVAL;
+		return -ENODEV;
 
 	opp_table = _find_table_of_opp_np(required_np);
 	if (IS_ERR(opp_table)) {

drivers/pci/pci.c

@@ -1906,11 +1906,7 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
 	 * so that things like MSI message writing will behave as expected
 	 * (e.g. if the device really is in D0 at enable time).
 	 */
-	if (dev->pm_cap) {
-		u16 pmcsr;
-		pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
-		dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
-	}
+	pci_update_current_state(dev, dev->current_state);
 
 	if (atomic_inc_return(&dev->enable_cnt) > 1)
 		return 0;		/* already enabled */
@@ -2495,7 +2491,14 @@ static int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable
 	if (enable) {
 		int error;
 
-		if (pci_pme_capable(dev, state))
+		/*
+		 * Enable PME signaling if the device can signal PME from
+		 * D3cold regardless of whether or not it can signal PME from
+		 * the current target state, because that will allow it to
+		 * signal PME when the hierarchy above it goes into D3cold and
+		 * the device itself ends up in D3cold as a result of that.
+		 */
+		if (pci_pme_capable(dev, state) || pci_pme_capable(dev, PCI_D3cold))
 			pci_pme_active(dev, true);
 		else
 			ret = 1;
@@ -2599,16 +2602,20 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 	if (dev->current_state == PCI_D3cold)
 		target_state = PCI_D3cold;
 
-	if (wakeup) {
+	if (wakeup && dev->pme_support) {
+		pci_power_t state = target_state;
+
 		/*
 		 * Find the deepest state from which the device can generate
 		 * PME#.
 		 */
-		if (dev->pme_support) {
-			while (target_state
-			      && !(dev->pme_support & (1 << target_state)))
-				target_state--;
-		}
+		while (state && !(dev->pme_support & (1 << state)))
+			state--;
+
+		if (state)
+			return state;
+		else if (dev->pme_support & 1)
+			return PCI_D0;
 	}
 
 	return target_state;

drivers/powercap/intel_rapl_common.c

@@ -158,16 +158,16 @@ static int get_energy_counter(struct powercap_zone *power_zone,
 	/* prevent CPU hotplug, make sure the RAPL domain does not go
 	 * away while reading the counter.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	rd = power_zone_to_rapl_domain(power_zone);
 
 	if (!rapl_read_data_raw(rd, ENERGY_COUNTER, true, &energy_now)) {
 		*energy_raw = energy_now;
-		put_online_cpus();
+		cpus_read_unlock();
 
 		return 0;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return -EIO;
 }
@@ -216,11 +216,11 @@ static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
 	if (rd->state & DOMAIN_STATE_BIOS_LOCKED)
 		return -EACCES;
 
-	get_online_cpus();
+	cpus_read_lock();
 	rapl_write_data_raw(rd, PL1_ENABLE, mode);
 	if (rapl_defaults->set_floor_freq)
 		rapl_defaults->set_floor_freq(rd, mode);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
@@ -234,13 +234,13 @@ static int get_domain_enable(struct powercap_zone *power_zone, bool *mode)
 		*mode = false;
 		return 0;
 	}
-	get_online_cpus();
+	cpus_read_lock();
 	if (rapl_read_data_raw(rd, PL1_ENABLE, true, &val)) {
-		put_online_cpus();
+		cpus_read_unlock();
 		return -EIO;
 	}
 	*mode = val;
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
@@ -317,7 +317,7 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid,
 	int ret = 0;
 	int id;
 
-	get_online_cpus();
+	cpus_read_lock();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
 	if (id < 0) {
@@ -350,7 +350,7 @@ static int set_power_limit(struct powercap_zone *power_zone, int cid,
 	if (!ret)
 		package_power_limit_irq_save(rp);
 set_exit:
-	put_online_cpus();
+	cpus_read_unlock();
 	return ret;
 }
 
@@ -363,7 +363,7 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 	int ret = 0;
 	int id;
 
-	get_online_cpus();
+	cpus_read_lock();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
 	if (id < 0) {
@@ -382,7 +382,7 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 		prim = POWER_LIMIT4;
 		break;
 	default:
-		put_online_cpus();
+		cpus_read_unlock();
 		return -EINVAL;
 	}
 	if (rapl_read_data_raw(rd, prim, true, &val))
@@ -391,7 +391,7 @@ static int get_current_power_limit(struct powercap_zone *power_zone, int cid,
 		*data = val;
 
 get_exit:
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -403,7 +403,7 @@ static int set_time_window(struct powercap_zone *power_zone, int cid,
 	int ret = 0;
 	int id;
 
-	get_online_cpus();
+	cpus_read_lock();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
 	if (id < 0) {
@@ -423,7 +423,7 @@ static int set_time_window(struct powercap_zone *power_zone, int cid,
 	}
 
 set_time_exit:
-	put_online_cpus();
+	cpus_read_unlock();
 	return ret;
 }
 
@@ -435,7 +435,7 @@ static int get_time_window(struct powercap_zone *power_zone, int cid,
 	int ret = 0;
 	int id;
 
-	get_online_cpus();
+	cpus_read_lock();
 	rd = power_zone_to_rapl_domain(power_zone);
 	id = contraint_to_pl(rd, cid);
 	if (id < 0) {
@@ -458,14 +458,14 @@ static int get_time_window(struct powercap_zone *power_zone, int cid,
 		val = 0;
 		break;
 	default:
-		put_online_cpus();
+		cpus_read_unlock();
 		return -EINVAL;
 	}
 	if (!ret)
 		*data = val;
 
 get_time_exit:
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -491,7 +491,7 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 	int prim;
 	int ret = 0;
 
-	get_online_cpus();
+	cpus_read_lock();
 	rd = power_zone_to_rapl_domain(power_zone);
 	switch (rd->rpl[id].prim_id) {
 	case PL1_ENABLE:
@@ -504,7 +504,7 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 		prim = MAX_POWER;
 		break;
 	default:
-		put_online_cpus();
+		cpus_read_unlock();
 		return -EINVAL;
 	}
 	if (rapl_read_data_raw(rd, prim, true, &val))
@@ -516,7 +516,7 @@ static int get_max_power(struct powercap_zone *power_zone, int id, u64 *data)
 	if (rd->rpl[id].prim_id == PL4_ENABLE)
 		*data = *data * 2;
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -1358,7 +1358,7 @@ static void power_limit_state_save(void)
 	struct rapl_domain *rd;
 	int nr_pl, ret, i;
 
-	get_online_cpus();
+	cpus_read_lock();
 	list_for_each_entry(rp, &rapl_packages, plist) {
 		if (!rp->power_zone)
 			continue;
@@ -1390,7 +1390,7 @@ static void power_limit_state_save(void)
 			}
 		}
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 static void power_limit_state_restore(void)
@@ -1399,7 +1399,7 @@ static void power_limit_state_restore(void)
 	struct rapl_domain *rd;
 	int nr_pl, i;
 
-	get_online_cpus();
+	cpus_read_lock();
 	list_for_each_entry(rp, &rapl_packages, plist) {
 		if (!rp->power_zone)
 			continue;
@@ -1425,7 +1425,7 @@ static void power_limit_state_restore(void)
 			}
 		}
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 }
 
 static int rapl_pm_callback(struct notifier_block *nb,

drivers/powercap/intel_rapl_msr.c

@@ -138,6 +138,8 @@ static int rapl_msr_write_raw(int cpu, struct reg_action *ra)
 /* List of verified CPUs. */
 static const struct x86_cpu_id pl4_support_ids[] = {
 	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_TIGERLAKE_L, X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE, X86_FEATURE_ANY },
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ALDERLAKE_L, X86_FEATURE_ANY },
 	{}
 };
 

drivers/thermal/intel/therm_throt.c

@@ -569,13 +569,18 @@ static void notify_thresholds(__u64 msr_val)
 		platform_thermal_notify(msr_val);
 }
 
+void __weak notify_hwp_interrupt(void)
+{
+	wrmsrl_safe(MSR_HWP_STATUS, 0);
+}
+
 /* Thermal transition interrupt handler */
 void intel_thermal_interrupt(void)
 {
 	__u64 msr_val;
 
 	if (static_cpu_has(X86_FEATURE_HWP))
-		wrmsrl_safe(MSR_HWP_STATUS, 0);
+		notify_hwp_interrupt();
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 

drivers/thermal/intel/thermal_interrupt.h

@@ -12,4 +12,7 @@ extern int (*platform_thermal_notify)(__u64 msr_val);
  * callback has rate control */
 extern bool (*platform_thermal_package_rate_control)(void);
 
+/* Handle HWP interrupt */
+extern void notify_hwp_interrupt(void);
+
 #endif /* _INTEL_THERMAL_INTERRUPT_H */

include/linux/energy_model.h

@@ -53,6 +53,22 @@ struct em_perf_domain {
 #ifdef CONFIG_ENERGY_MODEL
 #define EM_MAX_POWER 0xFFFF
 
+/*
+ * Increase resolution of energy estimation calculations for 64-bit
+ * architectures. The extra resolution improves decision made by EAS for the
+ * task placement when two Performance Domains might provide similar energy
+ * estimation values (w/o better resolution the values could be equal).
+ *
+ * We increase resolution only if we have enough bits to allow this increased
+ * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
+ * are pretty high and the returns do not justify the increased costs.
+ */
+#ifdef CONFIG_64BIT
+#define em_scale_power(p) ((p) * 1000)
+#else
+#define em_scale_power(p) (p)
+#endif
+
 struct em_data_callback {
 	/**
 	 * active_power() - Provide power at the next performance state of

include/linux/notifier.h

@@ -168,8 +168,6 @@ extern int raw_notifier_call_chain(struct raw_notifier_head *nh,
 extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 		unsigned long val, void *v);
 
-extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh,
-		unsigned long val_up, unsigned long val_down, void *v);
 extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
 		unsigned long val_up, unsigned long val_down, void *v);
 extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,

include/linux/pm_domain.h

@@ -198,6 +198,7 @@ struct generic_pm_domain_data {
 	struct notifier_block *power_nb;
 	int cpu;
 	unsigned int performance_state;
+	unsigned int default_pstate;
 	unsigned int rpm_pstate;
 	ktime_t	next_wakeup;
 	void *data;

kernel/cpu_pm.c

@@ -13,19 +13,32 @@
 #include <linux/spinlock.h>
 #include <linux/syscore_ops.h>
 
-static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain);
+/*
+ * atomic_notifiers use a spinlock_t, which can block under PREEMPT_RT.
+ * Notifications for cpu_pm will be issued by the idle task itself, which can
+ * never block, IOW it requires using a raw_spinlock_t.
+ */
+static struct {
+	struct raw_notifier_head chain;
+	raw_spinlock_t lock;
+} cpu_pm_notifier = {
+	.chain = RAW_NOTIFIER_INIT(cpu_pm_notifier.chain),
+	.lock  = __RAW_SPIN_LOCK_UNLOCKED(cpu_pm_notifier.lock),
+};
 
 static int cpu_pm_notify(enum cpu_pm_event event)
 {
 	int ret;
 
 	/*
-	 * atomic_notifier_call_chain has a RCU read critical section, which
-	 * could be disfunctional in cpu idle. Copy RCU_NONIDLE code to let
-	 * RCU know this.
+	 * This introduces a RCU read critical section, which could be
+	 * disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know
+	 * this.
 	 */
 	rcu_irq_enter_irqson();
-	ret = atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL);
+	rcu_read_lock();
+	ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL);
+	rcu_read_unlock();
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
@@ -33,10 +46,13 @@ static int cpu_pm_notify(enum cpu_pm_event event)
 
 static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event event_down)
 {
+	unsigned long flags;
 	int ret;
 
 	rcu_irq_enter_irqson();
-	ret = atomic_notifier_call_chain_robust(&cpu_pm_notifier_chain, event_up, event_down, NULL);
+	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
+	ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL);
+	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
@@ -49,12 +65,17 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev
  * Add a driver to a list of drivers that are notified about
  * CPU and CPU cluster low power entry and exit.
  *
- * This function may sleep, and has the same return conditions as
- * raw_notifier_chain_register.
+ * This function has the same return conditions as raw_notifier_chain_register.
  */
 int cpu_pm_register_notifier(struct notifier_block *nb)
 {
-	return atomic_notifier_chain_register(&cpu_pm_notifier_chain, nb);
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
+	ret = raw_notifier_chain_register(&cpu_pm_notifier.chain, nb);
+	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
 
@@ -64,12 +85,17 @@ EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
  *
  * Remove a driver from the CPU PM notifier list.
  *
- * This function may sleep, and has the same return conditions as
- * raw_notifier_chain_unregister.
+ * This function has the same return conditions as raw_notifier_chain_unregister.
  */
 int cpu_pm_unregister_notifier(struct notifier_block *nb)
 {
-	return atomic_notifier_chain_unregister(&cpu_pm_notifier_chain, nb);
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
+	ret = raw_notifier_chain_unregister(&cpu_pm_notifier.chain, nb);
+	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
 

kernel/notifier.c

@@ -172,25 +172,6 @@ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
 
-int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh,
-		unsigned long val_up, unsigned long val_down, void *v)
-{
-	unsigned long flags;
-	int ret;
-
-	/*
-	 * Musn't use RCU; because then the notifier list can
-	 * change between the up and down traversal.
-	 */
-	spin_lock_irqsave(&nh->lock, flags);
-	ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
-	spin_unlock_irqrestore(&nh->lock, flags);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(atomic_notifier_call_chain_robust);
-NOKPROBE_SYMBOL(atomic_notifier_call_chain_robust);
-
 /**
  *	atomic_notifier_call_chain - Call functions in an atomic notifier chain
  *	@nh: Pointer to head of the atomic notifier chain

kernel/power/energy_model.c

@@ -170,7 +170,9 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 	/* Compute the cost of each performance state. */
 	fmax = (u64) table[nr_states - 1].frequency;
 	for (i = 0; i < nr_states; i++) {
-		table[i].cost = div64_u64(fmax * table[i].power,
+		unsigned long power_res = em_scale_power(table[i].power);
+
+		table[i].cost = div64_u64(fmax * power_res,
 					  table[i].frequency);
 	}
 

kernel/power/main.c

@@ -577,7 +577,7 @@ static inline void pm_print_times_init(void) {}
 
 struct kobject *power_kobj;
 
-/**
+/*
  * state - control system sleep states.
  *
  * show() returns available sleep state labels, which may be "mem", "standby",

kernel/power/suspend.c

@@ -96,7 +96,7 @@ static void s2idle_enter(void)
 	s2idle_state = S2IDLE_STATE_ENTER;
 	raw_spin_unlock_irq(&s2idle_lock);
 
-	get_online_cpus();
+	cpus_read_lock();
 	cpuidle_resume();
 
 	/* Push all the CPUs into the idle loop. */
@@ -106,7 +106,7 @@ static void s2idle_enter(void)
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
 	cpuidle_pause();
-	put_online_cpus();
+	cpus_read_unlock();
 
 	raw_spin_lock_irq(&s2idle_lock);
 

kernel/power/suspend_test.c

@@ -129,7 +129,7 @@ static int __init has_wakealarm(struct device *dev, const void *data)
 {
 	struct rtc_device *candidate = to_rtc_device(dev);
 
-	if (!candidate->ops->set_alarm)
+	if (!test_bit(RTC_FEATURE_ALARM, candidate->features))
 		return 0;
 	if (!device_may_wakeup(candidate->dev.parent))
 		return 0;

kernel/sched/cpufreq_schedutil.c

@@ -537,9 +537,17 @@ static struct attribute *sugov_attrs[] = {
 };
 ATTRIBUTE_GROUPS(sugov);
 
+static void sugov_tunables_free(struct kobject *kobj)
+{
+	struct gov_attr_set *attr_set = container_of(kobj, struct gov_attr_set, kobj);
+
+	kfree(to_sugov_tunables(attr_set));
+}
+
 static struct kobj_type sugov_tunables_ktype = {
 	.default_groups = sugov_groups,
 	.sysfs_ops = &governor_sysfs_ops,
+	.release = &sugov_tunables_free,
 };
 
 /********************** cpufreq governor interface *********************/
@@ -639,12 +647,10 @@ static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_polic
 	return tunables;
 }
 
-static void sugov_tunables_free(struct sugov_tunables *tunables)
+static void sugov_clear_global_tunables(void)
 {
 	if (!have_governor_per_policy())
 		global_tunables = NULL;
-
-	kfree(tunables);
 }
 
 static int sugov_init(struct cpufreq_policy *policy)
@@ -707,7 +713,7 @@ static int sugov_init(struct cpufreq_policy *policy)
 fail:
 	kobject_put(&tunables->attr_set.kobj);
 	policy->governor_data = NULL;
-	sugov_tunables_free(tunables);
+	sugov_clear_global_tunables();
 
 stop_kthread:
 	sugov_kthread_stop(sg_policy);
@@ -734,7 +740,7 @@ static void sugov_exit(struct cpufreq_policy *policy)
 	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
 	policy->governor_data = NULL;
 	if (!count)
-		sugov_tunables_free(tunables);
+		sugov_clear_global_tunables();
 
 	mutex_unlock(&global_tunables_lock);