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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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 @@
 						<&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

@@ -1180,18 +1180,18 @@ 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)
 			supported_cpus++;
 	}
 
 	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)) {