Merge branches 'pm-pci', 'pm-sleep', 'pm-domains' and 'powercap'

* pm-pci:
  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()

* pm-sleep:
  PM: sleep: unmark 'state' functions as kernel-doc
  PM: sleep: check RTC features instead of ops in suspend_test
  PM: sleep: s2idle: Replace deprecated CPU-hotplug functions

* pm-domains:
  PM: domains: Fix domain attach for CONFIG_PM_OPP=n
  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

* powercap:
  powercap: Add Power Limit4 support for Alder Lake SoC
  powercap: intel_rapl: Replace deprecated CPU-hotplug functions

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/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 },
 	{}
 };
 

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/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;