Merge tag 'pm-5.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These are operating performance points (OPP) framework updates mostly,
  including support for interconnect bandwidth in the OPP core, plus a
  few cpufreq changes, including boost support in the CPPC cpufreq
  driver, an ACPI device power management fix and a hibernation code
  cleanup.

  Specifics:

   - Add support for interconnect bandwidth to the OPP core (Georgi
     Djakov, Saravana Kannan, Sibi Sankar, Viresh Kumar).

   - Add support for regulator enable/disable to the OPP core (Kamil
     Konieczny).

   - Add boost support to the CPPC cpufreq driver (Xiongfeng Wang).

   - Make the tegra186 cpufreq driver set the
     CPUFREQ_NEED_INITIAL_FREQ_CHECK flag (Mian Yousaf Kaukab).

   - Prevent the ACPI power management from using power resources with
     devices where the list of power resources for power state D0 (full
     power) is missing (Rafael Wysocki).

   - Annotate a hibernation-related function with __init (Christophe
     JAILLET)"

* tag 'pm-5.8-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  ACPI: PM: Avoid using power resources if there are none for D0
  cpufreq: CPPC: add SW BOOST support
  cpufreq: change '.set_boost' to act on one policy
  PM: hibernate: Add __init annotation to swsusp_header_init()
  opp: Don't parse icc paths unnecessarily
  opp: Remove bandwidth votes when target_freq is zero
  opp: core: add regulators enable and disable
  opp: Reorder the code for !target_freq case
  opp: Expose bandwidth information via debugfs
  cpufreq: dt: Add support for interconnect bandwidth scaling
  opp: Update the bandwidth on OPP frequency changes
  opp: Add sanity checks in _read_opp_key()
  opp: Add support for parsing interconnect bandwidth
  cpufreq: tegra186: add CPUFREQ_NEED_INITIAL_FREQ_CHECK flag
  OPP: Add helpers for reading the binding properties
  dt-bindings: opp: Introduce opp-peak-kBps and opp-avg-kBps bindings

Author: torvalds

Documentation/devicetree/bindings/opp/opp.txt

@@ -83,9 +83,14 @@ properties.
 
 Required properties:
 - opp-hz: Frequency in Hz, expressed as a 64-bit big-endian integer. This is a
-  required property for all device nodes but devices like power domains. The
-  power domain nodes must have another (implementation dependent) property which
-  uniquely identifies the OPP nodes.
+  required property for all device nodes, unless another "required" property to
+  uniquely identify the OPP nodes exists. Devices like power domains must have
+  another (implementation dependent) property.
+
+- opp-peak-kBps: Peak bandwidth in kilobytes per second, expressed as an array
+  of 32-bit big-endian integers. Each element of the array represents the
+  peak bandwidth value of each interconnect path. The number of elements should
+  match the number of interconnect paths.
 
 Optional properties:
 - opp-microvolt: voltage in micro Volts.
@@ -132,6 +137,12 @@ Optional properties:
 - opp-level: A value representing the performance level of the device,
   expressed as a 32-bit integer.
 
+- opp-avg-kBps: Average bandwidth in kilobytes per second, expressed as an array
+  of 32-bit big-endian integers. Each element of the array represents the
+  average bandwidth value of each interconnect path. The number of elements
+  should match the number of interconnect paths. This property is only
+  meaningful in OPP tables where opp-peak-kBps is present.
+
 - clock-latency-ns: Specifies the maximum possible transition latency (in
   nanoseconds) for switching to this OPP from any other OPP.
 

Documentation/devicetree/bindings/property-units.txt

@@ -41,3 +41,7 @@ Temperature
 Pressure
 ----------------------------------------
 -kpascal	: kilopascal
+
+Throughput
+----------------------------------------
+-kBps		: kilobytes per second

drivers/acpi/device_pm.c

@@ -186,7 +186,7 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		 * possibly drop references to the power resources in use.
 		 */
 		state = ACPI_STATE_D3_HOT;
-		/* If _PR3 is not available, use D3hot as the target state. */
+		/* If D3cold is not supported, use D3hot as the target state. */
 		if (!device->power.states[ACPI_STATE_D3_COLD].flags.valid)
 			target_state = state;
 	} else if (!device->power.states[state].flags.valid) {

drivers/acpi/scan.c

@@ -918,12 +918,9 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 
 		if (buffer.length && package
 		    && package->type == ACPI_TYPE_PACKAGE
-		    && package->package.count) {
-			int err = acpi_extract_power_resources(package, 0,
-							       &ps->resources);
-			if (!err)
-				device->power.flags.power_resources = 1;
-		}
+		    && package->package.count)
+			acpi_extract_power_resources(package, 0, &ps->resources);
+
 		ACPI_FREE(buffer.pointer);
 	}
 
@@ -970,14 +967,27 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 		acpi_bus_init_power_state(device, i);
 
 	INIT_LIST_HEAD(&device->power.states[ACPI_STATE_D3_COLD].resources);
-	if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
-		device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
 
-	/* Set defaults for D0 and D3hot states (always valid) */
+	/* Set the defaults for D0 and D3hot (always supported). */
 	device->power.states[ACPI_STATE_D0].flags.valid = 1;
 	device->power.states[ACPI_STATE_D0].power = 100;
 	device->power.states[ACPI_STATE_D3_HOT].flags.valid = 1;
 
+	/*
+	 * Use power resources only if the D0 list of them is populated, because
+	 * some platforms may provide _PR3 only to indicate D3cold support and
+	 * in those cases the power resources list returned by it may be bogus.
+	 */
+	if (!list_empty(&device->power.states[ACPI_STATE_D0].resources)) {
+		device->power.flags.power_resources = 1;
+		/*
+		 * D3cold is supported if the D3hot list of power resources is
+		 * not empty.
+		 */
+		if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
+			device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
+	}
+
 	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
 }

drivers/cpufreq/acpi-cpufreq.c

@@ -126,12 +126,12 @@ static void boost_set_msr_each(void *p_en)
 	boost_set_msr(enable);
 }
 
-static int set_boost(int val)
+static int set_boost(struct cpufreq_policy *policy, int val)
 {
-	get_online_cpus();
-	on_each_cpu(boost_set_msr_each, (void *)(long)val, 1);
-	put_online_cpus();
-	pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");
+	on_each_cpu_mask(policy->cpus, boost_set_msr_each,
+			 (void *)(long)val, 1);
+	pr_debug("CPU %*pbl: Core Boosting %sabled.\n",
+		 cpumask_pr_args(policy->cpus), val ? "en" : "dis");
 
 	return 0;
 }
@@ -162,7 +162,9 @@ static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
 	if (ret || val > 1)
 		return -EINVAL;
 
-	set_boost(val);
+	get_online_cpus();
+	set_boost(policy, val);
+	put_online_cpus();
 
 	return count;
 }

drivers/cpufreq/cppc_cpufreq.c

@@ -37,6 +37,7 @@
  * requested etc.
  */
 static struct cppc_cpudata **all_cpu_data;
+static bool boost_supported;
 
 struct cppc_workaround_oem_info {
 	char oem_id[ACPI_OEM_ID_SIZE + 1];
@@ -310,15 +311,15 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
 	policy->min = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_nonlinear_perf);
-	policy->max = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf);
+	policy->max = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.nominal_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
 	policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.lowest_perf);
-	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.highest_perf);
+	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu, cpu->perf_caps.nominal_perf);
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu_num);
 	policy->shared_type = cpu->shared_type;
@@ -343,6 +344,13 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	cpu->cur_policy = policy;
 
+	/*
+	 * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost
+	 * is supported.
+	 */
+	if (cpu->perf_caps.highest_perf > cpu->perf_caps.nominal_perf)
+		boost_supported = true;
+
 	/* Set policy->cur to max now. The governors will adjust later. */
 	policy->cur = cppc_cpufreq_perf_to_khz(cpu,
 					cpu->perf_caps.highest_perf);
@@ -410,13 +418,40 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum)
 	return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1);
 }
 
+static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
+{
+	struct cppc_cpudata *cpudata;
+	int ret;
+
+	if (!boost_supported) {
+		pr_err("BOOST not supported by CPU or firmware\n");
+		return -EINVAL;
+	}
+
+	cpudata = all_cpu_data[policy->cpu];
+	if (state)
+		policy->max = cppc_cpufreq_perf_to_khz(cpudata,
+					cpudata->perf_caps.highest_perf);
+	else
+		policy->max = cppc_cpufreq_perf_to_khz(cpudata,
+					cpudata->perf_caps.nominal_perf);
+	policy->cpuinfo.max_freq = policy->max;
+
+	ret = freq_qos_update_request(policy->max_freq_req, policy->max);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static struct cpufreq_driver cppc_cpufreq_driver = {
 	.flags = CPUFREQ_CONST_LOOPS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
 	.get = cppc_cpufreq_get_rate,
 	.init = cppc_cpufreq_cpu_init,
 	.stop_cpu = cppc_cpufreq_stop_cpu,
+	.set_boost = cppc_cpufreq_set_boost,
 	.name = "cppc_cpufreq",
 };
 

drivers/cpufreq/cpufreq-dt.c

@@ -121,6 +121,10 @@ static int resources_available(void)
 
 	clk_put(cpu_clk);
 
+	ret = dev_pm_opp_of_find_icc_paths(cpu_dev, NULL);
+	if (ret)
+		return ret;
+
 	name = find_supply_name(cpu_dev);
 	/* Platform doesn't require regulator */
 	if (!name)

drivers/cpufreq/cpufreq.c

@@ -2532,34 +2532,29 @@ EXPORT_SYMBOL_GPL(cpufreq_update_limits);
 /*********************************************************************
  *               BOOST						     *
  *********************************************************************/
-static int cpufreq_boost_set_sw(int state)
+static int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state)
 {
-	struct cpufreq_policy *policy;
-
-	for_each_active_policy(policy) {
-		int ret;
+	int ret;
 
-		if (!policy->freq_table)
-			return -ENXIO;
+	if (!policy->freq_table)
+		return -ENXIO;
 
-		ret = cpufreq_frequency_table_cpuinfo(policy,
-						      policy->freq_table);
-		if (ret) {
-			pr_err("%s: Policy frequency update failed\n",
-			       __func__);
-			return ret;
-		}
-
-		ret = freq_qos_update_request(policy->max_freq_req, policy->max);
-		if (ret < 0)
-			return ret;
+	ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table);
+	if (ret) {
+		pr_err("%s: Policy frequency update failed\n", __func__);
+		return ret;
 	}
 
+	ret = freq_qos_update_request(policy->max_freq_req, policy->max);
+	if (ret < 0)
+		return ret;
+
 	return 0;
 }
 
 int cpufreq_boost_trigger_state(int state)
 {
+	struct cpufreq_policy *policy;
 	unsigned long flags;
 	int ret = 0;
 
@@ -2570,15 +2565,25 @@ int cpufreq_boost_trigger_state(int state)
 	cpufreq_driver->boost_enabled = state;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	ret = cpufreq_driver->set_boost(state);
-	if (ret) {
-		write_lock_irqsave(&cpufreq_driver_lock, flags);
-		cpufreq_driver->boost_enabled = !state;
-		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-		pr_err("%s: Cannot %s BOOST\n",
-		       __func__, state ? "enable" : "disable");
+	get_online_cpus();
+	for_each_active_policy(policy) {
+		ret = cpufreq_driver->set_boost(policy, state);
+		if (ret)
+			goto err_reset_state;
 	}
+	put_online_cpus();
+
+	return 0;
+
+err_reset_state:
+	put_online_cpus();
+
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	cpufreq_driver->boost_enabled = !state;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	pr_err("%s: Cannot %s BOOST\n",
+	       __func__, state ? "enable" : "disable");
 
 	return ret;
 }

drivers/cpufreq/tegra186-cpufreq.c

@@ -93,7 +93,8 @@ static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy,
 
 static struct cpufreq_driver tegra186_cpufreq_driver = {
 	.name = "tegra186",
-	.flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+	.flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+			CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = tegra186_cpufreq_set_target,
 	.init = tegra186_cpufreq_init,

drivers/interconnect/core.c

@@ -543,6 +543,24 @@ void icc_set_tag(struct icc_path *path, u32 tag)
 }
 EXPORT_SYMBOL_GPL(icc_set_tag);
 
+/**
+ * icc_get_name() - Get name of the icc path
+ * @path: reference to the path returned by icc_get()
+ *
+ * This function is used by an interconnect consumer to get the name of the icc
+ * path.
+ *
+ * Returns a valid pointer on success, or NULL otherwise.
+ */
+const char *icc_get_name(struct icc_path *path)
+{
+	if (!path)
+		return NULL;
+
+	return path->name;
+}
+EXPORT_SYMBOL_GPL(icc_get_name);
+
 /**
  * icc_set_bw() - set bandwidth constraints on an interconnect path
  * @path: reference to the path returned by icc_get()