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

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];
@@ -310,7 +311,7 @@ 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
@@ -318,7 +319,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * 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);
@@ -410,6 +418,32 @@ 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,
@@ -417,6 +451,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 	.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;
 
 	if (!policy->freq_table)
 		return -ENXIO;
 
-		ret = cpufreq_frequency_table_cpuinfo(policy,
-						      policy->freq_table);
+	ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table);
 	if (ret) {
-			pr_err("%s: Policy frequency update failed\n",
-			       __func__);
+		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) {
+	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()

drivers/opp/core.c

@@ -664,7 +664,7 @@ static inline int _generic_set_opp_clk_only(struct device *dev, struct clk *clk,
 	return ret;
 }
 
-static int _generic_set_opp_regulator(const struct opp_table *opp_table,
+static int _generic_set_opp_regulator(struct opp_table *opp_table,
 				      struct device *dev,
 				      unsigned long old_freq,
 				      unsigned long freq,
@@ -699,6 +699,18 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
 			goto restore_freq;
 	}
 
+	/*
+	 * Enable the regulator after setting its voltages, otherwise it breaks
+	 * some boot-enabled regulators.
+	 */
+	if (unlikely(!opp_table->regulator_enabled)) {
+		ret = regulator_enable(reg);
+		if (ret < 0)
+			dev_warn(dev, "Failed to enable regulator: %d", ret);
+		else
+			opp_table->regulator_enabled = true;
+	}
+
 	return 0;
 
 restore_freq:
@@ -713,6 +725,34 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
 	return ret;
 }
 
+static int _set_opp_bw(const struct opp_table *opp_table,
+		       struct dev_pm_opp *opp, struct device *dev, bool remove)
+{
+	u32 avg, peak;
+	int i, ret;
+
+	if (!opp_table->paths)
+		return 0;
+
+	for (i = 0; i < opp_table->path_count; i++) {
+		if (remove) {
+			avg = 0;
+			peak = 0;
+		} else {
+			avg = opp->bandwidth[i].avg;
+			peak = opp->bandwidth[i].peak;
+		}
+		ret = icc_set_bw(opp_table->paths[i], avg, peak);
+		if (ret) {
+			dev_err(dev, "Failed to %s bandwidth[%d]: %d\n",
+				remove ? "remove" : "set", i, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int _set_opp_custom(const struct opp_table *opp_table,
 			   struct device *dev, unsigned long old_freq,
 			   unsigned long freq,
@@ -817,15 +857,31 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	}
 
 	if (unlikely(!target_freq)) {
-		if (opp_table->required_opp_tables) {
-			ret = _set_required_opps(dev, opp_table, NULL);
-		} else if (!_get_opp_count(opp_table)) {
+		/*
+		 * Some drivers need to support cases where some platforms may
+		 * have OPP table for the device, while others don't and
+		 * opp_set_rate() just needs to behave like clk_set_rate().
+		 */
+		if (!_get_opp_count(opp_table))
 			return 0;
-		} else {
+
+		if (!opp_table->required_opp_tables && !opp_table->regulators &&
+		    !opp_table->paths) {
 			dev_err(dev, "target frequency can't be 0\n");
 			ret = -EINVAL;
+			goto put_opp_table;
+		}
+
+		ret = _set_opp_bw(opp_table, NULL, dev, true);
+		if (ret)
+			return ret;
+
+		if (opp_table->regulator_enabled) {
+			regulator_disable(opp_table->regulators[0]);
+			opp_table->regulator_enabled = false;
 		}
 
+		ret = _set_required_opps(dev, opp_table, NULL);
 		goto put_opp_table;
 	}
 
@@ -909,6 +965,9 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 			dev_err(dev, "Failed to set required opps: %d\n", ret);
 	}
 
+	if (!ret)
+		ret = _set_opp_bw(opp_table, opp, dev, false);
+
 put_opp:
 	dev_pm_opp_put(opp);
 put_old_opp:
@@ -999,6 +1058,12 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index)
 				ret);
 	}
 
+	/* Find interconnect path(s) for the device */
+	ret = dev_pm_opp_of_find_icc_paths(dev, opp_table);
+	if (ret)
+		dev_warn(dev, "%s: Error finding interconnect paths: %d\n",
+			 __func__, ret);
+
 	BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
 	kref_init(&opp_table->kref);
@@ -1057,6 +1122,7 @@ static void _opp_table_kref_release(struct kref *kref)
 {
 	struct opp_table *opp_table = container_of(kref, struct opp_table, kref);
 	struct opp_device *opp_dev, *temp;
+	int i;
 
 	_of_clear_opp_table(opp_table);
 
@@ -1064,6 +1130,12 @@ static void _opp_table_kref_release(struct kref *kref)
 	if (!IS_ERR(opp_table->clk))
 		clk_put(opp_table->clk);
 
+	if (opp_table->paths) {
+		for (i = 0; i < opp_table->path_count; i++)
+			icc_put(opp_table->paths[i]);
+		kfree(opp_table->paths);
+	}
+
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	list_for_each_entry_safe(opp_dev, temp, &opp_table->dev_list, node) {
@@ -1243,19 +1315,23 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_remove_all_dynamic);
 struct dev_pm_opp *_opp_allocate(struct opp_table *table)
 {
 	struct dev_pm_opp *opp;
-	int count, supply_size;
+	int supply_count, supply_size, icc_size;
 
 	/* Allocate space for at least one supply */
-	count = table->regulator_count > 0 ? table->regulator_count : 1;
-	supply_size = sizeof(*opp->supplies) * count;
+	supply_count = table->regulator_count > 0 ? table->regulator_count : 1;
+	supply_size = sizeof(*opp->supplies) * supply_count;
+	icc_size = sizeof(*opp->bandwidth) * table->path_count;
 
 	/* allocate new OPP node and supplies structures */
-	opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL);
+	opp = kzalloc(sizeof(*opp) + supply_size + icc_size, GFP_KERNEL);
+
 	if (!opp)
 		return NULL;
 
 	/* Put the supplies at the end of the OPP structure as an empty array */
 	opp->supplies = (struct dev_pm_opp_supply *)(opp + 1);
+	if (icc_size)
+		opp->bandwidth = (struct dev_pm_opp_icc_bw *)(opp->supplies + supply_count);
 	INIT_LIST_HEAD(&opp->node);
 
 	return opp;
@@ -1286,11 +1362,24 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
+int _opp_compare_key(struct dev_pm_opp *opp1, struct dev_pm_opp *opp2)
+{
+	if (opp1->rate != opp2->rate)
+		return opp1->rate < opp2->rate ? -1 : 1;
+	if (opp1->bandwidth && opp2->bandwidth &&
+	    opp1->bandwidth[0].peak != opp2->bandwidth[0].peak)
+		return opp1->bandwidth[0].peak < opp2->bandwidth[0].peak ? -1 : 1;
+	if (opp1->level != opp2->level)
+		return opp1->level < opp2->level ? -1 : 1;
+	return 0;
+}
+
 static int _opp_is_duplicate(struct device *dev, struct dev_pm_opp *new_opp,
 			     struct opp_table *opp_table,
 			     struct list_head **head)
 {
 	struct dev_pm_opp *opp;
+	int opp_cmp;
 
 	/*
 	 * Insert new OPP in order of increasing frequency and discard if
@@ -1301,12 +1390,13 @@ static int _opp_is_duplicate(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop.
 	 */
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
-		if (new_opp->rate > opp->rate) {
+		opp_cmp = _opp_compare_key(new_opp, opp);
+		if (opp_cmp > 0) {
 			*head = &opp->node;
 			continue;
 		}
 
-		if (new_opp->rate < opp->rate)
+		if (opp_cmp < 0)
 			return 0;
 
 		/* Duplicate OPPs */
@@ -1670,6 +1760,13 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
+	if (opp_table->regulator_enabled) {
+		for (i = opp_table->regulator_count - 1; i >= 0; i--)
+			regulator_disable(opp_table->regulators[i]);
+
+		opp_table->regulator_enabled = false;
+	}
+
 	for (i = opp_table->regulator_count - 1; i >= 0; i--)
 		regulator_put(opp_table->regulators[i]);
 

drivers/opp/debugfs.c

@@ -32,6 +32,47 @@ void opp_debug_remove_one(struct dev_pm_opp *opp)
 	debugfs_remove_recursive(opp->dentry);
 }
 
+static ssize_t bw_name_read(struct file *fp, char __user *userbuf,
+			    size_t count, loff_t *ppos)
+{
+	struct icc_path *path = fp->private_data;
+	char buf[64];
+	int i;
+
+	i = scnprintf(buf, sizeof(buf), "%.62s\n", icc_get_name(path));
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, i);
+}
+
+static const struct file_operations bw_name_fops = {
+	.open = simple_open,
+	.read = bw_name_read,
+	.llseek = default_llseek,
+};
+
+static void opp_debug_create_bw(struct dev_pm_opp *opp,
+				struct opp_table *opp_table,
+				struct dentry *pdentry)
+{
+	struct dentry *d;
+	char name[11];
+	int i;
+
+	for (i = 0; i < opp_table->path_count; i++) {
+		snprintf(name, sizeof(name), "icc-path-%.1d", i);
+
+		/* Create per-path directory */
+		d = debugfs_create_dir(name, pdentry);
+
+		debugfs_create_file("name", S_IRUGO, d, opp_table->paths[i],
+				    &bw_name_fops);
+		debugfs_create_u32("peak_bw", S_IRUGO, d,
+				   &opp->bandwidth[i].peak);
+		debugfs_create_u32("avg_bw", S_IRUGO, d,
+				   &opp->bandwidth[i].avg);
+	}
+}
+
 static void opp_debug_create_supplies(struct dev_pm_opp *opp,
 				      struct opp_table *opp_table,
 				      struct dentry *pdentry)
@@ -94,6 +135,7 @@ void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 			     &opp->clock_latency_ns);
 
 	opp_debug_create_supplies(opp, opp_table, d);
+	opp_debug_create_bw(opp, opp_table, d);
 
 	opp->dentry = d;
 }

drivers/opp/of.c

@@ -332,6 +332,105 @@ static int _of_opp_alloc_required_opps(struct opp_table *opp_table,
 	return ret;
 }
 
+static int _bandwidth_supported(struct device *dev, struct opp_table *opp_table)
+{
+	struct device_node *np, *opp_np;
+	struct property *prop;
+
+	if (!opp_table) {
+		np = of_node_get(dev->of_node);
+		if (!np)
+			return -ENODEV;
+
+		opp_np = _opp_of_get_opp_desc_node(np, 0);
+		of_node_put(np);
+	} else {
+		opp_np = of_node_get(opp_table->np);
+	}
+
+	/* Lets not fail in case we are parsing opp-v1 bindings */
+	if (!opp_np)
+		return 0;
+
+	/* Checking only first OPP is sufficient */
+	np = of_get_next_available_child(opp_np, NULL);
+	if (!np) {
+		dev_err(dev, "OPP table empty\n");
+		return -EINVAL;
+	}
+	of_node_put(opp_np);
+
+	prop = of_find_property(np, "opp-peak-kBps", NULL);
+	of_node_put(np);
+
+	if (!prop || !prop->length)
+		return 0;
+
+	return 1;
+}
+
+int dev_pm_opp_of_find_icc_paths(struct device *dev,
+				 struct opp_table *opp_table)
+{
+	struct device_node *np;
+	int ret, i, count, num_paths;
+	struct icc_path **paths;
+
+	ret = _bandwidth_supported(dev, opp_table);
+	if (ret <= 0)
+		return ret;
+
+	ret = 0;
+
+	np = of_node_get(dev->of_node);
+	if (!np)
+		return 0;
+
+	count = of_count_phandle_with_args(np, "interconnects",
+					   "#interconnect-cells");
+	of_node_put(np);
+	if (count < 0)
+		return 0;
+
+	/* two phandles when #interconnect-cells = <1> */
+	if (count % 2) {
+		dev_err(dev, "%s: Invalid interconnects values\n", __func__);
+		return -EINVAL;
+	}
+
+	num_paths = count / 2;
+	paths = kcalloc(num_paths, sizeof(*paths), GFP_KERNEL);
+	if (!paths)
+		return -ENOMEM;
+
+	for (i = 0; i < num_paths; i++) {
+		paths[i] = of_icc_get_by_index(dev, i);
+		if (IS_ERR(paths[i])) {
+			ret = PTR_ERR(paths[i]);
+			if (ret != -EPROBE_DEFER) {
+				dev_err(dev, "%s: Unable to get path%d: %d\n",
+					__func__, i, ret);
+			}
+			goto err;
+		}
+	}
+
+	if (opp_table) {
+		opp_table->paths = paths;
+		opp_table->path_count = num_paths;
+		return 0;
+	}
+
+err:
+	while (i--)
+		icc_put(paths[i]);
+
+	kfree(paths);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_find_icc_paths);
+
 static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
 			      struct device_node *np)
 {
@@ -521,6 +620,90 @@ void dev_pm_opp_of_remove_table(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
+static int _read_bw(struct dev_pm_opp *new_opp, struct opp_table *table,
+		    struct device_node *np, bool peak)
+{
+	const char *name = peak ? "opp-peak-kBps" : "opp-avg-kBps";
+	struct property *prop;
+	int i, count, ret;
+	u32 *bw;
+
+	prop = of_find_property(np, name, NULL);
+	if (!prop)
+		return -ENODEV;
+
+	count = prop->length / sizeof(u32);
+	if (table->path_count != count) {
+		pr_err("%s: Mismatch between %s and paths (%d %d)\n",
+				__func__, name, count, table->path_count);
+		return -EINVAL;
+	}
+
+	bw = kmalloc_array(count, sizeof(*bw), GFP_KERNEL);
+	if (!bw)
+		return -ENOMEM;
+
+	ret = of_property_read_u32_array(np, name, bw, count);
+	if (ret) {
+		pr_err("%s: Error parsing %s: %d\n", __func__, name, ret);
+		goto out;
+	}
+
+	for (i = 0; i < count; i++) {
+		if (peak)
+			new_opp->bandwidth[i].peak = kBps_to_icc(bw[i]);
+		else
+			new_opp->bandwidth[i].avg = kBps_to_icc(bw[i]);
+	}
+
+out:
+	kfree(bw);
+	return ret;
+}
+
+static int _read_opp_key(struct dev_pm_opp *new_opp, struct opp_table *table,
+			 struct device_node *np, bool *rate_not_available)
+{
+	bool found = false;
+	u64 rate;
+	int ret;
+
+	ret = of_property_read_u64(np, "opp-hz", &rate);
+	if (!ret) {
+		/*
+		 * Rate is defined as an unsigned long in clk API, and so
+		 * casting explicitly to its type. Must be fixed once rate is 64
+		 * bit guaranteed in clk API.
+		 */
+		new_opp->rate = (unsigned long)rate;
+		found = true;
+	}
+	*rate_not_available = !!ret;
+
+	/*
+	 * Bandwidth consists of peak and average (optional) values:
+	 * opp-peak-kBps = <path1_value path2_value>;
+	 * opp-avg-kBps = <path1_value path2_value>;
+	 */
+	ret = _read_bw(new_opp, table, np, true);
+	if (!ret) {
+		found = true;
+		ret = _read_bw(new_opp, table, np, false);
+	}
+
+	/* The properties were found but we failed to parse them */
+	if (ret && ret != -ENODEV)
+		return ret;
+
+	if (!of_property_read_u32(np, "opp-level", &new_opp->level))
+		found = true;
+
+	if (found)
+		return 0;
+
+	return ret;
+}
+
 /**
  * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
  * @opp_table:	OPP table
@@ -558,26 +741,12 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table,
 	if (!new_opp)
 		return ERR_PTR(-ENOMEM);
 
-	ret = of_property_read_u64(np, "opp-hz", &rate);
-	if (ret < 0) {
-		/* "opp-hz" is optional for devices like power domains. */
-		if (!opp_table->is_genpd) {
-			dev_err(dev, "%s: opp-hz not found\n", __func__);
+	ret = _read_opp_key(new_opp, opp_table, np, &rate_not_available);
+	if (ret < 0 && !opp_table->is_genpd) {
+		dev_err(dev, "%s: opp key field not found\n", __func__);
 		goto free_opp;
 	}
 
-		rate_not_available = true;
-	} else {
-		/*
-		 * Rate is defined as an unsigned long in clk API, and so
-		 * casting explicitly to its type. Must be fixed once rate is 64
-		 * bit guaranteed in clk API.
-		 */
-		new_opp->rate = (unsigned long)rate;
-	}
-
-	of_property_read_u32(np, "opp-level", &new_opp->level);
-
 	/* Check if the OPP supports hardware's hierarchy of versions or not */
 	if (!_opp_is_supported(dev, opp_table, np)) {
 		dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate);

drivers/opp/opp.h

@@ -12,6 +12,7 @@
 #define __DRIVER_OPP_H__
 
 #include <linux/device.h>
+#include <linux/interconnect.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
@@ -59,6 +60,7 @@ extern struct list_head opp_tables;
  * @rate:	Frequency in hertz
  * @level:	Performance level
  * @supplies:	Power supplies voltage/current values
+ * @bandwidth:	Interconnect bandwidth values
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
  * @required_opps: List of OPPs that are required by this OPP.
@@ -81,6 +83,7 @@ struct dev_pm_opp {
 	unsigned int level;
 
 	struct dev_pm_opp_supply *supplies;
+	struct dev_pm_opp_icc_bw *bandwidth;
 
 	unsigned long clock_latency_ns;
 
@@ -144,8 +147,11 @@ enum opp_table_access {
  * @clk: Device's clock handle
  * @regulators: Supply regulators
  * @regulator_count: Number of power supply regulators. Its value can be -1
+ * @regulator_enabled: Set to true if regulators were previously enabled.
  * (uninitialized), 0 (no opp-microvolt property) or > 0 (has opp-microvolt
  * property).
+ * @paths: Interconnect path handles
+ * @path_count: Number of interconnect paths
  * @genpd_performance_state: Device's power domain support performance state.
  * @is_genpd: Marks if the OPP table belongs to a genpd.
  * @set_opp: Platform specific set_opp callback
@@ -189,6 +195,9 @@ struct opp_table {
 	struct clk *clk;
 	struct regulator **regulators;
 	int regulator_count;
+	bool regulator_enabled;
+	struct icc_path **paths;
+	unsigned int path_count;
 	bool genpd_performance_state;
 	bool is_genpd;
 
@@ -211,6 +220,7 @@ struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_
 void _dev_pm_opp_find_and_remove_table(struct device *dev);
 struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
 void _opp_free(struct dev_pm_opp *opp);
+int _opp_compare_key(struct dev_pm_opp *opp1, struct dev_pm_opp *opp2);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table, bool rate_not_available);
 int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, int last_cpu);

include/linux/cpufreq.h

@@ -367,7 +367,7 @@ struct cpufreq_driver {
 
 	/* platform specific boost support code */
 	bool		boost_enabled;
-	int		(*set_boost)(int state);
+	int		(*set_boost)(struct cpufreq_policy *policy, int state);
 };
 
 /* flags */

include/linux/interconnect.h

@@ -35,6 +35,7 @@ int icc_enable(struct icc_path *path);
 int icc_disable(struct icc_path *path);
 int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw);
 void icc_set_tag(struct icc_path *path, u32 tag);
+const char *icc_get_name(struct icc_path *path);
 
 #else
 
@@ -84,6 +85,11 @@ static inline void icc_set_tag(struct icc_path *path, u32 tag)
 {
 }
 
+static inline const char *icc_get_name(struct icc_path *path)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_INTERCONNECT */
 
 #endif /* __LINUX_INTERCONNECT_H */

include/linux/pm_opp.h

@@ -41,6 +41,18 @@ struct dev_pm_opp_supply {
 	unsigned long u_amp;
 };
 
+/**
+ * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
+ * @avg:	Average bandwidth corresponding to this OPP (in icc units)
+ * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
+ *
+ * This structure stores the bandwidth values for a single interconnect path.
+ */
+struct dev_pm_opp_icc_bw {
+	u32 avg;
+	u32 peak;
+};
+
 /**
  * struct dev_pm_opp_info - OPP freq/voltage/current values
  * @rate:	Target clk rate in hz
@@ -360,6 +372,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma
 struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
 struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp);
 int of_get_required_opp_performance_state(struct device_node *np, int index);
+int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table);
 void dev_pm_opp_of_register_em(struct cpumask *cpus);
 #else
 static inline int dev_pm_opp_of_add_table(struct device *dev)
@@ -408,6 +421,11 @@ static inline int of_get_required_opp_performance_state(struct device_node *np,
 {
 	return -ENOTSUPP;
 }
+
+static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table)
+{
+	return -ENOTSUPP;
+}
 #endif
 
 #endif		/* __LINUX_OPP_H__ */

kernel/power/swap.c

@@ -1590,7 +1590,7 @@ int swsusp_unmark(void)
 }
 #endif
 
-static int swsusp_header_init(void)
+static int __init swsusp_header_init(void)
 {
 	swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
 	if (!swsusp_header)