Merge tag 'pm-4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These include a significant update of the generic power domains
  (genpd) and Operating Performance Points (OPP) frameworks, mostly
  related to the introduction of power domain performance levels,
  cpufreq updates (new driver for Qualcomm Kryo processors, updates of
  the existing drivers, some core fixes, schedutil governor
  improvements), PCI power management fixes, ACPI workaround for
  EC-based wakeup events handling on resume from suspend-to-idle, and
  major updates of the turbostat and pm-graph utilities.

  Specifics:

   - Introduce power domain performance levels into the the generic
     power domains (genpd) and Operating Performance Points (OPP)
     frameworks (Viresh Kumar, Rajendra Nayak, Dan Carpenter).

   - Fix two issues in the runtime PM framework related to the
     initialization and removal of devices using device links (Ulf
     Hansson).

   - Clean up the initialization of drivers for devices in PM domains
     (Ulf Hansson, Geert Uytterhoeven).

   - Fix a cpufreq core issue related to the policy sysfs interface
     causing CPU online to fail for CPUs sharing one cpufreq policy in
     some situations (Tao Wang).

   - Make it possible to use platform-specific suspend/resume hooks in
     the cpufreq-dt driver and make the Armada 37xx DVFS use that
     feature (Viresh Kumar, Miquel Raynal).

   - Optimize policy transition notifications in cpufreq (Viresh Kumar).

   - Improve the iowait boost mechanism in the schedutil cpufreq
     governor (Patrick Bellasi).

   - Improve the handling of deferred frequency updates in the schedutil
     cpufreq governor (Joel Fernandes, Dietmar Eggemann, Rafael Wysocki,
     Viresh Kumar).

   - Add a new cpufreq driver for Qualcomm Kryo (Ilia Lin).

   - Fix and clean up some cpufreq drivers (Colin Ian King, Dmitry
     Osipenko, Doug Smythies, Luc Van Oostenryck, Simon Horman, Viresh
     Kumar).

   - Fix the handling of PCI devices with the DPM_SMART_SUSPEND flag set
     and update stale comments in the PCI core PM code (Rafael Wysocki).

   - Work around an issue related to the handling of EC-based wakeup
     events in the ACPI PM core during resume from suspend-to-idle if
     the EC has been put into the low-power mode (Rafael Wysocki).

   - Improve the handling of wakeup source objects in the PM core (Doug
     Berger, Mahendran Ganesh, Rafael Wysocki).

   - Update the driver core to prevent deferred probe from breaking
     suspend/resume ordering (Feng Kan).

   - Clean up the PM core somewhat (Bjorn Helgaas, Ulf Hansson, Rafael
     Wysocki).

   - Make the core suspend/resume code and cpufreq support the RT patch
     (Sebastian Andrzej Siewior, Thomas Gleixner).

   - Consolidate the PM QoS handling in cpuidle governors (Rafael
     Wysocki).

   - Fix a possible crash in the hibernation core (Tetsuo Handa).

   - Update the rockchip-io Adaptive Voltage Scaling (AVS) driver (David
     Wu).

   - Update the turbostat utility (fixes, cleanups, new CPU IDs, new
     command line options, built-in "Low Power Idle" counters support,
     new POLL and POLL% columns) and add an entry for it to MAINTAINERS
     (Len Brown, Artem Bityutskiy, Chen Yu, Laura Abbott, Matt Turner,
     Prarit Bhargava, Srinivas Pandruvada).

   - Update the pm-graph to version 5.1 (Todd Brandt).

   - Update the intel_pstate_tracer utility (Doug Smythies)"

* tag 'pm-4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (128 commits)
  tools/power turbostat: update version number
  tools/power turbostat: Add Node in output
  tools/power turbostat: add node information into turbostat calculations
  tools/power turbostat: remove num_ from cpu_topology struct
  tools/power turbostat: rename num_cores_per_pkg to num_cores_per_node
  tools/power turbostat: track thread ID in cpu_topology
  tools/power turbostat: Calculate additional node information for a package
  tools/power turbostat: Fix node and siblings lookup data
  tools/power turbostat: set max_num_cpus equal to the cpumask length
  tools/power turbostat: if --num_iterations, print for specific number of iterations
  tools/power turbostat: Add Cannon Lake support
  tools/power turbostat: delete duplicate #defines
  x86: msr-index.h: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: add POLL and POLL% column
  tools/power turbostat: Fix --hide Pk%pc10
  tools/power turbostat: Build-in "Low Power Idle" counters support
  tools/power turbostat: Don't make man pages executable
  tools/power turbostat: remove blank lines
  tools/power turbostat: a small C-states dump readability immprovement
  ...

1 files changed, 79 insertions, 188 deletions

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 92fa94a6dcc1..ab2f3fead6b1 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -33,8 +33,6 @@ LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
-static void dev_pm_opp_get(struct dev_pm_opp *opp);
-
 static struct opp_device *_find_opp_dev(const struct device *dev,
 					struct opp_table *opp_table)
 {
@@ -281,6 +279,23 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 
+int _get_opp_count(struct opp_table *opp_table)
+{
+	struct dev_pm_opp *opp;
+	int count = 0;
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
+		if (opp->available)
+			count++;
+	}
+
+	mutex_unlock(&opp_table->lock);
+
+	return count;
+}
+
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
  * @dev:	device for which we do this operation
@@ -291,25 +306,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp;
-	int count = 0;
+	int count;
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		count = PTR_ERR(opp_table);
 		dev_dbg(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		return count;
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->available)
-			count++;
+		return 0;
 	}
 
-	mutex_unlock(&opp_table->lock);
+	count = _get_opp_count(opp_table);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return count;
@@ -892,7 +899,7 @@ static void _opp_kref_release(struct kref *kref)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 
-static void dev_pm_opp_get(struct dev_pm_opp *opp)
+void dev_pm_opp_get(struct dev_pm_opp *opp)
 {
 	kref_get(&opp->kref);
 }
@@ -985,22 +992,11 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
-/*
- * Returns:
- * 0: On success. And appropriate error message for duplicate OPPs.
- * -EBUSY: For OPP with same freq/volt and is available. The callers of
- *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
- *  sure we don't print error messages unnecessarily if different parts of
- *  kernel try to initialize the OPP table.
- * -EEXIST: For OPP with same freq but different volt or is unavailable. This
- *  should be considered an error by the callers of _opp_add().
- */
-int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
-	     struct opp_table *opp_table)
+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;
-	struct list_head *head;
-	int ret;
 
 	/*
 	 * Insert new OPP in order of increasing frequency and discard if
@@ -1010,17 +1006,14 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
-	mutex_lock(&opp_table->lock);
-	head = &opp_table->opp_list;
-
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
-			head = &opp->node;
+			*head = &opp->node;
 			continue;
 		}
 
 		if (new_opp->rate < opp->rate)
-			break;
+			return 0;
 
 		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
@@ -1029,15 +1022,39 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			 new_opp->supplies[0].u_volt, new_opp->available);
 
 		/* Should we compare voltages for all regulators here ? */
-		ret = opp->available &&
-		      new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
-
-		mutex_unlock(&opp_table->lock);
-		return ret;
+		return opp->available &&
+		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
 	}
 
-	if (opp_table->get_pstate)
-		new_opp->pstate = opp_table->get_pstate(dev, new_opp->rate);
+	return 0;
+}
+
+/*
+ * Returns:
+ * 0: On success. And appropriate error message for duplicate OPPs.
+ * -EBUSY: For OPP with same freq/volt and is available. The callers of
+ *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
+ *  sure we don't print error messages unnecessarily if different parts of
+ *  kernel try to initialize the OPP table.
+ * -EEXIST: For OPP with same freq but different volt or is unavailable. This
+ *  should be considered an error by the callers of _opp_add().
+ */
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+	     struct opp_table *opp_table, bool rate_not_available)
+{
+	struct list_head *head;
+	int ret;
+
+	mutex_lock(&opp_table->lock);
+	head = &opp_table->opp_list;
+
+	if (likely(!rate_not_available)) {
+		ret = _opp_is_duplicate(dev, new_opp, opp_table, &head);
+		if (ret) {
+			mutex_unlock(&opp_table->lock);
+			return ret;
+		}
+	}
 
 	list_add(&new_opp->node, head);
 	mutex_unlock(&opp_table->lock);
@@ -1104,7 +1121,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	ret = _opp_add(dev, new_opp, opp_table);
+	ret = _opp_add(dev, new_opp, opp_table, false);
 	if (ret) {
 		/* Don't return error for duplicate OPPs */
 		if (ret == -EBUSY)
@@ -1140,7 +1157,6 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 			const u32 *versions, unsigned int count)
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
 	if (!opp_table)
@@ -1149,29 +1165,20 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a version hierarchy associated with opp_table? */
-	if (opp_table->supported_hw) {
-		dev_err(dev, "%s: Already have supported hardware list\n",
-			__func__);
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the property ? */
+	if (opp_table->supported_hw)
+		return opp_table;
 
 	opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions),
 					GFP_KERNEL);
 	if (!opp_table->supported_hw) {
-		ret = -ENOMEM;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	opp_table->supported_hw_count = count;
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
@@ -1188,12 +1195,6 @@ void dev_pm_opp_put_supported_hw(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->supported_hw) {
-		pr_err("%s: Doesn't have supported hardware list\n",
-		       __func__);
-		return;
-	}
-
 	kfree(opp_table->supported_hw);
 	opp_table->supported_hw = NULL;
 	opp_table->supported_hw_count = 0;
@@ -1215,7 +1216,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
 	if (!opp_table)
@@ -1224,26 +1224,17 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a prop-name associated with opp_table? */
-	if (opp_table->prop_name) {
-		dev_err(dev, "%s: Already have prop-name %s\n", __func__,
-			opp_table->prop_name);
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the property ? */
+	if (opp_table->prop_name)
+		return opp_table;
 
 	opp_table->prop_name = kstrdup(name, GFP_KERNEL);
 	if (!opp_table->prop_name) {
-		ret = -ENOMEM;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
@@ -1260,11 +1251,6 @@ void dev_pm_opp_put_prop_name(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->prop_name) {
-		pr_err("%s: Doesn't have a prop-name\n", __func__);
-		return;
-	}
-
 	kfree(opp_table->prop_name);
 	opp_table->prop_name = NULL;
 
@@ -1334,11 +1320,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 		goto err;
 	}
 
-	/* Already have regulators set */
-	if (opp_table->regulators) {
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the regulators ? */
+	if (opp_table->regulators)
+		return opp_table;
 
 	opp_table->regulators = kmalloc_array(count,
 					      sizeof(*opp_table->regulators),
@@ -1392,10 +1376,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 {
 	int i;
 
-	if (!opp_table->regulators) {
-		pr_err("%s: Doesn't have regulators set\n", __func__);
-		return;
-	}
+	if (!opp_table->regulators)
+		goto put_opp_table;
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1409,6 +1391,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 
+put_opp_table:
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
@@ -1494,7 +1477,6 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	if (!set_opp)
 		return ERR_PTR(-EINVAL);
@@ -1505,24 +1487,15 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	/* Already have custom set_opp helper */
-	if (WARN_ON(opp_table->set_opp)) {
-		ret = -EBUSY;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-EBUSY);
 	}
 
-	opp_table->set_opp = set_opp;
+	/* Another CPU that shares the OPP table has set the helper ? */
+	if (!opp_table->set_opp)
+		opp_table->set_opp = set_opp;
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
 
@@ -1535,97 +1508,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
  */
 void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table)
 {
-	if (!opp_table->set_opp) {
-		pr_err("%s: Doesn't have custom set_opp helper set\n",
-		       __func__);
-		return;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	opp_table->set_opp = NULL;
-
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_set_opp_helper);
 
 /**
- * dev_pm_opp_register_get_pstate_helper() - Register get_pstate() helper.
- * @dev: Device for which the helper is getting registered.
- * @get_pstate: Helper.
- *
- * TODO: Remove this callback after the same information is available via Device
- * Tree.
- *
- * This allows a platform to initialize the performance states of individual
- * OPPs for its devices, until we get similar information directly from DT.
- *
- * This must be called before the OPPs are initialized for the device.
- */
-struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
-		int (*get_pstate)(struct device *dev, unsigned long rate))
-{
-	struct opp_table *opp_table;
-	int ret;
-
-	if (!get_pstate)
-		return ERR_PTR(-EINVAL);
-
-	opp_table = dev_pm_opp_get_opp_table(dev);
-	if (!opp_table)
-		return ERR_PTR(-ENOMEM);
-
-	/* This should be called before OPPs are initialized */
-	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	/* Already have genpd_performance_state set */
-	if (WARN_ON(opp_table->genpd_performance_state)) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	opp_table->genpd_performance_state = true;
-	opp_table->get_pstate = get_pstate;
-
-	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_register_get_pstate_helper);
-
-/**
- * dev_pm_opp_unregister_get_pstate_helper() - Releases resources blocked for
- *					   get_pstate() helper
- * @opp_table: OPP table returned from dev_pm_opp_register_get_pstate_helper().
- *
- * Release resources blocked for platform specific get_pstate() helper.
- */
-void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table)
-{
-	if (!opp_table->genpd_performance_state) {
-		pr_err("%s: Doesn't have performance states set\n",
-		       __func__);
-		return;
-	}
-
-	/* Make sure there are no concurrent readers while updating opp_table */
-	WARN_ON(!list_empty(&opp_table->opp_list));
-
-	opp_table->genpd_performance_state = false;
-	opp_table->get_pstate = NULL;
-
-	dev_pm_opp_put_opp_table(opp_table);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_get_pstate_helper);
-
-/**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP