Merge tag 'pm-4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These make hibernation on 32-bit x86 systems work in all of the cases
  in which it works on 64-bit x86 ones, update the menu cpuidle governor
  and the "polling" state to make them more efficient, add more hardware
  support to cpufreq drivers and fix issues with some of them, fix a bug
  in the conservative cpufreq governor, fix the operating performance
  points (OPP) framework and make it more stable, update the devfreq
  subsystem to take changes in the APIs used by into account and clean
  up some things all over.

  Specifics:

   - Backport hibernation bug fixes from x86-64 to x86-32 and
     consolidate hibernation handling on x86 to allow 32-bit systems to
     work in all of the cases in which 64-bit ones work (Zhimin Gu, Chen
     Yu).

   - Fix hibernation documentation (Vladimir D. Seleznev).

   - Update the menu cpuidle governor to fix a couple of issues with it,
     make it more efficient in some cases and clean it up (Rafael
     Wysocki).

   - Rework the cpuidle polling state implementation to make it more
     efficient (Rafael Wysocki).

   - Clean up the cpuidle core somewhat (Fieah Lim).

   - Fix the cpufreq conservative governor to take policy limits into
     account properly in some cases (Rafael Wysocki).

   - Add support for retrieving guaranteed performance information to
     the ACPI CPPC library and make the intel_pstate driver use it to
     expose the CPU base frequency via sysfs on systems with the
     hardware-managed P-states (HWP) feature enabled (Srinivas
     Pandruvada).

   - Fix clang warning in the CPPC cpufreq driver (Nathan Chancellor).

   - Get rid of device_node.name printing from cpufreq (Rob Herring).

   - Remove unnecessary unlikely() from the cpufreq core (Igor Stoppa).

   - Add support for the r8a7744 SoC to the cpufreq-dt driver (Biju
     Das).

   - Update the dt-platdev cpufreq driver to allow RK3399 to have
     separate tunables per cluster (Dmitry Torokhov).

   - Fix the dma_alloc_coherent() usage in the tegra186 cpufreq driver
     (Christoph Hellwig).

   - Make the imx6q cpufreq driver read OCOTP through nvmem for
     imx6ul/imx6ull (Anson Huang).

   - Fix several bugs in the operating performance points (OPP)
     framework and make it more stable (Viresh Kumar, Dave Gerlach).

   - Update the devfreq subsystem to take changes in the APIs used by
     into account, fix some issues with it and make it stop print
     device_node.name directly (Bjorn Andersson, Enric Balletbo i Serra,
     Matthias Kaehlcke, Rob Herring, Vincent Donnefort, zhong jiang).

   - Prepare the generic power domains (genpd) framework for dealing
     with domains containing CPUs (Ulf Hansson).

   - Prevent sysfs attributes representing low-power S0 residency
     counters from being exposed if low-power S0 support is not
     indicated in ACPI FADT (Rajneesh Bhardwaj).

   - Get rid of custom CPU features macros for Intel CPUs from the
     intel_idle and RAPL drivers (Andy Shevchenko).

   - Update the tasks freezer to list tasks that refused to freeze and
     caused a system transition to a sleep state to be aborted (Todd
     Brandt).

   - Update the pm-graph set of tools to v5.2 (Todd Brandt).

   - Fix some issues in the cpupower utility (Anders Roxell, Prarit
     Bhargava)"

* tag 'pm-4.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (73 commits)
  PM / Domains: Document flags for genpd
  PM / Domains: Deal with multiple states but no governor in genpd
  PM / Domains: Don't treat zero found compatible idle states as an error
  cpuidle: menu: Avoid computations when result will be discarded
  cpuidle: menu: Drop redundant comparison
  cpufreq: tegra186: don't pass GFP_DMA32 to dma_alloc_coherent()
  cpufreq: conservative: Take limits changes into account properly
  Documentation: intel_pstate: Add base_frequency information
  cpufreq: intel_pstate: Add base_frequency attribute
  ACPI / CPPC: Add support for guaranteed performance
  cpuidle: menu: Simplify checks related to the polling state
  PM / tools: sleepgraph and bootgraph: upgrade to v5.2
  PM / tools: sleepgraph: first batch of v5.2 changes
  cpupower: Fix coredump on VMWare
  cpupower: Fix AMD Family 0x17 msr_pstate size
  cpufreq: imx6q: read OCOTP through nvmem for imx6ul/imx6ull
  cpufreq: dt-platdev: allow RK3399 to have separate tunables per cluster
  cpuidle: poll_state: Revise loop termination condition
  cpuidle: menu: Move the latency_req == 0 special case check
  cpuidle: menu: Avoid computations for very close timers
  ...

1 files changed, 130 insertions, 107 deletions

diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 7af0dde..5a4b479 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -23,11 +23,32 @@
 
 #include "opp.h"
 
-static struct opp_table *_managed_opp(const struct device_node *np)
+/*
+ * Returns opp descriptor node for a device node, caller must
+ * do of_node_put().
+ */
+static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np,
+						     int index)
+{
+	/* "operating-points-v2" can be an array for power domain providers */
+	return of_parse_phandle(np, "operating-points-v2", index);
+}
+
+/* Returns opp descriptor node for a device, caller must do of_node_put() */
+struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
+{
+	return _opp_of_get_opp_desc_node(dev->of_node, 0);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
+
+struct opp_table *_managed_opp(struct device *dev, int index)
 {
 	struct opp_table *opp_table, *managed_table = NULL;
+	struct device_node *np;
 
-	mutex_lock(&opp_table_lock);
+	np = _opp_of_get_opp_desc_node(dev->of_node, index);
+	if (!np)
+		return NULL;
 
 	list_for_each_entry(opp_table, &opp_tables, node) {
 		if (opp_table->np == np) {
@@ -47,29 +68,45 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 		}
 	}
 
-	mutex_unlock(&opp_table_lock);
+	of_node_put(np);
 
 	return managed_table;
 }
 
-void _of_init_opp_table(struct opp_table *opp_table, struct device *dev)
+void _of_init_opp_table(struct opp_table *opp_table, struct device *dev,
+			int index)
 {
-	struct device_node *np;
+	struct device_node *np, *opp_np;
+	u32 val;
 
 	/*
 	 * Only required for backward compatibility with v1 bindings, but isn't
 	 * harmful for other cases. And so we do it unconditionally.
 	 */
 	np = of_node_get(dev->of_node);
-	if (np) {
-		u32 val;
-
-		if (!of_property_read_u32(np, "clock-latency", &val))
-			opp_table->clock_latency_ns_max = val;
-		of_property_read_u32(np, "voltage-tolerance",
-				     &opp_table->voltage_tolerance_v1);
-		of_node_put(np);
-	}
+	if (!np)
+		return;
+
+	if (!of_property_read_u32(np, "clock-latency", &val))
+		opp_table->clock_latency_ns_max = val;
+	of_property_read_u32(np, "voltage-tolerance",
+			     &opp_table->voltage_tolerance_v1);
+
+	/* Get OPP table node */
+	opp_np = _opp_of_get_opp_desc_node(np, index);
+	of_node_put(np);
+
+	if (!opp_np)
+		return;
+
+	if (of_property_read_bool(opp_np, "opp-shared"))
+		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
+	else
+		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
+
+	opp_table->np = opp_np;
+
+	of_node_put(opp_np);
 }
 
 static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
@@ -245,26 +282,10 @@ free_microvolt:
  */
 void dev_pm_opp_of_remove_table(struct device *dev)
 {
-	_dev_pm_opp_find_and_remove_table(dev, false);
+	_dev_pm_opp_find_and_remove_table(dev);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
-/* Returns opp descriptor node for a device node, caller must
- * do of_node_put() */
-static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np,
-						     int index)
-{
-	/* "operating-points-v2" can be an array for power domain providers */
-	return of_parse_phandle(np, "operating-points-v2", index);
-}
-
-/* Returns opp descriptor node for a device, caller must do of_node_put() */
-struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
-{
-	return _opp_of_get_opp_desc_node(dev->of_node, 0);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
-
 /**
  * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
  * @opp_table:	OPP table
@@ -276,15 +297,21 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
  * removed by dev_pm_opp_remove.
  *
  * Return:
- * 0		On success OR
+ * Valid OPP pointer:
+ *		On success
+ * NULL:
  *		Duplicate OPPs (both freq and volt are same) and opp->available
- * -EEXIST	Freq are same and volt are different OR
+ *		OR if the OPP is not supported by hardware.
+ * ERR_PTR(-EEXIST):
+ *		Freq are same and volt are different OR
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
- * -ENOMEM	Memory allocation failure
- * -EINVAL	Failed parsing the OPP node
+ * ERR_PTR(-ENOMEM):
+ *		Memory allocation failure
+ * ERR_PTR(-EINVAL):
+ *		Failed parsing the OPP node
  */
-static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
-			      struct device_node *np)
+static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table,
+		struct device *dev, struct device_node *np)
 {
 	struct dev_pm_opp *new_opp;
 	u64 rate = 0;
@@ -294,7 +321,7 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 
 	new_opp = _opp_allocate(opp_table);
 	if (!new_opp)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	ret = of_property_read_u64(np, "opp-hz", &rate);
 	if (ret < 0) {
@@ -369,52 +396,47 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 	 * frequency/voltage list.
 	 */
 	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
-	return 0;
+	return new_opp;
 
 free_opp:
 	_opp_free(new_opp);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 
 /* Initializes OPP tables based on new bindings */
-static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
+static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table)
 {
 	struct device_node *np;
-	struct opp_table *opp_table;
-	int ret = 0, count = 0, pstate_count = 0;
+	int ret, count = 0, pstate_count = 0;
 	struct dev_pm_opp *opp;
 
-	opp_table = _managed_opp(opp_np);
-	if (opp_table) {
-		/* OPPs are already managed */
-		if (!_add_opp_dev(dev, opp_table))
-			ret = -ENOMEM;
-		goto put_opp_table;
+	/* OPP table is already initialized for the device */
+	if (opp_table->parsed_static_opps) {
+		kref_get(&opp_table->list_kref);
+		return 0;
 	}
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
-	if (!opp_table)
-		return -ENOMEM;
+	kref_init(&opp_table->list_kref);
 
 	/* We have opp-table node now, iterate over it and add OPPs */
-	for_each_available_child_of_node(opp_np, np) {
-		count++;
-
-		ret = _opp_add_static_v2(opp_table, dev, np);
-		if (ret) {
+	for_each_available_child_of_node(opp_table->np, np) {
+		opp = _opp_add_static_v2(opp_table, dev, np);
+		if (IS_ERR(opp)) {
+			ret = PTR_ERR(opp);
 			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
 				ret);
-			_dev_pm_opp_remove_table(opp_table, dev, false);
 			of_node_put(np);
-			goto put_opp_table;
+			goto put_list_kref;
+		} else if (opp) {
+			count++;
 		}
 	}
 
 	/* There should be one of more OPP defined */
 	if (WARN_ON(!count)) {
 		ret = -ENOENT;
-		goto put_opp_table;
+		goto put_list_kref;
 	}
 
 	list_for_each_entry(opp, &opp_table->opp_list, node)
@@ -425,28 +447,25 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 		dev_err(dev, "Not all nodes have performance state set (%d: %d)\n",
 			count, pstate_count);
 		ret = -ENOENT;
-		goto put_opp_table;
+		goto put_list_kref;
 	}
 
 	if (pstate_count)
 		opp_table->genpd_performance_state = true;
 
-	opp_table->np = opp_np;
-	if (of_property_read_bool(opp_np, "opp-shared"))
-		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
-	else
-		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
+	opp_table->parsed_static_opps = true;
 
-put_opp_table:
-	dev_pm_opp_put_opp_table(opp_table);
+	return 0;
+
+put_list_kref:
+	_put_opp_list_kref(opp_table);
 
 	return ret;
 }
 
 /* Initializes OPP tables based on old-deprecated bindings */
-static int _of_add_opp_table_v1(struct device *dev)
+static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
 	const struct property *prop;
 	const __be32 *val;
 	int nr, ret = 0;
@@ -467,9 +486,7 @@ static int _of_add_opp_table_v1(struct device *dev)
 		return -EINVAL;
 	}
 
-	opp_table = dev_pm_opp_get_opp_table(dev);
-	if (!opp_table)
-		return -ENOMEM;
+	kref_init(&opp_table->list_kref);
 
 	val = prop->value;
 	while (nr) {
@@ -480,13 +497,12 @@ static int _of_add_opp_table_v1(struct device *dev)
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
 				__func__, freq, ret);
-			_dev_pm_opp_remove_table(opp_table, dev, false);
-			break;
+			_put_opp_list_kref(opp_table);
+			return ret;
 		}
 		nr -= 2;
 	}
 
-	dev_pm_opp_put_opp_table(opp_table);
 	return ret;
 }
 
@@ -509,24 +525,24 @@ static int _of_add_opp_table_v1(struct device *dev)
  */
 int dev_pm_opp_of_add_table(struct device *dev)
 {
-	struct device_node *opp_np;
+	struct opp_table *opp_table;
 	int ret;
 
+	opp_table = dev_pm_opp_get_opp_table_indexed(dev, 0);
+	if (!opp_table)
+		return -ENOMEM;
+
 	/*
-	 * OPPs have two version of bindings now. The older one is deprecated,
-	 * try for the new binding first.
+	 * OPPs have two version of bindings now. Also try the old (v1)
+	 * bindings for backward compatibility with older dtbs.
 	 */
-	opp_np = dev_pm_opp_of_get_opp_desc_node(dev);
-	if (!opp_np) {
-		/*
-		 * Try old-deprecated bindings for backward compatibility with
-		 * older dtbs.
-		 */
-		return _of_add_opp_table_v1(dev);
-	}
+	if (opp_table->np)
+		ret = _of_add_opp_table_v2(dev, opp_table);
+	else
+		ret = _of_add_opp_table_v1(dev, opp_table);
 
-	ret = _of_add_opp_table_v2(dev, opp_np);
-	of_node_put(opp_np);
+	if (ret)
+		dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -553,28 +569,29 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
  */
 int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
 {
-	struct device_node *opp_np;
+	struct opp_table *opp_table;
 	int ret, count;
 
-again:
-	opp_np = _opp_of_get_opp_desc_node(dev->of_node, index);
-	if (!opp_np) {
+	if (index) {
 		/*
 		 * If only one phandle is present, then the same OPP table
 		 * applies for all index requests.
 		 */
 		count = of_count_phandle_with_args(dev->of_node,
 						   "operating-points-v2", NULL);
-		if (count == 1 && index) {
-			index = 0;
-			goto again;
-		}
+		if (count != 1)
+			return -ENODEV;
 
-		return -ENODEV;
+		index = 0;
 	}
 
-	ret = _of_add_opp_table_v2(dev, opp_np);
-	of_node_put(opp_np);
+	opp_table = dev_pm_opp_get_opp_table_indexed(dev, index);
+	if (!opp_table)
+		return -ENOMEM;
+
+	ret = _of_add_opp_table_v2(dev, opp_table);
+	if (ret)
+		dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -591,7 +608,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed);
  */
 void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask)
 {
-	_dev_pm_opp_cpumask_remove_table(cpumask, true);
+	_dev_pm_opp_cpumask_remove_table(cpumask, -1);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
 
@@ -604,16 +621,18 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
 int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask)
 {
 	struct device *cpu_dev;
-	int cpu, ret = 0;
+	int cpu, ret;
 
-	WARN_ON(cpumask_empty(cpumask));
+	if (WARN_ON(cpumask_empty(cpumask)))
+		return -ENODEV;
 
 	for_each_cpu(cpu, cpumask) {
 		cpu_dev = get_cpu_device(cpu);
 		if (!cpu_dev) {
 			pr_err("%s: failed to get cpu%d device\n", __func__,
 			       cpu);
-			continue;
+			ret = -ENODEV;
+			goto remove_table;
 		}
 
 		ret = dev_pm_opp_of_add_table(cpu_dev);
@@ -625,12 +644,16 @@ int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask)
 			pr_debug("%s: couldn't find opp table for cpu:%d, %d\n",
 				 __func__, cpu, ret);
 
-			/* Free all other OPPs */
-			dev_pm_opp_of_cpumask_remove_table(cpumask);
-			break;
+			goto remove_table;
 		}
 	}
 
+	return 0;
+
+remove_table:
+	/* Free all other OPPs */
+	_dev_pm_opp_cpumask_remove_table(cpumask, cpu);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table);