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, 98 insertions, 51 deletions

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 31ff03d..2c2df4e 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -48,9 +48,14 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
 static struct opp_table *_find_opp_table_unlocked(struct device *dev)
 {
 	struct opp_table *opp_table;
+	bool found;
 
 	list_for_each_entry(opp_table, &opp_tables, node) {
-		if (_find_opp_dev(dev, opp_table)) {
+		mutex_lock(&opp_table->lock);
+		found = !!_find_opp_dev(dev, opp_table);
+		mutex_unlock(&opp_table->lock);
+
+		if (found) {
 			_get_opp_table_kref(opp_table);
 
 			return opp_table;
@@ -313,7 +318,7 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 		count = PTR_ERR(opp_table);
 		dev_dbg(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		return 0;
+		return count;
 	}
 
 	count = _get_opp_count(opp_table);
@@ -754,8 +759,8 @@ static void _remove_opp_dev(struct opp_device *opp_dev,
 	kfree(opp_dev);
 }
 
-struct opp_device *_add_opp_dev(const struct device *dev,
-				struct opp_table *opp_table)
+static struct opp_device *_add_opp_dev_unlocked(const struct device *dev,
+						struct opp_table *opp_table)
 {
 	struct opp_device *opp_dev;
 	int ret;
@@ -766,6 +771,7 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 
 	/* Initialize opp-dev */
 	opp_dev->dev = dev;
+
 	list_add(&opp_dev->node, &opp_table->dev_list);
 
 	/* Create debugfs entries for the opp_table */
@@ -777,7 +783,19 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 	return opp_dev;
 }
 
-static struct opp_table *_allocate_opp_table(struct device *dev)
+struct opp_device *_add_opp_dev(const struct device *dev,
+				struct opp_table *opp_table)
+{
+	struct opp_device *opp_dev;
+
+	mutex_lock(&opp_table->lock);
+	opp_dev = _add_opp_dev_unlocked(dev, opp_table);
+	mutex_unlock(&opp_table->lock);
+
+	return opp_dev;
+}
+
+static struct opp_table *_allocate_opp_table(struct device *dev, int index)
 {
 	struct opp_table *opp_table;
 	struct opp_device *opp_dev;
@@ -791,6 +809,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 	if (!opp_table)
 		return NULL;
 
+	mutex_init(&opp_table->lock);
 	INIT_LIST_HEAD(&opp_table->dev_list);
 
 	opp_dev = _add_opp_dev(dev, opp_table);
@@ -799,7 +818,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 		return NULL;
 	}
 
-	_of_init_opp_table(opp_table, dev);
+	_of_init_opp_table(opp_table, dev, index);
 
 	/* Find clk for the device */
 	opp_table->clk = clk_get(dev, NULL);
@@ -812,7 +831,6 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 
 	BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
-	mutex_init(&opp_table->lock);
 	kref_init(&opp_table->kref);
 
 	/* Secure the device table modification */
@@ -825,7 +843,7 @@ void _get_opp_table_kref(struct opp_table *opp_table)
 	kref_get(&opp_table->kref);
 }
 
-struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
+static struct opp_table *_opp_get_opp_table(struct device *dev, int index)
 {
 	struct opp_table *opp_table;
 
@@ -836,31 +854,56 @@ struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
 	if (!IS_ERR(opp_table))
 		goto unlock;
 
-	opp_table = _allocate_opp_table(dev);
+	opp_table = _managed_opp(dev, index);
+	if (opp_table) {
+		if (!_add_opp_dev_unlocked(dev, opp_table)) {
+			dev_pm_opp_put_opp_table(opp_table);
+			opp_table = NULL;
+		}
+		goto unlock;
+	}
+
+	opp_table = _allocate_opp_table(dev, index);
 
 unlock:
 	mutex_unlock(&opp_table_lock);
 
 	return opp_table;
 }
+
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
+{
+	return _opp_get_opp_table(dev, 0);
+}
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
 
+struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev,
+						   int index)
+{
+	return _opp_get_opp_table(dev, index);
+}
+
 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;
+	struct opp_device *opp_dev, *temp;
 
 	/* Release clk */
 	if (!IS_ERR(opp_table->clk))
 		clk_put(opp_table->clk);
 
-	opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device,
-				   node);
+	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	_remove_opp_dev(opp_dev, opp_table);
+	list_for_each_entry_safe(opp_dev, temp, &opp_table->dev_list, node) {
+		/*
+		 * The OPP table is getting removed, drop the performance state
+		 * constraints.
+		 */
+		if (opp_table->genpd_performance_state)
+			dev_pm_genpd_set_performance_state((struct device *)(opp_dev->dev), 0);
 
-	/* dev_list must be empty now */
-	WARN_ON(!list_empty(&opp_table->dev_list));
+		_remove_opp_dev(opp_dev, opp_table);
+	}
 
 	mutex_destroy(&opp_table->lock);
 	list_del(&opp_table->node);
@@ -869,6 +912,33 @@ static void _opp_table_kref_release(struct kref *kref)
 	mutex_unlock(&opp_table_lock);
 }
 
+void _opp_remove_all_static(struct opp_table *opp_table)
+{
+	struct dev_pm_opp *opp, *tmp;
+
+	list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
+		if (!opp->dynamic)
+			dev_pm_opp_put(opp);
+	}
+
+	opp_table->parsed_static_opps = false;
+}
+
+static void _opp_table_list_kref_release(struct kref *kref)
+{
+	struct opp_table *opp_table = container_of(kref, struct opp_table,
+						   list_kref);
+
+	_opp_remove_all_static(opp_table);
+	mutex_unlock(&opp_table_lock);
+}
+
+void _put_opp_list_kref(struct opp_table *opp_table)
+{
+	kref_put_mutex(&opp_table->list_kref, _opp_table_list_kref_release,
+		       &opp_table_lock);
+}
+
 void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
 {
 	kref_put_mutex(&opp_table->kref, _opp_table_kref_release,
@@ -896,7 +966,6 @@ static void _opp_kref_release(struct kref *kref)
 	kfree(opp);
 
 	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
 }
 
 void dev_pm_opp_get(struct dev_pm_opp *opp)
@@ -940,11 +1009,15 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 
 	if (found) {
 		dev_pm_opp_put(opp);
+
+		/* Drop the reference taken by dev_pm_opp_add() */
+		dev_pm_opp_put_opp_table(opp_table);
 	} else {
 		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
 			 __func__, freq);
 	}
 
+	/* Drop the reference taken by _find_opp_table() */
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
@@ -1062,9 +1135,6 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	new_opp->opp_table = opp_table;
 	kref_init(&new_opp->kref);
 
-	/* Get a reference to the OPP table */
-	_get_opp_table_kref(opp_table);
-
 	ret = opp_debug_create_one(new_opp, opp_table);
 	if (ret)
 		dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n",
@@ -1543,8 +1613,9 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 		return -ENOMEM;
 
 	ret = _opp_add_v1(opp_table, dev, freq, u_volt, true);
+	if (ret)
+		dev_pm_opp_put_opp_table(opp_table);
 
-	dev_pm_opp_put_opp_table(opp_table);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_add);
@@ -1707,35 +1778,7 @@ int dev_pm_opp_unregister_notifier(struct device *dev,
 }
 EXPORT_SYMBOL(dev_pm_opp_unregister_notifier);
 
-/*
- * Free OPPs either created using static entries present in DT or even the
- * dynamically added entries based on remove_all param.
- */
-void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev,
-			      bool remove_all)
-{
-	struct dev_pm_opp *opp, *tmp;
-
-	/* Find if opp_table manages a single device */
-	if (list_is_singular(&opp_table->dev_list)) {
-		/* Free static OPPs */
-		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
-			if (remove_all || !opp->dynamic)
-				dev_pm_opp_put(opp);
-		}
-
-		/*
-		 * The OPP table is getting removed, drop the performance state
-		 * constraints.
-		 */
-		if (opp_table->genpd_performance_state)
-			dev_pm_genpd_set_performance_state(dev, 0);
-	} else {
-		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
-	}
-}
-
-void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
+void _dev_pm_opp_find_and_remove_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 
@@ -1752,8 +1795,12 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
 		return;
 	}
 
-	_dev_pm_opp_remove_table(opp_table, dev, remove_all);
+	_put_opp_list_kref(opp_table);
+
+	/* Drop reference taken by _find_opp_table() */
+	dev_pm_opp_put_opp_table(opp_table);
 
+	/* Drop reference taken while the OPP table was added */
 	dev_pm_opp_put_opp_table(opp_table);
 }
 
@@ -1766,6 +1813,6 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
  */
 void dev_pm_opp_remove_table(struct device *dev)
 {
-	_dev_pm_opp_find_and_remove_table(dev, true);
+	_dev_pm_opp_find_and_remove_table(dev);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table);