Merge branch 'opp/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm

Pull OPP (Operating Performance Points) updates for 5.11-rc1 from
Viresh Kumar:

"This contains the following updates:

 - Allow empty (node-less) OPP tables in DT for passing just the
   dependency related information (Nicola Mazzucato).

 - Fix a potential lockdep in OPP core and other OPP core cleanups
   (Viresh Kumar).

 - Don't abuse dev_pm_opp_get_opp_table() to create an OPP table, fix
   cpufreq-dt driver for the same (Viresh Kumar).

 - dev_pm_opp_put_regulators() accepts a NULL argument now, updates to
   all the users as well (Viresh Kumar)."

* 'opp/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  opp: of: Allow empty opp-table with opp-shared
  dt-bindings: opp: Allow empty OPP tables
  media: venus: dev_pm_opp_put_*() accepts NULL argument
  drm/panfrost: dev_pm_opp_put_*() accepts NULL argument
  drm/lima: dev_pm_opp_put_*() accepts NULL argument
  PM / devfreq: exynos: dev_pm_opp_put_*() accepts NULL argument
  cpufreq: qcom-cpufreq-nvmem: dev_pm_opp_put_*() accepts NULL argument
  cpufreq: dt: dev_pm_opp_put_regulators() accepts NULL argument
  opp: Allow dev_pm_opp_put_*() APIs to accept NULL opp_table
  opp: Don't create an OPP table from dev_pm_opp_get_opp_table()
  cpufreq: dt: Don't (ab)use dev_pm_opp_get_opp_table() to create OPP table
  opp: Reduce the size of critical section in _opp_kref_release()
  opp: Don't return opp_dev from _find_opp_dev()
  opp: Allocate the OPP table outside of opp_table_lock
  opp: Always add entries in dev_list with opp_table->lock held

Author: rafaeljw

Documentation/devicetree/bindings/opp/opp.txt

@@ -65,7 +65,9 @@ Required properties:
 
 - OPP nodes: One or more OPP nodes describing voltage-current-frequency
   combinations. Their name isn't significant but their phandle can be used to
-  reference an OPP.
+  reference an OPP. These are mandatory except for the case where the OPP table
+  is present only to indicate dependency between devices using the opp-shared
+  property.
 
 Optional properties:
 - opp-shared: Indicates that device nodes using this OPP Table Node's phandle
@@ -568,3 +570,53 @@ Example 6: opp-microvolt-<name>, opp-microamp-<name>:
 		};
 	};
 };
+
+Example 7: Single cluster Quad-core ARM cortex A53, OPP points from firmware,
+distinct clock controls but two sets of clock/voltage/current lines.
+
+/ {
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a53";
+			reg = <0x0 0x100>;
+			next-level-cache = <&A53_L2>;
+			clocks = <&dvfs_controller 0>;
+			operating-points-v2 = <&cpu_opp0_table>;
+		};
+		cpu@1 {
+			compatible = "arm,cortex-a53";
+			reg = <0x0 0x101>;
+			next-level-cache = <&A53_L2>;
+			clocks = <&dvfs_controller 1>;
+			operating-points-v2 = <&cpu_opp0_table>;
+		};
+		cpu@2 {
+			compatible = "arm,cortex-a53";
+			reg = <0x0 0x102>;
+			next-level-cache = <&A53_L2>;
+			clocks = <&dvfs_controller 2>;
+			operating-points-v2 = <&cpu_opp1_table>;
+		};
+		cpu@3 {
+			compatible = "arm,cortex-a53";
+			reg = <0x0 0x103>;
+			next-level-cache = <&A53_L2>;
+			clocks = <&dvfs_controller 3>;
+			operating-points-v2 = <&cpu_opp1_table>;
+		};
+
+	};
+
+	cpu_opp0_table: opp0_table {
+		compatible = "operating-points-v2";
+		opp-shared;
+	};
+
+	cpu_opp1_table: opp1_table {
+		compatible = "operating-points-v2";
+		opp-shared;
+	};
+};

drivers/base/power/domain.c

@@ -2249,7 +2249,7 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 			 * Save table for faster processing while setting
 			 * performance state.
 			 */
-			genpd->opp_table = dev_pm_opp_get_opp_table_indexed(&genpd->dev, i);
+			genpd->opp_table = dev_pm_opp_get_opp_table(&genpd->dev);
 			WARN_ON(IS_ERR(genpd->opp_table));
 		}
 

drivers/cpufreq/cpufreq-dt.c

@@ -30,7 +30,7 @@ struct private_data {
 	cpumask_var_t cpus;
 	struct device *cpu_dev;
 	struct opp_table *opp_table;
-	struct opp_table *reg_opp_table;
+	struct cpufreq_frequency_table *freq_table;
 	bool have_static_opps;
 };
 
@@ -102,7 +102,6 @@ static const char *find_supply_name(struct device *dev)
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct cpufreq_frequency_table *freq_table;
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
@@ -114,9 +113,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		pr_err("failed to find data for cpu%d\n", policy->cpu);
 		return -ENODEV;
 	}
-
 	cpu_dev = priv->cpu_dev;
-	cpumask_copy(policy->cpus, priv->cpus);
 
 	cpu_clk = clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
@@ -125,67 +122,32 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		return ret;
 	}
 
-	/*
-	 * Initialize OPP tables for all policy->cpus. They will be shared by
-	 * all CPUs which have marked their CPUs shared with OPP bindings.
-	 *
-	 * For platforms not using operating-points-v2 bindings, we do this
-	 * before updating policy->cpus. Otherwise, we will end up creating
-	 * duplicate OPPs for policy->cpus.
-	 *
-	 * OPPs might be populated at runtime, don't check for error here
-	 */
-	if (!dev_pm_opp_of_cpumask_add_table(policy->cpus))
-		priv->have_static_opps = true;
-
-	/*
-	 * But we need OPP table to function so if it is not there let's
-	 * give platform code chance to provide it for us.
-	 */
-	ret = dev_pm_opp_get_opp_count(cpu_dev);
-	if (ret <= 0) {
-		dev_err(cpu_dev, "OPP table can't be empty\n");
-		ret = -ENODEV;
-		goto out_free_opp;
-	}
-
-	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
-	if (ret) {
-		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
-		goto out_free_opp;
-	}
+	transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev);
+	if (!transition_latency)
+		transition_latency = CPUFREQ_ETERNAL;
 
+	cpumask_copy(policy->cpus, priv->cpus);
 	policy->driver_data = priv;
 	policy->clk = cpu_clk;
-	policy->freq_table = freq_table;
-
+	policy->freq_table = priv->freq_table;
 	policy->suspend_freq = dev_pm_opp_get_suspend_opp_freq(cpu_dev) / 1000;
+	policy->cpuinfo.transition_latency = transition_latency;
+	policy->dvfs_possible_from_any_cpu = true;
 
 	/* Support turbo/boost mode */
 	if (policy_has_boost_freq(policy)) {
 		/* This gets disabled by core on driver unregister */
 		ret = cpufreq_enable_boost_support();
 		if (ret)
-			goto out_free_cpufreq_table;
+			goto out_clk_put;
 		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
 	}
 
-	transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev);
-	if (!transition_latency)
-		transition_latency = CPUFREQ_ETERNAL;
-
-	policy->cpuinfo.transition_latency = transition_latency;
-	policy->dvfs_possible_from_any_cpu = true;
-
 	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	return 0;
 
-out_free_cpufreq_table:
-	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
-out_free_opp:
-	if (priv->have_static_opps)
-		dev_pm_opp_of_cpumask_remove_table(policy->cpus);
+out_clk_put:
 	clk_put(cpu_clk);
 
 	return ret;
@@ -208,11 +170,6 @@ static int cpufreq_offline(struct cpufreq_policy *policy)
 
 static int cpufreq_exit(struct cpufreq_policy *policy)
 {
-	struct private_data *priv = policy->driver_data;
-
-	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	if (priv->have_static_opps)
-		dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
 	clk_put(policy->clk);
 	return 0;
 }
@@ -236,6 +193,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 {
 	struct private_data *priv;
 	struct device *cpu_dev;
+	bool fallback = false;
 	const char *reg_name;
 	int ret;
 
@@ -254,68 +212,86 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 	if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL))
 		return -ENOMEM;
 
+	cpumask_set_cpu(cpu, priv->cpus);
 	priv->cpu_dev = cpu_dev;
 
-	/* Try to get OPP table early to ensure resources are available */
-	priv->opp_table = dev_pm_opp_get_opp_table(cpu_dev);
-	if (IS_ERR(priv->opp_table)) {
-		ret = PTR_ERR(priv->opp_table);
-		if (ret != -EPROBE_DEFER)
-			dev_err(cpu_dev, "failed to get OPP table: %d\n", ret);
-		goto free_cpumask;
-	}
-
 	/*
 	 * OPP layer will be taking care of regulators now, but it needs to know
 	 * the name of the regulator first.
 	 */
 	reg_name = find_supply_name(cpu_dev);
 	if (reg_name) {
-		priv->reg_opp_table = dev_pm_opp_set_regulators(cpu_dev,
-								&reg_name, 1);
-		if (IS_ERR(priv->reg_opp_table)) {
-			ret = PTR_ERR(priv->reg_opp_table);
+		priv->opp_table = dev_pm_opp_set_regulators(cpu_dev, &reg_name,
+							    1);
+		if (IS_ERR(priv->opp_table)) {
+			ret = PTR_ERR(priv->opp_table);
 			if (ret != -EPROBE_DEFER)
 				dev_err(cpu_dev, "failed to set regulators: %d\n",
 					ret);
-			goto put_table;
+			goto free_cpumask;
 		}
 	}
 
-	/* Find OPP sharing information so we can fill pri->cpus here */
 	/* Get OPP-sharing information from "operating-points-v2" bindings */
 	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, priv->cpus);
 	if (ret) {
 		if (ret != -ENOENT)
-			goto put_reg;
+			goto out;
 
 		/*
 		 * operating-points-v2 not supported, fallback to all CPUs share
 		 * OPP for backward compatibility if the platform hasn't set
 		 * sharing CPUs.
 		 */
-		if (dev_pm_opp_get_sharing_cpus(cpu_dev, priv->cpus)) {
-			cpumask_setall(priv->cpus);
-
-			/*
-			 * OPP tables are initialized only for cpu, do it for
-			 * others as well.
-			 */
-			ret = dev_pm_opp_set_sharing_cpus(cpu_dev, priv->cpus);
-			if (ret)
-				dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
-					__func__, ret);
-		}
+		if (dev_pm_opp_get_sharing_cpus(cpu_dev, priv->cpus))
+			fallback = true;
+	}
+
+	/*
+	 * Initialize OPP tables for all priv->cpus. They will be shared by
+	 * all CPUs which have marked their CPUs shared with OPP bindings.
+	 *
+	 * For platforms not using operating-points-v2 bindings, we do this
+	 * before updating priv->cpus. Otherwise, we will end up creating
+	 * duplicate OPPs for the CPUs.
+	 *
+	 * OPPs might be populated at runtime, don't check for error here.
+	 */
+	if (!dev_pm_opp_of_cpumask_add_table(priv->cpus))
+		priv->have_static_opps = true;
+
+	/*
+	 * The OPP table must be initialized, statically or dynamically, by this
+	 * point.
+	 */
+	ret = dev_pm_opp_get_opp_count(cpu_dev);
+	if (ret <= 0) {
+		dev_err(cpu_dev, "OPP table can't be empty\n");
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (fallback) {
+		cpumask_setall(priv->cpus);
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, priv->cpus);
+		if (ret)
+			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+				__func__, ret);
+	}
+
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &priv->freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
+		goto out;
 	}
 
 	list_add(&priv->node, &priv_list);
 	return 0;
 
-put_reg:
-	if (priv->reg_opp_table)
-		dev_pm_opp_put_regulators(priv->reg_opp_table);
-put_table:
-	dev_pm_opp_put_opp_table(priv->opp_table);
+out:
+	if (priv->have_static_opps)
+		dev_pm_opp_of_cpumask_remove_table(priv->cpus);
+	dev_pm_opp_put_regulators(priv->opp_table);
 free_cpumask:
 	free_cpumask_var(priv->cpus);
 	return ret;
@@ -326,9 +302,10 @@ static void dt_cpufreq_release(void)
 	struct private_data *priv, *tmp;
 
 	list_for_each_entry_safe(priv, tmp, &priv_list, node) {
-		if (priv->reg_opp_table)
-			dev_pm_opp_put_regulators(priv->reg_opp_table);
-		dev_pm_opp_put_opp_table(priv->opp_table);
+		dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &priv->freq_table);
+		if (priv->have_static_opps)
+			dev_pm_opp_of_cpumask_remove_table(priv->cpus);
+		dev_pm_opp_put_regulators(priv->opp_table);
 		free_cpumask_var(priv->cpus);
 		list_del(&priv->node);
 	}

drivers/cpufreq/qcom-cpufreq-nvmem.c

@@ -397,19 +397,19 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 
 free_genpd_opp:
 	for_each_possible_cpu(cpu) {
-		if (IS_ERR_OR_NULL(drv->genpd_opp_tables[cpu]))
+		if (IS_ERR(drv->genpd_opp_tables[cpu]))
 			break;
 		dev_pm_opp_detach_genpd(drv->genpd_opp_tables[cpu]);
 	}
 	kfree(drv->genpd_opp_tables);
 free_opp:
 	for_each_possible_cpu(cpu) {
-		if (IS_ERR_OR_NULL(drv->names_opp_tables[cpu]))
+		if (IS_ERR(drv->names_opp_tables[cpu]))
 			break;
 		dev_pm_opp_put_prop_name(drv->names_opp_tables[cpu]);
 	}
 	for_each_possible_cpu(cpu) {
-		if (IS_ERR_OR_NULL(drv->hw_opp_tables[cpu]))
+		if (IS_ERR(drv->hw_opp_tables[cpu]))
 			break;
 		dev_pm_opp_put_supported_hw(drv->hw_opp_tables[cpu]);
 	}
@@ -430,12 +430,9 @@ static int qcom_cpufreq_remove(struct platform_device *pdev)
 	platform_device_unregister(cpufreq_dt_pdev);
 
 	for_each_possible_cpu(cpu) {
-		if (drv->names_opp_tables[cpu])
-			dev_pm_opp_put_supported_hw(drv->names_opp_tables[cpu]);
-		if (drv->hw_opp_tables[cpu])
-			dev_pm_opp_put_supported_hw(drv->hw_opp_tables[cpu]);
-		if (drv->genpd_opp_tables[cpu])
-			dev_pm_opp_detach_genpd(drv->genpd_opp_tables[cpu]);
+		dev_pm_opp_put_supported_hw(drv->names_opp_tables[cpu]);
+		dev_pm_opp_put_supported_hw(drv->hw_opp_tables[cpu]);
+		dev_pm_opp_detach_genpd(drv->genpd_opp_tables[cpu]);
 	}
 
 	kfree(drv->names_opp_tables);

drivers/devfreq/exynos-bus.c

@@ -158,10 +158,8 @@ static void exynos_bus_exit(struct device *dev)
 
 	dev_pm_opp_of_remove_table(dev);
 	clk_disable_unprepare(bus->clk);
-	if (bus->opp_table) {
-		dev_pm_opp_put_regulators(bus->opp_table);
-		bus->opp_table = NULL;
-	}
+	dev_pm_opp_put_regulators(bus->opp_table);
+	bus->opp_table = NULL;
 }
 
 static void exynos_bus_passive_exit(struct device *dev)
@@ -444,10 +442,8 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	dev_pm_opp_of_remove_table(dev);
 	clk_disable_unprepare(bus->clk);
 err_reg:
-	if (!passive) {
-		dev_pm_opp_put_regulators(bus->opp_table);
-		bus->opp_table = NULL;
-	}
+	dev_pm_opp_put_regulators(bus->opp_table);
+	bus->opp_table = NULL;
 
 	return ret;
 }