Merge tag 'pm-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These rework the collection of cpufreq statistics to allow it to take
  place if fast frequency switching is enabled in the governor, rework
  the frequency invariance handling in the cpufreq core and drivers, add
  new hardware support to a couple of cpufreq drivers, fix a number of
  assorted issues and clean up the code all over.

  Specifics:

   - Rework cpufreq statistics collection to allow it to take place when
     fast frequency switching is enabled in the governor (Viresh Kumar).

   - Make the cpufreq core set the frequency scale on behalf of the
     driver and update several cpufreq drivers accordingly (Ionela
     Voinescu, Valentin Schneider).

   - Add new hardware support to the STI and qcom cpufreq drivers and
     improve them (Alain Volmat, Manivannan Sadhasivam).

   - Fix multiple assorted issues in cpufreq drivers (Jon Hunter,
     Krzysztof Kozlowski, Matthias Kaehlcke, Pali Rohár, Stephan
     Gerhold, Viresh Kumar).

   - Fix several assorted issues in the operating performance points
     (OPP) framework (Stephan Gerhold, Viresh Kumar).

   - Allow devfreq drivers to fetch devfreq instances by DT enumeration
     instead of using explicit phandles and modify the devfreq core code
     to support driver-specific devfreq DT bindings (Leonard Crestez,
     Chanwoo Choi).

   - Improve initial hardware resetting in the tegra30 devfreq driver
     and clean up the tegra cpuidle driver (Dmitry Osipenko).

   - Update the cpuidle core to collect state entry rejection statistics
     and expose them via sysfs (Lina Iyer).

   - Improve the ACPI _CST code handling diagnostics (Chen Yu).

   - Update the PSCI cpuidle driver to allow the PM domain
     initialization to occur in the OSI mode as well as in the PC mode
     (Ulf Hansson).

   - Rework the generic power domains (genpd) core code to allow domain
     power off transition to be aborted in the absence of the "power
     off" domain callback (Ulf Hansson).

   - Fix two suspend-to-idle issues in the ACPI EC driver (Rafael
     Wysocki).

   - Fix the handling of timer_expires in the PM-runtime framework on
     32-bit systems and the handling of device links in it (Grygorii
     Strashko, Xiang Chen).

   - Add IO requests batching support to the hibernate image saving and
     reading code and drop a bogus get_gendisk() from there (Xiaoyi
     Chen, Christoph Hellwig).

   - Allow PCIe ports to be put into the D3cold power state if they are
     power-manageable via ACPI (Lukas Wunner).

   - Add missing header file include to a power capping driver (Pujin
     Shi).

   - Clean up the qcom-cpr AVS driver a bit (Liu Shixin).

   - Kevin Hilman steps down as designated reviwer of adaptive voltage
     scaling (AVS) drivers (Kevin Hilman)"

* tag 'pm-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (65 commits)
  cpufreq: stats: Fix string format specifier mismatch
  arm: disable frequency invariance for CONFIG_BL_SWITCHER
  cpufreq,arm,arm64: restructure definitions of arch_set_freq_scale()
  cpufreq: stats: Add memory barrier to store_reset()
  cpufreq: schedutil: Simplify sugov_fast_switch()
  ACPI: EC: PM: Drop ec_no_wakeup check from acpi_ec_dispatch_gpe()
  ACPI: EC: PM: Flush EC work unconditionally after wakeup
  PCI/ACPI: Whitelist hotplug ports for D3 if power managed by ACPI
  PM: hibernate: remove the bogus call to get_gendisk() in software_resume()
  cpufreq: Move traces and update to policy->cur to cpufreq core
  cpufreq: stats: Enable stats for fast-switch as well
  cpufreq: stats: Mark few conditionals with unlikely()
  cpufreq: stats: Remove locking
  cpufreq: stats: Defer stats update to cpufreq_stats_record_transition()
  PM: domains: Allow to abort power off when no ->power_off() callback
  PM: domains: Rename power state enums for genpd
  PM / devfreq: tegra30: Improve initial hardware resetting
  PM / devfreq: event: Change prototype of devfreq_event_get_edev_by_phandle function
  PM / devfreq: Change prototype of devfreq_get_devfreq_by_phandle function
  PM / devfreq: Add devfreq_get_devfreq_by_node function
  ...

1 files changed, 144 insertions, 152 deletions

diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 944d7b45afe9..e363ae04aac6 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -13,6 +13,7 @@
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/err.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/pm_opp.h>
@@ -24,32 +25,41 @@
 #include "cpufreq-dt.h"
 
 struct private_data {
-	struct opp_table *opp_table;
+	struct list_head node;
+
+	cpumask_var_t cpus;
 	struct device *cpu_dev;
-	const char *reg_name;
+	struct opp_table *opp_table;
+	struct opp_table *reg_opp_table;
 	bool have_static_opps;
 };
 
+static LIST_HEAD(priv_list);
+
 static struct freq_attr *cpufreq_dt_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	NULL,   /* Extra space for boost-attr if required */
 	NULL,
 };
 
+static struct private_data *cpufreq_dt_find_data(int cpu)
+{
+	struct private_data *priv;
+
+	list_for_each_entry(priv, &priv_list, node) {
+		if (cpumask_test_cpu(cpu, priv->cpus))
+			return priv;
+	}
+
+	return NULL;
+}
+
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct private_data *priv = policy->driver_data;
 	unsigned long freq = policy->freq_table[index].frequency;
-	int ret;
-
-	ret = dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000);
-
-	if (!ret) {
-		arch_set_freq_scale(policy->related_cpus, freq,
-				    policy->cpuinfo.max_freq);
-	}
 
-	return ret;
+	return dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000);
 }
 
 /*
@@ -90,83 +100,24 @@ node_put:
 	return name;
 }
 
-static int resources_available(void)
-{
-	struct device *cpu_dev;
-	struct regulator *cpu_reg;
-	struct clk *cpu_clk;
-	int ret = 0;
-	const char *name;
-
-	cpu_dev = get_cpu_device(0);
-	if (!cpu_dev) {
-		pr_err("failed to get cpu0 device\n");
-		return -ENODEV;
-	}
-
-	cpu_clk = clk_get(cpu_dev, NULL);
-	ret = PTR_ERR_OR_ZERO(cpu_clk);
-	if (ret) {
-		/*
-		 * If cpu's clk node is present, but clock is not yet
-		 * registered, we should try defering probe.
-		 */
-		if (ret == -EPROBE_DEFER)
-			dev_dbg(cpu_dev, "clock not ready, retry\n");
-		else
-			dev_err(cpu_dev, "failed to get clock: %d\n", ret);
-
-		return ret;
-	}
-
-	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)
-		return 0;
-
-	cpu_reg = regulator_get_optional(cpu_dev, name);
-	ret = PTR_ERR_OR_ZERO(cpu_reg);
-	if (ret) {
-		/*
-		 * If cpu's regulator supply node is present, but regulator is
-		 * not yet registered, we should try defering probe.
-		 */
-		if (ret == -EPROBE_DEFER)
-			dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n");
-		else
-			dev_dbg(cpu_dev, "no regulator for cpu0: %d\n", ret);
-
-		return ret;
-	}
-
-	regulator_put(cpu_reg);
-	return 0;
-}
-
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct cpufreq_frequency_table *freq_table;
-	struct opp_table *opp_table = NULL;
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
 	unsigned int transition_latency;
-	bool fallback = false;
-	const char *name;
 	int ret;
 
-	cpu_dev = get_cpu_device(policy->cpu);
-	if (!cpu_dev) {
-		pr_err("failed to get cpu%d device\n", policy->cpu);
+	priv = cpufreq_dt_find_data(policy->cpu);
+	if (!priv) {
+		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)) {
 		ret = PTR_ERR(cpu_clk);
@@ -174,45 +125,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		return ret;
 	}
 
-	/* Get OPP-sharing information from "operating-points-v2" bindings */
-	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, policy->cpus);
-	if (ret) {
-		if (ret != -ENOENT)
-			goto out_put_clk;
-
-		/*
-		 * operating-points-v2 not supported, fallback to old method of
-		 * finding shared-OPPs for backward compatibility if the
-		 * platform hasn't set sharing CPUs.
-		 */
-		if (dev_pm_opp_get_sharing_cpus(cpu_dev, policy->cpus))
-			fallback = true;
-	}
-
-	/*
-	 * OPP layer will be taking care of regulators now, but it needs to know
-	 * the name of the regulator first.
-	 */
-	name = find_supply_name(cpu_dev);
-	if (name) {
-		opp_table = dev_pm_opp_set_regulators(cpu_dev, &name, 1);
-		if (IS_ERR(opp_table)) {
-			ret = PTR_ERR(opp_table);
-			dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n",
-				policy->cpu, ret);
-			goto out_put_clk;
-		}
-	}
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto out_put_regulator;
-	}
-
-	priv->reg_name = name;
-	priv->opp_table = opp_table;
-
 	/*
 	 * Initialize OPP tables for all policy->cpus. They will be shared by
 	 * all CPUs which have marked their CPUs shared with OPP bindings.
@@ -232,31 +144,17 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	ret = dev_pm_opp_get_opp_count(cpu_dev);
 	if (ret <= 0) {
-		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
-		ret = -EPROBE_DEFER;
+		dev_err(cpu_dev, "OPP table can't be empty\n");
+		ret = -ENODEV;
 		goto out_free_opp;
 	}
 
-	if (fallback) {
-		cpumask_setall(policy->cpus);
-
-		/*
-		 * OPP tables are initialized only for policy->cpu, do it for
-		 * others as well.
-		 */
-		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->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, &freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
 		goto out_free_opp;
 	}
 
-	priv->cpu_dev = cpu_dev;
 	policy->driver_data = priv;
 	policy->clk = cpu_clk;
 	policy->freq_table = freq_table;
@@ -288,11 +186,6 @@ out_free_cpufreq_table:
 out_free_opp:
 	if (priv->have_static_opps)
 		dev_pm_opp_of_cpumask_remove_table(policy->cpus);
-	kfree(priv);
-out_put_regulator:
-	if (name)
-		dev_pm_opp_put_regulators(opp_table);
-out_put_clk:
 	clk_put(cpu_clk);
 
 	return ret;
@@ -320,12 +213,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	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);
-	if (priv->reg_name)
-		dev_pm_opp_put_regulators(priv->opp_table);
-
 	clk_put(policy->clk);
-	kfree(priv);
-
 	return 0;
 }
 
@@ -344,21 +232,119 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.suspend = cpufreq_generic_suspend,
 };
 
-static int dt_cpufreq_probe(struct platform_device *pdev)
+static int dt_cpufreq_early_init(struct device *dev, int cpu)
 {
-	struct cpufreq_dt_platform_data *data = dev_get_platdata(&pdev->dev);
+	struct private_data *priv;
+	struct device *cpu_dev;
+	const char *reg_name;
 	int ret;
 
+	/* Check if this CPU is already covered by some other policy */
+	if (cpufreq_dt_find_data(cpu))
+		return 0;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return -EPROBE_DEFER;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL))
+		return -ENOMEM;
+
+	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;
+	}
+
 	/*
-	 * All per-cluster (CPUs sharing clock/voltages) initialization is done
-	 * from ->init(). In probe(), we just need to make sure that clk and
-	 * regulators are available. Else defer probe and retry.
-	 *
-	 * FIXME: Is checking this only for CPU0 sufficient ?
+	 * OPP layer will be taking care of regulators now, but it needs to know
+	 * the name of the regulator first.
 	 */
-	ret = resources_available();
-	if (ret)
-		return ret;
+	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);
+			if (ret != -EPROBE_DEFER)
+				dev_err(cpu_dev, "failed to set regulators: %d\n",
+					ret);
+			goto put_table;
+		}
+	}
+
+	/* 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;
+
+		/*
+		 * 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);
+		}
+	}
+
+	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);
+free_cpumask:
+	free_cpumask_var(priv->cpus);
+	return ret;
+}
+
+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);
+		free_cpumask_var(priv->cpus);
+		list_del(&priv->node);
+	}
+}
+
+static int dt_cpufreq_probe(struct platform_device *pdev)
+{
+	struct cpufreq_dt_platform_data *data = dev_get_platdata(&pdev->dev);
+	int ret, cpu;
+
+	/* Request resources early so we can return in case of -EPROBE_DEFER */
+	for_each_possible_cpu(cpu) {
+		ret = dt_cpufreq_early_init(&pdev->dev, cpu);
+		if (ret)
+			goto err;
+	}
 
 	if (data) {
 		if (data->have_governor_per_policy)
@@ -374,15 +360,21 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	ret = cpufreq_register_driver(&dt_cpufreq_driver);
-	if (ret)
+	if (ret) {
 		dev_err(&pdev->dev, "failed register driver: %d\n", ret);
+		goto err;
+	}
 
+	return 0;
+err:
+	dt_cpufreq_release();
 	return ret;
 }
 
 static int dt_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&dt_cpufreq_driver);
+	dt_cpufreq_release();
 	return 0;
 }