Merge tag 'pm+acpi-4.3-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management and ACPI updates from Rafael Wysocki:
 "These are mostly fixes and cleanups on top of the previous PM+ACPI
  pull request (cpufreq core and drivers, cpuidle, generic power domains
  framework).  Some of them didn't make to that pull request and some
  fix issues introduced by it.

  The only really new thing is the support for suspend frequency in the
  cpufreq-dt driver, but it is needed to fix an issue with Exynos
  platforms.

  Specifics:

   - build fix for the new Mediatek MT8173 cpufreq driver (Guenter
     Roeck).

   - generic power domains framework fixes (power on error code path,
     subdomain removal) and cleanup of a deprecated API user (Geert
     Uytterhoeven, Jon Hunter, Ulf Hansson).

   - cpufreq-dt driver fixes including two fixes for bugs related to the
     new Operating Performance Points Device Tree bindings introduced
     recently (Viresh Kumar).

   - suspend frequency support for the cpufreq-dt driver (Bartlomiej
     Zolnierkiewicz, Viresh Kumar).

   - cpufreq core cleanups (Viresh Kumar).

   - intel_pstate driver fixes (Chen Yu, Kristen Carlson Accardi).

   - additional sanity check in the cpuidle core (Xunlei Pang).

   - fix for a comment related to CPU power management (Lina Iyer)"

* tag 'pm+acpi-4.3-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  intel_pstate: fix PCT_TO_HWP macro
  intel_pstate: Fix user input of min/max to legal policy region
  PM / OPP: Return suspend_opp only if it is enabled
  cpufreq-dt: add suspend frequency support
  cpufreq: allow cpufreq_generic_suspend() to work without suspend frequency
  PM / OPP: add dev_pm_opp_get_suspend_opp() helper
  staging: board: Migrate away from __pm_genpd_name_add_device()
  cpufreq: Use __func__ to print function's name
  cpufreq: staticize cpufreq_cpu_get_raw()
  PM / Domains: Ensure subdomain is not in use before removing
  cpufreq: Add ARM_MT8173_CPUFREQ dependency on THERMAL
  cpuidle/coupled: Add sanity check for safe_state_index
  PM / Domains: Try power off masters in error path of __pm_genpd_poweron()
  cpufreq: dt: Tolerance applies on both sides of target voltage
  cpufreq: dt: Print error on failing to mark OPPs as shared
  cpufreq: dt: Check OPP count before marking them shared
  kernel/cpu_pm: fix cpu_cluster_pm_exit comment

4 files changed, 59 insertions, 28 deletions

diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 5f498d9f1825..cd0391e46c6d 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -84,6 +84,7 @@ config ARM_KIRKWOOD_CPUFREQ
 config ARM_MT8173_CPUFREQ
 	bool "Mediatek MT8173 CPUFreq support"
 	depends on ARCH_MEDIATEK && REGULATOR
+	depends on !CPU_THERMAL || THERMAL=y
 	select PM_OPP
 	help
 	  This adds the CPUFreq driver support for Mediatek MT8173 SoC.
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index c3583cdfadbd..7c0d70e2a861 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -196,6 +196,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct device *cpu_dev;
 	struct regulator *cpu_reg;
 	struct clk *cpu_clk;
+	struct dev_pm_opp *suspend_opp;
 	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
 	bool need_update = false;
@@ -239,6 +240,17 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	of_cpumask_init_opp_table(policy->cpus);
 
+	/*
+	 * 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) {
+		pr_debug("OPP table is not ready, deferring probe\n");
+		ret = -EPROBE_DEFER;
+		goto out_free_opp;
+	}
+
 	if (need_update) {
 		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
 
@@ -249,24 +261,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		 * OPP tables are initialized only for policy->cpu, do it for
 		 * others as well.
 		 */
-		set_cpus_sharing_opps(cpu_dev, policy->cpus);
+		ret = set_cpus_sharing_opps(cpu_dev, policy->cpus);
+		if (ret)
+			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+				__func__, ret);
 
 		of_property_read_u32(np, "clock-latency", &transition_latency);
 	} else {
 		transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev);
 	}
 
-	/*
-	 * 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) {
-		pr_debug("OPP table is not ready, deferring probe\n");
-		ret = -EPROBE_DEFER;
-		goto out_free_opp;
-	}
-
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		ret = -ENOMEM;
@@ -300,7 +304,8 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 			rcu_read_unlock();
 
 			tol_uV = opp_uV * priv->voltage_tolerance / 100;
-			if (regulator_is_supported_voltage(cpu_reg, opp_uV,
+			if (regulator_is_supported_voltage(cpu_reg,
+							   opp_uV - tol_uV,
 							   opp_uV + tol_uV)) {
 				if (opp_uV < min_uV)
 					min_uV = opp_uV;
@@ -329,6 +334,13 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = priv;
 
 	policy->clk = cpu_clk;
+
+	rcu_read_lock();
+	suspend_opp = dev_pm_opp_get_suspend_opp(cpu_dev);
+	if (suspend_opp)
+		policy->suspend_freq = dev_pm_opp_get_freq(suspend_opp) / 1000;
+	rcu_read_unlock();
+
 	ret = cpufreq_table_validate_and_show(policy, freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
@@ -419,6 +431,7 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.ready = cpufreq_ready,
 	.name = "cpufreq-dt",
 	.attr = cpufreq_dt_attr,
+	.suspend = cpufreq_generic_suspend,
 };
 
 static int dt_cpufreq_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b3d9368339af..6633b3fa996e 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -239,7 +239,7 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 EXPORT_SYMBOL_GPL(cpufreq_generic_init);
 
 /* Only for cpufreq core internal use */
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
+static struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
@@ -1626,8 +1626,8 @@ int cpufreq_generic_suspend(struct cpufreq_policy *policy)
 	int ret;
 
 	if (!policy->suspend_freq) {
-		pr_err("%s: suspend_freq can't be zero\n", __func__);
-		return -EINVAL;
+		pr_debug("%s: suspend_freq not defined\n", __func__);
+		return 0;
 	}
 
 	pr_debug("%s: Setting suspend-freq: %u\n", __func__,
@@ -2031,8 +2031,7 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 		if (!try_module_get(policy->governor->owner))
 			return -EINVAL;
 
-	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
-		 policy->cpu, event);
+	pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event);
 
 	mutex_lock(&cpufreq_governor_lock);
 	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index cddc61939a86..3af9dd7332e6 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -260,24 +260,31 @@ static inline void update_turbo_state(void)
 		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
 }
 
-#define PCT_TO_HWP(x) (x * 255 / 100)
 static void intel_pstate_hwp_set(void)
 {
-	int min, max, cpu;
-	u64 value, freq;
+	int min, hw_min, max, hw_max, cpu, range, adj_range;
+	u64 value, cap;
+
+	rdmsrl(MSR_HWP_CAPABILITIES, cap);
+	hw_min = HWP_LOWEST_PERF(cap);
+	hw_max = HWP_HIGHEST_PERF(cap);
+	range = hw_max - hw_min;
 
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
-		min = PCT_TO_HWP(limits.min_perf_pct);
+		adj_range = limits.min_perf_pct * range / 100;
+		min = hw_min + adj_range;
 		value &= ~HWP_MIN_PERF(~0L);
 		value |= HWP_MIN_PERF(min);
 
-		max = PCT_TO_HWP(limits.max_perf_pct);
+		adj_range = limits.max_perf_pct * range / 100;
+		max = hw_min + adj_range;
 		if (limits.no_turbo) {
-			rdmsrl( MSR_HWP_CAPABILITIES, freq);
-			max = HWP_GUARANTEED_PERF(freq);
+			hw_max = HWP_GUARANTEED_PERF(cap);
+			if (hw_max < max)
+				max = hw_max;
 		}
 
 		value &= ~HWP_MAX_PERF(~0L);
@@ -423,6 +430,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 
 	limits.max_sysfs_pct = clamp_t(int, input, 0 , 100);
 	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
+	limits.max_perf_pct = max(limits.min_policy_pct, limits.max_perf_pct);
+	limits.max_perf_pct = max(limits.min_perf_pct, limits.max_perf_pct);
 	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
 
 	if (hwp_active)
@@ -442,6 +451,8 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 
 	limits.min_sysfs_pct = clamp_t(int, input, 0 , 100);
 	limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct);
+	limits.min_perf_pct = min(limits.max_policy_pct, limits.min_perf_pct);
+	limits.min_perf_pct = min(limits.max_perf_pct, limits.min_perf_pct);
 	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
 
 	if (hwp_active)
@@ -989,12 +1000,19 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	limits.min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
 	limits.min_policy_pct = clamp_t(int, limits.min_policy_pct, 0 , 100);
-	limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct);
-	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
-
 	limits.max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq;
 	limits.max_policy_pct = clamp_t(int, limits.max_policy_pct, 0 , 100);
+
+	/* Normalize user input to [min_policy_pct, max_policy_pct] */
+	limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct);
+	limits.min_perf_pct = min(limits.max_policy_pct, limits.min_perf_pct);
 	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
+	limits.max_perf_pct = max(limits.min_policy_pct, limits.max_perf_pct);
+
+	/* Make sure min_perf_pct <= max_perf_pct */
+	limits.min_perf_pct = min(limits.max_perf_pct, limits.min_perf_pct);
+
+	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
 	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
 
 	if (hwp_active)