Merge branch 'pm-cpufreq'

* pm-cpufreq:
  cpufreq / intel_pstate: use vzalloc() instead of vmalloc()/memset(0)
  cpufreq, ondemand: Remove leftover debug line
  cpufreq / kirkwood: don't check resource with devm_ioremap_resource
  cpufreq / intel_pstate: remove #ifdef MODULE compile fence
  cpufreq / intel_pstate: Remove idle mode PID
  cpufreq / intel_pstate: fix ffmpeg regression
  cpufreq / intel_pstate: use lowest requested max performance
  cpufreq / intel_pstate: remove idle time and duration from sample and calculations
  cpufreq: Fix incorrect dependecies for ARM SA11xx drivers
  cpufreq: ARM big LITTLE: Fix Kconfig entries
  cpufreq: cpufreq-cpu0: Free parent node for error cases
  cpufreq: cpufreq-cpu0: defer probe when regulator is not ready
  cpufreq: Issue CPUFREQ_GOV_POLICY_EXIT notifier before dropping policy refcount
  cpufreq: governors: Fix CPUFREQ_GOV_POLICY_{INIT|EXIT} notifiers
  cpufreq: ARM big LITTLE: Improve print message
  cpufreq: ARM big LITTLE: Move cpu_to_cluster() to arm_big_little.h
  cpufreq: ARM big LITTLE DT: Return CPUFREQ_ETERNAL if clock-latency isn't found
  cpufreq: ARM big LITTLE DT: Return correct transition latency
  cpufreq: ARM big LITTLE: Select PM_OPP

drivers/cpufreq/Kconfig

@@ -47,7 +47,7 @@ config CPU_FREQ_STAT_DETAILS
 
 choice
 	prompt "Default CPUFreq governor"
-	default CPU_FREQ_DEFAULT_GOV_USERSPACE if CPU_FREQ_SA1100 || CPU_FREQ_SA1110
+	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
 	default CPU_FREQ_DEFAULT_GOV_PERFORMANCE
 	help
 	  This option sets which CPUFreq governor shall be loaded at

drivers/cpufreq/Kconfig.arm

@@ -3,16 +3,17 @@
 #
 
 config ARM_BIG_LITTLE_CPUFREQ
-	tristate
-	depends on ARM_CPU_TOPOLOGY
+	tristate "Generic ARM big LITTLE CPUfreq driver"
+	depends on ARM_CPU_TOPOLOGY && PM_OPP && HAVE_CLK
+	help
+	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
 
 config ARM_DT_BL_CPUFREQ
-	tristate "Generic ARM big LITTLE CPUfreq driver probed via DT"
-	select ARM_BIG_LITTLE_CPUFREQ
-	depends on OF && HAVE_CLK
+	tristate "Generic probing via DT for ARM big LITTLE CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && OF
 	help
-	  This enables the Generic CPUfreq driver for ARM big.LITTLE platform.
-	  This gets frequency tables from DT.
+	  This enables probing via DT for Generic CPUfreq driver for ARM
+	  big.LITTLE platform. This gets frequency tables from DT.
 
 config ARM_EXYNOS_CPUFREQ
 	bool "SAMSUNG EXYNOS SoCs"

drivers/cpufreq/arm_big_little.c

@@ -40,11 +40,6 @@ static struct clk *clk[MAX_CLUSTERS];
 static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS];
 static atomic_t cluster_usage[MAX_CLUSTERS] = {ATOMIC_INIT(0), ATOMIC_INIT(0)};
 
-static int cpu_to_cluster(int cpu)
-{
-	return topology_physical_package_id(cpu);
-}
-
 static unsigned int bL_cpufreq_get(unsigned int cpu)
 {
 	u32 cur_cluster = cpu_to_cluster(cpu);
@@ -192,7 +187,7 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 
 	cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
 
-	dev_info(cpu_dev, "CPU %d initialized\n", policy->cpu);
+	dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
 	return 0;
 }
 

drivers/cpufreq/arm_big_little.h

@@ -34,6 +34,11 @@ struct cpufreq_arm_bL_ops {
 	int (*init_opp_table)(struct device *cpu_dev);
 };
 
+static inline int cpu_to_cluster(int cpu)
+{
+	return topology_physical_package_id(cpu);
+}
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops);
 void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops);
 

drivers/cpufreq/arm_big_little_dt.c

@@ -66,8 +66,8 @@ static int dt_get_transition_latency(struct device *cpu_dev)
 
 	parent = of_find_node_by_path("/cpus");
 	if (!parent) {
-		pr_err("failed to find OF /cpus\n");
-		return -ENOENT;
+		pr_info("Failed to find OF /cpus. Use CPUFREQ_ETERNAL transition latency\n");
+		return CPUFREQ_ETERNAL;
 	}
 
 	for_each_child_of_node(parent, np) {
@@ -78,10 +78,11 @@ static int dt_get_transition_latency(struct device *cpu_dev)
 		of_node_put(np);
 		of_node_put(parent);
 
-		return 0;
+		return transition_latency;
 	}
 
-	return -ENODEV;
+	pr_info("clock-latency isn't found, use CPUFREQ_ETERNAL transition latency\n");
+	return CPUFREQ_ETERNAL;
 }
 
 static struct cpufreq_arm_bL_ops dt_bL_ops = {

drivers/cpufreq/cpufreq-cpu0.c

@@ -189,12 +189,29 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 
 	if (!np) {
 		pr_err("failed to find cpu0 node\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto out_put_parent;
 	}
 
 	cpu_dev = &pdev->dev;
 	cpu_dev->of_node = np;
 
+	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
+	if (IS_ERR(cpu_reg)) {
+		/*
+		 * If cpu0 regulator supply node is present, but regulator is
+		 * not yet registered, we should try defering probe.
+		 */
+		if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) {
+			dev_err(cpu_dev, "cpu0 regulator not ready, retry\n");
+			ret = -EPROBE_DEFER;
+			goto out_put_node;
+		}
+		pr_warn("failed to get cpu0 regulator: %ld\n",
+			PTR_ERR(cpu_reg));
+		cpu_reg = NULL;
+	}
+
 	cpu_clk = devm_clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
 		ret = PTR_ERR(cpu_clk);
@@ -202,12 +219,6 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		goto out_put_node;
 	}
 
-	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
-	if (IS_ERR(cpu_reg)) {
-		pr_warn("failed to get cpu0 regulator\n");
-		cpu_reg = NULL;
-	}
-
 	ret = of_init_opp_table(cpu_dev);
 	if (ret) {
 		pr_err("failed to init OPP table: %d\n", ret);
@@ -264,6 +275,8 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 	opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_put_node:
 	of_node_put(np);
+out_put_parent:
+	of_node_put(parent);
 	return ret;
 }
 

drivers/cpufreq/cpufreq.c

@@ -1075,14 +1075,14 @@ static int __cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif
 				__func__, cpu_dev->id, cpu);
 	}
 
+	if ((cpus == 1) && (cpufreq_driver->target))
+		__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+
 	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
 	cpufreq_cpu_put(data);
 
 	/* If cpu is last user of policy, free policy */
 	if (cpus == 1) {
-		if (cpufreq_driver->target)
-			__cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
 		lock_policy_rwsem_read(cpu);
 		kobj = &data->kobj;
 		cmp = &data->kobj_unregister;

drivers/cpufreq/cpufreq_governor.c

@@ -255,6 +255,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		if (have_governor_per_policy()) {
 			WARN_ON(dbs_data);
 		} else if (dbs_data) {
+			dbs_data->usage_count++;
 			policy->governor_data = dbs_data;
 			return 0;
 		}
@@ -266,6 +267,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		}
 
 		dbs_data->cdata = cdata;
+		dbs_data->usage_count = 1;
 		rc = cdata->init(dbs_data);
 		if (rc) {
 			pr_err("%s: POLICY_INIT: init() failed\n", __func__);
@@ -294,7 +296,8 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
 					latency * LATENCY_MULTIPLIER));
 
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+		if ((cdata->governor == GOV_CONSERVATIVE) &&
+				(!policy->governor->initialized)) {
 			struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
 
 			cpufreq_register_notifier(cs_ops->notifier_block,
@@ -306,12 +309,12 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 		return 0;
 	case CPUFREQ_GOV_POLICY_EXIT:
-		if ((policy->governor->initialized == 1) ||
-				have_governor_per_policy()) {
+		if (!--dbs_data->usage_count) {
 			sysfs_remove_group(get_governor_parent_kobj(policy),
 					get_sysfs_attr(dbs_data));
 
-			if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+			if ((dbs_data->cdata->governor == GOV_CONSERVATIVE) &&
+				(policy->governor->initialized == 1)) {
 				struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
 
 				cpufreq_unregister_notifier(cs_ops->notifier_block,

drivers/cpufreq/cpufreq_governor.h

@@ -211,6 +211,7 @@ struct common_dbs_data {
 struct dbs_data {
 	struct common_dbs_data *cdata;
 	unsigned int min_sampling_rate;
+	int usage_count;
 	void *tuners;
 
 	/* dbs_mutex protects dbs_enable in governor start/stop */

drivers/cpufreq/cpufreq_ondemand.c

@@ -547,7 +547,6 @@ static int od_init(struct dbs_data *dbs_data)
 	tuners->io_is_busy = should_io_be_busy();
 
 	dbs_data->tuners = tuners;
-	pr_info("%s: tuners %p\n", __func__, tuners);
 	mutex_init(&dbs_data->mutex);
 	return 0;
 }

drivers/cpufreq/intel_pstate.c

@@ -48,12 +48,7 @@ static inline int32_t div_fp(int32_t x, int32_t y)
 }
 
 struct sample {
-	ktime_t start_time;
-	ktime_t end_time;
 	int core_pct_busy;
-	int pstate_pct_busy;
-	u64 duration_us;
-	u64 idletime_us;
 	u64 aperf;
 	u64 mperf;
 	int freq;
@@ -86,13 +81,9 @@ struct cpudata {
 	struct pstate_adjust_policy *pstate_policy;
 	struct pstate_data pstate;
 	struct _pid pid;
-	struct _pid idle_pid;
 
 	int min_pstate_count;
-	int idle_mode;
 
-	ktime_t prev_sample;
-	u64	prev_idle_time_us;
 	u64	prev_aperf;
 	u64	prev_mperf;
 	int	sample_ptr;
@@ -124,6 +115,8 @@ struct perf_limits {
 	int min_perf_pct;
 	int32_t max_perf;
 	int32_t min_perf;
+	int max_policy_pct;
+	int max_sysfs_pct;
 };
 
 static struct perf_limits limits = {
@@ -132,6 +125,8 @@ static struct perf_limits limits = {
 	.max_perf = int_tofp(1),
 	.min_perf_pct = 0,
 	.min_perf = 0,
+	.max_policy_pct = 100,
+	.max_sysfs_pct = 100,
 };
 
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
@@ -202,19 +197,6 @@ static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu)
 		0);
 }
 
-static inline void intel_pstate_idle_pid_reset(struct cpudata *cpu)
-{
-	pid_p_gain_set(&cpu->idle_pid, cpu->pstate_policy->p_gain_pct);
-	pid_d_gain_set(&cpu->idle_pid, cpu->pstate_policy->d_gain_pct);
-	pid_i_gain_set(&cpu->idle_pid, cpu->pstate_policy->i_gain_pct);
-
-	pid_reset(&cpu->idle_pid,
-		75,
-		50,
-		cpu->pstate_policy->deadband,
-		0);
-}
-
 static inline void intel_pstate_reset_all_pid(void)
 {
 	unsigned int cpu;
@@ -302,7 +284,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
-	limits.max_perf_pct = clamp_t(int, input, 0 , 100);
+	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 = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
 	return count;
 }
@@ -408,9 +391,8 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-#ifndef MODULE
 	trace_cpu_frequency(pstate * 100000, cpu->cpu);
-#endif
+
 	cpu->pstate.current_pstate = pstate;
 	wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
 
@@ -450,48 +432,26 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu,
 					struct sample *sample)
 {
 	u64 core_pct;
-	sample->pstate_pct_busy = 100 - div64_u64(
-					sample->idletime_us * 100,
-					sample->duration_us);
 	core_pct = div64_u64(sample->aperf * 100, sample->mperf);
 	sample->freq = cpu->pstate.max_pstate * core_pct * 1000;
 
-	sample->core_pct_busy = div_s64((sample->pstate_pct_busy * core_pct),
-					100);
+	sample->core_pct_busy = core_pct;
 }
 
 static inline void intel_pstate_sample(struct cpudata *cpu)
 {
-	ktime_t now;
-	u64 idle_time_us;
 	u64 aperf, mperf;
 
-	now = ktime_get();
-	idle_time_us = get_cpu_idle_time_us(cpu->cpu, NULL);
-
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
-	/* for the first sample, don't actually record a sample, just
-	 * set the baseline */
-	if (cpu->prev_idle_time_us > 0) {
-		cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
-		cpu->samples[cpu->sample_ptr].start_time = cpu->prev_sample;
-		cpu->samples[cpu->sample_ptr].end_time = now;
-		cpu->samples[cpu->sample_ptr].duration_us =
-			ktime_us_delta(now, cpu->prev_sample);
-		cpu->samples[cpu->sample_ptr].idletime_us =
-			idle_time_us - cpu->prev_idle_time_us;
-
-		cpu->samples[cpu->sample_ptr].aperf = aperf;
-		cpu->samples[cpu->sample_ptr].mperf = mperf;
-		cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
-		cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
-
-		intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
-	}
+	cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
+	cpu->samples[cpu->sample_ptr].aperf = aperf;
+	cpu->samples[cpu->sample_ptr].mperf = mperf;
+	cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
+	cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
+
+	intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
 
-	cpu->prev_sample = now;
-	cpu->prev_idle_time_us = idle_time_us;
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
 }
@@ -505,16 +465,6 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 	mod_timer_pinned(&cpu->timer, jiffies + delay);
 }
 
-static inline void intel_pstate_idle_mode(struct cpudata *cpu)
-{
-	cpu->idle_mode = 1;
-}
-
-static inline void intel_pstate_normal_mode(struct cpudata *cpu)
-{
-	cpu->idle_mode = 0;
-}
-
 static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
 	int32_t busy_scaled;
@@ -547,50 +497,21 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 		intel_pstate_pstate_decrease(cpu, steps);
 }
 
-static inline void intel_pstate_adjust_idle_pstate(struct cpudata *cpu)
-{
-	int busy_scaled;
-	struct _pid *pid;
-	int ctl = 0;
-	int steps;
-
-	pid = &cpu->idle_pid;
-
-	busy_scaled = intel_pstate_get_scaled_busy(cpu);
-
-	ctl = pid_calc(pid, 100 - busy_scaled);
-
-	steps = abs(ctl);
-	if (ctl < 0)
-		intel_pstate_pstate_decrease(cpu, steps);
-	else
-		intel_pstate_pstate_increase(cpu, steps);
-
-	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate)
-		intel_pstate_normal_mode(cpu);
-}
-
 static void intel_pstate_timer_func(unsigned long __data)
 {
 	struct cpudata *cpu = (struct cpudata *) __data;
 
 	intel_pstate_sample(cpu);
+	intel_pstate_adjust_busy_pstate(cpu);
 
-	if (!cpu->idle_mode)
-		intel_pstate_adjust_busy_pstate(cpu);
-	else
-		intel_pstate_adjust_idle_pstate(cpu);
-
-#if defined(XPERF_FIX)
 	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate) {
 		cpu->min_pstate_count++;
 		if (!(cpu->min_pstate_count % 5)) {
 			intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
-			intel_pstate_idle_mode(cpu);
 		}
 	} else
 		cpu->min_pstate_count = 0;
-#endif
+
 	intel_pstate_set_sample_time(cpu);
 }
 
@@ -631,7 +552,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 		(unsigned long)cpu;
 	cpu->timer.expires = jiffies + HZ/100;
 	intel_pstate_busy_pid_reset(cpu);
-	intel_pstate_idle_pid_reset(cpu);
 	intel_pstate_sample(cpu);
 	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
 
@@ -675,8 +595,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	limits.min_perf_pct = clamp_t(int, limits.min_perf_pct, 0 , 100);
 	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
 
-	limits.max_perf_pct = policy->max * 100 / policy->cpuinfo.max_freq;
-	limits.max_perf_pct = clamp_t(int, limits.max_perf_pct, 0 , 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);
+	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
 	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
 
 	return 0;
@@ -788,10 +709,9 @@ static int __init intel_pstate_init(void)
 
 	pr_info("Intel P-state driver initializing.\n");
 
-	all_cpu_data = vmalloc(sizeof(void *) * num_possible_cpus());
+	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
 		return -ENOMEM;
-	memset(all_cpu_data, 0, sizeof(void *) * num_possible_cpus());
 
 	rc = cpufreq_register_driver(&intel_pstate_driver);
 	if (rc)

drivers/cpufreq/kirkwood-cpufreq.c

@@ -171,10 +171,6 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
 	priv.dev = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "Cannot get memory resource\n");
-		return -ENODEV;
-	}
 	priv.base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(priv.base))
 		return PTR_ERR(priv.base);