4 files changed, 183 insertions, 61 deletions

diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 6bbb8b913446..f657c571b18e 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -18,6 +18,7 @@
 #include <linux/cpu.h>
 #include <linux/cpu_cooling.h>
 #include <linux/cpufreq.h>
+#include <linux/cpufreq-dt.h>
 #include <linux/cpumask.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -146,8 +147,8 @@ try_again:
 			goto try_again;
 		}
 
-		dev_warn(cpu_dev, "failed to get cpu%d regulator: %ld\n",
-			 cpu, PTR_ERR(cpu_reg));
+		dev_dbg(cpu_dev, "no regulator for cpu%d: %ld\n",
+			cpu, PTR_ERR(cpu_reg));
 	}
 
 	cpu_clk = clk_get(cpu_dev, NULL);
@@ -165,8 +166,8 @@ try_again:
 		if (ret == -EPROBE_DEFER)
 			dev_dbg(cpu_dev, "cpu%d clock not ready, retry\n", cpu);
 		else
-			dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", ret,
-				cpu);
+			dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", cpu,
+				ret);
 	} else {
 		*cdev = cpu_dev;
 		*creg = cpu_reg;
@@ -178,6 +179,7 @@ try_again:
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
+	struct cpufreq_dt_platform_data *pd;
 	struct cpufreq_frequency_table *freq_table;
 	struct thermal_cooling_device *cdev;
 	struct device_node *np;
@@ -185,6 +187,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct device *cpu_dev;
 	struct regulator *cpu_reg;
 	struct clk *cpu_clk;
+	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
 	int ret;
 
@@ -204,16 +207,10 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	/* OPPs might be populated at runtime, don't check for error here */
 	of_init_opp_table(cpu_dev);
 
-	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_put_node;
-	}
-
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		ret = -ENOMEM;
-		goto out_free_table;
+		goto out_put_node;
 	}
 
 	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
@@ -222,30 +219,51 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		transition_latency = CPUFREQ_ETERNAL;
 
 	if (!IS_ERR(cpu_reg)) {
-		struct dev_pm_opp *opp;
-		unsigned long min_uV, max_uV;
-		int i;
+		unsigned long opp_freq = 0;
 
 		/*
-		 * OPP is maintained in order of increasing frequency, and
-		 * freq_table initialised from OPP is therefore sorted in the
-		 * same order.
+		 * Disable any OPPs where the connected regulator isn't able to
+		 * provide the specified voltage and record minimum and maximum
+		 * voltage levels.
 		 */
-		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
-			;
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_exact(cpu_dev,
-				freq_table[0].frequency * 1000, true);
-		min_uV = dev_pm_opp_get_voltage(opp);
-		opp = dev_pm_opp_find_freq_exact(cpu_dev,
-				freq_table[i-1].frequency * 1000, true);
-		max_uV = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
+		while (1) {
+			struct dev_pm_opp *opp;
+			unsigned long opp_uV, tol_uV;
+
+			rcu_read_lock();
+			opp = dev_pm_opp_find_freq_ceil(cpu_dev, &opp_freq);
+			if (IS_ERR(opp)) {
+				rcu_read_unlock();
+				break;
+			}
+			opp_uV = dev_pm_opp_get_voltage(opp);
+			rcu_read_unlock();
+
+			tol_uV = opp_uV * priv->voltage_tolerance / 100;
+			if (regulator_is_supported_voltage(cpu_reg, opp_uV,
+							   opp_uV + tol_uV)) {
+				if (opp_uV < min_uV)
+					min_uV = opp_uV;
+				if (opp_uV > max_uV)
+					max_uV = opp_uV;
+			} else {
+				dev_pm_opp_disable(cpu_dev, opp_freq);
+			}
+
+			opp_freq++;
+		}
+
 		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
 		if (ret > 0)
 			transition_latency += ret * 1000;
 	}
 
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
+	if (ret) {
+		pr_err("failed to init cpufreq table: %d\n", ret);
+		goto out_free_priv;
+	}
+
 	/*
 	 * For now, just loading the cooling device;
 	 * thermal DT code takes care of matching them.
@@ -265,9 +283,18 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = priv;
 
 	policy->clk = cpu_clk;
-	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
-	if (ret)
+	ret = cpufreq_table_validate_and_show(policy, freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
+			ret);
 		goto out_cooling_unregister;
+	}
+
+	policy->cpuinfo.transition_latency = transition_latency;
+
+	pd = cpufreq_get_driver_data();
+	if (!pd || !pd->independent_clocks)
+		cpumask_setall(policy->cpus);
 
 	of_node_put(np);
 
@@ -275,9 +302,9 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 out_cooling_unregister:
 	cpufreq_cooling_unregister(priv->cdev);
-	kfree(priv);
-out_free_table:
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_free_priv:
+	kfree(priv);
 out_put_node:
 	of_node_put(np);
 out_put_reg_clk:
@@ -335,6 +362,8 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
 	if (!IS_ERR(cpu_reg))
 		regulator_put(cpu_reg);
 
+	dt_cpufreq_driver.driver_data = dev_get_platdata(&pdev->dev);
+
 	ret = cpufreq_register_driver(&dt_cpufreq_driver);
 	if (ret)
 		dev_err(cpu_dev, "failed register driver: %d\n", ret);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 24bf76fba141..4473eba1d6b0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -512,7 +512,18 @@ show_one(cpuinfo_max_freq, cpuinfo.max_freq);
 show_one(cpuinfo_transition_latency, cpuinfo.transition_latency);
 show_one(scaling_min_freq, min);
 show_one(scaling_max_freq, max);
-show_one(scaling_cur_freq, cur);
+
+static ssize_t show_scaling_cur_freq(
+	struct cpufreq_policy *policy, char *buf)
+{
+	ssize_t ret;
+
+	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)
+		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
+	else
+		ret = sprintf(buf, "%u\n", policy->cur);
+	return ret;
+}
 
 static int cpufreq_set_policy(struct cpufreq_policy *policy,
 				struct cpufreq_policy *new_policy);
@@ -906,11 +917,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 		if (ret)
 			goto err_out_kobj_put;
 	}
-	if (has_target()) {
-		ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
-		if (ret)
-			goto err_out_kobj_put;
-	}
+
+	ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
+	if (ret)
+		goto err_out_kobj_put;
+
 	if (cpufreq_driver->bios_limit) {
 		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
 		if (ret)
@@ -1011,7 +1022,8 @@ static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
 
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	policy->governor = NULL;
+	if (policy)
+		policy->governor = NULL;
 
 	return policy;
 }
@@ -1731,6 +1743,21 @@ const char *cpufreq_get_current_driver(void)
 }
 EXPORT_SYMBOL_GPL(cpufreq_get_current_driver);
 
+/**
+ *	cpufreq_get_driver_data - return current driver data
+ *
+ *	Return the private data of the currently loaded cpufreq
+ *	driver, or NULL if no cpufreq driver is loaded.
+ */
+void *cpufreq_get_driver_data(void)
+{
+	if (cpufreq_driver)
+		return cpufreq_driver->driver_data;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_get_driver_data);
+
 /*********************************************************************
  *                     NOTIFIER LISTS INTERFACE                      *
  *********************************************************************/
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index ec399ad2f059..1608f7105c9f 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -19,7 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
 #include <linux/platform_device.h>
 
 #define HB_CPUFREQ_CHANGE_NOTE	0x80000001
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 0668b389c516..27bb6d3877ed 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -52,6 +52,17 @@ static inline int32_t div_fp(int32_t x, int32_t y)
 	return div_s64((int64_t)x << FRAC_BITS, y);
 }
 
+static inline int ceiling_fp(int32_t x)
+{
+	int mask, ret;
+
+	ret = fp_toint(x);
+	mask = (1 << FRAC_BITS) - 1;
+	if (x & mask)
+		ret += 1;
+	return ret;
+}
+
 struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
@@ -64,6 +75,7 @@ struct pstate_data {
 	int	current_pstate;
 	int	min_pstate;
 	int	max_pstate;
+	int	scaling;
 	int	turbo_pstate;
 };
 
@@ -113,6 +125,7 @@ struct pstate_funcs {
 	int (*get_max)(void);
 	int (*get_min)(void);
 	int (*get_turbo)(void);
+	int (*get_scaling)(void);
 	void (*set)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
 };
@@ -138,6 +151,7 @@ struct perf_limits {
 
 static struct perf_limits limits = {
 	.no_turbo = 0,
+	.turbo_disabled = 0,
 	.max_perf_pct = 100,
 	.max_perf = int_tofp(1),
 	.min_perf_pct = 0,
@@ -218,6 +232,18 @@ static inline void intel_pstate_reset_all_pid(void)
 	}
 }
 
+static inline void update_turbo_state(void)
+{
+	u64 misc_en;
+	struct cpudata *cpu;
+
+	cpu = all_cpu_data[0];
+	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
+	limits.turbo_disabled =
+		(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
+		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
+}
+
 /************************** debugfs begin ************************/
 static int pid_param_set(void *data, u64 val)
 {
@@ -274,6 +300,20 @@ static void __init intel_pstate_debug_expose_params(void)
 		return sprintf(buf, "%u\n", limits.object);		\
 	}
 
+static ssize_t show_no_turbo(struct kobject *kobj,
+			     struct attribute *attr, char *buf)
+{
+	ssize_t ret;
+
+	update_turbo_state();
+	if (limits.turbo_disabled)
+		ret = sprintf(buf, "%u\n", limits.turbo_disabled);
+	else
+		ret = sprintf(buf, "%u\n", limits.no_turbo);
+
+	return ret;
+}
+
 static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 			      const char *buf, size_t count)
 {
@@ -283,11 +323,14 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
-	limits.no_turbo = clamp_t(int, input, 0 , 1);
+
+	update_turbo_state();
 	if (limits.turbo_disabled) {
 		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
-		limits.no_turbo = limits.turbo_disabled;
+		return -EPERM;
 	}
+	limits.no_turbo = clamp_t(int, input, 0, 1);
+
 	return count;
 }
 
@@ -323,7 +366,6 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 	return count;
 }
 
-show_one(no_turbo, no_turbo);
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
 
@@ -394,7 +436,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 		cpudata->vid.ratio);
 
 	vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max);
-	vid = fp_toint(vid_fp);
+	vid = ceiling_fp(vid_fp);
 
 	if (pstate > cpudata->pstate.max_pstate)
 		vid = cpudata->vid.turbo;
@@ -404,6 +446,22 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
+#define BYT_BCLK_FREQS 5
+static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
+
+static int byt_get_scaling(void)
+{
+	u64 value;
+	int i;
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0x3;
+
+	BUG_ON(i > BYT_BCLK_FREQS);
+
+	return byt_freq_table[i] * 100;
+}
+
 static void byt_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
@@ -449,6 +507,11 @@ static int core_get_turbo_pstate(void)
 	return ret;
 }
 
+static inline int core_get_scaling(void)
+{
+	return 100000;
+}
+
 static void core_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
@@ -473,6 +536,7 @@ static struct cpu_defaults core_params = {
 		.get_max = core_get_max_pstate,
 		.get_min = core_get_min_pstate,
 		.get_turbo = core_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
 	},
 };
@@ -491,6 +555,7 @@ static struct cpu_defaults byt_params = {
 		.get_min = byt_get_min_pstate,
 		.get_turbo = byt_get_turbo_pstate,
 		.set = byt_set_pstate,
+		.get_scaling = byt_get_scaling,
 		.get_vid = byt_get_vid,
 	},
 };
@@ -501,7 +566,7 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	int max_perf_adj;
 	int min_perf;
 
-	if (limits.no_turbo)
+	if (limits.no_turbo || limits.turbo_disabled)
 		max_perf = cpu->pstate.max_pstate;
 
 	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
@@ -516,6 +581,8 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	int max_perf, min_perf;
 
+	update_turbo_state();
+
 	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 
 	pstate = clamp_t(int, pstate, min_perf, max_perf);
@@ -523,7 +590,7 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 	if (pstate == cpu->pstate.current_pstate)
 		return;
 
-	trace_cpu_frequency(pstate * 100000, cpu->cpu);
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
 
@@ -535,6 +602,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
 	cpu->pstate.max_pstate = pstate_funcs.get_max();
 	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
+	cpu->pstate.scaling = pstate_funcs.get_scaling();
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
@@ -550,7 +618,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));
 
 	sample->freq = fp_toint(
-		mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
+		mul_fp(int_tofp(
+			cpu->pstate.max_pstate * cpu->pstate.scaling / 100),
+			core_pct));
 
 	sample->core_pct_busy = (int32_t)core_pct;
 }
@@ -671,7 +741,9 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
 
-	all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
+	if (!all_cpu_data[cpunum])
+		all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata),
+					       GFP_KERNEL);
 	if (!all_cpu_data[cpunum])
 		return -ENOMEM;
 
@@ -714,9 +786,10 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits.min_perf_pct = 100;
 		limits.min_perf = int_tofp(1);
+		limits.max_policy_pct = 100;
 		limits.max_perf_pct = 100;
 		limits.max_perf = int_tofp(1);
-		limits.no_turbo = limits.turbo_disabled;
+		limits.no_turbo = 0;
 		return 0;
 	}
 	limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
@@ -751,15 +824,12 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 
 	del_timer_sync(&all_cpu_data[cpu_num]->timer);
 	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
-	kfree(all_cpu_data[cpu_num]);
-	all_cpu_data[cpu_num] = NULL;
 }
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
 	int rc;
-	u64 misc_en;
 
 	rc = intel_pstate_init_cpu(policy->cpu);
 	if (rc)
@@ -767,23 +837,18 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
-	if (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
-	    cpu->pstate.max_pstate == cpu->pstate.turbo_pstate) {
-		limits.turbo_disabled = 1;
-		limits.no_turbo = 1;
-	}
 	if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	policy->min = cpu->pstate.min_pstate * 100000;
-	policy->max = cpu->pstate.turbo_pstate * 100000;
+	policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
-	policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000;
+	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->cpuinfo.max_freq =
+		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
@@ -841,6 +906,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 	pstate_funcs.get_max   = funcs->get_max;
 	pstate_funcs.get_min   = funcs->get_min;
 	pstate_funcs.get_turbo = funcs->get_turbo;
+	pstate_funcs.get_scaling = funcs->get_scaling;
 	pstate_funcs.set       = funcs->set;
 	pstate_funcs.get_vid   = funcs->get_vid;
 }