Merge branches 'pm-cpuidle' and 'pm-cpufreq'

* pm-cpuidle:
  cpuidle: powernv: Populate cpuidle state details by querying the device-tree

* pm-cpufreq:
  intel_pstate: Correct BYT VID values.
  intel_pstate: Fix BYT frequency reporting
  intel_pstate: Don't lose sysfs settings during cpu offline
  cpufreq: intel_pstate: Reflect current no_turbo state correctly
  cpufreq: expose scaling_cur_freq sysfs file for set_policy() drivers
  cpufreq: intel_pstate: Fix setting max_perf_pct in performance policy
  cpufreq: cpufreq-dt: adjust message related to regulators
  cpufreq: cpufreq-dt: extend with platform_data
  cpufreq: allow driver-specific data

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",
+		dev_dbg(cpu_dev, "no regulator for cpu%d: %ld\n",
-			 cpu, PTR_ERR(cpu_reg));
+			cpu, PTR_ERR(cpu_reg));
 	}
 
 	cpu_clk = clk_get(cpu_dev, NULL);
@@ -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;
@@ -265,9 +267,18 @@ 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);
+	ret = cpufreq_table_validate_and_show(policy, freq_table);
-	if (ret)
+	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);
 
@@ -335,6 +346,8 @@ 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);

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);
+	ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
-		if (ret)
+	if (ret)
-			goto err_out_kobj_put;
+		goto err_out_kobj_put;
-	}
+
 	if (cpufreq_driver->bios_limit) {
 		ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
 		if (ret)
@@ -1731,6 +1742,21 @@ 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                      *
  *********************************************************************/

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->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
-	policy->max = cpu->pstate.turbo_pstate * 100000;
+	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.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
-	policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000;
+	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;
 }

drivers/cpuidle/cpuidle-powernv.c

@@ -163,7 +163,8 @@ static int powernv_add_idle_states(void)
 	int nr_idle_states = 1; /* Snooze */
 	int dt_idle_states;
 	const __be32 *idle_state_flags;
-	u32 len_flags, flags;
+	const __be32 *idle_state_latency;
+	u32 len_flags, flags, latency_ns;
 	int i;
 
 	/* Currently we have snooze statically defined */
@@ -180,18 +181,32 @@ static int powernv_add_idle_states(void)
 		return nr_idle_states;
 	}
 
+	idle_state_latency = of_get_property(power_mgt,
+			"ibm,cpu-idle-state-latencies-ns", NULL);
+	if (!idle_state_latency) {
+		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-latencies-ns\n");
+		return nr_idle_states;
+	}
+
 	dt_idle_states = len_flags / sizeof(u32);
 
 	for (i = 0; i < dt_idle_states; i++) {
 
 		flags = be32_to_cpu(idle_state_flags[i]);
+
+		/* Cpuidle accepts exit_latency in us and we estimate
+		 * target residency to be 10x exit_latency
+		 */
+		latency_ns = be32_to_cpu(idle_state_latency[i]);
 		if (flags & IDLE_USE_INST_NAP) {
 			/* Add NAP state */
 			strcpy(powernv_states[nr_idle_states].name, "Nap");
 			strcpy(powernv_states[nr_idle_states].desc, "Nap");
 			powernv_states[nr_idle_states].flags = CPUIDLE_FLAG_TIME_VALID;
-			powernv_states[nr_idle_states].exit_latency = 10;
+			powernv_states[nr_idle_states].exit_latency =
-			powernv_states[nr_idle_states].target_residency = 100;
+					((unsigned int)latency_ns) / 1000;
+			powernv_states[nr_idle_states].target_residency =
+					((unsigned int)latency_ns / 100);
 			powernv_states[nr_idle_states].enter = &nap_loop;
 			nr_idle_states++;
 		}
@@ -202,8 +217,10 @@ static int powernv_add_idle_states(void)
 			strcpy(powernv_states[nr_idle_states].desc, "FastSleep");
 			powernv_states[nr_idle_states].flags =
 				CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TIMER_STOP;
-			powernv_states[nr_idle_states].exit_latency = 300;
+			powernv_states[nr_idle_states].exit_latency =
-			powernv_states[nr_idle_states].target_residency = 1000000;
+					((unsigned int)latency_ns) / 1000;
+			powernv_states[nr_idle_states].target_residency =
+					((unsigned int)latency_ns / 100);
 			powernv_states[nr_idle_states].enter = &fastsleep_loop;
 			nr_idle_states++;
 		}

include/linux/cpufreq-dt.h

@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2014 Marvell
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CPUFREQ_DT_H__
+#define __CPUFREQ_DT_H__
+
+struct cpufreq_dt_platform_data {
+	/*
+	 * True when each CPU has its own clock to control its
+	 * frequency, false when all CPUs are controlled by a single
+	 * clock.
+	 */
+	bool independent_clocks;
+};
+
+#endif /* __CPUFREQ_DT_H__ */

include/linux/cpufreq.h

@@ -219,6 +219,7 @@ __ATTR(_name, 0644, show_##_name, store_##_name)
 struct cpufreq_driver {
 	char			name[CPUFREQ_NAME_LEN];
 	u8			flags;
+	void			*driver_data;
 
 	/* needed by all drivers */
 	int	(*init)		(struct cpufreq_policy *policy);
@@ -312,6 +313,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data);
 int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
 
 const char *cpufreq_get_current_driver(void);
+void *cpufreq_get_driver_data(void);
 
 static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
 		unsigned int min, unsigned int max)