Merge branch 'pm-cpufreq'

* pm-cpufreq: (94 commits)
  intel_pstate: Do not skip samples partially
  intel_pstate: Remove freq calculation from intel_pstate_calc_busy()
  intel_pstate: Move intel_pstate_calc_busy() into get_target_pstate_use_performance()
  intel_pstate: Optimize calculation for max/min_perf_adj
  intel_pstate: Remove extra conversions in pid calculation
  cpufreq: Move scheduler-related code to the sched directory
  Revert "cpufreq: postfix policy directory with the first CPU in related_cpus"
  cpufreq: Reduce cpufreq_update_util() overhead a bit
  cpufreq: Select IRQ_WORK if CPU_FREQ_GOV_COMMON is set
  cpufreq: Remove 'policy->governor_enabled'
  cpufreq: Rename __cpufreq_governor() to cpufreq_governor()
  cpufreq: Relocate handle_update() to kill its declaration
  cpufreq: governor: Drop unnecessary checks from show() and store()
  cpufreq: governor: Fix race in dbs_update_util_handler()
  cpufreq: governor: Make gov_set_update_util() static
  cpufreq: governor: Narrow down the dbs_data_mutex coverage
  cpufreq: governor: Make dbs_data_mutex static
  cpufreq: governor: Relocate definitions of tuners structures
  cpufreq: governor: Move per-CPU data to the common code
  cpufreq: governor: Make governor private data per-policy
  ...

15 files changed, 1344 insertions, 1676 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index f93511031177..a7f45853c103 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -19,6 +19,7 @@ config CPU_FREQ
 if CPU_FREQ
 
 config CPU_FREQ_GOV_COMMON
+	select IRQ_WORK
 	bool
 
 config CPU_FREQ_BOOST_SW
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 51eef87bbc37..59a7b380fbe2 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -70,6 +70,8 @@ struct acpi_cpufreq_data {
 	unsigned int cpu_feature;
 	unsigned int acpi_perf_cpu;
 	cpumask_var_t freqdomain_cpus;
+	void (*cpu_freq_write)(struct acpi_pct_register *reg, u32 val);
+	u32 (*cpu_freq_read)(struct acpi_pct_register *reg);
 };
 
 /* acpi_perf_data is a pointer to percpu data. */
@@ -243,125 +245,119 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
 	}
 }
 
-struct msr_addr {
-	u32 reg;
-};
+u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
+{
+	u32 val, dummy;
 
-struct io_addr {
-	u16 port;
-	u8 bit_width;
-};
+	rdmsr(MSR_IA32_PERF_CTL, val, dummy);
+	return val;
+}
+
+void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
+{
+	u32 lo, hi;
+
+	rdmsr(MSR_IA32_PERF_CTL, lo, hi);
+	lo = (lo & ~INTEL_MSR_RANGE) | (val & INTEL_MSR_RANGE);
+	wrmsr(MSR_IA32_PERF_CTL, lo, hi);
+}
+
+u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
+{
+	u32 val, dummy;
+
+	rdmsr(MSR_AMD_PERF_CTL, val, dummy);
+	return val;
+}
+
+void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)
+{
+	wrmsr(MSR_AMD_PERF_CTL, val, 0);
+}
+
+u32 cpu_freq_read_io(struct acpi_pct_register *reg)
+{
+	u32 val;
+
+	acpi_os_read_port(reg->address, &val, reg->bit_width);
+	return val;
+}
+
+void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)
+{
+	acpi_os_write_port(reg->address, val, reg->bit_width);
+}
 
 struct drv_cmd {
-	unsigned int type;
-	const struct cpumask *mask;
-	union {
-		struct msr_addr msr;
-		struct io_addr io;
-	} addr;
+	struct acpi_pct_register *reg;
 	u32 val;
+	union {
+		void (*write)(struct acpi_pct_register *reg, u32 val);
+		u32 (*read)(struct acpi_pct_register *reg);
+	} func;
 };
 
 /* Called via smp_call_function_single(), on the target CPU */
 static void do_drv_read(void *_cmd)
 {
 	struct drv_cmd *cmd = _cmd;
-	u32 h;
 
-	switch (cmd->type) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-	case SYSTEM_AMD_MSR_CAPABLE:
-		rdmsr(cmd->addr.msr.reg, cmd->val, h);
-		break;
-	case SYSTEM_IO_CAPABLE:
-		acpi_os_read_port((acpi_io_address)cmd->addr.io.port,
-				&cmd->val,
-				(u32)cmd->addr.io.bit_width);
-		break;
-	default:
-		break;
-	}
+	cmd->val = cmd->func.read(cmd->reg);
 }
 
-/* Called via smp_call_function_many(), on the target CPUs */
-static void do_drv_write(void *_cmd)
+static u32 drv_read(struct acpi_cpufreq_data *data, const struct cpumask *mask)
 {
-	struct drv_cmd *cmd = _cmd;
-	u32 lo, hi;
+	struct acpi_processor_performance *perf = to_perf_data(data);
+	struct drv_cmd cmd = {
+		.reg = &perf->control_register,
+		.func.read = data->cpu_freq_read,
+	};
+	int err;
 
-	switch (cmd->type) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-		rdmsr(cmd->addr.msr.reg, lo, hi);
-		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
-		wrmsr(cmd->addr.msr.reg, lo, hi);
-		break;
-	case SYSTEM_AMD_MSR_CAPABLE:
-		wrmsr(cmd->addr.msr.reg, cmd->val, 0);
-		break;
-	case SYSTEM_IO_CAPABLE:
-		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
-				cmd->val,
-				(u32)cmd->addr.io.bit_width);
-		break;
-	default:
-		break;
-	}
+	err = smp_call_function_any(mask, do_drv_read, &cmd, 1);
+	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
+	return cmd.val;
 }
 
-static void drv_read(struct drv_cmd *cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
 {
-	int err;
-	cmd->val = 0;
+	struct drv_cmd *cmd = _cmd;
 
-	err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
-	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
+	cmd->func.write(cmd->reg, cmd->val);
 }
 
-static void drv_write(struct drv_cmd *cmd)
+static void drv_write(struct acpi_cpufreq_data *data,
+		      const struct cpumask *mask, u32 val)
 {
+	struct acpi_processor_performance *perf = to_perf_data(data);
+	struct drv_cmd cmd = {
+		.reg = &perf->control_register,
+		.val = val,
+		.func.write = data->cpu_freq_write,
+	};
 	int this_cpu;
 
 	this_cpu = get_cpu();
-	if (cpumask_test_cpu(this_cpu, cmd->mask))
-		do_drv_write(cmd);
-	smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+	if (cpumask_test_cpu(this_cpu, mask))
+		do_drv_write(&cmd);
+
+	smp_call_function_many(mask, do_drv_write, &cmd, 1);
 	put_cpu();
 }
 
-static u32
-get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
+static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
 {
-	struct acpi_processor_performance *perf;
-	struct drv_cmd cmd;
+	u32 val;
 
 	if (unlikely(cpumask_empty(mask)))
 		return 0;
 
-	switch (data->cpu_feature) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
-		break;
-	case SYSTEM_AMD_MSR_CAPABLE:
-		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
-		break;
-	case SYSTEM_IO_CAPABLE:
-		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = to_perf_data(data);
-		cmd.addr.io.port = perf->control_register.address;
-		cmd.addr.io.bit_width = perf->control_register.bit_width;
-		break;
-	default:
-		return 0;
-	}
-
-	cmd.mask = mask;
-	drv_read(&cmd);
+	val = drv_read(data, mask);
 
-	pr_debug("get_cur_val = %u\n", cmd.val);
+	pr_debug("get_cur_val = %u\n", val);
 
-	return cmd.val;
+	return val;
 }
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
@@ -416,7 +412,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
-	struct drv_cmd cmd;
+	const struct cpumask *mask;
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	int result = 0;
 
@@ -434,42 +430,21 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		} else {
 			pr_debug("Already at target state (P%d)\n",
 				next_perf_state);
-			goto out;
+			return 0;
 		}
 	}
 
-	switch (data->cpu_feature) {
-	case SYSTEM_INTEL_MSR_CAPABLE:
-		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
-		cmd.val = (u32) perf->states[next_perf_state].control;
-		break;
-	case SYSTEM_AMD_MSR_CAPABLE:
-		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
-		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
-		cmd.val = (u32) perf->states[next_perf_state].control;
-		break;
-	case SYSTEM_IO_CAPABLE:
-		cmd.type = SYSTEM_IO_CAPABLE;
-		cmd.addr.io.port = perf->control_register.address;
-		cmd.addr.io.bit_width = perf->control_register.bit_width;
-		cmd.val = (u32) perf->states[next_perf_state].control;
-		break;
-	default:
-		result = -ENODEV;
-		goto out;
-	}
-
-	/* cpufreq holds the hotplug lock, so we are safe from here on */
-	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
-		cmd.mask = policy->cpus;
-	else
-		cmd.mask = cpumask_of(policy->cpu);
+	/*
+	 * The core won't allow CPUs to go away until the governor has been
+	 * stopped, so we can rely on the stability of policy->cpus.
+	 */
+	mask = policy->shared_type == CPUFREQ_SHARED_TYPE_ANY ?
+		cpumask_of(policy->cpu) : policy->cpus;
 
-	drv_write(&cmd);
+	drv_write(data, mask, perf->states[next_perf_state].control);
 
 	if (acpi_pstate_strict) {
-		if (!check_freqs(cmd.mask, data->freq_table[index].frequency,
+		if (!check_freqs(mask, data->freq_table[index].frequency,
 					data)) {
 			pr_debug("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
@@ -480,7 +455,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	if (!result)
 		perf->state = next_perf_state;
 
-out:
 	return result;
 }
 
@@ -740,15 +714,21 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		}
 		pr_debug("SYSTEM IO addr space\n");
 		data->cpu_feature = SYSTEM_IO_CAPABLE;
+		data->cpu_freq_read = cpu_freq_read_io;
+		data->cpu_freq_write = cpu_freq_write_io;
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
 		pr_debug("HARDWARE addr space\n");
 		if (check_est_cpu(cpu)) {
 			data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
+			data->cpu_freq_read = cpu_freq_read_intel;
+			data->cpu_freq_write = cpu_freq_write_intel;
 			break;
 		}
 		if (check_amd_hwpstate_cpu(cpu)) {
 			data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE;
+			data->cpu_freq_read = cpu_freq_read_amd;
+			data->cpu_freq_write = cpu_freq_write_amd;
 			break;
 		}
 		result = -ENODEV;
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index f6b79ab0070b..404360cad25c 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -21,7 +21,7 @@
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
 
-#include "cpufreq_governor.h"
+#include "cpufreq_ondemand.h"
 
 #define MSR_AMD64_FREQ_SENSITIVITY_ACTUAL	0xc0010080
 #define MSR_AMD64_FREQ_SENSITIVITY_REFERENCE	0xc0010081
@@ -45,10 +45,10 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 	long d_actual, d_reference;
 	struct msr actual, reference;
 	struct cpu_data_t *data = &per_cpu(cpu_data, policy->cpu);
-	struct dbs_data *od_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct dbs_data *od_data = policy_dbs->dbs_data;
 	struct od_dbs_tuners *od_tuners = od_data->tuners;
-	struct od_cpu_dbs_info_s *od_info =
-		od_data->cdata->get_cpu_dbs_info_s(policy->cpu);
+	struct od_policy_dbs_info *od_info = to_dbs_info(policy_dbs);
 
 	if (!od_info->freq_table)
 		return freq_next;
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 0ca74d070058..f951f911786e 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -31,9 +31,8 @@
 
 struct private_data {
 	struct device *cpu_dev;
-	struct regulator *cpu_reg;
 	struct thermal_cooling_device *cdev;
-	unsigned int voltage_tolerance; /* in percentage */
+	const char *reg_name;
 };
 
 static struct freq_attr *cpufreq_dt_attr[] = {
@@ -44,175 +43,128 @@ static struct freq_attr *cpufreq_dt_attr[] = {
 
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	struct dev_pm_opp *opp;
-	struct cpufreq_frequency_table *freq_table = policy->freq_table;
-	struct clk *cpu_clk = policy->clk;
 	struct private_data *priv = policy->driver_data;
-	struct device *cpu_dev = priv->cpu_dev;
-	struct regulator *cpu_reg = priv->cpu_reg;
-	unsigned long volt = 0, tol = 0;
-	int volt_old = 0;
-	unsigned int old_freq, new_freq;
-	long freq_Hz, freq_exact;
-	int ret;
-
-	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
-	if (freq_Hz <= 0)
-		freq_Hz = freq_table[index].frequency * 1000;
 
-	freq_exact = freq_Hz;
-	new_freq = freq_Hz / 1000;
-	old_freq = clk_get_rate(cpu_clk) / 1000;
+	return dev_pm_opp_set_rate(priv->cpu_dev,
+				   policy->freq_table[index].frequency * 1000);
+}
 
-	if (!IS_ERR(cpu_reg)) {
-		unsigned long opp_freq;
+/*
+ * An earlier version of opp-v1 bindings used to name the regulator
+ * "cpu0-supply", we still need to handle that for backwards compatibility.
+ */
+static const char *find_supply_name(struct device *dev)
+{
+	struct device_node *np;
+	struct property *pp;
+	int cpu = dev->id;
+	const char *name = NULL;
 
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz);
-		if (IS_ERR(opp)) {
-			rcu_read_unlock();
-			dev_err(cpu_dev, "failed to find OPP for %ld\n",
-				freq_Hz);
-			return PTR_ERR(opp);
-		}
-		volt = dev_pm_opp_get_voltage(opp);
-		opp_freq = dev_pm_opp_get_freq(opp);
-		rcu_read_unlock();
-		tol = volt * priv->voltage_tolerance / 100;
-		volt_old = regulator_get_voltage(cpu_reg);
-		dev_dbg(cpu_dev, "Found OPP: %ld kHz, %ld uV\n",
-			opp_freq / 1000, volt);
-	}
+	np = of_node_get(dev->of_node);
 
-	dev_dbg(cpu_dev, "%u MHz, %d mV --> %u MHz, %ld mV\n",
-		old_freq / 1000, (volt_old > 0) ? volt_old / 1000 : -1,
-		new_freq / 1000, volt ? volt / 1000 : -1);
+	/* This must be valid for sure */
+	if (WARN_ON(!np))
+		return NULL;
 
-	/* scaling up?  scale voltage before frequency */
-	if (!IS_ERR(cpu_reg) && new_freq > old_freq) {
-		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
-		if (ret) {
-			dev_err(cpu_dev, "failed to scale voltage up: %d\n",
-				ret);
-			return ret;
+	/* Try "cpu0" for older DTs */
+	if (!cpu) {
+		pp = of_find_property(np, "cpu0-supply", NULL);
+		if (pp) {
+			name = "cpu0";
+			goto node_put;
 		}
 	}
 
-	ret = clk_set_rate(cpu_clk, freq_exact);
-	if (ret) {
-		dev_err(cpu_dev, "failed to set clock rate: %d\n", ret);
-		if (!IS_ERR(cpu_reg) && volt_old > 0)
-			regulator_set_voltage_tol(cpu_reg, volt_old, tol);
-		return ret;
+	pp = of_find_property(np, "cpu-supply", NULL);
+	if (pp) {
+		name = "cpu";
+		goto node_put;
 	}
 
-	/* scaling down?  scale voltage after frequency */
-	if (!IS_ERR(cpu_reg) && new_freq < old_freq) {
-		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
-		if (ret) {
-			dev_err(cpu_dev, "failed to scale voltage down: %d\n",
-				ret);
-			clk_set_rate(cpu_clk, old_freq * 1000);
-		}
-	}
-
-	return ret;
+	dev_dbg(dev, "no regulator for cpu%d\n", cpu);
+node_put:
+	of_node_put(np);
+	return name;
 }
 
-static int allocate_resources(int cpu, struct device **cdev,
-			      struct regulator **creg, struct clk **cclk)
+static int resources_available(void)
 {
 	struct device *cpu_dev;
 	struct regulator *cpu_reg;
 	struct clk *cpu_clk;
 	int ret = 0;
-	char *reg_cpu0 = "cpu0", *reg_cpu = "cpu", *reg;
+	const char *name;
 
-	cpu_dev = get_cpu_device(cpu);
+	cpu_dev = get_cpu_device(0);
 	if (!cpu_dev) {
-		pr_err("failed to get cpu%d device\n", cpu);
+		pr_err("failed to get cpu0 device\n");
 		return -ENODEV;
 	}
 
-	/* Try "cpu0" for older DTs */
-	if (!cpu)
-		reg = reg_cpu0;
-	else
-		reg = reg_cpu;
-
-try_again:
-	cpu_reg = regulator_get_optional(cpu_dev, reg);
-	ret = PTR_ERR_OR_ZERO(cpu_reg);
+	cpu_clk = clk_get(cpu_dev, NULL);
+	ret = PTR_ERR_OR_ZERO(cpu_clk);
 	if (ret) {
 		/*
-		 * If cpu's regulator supply node is present, but regulator is
-		 * not yet registered, we should try defering probe.
+		 * 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, "cpu%d regulator not ready, retry\n",
-				cpu);
-			return ret;
-		}
-
-		/* Try with "cpu-supply" */
-		if (reg == reg_cpu0) {
-			reg = reg_cpu;
-			goto try_again;
-		}
+		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);
 
-		dev_dbg(cpu_dev, "no regulator for cpu%d: %d\n", cpu, ret);
+		return ret;
 	}
 
-	cpu_clk = clk_get(cpu_dev, NULL);
-	ret = PTR_ERR_OR_ZERO(cpu_clk);
-	if (ret) {
-		/* put regulator */
-		if (!IS_ERR(cpu_reg))
-			regulator_put(cpu_reg);
+	clk_put(cpu_clk);
 
+	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 clk node is present, but clock is not yet
-		 * registered, we should try defering probe.
+		 * 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, "cpu%d clock not ready, retry\n", cpu);
+			dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n");
 		else
-			dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", cpu,
-				ret);
-	} else {
-		*cdev = cpu_dev;
-		*creg = cpu_reg;
-		*cclk = cpu_clk;
+			dev_dbg(cpu_dev, "no regulator for cpu0: %d\n", ret);
+
+		return ret;
 	}
 
-	return ret;
+	regulator_put(cpu_reg);
+	return 0;
 }
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct cpufreq_frequency_table *freq_table;
-	struct device_node *np;
 	struct private_data *priv;
 	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;
+	bool opp_v1 = false;
+	const char *name;
 	int ret;
 
-	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
-	if (ret) {
-		pr_err("%s: Failed to allocate resources: %d\n", __func__, ret);
-		return ret;
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", policy->cpu);
+		return -ENODEV;
 	}
 
-	np = of_node_get(cpu_dev->of_node);
-	if (!np) {
-		dev_err(cpu_dev, "failed to find cpu%d node\n", policy->cpu);
-		ret = -ENOENT;
-		goto out_put_reg_clk;
+	cpu_clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(cpu_clk)) {
+		ret = PTR_ERR(cpu_clk);
+		dev_err(cpu_dev, "%s: failed to get clk: %d\n", __func__, ret);
+		return ret;
 	}
 
 	/* Get OPP-sharing information from "operating-points-v2" bindings */
@@ -223,9 +175,23 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		 * finding shared-OPPs for backward compatibility.
 		 */
 		if (ret == -ENOENT)
-			need_update = true;
+			opp_v1 = true;
 		else
-			goto out_node_put;
+			goto out_put_clk;
+	}
+
+	/*
+	 * 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) {
+		ret = dev_pm_opp_set_regulator(cpu_dev, name);
+		if (ret) {
+			dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n",
+				policy->cpu, ret);
+			goto out_put_clk;
+		}
 	}
 
 	/*
@@ -246,12 +212,12 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	ret = dev_pm_opp_get_opp_count(cpu_dev);
 	if (ret <= 0) {
-		pr_debug("OPP table is not ready, deferring probe\n");
+		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
 		ret = -EPROBE_DEFER;
 		goto out_free_opp;
 	}
 
-	if (need_update) {
+	if (opp_v1) {
 		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
 
 		if (!pd || !pd->independent_clocks)
@@ -265,10 +231,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		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);
 	}
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
@@ -277,62 +239,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_opp;
 	}
 
-	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
-
-	if (!transition_latency)
-		transition_latency = CPUFREQ_ETERNAL;
-
-	if (!IS_ERR(cpu_reg)) {
-		unsigned long opp_freq = 0;
-
-		/*
-		 * Disable any OPPs where the connected regulator isn't able to
-		 * provide the specified voltage and record minimum and maximum
-		 * voltage levels.
-		 */
-		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 - tol_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;
-	}
+	priv->reg_name = name;
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
-		pr_err("failed to init cpufreq table: %d\n", ret);
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
 		goto out_free_priv;
 	}
 
 	priv->cpu_dev = cpu_dev;
-	priv->cpu_reg = cpu_reg;
 	policy->driver_data = priv;
-
 	policy->clk = cpu_clk;
 
 	rcu_read_lock();
@@ -357,9 +273,11 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
 	}
 
-	policy->cpuinfo.transition_latency = transition_latency;
+	transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev);
+	if (!transition_latency)
+		transition_latency = CPUFREQ_ETERNAL;
 
-	of_node_put(np);
+	policy->cpuinfo.transition_latency = transition_latency;
 
 	return 0;
 
@@ -369,12 +287,10 @@ out_free_priv:
 	kfree(priv);
 out_free_opp:
 	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
-out_node_put:
-	of_node_put(np);
-out_put_reg_clk:
+	if (name)
+		dev_pm_opp_put_regulator(cpu_dev);
+out_put_clk:
 	clk_put(cpu_clk);
-	if (!IS_ERR(cpu_reg))
-		regulator_put(cpu_reg);
 
 	return ret;
 }
@@ -386,9 +302,10 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
+	if (priv->reg_name)
+		dev_pm_opp_put_regulator(priv->cpu_dev);
+
 	clk_put(policy->clk);
-	if (!IS_ERR(priv->cpu_reg))
-		regulator_put(priv->cpu_reg);
 	kfree(priv);
 
 	return 0;
@@ -441,9 +358,6 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 
 static int dt_cpufreq_probe(struct platform_device *pdev)
 {
-	struct device *cpu_dev;
-	struct regulator *cpu_reg;
-	struct clk *cpu_clk;
 	int ret;
 
 	/*
@@ -453,19 +367,15 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
 	 *
 	 * FIXME: Is checking this only for CPU0 sufficient ?
 	 */
-	ret = allocate_resources(0, &cpu_dev, &cpu_reg, &cpu_clk);
+	ret = resources_available();
 	if (ret)
 		return ret;
 
-	clk_put(cpu_clk);
-	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);
+		dev_err(&pdev->dev, "failed register driver: %d\n", ret);
 
 	return ret;
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e979ec78b695..4c7825856eab 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -38,48 +38,10 @@ static inline bool policy_is_inactive(struct cpufreq_policy *policy)
 	return cpumask_empty(policy->cpus);
 }
 
-static bool suitable_policy(struct cpufreq_policy *policy, bool active)
-{
-	return active == !policy_is_inactive(policy);
-}
-
-/* Finds Next Acive/Inactive policy */
-static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
-					  bool active)
-{
-	do {
-		/* No more policies in the list */
-		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
-			return NULL;
-
-		policy = list_next_entry(policy, policy_list);
-	} while (!suitable_policy(policy, active));
-
-	return policy;
-}
-
-static struct cpufreq_policy *first_policy(bool active)
-{
-	struct cpufreq_policy *policy;
-
-	/* No policies in the list */
-	if (list_empty(&cpufreq_policy_list))
-		return NULL;
-
-	policy = list_first_entry(&cpufreq_policy_list, typeof(*policy),
-				  policy_list);
-
-	if (!suitable_policy(policy, active))
-		policy = next_policy(policy, active);
-
-	return policy;
-}
-
 /* Macros to iterate over CPU policies */
-#define for_each_suitable_policy(__policy, __active)	\
-	for (__policy = first_policy(__active);		\
-	     __policy;					\
-	     __policy = next_policy(__policy, __active))
+#define for_each_suitable_policy(__policy, __active)			 \
+	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \
+		if ((__active) == !policy_is_inactive(__policy))
 
 #define for_each_active_policy(__policy)		\
 	for_each_suitable_policy(__policy, true)
@@ -102,7 +64,6 @@ static LIST_HEAD(cpufreq_governor_list);
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
-DEFINE_MUTEX(cpufreq_governor_lock);
 
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
@@ -113,10 +74,8 @@ static inline bool has_target(void)
 }
 
 /* internal prototypes */
-static int __cpufreq_governor(struct cpufreq_policy *policy,
-		unsigned int event);
+static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
-static void handle_update(struct work_struct *work);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -818,12 +777,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 	ssize_t ret;
 
 	down_read(&policy->rwsem);
-
-	if (fattr->show)
-		ret = fattr->show(policy, buf);
-	else
-		ret = -EIO;
-
+	ret = fattr->show(policy, buf);
 	up_read(&policy->rwsem);
 
 	return ret;
@@ -838,18 +792,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 
 	get_online_cpus();
 
-	if (!cpu_online(policy->cpu))
-		goto unlock;
-
-	down_write(&policy->rwsem);
-
-	if (fattr->store)
+	if (cpu_online(policy->cpu)) {
+		down_write(&policy->rwsem);
 		ret = fattr->store(policy, buf, count);
-	else
-		ret = -EIO;
+		up_write(&policy->rwsem);
+	}
 
-	up_write(&policy->rwsem);
-unlock:
 	put_online_cpus();
 
 	return ret;
@@ -959,6 +907,11 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
 	return cpufreq_add_dev_symlink(policy);
 }
 
+__weak struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return NULL;
+}
+
 static int cpufreq_init_policy(struct cpufreq_policy *policy)
 {
 	struct cpufreq_governor *gov = NULL;
@@ -968,11 +921,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 
 	/* Update governor of new_policy to the governor used before hotplug */
 	gov = find_governor(policy->last_governor);
-	if (gov)
+	if (gov) {
 		pr_debug("Restoring governor %s for cpu %d\n",
 				policy->governor->name, policy->cpu);
-	else
-		gov = CPUFREQ_DEFAULT_GOVERNOR;
+	} else {
+		gov = cpufreq_default_governor();
+		if (!gov)
+			return -ENODATA;
+	}
 
 	new_policy.governor = gov;
 
@@ -996,36 +952,45 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 	if (cpumask_test_cpu(cpu, policy->cpus))
 		return 0;
 
+	down_write(&policy->rwsem);
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
+			goto unlock;
 		}
 	}
 
-	down_write(&policy->rwsem);
 	cpumask_set_cpu(cpu, policy->cpus);
-	up_write(&policy->rwsem);
 
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 		if (!ret)
-			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to start governor\n", __func__);
-			return ret;
-		}
 	}
 
-	return 0;
+unlock:
+	up_write(&policy->rwsem);
+	return ret;
+}
+
+static void handle_update(struct work_struct *work)
+{
+	struct cpufreq_policy *policy =
+		container_of(work, struct cpufreq_policy, update);
+	unsigned int cpu = policy->cpu;
+	pr_debug("handle_update for cpu %u called\n", cpu);
+	cpufreq_update_policy(cpu);
 }
 
 static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (WARN_ON(!dev))
 		return NULL;
@@ -1043,7 +1008,13 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
 		goto err_free_rcpumask;
 
-	kobject_init(&policy->kobj, &ktype_cpufreq);
+	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
+				   cpufreq_global_kobject, "policy%u