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
  ...

Documentation/cpu-freq/intel-pstate.txt

@@ -25,7 +25,7 @@ callback, so cpufreq core can't request a transition to a specific frequency.
 The driver provides minimum and maximum frequency limits and callbacks to set a
 policy. The policy in cpufreq sysfs is referred to as the "scaling governor".
 The cpufreq core can request the driver to operate in any of the two policies:
-"performance: and "powersave". The driver decides which frequency to use based
+"performance" and "powersave". The driver decides which frequency to use based
 on the above policy selection considering minimum and maximum frequency limits.
 
 The Intel P-State driver falls under the latter category, which implements the

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

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;

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;

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 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	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;
 }

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", cpu);
+	if (ret) {
+		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		goto err_free_real_cpus;
+	}
+
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1054,6 +1025,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	policy->cpu = cpu;
 	return policy;
 
+err_free_real_cpus:
+	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
 	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
@@ -1158,16 +1131,6 @@ static int cpufreq_online(unsigned int cpu)
 		cpumask_copy(policy->related_cpus, policy->cpus);
 		/* Remember CPUs present at the policy creation time. */
 		cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
-
-		/* Name and add the kobject */
-		ret = kobject_add(&policy->kobj, cpufreq_global_kobject,
-				  "policy%u",
-				  cpumask_first(policy->related_cpus));
-		if (ret) {
-			pr_err("%s: failed to add policy->kobj: %d\n", __func__,
-			       ret);
-			goto out_exit_policy;
-		}
 	}
 
 	/*
@@ -1309,9 +1272,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	return ret;
 }
 
-static void cpufreq_offline_prepare(unsigned int cpu)
+static void cpufreq_offline(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
@@ -1321,13 +1285,13 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		return;
 	}
 
+	down_write(&policy->rwsem);
 	if (has_target()) {
-		int 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__);
 	}
 
-	down_write(&policy->rwsem);
 	cpumask_clear_cpu(cpu, policy->cpus);
 
 	if (policy_is_inactive(policy)) {
@@ -1340,39 +1304,27 @@ static void cpufreq_offline_prepare(unsigned int cpu)
 		/* Nominate new CPU */
 		policy->cpu = cpumask_any(policy->cpus);
 	}
-	up_write(&policy->rwsem);
 
 	/* Start governor again for active policy */
 	if (!policy_is_inactive(policy)) {
 		if (has_target()) {
-			int 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)
 				pr_err("%s: Failed to start governor\n", __func__);
 		}
-	} else if (cpufreq_driver->stop_cpu) {
-		cpufreq_driver->stop_cpu(policy);
-	}
-}
 
-static void cpufreq_offline_finish(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-
-	if (!policy) {
-		pr_debug("%s: No cpu_data found\n", __func__);
-		return;
+		goto unlock;
 	}
 
-	/* Only proceed for inactive policies */
-	if (!policy_is_inactive(policy))
-		return;
+	if (cpufreq_driver->stop_cpu)
+		cpufreq_driver->stop_cpu(policy);
 
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
-		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
 	}
@@ -1386,6 +1338,9 @@ static void cpufreq_offline_finish(unsigned int cpu)
 		cpufreq_driver->exit(policy);
 		policy->freq_table = NULL;
 	}
+
+unlock:
+	up_write(&policy->rwsem);
 }
 
 /**
@@ -1401,10 +1356,8 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (!policy)
 		return;
 
-	if (cpu_online(cpu)) {
-		cpufreq_offline_prepare(cpu);
-		cpufreq_offline_finish(cpu);
-	}
+	if (cpu_online(cpu))
+		cpufreq_offline(cpu);
 
 	cpumask_clear_cpu(cpu, policy->real_cpus);
 	remove_cpu_dev_symlink(policy, cpu);
@@ -1413,15 +1366,6 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 		cpufreq_policy_free(policy, true);
 }
 
-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);
-}
-
 /**
  *	cpufreq_out_of_sync - If actual and saved CPU frequency differs, we're
  *	in deep trouble.
@@ -1584,6 +1528,7 @@ EXPORT_SYMBOL(cpufreq_generic_suspend);
 void cpufreq_suspend(void)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (!cpufreq_driver)
 		return;
@@ -1594,7 +1539,11 @@ void cpufreq_suspend(void)
 	pr_debug("%s: Suspending Governors\n", __func__);
 
 	for_each_active_policy(policy) {
-		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+		down_write(&policy->rwsem);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		up_write(&policy->rwsem);
+
+		if (ret)
 			pr_err("%s: Failed to stop governor for policy: %p\n",
 				__func__, policy);
 		else if (cpufreq_driver->suspend
@@ -1616,6 +1565,7 @@ void cpufreq_suspend(void)
 void cpufreq_resume(void)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	if (!cpufreq_driver)
 		return;
@@ -1628,13 +1578,20 @@ void cpufreq_resume(void)
 	pr_debug("%s: Resuming Governors\n", __func__);
 
 	for_each_active_policy(policy) {
-		if (cpufreq_driver->resume && cpufreq_driver->resume(policy))
+		if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) {
 			pr_err("%s: Failed to resume driver: %p\n", __func__,
 				policy);
-		else if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
-		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
-			pr_err("%s: Failed to start governor for policy: %p\n",
-				__func__, policy);
+		} else {
+			down_write(&policy->rwsem);
+			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
+			if (!ret)
+				cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			up_write(&policy->rwsem);
+
+			if (ret)
+				pr_err("%s: Failed to start governor for policy: %p\n",
+				       __func__, policy);
+		}
 	}
 
 	/*
@@ -1846,7 +1803,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			    unsigned int relation)
 {
 	unsigned int old_target_freq = target_freq;
-	int retval = -EINVAL;
+	struct cpufreq_frequency_table *freq_table;
+	int index, retval;
 
 	if (cpufreq_disabled())
 		return -ENODEV;
@@ -1873,34 +1831,28 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	policy->restore_freq = policy->cur;
 
 	if (cpufreq_driver->target)
-		retval = cpufreq_driver->target(policy, target_freq, relation);
-	else if (cpufreq_driver->target_index) {
-		struct cpufreq_frequency_table *freq_table;
-		int index;
-
-		freq_table = cpufreq_frequency_get_table(policy->cpu);
-		if (unlikely(!freq_table)) {
-			pr_err("%s: Unable to find freq_table\n", __func__);
-			goto out;
-		}
+		return cpufreq_driver->target(policy, target_freq, relation);
 
-		retval = cpufreq_frequency_table_target(policy, freq_table,
-				target_freq, relation, &index);
-		if (unlikely(retval)) {
-			pr_err("%s: Unable to find matching freq\n", __func__);
-			goto out;
-		}
+	if (!cpufreq_driver->target_index)
+		return -EINVAL;
 
-		if (freq_table[index].frequency == policy->cur) {
-			retval = 0;
-			goto out;
-		}
+	freq_table = cpufreq_frequency_get_table(policy->cpu);
+	if (unlikely(!freq_table)) {
+		pr_err("%s: Unable to find freq_table\n", __func__);
+		return -EINVAL;
+	}
 
-		retval = __target_index(policy, freq_table, index);
+	retval = cpufreq_frequency_table_target(policy, freq_table, target_freq,
+						relation, &index);
+	if (unlikely(retval)) {
+		pr_err("%s: Unable to find matching freq\n", __func__);
+		return retval;
 	}
 
-out:
-	return retval;
+	if (freq_table[index].frequency == policy->cur)
+		return 0;
+
+	return __target_index(policy, freq_table, index);
 }
 EXPORT_SYMBOL_GPL(__cpufreq_driver_target);
 
@@ -1920,20 +1872,14 @@ int cpufreq_driver_target(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_target);
 
-static int __cpufreq_governor(struct cpufreq_policy *policy,
-					unsigned int event)
+__weak struct cpufreq_governor *cpufreq_fallback_governor(void)
 {
-	int ret;
+	return NULL;
+}
 
-	/* Only must be defined when default governor is known to have latency
-	   restrictions, like e.g. conservative or ondemand.
-	   That this is the case is already ensured in Kconfig
-	*/
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
-	struct cpufreq_governor *gov = &cpufreq_gov_performance;
-#else
-	struct cpufreq_governor *gov = NULL;
-#endif
+static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
+{
+	int ret;
 
 	/* Don't start any governor operations if we are entering suspend */
 	if (cpufreq_suspended)
@@ -1948,12 +1894,14 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >
 	    policy->governor->max_transition_latency) {
-		if (!gov)
-			return -EINVAL;
-		else {
+		struct cpufreq_governor *gov = cpufreq_fallback_governor();
+
+		if (gov) {
 			pr_warn("%s governor failed, too long transition latency of HW, fallback to %s governor\n",
 				policy->governor->name, gov->name);
 			policy->governor = gov;
+		} else {
+			return -EINVAL;
 		}
 	}
 
@@ -1963,21 +1911,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 
 	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)
-	    || (!policy->governor_enabled
-	    && (event == CPUFREQ_GOV_LIMITS || event == CPUFREQ_GOV_STOP))) {
-		mutex_unlock(&cpufreq_governor_lock);
-		return -EBUSY;
-	}
-
-	if (event == CPUFREQ_GOV_STOP)
-		policy->governor_enabled = false;
-	else if (event == CPUFREQ_GOV_START)
-		policy->governor_enabled = true;
-
-	mutex_unlock(&cpufreq_governor_lock);
-
 	ret = policy->governor->governor(policy, event);
 
 	if (!ret) {
@@ -1985,14 +1918,6 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 			policy->governor->initialized++;
 		else if (event == CPUFREQ_GOV_POLICY_EXIT)
 			policy->governor->initialized--;
-	} else {
-		/* Restore original values */
-		mutex_lock(&cpufreq_governor_lock);
-		if (event == CPUFREQ_GOV_STOP)
-			policy->governor_enabled = true;
-		else if (event == CPUFREQ_GOV_START)
-			policy->governor_enabled = false;
-		mutex_unlock(&cpufreq_governor_lock);
 	}
 
 	if (((event == CPUFREQ_GOV_POLICY_INIT) && ret) ||
@@ -2147,7 +2072,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	old_gov = policy->governor;
 	/* end old governor */
 	if (old_gov) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP);
 		if (ret) {
 			/* This can happen due to race with other operations */
 			pr_debug("%s: Failed to Stop Governor: %s (%d)\n",
@@ -2155,10 +2080,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 			return ret;
 		}
 
-		up_write(&policy->rwsem);
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		down_write(&policy->rwsem);
-
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret) {
 			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
 			       __func__, old_gov->name, ret);
@@ -2168,32 +2090,30 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
 	if (!ret) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
 		if (!ret)
 			goto out;
 
-		up_write(&policy->rwsem);
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		down_write(&policy->rwsem);
+		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 	}
 
 	/* new governor failed, so re-start old one */
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
 			policy->governor = NULL;
 		else
-			__cpufreq_governor(policy, CPUFREQ_GOV_START);
+			cpufreq_governor(policy, CPUFREQ_GOV_START);
 	}
 
 	return ret;
 
  out:
 	pr_debug("governor: change or update limits\n");
-	return __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 }
 
 /**
@@ -2260,11 +2180,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 		break;
 
 	case CPU_DOWN_PREPARE:
-		cpufreq_offline_prepare(cpu);
-		break;
-
-	case CPU_POST_DEAD:
-		cpufreq_offline_finish(cpu);
+		cpufreq_offline(cpu);
 		break;
 
 	case CPU_DOWN_FAILED:
@@ -2297,8 +2213,11 @@ static int cpufreq_boost_set_sw(int state)
 				       __func__);
 				break;
 			}
+
+			down_write(&policy->rwsem);
 			policy->user_policy.max = policy->max;
-			__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			up_write(&policy->rwsem);
 		}
 	}
 
@@ -2384,7 +2303,7 @@ EXPORT_SYMBOL_GPL(cpufreq_boost_enabled);
  * submitted by the CPU Frequency driver.
  *
  * Registers a CPU Frequency driver to this core code. This code
- * returns zero on success, -EBUSY when another driver got here first
+ * returns zero on success, -EEXIST when another driver got here first
  * (and isn't unregistered in the meantime).
  *
  */

drivers/cpufreq/cpufreq_conservative.c

@@ -14,6 +14,22 @@
 #include <linux/slab.h>
 #include "cpufreq_governor.h"
 
+struct cs_policy_dbs_info {
+	struct policy_dbs_info policy_dbs;
+	unsigned int down_skip;
+	unsigned int requested_freq;
+};
+
+static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
+{
+	return container_of(policy_dbs, struct cs_policy_dbs_info, policy_dbs);
+}
+
+struct cs_dbs_tuners {
+	unsigned int down_threshold;
+	unsigned int freq_step;
+};
+
 /* Conservative governor macros */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
@@ -21,21 +37,6 @@
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(10)
 
-static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
-
-static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event);
-
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_conservative = {
-	.name			= "conservative",
-	.governor		= cs_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
-
 static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
 					   struct cpufreq_policy *policy)
 {
@@ -57,27 +58,28 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
  * Any frequency increase takes it to the maximum frequency. Frequency reduction
  * happens at minimum steps of 5% (default) of maximum frequency
  */
-static void cs_check_cpu(int cpu, unsigned int load)
+static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
 {
-	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
-	struct dbs_data *dbs_data = policy->governor_data;
+	struct policy_dbs_info *policy_dbs = policy->governor_data;
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+	struct dbs_data *dbs_data = policy_dbs->dbs_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	unsigned int load = dbs_update(policy);
 
 	/*
 	 * break out if we 'cannot' reduce the speed as the user might
 	 * want freq_step to be zero
 	 */
 	if (cs_tuners->freq_step == 0)
-		return;
+		goto out;
 
 	/* Check for frequency increase */
-	if (load > cs_tuners->up_threshold) {
+	if (load > dbs_data->up_threshold) {
 		dbs_info->down_skip = 0;
 
 		/* if we are already at full speed then break out early */
 		if (dbs_info->requested_freq == policy->max)
-			return;
+			goto out;
 
 		dbs_info->requested_freq += get_freq_target(cs_tuners, policy);
 
@@ -86,12 +88,12 @@ static void cs_check_cpu(int cpu, unsigned int load)
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 			CPUFREQ_RELATION_H);
-		return;
+		goto out;
 	}
 
 	/* if sampling_down_factor is active break out early */
-	if (++dbs_info->down_skip < cs_tuners->sampling_down_factor)
-		return;
+	if (++dbs_info->down_skip < dbs_data->sampling_down_factor)
+		goto out;
 	dbs_info->down_skip = 0;
 
 	/* Check for frequency decrease */
@@ -101,7 +103,7 @@ static void cs_check_cpu(int cpu, unsigned int load)
 		 * if we cannot reduce the frequency anymore, break out early
 		 */
 		if (policy->cur == policy->min)
-			return;
+			goto out;
 
 		freq_target = get_freq_target(cs_tuners, policy);
 		if (dbs_info->requested_freq > freq_target)
@@ -111,58 +113,25 @@ static void cs_check_cpu(int cpu, unsigned int load)
 
 		__cpufreq_driver_target(policy, dbs_info->requested_freq,
 				CPUFREQ_RELATION_L);
-		return;
 	}
-}
-
-static unsigned int cs_dbs_timer(struct cpufreq_policy *policy, bool modify_all)
-{
-	struct dbs_data *dbs_data = policy->governor_data;
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-
-	if (modify_all)
-		dbs_check_cpu(dbs_data, policy->cpu);
 
-	return delay_for_sampling_rate(cs_tuners->sampling_rate);
+ out:
+	return dbs_data->sampling_rate;
 }
 
 static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-		void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	struct cs_cpu_dbs_info_s *dbs_info =
-					&per_cpu(cs_cpu_dbs_info, freq->cpu);
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
-
-	if (!policy)
-		return 0;
-
-	/* policy isn't governed by conservative governor */
-	if (policy->governor != &cpufreq_gov_conservative)
-		return 0;
-
-	/*
-	 * we only care if our internally tracked freq moves outside the 'valid'
-	 * ranges of frequency available to us otherwise we do not change it
-	*/
-	if (dbs_info->requested_freq > policy->max
-			|| dbs_info->requested_freq < policy->min)
-		dbs_info->requested_freq = freq->new;
-
-	return 0;
-}
+				void *data);
 
 static struct notifier_block cs_cpufreq_notifier_block = {
 	.notifier_call = dbs_cpufreq_notifier,
 };
 
 /************************** sysfs interface ************************/
-static struct common_dbs_data cs_dbs_cdata;
+static struct dbs_governor cs_dbs_gov;
 
 static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
 	ret = sscanf(buf, "%u", &input);
@@ -170,22 +139,7 @@ static ssize_t store_sampling_down_factor(struct dbs_data *dbs_data,
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
 
-	cs_tuners->sampling_down_factor = input;
-	return count;
-}
-
-static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
-		size_t count)
-{
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	unsigned int input;
-	int ret;
-	ret = sscanf(buf, "%u", &input);
-
-	if (ret != 1)
-		return -EINVAL;
-
-	cs_tuners->sampling_rate = max(input, dbs_data->min_sampling_rate);
+	dbs_data->sampling_down_factor = input;
 	return count;
 }
 
@@ -200,7 +154,7 @@ static ssize_t store_up_threshold(struct dbs_data *dbs_data, const char *buf,
 	if (ret != 1 || input > 100 || input <= cs_tuners->down_threshold)
 		return -EINVAL;
 
-	cs_tuners->up_threshold = input;
+	dbs_data->up_threshold = input;
 	return count;
 }
 
@@ -214,7 +168,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 
 	/* cannot be lower than 11 otherwise freq will not fall */
 	if (ret != 1 || input < 11 || input > 100 ||
-			input >= cs_tuners->up_threshold)
+			input >= dbs_data->up_threshold)
 		return -EINVAL;
 
 	cs_tuners->down_threshold = input;
@@ -224,8 +178,7 @@ static ssize_t store_down_threshold(struct dbs_data *dbs_data, const char *buf,
 static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 		const char *buf, size_t count)
 {
-	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	unsigned int input, j;
+	unsigned int input;
 	int ret;
 
 	ret = sscanf(buf, "%u", &input);
@@ -235,21 +188,14 @@ static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
 	if (input > 1)
 		input = 1;
 
-	if (input == cs_tuners->ignore_nice_load) /* nothing to do */
+	if (input == dbs_data->ignore_nice_load) /* nothing to do */
 		return count;
 
-	cs_tuners->ignore_nice_load = input;
+	dbs_data->ignore_nice_load = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
-	for_each_online_cpu(j) {
-		struct cs_cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-					&dbs_info->cdbs.prev_cpu_wall, 0);
-		if (cs_tuners->ignore_nice_load)
-			dbs_info->cdbs.prev_cpu_nice =
-				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-	}
+	gov_update_cpu_data(dbs_data);
+
 	return count;
 }
 
@@ -275,55 +221,47 @@ static ssize_t store_freq_step(struct dbs_data *dbs_data, const char *buf,
 	return count;
 }
 
-show_store_one(cs, sampling_rate);
-show_store_one(cs, sampling_down_factor);
-show_store_one(cs, up_threshold);
-show_store_one(cs, down_threshold);
-show_store_one(cs, ignore_nice_load);
-show_store_one(cs, freq_step);
-declare_show_sampling_rate_min(cs);
-
-gov_sys_pol_attr_rw(sampling_rate);
-gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(up_threshold);
-gov_sys_pol_attr_rw(down_threshold);
-gov_sys_pol_attr_rw(ignore_nice_load);
-gov_sys_pol_attr_rw(freq_step);
-gov_sys_pol_attr_ro(sampling_rate_min);
-
-static struct attribute *dbs_attributes_gov_sys[] = {
-	&sampling_rate_min_gov_sys.attr,
-	&sampling_rate_gov_sys.attr,
-	&sampling_down_factor_gov_sys.attr,
-	&up_threshold_gov_sys.attr,
-	&down_threshold_gov_sys.attr,
-	&ignore_nice_load_gov_sys.attr,
-	&freq_step_gov_sys.attr,
+gov_show_one_common(sampling_rate);
+gov_show_one_common(sampling_down_factor);
+gov_show_one_common(up_threshold);
+gov_show_one_common(ignore_nice_load);
+gov_show_one_common(min_sampling_rate);
+gov_show_one(cs, down_threshold);
+gov_show_one(cs, freq_step);
+
+gov_attr_rw(sampling_rate);
+gov_attr_rw(sampling_down_factor);
+gov_attr_rw(up_threshold);
+gov_attr_rw(ignore_nice_load);
+gov_attr_ro(min_sampling_rate);
+gov_attr_rw(down_threshold);
+gov_attr_rw(freq_step);
+
+static struct attribute *cs_attributes[] = {
+	&min_sampling_rate.attr,
+	&sampling_rate.attr,
+	&sampling_down_factor.attr,
+	&up_threshold.attr,
+	&down_threshold.attr,
+	&ignore_nice_load.attr,
+	&freq_step.attr,
 	NULL
 };
 
-static struct attribute_group cs_attr_group_gov_sys = {
-	.attrs = dbs_attributes_gov_sys,
-	.name = "conservative",
-};
+/************************** sysfs end ************************/
 
-static struct attribute *dbs_attributes_gov_pol[] = {
-	&sampling_rate_min_gov_pol.attr,
-	&sampling_rate_gov_pol.attr,
-	&sampling_down_factor_gov_pol.attr,
-	&up_threshold_gov_pol.attr,
-	&down_threshold_gov_pol.attr,
-	&ignore_nice_load_gov_pol.attr,
-	&freq_step_gov_pol.attr,
-	NULL
-};
+static struct policy_dbs_info *cs_alloc(void)
+{
+	struct cs_policy_dbs_info *dbs_info;
 
-static struct attribute_group cs_attr_group_gov_pol = {
-	.attrs = dbs_attributes_gov_pol,
-	.name = "conservative",
-};
+	dbs_info = kzalloc(sizeof(*dbs_info), GFP_KERNEL);
+	return dbs_info ? &dbs_info->policy_dbs : NULL;
+}
 
-/************************** sysfs end ************************/
+static void cs_free(struct policy_dbs_info *policy_dbs)
+{
+	kfree(to_dbs_info(policy_dbs));
+}
 
 static int cs_init(struct dbs_data *dbs_data, bool notify)
 {
@@ -335,11 +273,11 @@ static int cs_init(struct dbs_data *dbs_data, bool notify)
 		return -ENOMEM;
 	}
 
-	tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
 	tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
-	tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
-	tuners->ignore_nice_load = 0;
 	tuners->freq_step = DEF_FREQUENCY_STEP;
+	dbs_data->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
+	dbs_data->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
+	dbs_data->ignore_nice_load = 0;
 
 	dbs_data->tuners = tuners;
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
@@ -361,35 +299,66 @@ static void cs_exit(struct dbs_data *dbs_data, bool notify)
 	kfree(dbs_data->tuners);
 }
 
-define_get_cpu_dbs_routines(cs_cpu_dbs_info);
+static void cs_start(struct cpufreq_policy *policy)
+{
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	dbs_info->down_skip = 0;
+	dbs_info->requested_freq = policy->cur;
+}
 
-static struct common_dbs_data cs_dbs_cdata = {
-	.governor = GOV_CONSERVATIVE,
-	.attr_group_gov_sys = &cs_attr_group_gov_sys,
-	.attr_group_gov_pol = &cs_attr_group_gov_pol,
-	.get_cpu_cdbs = get_cpu_cdbs,
-	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+static struct dbs_governor cs_dbs_gov = {
+	.gov = {
+		.name = "conservative",
+		.governor = cpufreq_governor_dbs,
+		.max_transition_latency = TRANSITION_LATENCY_LIMIT,
+		.owner = THIS_MODULE,
+	},
+	.kobj_type = { .default_attrs = cs_attributes },
 	.gov_dbs_timer = cs_dbs_timer,
-	.gov_check_cpu = cs_check_cpu,
+	.alloc = cs_alloc,
+	.free = cs_free,
 	.init = cs_init,
 	.exit = cs_exit,
-	.mutex = __MUTEX_INITIALIZER(cs_dbs_cdata.mutex),
+	.start = cs_start,
 };
 
-static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event)
+#define CPU_FREQ_GOV_CONSERVATIVE	(&cs_dbs_gov.gov)
+
+static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
 {
-	return cpufreq_governor_dbs(policy, &cs_dbs_cdata, event);
+	struct cpufreq_freqs *freq = data;
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
+	struct cs_policy_dbs_info *dbs_info;
+
+	if (!policy)
+		return 0;
+
+	/* policy isn't governed by conservative governor */
+	if (policy->governor != CPU_FREQ_GOV_CONSERVATIVE)
+		return 0;
+
+	dbs_info = to_dbs_info(policy->governor_data);
+	/*
+	 * we only care if our internally tracked freq moves outside the 'valid'
+	 * ranges of frequency available to us otherwise we do not change it
+	*/
+	if (dbs_info->requested_freq > policy->max
+			|| dbs_info->requested_freq < policy->min)
+		dbs_info->requested_freq = freq->new;
+
+	return 0;
 }
 
 static int __init cpufreq_gov_dbs_init(void)
 {
-	return cpufreq_register_governor(&cpufreq_gov_conservative);
+	return cpufreq_register_governor(CPU_FREQ_GOV_CONSERVATIVE);
 }
 
 static void __exit cpufreq_gov_dbs_exit(void)
 {
-	cpufreq_unregister_governor(&cpufreq_gov_conservative);
+	cpufreq_unregister_governor(CPU_FREQ_GOV_CONSERVATIVE);
 }
 
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
@@ -399,6 +368,11 @@ MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return CPU_FREQ_GOV_CONSERVATIVE;
+}
+
 fs_initcall(cpufreq_gov_dbs_init);
 #else
 module_init(cpufreq_gov_dbs_init);

drivers/cpufreq/cpufreq_governor.h

@@ -18,6 +18,7 @@
 #define _CPUFREQ_GOVERNOR_H
 
 #include <linux/atomic.h>
+#include <linux/irq_work.h>
 #include <linux/cpufreq.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
@@ -41,96 +42,68 @@
 enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
 
 /*
- * Macro for creating governors sysfs routines
- *
- * - gov_sys: One governor instance per whole system
- * - gov_pol: One governor instance per policy
+ * Abbreviations:
+ * dbs: used as a shortform for demand based switching It helps to keep variable
+ *	names smaller, simpler
+ * cdbs: common dbs
+ * od_*: On-demand governor
+ * cs_*: Conservative governor
  */
 
-/* Create attributes */
-#define gov_sys_attr_ro(_name)						\
-static struct global_attr _name##_gov_sys =				\
-__ATTR(_name, 0444, show_##_name##_gov_sys, NULL)
-
-#define gov_sys_attr_rw(_name)						\
-static struct global_attr _name##_gov_sys =				\
-__ATTR(_name, 0644, show_##_name##_gov_sys, store_##_name##_gov_sys)
-
-#define gov_pol_attr_ro(_name)						\
-static struct freq_attr _name##_gov_pol =				\
-__ATTR(_name, 0444, show_##_name##_gov_pol, NULL)
-
-#define gov_pol_attr_rw(_name)						\
-static struct freq_attr _name##_gov_pol =				\
-__ATTR(_name, 0644, show_##_name##_gov_pol, store_##_name##_gov_pol)
+/* Governor demand based switching data (per-policy or global). */
+struct dbs_data {
+	int usage_count;
+	void *tuners;
+	unsigned int min_sampling_rate;
+	unsigned int ignore_nice_load;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int io_is_busy;
 
-#define gov_sys_pol_attr_rw(_name)					\
-	gov_sys_attr_rw(_name);						\
-	gov_pol_attr_rw(_name)
+	struct kobject kobj;
+	struct list_head policy_dbs_list;
+	/*
+	 * Protect concurrent updates to governor tunables from sysfs,
+	 * policy_dbs_list and usage_count.
+	 */
+	struct mutex mutex;
+};
 
-#define gov_sys_pol_attr_ro(_name)					\
-	gov_sys_attr_ro(_name);						\
-	gov_pol_attr_ro(_name)
+/* Governor's specific attributes */
+struct dbs_data;
+struct governor_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct dbs_data *dbs_data, char *buf);
+	ssize_t (*store)(struct dbs_data *dbs_data, const char *buf,
+			 size_t count);
+};
 
-/* Create show/store routines */
-#define show_one(_gov, file_name)					\
-static ssize_t show_##file_name##_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
+#define gov_show_one(_gov, file_name)					\
+static ssize_t show_##file_name						\
+(struct dbs_data *dbs_data, char *buf)					\
 {									\
-	struct _gov##_dbs_tuners *tuners = _gov##_dbs_cdata.gdbs_data->tuners; \
-	return sprintf(buf, "%u\n", tuners->file_name);			\
-}									\
-									\
-static ssize_t show_##file_name##_gov_pol				\
-(struct cpufreq_policy *policy, char *buf)				\
-{									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
 	struct _gov##_dbs_tuners *tuners = dbs_data->tuners;		\
 	return sprintf(buf, "%u\n", tuners->file_name);			\
 }
 
-#define store_one(_gov, file_name)					\
-static ssize_t store_##file_name##_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) \
-{									\
-	struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data;		\
-	return store_##file_name(dbs_data, buf, count);			\
-}									\
-									\
-static ssize_t store_##file_name##_gov_pol				\
-(struct cpufreq_policy *policy, const char *buf, size_t count)		\
+#define gov_show_one_common(file_name)					\
+static ssize_t show_##file_name						\
+(struct dbs_data *dbs_data, char *buf)					\
 {									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
-	return store_##file_name(dbs_data, buf, count);			\
+	return sprintf(buf, "%u\n", dbs_data->file_name);		\
 }
 
-#define show_store_one(_gov, file_name)					\
-show_one(_gov, file_name);						\
-store_one(_gov, file_name)
+#define gov_attr_ro(_name)						\
+static struct governor_attr _name =					\
+__ATTR(_name, 0444, show_##_name, NULL)
 
-/* create helper routines */
-#define define_get_cpu_dbs_routines(_dbs_info)				\
-static struct cpu_dbs_info *get_cpu_cdbs(int cpu)			\
-{									\
-	return &per_cpu(_dbs_info, cpu).cdbs;				\
-}									\
-									\
-static void *get_cpu_dbs_info_s(int cpu)				\
-{									\
-	return &per_cpu(_dbs_info, cpu);				\
-}
-
-/*
- * Abbreviations:
- * dbs: used as a shortform for demand based switching It helps to keep variable
- *	names smaller, simpler
- * cdbs: common dbs
- * od_*: On-demand governor
- * cs_*: Conservative governor
- */
+#define gov_attr_rw(_name)						\
+static struct governor_attr _name =					\
+__ATTR(_name, 0644, show_##_name, store_##_name)
 
 /* Common to all CPUs of a policy */
-struct cpu_common_dbs_info {
+struct policy_dbs_info {
 	struct cpufreq_policy *policy;
 	/*
 	 * Per policy mutex that serializes load evaluation from limit-change
@@ -138,11 +111,27 @@ struct cpu_common_dbs_info {
 	 */
 	struct mutex timer_mutex;
 
-	ktime_t time_stamp;
-	atomic_t skip_work;
+	u64 last_sample_time;
+	s64 sample_delay_ns;
+	atomic_t work_count;
+	struct irq_work irq_work;
 	struct work_struct work;
+	/* dbs_data may be shared between multiple policy objects */
+	struct dbs_data *dbs_data;
+	struct list_head list;
+	/* Multiplier for increasing sample delay temporarily. */
+	unsigned int rate_mult;
+	/* Status indicators */
+	bool is_shared;		/* This object is used by multiple CPUs */
+	bool work_in_progress;	/* Work is being queued up or in progress */
 };
 
+static inline void gov_update_sample_delay(struct policy_dbs_info *policy_dbs,
+					   unsigned int delay_us)
+{
+	policy_dbs->sample_delay_ns = delay_us * NSEC_PER_USEC;
+}
+
 /* Per cpu structures */
 struct cpu_dbs_info {
 	u64 prev_cpu_idle;
@@ -155,54 +144,14 @@ struct cpu_dbs_info {
 	 * wake-up from idle.
 	 */
 	unsigned int prev_load;
-	struct timer_list timer;
-	struct cpu_common_dbs_info *shared;
-};
-
-struct od_cpu_dbs_info_s {
-	struct cpu_dbs_info cdbs;
-	struct cpufreq_frequency_table *freq_table;
-	unsigned int freq_lo;
-	unsigned int freq_lo_jiffies;
-	unsigned int freq_hi_jiffies;
-	unsigned int rate_mult;
-	unsigned int sample_type:1;
-};
-
-struct cs_cpu_dbs_info_s {
-	struct cpu_dbs_info cdbs;
-	unsigned int down_skip;
-	unsigned int requested_freq;
-};
-
-/* Per policy Governors sysfs tunables */
-struct od_dbs_tuners {
-	unsigned int ignore_nice_load;
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int powersave_bias;
-	unsigned int io_is_busy;
-};
-
-struct cs_dbs_tuners {
-	unsigned int ignore_nice_load;
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int down_threshold;
-	unsigned int freq_step;
+	struct update_util_data update_util;
+	struct policy_dbs_info *policy_dbs;
 };
 
 /* Common Governor data across policies */
-struct dbs_data;
-struct common_dbs_data {
-	/* Common across governors */
-	#define GOV_ONDEMAND		0
-	#define GOV_CONSERVATIVE	1
-	int governor;
-	struct attribute_group *attr_group_gov_sys; /* one governor - system */
-	struct attribute_group *attr_group_gov_pol; /* one governor - policy */
+struct dbs_governor {
+	struct cpufreq_governor gov;
+	struct kobj_type kobj_type;
 
 	/*
 	 * Common data for platforms that don't set
@@ -210,74 +159,32 @@ struct common_dbs_data {
 	 */
 	struct dbs_data *gdbs_data;
 
-	struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
-	void *(*get_cpu_dbs_info_s)(int cpu);
-	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy,
-				      bool modify_all);
-	void (*gov_check_cpu)(int cpu, unsigned int load);
+	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy);
+	struct policy_dbs_info *(*alloc)(void);
+	void (*free)(struct policy_dbs_info *policy_dbs);
 	int (*init)(struct dbs_data *dbs_data, bool notify);
 	void (*exit)(struct dbs_data *dbs_data, bool notify);
-
-	/* Governor specific ops, see below */
-	void *gov_ops;
-
-	/*
-	 * Protects governor's data (struct dbs_data and struct common_dbs_data)
-	 */
-	struct mutex mutex;
+	void (*start)(struct cpufreq_policy *policy);
 };
 
-/* Governor Per policy data */
-struct dbs_data {
-	struct common_dbs_data *cdata;
-	unsigned int min_sampling_rate;
-	int usage_count;
-	void *tuners;
-};
+static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)
+{
+	return container_of(policy->governor, struct dbs_governor, gov);
+}
 
-/* Governor specific ops, will be passed to dbs_data->gov_ops */
+/* Governor specific operations */
 struct od_ops {
-	void (*powersave_bias_init_cpu)(int cpu);
 	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
 			unsigned int freq_next, unsigned int relation);
-	void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
 };
 
-static inline int delay_for_sampling_rate(unsigned int sampling_rate)
-{
-	int delay = usecs_to_jiffies(sampling_rate);
-
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	if (num_online_cpus() > 1)
-		delay -= jiffies % delay;
-
-	return delay;
-}
-
-#define declare_show_sampling_rate_min(_gov)				\
-static ssize_t show_sampling_rate_min_gov_sys				\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
-{									\
-	struct dbs_data *dbs_data = _gov##_dbs_cdata.gdbs_data;		\
-	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
-}									\
-									\
-static ssize_t show_sampling_rate_min_gov_pol				\
-(struct cpufreq_policy *policy, char *buf)				\
-{									\
-	struct dbs_data *dbs_data = policy->governor_data;		\
-	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
-}
-
-extern struct mutex cpufreq_governor_lock;
-
-void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay);
-void gov_cancel_work(struct cpu_common_dbs_info *shared);
-void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		struct common_dbs_data *cdata, unsigned int event);
+unsigned int dbs_update(struct cpufreq_policy *policy);
+int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int event);
 void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);
 void od_unregister_powersave_bias_handler(void);
+ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,
+			    size_t count);
+void gov_update_cpu_data(struct dbs_data *dbs_data);
 #endif /* _CPUFREQ_GOVERNOR_H */

drivers/cpufreq/cpufreq_ondemand.h

+/*
+ * Header file for CPUFreq ondemand governor and related code.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.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.
+ */
+
+#include "cpufreq_governor.h"
+
+struct od_policy_dbs_info {
+	struct policy_dbs_info policy_dbs;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_delay_us;
+	unsigned int freq_hi_delay_us;
+	unsigned int sample_type:1;
+};
+
+static inline struct od_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
+{
+	return container_of(policy_dbs, struct od_policy_dbs_info, policy_dbs);
+}
+
+struct od_dbs_tuners {
+	unsigned int powersave_bias;
+};

drivers/cpufreq/cpufreq_performance.c

@@ -33,10 +33,7 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy,
 	return 0;
 }
 
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_performance = {
+static struct cpufreq_governor cpufreq_gov_performance = {
 	.name		= "performance",
 	.governor	= cpufreq_governor_performance,
 	.owner		= THIS_MODULE,
@@ -52,6 +49,19 @@ static void __exit cpufreq_gov_performance_exit(void)
 	cpufreq_unregister_governor(&cpufreq_gov_performance);
 }
 
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &cpufreq_gov_performance;
+}
+#endif
+#ifndef CONFIG_CPU_FREQ_GOV_PERFORMANCE_MODULE
+struct cpufreq_governor *cpufreq_fallback_governor(void)
+{
+	return &cpufreq_gov_performance;
+}
+#endif
+
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq policy governor 'performance'");
 MODULE_LICENSE("GPL");

drivers/cpufreq/cpufreq_powersave.c

@@ -33,10 +33,7 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy,
 	return 0;
 }
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_powersave = {
+static struct cpufreq_governor cpufreq_gov_powersave = {
 	.name		= "powersave",
 	.governor	= cpufreq_governor_powersave,
 	.owner		= THIS_MODULE,
@@ -57,6 +54,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'powersave'");
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &cpufreq_gov_powersave;
+}
+
 fs_initcall(cpufreq_gov_powersave_init);
 #else
 module_init(cpufreq_gov_powersave_init);

drivers/cpufreq/cpufreq_userspace.c

@@ -89,10 +89,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 	return rc;
 }
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_userspace = {
+static struct cpufreq_governor cpufreq_gov_userspace = {
 	.name		= "userspace",
 	.governor	= cpufreq_governor_userspace,
 	.store_setspeed	= cpufreq_set,
@@ -116,6 +113,11 @@ MODULE_DESCRIPTION("CPUfreq policy governor 'userspace'");
 MODULE_LICENSE("GPL");
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE
+struct cpufreq_governor *cpufreq_default_governor(void)
+{
+	return &cpufreq_gov_userspace;
+}
+
 fs_initcall(cpufreq_gov_userspace_init);
 #else
 module_init(cpufreq_gov_userspace_init);

drivers/cpufreq/intel_pstate.c

@@ -71,7 +71,7 @@ struct sample {
 	u64 mperf;
 	u64 tsc;
 	int freq;
-	ktime_t time;
+	u64 time;
 };
 
 struct pstate_data {
@@ -103,13 +103,13 @@ struct _pid {
 struct cpudata {
 	int cpu;
 
-	struct timer_list timer;
+	struct update_util_data update_util;
 
 	struct pstate_data pstate;
 	struct vid_data vid;
 	struct _pid pid;
 
-	ktime_t last_sample_time;
+	u64	last_sample_time;
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;
@@ -120,6 +120,7 @@ struct cpudata {
 static struct cpudata **all_cpu_data;
 struct pstate_adjust_policy {
 	int sample_rate_ms;
+	s64 sample_rate_ns;
 	int deadband;
 	int setpoint;
 	int p_gain_pct;
@@ -197,8 +198,8 @@ static struct perf_limits *limits = &powersave_limits;
 
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
-	pid->setpoint = setpoint;
-	pid->deadband  = deadband;
+	pid->setpoint = int_tofp(setpoint);
+	pid->deadband  = int_tofp(deadband);
 	pid->integral  = int_tofp(integral);
 	pid->last_err  = int_tofp(setpoint) - int_tofp(busy);
 }
@@ -224,9 +225,9 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
 	int32_t pterm, dterm, fp_error;
 	int32_t integral_limit;
 
-	fp_error = int_tofp(pid->setpoint) - busy;
+	fp_error = pid->setpoint - busy;
 
-	if (abs(fp_error) <= int_tofp(pid->deadband))
+	if (abs(fp_error) <= pid->deadband)
 		return 0;
 
 	pterm = mul_fp(pid->p_gain, fp_error);
@@ -286,7 +287,7 @@ static inline void update_turbo_state(void)
 		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
 }
 
-static void intel_pstate_hwp_set(void)
+static void intel_pstate_hwp_set(const struct cpumask *cpumask)
 {
 	int min, hw_min, max, hw_max, cpu, range, adj_range;
 	u64 value, cap;
@@ -296,9 +297,7 @@ static void intel_pstate_hwp_set(void)
 	hw_max = HWP_HIGHEST_PERF(cap);
 	range = hw_max - hw_min;
 
-	get_online_cpus();
-
-	for_each_online_cpu(cpu) {
+	for_each_cpu(cpu, cpumask) {
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
 		adj_range = limits->min_perf_pct * range / 100;
 		min = hw_min + adj_range;
@@ -317,7 +316,12 @@ static void intel_pstate_hwp_set(void)
 		value |= HWP_MAX_PERF(max);
 		wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 	}
+}
 
+static void intel_pstate_hwp_set_online_cpus(void)
+{
+	get_online_cpus();
+	intel_pstate_hwp_set(cpu_online_mask);
 	put_online_cpus();
 }
 
@@ -439,7 +443,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	limits->no_turbo = clamp_t(int, input, 0, 1);
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set_online_cpus();
 
 	return count;
 }
@@ -465,7 +469,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 				  int_tofp(100));
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set_online_cpus();
 	return count;
 }
 
@@ -490,7 +494,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 				  int_tofp(100));
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set_online_cpus();
 	return count;
 }
 
@@ -531,6 +535,9 @@ static void __init intel_pstate_sysfs_expose_params(void)
 
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
+	/* First disable HWP notification interrupt as we don't process them */
+	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
+
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
@@ -712,7 +719,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 	if (limits->no_turbo && !limits->turbo_disabled)
 		val |= (u64)1 << 32;
 
-	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
+	wrmsrl(MSR_IA32_PERF_CTL, val);
 }
 
 static int knl_get_turbo_pstate(void)
@@ -824,11 +831,11 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	 * policy, or by cpu specific default values determined through
 	 * experimentation.
 	 */
-	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf));
+	max_perf_adj = fp_toint(max_perf * limits->max_perf);
 	*max = clamp_t(int, max_perf_adj,
 			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
-	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf));
+	min_perf = fp_toint(max_perf * limits->min_perf);
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
@@ -874,16 +881,10 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 	core_pct = int_tofp(sample->aperf) * int_tofp(100);
 	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));
 
-	sample->freq = fp_toint(
-		mul_fp(int_tofp(
-			cpu->pstate.max_pstate_physical *
-			cpu->pstate.scaling / 100),
-			core_pct));
-
 	sample->core_pct_busy = (int32_t)core_pct;
 }
 
-static inline void intel_pstate_sample(struct cpudata *cpu)
+static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
 {
 	u64 aperf, mperf;
 	unsigned long flags;
@@ -893,14 +894,14 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
 	tsc = rdtsc();
-	if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) {
+	if (cpu->prev_mperf == mperf || cpu->prev_tsc == tsc) {
 		local_irq_restore(flags);
-		return;
+		return false;
 	}
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
-	cpu->sample.time = ktime_get();
+	cpu->sample.time = time;
 	cpu->sample.aperf = aperf;
 	cpu->sample.mperf = mperf;
 	cpu->sample.tsc =  tsc;
@@ -908,27 +909,16 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	cpu->sample.mperf -= cpu->prev_mperf;
 	cpu->sample.tsc -= cpu->prev_tsc;
 
-	intel_pstate_calc_busy(cpu);
-
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
 	cpu->prev_tsc = tsc;
+	return true;
 }
 
-static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
-{
-	int delay;
-
-	delay = msecs_to_jiffies(50);
-	mod_timer_pinned(&cpu->timer, jiffies + delay);
-}
-
-static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
+static inline int32_t get_avg_frequency(struct cpudata *cpu)
 {
-	int delay;
-
-	delay = msecs_to_jiffies(pid_params.sample_rate_ms);
-	mod_timer_pinned(&cpu->timer, jiffies + delay);
+	return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf *
+		cpu->pstate.scaling, cpu->sample.mperf);
 }
 
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
@@ -954,7 +944,6 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 	mperf = cpu->sample.mperf + delta_iowait_mperf;
 	cpu->prev_cummulative_iowait = cummulative_iowait;
 
-
 	/*
 	 * The load can be estimated as the ratio of the mperf counter
 	 * running at a constant frequency during active periods
@@ -970,8 +959,9 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 {
 	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
-	s64 duration_us;
-	u32 sample_time;
+	u64 duration_ns;
+
+	intel_pstate_calc_busy(cpu);
 
 	/*
 	 * core_busy is the ratio of actual performance to max
@@ -990,18 +980,16 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 
 	/*
-	 * Since we have a deferred timer, it will not fire unless
-	 * we are in C0.  So, determine if the actual elapsed time
-	 * is significantly greater (3x) than our sample interval.  If it
-	 * is, then we were idle for a long enough period of time
-	 * to adjust our busyness.
+	 * Since our utilization update callback will not run unless we are
+	 * in C0, check if the actual elapsed time is significantly greater (3x)
+	 * than our sample interval.  If it is, then we were idle for a long
+	 * enough period of time to adjust our busyness.
 	 */
-	sample_time = pid_params.sample_rate_ms  * USEC_PER_MSEC;
-	duration_us = ktime_us_delta(cpu->sample.time,
-				     cpu->last_sample_time);
-	if (duration_us > sample_time * 3) {
-		sample_ratio = div_fp(int_tofp(sample_time),
-				      int_tofp(duration_us));
+	duration_ns = cpu->sample.time - cpu->last_sample_time;
+	if ((s64)duration_ns > pid_params.sample_rate_ns * 3
+	    && cpu->last_sample_time > 0) {
+		sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
+				      int_tofp(duration_ns));
 		core_busy = mul_fp(core_busy, sample_ratio);
 	}
 
@@ -1028,26 +1016,21 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 		sample->mperf,
 		sample->aperf,
 		sample->tsc,
-		sample->freq);
+		get_avg_frequency(cpu));
 }
 
-static void intel_hwp_timer_func(unsigned long __data)
+static void intel_pstate_update_util(struct update_util_data *data, u64 time,
+				     unsigned long util, unsigned long max)
 {
-	struct cpudata *cpu = (struct cpudata *) __data;
+	struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+	u64 delta_ns = time - cpu->sample.time;
 
-	intel_pstate_sample(cpu);
-	intel_hwp_set_sample_time(cpu);
-}
+	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
+		bool sample_taken = intel_pstate_sample(cpu, time);
 
-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);
-
-	intel_pstate_set_sample_time(cpu);
+		if (sample_taken && !hwp_active)
+			intel_pstate_adjust_busy_pstate(cpu);
+	}
 }
 
 #define ICPU(model, policy) \
@@ -1095,24 +1078,19 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	cpu->cpu = cpunum;
 
-	if (hwp_active)
+	if (hwp_active) {
 		intel_pstate_hwp_enable(cpu);
+		pid_params.sample_rate_ms = 50;
+		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
+	}
 
 	intel_pstate_get_cpu_pstates(cpu);
 
-	init_timer_deferrable(&cpu->timer);
-	cpu->timer.data = (unsigned long)cpu;
-	cpu->timer.expires = jiffies + HZ/100;
-
-	if (!hwp_active)
-		cpu->timer.function = intel_pstate_timer_func;
-	else
-		cpu->timer.function = intel_hwp_timer_func;
-
 	intel_pstate_busy_pid_reset(cpu);
-	intel_pstate_sample(cpu);
+	intel_pstate_sample(cpu, 0);
 
-	add_timer_on(&cpu->timer, cpunum);
+	cpu->update_util.func = intel_pstate_update_util;
+	cpufreq_set_update_util_data(cpunum, &cpu->update_util);
 
 	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
@@ -1128,7 +1106,7 @@ static unsigned int intel_pstate_get(unsigned int cpu_num)
 	if (!cpu)
 		return 0;
 	sample = &cpu->sample;
-	return sample->freq;
+	return get_avg_frequency(cpu);
 }
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
@@ -1141,7 +1119,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		pr_debug("intel_pstate: set performance\n");
 		limits = &performance_limits;
 		if (hwp_active)
-			intel_pstate_hwp_set();
+			intel_pstate_hwp_set(policy->cpus);
 		return 0;
 	}
 
@@ -1173,7 +1151,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 				  int_tofp(100));
 
 	if (hwp_active)
-		intel_pstate_hwp_set();
+		intel_pstate_hwp_set(policy->cpus);
 
 	return 0;
 }
@@ -1196,7 +1174,9 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 
 	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
 
-	del_timer_sync(&all_cpu_data[cpu_num]->timer);
+	cpufreq_set_update_util_data(cpu_num, NULL);
+	synchronize_sched();
+
 	if (hwp_active)
 		return;
 
@@ -1260,6 +1240,7 @@ static int intel_pstate_msrs_not_valid(void)
 static void copy_pid_params(struct pstate_adjust_policy *policy)
 {
 	pid_params.sample_rate_ms = policy->sample_rate_ms;
+	pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
 	pid_params.p_gain_pct = policy->p_gain_pct;
 	pid_params.i_gain_pct = policy->i_gain_pct;
 	pid_params.d_gain_pct = policy->d_gain_pct;
@@ -1397,6 +1378,11 @@ static inline bool intel_pstate_platform_pwr_mgmt_exists(void) { return false; }
 static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
 #endif /* CONFIG_ACPI */
 
+static const struct x86_cpu_id hwp_support_ids[] __initconst = {
+	{ X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_HWP },
+	{}
+};
+
 static int __init intel_pstate_init(void)
 {
 	int cpu, rc = 0;
@@ -1406,17 +1392,16 @@ static int __init intel_pstate_init(void)
 	if (no_load)
 		return -ENODEV;
 
+	if (x86_match_cpu(hwp_support_ids) && !no_hwp) {
+		copy_cpu_funcs(&core_params.funcs);
+		hwp_active++;
+		goto hwp_cpu_matched;
+	}
+
 	id = x86_match_cpu(intel_pstate_cpu_ids);
 	if (!id)
 		return -ENODEV;
 
-	/*
-	 * The Intel pstate driver will be ignored if the platform
-	 * firmware has its own power management modes.
-	 */
-	if (intel_pstate_platform_pwr_mgmt_exists())
-		return -ENODEV;
-
 	cpu_def = (struct cpu_defaults *)id->driver_data;
 
 	copy_pid_params(&cpu_def->pid_policy);
@@ -1425,17 +1410,20 @@ static int __init intel_pstate_init(void)
 	if (intel_pstate_msrs_not_valid())
 		return -ENODEV;
 
+hwp_cpu_matched:
+	/*
+	 * The Intel pstate driver will be ignored if the platform
+	 * firmware has its own power management modes.
+	 */
+	if (intel_pstate_platform_pwr_mgmt_exists())
+		return -ENODEV;
+
 	pr_info("Intel P-state driver initializing.\n");
 
 	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
 		return -ENOMEM;
 
-	if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) {
-		pr_info("intel_pstate: HWP enabled\n");
-		hwp_active++;
-	}
-
 	if (!hwp_active && hwp_only)
 		goto out;
 
@@ -1446,12 +1434,16 @@ static int __init intel_pstate_init(void)
 	intel_pstate_debug_expose_params();
 	intel_pstate_sysfs_expose_params();
 
+	if (hwp_active)
+		pr_info("intel_pstate: HWP enabled\n");
+
 	return rc;
 out:
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		if (all_cpu_data[cpu]) {
-			del_timer_sync(&all_cpu_data[cpu]->timer);
+			cpufreq_set_update_util_data(cpu, NULL);
+			synchronize_sched();
 			kfree(all_cpu_data[cpu]);
 		}
 	}

drivers/cpufreq/powernv-cpufreq.c

@@ -28,6 +28,8 @@
 #include <linux/of.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
+#include <trace/events/power.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
@@ -42,13 +44,24 @@
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
 static bool rebooting, throttled, occ_reset;
+static unsigned int *core_to_chip_map;
+
+static const char * const throttle_reason[] = {
+	"No throttling",
+	"Power Cap",
+	"Processor Over Temperature",
+	"Power Supply Failure",
+	"Over Current",
+	"OCC Reset"
+};
 
 static struct chip {
 	unsigned int id;
 	bool throttled;
+	bool restore;
+	u8 throttle_reason;
 	cpumask_t mask;
 	struct work_struct throttle;
-	bool restore;
 } *chips;
 
 static int nr_chips;
@@ -312,13 +325,14 @@ static inline unsigned int get_nominal_index(void)
 static void powernv_cpufreq_throttle_check(void *data)
 {
 	unsigned int cpu = smp_processor_id();
+	unsigned int chip_id = core_to_chip_map[cpu_core_index_of_thread(cpu)];
 	unsigned long pmsr;
 	int pmsr_pmax, i;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 
 	for (i = 0; i < nr_chips; i++)
-		if (chips[i].id == cpu_to_chip_id(cpu))
+		if (chips[i].id == chip_id)
 			break;
 
 	/* Check for Pmax Capping */
@@ -328,17 +342,17 @@ static void powernv_cpufreq_throttle_check(void *data)
 			goto next;
 		chips[i].throttled = true;
 		if (pmsr_pmax < powernv_pstate_info.nominal)
-			pr_crit("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
-				cpu, chips[i].id, pmsr_pmax,
-				powernv_pstate_info.nominal);
-		else
-			pr_info("CPU %d on Chip %u has Pmax reduced below turbo frequency (%d < %d)\n",
-				cpu, chips[i].id, pmsr_pmax,
-				powernv_pstate_info.max);
+			pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
+				     cpu, chips[i].id, pmsr_pmax,
+				     powernv_pstate_info.nominal);
+		trace_powernv_throttle(chips[i].id,
+				      throttle_reason[chips[i].throttle_reason],
+				      pmsr_pmax);
 	} else if (chips[i].throttled) {
 		chips[i].throttled = false;
-		pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu,
-			chips[i].id, pmsr_pmax);
+		trace_powernv_throttle(chips[i].id,
+				      throttle_reason[chips[i].throttle_reason],
+				      pmsr_pmax);
 	}
 
 	/* Check if Psafe_mode_active is set in PMSR. */
@@ -356,7 +370,7 @@ static void powernv_cpufreq_throttle_check(void *data)
 
 	if (throttled) {
 		pr_info("PMSR = %16lx\n", pmsr);
-		pr_crit("CPU Frequency could be throttled\n");
+		pr_warn("CPU Frequency could be throttled\n");
 	}
 }
 
@@ -423,18 +437,19 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 {
 	struct chip *chip = container_of(work, struct chip, throttle);
 	unsigned int cpu;
-	cpumask_var_t mask;
+	cpumask_t mask;
 
-	smp_call_function_any(&chip->mask,
+	get_online_cpus();
+	cpumask_and(&mask, &chip->mask, cpu_online_mask);
+	smp_call_function_any(&mask,
 			      powernv_cpufreq_throttle_check, NULL, 0);
 
 	if (!chip->restore)
-		return;
+		goto out;
 
 	chip->restore = false;
-	cpumask_copy(mask, &chip->mask);
-	for_each_cpu_and(cpu, mask, cpu_online_mask) {
-		int index, tcpu;
+	for_each_cpu(cpu, &mask) {
+		int index;
 		struct cpufreq_policy policy;
 
 		cpufreq_get_policy(&policy, cpu);
@@ -442,20 +457,12 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 					       policy.cur,
 					       CPUFREQ_RELATION_C, &index);
 		powernv_cpufreq_target_index(&policy, index);
-		for_each_cpu(tcpu, policy.cpus)
-			cpumask_clear_cpu(tcpu, mask);
+		cpumask_andnot(&mask, &mask, policy.cpus);
 	}
+out:
+	put_online_cpus();
 }
 
-static char throttle_reason[][30] = {
-					"No throttling",
-					"Power Cap",
-					"Processor Over Temperature",
-					"Power Supply Failure",
-					"Over Current",
-					"OCC Reset"
-				     };
-
 static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 				   unsigned long msg_type, void *_msg)
 {
@@ -481,7 +488,7 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 		 */
 		if (!throttled) {
 			throttled = true;
-			pr_crit("CPU frequency is throttled for duration\n");
+			pr_warn("CPU frequency is throttled for duration\n");
 		}
 
 		break;
@@ -505,23 +512,18 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 			return 0;
 		}
 
-		if (omsg.throttle_status &&
+		for (i = 0; i < nr_chips; i++)
+			if (chips[i].id == omsg.chip)
+				break;
+
+		if (omsg.throttle_status >= 0 &&
 		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS)
-			pr_info("OCC: Chip %u Pmax reduced due to %s\n",
-				(unsigned int)omsg.chip,
-				throttle_reason[omsg.throttle_status]);
-		else if (!omsg.throttle_status)
-			pr_info("OCC: Chip %u %s\n", (unsigned int)omsg.chip,
-				throttle_reason[omsg.throttle_status]);
-		else
-			return 0;
+			chips[i].throttle_reason = omsg.throttle_status;
 
-		for (i = 0; i < nr_chips; i++)
-			if (chips[i].id == omsg.chip) {
-				if (!omsg.throttle_status)
-					chips[i].restore = true;
-				schedule_work(&chips[i].throttle);
-			}
+		if (!omsg.throttle_status)
+			chips[i].restore = true;
+
+		schedule_work(&chips[i].throttle);
 	}
 	return 0;
 }
@@ -556,29 +558,54 @@ static int init_chip_info(void)
 	unsigned int chip[256];
 	unsigned int cpu, i;
 	unsigned int prev_chip_id = UINT_MAX;
+	cpumask_t cpu_mask;
+	int ret = -ENOMEM;
+
+	core_to_chip_map = kcalloc(cpu_nr_cores(), sizeof(unsigned int),
+				   GFP_KERNEL);
+	if (!core_to_chip_map)
+		goto out;
 
-	for_each_possible_cpu(cpu) {
+	cpumask_copy(&cpu_mask, cpu_possible_mask);
+	for_each_cpu(cpu, &cpu_mask) {
 		unsigned int id = cpu_to_chip_id(cpu);
 
 		if (prev_chip_id != id) {
 			prev_chip_id = id;
 			chip[nr_chips++] = id;
 		}
+		core_to_chip_map[cpu_core_index_of_thread(cpu)] = id;
+		cpumask_andnot(&cpu_mask, &cpu_mask, cpu_sibling_mask(cpu));
 	}
 
-	chips = kmalloc_array(nr_chips, sizeof(struct chip), GFP_KERNEL);
+	chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
 	if (!chips)
-		return -ENOMEM;
+		goto free_chip_map;
 
 	for (i = 0; i < nr_chips; i++) {
 		chips[i].id = chip[i];
-		chips[i].throttled = false;
 		cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
 		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
-		chips[i].restore = false;
 	}
 
 	return 0;
+free_chip_map:
+	kfree(core_to_chip_map);
+out:
+	return ret;
+}
+
+static inline void clean_chip_info(void)
+{
+	kfree(chips);
+	kfree(core_to_chip_map);
+}
+
+static inline void unregister_all_notifiers(void)
+{
+	opal_message_notifier_unregister(OPAL_MSG_OCC,
+					 &powernv_cpufreq_opal_nb);
+	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
 }
 
 static int __init powernv_cpufreq_init(void)
@@ -591,28 +618,35 @@ static int __init powernv_cpufreq_init(void)
 
 	/* Discover pstates from device tree and init */
 	rc = init_powernv_pstates();
-	if (rc) {
-		pr_info("powernv-cpufreq disabled. System does not support PState control\n");
-		return rc;
-	}
+	if (rc)
+		goto out;
 
 	/* Populate chip info */
 	rc = init_chip_info();
 	if (rc)
-		return rc;
+		goto out;
 
 	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
-	return cpufreq_register_driver(&powernv_cpufreq_driver);
+
+	rc = cpufreq_register_driver(&powernv_cpufreq_driver);
+	if (!rc)
+		return 0;
+
+	pr_info("Failed to register the cpufreq driver (%d)\n", rc);
+	unregister_all_notifiers();
+	clean_chip_info();
+out:
+	pr_info("Platform driver disabled. System does not support PState control\n");
+	return rc;
 }
 module_init(powernv_cpufreq_init);
 
 static void __exit powernv_cpufreq_exit(void)
 {
-	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
-	opal_message_notifier_unregister(OPAL_MSG_OCC,
-					 &powernv_cpufreq_opal_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
+	unregister_all_notifiers();
+	clean_chip_info();
 }
 module_exit(powernv_cpufreq_exit);
 

include/linux/cpufreq.h

@@ -80,7 +80,6 @@ struct cpufreq_policy {
 	unsigned int		last_policy; /* policy before unplug */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
-	bool			governor_enabled; /* governor start/stop flag */
 	char			last_governor[CPUFREQ_NAME_LEN]; /* last governor used */
 
 	struct work_struct	update; /* if update_policy() needs to be
@@ -100,10 +99,6 @@ struct cpufreq_policy {
 	 * - Any routine that will write to the policy structure and/or may take away
 	 *   the policy altogether (eg. CPU hotplug), will hold this lock in write
 	 *   mode before doing so.
-	 *
-	 * Additional rules:
-	 * - Lock should not be held across
-	 *     __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
 	 */
 	struct rw_semaphore	rwsem;
 
@@ -464,29 +459,8 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 int cpufreq_register_governor(struct cpufreq_governor *governor);
 void cpufreq_unregister_governor(struct cpufreq_governor *governor);
 
-/* CPUFREQ DEFAULT GOVERNOR */
-/*
- * Performance governor is fallback governor if any other gov failed to auto
- * load due latency restrictions
- */
-#ifdef CONFIG_CPU_FREQ_GOV_PERFORMANCE
-extern struct cpufreq_governor cpufreq_gov_performance;
-#endif
-#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_performance)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
-extern struct cpufreq_governor cpufreq_gov_powersave;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_powersave)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE)
-extern struct cpufreq_governor cpufreq_gov_userspace;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_userspace)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND)
-extern struct cpufreq_governor cpufreq_gov_ondemand;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_ondemand)
-#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
-extern struct cpufreq_governor cpufreq_gov_conservative;
-#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_conservative)
-#endif
+struct cpufreq_governor *cpufreq_default_governor(void);
+struct cpufreq_governor *cpufreq_fallback_governor(void);
 
 /*********************************************************************
  *                     FREQUENCY TABLE HELPERS                       *
@@ -525,16 +499,6 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev,
 }
 #endif
 
-static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
-{
-	while ((*pos)->frequency != CPUFREQ_TABLE_END)
-		if ((*pos)->frequency != CPUFREQ_ENTRY_INVALID)
-			return true;
-		else
-			(*pos)++;
-	return false;
-}
-
 /*
  * cpufreq_for_each_entry -	iterate over a cpufreq_frequency_table
  * @pos:	the cpufreq_frequency_table * to use as a loop cursor.
@@ -551,8 +515,11 @@ static inline bool cpufreq_next_valid(struct cpufreq_frequency_table **pos)
  * @table:      the cpufreq_frequency_table * to iterate over.
  */
 
-#define cpufreq_for_each_valid_entry(pos, table)	\
-	for (pos = table; cpufreq_next_valid(&pos); pos++)
+#define cpufreq_for_each_valid_entry(pos, table)			\
+	for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++)	\
+		if (pos->frequency == CPUFREQ_ENTRY_INVALID)		\
+			continue;					\
+		else
 
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table);

include/linux/sched.h

@@ -3207,4 +3207,13 @@ static inline unsigned long rlimit_max(unsigned int limit)
 	return task_rlimit_max(current, limit);
 }
 
+#ifdef CONFIG_CPU_FREQ
+struct update_util_data {
+	void (*func)(struct update_util_data *data,
+		     u64 time, unsigned long util, unsigned long max);
+};
+
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data);
+#endif /* CONFIG_CPU_FREQ */
+
 #endif

include/trace/events/power.h

@@ -38,6 +38,28 @@ DEFINE_EVENT(cpu, cpu_idle,
 	TP_ARGS(state, cpu_id)
 );
 
+TRACE_EVENT(powernv_throttle,
+
+	TP_PROTO(int chip_id, const char *reason, int pmax),
+
+	TP_ARGS(chip_id, reason, pmax),
+
+	TP_STRUCT__entry(
+		__field(int, chip_id)
+		__string(reason, reason)
+		__field(int, pmax)
+	),
+
+	TP_fast_assign(
+		__entry->chip_id = chip_id;
+		__assign_str(reason, reason);
+		__entry->pmax = pmax;
+	),
+
+	TP_printk("Chip %d Pmax %d %s", __entry->chip_id,
+		  __entry->pmax, __get_str(reason))
+);
+
 TRACE_EVENT(pstate_sample,
 
 	TP_PROTO(u32 core_busy,

kernel/sched/Makefile

@@ -19,3 +19,4 @@ obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+obj-$(CONFIG_CPU_FREQ) += cpufreq.o

kernel/sched/cpufreq.c

+/*
+ * Scheduler code and data structures related to cpufreq.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.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.
+ */
+
+#include "sched.h"
+
+DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_set_update_util_data - Populate the CPU's update_util_data pointer.
+ * @cpu: The CPU to set the pointer for.
+ * @data: New pointer value.
+ *
+ * Set and publish the update_util_data pointer for the given CPU.  That pointer
+ * points to a struct update_util_data object containing a callback function
+ * to call from cpufreq_update_util().  That function will be called from an RCU
+ * read-side critical section, so it must not sleep.
+ *
+ * Callers must use RCU-sched callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * right after this function to avoid use-after-free.
+ */
+void cpufreq_set_update_util_data(int cpu, struct update_util_data *data)
+{
+	if (WARN_ON(data && !data->func))
+		return;
+
+	rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
+}
+EXPORT_SYMBOL_GPL(cpufreq_set_update_util_data);

kernel/sched/deadline.c

@@ -726,6 +726,10 @@ static void update_curr_dl(struct rq *rq)
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	/*
 	 * Consumed budget is computed considering the time as
 	 * observed by schedulable tasks (excluding time spent

kernel/sched/fair.c

@@ -2824,7 +2824,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 now = cfs_rq_clock_task(cfs_rq);
-	int cpu = cpu_of(rq_of(cfs_rq));
+	struct rq *rq = rq_of(cfs_rq);
+	int cpu = cpu_of(rq);
 
 	/*
 	 * Track task load average for carrying it to new CPU after migrated, and
@@ -2836,6 +2837,29 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 
 	if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
 		update_tg_load_avg(cfs_rq, 0);
+
+	if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) {
+		unsigned long max = rq->cpu_capacity_orig;
+
+		/*
+		 * There are a few boundary cases this might miss but it should
+		 * get called often enough that that should (hopefully) not be
+		 * a real problem -- added to that it only calls on the local
+		 * CPU, so if we enqueue remotely we'll miss an update, but
+		 * the next tick/schedule should update.
+		 *
+		 * It will not get called when we go idle, because the idle
+		 * thread is a different class (!fair), nor will the utilization
+		 * number include things like RT tasks.
+		 *
+		 * As is, the util number is not freq-invariant (we'd have to
+		 * implement arch_scale_freq_capacity() for that).
+		 *
+		 * See cpu_util().
+		 */
+		cpufreq_update_util(rq_clock(rq),
+				    min(cfs_rq->avg.util_avg, max), max);
+	}
 }
 
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)

kernel/sched/rt.c

@@ -945,6 +945,10 @@ static void update_curr_rt(struct rq *rq)
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
+	/* Kick cpufreq (see the comment in linux/cpufreq.h). */
+	if (cpu_of(rq) == smp_processor_id())
+		cpufreq_trigger_update(rq_clock(rq));
+
 	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
 	if (unlikely((s64)delta_exec <= 0))
 		return;

kernel/sched/sched.h

@@ -1738,3 +1738,51 @@ static inline u64 irq_time_read(int cpu)
 }
 #endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @time: Current time.
+ * @util: Current utilization.
+ * @max: Utilization ceiling.
+ *
+ * This function is called by the scheduler on every invocation of
+ * update_load_avg() on the CPU whose utilization is being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ */
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max)
+{
+       struct update_util_data *data;
+
+       data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+       if (data)
+               data->func(data, time, util, max);
+}
+
+/**
+ * cpufreq_trigger_update - Trigger CPU performance state evaluation if needed.
+ * @time: Current time.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid.  Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_trigger_update(u64 time)
+{
+	cpufreq_update_util(time, ULONG_MAX, 0);
+}
+#else
+static inline void cpufreq_update_util(u64 time, unsigned long util, unsigned long max) {}
+static inline void cpufreq_trigger_update(u64 time) {}
+#endif /* CONFIG_CPU_FREQ */

kernel/trace/power-traces.c

@@ -15,4 +15,5 @@
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
 EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);