Merge branch 'pm-cpufreq'

* pm-cpufreq: (30 commits)
  Documentation: cpufreq: intel_pstate: enhance documentation
  cpufreq-dt: fix handling regulator_get_voltage() result
  cpufreq: governor: Fix negative idle_time when configured with CONFIG_HZ_PERIODIC
  cpufreq: mt8173: migrate to use operating-points-v2 bindings
  cpufreq: Simplify core code related to boost support
  cpufreq: acpi-cpufreq: Simplify boost-related code
  cpufreq: Make cpufreq_boost_supported() static
  blackfin-cpufreq: Mark cpu_set_cclk() as static
  blackfin-cpufreq: Change return type of cpu_set_cclk() to that of clk_set_rate()
  dt: cpufreq: st: Provide bindings for ST's CPUFreq implementation
  cpufreq: st: Provide runtime initialised driver for ST's platforms
  cpufreq: mt8173: Move resources allocation into ->probe()
  cpufreq: intel_pstate: Account for IO wait time
  cpufreq: intel_pstate: Account for non C0 time
  cpufreq: intel_pstate: Configurable algorithm to get target pstate
  cpufreq: mt8173: check return value of regulator_get_voltage() call
  cpufreq: mt8173: remove redundant regulator_get_voltage() call
  cpufreq: mt8173: add CPUFREQ_HAVE_GOVERNOR_PER_POLICY flag
  cpufreq: qoriq: Register cooling device based on device tree
  cpufreq: pcc-cpufreq: update default value of cpuinfo_transition_latency
  ...

Documentation/cpu-freq/pcc-cpufreq.txt

@@ -159,8 +159,8 @@ to be strictly associated with a P-state.
 
 2.2 cpuinfo_transition_latency:
 -------------------------------
-The cpuinfo_transition_latency field is 0. The PCC specification does
-not include a field to expose this value currently.
+The cpuinfo_transition_latency field is CPUFREQ_ETERNAL. The PCC specification
+does not include a field to expose this value currently.
 
 2.3 cpuinfo_cur_freq:
 ---------------------

Documentation/devicetree/bindings/arm/cpus.txt

@@ -242,6 +242,23 @@ nodes to be present and contain the properties described below.
 		Definition: Specifies the syscon node controlling the cpu core
 			    power domains.
 
+	- dynamic-power-coefficient
+		Usage: optional
+		Value type: <prop-encoded-array>
+		Definition: A u32 value that represents the running time dynamic
+			    power coefficient in units of mW/MHz/uVolt^2. The
+			    coefficient can either be calculated from power
+			    measurements or derived by analysis.
+
+			    The dynamic power consumption of the CPU  is
+			    proportional to the square of the Voltage (V) and
+			    the clock frequency (f). The coefficient is used to
+			    calculate the dynamic power as below -
+
+			    Pdyn = dynamic-power-coefficient * V^2 * f
+
+			    where voltage is in uV, frequency is in MHz.
+
 Example 1 (dual-cluster big.LITTLE system 32-bit):
 
 	cpus {

Documentation/devicetree/bindings/cpufreq/cpufreq-st.txt

+Binding for ST's CPUFreq driver
+===============================
+
+ST's CPUFreq driver attempts to read 'process' and 'version' attributes
+from the SoC, then supplies the OPP framework with 'prop' and 'supported
+hardware' information respectively.  The framework is then able to read
+the DT and operate in the usual way.
+
+For more information about the expected DT format [See: ../opp/opp.txt].
+
+Frequency Scaling only
+----------------------
+
+No vendor specific driver required for this.
+
+Located in CPU's node:
+
+- operating-points		: [See: ../power/opp.txt]
+
+Example [safe]
+--------------
+
+cpus {
+	cpu@0 {
+				 /* kHz     uV   */
+		operating-points = <1500000 0
+				    1200000 0
+				    800000  0
+				    500000  0>;
+	};
+};
+
+Dynamic Voltage and Frequency Scaling (DVFS)
+--------------------------------------------
+
+This requires the ST CPUFreq driver to supply 'process' and 'version' info.
+
+Located in CPU's node:
+
+- operating-points-v2		: [See ../power/opp.txt]
+
+Example [unsafe]
+----------------
+
+cpus {
+	cpu@0 {
+		operating-points-v2	= <&cpu0_opp_table>;
+	};
+};
+
+cpu0_opp_table: opp_table {
+	compatible = "operating-points-v2";
+
+	/* ############################################################### */
+	/* # WARNING: Do not attempt to copy/replicate these nodes,      # */
+	/* #          they are only to be supplied by the bootloader !!! # */
+	/* ############################################################### */
+	opp0 {
+		/*			   Major       Minor       Substrate */
+		/*			   2           all         all       */
+		opp-supported-hw	= <0x00000004  0xffffffff  0xffffffff>;
+		opp-hz			= /bits/ 64 <1500000000>;
+		clock-latency-ns	= <10000000>;
+
+		opp-microvolt-pcode0	= <1200000>;
+		opp-microvolt-pcode1	= <1200000>;
+		opp-microvolt-pcode2	= <1200000>;
+		opp-microvolt-pcode3	= <1200000>;
+		opp-microvolt-pcode4	= <1170000>;
+		opp-microvolt-pcode5	= <1140000>;
+		opp-microvolt-pcode6	= <1100000>;
+		opp-microvolt-pcode7	= <1070000>;
+	};
+
+	opp1 {
+		/*			   Major       Minor       Substrate */
+		/*			   all         all         all       */
+		opp-supported-hw	= <0xffffffff  0xffffffff  0xffffffff>;
+		opp-hz			= /bits/ 64 <1200000000>;
+		clock-latency-ns	= <10000000>;
+
+		opp-microvolt-pcode0	= <1110000>;
+		opp-microvolt-pcode1	= <1150000>;
+		opp-microvolt-pcode2	= <1100000>;
+		opp-microvolt-pcode3	= <1080000>;
+		opp-microvolt-pcode4	= <1040000>;
+		opp-microvolt-pcode5	= <1020000>;
+		opp-microvolt-pcode6	= <980000>;
+		opp-microvolt-pcode7	= <930000>;
+	};
+};

drivers/cpufreq/Kconfig.arm

@@ -6,6 +6,8 @@
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
 	depends on (ARM_CPU_TOPOLOGY || ARM64) && HAVE_CLK
+	# if CPU_THERMAL is on and THERMAL=m, ARM_BIT_LITTLE_CPUFREQ cannot be =y
+	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -217,6 +219,16 @@ config ARM_SPEAR_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
 
+config ARM_STI_CPUFREQ
+	tristate "STi CPUFreq support"
+	depends on SOC_STIH407
+	help
+	  This driver uses the generic OPP framework to match the running
+	  platform with a predefined set of suitable values.  If not provided
+	  we will fall-back so safe-values contained in Device Tree.  Enable
+	  this config option if you wish to add CPUFreq support for STi based
+	  SoCs.
+
 config ARM_TEGRA20_CPUFREQ
 	bool "Tegra20 CPUFreq support"
 	depends on ARCH_TEGRA

drivers/cpufreq/Makefile

@@ -73,6 +73,7 @@ obj-$(CONFIG_ARM_SA1100_CPUFREQ)	+= sa1100-cpufreq.o
 obj-$(CONFIG_ARM_SA1110_CPUFREQ)	+= sa1110-cpufreq.o
 obj-$(CONFIG_ARM_SCPI_CPUFREQ)		+= scpi-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
+obj-$(CONFIG_ARM_STI_CPUFREQ)		+= sti-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o

drivers/cpufreq/acpi-cpufreq.c

@@ -135,7 +135,7 @@ static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
 	wrmsr_on_cpus(cpumask, msr_addr, msrs);
 }
 
-static int _store_boost(int val)
+static int set_boost(int val)
 {
 	get_online_cpus();
 	boost_set_msrs(val, cpu_online_mask);
@@ -158,29 +158,24 @@ static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
 cpufreq_freq_attr_ro(freqdomain_cpus);
 
 #ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
-static ssize_t store_boost(const char *buf, size_t count)
+static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
+			 size_t count)
 {
 	int ret;
-	unsigned long val = 0;
+	unsigned int val = 0;
 
-	if (!acpi_cpufreq_driver.boost_supported)
+	if (!acpi_cpufreq_driver.set_boost)
 		return -EINVAL;
 
-	ret = kstrtoul(buf, 10, &val);
-	if (ret || (val > 1))
+	ret = kstrtouint(buf, 10, &val);
+	if (ret || val > 1)
 		return -EINVAL;
 
-	_store_boost((int) val);
+	set_boost(val);
 
 	return count;
 }
 
-static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
-			 size_t count)
-{
-	return store_boost(buf, count);
-}
-
 static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
 {
 	return sprintf(buf, "%u\n", acpi_cpufreq_driver.boost_enabled);
@@ -905,7 +900,6 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.resume		= acpi_cpufreq_resume,
 	.name		= "acpi-cpufreq",
 	.attr		= acpi_cpufreq_attr,
-	.set_boost      = _store_boost,
 };
 
 static void __init acpi_cpufreq_boost_init(void)
@@ -916,7 +910,7 @@ static void __init acpi_cpufreq_boost_init(void)
 		if (!msrs)
 			return;
 
-		acpi_cpufreq_driver.boost_supported = true;
+		acpi_cpufreq_driver.set_boost = set_boost;
 		acpi_cpufreq_driver.boost_enabled = boost_state(0);
 
 		cpu_notifier_register_begin();

drivers/cpufreq/arm_big_little.c

@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
+#include <linux/cpu_cooling.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -55,6 +56,7 @@ static bool bL_switching_enabled;
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
 #define VIRT_FREQ(cluster, freq)    ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
 
+static struct thermal_cooling_device *cdev[MAX_CLUSTERS];
 static struct cpufreq_arm_bL_ops *arm_bL_ops;
 static struct clk *clk[MAX_CLUSTERS];
 static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
@@ -493,6 +495,12 @@ static int bL_cpufreq_init(struct cpufreq_policy *policy)
 static int bL_cpufreq_exit(struct cpufreq_policy *policy)
 {
 	struct device *cpu_dev;
+	int cur_cluster = cpu_to_cluster(policy->cpu);
+
+	if (cur_cluster < MAX_CLUSTERS) {
+		cpufreq_cooling_unregister(cdev[cur_cluster]);
+		cdev[cur_cluster] = NULL;
+	}
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
@@ -507,6 +515,38 @@ static int bL_cpufreq_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
+static void bL_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	struct device *cpu_dev = get_cpu_device(policy->cpu);
+	int cur_cluster = cpu_to_cluster(policy->cpu);
+	struct device_node *np;
+
+	/* Do not register a cpu_cooling device if we are in IKS mode */
+	if (cur_cluster >= MAX_CLUSTERS)
+		return;
+
+	np = of_node_get(cpu_dev->of_node);
+	if (WARN_ON(!np))
+		return;
+
+	if (of_find_property(np, "#cooling-cells", NULL)) {
+		u32 power_coefficient = 0;
+
+		of_property_read_u32(np, "dynamic-power-coefficient",
+				     &power_coefficient);
+
+		cdev[cur_cluster] = of_cpufreq_power_cooling_register(np,
+				policy->related_cpus, power_coefficient, NULL);
+		if (IS_ERR(cdev[cur_cluster])) {
+			dev_err(cpu_dev,
+				"running cpufreq without cooling device: %ld\n",
+				PTR_ERR(cdev[cur_cluster]));
+			cdev[cur_cluster] = NULL;
+		}
+	}
+	of_node_put(np);
+}
+
 static struct cpufreq_driver bL_cpufreq_driver = {
 	.name			= "arm-big-little",
 	.flags			= CPUFREQ_STICKY |
@@ -517,6 +557,7 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.get			= bL_cpufreq_get_rate,
 	.init			= bL_cpufreq_init,
 	.exit			= bL_cpufreq_exit,
+	.ready			= bL_cpufreq_ready,
 	.attr			= cpufreq_generic_attr,
 };
 

drivers/cpufreq/blackfin-cpufreq.c

@@ -112,7 +112,7 @@ static unsigned int bfin_getfreq_khz(unsigned int cpu)
 }
 
 #ifdef CONFIG_BF60x
-unsigned long cpu_set_cclk(int cpu, unsigned long new)
+static int cpu_set_cclk(int cpu, unsigned long new)
 {
 	struct clk *clk;
 	int ret;

drivers/cpufreq/cpufreq-dt.c

@@ -50,7 +50,8 @@ static int set_target(struct cpufreq_policy *policy, unsigned int index)
 	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, volt_old = 0, tol = 0;
+	unsigned long volt = 0, tol = 0;
+	int volt_old = 0;
 	unsigned int old_freq, new_freq;
 	long freq_Hz, freq_exact;
 	int ret;
@@ -83,7 +84,7 @@ static int set_target(struct cpufreq_policy *policy, unsigned int index)
 			opp_freq / 1000, volt);
 	}
 
-	dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n",
+	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);
 
@@ -407,8 +408,13 @@ static void cpufreq_ready(struct cpufreq_policy *policy)
 	 * thermal DT code takes care of matching them.
 	 */
 	if (of_find_property(np, "#cooling-cells", NULL)) {
-		priv->cdev = of_cpufreq_cooling_register(np,
-							 policy->related_cpus);
+		u32 power_coefficient = 0;
+
+		of_property_read_u32(np, "dynamic-power-coefficient",
+				     &power_coefficient);
+
+		priv->cdev = of_cpufreq_power_cooling_register(np,
+				policy->related_cpus, power_coefficient, NULL);
 		if (IS_ERR(priv->cdev)) {
 			dev_err(priv->cpu_dev,
 				"running cpufreq without cooling device: %ld\n",

drivers/cpufreq/cpufreq.c

@@ -2330,29 +2330,15 @@ int cpufreq_boost_trigger_state(int state)
 	return ret;
 }
 
-int cpufreq_boost_supported(void)
+static bool cpufreq_boost_supported(void)
 {
-	if (likely(cpufreq_driver))
-		return cpufreq_driver->boost_supported;
-
-	return 0;
+	return likely(cpufreq_driver) && cpufreq_driver->set_boost;
 }
-EXPORT_SYMBOL_GPL(cpufreq_boost_supported);
 
 static int create_boost_sysfs_file(void)
 {
 	int ret;
 
-	if (!cpufreq_boost_supported())
-		return 0;
-
-	/*
-	 * Check if driver provides function to enable boost -
-	 * if not, use cpufreq_boost_set_sw as default
-	 */
-	if (!cpufreq_driver->set_boost)
-		cpufreq_driver->set_boost = cpufreq_boost_set_sw;
-
 	ret = sysfs_create_file(cpufreq_global_kobject, &boost.attr);
 	if (ret)
 		pr_err("%s: cannot register global BOOST sysfs file\n",
@@ -2375,7 +2361,7 @@ int cpufreq_enable_boost_support(void)
 	if (cpufreq_boost_supported())
 		return 0;
 
-	cpufreq_driver->boost_supported = true;
+	cpufreq_driver->set_boost = cpufreq_boost_set_sw;
 
 	/* This will get removed on driver unregister */
 	return create_boost_sysfs_file();
@@ -2435,9 +2421,11 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
-	ret = create_boost_sysfs_file();
-	if (ret)
-		goto err_null_driver;
+	if (cpufreq_boost_supported()) {
+		ret = create_boost_sysfs_file();
+		if (ret)
+			goto err_null_driver;
+	}
 
 	ret = subsys_interface_register(&cpufreq_interface);
 	if (ret)

drivers/cpufreq/cpufreq_conservative.c

@@ -115,13 +115,13 @@ static void cs_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static unsigned int cs_dbs_timer(struct cpu_dbs_info *cdbs,
-				 struct dbs_data *dbs_data, bool modify_all)
+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, cdbs->shared->policy->cpu);
+		dbs_check_cpu(dbs_data, policy->cpu);
 
 	return delay_for_sampling_rate(cs_tuners->sampling_rate);
 }

drivers/cpufreq/cpufreq_governor.c

@@ -84,6 +84,9 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 			(cur_wall_time - j_cdbs->prev_cpu_wall);
 		j_cdbs->prev_cpu_wall = cur_wall_time;
 
+		if (cur_idle_time < j_cdbs->prev_cpu_idle)
+			cur_idle_time = j_cdbs->prev_cpu_idle;
+
 		idle_time = (unsigned int)
 			(cur_idle_time - j_cdbs->prev_cpu_idle);
 		j_cdbs->prev_cpu_idle = cur_idle_time;
@@ -158,47 +161,55 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 }
 EXPORT_SYMBOL_GPL(dbs_check_cpu);
 
-static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
-		unsigned int delay)
+void gov_add_timers(struct cpufreq_policy *policy, unsigned int delay)
 {
-	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
-
-	mod_delayed_work_on(cpu, system_wq, &cdbs->dwork, delay);
-}
-
-void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
-		unsigned int delay, bool all_cpus)
-{
-	int i;
+	struct dbs_data *dbs_data = policy->governor_data;
+	struct cpu_dbs_info *cdbs;
+	int cpu;
 
-	if (!all_cpus) {
-		/*
-		 * Use raw_smp_processor_id() to avoid preemptible warnings.
-		 * We know that this is only called with all_cpus == false from
-		 * works that have been queued with *_work_on() functions and
-		 * those works are canceled during CPU_DOWN_PREPARE so they
-		 * can't possibly run on any other CPU.
-		 */
-		__gov_queue_work(raw_smp_processor_id(), dbs_data, delay);
-	} else {
-		for_each_cpu(i, policy->cpus)
-			__gov_queue_work(i, dbs_data, delay);
+	for_each_cpu(cpu, policy->cpus) {
+		cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+		cdbs->timer.expires = jiffies + delay;
+		add_timer_on(&cdbs->timer, cpu);
 	}
 }
-EXPORT_SYMBOL_GPL(gov_queue_work);
+EXPORT_SYMBOL_GPL(gov_add_timers);
 
-static inline void gov_cancel_work(struct dbs_data *dbs_data,
-		struct cpufreq_policy *policy)
+static inline void gov_cancel_timers(struct cpufreq_policy *policy)
 {
+	struct dbs_data *dbs_data = policy->governor_data;
 	struct cpu_dbs_info *cdbs;
 	int i;
 
 	for_each_cpu(i, policy->cpus) {
 		cdbs = dbs_data->cdata->get_cpu_cdbs(i);
-		cancel_delayed_work_sync(&cdbs->dwork);
+		del_timer_sync(&cdbs->timer);
 	}
 }
 
+void gov_cancel_work(struct cpu_common_dbs_info *shared)
+{
+	/* Tell dbs_timer_handler() to skip queuing up work items. */
+	atomic_inc(&shared->skip_work);
+	/*
+	 * If dbs_timer_handler() is already running, it may not notice the
+	 * incremented skip_work, so wait for it to complete to prevent its work
+	 * item from being queued up after the cancel_work_sync() below.
+	 */
+	gov_cancel_timers(shared->policy);
+	/*
+	 * In case dbs_timer_handler() managed to run and spawn a work item
+	 * before the timers have been canceled, wait for that work item to
+	 * complete and then cancel all of the timers set up by it.  If
+	 * dbs_timer_handler() runs again at that point, it will see the
+	 * positive value of skip_work and won't spawn any more work items.
+	 */
+	cancel_work_sync(&shared->work);
+	gov_cancel_timers(shared->policy);
+	atomic_set(&shared->skip_work, 0);
+}
+EXPORT_SYMBOL_GPL(gov_cancel_work);
+
 /* Will return if we need to evaluate cpu load again or not */
 static bool need_load_eval(struct cpu_common_dbs_info *shared,
 			   unsigned int sampling_rate)
@@ -217,29 +228,21 @@ static bool need_load_eval(struct cpu_common_dbs_info *shared,
 	return true;
 }
 
-static void dbs_timer(struct work_struct *work)
+static void dbs_work_handler(struct work_struct *work)
 {
-	struct cpu_dbs_info *cdbs = container_of(work, struct cpu_dbs_info,
-						 dwork.work);
-	struct cpu_common_dbs_info *shared = cdbs->shared;
+	struct cpu_common_dbs_info *shared = container_of(work, struct
+					cpu_common_dbs_info, work);
 	struct cpufreq_policy *policy;
 	struct dbs_data *dbs_data;
 	unsigned int sampling_rate, delay;
-	bool modify_all = true;
-
-	mutex_lock(&shared->timer_mutex);
+	bool eval_load;
 
 	policy = shared->policy;
-
-	/*
-	 * Governor might already be disabled and there is no point continuing
-	 * with the work-handler.
-	 */
-	if (!policy)
-		goto unlock;
-
 	dbs_data = policy->governor_data;
 
+	/* Kill all timers */
+	gov_cancel_timers(policy);
+
 	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
 		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 
@@ -250,14 +253,37 @@ static void dbs_timer(struct work_struct *work)
 		sampling_rate = od_tuners->sampling_rate;
 	}
 
-	if (!need_load_eval(cdbs->shared, sampling_rate))
-		modify_all = false;
-
-	delay = dbs_data->cdata->gov_dbs_timer(cdbs, dbs_data, modify_all);
-	gov_queue_work(dbs_data, policy, delay, modify_all);
+	eval_load = need_load_eval(shared, sampling_rate);
 
-unlock:
+	/*
+	 * Make sure cpufreq_governor_limits() isn't evaluating load in
+	 * parallel.
+	 */
+	mutex_lock(&shared->timer_mutex);
+	delay = dbs_data->cdata->gov_dbs_timer(policy, eval_load);
 	mutex_unlock(&shared->timer_mutex);
+
+	atomic_dec(&shared->skip_work);
+
+	gov_add_timers(policy, delay);
+}
+
+static void dbs_timer_handler(unsigned long data)
+{
+	struct cpu_dbs_info *cdbs = (struct cpu_dbs_info *)data;
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+
+	/*
+	 * Timer handler may not be allowed to queue the work at the moment,
+	 * because:
+	 * - Another timer handler has done that
+	 * - We are stopping the governor
+	 * - Or we are updating the sampling rate of the ondemand governor
+	 */
+	if (atomic_inc_return(&shared->skip_work) > 1)
+		atomic_dec(&shared->skip_work);
+	else
+		queue_work(system_wq, &shared->work);
 }
 
 static void set_sampling_rate(struct dbs_data *dbs_data,
@@ -287,6 +313,9 @@ static int alloc_common_dbs_info(struct cpufreq_policy *policy,
 	for_each_cpu(j, policy->related_cpus)
 		cdata->get_cpu_cdbs(j)->shared = shared;
 
+	mutex_init(&shared->timer_mutex);
+	atomic_set(&shared->skip_work, 0);
+	INIT_WORK(&shared->work, dbs_work_handler);
 	return 0;
 }
 
@@ -297,6 +326,8 @@ static void free_common_dbs_info(struct cpufreq_policy *policy,
 	struct cpu_common_dbs_info *shared = cdbs->shared;
 	int j;
 
+	mutex_destroy(&shared->timer_mutex);
+
 	for_each_cpu(j, policy->cpus)
 		cdata->get_cpu_cdbs(j)->shared = NULL;
 
@@ -433,7 +464,6 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 
 	shared->policy = policy;
 	shared->time_stamp = ktime_get();
-	mutex_init(&shared->timer_mutex);
 
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_info *j_cdbs = cdata->get_cpu_cdbs(j);
@@ -450,7 +480,9 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 		if (ignore_nice)
 			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-		INIT_DEFERRABLE_WORK(&j_cdbs->dwork, dbs_timer);
+		__setup_timer(&j_cdbs->timer, dbs_timer_handler,
+			      (unsigned long)j_cdbs,
+			      TIMER_DEFERRABLE | TIMER_IRQSAFE);
 	}
 
 	if (cdata->governor == GOV_CONSERVATIVE) {
@@ -468,8 +500,7 @@ static int cpufreq_governor_start(struct cpufreq_policy *policy,
 		od_ops->powersave_bias_init_cpu(cpu);
 	}
 
-	gov_queue_work(dbs_data, policy, delay_for_sampling_rate(sampling_rate),
-		       true);
+	gov_add_timers(policy, delay_for_sampling_rate(sampling_rate));
 	return 0;
 }
 
@@ -483,18 +514,9 @@ static int cpufreq_governor_stop(struct cpufreq_policy *policy,
 	if (!shared || !shared->policy)
 		return -EBUSY;
 
-	/*
-	 * Work-handler must see this updated, as it should not proceed any
-	 * further after governor is disabled. And so timer_mutex is taken while
-	 * updating this value.
-	 */
-	mutex_lock(&shared->timer_mutex);
+	gov_cancel_work(shared);
 	shared->policy = NULL;
-	mutex_unlock(&shared->timer_mutex);
-
-	gov_cancel_work(dbs_data, policy);
 
-	mutex_destroy(&shared->timer_mutex);
 	return 0;
 }
 

drivers/cpufreq/cpufreq_governor.h

@@ -17,6 +17,7 @@
 #ifndef _CPUFREQ_GOVERNOR_H
 #define _CPUFREQ_GOVERNOR_H
 
+#include <linux/atomic.h>
 #include <linux/cpufreq.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
@@ -132,12 +133,14 @@ static void *get_cpu_dbs_info_s(int cpu)				\
 struct cpu_common_dbs_info {
 	struct cpufreq_policy *policy;
 	/*
-	 * percpu mutex that serializes governor limit change with dbs_timer
-	 * invocation. We do not want dbs_timer to run when user is changing
-	 * the governor or limits.
+	 * Per policy mutex that serializes load evaluation from limit-change
+	 * and work-handler.
 	 */
 	struct mutex timer_mutex;
+
 	ktime_t time_stamp;
+	atomic_t skip_work;
+	struct work_struct work;
 };
 
 /* Per cpu structures */
@@ -152,7 +155,7 @@ struct cpu_dbs_info {
 	 * wake-up from idle.
 	 */
 	unsigned int prev_load;
-	struct delayed_work dwork;
+	struct timer_list timer;
 	struct cpu_common_dbs_info *shared;
 };
 
@@ -209,8 +212,7 @@ struct common_dbs_data {
 
 	struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
 	void *(*get_cpu_dbs_info_s)(int cpu);
-	unsigned int (*gov_dbs_timer)(struct cpu_dbs_info *cdbs,
-				      struct dbs_data *dbs_data,
+	unsigned int (*gov_dbs_timer)(struct cpufreq_policy *policy,
 				      bool modify_all);
 	void (*gov_check_cpu)(int cpu, unsigned int load);
 	int (*init)(struct dbs_data *dbs_data, bool notify);
@@ -269,11 +271,11 @@ static ssize_t show_sampling_rate_min_gov_pol				\
 
 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);
-void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
-		unsigned int delay, bool all_cpus);
 void od_register_powersave_bias_handler(unsigned int (*f)
 		(struct cpufreq_policy *, unsigned int, unsigned int),
 		unsigned int powersave_bias);

drivers/cpufreq/cpufreq_ondemand.c

@@ -191,10 +191,9 @@ static void od_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static unsigned int od_dbs_timer(struct cpu_dbs_info *cdbs,
-				 struct dbs_data *dbs_data, bool modify_all)
+static unsigned int od_dbs_timer(struct cpufreq_policy *policy, bool modify_all)
 {
-	struct cpufreq_policy *policy = cdbs->shared->policy;
+	struct dbs_data *dbs_data = policy->governor_data;
 	unsigned int cpu = policy->cpu;
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
 			cpu);
@@ -247,40 +246,66 @@ static void update_sampling_rate(struct dbs_data *dbs_data,
 		unsigned int new_rate)
 {
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cpumask cpumask;
 	int cpu;
 
 	od_tuners->sampling_rate = new_rate = max(new_rate,
 			dbs_data->min_sampling_rate);
 
-	for_each_online_cpu(cpu) {
+	/*
+	 * Lock governor so that governor start/stop can't execute in parallel.
+	 */
+	mutex_lock(&od_dbs_cdata.mutex);
+
+	cpumask_copy(&cpumask, cpu_online_mask);
+
+	for_each_cpu(cpu, &cpumask) {
 		struct cpufreq_policy *policy;
 		struct od_cpu_dbs_info_s *dbs_info;
+		struct cpu_dbs_info *cdbs;
+		struct cpu_common_dbs_info *shared;
 		unsigned long next_sampling, appointed_at;
 
-		policy = cpufreq_cpu_get(cpu);
-		if (!policy)
-			continue;
-		if (policy->governor != &cpufreq_gov_ondemand) {
-			cpufreq_cpu_put(policy);
-			continue;
-		}
 		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-		cpufreq_cpu_put(policy);
+		cdbs = &dbs_info->cdbs;
+		shared = cdbs->shared;
 
-		if (!delayed_work_pending(&dbs_info->cdbs.dwork))
+		/*
+		 * A valid shared and shared->policy means governor hasn't
+		 * stopped or exited yet.
+		 */
+		if (!shared || !shared->policy)
+			continue;
+
+		policy = shared->policy;
+
+		/* clear all CPUs of this policy */
+		cpumask_andnot(&cpumask, &cpumask, policy->cpus);
+
+		/*
+		 * Update sampling rate for CPUs whose policy is governed by
+		 * dbs_data. In case of governor_per_policy, only a single
+		 * policy will be governed by dbs_data, otherwise there can be
+		 * multiple policies that are governed by the same dbs_data.
+		 */
+		if (dbs_data != policy->governor_data)
 			continue;
 
+		/*
+		 * Checking this for any CPU should be fine, timers for all of
+		 * them are scheduled together.
+		 */
 		next_sampling = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->cdbs.dwork.timer.expires;
+		appointed_at = dbs_info->cdbs.timer.expires;
 
 		if (time_before(next_sampling, appointed_at)) {
-			cancel_delayed_work_sync(&dbs_info->cdbs.dwork);
-
-			gov_queue_work(dbs_data, policy,
-				       usecs_to_jiffies(new_rate), true);
+			gov_cancel_work(shared);
+			gov_add_timers(policy, usecs_to_jiffies(new_rate));
 
 		}
 	}
+
+	mutex_unlock(&od_dbs_cdata.mutex);
 }
 
 static ssize_t store_sampling_rate(struct dbs_data *dbs_data, const char *buf,

drivers/cpufreq/intel_pstate.c

@@ -66,6 +66,7 @@ static inline int ceiling_fp(int32_t x)
 
 struct sample {
 	int32_t core_pct_busy;
+	int32_t busy_scaled;
 	u64 aperf;
 	u64 mperf;
 	u64 tsc;
@@ -112,6 +113,7 @@ struct cpudata {
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;
+	u64	prev_cummulative_iowait;
 	struct sample sample;
 };
 
@@ -133,6 +135,7 @@ struct pstate_funcs {
 	int (*get_scaling)(void);
 	void (*set)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
+	int32_t (*get_target_pstate)(struct cpudata *);
 };
 
 struct cpu_defaults {
@@ -140,6 +143,9 @@ struct cpu_defaults {
 	struct pstate_funcs funcs;
 };
 
+static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
+static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
+
 static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
 static int hwp_active;
@@ -738,6 +744,7 @@ static struct cpu_defaults core_params = {
 		.get_turbo = core_get_turbo_pstate,
 		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
+		.get_target_pstate = get_target_pstate_use_performance,
 	},
 };
 
@@ -758,6 +765,7 @@ static struct cpu_defaults silvermont_params = {
 		.set = atom_set_pstate,
 		.get_scaling = silvermont_get_scaling,
 		.get_vid = atom_get_vid,
+		.get_target_pstate = get_target_pstate_use_cpu_load,
 	},
 };
 
@@ -778,6 +786,7 @@ static struct cpu_defaults airmont_params = {
 		.set = atom_set_pstate,
 		.get_scaling = airmont_get_scaling,
 		.get_vid = atom_get_vid,
+		.get_target_pstate = get_target_pstate_use_cpu_load,
 	},
 };
 
@@ -797,6 +806,7 @@ static struct cpu_defaults knl_params = {
 		.get_turbo = knl_get_turbo_pstate,
 		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
+		.get_target_pstate = get_target_pstate_use_performance,
 	},
 };
 
@@ -882,12 +892,11 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
-	if (cpu->prev_mperf == mperf) {
+	tsc = rdtsc();
+	if ((cpu->prev_mperf == mperf) || (cpu->prev_tsc == tsc)) {
 		local_irq_restore(flags);
 		return;
 	}
-
-	tsc = rdtsc();
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
@@ -922,7 +931,43 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 	mod_timer_pinned(&cpu->timer, jiffies + delay);
 }
 
-static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
+static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
+{
+	struct sample *sample = &cpu->sample;
+	u64 cummulative_iowait, delta_iowait_us;
+	u64 delta_iowait_mperf;
+	u64 mperf, now;
+	int32_t cpu_load;
+
+	cummulative_iowait = get_cpu_iowait_time_us(cpu->cpu, &now);
+
+	/*
+	 * Convert iowait time into number of IO cycles spent at max_freq.
+	 * IO is considered as busy only for the cpu_load algorithm. For
+	 * performance this is not needed since we always try to reach the
+	 * maximum P-State, so we are already boosting the IOs.
+	 */
+	delta_iowait_us = cummulative_iowait - cpu->prev_cummulative_iowait;
+	delta_iowait_mperf = div64_u64(delta_iowait_us * cpu->pstate.scaling *
+		cpu->pstate.max_pstate, MSEC_PER_SEC);
+
+	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
+	 * (C0) and the time stamp counter running at the same frequency
+	 * also during C-states.
+	 */
+	cpu_load = div64_u64(int_tofp(100) * mperf, sample->tsc);
+	cpu->sample.busy_scaled = cpu_load;
+
+	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, cpu_load);
+}
+
+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;
@@ -960,30 +1005,24 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 		core_busy = mul_fp(core_busy, sample_ratio);
 	}
 
-	return core_busy;
+	cpu->sample.busy_scaled = core_busy;
+	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, core_busy);
 }
 
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 {
-	int32_t busy_scaled;
-	struct _pid *pid;
-	signed int ctl;
-	int from;
+	int from, target_pstate;
 	struct sample *sample;
 
 	from = cpu->pstate.current_pstate;
 
-	pid = &cpu->pid;
-	busy_scaled = intel_pstate_get_scaled_busy(cpu);
+	target_pstate = pstate_funcs.get_target_pstate(cpu);
 
-	ctl = pid_calc(pid, busy_scaled);
-
-	/* Negative values of ctl increase the pstate and vice versa */
-	intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl, true);
+	intel_pstate_set_pstate(cpu, target_pstate, true);
 
 	sample = &cpu->sample;
 	trace_pstate_sample(fp_toint(sample->core_pct_busy),
-		fp_toint(busy_scaled),
+		fp_toint(sample->busy_scaled),
 		from,
 		cpu->pstate.current_pstate,
 		sample->mperf,
@@ -1237,6 +1276,8 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 	pstate_funcs.get_scaling = funcs->get_scaling;
 	pstate_funcs.set       = funcs->set;
 	pstate_funcs.get_vid   = funcs->get_vid;
+	pstate_funcs.get_target_pstate = funcs->get_target_pstate;
+
 }
 
 #if IS_ENABLED(CONFIG_ACPI)

drivers/cpufreq/mt8173-cpufreq.c

@@ -41,16 +41,35 @@
  * the original PLL becomes stable at target frequency.
  */
 struct mtk_cpu_dvfs_info {
+	struct cpumask cpus;
 	struct device *cpu_dev;
 	struct regulator *proc_reg;
 	struct regulator *sram_reg;
 	struct clk *cpu_clk;
 	struct clk *inter_clk;
 	struct thermal_cooling_device *cdev;
+	struct list_head list_head;
 	int intermediate_voltage;
 	bool need_voltage_tracking;
 };
 
+static LIST_HEAD(dvfs_info_list);
+
+static struct mtk_cpu_dvfs_info *mtk_cpu_dvfs_info_lookup(int cpu)
+{
+	struct mtk_cpu_dvfs_info *info;
+	struct list_head *list;
+
+	list_for_each(list, &dvfs_info_list) {
+		info = list_entry(list, struct mtk_cpu_dvfs_info, list_head);
+
+		if (cpumask_test_cpu(cpu, &info->cpus))
+			return info;
+	}
+
+	return NULL;
+}
+
 static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
 					int new_vproc)
 {
@@ -59,7 +78,10 @@ static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
 	int old_vproc, old_vsram, new_vsram, vsram, vproc, ret;
 
 	old_vproc = regulator_get_voltage(proc_reg);
-	old_vsram = regulator_get_voltage(sram_reg);
+	if (old_vproc < 0) {
+		pr_err("%s: invalid Vproc value: %d\n", __func__, old_vproc);
+		return old_vproc;
+	}
 	/* Vsram should not exceed the maximum allowed voltage of SoC. */
 	new_vsram = min(new_vproc + MIN_VOLT_SHIFT, MAX_VOLT_LIMIT);
 
@@ -72,7 +94,17 @@ static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
 		 */
 		do {
 			old_vsram = regulator_get_voltage(sram_reg);
+			if (old_vsram < 0) {
+				pr_err("%s: invalid Vsram value: %d\n",
+				       __func__, old_vsram);
+				return old_vsram;
+			}
 			old_vproc = regulator_get_voltage(proc_reg);
+			if (old_vproc < 0) {
+				pr_err("%s: invalid Vproc value: %d\n",
+				       __func__, old_vproc);
+				return old_vproc;
+			}
 
 			vsram = min(new_vsram, old_vproc + MAX_VOLT_SHIFT);
 
@@ -117,7 +149,17 @@ static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
 		 */
 		do {
 			old_vproc = regulator_get_voltage(proc_reg);
+			if (old_vproc < 0) {
+				pr_err("%s: invalid Vproc value: %d\n",
+				       __func__, old_vproc);
+				return old_vproc;
+			}
 			old_vsram = regulator_get_voltage(sram_reg);
+			if (old_vsram < 0) {
+				pr_err("%s: invalid Vsram value: %d\n",
+				       __func__, old_vsram);
+				return old_vsram;
+			}
 
 			vproc = max(new_vproc, old_vsram - MAX_VOLT_SHIFT);
 			ret = regulator_set_voltage(proc_reg, vproc,
@@ -185,6 +227,10 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 
 	old_freq_hz = clk_get_rate(cpu_clk);
 	old_vproc = regulator_get_voltage(info->proc_reg);
+	if (old_vproc < 0) {
+		pr_err("%s: invalid Vproc value: %d\n", __func__, old_vproc);
+		return old_vproc;
+	}
 
 	freq_hz = freq_table[index].frequency * 1000;
 
@@ -344,7 +390,15 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 	/* Both presence and absence of sram regulator are valid cases. */
 	sram_reg = regulator_get_exclusive(cpu_dev, "sram");
 
-	ret = dev_pm_opp_of_add_table(cpu_dev);
+	/* Get OPP-sharing information from "operating-points-v2" bindings */
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, &info->cpus);
+	if (ret) {
+		pr_err("failed to get OPP-sharing information for cpu%d\n",
+		       cpu);
+		goto out_free_resources;
+	}
+
+	ret = dev_pm_opp_of_cpumask_add_table(&info->cpus);
 	if (ret) {
 		pr_warn("no OPP table for cpu%d\n", cpu);
 		goto out_free_resources;
@@ -378,7 +432,7 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 	return 0;
 
 out_free_opp_table:
-	dev_pm_opp_of_remove_table(cpu_dev);
+	dev_pm_opp_of_cpumask_remove_table(&info->cpus);
 
 out_free_resources:
 	if (!IS_ERR(proc_reg))
@@ -404,7 +458,7 @@ static void mtk_cpu_dvfs_info_release(struct mtk_cpu_dvfs_info *info)
 	if (!IS_ERR(info->inter_clk))
 		clk_put(info->inter_clk);
 
-	dev_pm_opp_of_remove_table(info->cpu_dev);
+	dev_pm_opp_of_cpumask_remove_table(&info->cpus);
 }
 
 static int mtk_cpufreq_init(struct cpufreq_policy *policy)
@@ -413,22 +467,18 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 	struct cpufreq_frequency_table *freq_table;
 	int ret;
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	ret = mtk_cpu_dvfs_info_init(info, policy->cpu);
-	if (ret) {
-		pr_err("%s failed to initialize dvfs info for cpu%d\n",
-		       __func__, policy->cpu);
-		goto out_free_dvfs_info;
+	info = mtk_cpu_dvfs_info_lookup(policy->cpu);
+	if (!info) {
+		pr_err("dvfs info for cpu%d is not initialized.\n",
+		       policy->cpu);
+		return -EINVAL;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(info->cpu_dev, &freq_table);
 	if (ret) {
 		pr_err("failed to init cpufreq table for cpu%d: %d\n",
 		       policy->cpu, ret);
-		goto out_release_dvfs_info;
+		return ret;
 	}
 
 	ret = cpufreq_table_validate_and_show(policy, freq_table);
@@ -437,8 +487,7 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_cpufreq_table;
 	}
 
-	/* CPUs in the same cluster share a clock and power domain. */
-	cpumask_copy(policy->cpus, &cpu_topology[policy->cpu].core_sibling);
+	cpumask_copy(policy->cpus, &info->cpus);
 	policy->driver_data = info;
 	policy->clk = info->cpu_clk;
 
@@ -446,13 +495,6 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 
 out_free_cpufreq_table:
 	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &freq_table);
-
-out_release_dvfs_info:
-	mtk_cpu_dvfs_info_release(info);
-
-out_free_dvfs_info:
-	kfree(info);
-
 	return ret;
 }
 
@@ -462,14 +504,13 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy)
 
 	cpufreq_cooling_unregister(info->cdev);
 	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &policy->freq_table);
-	mtk_cpu_dvfs_info_release(info);
-	kfree(info);
 
 	return 0;
 }
 
 static struct cpufreq_driver mt8173_cpufreq_driver = {
-	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK |
+		 CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = mtk_cpufreq_set_target,
 	.get = cpufreq_generic_get,
@@ -482,11 +523,47 @@ static struct cpufreq_driver mt8173_cpufreq_driver = {
 
 static int mt8173_cpufreq_probe(struct platform_device *pdev)
 {
-	int ret;
+	struct mtk_cpu_dvfs_info *info;
+	struct list_head *list, *tmp;
+	int cpu, ret;
+
+	for_each_possible_cpu(cpu) {
+		info = mtk_cpu_dvfs_info_lookup(cpu);
+		if (info)
+			continue;
+
+		info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+		if (!info) {
+			ret = -ENOMEM;
+			goto release_dvfs_info_list;
+		}
+
+		ret = mtk_cpu_dvfs_info_init(info, cpu);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"failed to initialize dvfs info for cpu%d\n",
+				cpu);
+			goto release_dvfs_info_list;
+		}
+
+		list_add(&info->list_head, &dvfs_info_list);
+	}
 
 	ret = cpufreq_register_driver(&mt8173_cpufreq_driver);
-	if (ret)
-		pr_err("failed to register mtk cpufreq driver\n");
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register mtk cpufreq driver\n");
+		goto release_dvfs_info_list;
+	}
+
+	return 0;
+
+release_dvfs_info_list:
+	list_for_each_safe(list, tmp, &dvfs_info_list) {
+		info = list_entry(list, struct mtk_cpu_dvfs_info, list_head);
+
+		mtk_cpu_dvfs_info_release(info);
+		list_del(list);
+	}
 
 	return ret;
 }

drivers/cpufreq/pcc-cpufreq.c

@@ -555,6 +555,8 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->min = policy->cpuinfo.min_freq =
 		ioread32(&pcch_hdr->minimum_frequency) * 1000;
 
+	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+
 	pr_debug("init: policy->max is %d, policy->min is %d\n",
 		policy->max, policy->min);
 out:

drivers/cpufreq/qoriq-cpufreq.c

@@ -12,6 +12,7 @@
 
 #include <linux/clk.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -33,6 +34,7 @@
 struct cpu_data {
 	struct clk **pclk;
 	struct cpufreq_frequency_table *table;
+	struct thermal_cooling_device *cdev;
 };
 
 /**
@@ -321,6 +323,27 @@ static int qoriq_cpufreq_target(struct cpufreq_policy *policy,
 	return clk_set_parent(policy->clk, parent);
 }
 
+
+static void qoriq_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	struct cpu_data *cpud = policy->driver_data;
+	struct device_node *np = of_get_cpu_node(policy->cpu, NULL);
+
+	if (of_find_property(np, "#cooling-cells", NULL)) {
+		cpud->cdev = of_cpufreq_cooling_register(np,
+							 policy->related_cpus);
+
+		if (IS_ERR(cpud->cdev)) {
+			pr_err("Failed to register cooling device cpu%d: %ld\n",
+					policy->cpu, PTR_ERR(cpud->cdev));
+
+			cpud->cdev = NULL;
+		}
+	}
+
+	of_node_put(np);
+}
+
 static struct cpufreq_driver qoriq_cpufreq_driver = {
 	.name		= "qoriq_cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
@@ -329,6 +352,7 @@ static struct cpufreq_driver qoriq_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= qoriq_cpufreq_target,
 	.get		= cpufreq_generic_get,
+	.ready		= qoriq_cpufreq_ready,
 	.attr		= cpufreq_generic_attr,
 };
 

drivers/cpufreq/sti-cpufreq.c

+/*
+ * Match running platform with pre-defined OPP values for CPUFreq
+ *
+ * Author: Ajit Pal Singh <ajitpal.singh@st.com>
+ *         Lee Jones <lee.jones@linaro.org>
+ *
+ * Copyright (C) 2015 STMicroelectronics (R&D) Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License as
+ * published by the Free Software Foundation
+ */
+
+#include <linux/cpu.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pm_opp.h>
+#include <linux/regmap.h>
+
+#define VERSION_ELEMENTS	3
+#define MAX_PCODE_NAME_LEN	7
+
+#define VERSION_SHIFT		28
+#define HW_INFO_INDEX		1
+#define MAJOR_ID_INDEX		1
+#define MINOR_ID_INDEX		2
+
+/*
+ * Only match on "suitable for ALL versions" entries
+ *
+ * This will be used with the BIT() macro.  It sets the
+ * top bit of a 32bit value and is equal to 0x80000000.
+ */
+#define DEFAULT_VERSION		31
+
+enum {
+	PCODE = 0,
+	SUBSTRATE,
+	DVFS_MAX_REGFIELDS,
+};
+
+/**
+ * ST CPUFreq Driver Data
+ *
+ * @cpu_node		CPU's OF node
+ * @syscfg_eng		Engineering Syscon register map
+ * @regmap		Syscon register map
+ */
+static struct sti_cpufreq_ddata {
+	struct device *cpu;
+	struct regmap *syscfg_eng;
+	struct regmap *syscfg;
+} ddata;
+
+static int sti_cpufreq_fetch_major(void) {
+	struct device_node *np = ddata.cpu->of_node;
+	struct device *dev = ddata.cpu;
+	unsigned int major_offset;
+	unsigned int socid;
+	int ret;
+
+	ret = of_property_read_u32_index(np, "st,syscfg",
+					 MAJOR_ID_INDEX, &major_offset);
+	if (ret) {
+		dev_err(dev, "No major number offset provided in %s [%d]\n",
+			np->full_name, ret);
+		return ret;
+	}
+
+	ret = regmap_read(ddata.syscfg, major_offset, &socid);
+	if (ret) {
+		dev_err(dev, "Failed to read major number from syscon [%d]\n",
+			ret);
+		return ret;
+	}
+
+	return ((socid >> VERSION_SHIFT) & 0xf) + 1;
+}
+
+static int sti_cpufreq_fetch_minor(void)
+{
+	struct device *dev = ddata.cpu;
+	struct device_node *np = dev->of_node;
+	unsigned int minor_offset;
+	unsigned int minid;
+	int ret;
+
+	ret = of_property_read_u32_index(np, "st,syscfg-eng",
+					 MINOR_ID_INDEX, &minor_offset);
+	if (ret) {
+		dev_err(dev,
+			"No minor number offset provided %s [%d]\n",
+			np->full_name, ret);
+		return ret;
+	}
+
+	ret = regmap_read(ddata.syscfg_eng, minor_offset, &minid);
+	if (ret) {
+		dev_err(dev,
+			"Failed to read the minor number from syscon [%d]\n",
+			ret);
+		return ret;
+	}
+
+	return minid & 0xf;
+}
+
+static int sti_cpufreq_fetch_regmap_field(const struct reg_field *reg_fields,
+					  int hw_info_offset, int field)
+{
+	struct regmap_field *regmap_field;
+	struct reg_field reg_field = reg_fields[field];
+	struct device *dev = ddata.cpu;
+	unsigned int value;
+	int ret;
+
+	reg_field.reg = hw_info_offset;
+	regmap_field = devm_regmap_field_alloc(dev,
+					       ddata.syscfg_eng,
+					       reg_field);
+	if (IS_ERR(regmap_field)) {
+		dev_err(dev, "Failed to allocate reg field\n");
+		return PTR_ERR(regmap_field);
+	}
+
+	ret = regmap_field_read(regmap_field, &value);
+	if (ret) {
+		dev_err(dev, "Failed to read %s code\n",
+			field ? "SUBSTRATE" : "PCODE");
+		return ret;
+	}
+
+	return value;
+}
+
+static const struct reg_field sti_stih407_dvfs_regfields[DVFS_MAX_REGFIELDS] = {
+	[PCODE]		= REG_FIELD(0, 16, 19),
+	[SUBSTRATE]	= REG_FIELD(0, 0, 2),
+};
+
+static const struct reg_field *sti_cpufreq_match(void)
+{
+	if (of_machine_is_compatible("st,stih407") ||
+	    of_machine_is_compatible("st,stih410"))
+		return sti_stih407_dvfs_regfields;
+
+	return NULL;
+}
+
+static int sti_cpufreq_set_opp_info(void)
+{
+	struct device *dev = ddata.cpu;
+	struct device_node *np = dev->of_node;
+	const struct reg_field *reg_fields;
+	unsigned int hw_info_offset;
+	unsigned int version[VERSION_ELEMENTS];
+	int pcode, substrate, major, minor;
+	int ret;
+	char name[MAX_PCODE_NAME_LEN];
+
+	reg_fields = sti_cpufreq_match();
+	if (!reg_fields) {
+		dev_err(dev, "This SoC doesn't support voltage scaling");
+		return -ENODEV;
+	}
+
+	ret = of_property_read_u32_index(np, "st,syscfg-eng",
+					 HW_INFO_INDEX, &hw_info_offset);
+	if (ret) {
+		dev_warn(dev, "Failed to read HW info offset from DT\n");
+		substrate = DEFAULT_VERSION;
+		pcode = 0;
+		goto use_defaults;
+	}
+
+	pcode = sti_cpufreq_fetch_regmap_field(reg_fields,
+					       hw_info_offset,
+					       PCODE);
+	if (pcode < 0) {
+		dev_warn(dev, "Failed to obtain process code\n");
+		/* Use default pcode */
+		pcode = 0;
+	}
+
+	substrate = sti_cpufreq_fetch_regmap_field(reg_fields,
+						   hw_info_offset,
+						   SUBSTRATE);
+	if (substrate) {
+		dev_warn(dev, "Failed to obtain substrate code\n");
+		/* Use default substrate */
+		substrate = DEFAULT_VERSION;
+	}
+
+use_defaults:
+	major = sti_cpufreq_fetch_major();
+	if (major < 0) {
+		dev_err(dev, "Failed to obtain major version\n");
+		/* Use default major number */
+		major = DEFAULT_VERSION;
+	}
+
+	minor = sti_cpufreq_fetch_minor();
+	if (minor < 0) {
+		dev_err(dev, "Failed to obtain minor version\n");
+		/* Use default minor number */
+		minor = DEFAULT_VERSION;
+	}
+
+	snprintf(name, MAX_PCODE_NAME_LEN, "pcode%d", pcode);
+
+	ret = dev_pm_opp_set_prop_name(dev, name);
+	if (ret) {
+		dev_err(dev, "Failed to set prop name\n");
+		return ret;
+	}
+
+	version[0] = BIT(major);
+	version[1] = BIT(minor);
+	version[2] = BIT(substrate);
+
+	ret = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
+	if (ret) {
+		dev_err(dev, "Failed to set supported hardware\n");
+		return ret;
+	}
+
+	dev_dbg(dev, "pcode: %d major: %d minor: %d substrate: %d\n",
+		pcode, major, minor, substrate);
+	dev_dbg(dev, "version[0]: %x version[1]: %x version[2]: %x\n",
+		version[0], version[1], version[2]);
+
+	return 0;
+}
+
+static int sti_cpufreq_fetch_syscon_regsiters(void)
+{
+	struct device *dev = ddata.cpu;
+	struct device_node *np = dev->of_node;
+
+	ddata.syscfg = syscon_regmap_lookup_by_phandle(np, "st,syscfg");
+	if (IS_ERR(ddata.syscfg)) {
+		dev_err(dev,  "\"st,syscfg\" not supplied\n");
+		return PTR_ERR(ddata.syscfg);
+	}
+
+	ddata.syscfg_eng = syscon_regmap_lookup_by_phandle(np, "st,syscfg-eng");
+	if (IS_ERR(ddata.syscfg_eng)) {
+		dev_err(dev, "\"st,syscfg-eng\" not supplied\n");
+		return PTR_ERR(ddata.syscfg_eng);
+	}
+
+	return 0;
+}
+
+static int sti_cpufreq_init(void)
+{
+	int ret;
+
+	ddata.cpu = get_cpu_device(0);
+	if (!ddata.cpu) {
+		dev_err(ddata.cpu, "Failed to get device for CPU0\n");
+		goto skip_voltage_scaling;
+	}
+
+	if (!of_get_property(ddata.cpu->of_node, "operating-points-v2", NULL)) {
+		dev_err(ddata.cpu, "OPP-v2 not supported\n");
+		goto skip_voltage_scaling;
+	}
+
+	ret = sti_cpufreq_fetch_syscon_regsiters();
+	if (ret)
+		goto skip_voltage_scaling;
+
+	ret = sti_cpufreq_set_opp_info();
+	if (!ret)
+		goto register_cpufreq_dt;
+
+skip_voltage_scaling:
+	dev_err(ddata.cpu, "Not doing voltage scaling\n");
+
+register_cpufreq_dt:
+	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+
+	return 0;
+}
+module_init(sti_cpufreq_init);
+
+MODULE_DESCRIPTION("STMicroelectronics CPUFreq/OPP driver");
+MODULE_AUTHOR("Ajitpal Singh <ajitpal.singh@st.com>");
+MODULE_AUTHOR("Lee Jones <lee.jones@linaro.org>");
+MODULE_LICENSE("GPL v2");

include/linux/cpufreq.h

@@ -278,7 +278,6 @@ struct cpufreq_driver {
 	struct freq_attr **attr;
 
 	/* platform specific boost support code */
-	bool		boost_supported;
 	bool		boost_enabled;
 	int		(*set_boost)(int state);
 };
@@ -574,7 +573,6 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
 
 #ifdef CONFIG_CPU_FREQ
 int cpufreq_boost_trigger_state(int state);
-int cpufreq_boost_supported(void);
 int cpufreq_boost_enabled(void);
 int cpufreq_enable_boost_support(void);
 bool policy_has_boost_freq(struct cpufreq_policy *policy);
@@ -583,10 +581,6 @@ static inline int cpufreq_boost_trigger_state(int state)
 {
 	return 0;
 }
-static inline int cpufreq_boost_supported(void)
-{
-	return 0;
-}
 static inline int cpufreq_boost_enabled(void)
 {
 	return 0;