Merge branch 'pm-devfreq'

* pm-devfreq: (26 commits)
  PM / devfreq: tegra30: Tune up MCCPU boost-down coefficient
  PM / devfreq: tegra30: Support variable polling interval
  PM / devfreq: Add new interrupt_driven flag for governors
  PM / devfreq: tegra30: Use kHz units for dependency threshold
  PM / devfreq: tegra30: Disable consecutive interrupts when appropriate
  PM / devfreq: tegra30: Don't enable already enabled consecutive interrupts
  PM / devfreq: tegra30: Include appropriate header
  PM / devfreq: tegra30: Constify structs
  PM / devfreq: tegra30: Don't enable consecutive-down interrupt on startup
  PM / devfreq: tegra30: Reset boosting on startup
  PM / devfreq: tegra30: Move clk-notifier's registration to governor's start
  PM / devfreq: tegra30: Use CPUFreq notifier
  PM / devfreq: tegra30: Use kHz units uniformly in the code
  PM / devfreq: tegra30: Fix integer overflow on CPU's freq max out
  PM / devfreq: tegra30: Drop write-barrier
  PM / devfreq: tegra30: Handle possible round-rate error
  PM / devfreq: tegra30: Keep interrupt disabled while governor is stopped
  PM / devfreq: tegra30: Change irq type to unsigned int
  PM / devfreq: exynos-ppmu: remove useless assignment
  PM / devfreq: Lock devfreq in trans_stat_show
  ...

Documentation/devicetree/bindings/devfreq/event/exynos-ppmu.txt

@@ -10,14 +10,23 @@ The Exynos PPMU driver uses the devfreq-event class to provide event data
 to various devfreq devices. The devfreq devices would use the event data when
 derterming the current state of each IP.
 
-Required properties:
+Required properties for PPMU device:
 - compatible: Should be "samsung,exynos-ppmu" or "samsung,exynos-ppmu-v2.
 - reg: physical base address of each PPMU and length of memory mapped region.
 
-Optional properties:
+Optional properties for PPMU device:
 - clock-names : the name of clock used by the PPMU, "ppmu"
 - clocks : phandles for clock specified in "clock-names" property
 
+Required properties for 'events' child node of PPMU device:
+- event-name : the unique event name among PPMU device
+Optional properties for 'events' child node of PPMU device:
+- event-data-type : Define the type of data which shell be counted
+by the counter. You can check include/dt-bindings/pmu/exynos_ppmu.h for
+all possible type, i.e. count read requests, count write data in bytes,
+etc. This field is optional and when it is missing, the driver code
+will use default data type.
+
 Example1 : PPMUv1 nodes in exynos3250.dtsi are listed below.
 
 		ppmu_dmc0: ppmu_dmc0@106a0000 {
@@ -145,3 +154,16 @@ Example3 : PPMUv2 nodes in exynos5433.dtsi are listed below.
 			reg = <0x104d0000 0x2000>;
 			status = "disabled";
 		};
+
+Example4 : 'event-data-type' in exynos4412-ppmu-common.dtsi are listed below.
+
+	&ppmu_dmc0 {
+		status = "okay";
+		events {
+			ppmu_dmc0_3: ppmu-event3-dmc0 {
+			event-name = "ppmu-event3-dmc0";
+			event-data-type = <(PPMU_RO_DATA_CNT |
+					PPMU_WO_DATA_CNT)>;
+			};
+		};
+	};

Documentation/devicetree/bindings/devfreq/exynos-bus.txt

@@ -50,8 +50,6 @@ Required properties only for passive bus device:
 Optional properties only for parent bus device:
 - exynos,saturation-ratio: the percentage value which is used to calibrate
 			the performance count against total cycle count.
-- exynos,voltage-tolerance: the percentage value for bus voltage tolerance
-			which is used to calculate the max voltage.
 
 Detailed correlation between sub-blocks and power line according to Exynos SoC:
 - In case of Exynos3250, there are two power line as following:

MAINTAINERS

@@ -3532,7 +3532,7 @@ BUS FREQUENCY DRIVER FOR SAMSUNG EXYNOS
 M:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
 L:	linux-samsung-soc@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
 S:	Maintained
 F:	drivers/devfreq/exynos-bus.c
 F:	Documentation/devicetree/bindings/devfreq/exynos-bus.txt
@@ -4760,9 +4760,9 @@ F:	include/linux/devcoredump.h
 DEVICE FREQUENCY (DEVFREQ)
 M:	MyungJoo Ham <myungjoo.ham@samsung.com>
 M:	Kyungmin Park <kyungmin.park@samsung.com>
-R:	Chanwoo Choi <cw00.choi@samsung.com>
+M:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
 S:	Maintained
 F:	drivers/devfreq/
 F:	include/linux/devfreq.h
@@ -4772,10 +4772,11 @@ F:	include/trace/events/devfreq.h
 DEVICE FREQUENCY EVENT (DEVFREQ-EVENT)
 M:	Chanwoo Choi <cw00.choi@samsung.com>
 L:	linux-pm@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git
 S:	Supported
 F:	drivers/devfreq/event/
 F:	drivers/devfreq/devfreq-event.c
+F:	include/dt-bindings/pmu/exynos_ppmu.h
 F:	include/linux/devfreq-event.h
 F:	Documentation/devicetree/bindings/devfreq/event/
 

drivers/devfreq/devfreq.c

@@ -160,6 +160,7 @@ int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
 	int lev, prev_lev, ret = 0;
 	unsigned long cur_time;
 
+	lockdep_assert_held(&devfreq->lock);
 	cur_time = jiffies;
 
 	/* Immediately exit if previous_freq is not initialized yet. */
@@ -409,6 +410,9 @@ static void devfreq_monitor(struct work_struct *work)
  */
 void devfreq_monitor_start(struct devfreq *devfreq)
 {
+	if (devfreq->governor->interrupt_driven)
+		return;
+
 	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
@@ -426,6 +430,9 @@ EXPORT_SYMBOL(devfreq_monitor_start);
  */
 void devfreq_monitor_stop(struct devfreq *devfreq)
 {
+	if (devfreq->governor->interrupt_driven)
+		return;
+
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_stop);
@@ -453,6 +460,10 @@ void devfreq_monitor_suspend(struct devfreq *devfreq)
 	devfreq_update_status(devfreq, devfreq->previous_freq);
 	devfreq->stop_polling = true;
 	mutex_unlock(&devfreq->lock);
+
+	if (devfreq->governor->interrupt_driven)
+		return;
+
 	cancel_delayed_work_sync(&devfreq->work);
 }
 EXPORT_SYMBOL(devfreq_monitor_suspend);
@@ -473,11 +484,15 @@ void devfreq_monitor_resume(struct devfreq *devfreq)
 	if (!devfreq->stop_polling)
 		goto out;
 
+	if (devfreq->governor->interrupt_driven)
+		goto out_update;
+
 	if (!delayed_work_pending(&devfreq->work) &&
 			devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
 
+out_update:
 	devfreq->last_stat_updated = jiffies;
 	devfreq->stop_polling = false;
 
@@ -509,6 +524,9 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
 	if (devfreq->stop_polling)
 		goto out;
 
+	if (devfreq->governor->interrupt_driven)
+		goto out;
+
 	/* if new delay is zero, stop polling */
 	if (!new_delay) {
 		mutex_unlock(&devfreq->lock);
@@ -625,7 +643,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq = find_device_devfreq(dev);
 	mutex_unlock(&devfreq_list_lock);
 	if (!IS_ERR(devfreq)) {
-		dev_err(dev, "%s: Unable to create devfreq for the device.\n",
+		dev_err(dev, "%s: devfreq device already exists!\n",
 			__func__);
 		err = -EINVAL;
 		goto err_out;
@@ -1195,7 +1213,7 @@ static ssize_t available_governors_show(struct device *d,
 	 * The devfreq with immutable governor (e.g., passive) shows
 	 * only own governor.
 	 */
-	if (df->governor->immutable) {
+	if (df->governor && df->governor->immutable) {
 		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
 				  "%s ", df->governor_name);
 	/*
@@ -1397,12 +1415,17 @@ static ssize_t trans_stat_show(struct device *dev,
 	int i, j;
 	unsigned int max_state = devfreq->profile->max_state;
 
-	if (!devfreq->stop_polling &&
-			devfreq_update_status(devfreq, devfreq->previous_freq))
-		return 0;
 	if (max_state == 0)
 		return sprintf(buf, "Not Supported.\n");
 
+	mutex_lock(&devfreq->lock);
+	if (!devfreq->stop_polling &&
+			devfreq_update_status(devfreq, devfreq->previous_freq)) {
+		mutex_unlock(&devfreq->lock);
+		return 0;
+	}
+	mutex_unlock(&devfreq->lock);
+
 	len = sprintf(buf, "     From  :   To\n");
 	len += sprintf(buf + len, "           :");
 	for (i = 0; i < max_state; i++)

drivers/devfreq/event/exynos-ppmu.c

@@ -673,7 +673,6 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	for (i = 0; i < info->num_events; i++) {
 		edev[i] = devm_devfreq_event_add_edev(&pdev->dev, &desc[i]);
 		if (IS_ERR(edev[i])) {
-			ret = PTR_ERR(edev[i]);
 			dev_err(&pdev->dev,
 				"failed to add devfreq-event device\n");
 			return PTR_ERR(edev[i]);

drivers/devfreq/governor.h

@@ -31,6 +31,8 @@
  * @name:		Governor's name
  * @immutable:		Immutable flag for governor. If the value is 1,
  *			this govenror is never changeable to other governor.
+ * @interrupt_driven:	Devfreq core won't schedule polling work for this
+ *			governor if value is set to 1.
  * @get_target_freq:	Returns desired operating frequency for the device.
  *			Basically, get_target_freq will run
  *			devfreq_dev_profile.get_dev_status() to get the
@@ -49,6 +51,7 @@ struct devfreq_governor {
 
 	const char name[DEVFREQ_NAME_LEN];
 	const unsigned int immutable;
+	const unsigned int interrupt_driven;
 	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
 	int (*event_handler)(struct devfreq *devfreq,
 				unsigned int event, void *data);

drivers/devfreq/tegra30-devfreq.c

@@ -11,11 +11,13 @@
 #include <linux/devfreq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
-#include <linux/mod_devicetable.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/reset.h>
+#include <linux/workqueue.h>
 
 #include "governor.h"
 
@@ -33,6 +35,8 @@
 #define ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN		BIT(30)
 #define ACTMON_DEV_CTRL_ENB					BIT(31)
 
+#define ACTMON_DEV_CTRL_STOP					0x00000000
+
 #define ACTMON_DEV_UPPER_WMARK					0x4
 #define ACTMON_DEV_LOWER_WMARK					0x8
 #define ACTMON_DEV_INIT_AVG					0xc
@@ -68,6 +72,8 @@
 
 #define KHZ							1000
 
+#define KHZ_MAX						(ULONG_MAX / KHZ)
+
 /* Assume that the bus is saturated if the utilization is 25% */
 #define BUS_SATURATION_RATIO					25
 
@@ -90,9 +96,10 @@ struct tegra_devfreq_device_config {
 	unsigned int	boost_down_threshold;
 
 	/*
-	 * Threshold of activity (cycles) below which the CPU frequency isn't
+	 * Threshold of activity (cycles translated to kHz) below which the
-	 * to be taken into account. This is to avoid increasing the EMC
+	 * CPU frequency isn't to be taken into account. This is to avoid
-	 * frequency when the CPU is very busy but not accessing the bus often.
+	 * increasing the EMC frequency when the CPU is very busy but not
+	 * accessing the bus often.
 	 */
 	u32		avg_dependency_threshold;
 };
@@ -102,7 +109,7 @@ enum tegra_actmon_device {
 	MCCPU,
 };
 
-static struct tegra_devfreq_device_config actmon_device_configs[] = {
+static const struct tegra_devfreq_device_config actmon_device_configs[] = {
 	{
 		/* MCALL: All memory accesses (including from the CPUs) */
 		.offset = 0x1c0,
@@ -117,10 +124,10 @@ static struct tegra_devfreq_device_config actmon_device_configs[] = {
 		.offset = 0x200,
 		.irq_mask = 1 << 25,
 		.boost_up_coeff = 800,
-		.boost_down_coeff = 90,
+		.boost_down_coeff = 40,
 		.boost_up_threshold = 27,
 		.boost_down_threshold = 10,
-		.avg_dependency_threshold = 50000,
+		.avg_dependency_threshold = 16000, /* 16MHz in kHz units */
 	},
 };
 
@@ -156,11 +163,16 @@ struct tegra_devfreq {
 	struct clk		*emc_clock;
 	unsigned long		max_freq;
 	unsigned long		cur_freq;
-	struct notifier_block	rate_change_nb;
+	struct notifier_block	clk_rate_change_nb;
+
+	struct delayed_work	cpufreq_update_work;
+	struct notifier_block	cpu_rate_change_nb;
 
 	struct tegra_devfreq_device devices[ARRAY_SIZE(actmon_device_configs)];
 
-	int irq;
+	unsigned int		irq;
+
+	bool			started;
 };
 
 struct tegra_actmon_emc_ratio {
@@ -168,8 +180,8 @@ struct tegra_actmon_emc_ratio {
 	unsigned long emc_freq;
 };
 
-static struct tegra_actmon_emc_ratio actmon_emc_ratios[] = {
+static const struct tegra_actmon_emc_ratio actmon_emc_ratios[] = {
-	{ 1400000, ULONG_MAX },
+	{ 1400000,    KHZ_MAX },
 	{ 1200000,    750000 },
 	{ 1100000,    600000 },
 	{ 1000000,    500000 },
@@ -199,18 +211,26 @@ static void device_writel(struct tegra_devfreq_device *dev, u32 val,
 	writel_relaxed(val, dev->regs + offset);
 }
 
-static unsigned long do_percent(unsigned long val, unsigned int pct)
+static unsigned long do_percent(unsigned long long val, unsigned int pct)
 {
-	return val * pct / 100;
+	val = val * pct;
+	do_div(val, 100);
+
+	/*
+	 * High freq + high boosting percent + large polling interval are
+	 * resulting in integer overflow when watermarks are calculated.
+	 */
+	return min_t(u64, val, U32_MAX);
 }
 
 static void tegra_devfreq_update_avg_wmark(struct tegra_devfreq *tegra,
 					   struct tegra_devfreq_device *dev)
 {
-	u32 avg = dev->avg_count;
 	u32 avg_band_freq = tegra->max_freq * ACTMON_DEFAULT_AVG_BAND / KHZ;
-	u32 band = avg_band_freq * ACTMON_SAMPLING_PERIOD;
+	u32 band = avg_band_freq * tegra->devfreq->profile->polling_ms;
+	u32 avg;
 
+	avg = min(dev->avg_count, U32_MAX - band);
 	device_writel(dev, avg + band, ACTMON_DEV_AVG_UPPER_WMARK);
 
 	avg = max(dev->avg_count, band);
@@ -220,7 +240,7 @@ static void tegra_devfreq_update_avg_wmark(struct tegra_devfreq *tegra,
 static void tegra_devfreq_update_wmark(struct tegra_devfreq *tegra,
 				       struct tegra_devfreq_device *dev)
 {
-	u32 val = tegra->cur_freq * ACTMON_SAMPLING_PERIOD;
+	u32 val = tegra->cur_freq * tegra->devfreq->profile->polling_ms;
 
 	device_writel(dev, do_percent(val, dev->config->boost_up_threshold),
 		      ACTMON_DEV_UPPER_WMARK);
@@ -229,12 +249,6 @@ static void tegra_devfreq_update_wmark(struct tegra_devfreq *tegra,
 		      ACTMON_DEV_LOWER_WMARK);
 }
 
-static void actmon_write_barrier(struct tegra_devfreq *tegra)
-{
-	/* ensure the update has reached the ACTMON */
-	readl(tegra->regs + ACTMON_GLB_STATUS);
-}
-
 static void actmon_isr_device(struct tegra_devfreq *tegra,
 			      struct tegra_devfreq_device *dev)
 {
@@ -256,10 +270,10 @@ static void actmon_isr_device(struct tegra_devfreq *tegra,
 
 		dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
 
-		if (dev->boost_freq >= tegra->max_freq)
+		if (dev->boost_freq >= tegra->max_freq) {
+			dev_ctrl &= ~ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 			dev->boost_freq = tegra->max_freq;
-		else
+		}
-			dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 	} else if (intr_status & ACTMON_DEV_INTR_CONSECUTIVE_LOWER) {
 		/*
 		 * new_boost = old_boost * down_coef
@@ -270,31 +284,22 @@ static void actmon_isr_device(struct tegra_devfreq *tegra,
 
 		dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 
-		if (dev->boost_freq < (ACTMON_BOOST_FREQ_STEP >> 1))
+		if (dev->boost_freq < (ACTMON_BOOST_FREQ_STEP >> 1)) {
-			dev->boost_freq = 0;
-		else
-			dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
-	}
-
-	if (dev->config->avg_dependency_threshold) {
-		if (dev->avg_count >= dev->config->avg_dependency_threshold)
-			dev_ctrl |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
-		else if (dev->boost_freq == 0)
 			dev_ctrl &= ~ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
+			dev->boost_freq = 0;
+		}
 	}
 
 	device_writel(dev, dev_ctrl, ACTMON_DEV_CTRL);
 
 	device_writel(dev, ACTMON_INTR_STATUS_CLEAR, ACTMON_DEV_INTR_STATUS);
-
-	actmon_write_barrier(tegra);
 }
 
 static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra,
 					    unsigned long cpu_freq)
 {
 	unsigned int i;
-	struct tegra_actmon_emc_ratio *ratio = actmon_emc_ratios;
+	const struct tegra_actmon_emc_ratio *ratio = actmon_emc_ratios;
 
 	for (i = 0; i < ARRAY_SIZE(actmon_emc_ratios); i++, ratio++) {
 		if (cpu_freq >= ratio->cpu_freq) {
@@ -308,25 +313,37 @@ static unsigned long actmon_cpu_to_emc_rate(struct tegra_devfreq *tegra,
 	return 0;
 }
 
+static unsigned long actmon_device_target_freq(struct tegra_devfreq *tegra,
+					       struct tegra_devfreq_device *dev)
+{
+	unsigned int avg_sustain_coef;
+	unsigned long target_freq;
+
+	target_freq = dev->avg_count / tegra->devfreq->profile->polling_ms;
+	avg_sustain_coef = 100 * 100 / dev->config->boost_up_threshold;
+	target_freq = do_percent(target_freq, avg_sustain_coef);
+
+	return target_freq;
+}
+
 static void actmon_update_target(struct tegra_devfreq *tegra,
 				 struct tegra_devfreq_device *dev)
 {
 	unsigned long cpu_freq = 0;
 	unsigned long static_cpu_emc_freq = 0;
-	unsigned int avg_sustain_coef;
 
-	if (dev->config->avg_dependency_threshold) {
+	dev->target_freq = actmon_device_target_freq(tegra, dev);
-		cpu_freq = cpufreq_get(0);
+
+	if (dev->config->avg_dependency_threshold &&
+	    dev->config->avg_dependency_threshold <= dev->target_freq) {
+		cpu_freq = cpufreq_quick_get(0);
 		static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq);
-	}
 
-	dev->target_freq = dev->avg_count / ACTMON_SAMPLING_PERIOD;
+		dev->target_freq += dev->boost_freq;
-	avg_sustain_coef = 100 * 100 / dev->config->boost_up_threshold;
-	dev->target_freq = do_percent(dev->target_freq, avg_sustain_coef);
-	dev->target_freq += dev->boost_freq;
-
-	if (dev->avg_count >= dev->config->avg_dependency_threshold)
 		dev->target_freq = max(dev->target_freq, static_cpu_emc_freq);
+	} else {
+		dev->target_freq += dev->boost_freq;
+	}
 }
 
 static irqreturn_t actmon_thread_isr(int irq, void *data)
@@ -354,8 +371,8 @@ static irqreturn_t actmon_thread_isr(int irq, void *data)
 	return handled ? IRQ_HANDLED : IRQ_NONE;
 }
 
-static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
+static int tegra_actmon_clk_notify_cb(struct notifier_block *nb,
-				       unsigned long action, void *ptr)
+				      unsigned long action, void *ptr)
 {
 	struct clk_notifier_data *data = ptr;
 	struct tegra_devfreq *tegra;
@@ -365,7 +382,7 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 	if (action != POST_RATE_CHANGE)
 		return NOTIFY_OK;
 
-	tegra = container_of(nb, struct tegra_devfreq, rate_change_nb);
+	tegra = container_of(nb, struct tegra_devfreq, clk_rate_change_nb);
 
 	tegra->cur_freq = data->new_rate / KHZ;
 
@@ -375,7 +392,79 @@ static int tegra_actmon_rate_notify_cb(struct notifier_block *nb,
 		tegra_devfreq_update_wmark(tegra, dev);
 	}
 
-	actmon_write_barrier(tegra);
+	return NOTIFY_OK;
+}
+
+static void tegra_actmon_delayed_update(struct work_struct *work)
+{
+	struct tegra_devfreq *tegra = container_of(work, struct tegra_devfreq,
+						   cpufreq_update_work.work);
+
+	mutex_lock(&tegra->devfreq->lock);
+	update_devfreq(tegra->devfreq);
+	mutex_unlock(&tegra->devfreq->lock);
+}
+
+static unsigned long
+tegra_actmon_cpufreq_contribution(struct tegra_devfreq *tegra,
+				  unsigned int cpu_freq)
+{
+	struct tegra_devfreq_device *actmon_dev = &tegra->devices[MCCPU];
+	unsigned long static_cpu_emc_freq, dev_freq;
+
+	dev_freq = actmon_device_target_freq(tegra, actmon_dev);
+
+	/* check whether CPU's freq is taken into account at all */
+	if (dev_freq < actmon_dev->config->avg_dependency_threshold)
+		return 0;
+
+	static_cpu_emc_freq = actmon_cpu_to_emc_rate(tegra, cpu_freq);
+
+	if (dev_freq >= static_cpu_emc_freq)
+		return 0;
+
+	return static_cpu_emc_freq;
+}
+
+static int tegra_actmon_cpu_notify_cb(struct notifier_block *nb,
+				      unsigned long action, void *ptr)
+{
+	struct cpufreq_freqs *freqs = ptr;
+	struct tegra_devfreq *tegra;
+	unsigned long old, new, delay;
+
+	if (action != CPUFREQ_POSTCHANGE)
+		return NOTIFY_OK;
+
+	tegra = container_of(nb, struct tegra_devfreq, cpu_rate_change_nb);
+
+	/*
+	 * Quickly check whether CPU frequency should be taken into account
+	 * at all, without blocking CPUFreq's core.
+	 */
+	if (mutex_trylock(&tegra->devfreq->lock)) {
+		old = tegra_actmon_cpufreq_contribution(tegra, freqs->old);
+		new = tegra_actmon_cpufreq_contribution(tegra, freqs->new);
+		mutex_unlock(&tegra->devfreq->lock);
+
+		/*
+		 * If CPU's frequency shouldn't be taken into account at
+		 * the moment, then there is no need to update the devfreq's
+		 * state because ISR will re-check CPU's frequency on the
+		 * next interrupt.
+		 */
+		if (old == new)
+			return NOTIFY_OK;
+	}
+
+	/*
+	 * CPUFreq driver should support CPUFREQ_ASYNC_NOTIFICATION in order
+	 * to allow asynchronous notifications. This means we can't block
+	 * here for too long, otherwise CPUFreq's core will complain with a
+	 * warning splat.
+	 */
+	delay = msecs_to_jiffies(ACTMON_SAMPLING_PERIOD);
+	schedule_delayed_work(&tegra->cpufreq_update_work, delay);
 
 	return NOTIFY_OK;
 }
@@ -385,9 +474,12 @@ static void tegra_actmon_configure_device(struct tegra_devfreq *tegra,
 {
 	u32 val = 0;
 
+	/* reset boosting on governor's restart */
+	dev->boost_freq = 0;
+
 	dev->target_freq = tegra->cur_freq;
 
-	dev->avg_count = tegra->cur_freq * ACTMON_SAMPLING_PERIOD;
+	dev->avg_count = tegra->cur_freq * tegra->devfreq->profile->polling_ms;
 	device_writel(dev, dev->avg_count, ACTMON_DEV_INIT_AVG);
 
 	tegra_devfreq_update_avg_wmark(tegra, dev);
@@ -405,45 +497,116 @@ static void tegra_actmon_configure_device(struct tegra_devfreq *tegra,
 		<< ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_NUM_SHIFT;
 	val |= ACTMON_DEV_CTRL_AVG_ABOVE_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_AVG_BELOW_WMARK_EN;
-	val |= ACTMON_DEV_CTRL_CONSECUTIVE_BELOW_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_CONSECUTIVE_ABOVE_WMARK_EN;
 	val |= ACTMON_DEV_CTRL_ENB;
 
 	device_writel(dev, val, ACTMON_DEV_CTRL);
 }
 
-static void tegra_actmon_start(struct tegra_devfreq *tegra)
+static void tegra_actmon_stop_devices(struct tegra_devfreq *tegra)
 {
+	struct tegra_devfreq_device *dev = tegra->devices;
 	unsigned int i;
 
-	disable_irq(tegra->irq);
+	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++, dev++) {
+		device_writel(dev, ACTMON_DEV_CTRL_STOP, ACTMON_DEV_CTRL);
+		device_writel(dev, ACTMON_INTR_STATUS_CLEAR,
+			      ACTMON_DEV_INTR_STATUS);
+	}
+}
 
-	actmon_writel(tegra, ACTMON_SAMPLING_PERIOD - 1,
+static int tegra_actmon_resume(struct tegra_devfreq *tegra)
+{
+	unsigned int i;
+	int err;
+
+	if (!tegra->devfreq->profile->polling_ms || !tegra->started)
+		return 0;
+
+	actmon_writel(tegra, tegra->devfreq->profile->polling_ms - 1,
 		      ACTMON_GLB_PERIOD_CTRL);
 
+	/*
+	 * CLK notifications are needed in order to reconfigure the upper
+	 * consecutive watermark in accordance to the actual clock rate
+	 * to avoid unnecessary upper interrupts.
+	 */
+	err = clk_notifier_register(tegra->emc_clock,
+				    &tegra->clk_rate_change_nb);
+	if (err) {
+		dev_err(tegra->devfreq->dev.parent,
+			"Failed to register rate change notifier\n");
+		return err;
+	}
+
+	tegra->cur_freq = clk_get_rate(tegra->emc_clock) / KHZ;
+
 	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++)
 		tegra_actmon_configure_device(tegra, &tegra->devices[i]);
 
-	actmon_write_barrier(tegra);
+	/*
+	 * We are estimating CPU's memory bandwidth requirement based on
+	 * amount of memory accesses and system's load, judging by CPU's
+	 * frequency. We also don't want to receive events about CPU's
+	 * frequency transaction when governor is stopped, hence notifier
+	 * is registered dynamically.
+	 */
+	err = cpufreq_register_notifier(&tegra->cpu_rate_change_nb,
+					CPUFREQ_TRANSITION_NOTIFIER);
+	if (err) {
+		dev_err(tegra->devfreq->dev.parent,
+			"Failed to register rate change notifier: %d\n", err);
+		goto err_stop;
+	}
 
 	enable_irq(tegra->irq);
+
+	return 0;
+
+err_stop:
+	tegra_actmon_stop_devices(tegra);
+
+	clk_notifier_unregister(tegra->emc_clock, &tegra->clk_rate_change_nb);
+
+	return err;
+}
+
+static int tegra_actmon_start(struct tegra_devfreq *tegra)
+{
+	int ret = 0;
+
+	if (!tegra->started) {
+		tegra->started = true;
+
+		ret = tegra_actmon_resume(tegra);
+		if (ret)
+			tegra->started = false;
+	}
+
+	return ret;
+}
+
+static void tegra_actmon_pause(struct tegra_devfreq *tegra)
+{
+	if (!tegra->devfreq->profile->polling_ms || !tegra->started)
+		return;
+
+	disable_irq(tegra->irq);
+
+	cpufreq_unregister_notifier(&tegra->cpu_rate_change_nb,
+				    CPUFREQ_TRANSITION_NOTIFIER);
+
+	cancel_delayed_work_sync(&tegra->cpufreq_update_work);
+
+	tegra_actmon_stop_devices(tegra);
+
+	clk_notifier_unregister(tegra->emc_clock, &tegra->clk_rate_change_nb);
 }
 
 static void tegra_actmon_stop(struct tegra_devfreq *tegra)
 {
-	unsigned int i;
+	tegra_actmon_pause(tegra);
-
+	tegra->started = false;
-	disable_irq(tegra->irq);
-
-	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
-		device_writel(&tegra->devices[i], 0x00000000, ACTMON_DEV_CTRL);
-		device_writel(&tegra->devices[i], ACTMON_INTR_STATUS_CLEAR,
-			      ACTMON_DEV_INTR_STATUS);
-	}
-
-	actmon_write_barrier(tegra);
-
-	enable_irq(tegra->irq);
 }
 
 static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
@@ -463,7 +626,7 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	rate = dev_pm_opp_get_freq(opp);
 	dev_pm_opp_put(opp);
 
-	err = clk_set_min_rate(tegra->emc_clock, rate);
+	err = clk_set_min_rate(tegra->emc_clock, rate * KHZ);
 	if (err)
 		return err;
 
@@ -492,7 +655,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 	stat->private_data = tegra;
 
 	/* The below are to be used by the other governors */
-	stat->current_frequency = cur_freq * KHZ;
+	stat->current_frequency = cur_freq;
 
 	actmon_dev = &tegra->devices[MCALL];
 
@@ -503,7 +666,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 	stat->busy_time *= 100 / BUS_SATURATION_RATIO;
 
 	/* Number of cycles in a sampling period */
-	stat->total_time = ACTMON_SAMPLING_PERIOD * cur_freq;
+	stat->total_time = tegra->devfreq->profile->polling_ms * cur_freq;
 
 	stat->busy_time = min(stat->busy_time, stat->total_time);
 
@@ -511,7 +674,7 @@ static int tegra_devfreq_get_dev_status(struct device *dev,
 }
 
 static struct devfreq_dev_profile tegra_devfreq_profile = {
-	.polling_ms	= 0,
+	.polling_ms	= ACTMON_SAMPLING_PERIOD,
 	.target		= tegra_devfreq_target,
 	.get_dev_status	= tegra_devfreq_get_dev_status,
 };
@@ -542,7 +705,7 @@ static int tegra_governor_get_target(struct devfreq *devfreq,
 		target_freq = max(target_freq, dev->target_freq);
 	}
 
-	*freq = target_freq * KHZ;
+	*freq = target_freq;
 
 	return 0;
 }
@@ -551,11 +714,19 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 					unsigned int event, void *data)
 {
 	struct tegra_devfreq *tegra = dev_get_drvdata(devfreq->dev.parent);
+	unsigned int *new_delay = data;
+	int ret = 0;
+
+	/*
+	 * Couple devfreq-device with the governor early because it is
+	 * needed at the moment of governor's start (used by ISR).
+	 */
+	tegra->devfreq = devfreq;
 
 	switch (event) {
 	case DEVFREQ_GOV_START:
 		devfreq_monitor_start(devfreq);
-		tegra_actmon_start(tegra);
+		ret = tegra_actmon_start(tegra);
 		break;
 
 	case DEVFREQ_GOV_STOP:
@@ -563,6 +734,21 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 		devfreq_monitor_stop(devfreq);
 		break;
 
+	case DEVFREQ_GOV_INTERVAL:
+		/*
+		 * ACTMON hardware supports up to 256 milliseconds for the
+		 * sampling period.
+		 */
+		if (*new_delay > 256) {
+			ret = -EINVAL;
+			break;
+		}
+
+		tegra_actmon_pause(tegra);
+		devfreq_interval_update(devfreq, new_delay);
+		ret = tegra_actmon_resume(tegra);
+		break;
+
 	case DEVFREQ_GOV_SUSPEND:
 		tegra_actmon_stop(tegra);
 		devfreq_monitor_suspend(devfreq);
@@ -570,11 +756,11 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 
 	case DEVFREQ_GOV_RESUME:
 		devfreq_monitor_resume(devfreq);
-		tegra_actmon_start(tegra);
+		ret = tegra_actmon_start(tegra);
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static struct devfreq_governor tegra_devfreq_governor = {
@@ -582,14 +768,16 @@ static struct devfreq_governor tegra_devfreq_governor = {
 	.get_target_freq = tegra_governor_get_target,
 	.event_handler = tegra_governor_event_handler,
 	.immutable = true,
+	.interrupt_driven = true,
 };
 
 static int tegra_devfreq_probe(struct platform_device *pdev)
 {
-	struct tegra_devfreq *tegra;
 	struct tegra_devfreq_device *dev;
+	struct tegra_devfreq *tegra;
+	struct devfreq *devfreq;
 	unsigned int i;
-	unsigned long rate;
+	long rate;
 	int err;
 
 	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
@@ -618,12 +806,22 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 		return PTR_ERR(tegra->emc_clock);
 	}
 
-	tegra->irq = platform_get_irq(pdev, 0);
+	err = platform_get_irq(pdev, 0);
-	if (tegra->irq < 0) {
+	if (err < 0) {
-		err = tegra->irq;
 		dev_err(&pdev->dev, "Failed to get IRQ: %d\n", err);
 		return err;
 	}
+	tegra->irq = err;
+
+	irq_set_status_flags(tegra->irq, IRQ_NOAUTOEN);
+
+	err = devm_request_threaded_irq(&pdev->dev, tegra->irq, NULL,
+					actmon_thread_isr, IRQF_ONESHOT,
+					"tegra-devfreq", tegra);
+	if (err) {
+		dev_err(&pdev->dev, "Interrupt request failed: %d\n", err);
+		return err;
+	}
 
 	reset_control_assert(tegra->reset);
 
@@ -636,8 +834,13 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 
 	reset_control_deassert(tegra->reset);
 
-	tegra->max_freq = clk_round_rate(tegra->emc_clock, ULONG_MAX) / KHZ;
+	rate = clk_round_rate(tegra->emc_clock, ULONG_MAX);
-	tegra->cur_freq = clk_get_rate(tegra->emc_clock) / KHZ;
+	if (rate < 0) {
+		dev_err(&pdev->dev, "Failed to round clock rate: %ld\n", rate);
+		return rate;
+	}
+
+	tegra->max_freq = rate / KHZ;
 
 	for (i = 0; i < ARRAY_SIZE(actmon_device_configs); i++) {
 		dev = tegra->devices + i;
@@ -648,7 +851,14 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 	for (rate = 0; rate <= tegra->max_freq * KHZ; rate++) {
 		rate = clk_round_rate(tegra->emc_clock, rate);
 
-		err = dev_pm_opp_add(&pdev->dev, rate, 0);
+		if (rate < 0) {
+			dev_err(&pdev->dev,
+				"Failed to round clock rate: %ld\n", rate);
+			err = rate;
+			goto remove_opps;
+		}
+
+		err = dev_pm_opp_add(&pdev->dev, rate / KHZ, 0);
 		if (err) {
 			dev_err(&pdev->dev, "Failed to add OPP: %d\n", err);
 			goto remove_opps;
@@ -657,49 +867,33 @@ static int tegra_devfreq_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, tegra);
 
-	tegra->rate_change_nb.notifier_call = tegra_actmon_rate_notify_cb;
+	tegra->clk_rate_change_nb.notifier_call = tegra_actmon_clk_notify_cb;
-	err = clk_notifier_register(tegra->emc_clock, &tegra->rate_change_nb);
+	tegra->cpu_rate_change_nb.notifier_call = tegra_actmon_cpu_notify_cb;
-	if (err) {
+
-		dev_err(&pdev->dev,
+	INIT_DELAYED_WORK(&tegra->cpufreq_update_work,
-			"Failed to register rate change notifier\n");
+			  tegra_actmon_delayed_update);
-		goto remove_opps;
-	}
 
 	err = devfreq_add_governor(&tegra_devfreq_governor);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to add governor: %d\n", err);
-		goto unreg_notifier;
+		goto remove_opps;
 	}
 
 	tegra_devfreq_profile.initial_freq = clk_get_rate(tegra->emc_clock);
-	tegra->devfreq = devfreq_add_device(&pdev->dev,
+	tegra_devfreq_profile.initial_freq /= KHZ;
-					    &tegra_devfreq_profile,
-					    "tegra_actmon",
-					    NULL);
-	if (IS_ERR(tegra->devfreq)) {
-		err = PTR_ERR(tegra->devfreq);
-		goto remove_governor;
-	}
 
-	err = devm_request_threaded_irq(&pdev->dev, tegra->irq, NULL,
+	devfreq = devfreq_add_device(&pdev->dev, &tegra_devfreq_profile,
-					actmon_thread_isr, IRQF_ONESHOT,
+				     "tegra_actmon", NULL);
-					"tegra-devfreq", tegra);
+	if (IS_ERR(devfreq)) {
-	if (err) {
+		err = PTR_ERR(devfreq);
-		dev_err(&pdev->dev, "Interrupt request failed: %d\n", err);
+		goto remove_governor;
-		goto remove_devfreq;
 	}
 
 	return 0;
 
-remove_devfreq:
-	devfreq_remove_device(tegra->devfreq);
-
 remove_governor:
 	devfreq_remove_governor(&tegra_devfreq_governor);
 
-unreg_notifier:
-	clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb);
-
 remove_opps:
 	dev_pm_opp_remove_all_dynamic(&pdev->dev);
 
@@ -716,7 +910,6 @@ static int tegra_devfreq_remove(struct platform_device *pdev)
 	devfreq_remove_device(tegra->devfreq);
 	devfreq_remove_governor(&tegra_devfreq_governor);
 
-	clk_notifier_unregister(tegra->emc_clock, &tegra->rate_change_nb);
 	dev_pm_opp_remove_all_dynamic(&pdev->dev);
 
 	reset_control_reset(tegra->reset);

include/dt-bindings/pmu/exynos_ppmu.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Samsung Exynos PPMU event types for counting in regs
+ *
+ * Copyright (c) 2019, Samsung Electronics
+ * Author: Lukasz Luba <l.luba@partner.samsung.com>
+ */
+
+#ifndef __DT_BINDINGS_PMU_EXYNOS_PPMU_H
+#define __DT_BINDINGS_PMU_EXYNOS_PPMU_H
+
+#define PPMU_RO_BUSY_CYCLE_CNT		0x0
+#define PPMU_WO_BUSY_CYCLE_CNT		0x1
+#define PPMU_RW_BUSY_CYCLE_CNT		0x2
+#define PPMU_RO_REQUEST_CNT		0x3
+#define PPMU_WO_REQUEST_CNT		0x4
+#define PPMU_RO_DATA_CNT		0x5
+#define PPMU_WO_DATA_CNT		0x6
+#define PPMU_RO_LATENCY			0x12
+#define PPMU_WO_LATENCY			0x16
+#define PPMU_V2_RO_DATA_CNT		0x4
+#define PPMU_V2_WO_DATA_CNT		0x5
+#define PPMU_V2_EVT3_RW_DATA_CNT	0x22
+
+#endif