[v2,1/2] PM / devfreq: Add support delayed timer for polling mode

Commit Message

Chanwoo Choi July 9, 2020, 5:45 a.m. UTC

Until now, the devfreq driver using polling mode like simple_ondemand
governor have used only deferrable timer for reducing the redundant
power consumption. It reduces the CPU wake-up from idle due to polling mode
which check the status of Non-CPU device.

But, it has a problem for Non-CPU device like DMC device with DMA operation.
Some Non-CPU device need to do monitor continuously regardless of CPU state
in order to decide the proper next status of Non-CPU device.

So, add support the delayed timer for polling mode to support
the repetitive monitoring. The devfreq driver and user can select
the kind of timer on either deferrable and delayed timer.

For example, change the timer type of DMC device
based on Exynos5422-based Odroid-XU3 as following:

- If want to use deferrable timer as following:
echo deferrable > /sys/class/devfreq/10c20000.memory-controller/timer

- If want to use delayed timer as following:
echo delayed > /sys/class/devfreq/10c20000.memory-controller/timer

Reviewed-by: Bartlomiej Zolnierkiewicz <[e-mail]>
Reviewed-by: Lukasz Luba <[e-mail]>
Signed-off-by: Chanwoo Choi <[e-mail]>
---
 Documentation/ABI/testing/sysfs-class-devfreq | 12 +++
 drivers/devfreq/devfreq.c                     | 86 ++++++++++++++++++-
 include/linux/devfreq.h                       |  9 ++
 3 files changed, 106 insertions(+), 1 deletion(-)

Patch

diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index 9758eb85ade3..deefffb3bbe4 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -108,3 +108,15 @@  Description:
 		frequency requested by governors and min_freq.
 		The max_freq overrides min_freq because max_freq may be
 		used to throttle devices to avoid overheating.
+
+What:		/sys/class/devfreq/.../timer
+Date:		July 2020
+Contact:	Chanwoo Choi <[e-mail]>
+Description:
+		This ABI shows and stores the kind of work timer by users.
+		This work timer is used by devfreq workqueue in order to
+		monitor the device status such as utilization. The user
+		can change the work timer on runtime according to their demand
+		as following:
+			echo deferrable > /sys/class/devfreq/.../timer
+			echo delayed > /sys/class/devfreq/.../timer
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 52b9c3e141f3..10f1543df84b 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -49,6 +49,11 @@  static LIST_HEAD(devfreq_governor_list);
 static LIST_HEAD(devfreq_list);
 static DEFINE_MUTEX(devfreq_list_lock);
 
+static const char timer_name[][DEVFREQ_NAME_LEN] = {
+	[DEVFREQ_TIMER_DEFERRABLE] = { "deferrable" },
+	[DEVFREQ_TIMER_DELAYED] = { "delayed" },
+};
+
 /**
  * find_device_devfreq() - find devfreq struct using device pointer
  * @dev:	device pointer used to lookup device devfreq.
@@ -454,7 +459,17 @@  void devfreq_monitor_start(struct devfreq *devfreq)
 	if (devfreq->governor->interrupt_driven)
 		return;
 
-	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
+	switch (devfreq->profile->timer) {
+	case DEVFREQ_TIMER_DEFERRABLE:
+		INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
+		break;
+	case DEVFREQ_TIMER_DELAYED:
+		INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
+		break;
+	default:
+		return;
+	}
+
 	if (devfreq->profile->polling_ms)
 		queue_delayed_work(devfreq_wq, &devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
@@ -771,6 +786,11 @@  struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq->data = data;
 	devfreq->nb.notifier_call = devfreq_notifier_call;
 
+	if (devfreq->profile->timer < 0
+		|| devfreq->profile->timer >= DEVFREQ_TIMER_NUM) {
+		goto err_out;
+	}
+
 	if (!devfreq->profile->max_state && !devfreq->profile->freq_table) {
 		mutex_unlock(&devfreq->lock);
 		err = set_freq_table(devfreq);
@@ -1625,6 +1645,69 @@  static ssize_t trans_stat_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(trans_stat);
 
+static ssize_t timer_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct devfreq *df = to_devfreq(dev);
+
+	if (!df->governor)
+		return -EINVAL;
+
+	return sprintf(buf, "%s\n", timer_name[df->profile->timer]);
+}
+
+static ssize_t timer_store(struct device *dev, struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct devfreq *df = to_devfreq(dev);
+	char str_timer[DEVFREQ_NAME_LEN + 1];
+	int timer = -1;
+	int ret = 0, i;
+
+	if (!df->governor)
+		return -EINVAL;
+
+	ret = sscanf(buf, "%16s", str_timer);
+	if (ret != 1)
+		return -EINVAL;
+
+	for (i = 0; i < DEVFREQ_TIMER_NUM; i++) {
+		if (!strncmp(timer_name[i], str_timer, DEVFREQ_NAME_LEN)) {
+			timer = i;
+			break;
+		}
+	}
+
+	if (timer < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (df->profile->timer == timer) {
+		ret = 0;
+		goto out;
+	}
+
+	mutex_lock(&df->lock);
+	df->profile->timer = timer;
+	mutex_unlock(&df->lock);
+
+	ret = df->governor->event_handler(df, DEVFREQ_GOV_STOP, NULL);
+	if (ret) {
+		dev_warn(dev, "%s: Governor %s not stopped(%d)\n",
+			 __func__, df->governor->name, ret);
+		goto out;
+	}
+
+	ret = df->governor->event_handler(df, DEVFREQ_GOV_START, NULL);
+	if (ret)
+		dev_warn(dev, "%s: Governor %s not started(%d)\n",
+			 __func__, df->governor->name, ret);
+out:
+	return ret ? ret : count;
+}
+static DEVICE_ATTR_RW(timer);
+
 static struct attribute *devfreq_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_governor.attr,
@@ -1636,6 +1719,7 @@  static struct attribute *devfreq_attrs[] = {
 	&dev_attr_min_freq.attr,
 	&dev_attr_max_freq.attr,
 	&dev_attr_trans_stat.attr,
+	&dev_attr_timer.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(devfreq);
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 57e871a559a9..12782fbb4c25 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -31,6 +31,13 @@ 
 #define	DEVFREQ_PRECHANGE		(0)
 #define DEVFREQ_POSTCHANGE		(1)
 
+/* DEVFREQ work timers */
+enum devfreq_timer {
+	DEVFREQ_TIMER_DEFERRABLE = 0,
+	DEVFREQ_TIMER_DELAYED,
+	DEVFREQ_TIMER_NUM,
+};
+
 struct devfreq;
 struct devfreq_governor;
 
@@ -70,6 +77,7 @@  struct devfreq_dev_status {
  * @initial_freq:	The operating frequency when devfreq_add_device() is
  *			called.
  * @polling_ms:		The polling interval in ms. 0 disables polling.
+ * @timer:		Timer type is either deferrable or delayed timer.
  * @target:		The device should set its operating frequency at
  *			freq or lowest-upper-than-freq value. If freq is
  *			higher than any operable frequency, set maximum.
@@ -96,6 +104,7 @@  struct devfreq_dev_status {
 struct devfreq_dev_profile {
 	unsigned long initial_freq;
 	unsigned int polling_ms;
+	enum devfreq_timer timer;
 
 	int (*target)(struct device *dev, unsigned long *freq, u32 flags);
 	int (*get_dev_status)(struct device *dev,