[v4,3/6] cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support

Message ID 20210727152512.1098329-4-thara.gopinath@linaro.org
State New
Headers show
Series
  • Introduce LMh driver for Qualcomm SoCs
Related show

Commit Message

Thara Gopinath July 27, 2021, 3:25 p.m.
Add interrupt support to notify the kernel of h/w initiated frequency
throttling by LMh. Convey this to scheduler via thermal presssure
interface.

Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
---

v3->v4:
	- Dropped devm_ versions of request_irq and free_irq as per comments on
	  mailing list.
	- Introduced locking to prevent race between LMh de-init sequence and
	  re-enabling of interrupts/polling after a thermal throttle event.
	- Moved the LMh de-init sequence to qcom_cpufreq_hw_lmh_exit as per
	  Viresh's review comments
	- Code rearrangement as per Bjorn's review comments.
	- Moved the interrupt handling to threaded interrupt handling since Steev
	  reported some scheduling while atomic bug on the mailing list.

v2->v3:
	- Cosmetic fixes from review comments on the list.
	- Moved all LMh initializations to qcom_cpufreq_hw_lmh_init.
	- Added freeing of LMh interrupt and cancelling the polling worker to
	  qcom_cpufreq_hw_cpu_exit as per Viresh's suggestion.
	- LMh interrupts are now tied to cpu dev and not cpufreq dev. This will be
	  useful for further generation of SoCs where the same interrupt signals
	  multiple cpu clusters.

v1->v2:
	- Introduced qcom_cpufreq_hw_lmh_init to consolidate LMh related initializations
	  as per Viresh's review comment.
	- Moved the piece of code restarting polling/re-enabling LMh interrupt to
	  qcom_lmh_dcvs_notify therby simplifying isr and timer callback as per Viresh's
	  suggestion.
	- Droped cpus from qcom_cpufreq_data and instead using cpus from cpufreq_policy in
	  qcom_lmh_dcvs_notify as per Viresh's review comment.
	- Dropped dt property qcom,support-lmh as per Bjorn's suggestion.
	- Other minor/cosmetic fixes

 drivers/cpufreq/qcom-cpufreq-hw.c | 142 ++++++++++++++++++++++++++++++
 1 file changed, 142 insertions(+)

Comments

Viresh Kumar July 28, 2021, 3:50 a.m. | #1
On 27-07-21, 11:25, Thara Gopinath wrote:
> +static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
> +{

> +	/* In the unlikely case cpufreq is de-registered do not enable polling or h/w interrupt */
> +
> +	spin_lock(&data->throttle_lock);
> +	if (data->cancel_throttle) {
> +		spin_unlock(&data->throttle_lock);
> +		return;
> +	}
> +	spin_unlock(&data->throttle_lock);
> +
> +	/*
> +	 * If h/w throttled frequency is higher than what cpufreq has requested for, stop
> +	 * polling and switch back to interrupt mechanism
> +	 */
> +
> +	if (throttled_freq >= qcom_cpufreq_hw_get(cpumask_first(policy->cpus)))
> +		/* Clear the existing interrupts and enable it back */
> +		enable_irq(data->throttle_irq);
> +	else
> +		mod_delayed_work(system_highpri_wq, &data->throttle_work,
> +				 msecs_to_jiffies(10));
> +}

> +static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
> +{
> +	if (data->throttle_irq <= 0)
> +		return;
> +
> +	spin_lock(&data->throttle_lock);
> +	data->cancel_throttle = true;
> +	spin_unlock(&data->throttle_lock);
> +	cancel_delayed_work_sync(&data->throttle_work);
> +	free_irq(data->throttle_irq, data);
> +}

Lets see if we can still make it break :)

CPU0                                            CPU1

qcom_lmh_dcvs_notify()                          qcom_cpufreq_hw_lmh_exit()

spin_unlock()
                                                spin_lock(),
                                                cancel_throttle = true
                                                spin_unlock()

                                                cancel_delayed_work_sync()
mod_delayed_work()
                                                free_irq()
                                                kfree(data)
qcom_lmh_dcvs_poll()
Uses data.


Sorry, locking is fun :)
Thara Gopinath July 28, 2021, 10:19 p.m. | #2
On 7/27/21 11:50 PM, Viresh Kumar wrote:
> On 27-07-21, 11:25, Thara Gopinath wrote:

>> +static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)

>> +{

> 

>> +	/* In the unlikely case cpufreq is de-registered do not enable polling or h/w interrupt */

>> +

>> +	spin_lock(&data->throttle_lock);

>> +	if (data->cancel_throttle) {

>> +		spin_unlock(&data->throttle_lock);

>> +		return;

>> +	}

>> +	spin_unlock(&data->throttle_lock);

>> +

>> +	/*

>> +	 * If h/w throttled frequency is higher than what cpufreq has requested for, stop

>> +	 * polling and switch back to interrupt mechanism

>> +	 */

>> +

>> +	if (throttled_freq >= qcom_cpufreq_hw_get(cpumask_first(policy->cpus)))

>> +		/* Clear the existing interrupts and enable it back */

>> +		enable_irq(data->throttle_irq);

>> +	else

>> +		mod_delayed_work(system_highpri_wq, &data->throttle_work,

>> +				 msecs_to_jiffies(10));

>> +}

> 

>> +static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)

>> +{

>> +	if (data->throttle_irq <= 0)

>> +		return;

>> +

>> +	spin_lock(&data->throttle_lock);

>> +	data->cancel_throttle = true;

>> +	spin_unlock(&data->throttle_lock);

>> +	cancel_delayed_work_sync(&data->throttle_work);

>> +	free_irq(data->throttle_irq, data);

>> +}

> 

> Lets see if we can still make it break :)

> 

> CPU0                                            CPU1

> 

> qcom_lmh_dcvs_notify()                          qcom_cpufreq_hw_lmh_exit()

> 

> spin_unlock()

>                                                  spin_lock(),

>                                                  cancel_throttle = true

>                                                  spin_unlock()

> 

>                                                  cancel_delayed_work_sync()

> mod_delayed_work()

>                                                  free_irq()

>                                                  kfree(data)

> qcom_lmh_dcvs_poll()

> Uses data.

> 

> 

> Sorry, locking is fun :)


Ha! I was too lazy to write this down! So how about I make this a mutex 
and put mod_delayed_work() inside the lock. So it will be something like 
below

qcom_lmh_dcvs_notify()			qcom_cpufreq_hw_lmh_exit()

mutex_lock()				mutex_lock()
   if (data->cancel_throttle) {		cancel_throttle = true
	mutex_unlock()			mutex_unlock()
	return				cancel_delayed_work_sync()
   }					free_irq()
   enable_irq() / mod_delayed_work()
mutex_unlock()

I will let you break it!

> 


-- 
Warm Regards
Thara (She/Her/Hers)
Thara Gopinath July 29, 2021, 11:13 a.m. | #3
On 7/29/21 2:17 AM, Viresh Kumar wrote:
> On 28-07-21, 18:19, Thara Gopinath wrote:

>> Ha! I was too lazy to write this down! So how about I make this a mutex and

> 

> mutex may not work as you come here from irq.


Hi!

So the interrupt handler is a threaded handler. I moved it in v4 since 
one of the "_opp" api has an underlying mutex and was causing issues. So 
using a mutex should be pretty safe in this case.

> 

>> put mod_delayed_work() inside the lock. So it will be something like below

>>

>> qcom_lmh_dcvs_notify()			qcom_cpufreq_hw_lmh_exit()

>>

>> mutex_lock()				mutex_lock()

>>    if (data->cancel_throttle) {		cancel_throttle = true

>> 	mutex_unlock()			mutex_unlock()

>> 	return				cancel_delayed_work_sync()

>>    }					free_irq()

>>    enable_irq() / mod_delayed_work()

>> mutex_unlock()

>>

>> I will let you break it!

> 

> I can't any further :)

> 

> Consider merging below to this patch, it fixes sever other minor

> issues I see in the code.


IIUC, the main change you are suggesting below is to include 
enable_irq() / mod_delayed_work() under the spin_lock as well. Is that 
right ? In which case isn't a mutex better than spinlock?

> 


-- 
Warm Regards
Thara (She/Her/Hers)

Patch

diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index f86859bf76f1..3cc27d9e2ed1 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -7,12 +7,14 @@ 
 #include <linux/cpufreq.h>
 #include <linux/init.h>
 #include <linux/interconnect.h>
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 
 #define LUT_MAX_ENTRIES			40U
 #define LUT_SRC				GENMASK(31, 30)
@@ -22,10 +24,13 @@ 
 #define CLK_HW_DIV			2
 #define LUT_TURBO_IND			1
 
+#define HZ_PER_KHZ			1000
+
 struct qcom_cpufreq_soc_data {
 	u32 reg_enable;
 	u32 reg_freq_lut;
 	u32 reg_volt_lut;
+	u32 reg_current_vote;
 	u32 reg_perf_state;
 	u8 lut_row_size;
 };
@@ -33,7 +38,13 @@  struct qcom_cpufreq_soc_data {
 struct qcom_cpufreq_data {
 	void __iomem *base;
 	struct resource *res;
+	struct delayed_work throttle_work;
 	const struct qcom_cpufreq_soc_data *soc_data;
+	struct cpufreq_policy *policy;
+	/* Lock to synchronize between de-init sequence and re-starting LMh polling/interrupts */
+	spinlock_t throttle_lock;
+	int throttle_irq;
+	bool cancel_throttle;
 };
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -251,10 +262,92 @@  static void qcom_get_related_cpus(int index, struct cpumask *m)
 	}
 }
 
+static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
+{
+	unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote);
+
+	return (val & 0x3FF) * 19200;
+}
+
+static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
+{
+	struct cpufreq_policy *policy = data->policy;
+	struct dev_pm_opp *opp;
+	struct device *dev;
+	unsigned long max_capacity, capacity, freq_hz, throttled_freq;
+	unsigned int freq;
+
+	/*
+	 * Get the h/w throttled frequency, normalize it using the
+	 * registered opp table and use it to calculate thermal pressure.
+	 */
+	freq = qcom_lmh_get_throttle_freq(data);
+	freq_hz = freq * HZ_PER_KHZ;
+
+	dev = get_cpu_device(cpumask_first(policy->cpus));
+	opp = dev_pm_opp_find_freq_floor(dev, &freq_hz);
+	if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE)
+		opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz);
+
+	throttled_freq = freq_hz / HZ_PER_KHZ;
+
+	/* Update thermal pressure */
+
+	max_capacity = arch_scale_cpu_capacity(cpumask_first(policy->cpus));
+	capacity = mult_frac(max_capacity, throttled_freq, policy->cpuinfo.max_freq);
+	/* Don't pass boost capacity to scheduler */
+	if (capacity > max_capacity)
+		capacity = max_capacity;
+
+	arch_set_thermal_pressure(policy->cpus, max_capacity - capacity);
+
+	/* In the unlikely case cpufreq is de-registered do not enable polling or h/w interrupt */
+
+	spin_lock(&data->throttle_lock);
+	if (data->cancel_throttle) {
+		spin_unlock(&data->throttle_lock);
+		return;
+	}
+	spin_unlock(&data->throttle_lock);
+
+	/*
+	 * If h/w throttled frequency is higher than what cpufreq has requested for, stop
+	 * polling and switch back to interrupt mechanism
+	 */
+
+	if (throttled_freq >= qcom_cpufreq_hw_get(cpumask_first(policy->cpus)))
+		/* Clear the existing interrupts and enable it back */
+		enable_irq(data->throttle_irq);
+	else
+		mod_delayed_work(system_highpri_wq, &data->throttle_work,
+				 msecs_to_jiffies(10));
+}
+
+static void qcom_lmh_dcvs_poll(struct work_struct *work)
+{
+	struct qcom_cpufreq_data *data;
+
+	data = container_of(work, struct qcom_cpufreq_data, throttle_work.work);
+
+	qcom_lmh_dcvs_notify(data);
+}
+
+static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
+{
+	struct qcom_cpufreq_data *c_data = data;
+
+	/* Disable interrupt and enable polling */
+	disable_irq_nosync(c_data->throttle_irq);
+	qcom_lmh_dcvs_notify(c_data);
+
+	return 0;
+}
+
 static const struct qcom_cpufreq_soc_data qcom_soc_data = {
 	.reg_enable = 0x0,
 	.reg_freq_lut = 0x110,
 	.reg_volt_lut = 0x114,
+	.reg_current_vote = 0x704,
 	.reg_perf_state = 0x920,
 	.lut_row_size = 32,
 };
@@ -274,6 +367,50 @@  static const struct of_device_id qcom_cpufreq_hw_match[] = {
 };
 MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match);
 
+static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
+{
+	struct qcom_cpufreq_data *data = policy->driver_data;
+	struct platform_device *pdev = cpufreq_get_driver_data();
+	char irq_name[15];
+	int ret;
+
+	/*
+	 * Look for LMh interrupt. If no interrupt line is specified /
+	 * if there is an error, allow cpufreq to be enabled as usual.
+	 */
+	data->throttle_irq = platform_get_irq(pdev, index);
+	if (data->throttle_irq <= 0)
+		return data->throttle_irq == -EPROBE_DEFER ? -EPROBE_DEFER : 0;
+
+	data->cancel_throttle = false;
+	data->policy = policy;
+
+	spin_lock_init(&data->throttle_lock);
+	INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll);
+
+	snprintf(irq_name, sizeof(irq_name), "dcvsh-irq-%u", policy->cpu);
+	ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq,
+				   IRQF_ONESHOT, irq_name, data);
+	if (ret) {
+		dev_err(&pdev->dev, "Error registering %s: %d\n", irq_name, ret);
+		return 0;
+	}
+
+	return 0;
+}
+
+static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+{
+	if (data->throttle_irq <= 0)
+		return;
+
+	spin_lock(&data->throttle_lock);
+	data->cancel_throttle = true;
+	spin_unlock(&data->throttle_lock);
+	cancel_delayed_work_sync(&data->throttle_work);
+	free_irq(data->throttle_irq, data);
+}
+
 static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 {
 	struct platform_device *pdev = cpufreq_get_driver_data();
@@ -370,6 +507,10 @@  static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 			dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
 	}
 
+	ret = qcom_cpufreq_hw_lmh_init(policy, index);
+	if (ret)
+		goto error;
+
 	return 0;
 error:
 	kfree(data);
@@ -389,6 +530,7 @@  static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
 
 	dev_pm_opp_remove_all_dynamic(cpu_dev);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
+	qcom_cpufreq_hw_lmh_exit(data);
 	kfree(policy->freq_table);
 	kfree(data);
 	iounmap(base);