Re: [v5, PATCH 4/5] cpufreq: mediatek: add opp notification for SVS support

[Viresh Kumar]

On 26-11-19, 19:50, Andrew-sh.Cheng wrote:
> diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
> index 4b0cc50dd93b..7c37ab31230a 100644
> --- a/drivers/cpufreq/mediatek-cpufreq.c
> +++ b/drivers/cpufreq/mediatek-cpufreq.c
> @@ -42,6 +42,10 @@ struct mtk_cpu_dvfs_info {
>  	struct list_head list_head;
>  	int intermediate_voltage;
>  	bool need_voltage_tracking;
> +	struct mutex lock; /* avoid notify and policy race condition */

Will a read-write lock be better suited here for performance reasons ?

> +	struct notifier_block opp_nb;
> +	int opp_cpu;
> +	unsigned long opp_freq;
>  };
>  
>  static LIST_HEAD(dvfs_info_list);
> @@ -231,6 +235,7 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
>  	vproc = dev_pm_opp_get_voltage(opp);
>  	dev_pm_opp_put(opp);
>  
> +	mutex_lock(&info->lock);
>  	/*
>  	 * If the new voltage or the intermediate voltage is higher than the
>  	 * current voltage, scale up voltage first.
> @@ -242,6 +247,7 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
>  			pr_err("cpu%d: failed to scale up voltage!\n",
>  			       policy->cpu);
>  			mtk_cpufreq_set_voltage(info, old_vproc);
> +			mutex_unlock(&info->lock);
>  			return ret;
>  		}
>  	}
> @@ -253,6 +259,7 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
>  		       policy->cpu);
>  		mtk_cpufreq_set_voltage(info, old_vproc);
>  		WARN_ON(1);
> +		mutex_unlock(&info->lock);
>  		return ret;
>  	}
>  
> @@ -263,6 +270,7 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
>  		       policy->cpu);
>  		clk_set_parent(cpu_clk, armpll);
>  		mtk_cpufreq_set_voltage(info, old_vproc);
> +		mutex_unlock(&info->lock);
>  		return ret;
>  	}
>  
> @@ -273,6 +281,7 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
>  		       policy->cpu);
>  		mtk_cpufreq_set_voltage(info, inter_vproc);
>  		WARN_ON(1);
> +		mutex_unlock(&info->lock);
>  		return ret;
>  	}
>  
> @@ -288,15 +297,75 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
>  			clk_set_parent(cpu_clk, info->inter_clk);
>  			clk_set_rate(armpll, old_freq_hz);
>  			clk_set_parent(cpu_clk, armpll);
> +			mutex_unlock(&info->lock);
>  			return ret;
>  		}
>  	}
>  
> +	info->opp_freq = freq_hz;
> +	mutex_unlock(&info->lock);
> +
>  	return 0;
>  }
>  
>  #define DYNAMIC_POWER "dynamic-power-coefficient"
>  
> +static int mtk_cpufreq_opp_notifier(struct notifier_block *nb,
> +				    unsigned long event, void *data)
> +{
> +	struct dev_pm_opp *opp = data;
> +	struct dev_pm_opp *opp_item;
> +	struct mtk_cpu_dvfs_info *info =
> +		container_of(nb, struct mtk_cpu_dvfs_info, opp_nb);

Do the assignment after all definitions, instead of awkwardly breaking
the line here.

> +	unsigned long freq, volt;
> +	struct cpufreq_policy *policy;
> +	int ret = 0;
> +
> +	if (event == OPP_EVENT_ADJUST_VOLTAGE) {
> +		freq = dev_pm_opp_get_freq(opp);
> +
> +		mutex_lock(&info->lock);
> +		if (info->opp_freq == freq) {
> +			volt = dev_pm_opp_get_voltage(opp);
> +			ret = mtk_cpufreq_set_voltage(info, volt);
> +			if (ret)
> +				dev_err(info->cpu_dev, "failed to scale voltage: %d\n",
> +					ret);
> +		}
> +		mutex_unlock(&info->lock);
> +	} else if (event == OPP_EVENT_DISABLE) {
> +		freq = info->opp_freq;
> +		opp_item = dev_pm_opp_find_freq_ceil(info->cpu_dev, &freq);

name it new_opp instead of opp_item.

> +		if (!IS_ERR(opp_item))
> +			dev_pm_opp_put(opp_item);
> +		else
> +			freq = 0;
> +

What is the purpose of the above code ?

> +		/* case of current opp is disabled */
> +		if (freq == 0 || freq != info->opp_freq) {
> +			// find an enable opp item

Use proper commenting style please.

> +			freq = 1;
> +			opp_item = dev_pm_opp_find_freq_ceil(info->cpu_dev,
> +							     &freq);
> +			if (!IS_ERR(opp_item)) {
> +				dev_pm_opp_put(opp_item);
> +				policy = cpufreq_cpu_get(info->opp_cpu);
> +				if (policy) {
> +					cpufreq_driver_target(policy,
> +						freq / 1000,
> +						CPUFREQ_RELATION_L);

Why don't you simply call this instead of all the code in the else
block ?

> +					cpufreq_cpu_put(policy);
> +				}
> +			} else {
> +				pr_err("%s: all opp items are disabled\n",
> +				       __func__);
> +			}
> +		}
> +	}
> +
> +	return notifier_from_errno(ret);
> +}
> +
>  static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
>  {
>  	struct device *cpu_dev;
> @@ -383,11 +452,21 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
>  	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
>  	dev_pm_opp_put(opp);
>  
> +	info->opp_cpu = cpu;
> +	info->opp_nb.notifier_call = mtk_cpufreq_opp_notifier;
> +	ret = dev_pm_opp_register_notifier(cpu_dev, &info->opp_nb);
> +	if (ret) {
> +		pr_warn("cannot register opp notification\n");
> +		goto out_free_opp_table;
> +	}
> +
> +	mutex_init(&info->lock);
>  	info->cpu_dev = cpu_dev;
>  	info->proc_reg = proc_reg;
>  	info->sram_reg = IS_ERR(sram_reg) ? NULL : sram_reg;
>  	info->cpu_clk = cpu_clk;
>  	info->inter_clk = inter_clk;
> +	info->opp_freq = clk_get_rate(cpu_clk);
>  
>  	/*
>  	 * If SRAM regulator is present, software "voltage tracking" is needed
> -- 
> 2.12.5

-- 
viresh