Re: [PATCH 12/15] hwmon, fam15h_power: introduce a cpu accumulated power reporting algorithm

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Aug 27, 2015 at 04:07:43PM +0800, Huang Rui wrote:
> +static ssize_t show_power_acc(struct device *dev,
> +			      struct device_attribute *attr, char *buf)
> +{
> +	int cpu, cu, cu_num, cores_per_cu;
> +	u64 curr_cu_acc_power[MAX_CUS],
> +	    curr_ptsc[MAX_CUS], jdelta[MAX_CUS];
> +	u64 tdelta, avg_acc;
> +	struct fam15h_power_data *data = dev_get_drvdata(dev);
> +
> +	cores_per_cu = amd_get_cores_per_cu();
> +	cu_num = boot_cpu_data.x86_max_cores / cores_per_cu;
> +
> +	for (cpu = 0, avg_acc = 0; cpu < cu_num * cores_per_cu; cpu += cores_per_cu) {
> +		cu = cpu / cores_per_cu;
> +		if (rdmsrl_safe_on_cpu(cpu, MSR_F15H_PTSC, &curr_ptsc[cu])) {
> +			pr_err("Failed to read PTSC counter MSR on core%d\n",
> +			       cpu);
> +			return 0;
> +		}
> +
> +		if (rdmsrl_safe_on_cpu(cpu, MSR_F15H_CU_PWR_ACCUMULATOR,
> +				       &curr_cu_acc_power[cu])) {
> +			pr_err("Failed to read compute unit power accumulator MSR on core%d\n",
> +			       cpu);
> +			return 0;
> +		}
> +
> +		if (curr_cu_acc_power[cu] < data->cu_acc_power[cu]) {
> +			jdelta[cu] = data->max_cu_acc_power + curr_cu_acc_power[cu];
> +			jdelta[cu] -= data->cu_acc_power[cu];
> +		} else {
> +			jdelta[cu] = curr_cu_acc_power[cu] - data->cu_acc_power[cu];
> +		}
> +		tdelta = curr_ptsc[cu] - data->cpu_sw_pwr_ptsc[cu];
> +		jdelta[cu] *= data->cpu_pwr_sample_ratio * 1000;
> +		do_div(jdelta[cu], tdelta);
> +
> +		mutex_lock(&data->acc_pwr_mutex);
> +		data->cu_acc_power[cu] = curr_cu_acc_power[cu];
> +		data->cpu_sw_pwr_ptsc[cu] = curr_ptsc[cu];
> +		mutex_unlock(&data->acc_pwr_mutex);
> +
> +		/* the unit is microWatt */
> +		avg_acc += jdelta[cu];
> +	}
> +
> +	return sprintf(buf, "%u\n", (unsigned int) avg_acc);
> +}
> +static DEVICE_ATTR(power1_acc, S_IRUGO, show_power_acc, NULL);

This is a world readable file that sprays IPIs across the entire system,
how is that a good idea?