On Mon, Mar 28, 2016 at 01:32:14PM +0800, Huang Rui wrote:
> This patch introduces an algorithm that computes the average power by
> reading a delta value of “core power accumulator” register during
> measurement interval, and then dividing delta value by the length of
> the time interval.
> 
> User is able to use power1_average entry to measure the processor power
> consumption and power1_average_interval entry to set the interval.
> 
> A simple example:
> 
> ray@hr-ub:~/tip$ sensors
> fam15h_power-pci-00c4
> Adapter: PCI adapter
> power1:       19.58 mW (avg =   2.55 mW, interval =   0.01 s)
>                        (crit =  15.00 W)
> 
> ...
> 
> The result is current average processor power consumption in 10
> millisecond. The unit of the result is uWatt.
> 
> Suggested-by: Guenter Roeck <li...@roeck-us.net>
> Signed-off-by: Huang Rui <ray.hu...@amd.com>
> Cc: Borislav Petkov <b...@alien8.de>
> ---
>  drivers/hwmon/fam15h_power.c | 119 
> +++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 119 insertions(+)
> 
> diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
> index de6f52b..003564b 100644
> --- a/drivers/hwmon/fam15h_power.c
> +++ b/drivers/hwmon/fam15h_power.c
> @@ -27,6 +27,8 @@
>  #include <linux/bitops.h>
>  #include <linux/cpu.h>
>  #include <linux/cpumask.h>
> +#include <linux/time.h>
> +#include <linux/sched.h>
>  #include <asm/processor.h>
>  #include <asm/msr.h>
>  
> @@ -48,6 +50,9 @@ MODULE_LICENSE("GPL");
>  #define FAM15H_NUM_GROUPS            2
>  #define MAX_CUS                              8
>  
> +/* set maximum interval as 1 second */
> +#define MAX_INTERVAL                 1000
> +
>  #define MSR_F15H_CU_PWR_ACCUMULATOR  0xc001007a
>  #define MSR_F15H_CU_MAX_PWR_ACCUMULATOR      0xc001007b
>  #define MSR_F15H_PTSC                        0xc0010280
> @@ -68,6 +73,9 @@ struct fam15h_power_data {
>       u64 cu_acc_power[MAX_CUS];
>       /* performance timestamp counter */
>       u64 cpu_sw_pwr_ptsc[MAX_CUS];
> +     /* online/offline status of current compute unit */
> +     int cu_on[MAX_CUS];
> +     unsigned long power_period;
>  };
>  
>  static ssize_t show_power(struct device *dev,
> @@ -149,6 +157,8 @@ static void do_read_registers_on_cu(void *_data)
>  
>       rdmsrl_safe(MSR_F15H_CU_PWR_ACCUMULATOR, &data->cu_acc_power[cu]);
>       rdmsrl_safe(MSR_F15H_PTSC, &data->cpu_sw_pwr_ptsc[cu]);
> +
> +     data->cu_on[cu] = 1;
>  }
>  
>  /*
> @@ -165,6 +175,8 @@ static int read_registers(struct fam15h_power_data *data)
>       if (!ret)
>               return -ENOMEM;
>  
> +     memset(data->cu_on, 0, sizeof(int) * MAX_CUS);
> +
>       get_online_cpus();
>       this_cpu = get_cpu();
>  
> @@ -192,18 +204,117 @@ static int read_registers(struct fam15h_power_data 
> *data)
>       return 0;
>  }
>  
> +static ssize_t acc_show_power(struct device *dev,
> +                           struct device_attribute *attr,
> +                           char *buf)
> +{
> +     struct fam15h_power_data *data = dev_get_drvdata(dev);
> +     u64 prev_cu_acc_power[MAX_CUS], prev_ptsc[MAX_CUS],
> +         jdelta[MAX_CUS];
> +     u64 tdelta, avg_acc;
> +     int cu, cu_num, ret;
> +     signed long leftover;
> +
> +     /*
> +      * With the new x86 topology modelling, x86_max_cores is the
> +      * compute unit number.
> +      */
> +     cu_num = boot_cpu_data.x86_max_cores;
> +
> +     ret = read_registers(data);
> +     if (ret)
> +             return 0;
> +
> +     for (cu = 0; cu < cu_num; cu++) {
> +             prev_cu_acc_power[cu] = data->cu_acc_power[cu];
> +             prev_ptsc[cu] = data->cpu_sw_pwr_ptsc[cu];
> +     }
> +
> +     leftover = 
> schedule_timeout_interruptible(msecs_to_jiffies(data->power_period));
> +     if (leftover)
> +             return 0;
> +
> +     ret = read_registers(data);
> +     if (ret)
> +             return 0;
> +
> +     for (cu = 0, avg_acc = 0; cu < cu_num; cu++) {
> +             /* check if current compute unit is online */
> +             if (data->cu_on[cu] == 0)
> +                     continue;
> +
> +             if (data->cu_acc_power[cu] < prev_cu_acc_power[cu]) {
> +                     jdelta[cu] = data->max_cu_acc_power + 
> data->cu_acc_power[cu];
> +                     jdelta[cu] -= prev_cu_acc_power[cu];
> +             } else {
> +                     jdelta[cu] = data->cu_acc_power[cu] - 
> prev_cu_acc_power[cu];
> +             }
> +             tdelta = data->cpu_sw_pwr_ptsc[cu] - prev_ptsc[cu];
> +             jdelta[cu] *= data->cpu_pwr_sample_ratio * 1000;
> +             do_div(jdelta[cu], tdelta);
> +
> +             /* the unit is microWatt */
> +             avg_acc += jdelta[cu];
> +     }
> +
> +     return sprintf(buf, "%llu\n", (unsigned long long)avg_acc);
> +}
> +static DEVICE_ATTR(power1_average, S_IRUGO, acc_show_power, NULL);
> +
> +static ssize_t acc_show_power_period(struct device *dev,
> +                                  struct device_attribute *attr,
> +                                  char *buf)
> +{
> +     struct fam15h_power_data *data = dev_get_drvdata(dev);
> +
> +     return sprintf(buf, "%lu\n", data->power_period);
> +}
> +
> +static ssize_t acc_set_power_period(struct device *dev,
> +                                 struct device_attribute *attr,
> +                                 const char *buf, size_t count)
> +{
> +     struct fam15h_power_data *data = dev_get_drvdata(dev);
> +     unsigned long temp;
> +     int ret;
> +
> +     ret = kstrtoul(buf, 10, &temp);
> +     if (ret)
> +             return ret;
> +
> +     if (temp > MAX_INTERVAL)
> +             return -EINVAL;
> +
> +     /* the interval value should be greater than 0 */
> +     if (temp <= 0)
> +             return -EINVAL;
> +
> +     data->power_period = temp;
> +
> +     return count;
> +}
> +static DEVICE_ATTR(power1_average_interval, S_IRUGO | S_IWUSR,
> +                acc_show_power_period, acc_set_power_period);
> +
>  static int fam15h_power_init_attrs(struct pci_dev *pdev,
>                                  struct fam15h_power_data *data)
>  {
>       int n = FAM15H_MIN_NUM_ATTRS;
>       struct attribute **fam15h_power_attrs;
>       struct cpuinfo_x86 *c = &boot_cpu_data;
> +     u32 cpuid;
>  
>       if (c->x86 == 0x15 &&
>           (c->x86_model <= 0xf ||
>            (c->x86_model >= 0x60 && c->x86_model <= 0x7f)))
>               n += 1;
>  
> +     cpuid = cpuid_edx(0x80000007);
> +
> +     /* check if processor supports accumulated power */
> +     if (cpuid & BIT(12))
> +             n += 2;

        if (boot_cpu_has(X86_FEATURE_ACC_POWER))

> +
>       fam15h_power_attrs = devm_kcalloc(&pdev->dev, n,
>                                         sizeof(*fam15h_power_attrs),
>                                         GFP_KERNEL);
> @@ -218,6 +329,11 @@ static int fam15h_power_init_attrs(struct pci_dev *pdev,
>            (c->x86_model >= 0x60 && c->x86_model <= 0x7f)))
>               fam15h_power_attrs[n++] = &dev_attr_power1_input.attr;
>  
> +     if (cpuid & BIT(12)) {

Ditto.

> +             fam15h_power_attrs[n++] = &dev_attr_power1_average.attr;
> +             fam15h_power_attrs[n++] = 
> &dev_attr_power1_average_interval.attr;
> +     }
> +
>       data->group.attrs = fam15h_power_attrs;
>  
>       return 0;
> @@ -330,6 +446,9 @@ static int fam15h_power_init_data(struct pci_dev *f4,
>  
>       data->max_cu_acc_power = tmp;
>  
> +     /* set default interval as 10 ms */

Because...?

> +     data->power_period = 10;
> +
>       return read_registers(data);
>  }
>  
> -- 
> 1.9.1
> 
> 

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.

Reply via email to