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

[Huang Rui <ray.huang@amd.com>]

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_acc entry to measure the processor power
consumption and power1_acc just needs to be read twice with an needed
interval in-between.

A simple example:

$ cat /sys/bus/pci/devices/0000\:00\:18.4/hwmon/hwmon0/power1_acc
$ sleep 10000s
$ cat /sys/bus/pci/devices/0000\:00\:18.4/hwmon/hwmon0/power1_acc

The result is current average processor power consumption in 10000
seconds. The unit of the result is uWatt.

Signed-off-by: Huang Rui <ray.huang@amd.com>
---
 drivers/hwmon/fam15h_power.c | 62 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index d529e4b..3bab797 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -60,6 +60,7 @@ struct fam15h_power_data {
 	u64 cu_acc_power[MAX_CUS];
 	/* performance timestamp counter */
 	u64 cpu_sw_pwr_ptsc[MAX_CUS];
+	struct mutex acc_pwr_mutex;
 };
 
 static ssize_t show_power(struct device *dev,
@@ -121,17 +122,74 @@ static DEVICE_ATTR(power1_crit, S_IRUGO, show_power_crit, NULL);
 static struct attribute_group fam15h_power_group;
 __ATTRIBUTE_GROUPS(fam15h_power);
 
+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);
+
 static int fam15h_power_init_attrs(struct pci_dev *pdev)
 {
 	int n = FAM15H_MIN_POWER_GROUPS;
 	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 <= 0x6f)))
 		n += 1;
 
+	cpuid = cpuid_edx(0x80000007);
+
+	/* check if processor supports accumulated power */
+	if (cpuid & BIT(12))
+		n += 1;
+
 	fam15h_power_attrs = devm_kcalloc(&pdev->dev, n,
 					  sizeof(*fam15h_power_attrs),
 					  GFP_KERNEL);
@@ -148,6 +206,9 @@ static int fam15h_power_init_attrs(struct pci_dev *pdev)
 	     (c->x86_model >= 0x60 && c->x86_model <= 0x6f)))
 		fam15h_power_attrs[n++] = &dev_attr_power1_input.attr;
 
+	if (cpuid & BIT(12))
+		fam15h_power_attrs[n++] = &dev_attr_power1_acc.attr;
+
 	fam15h_power_group.attrs = fam15h_power_attrs;
 
 	return 0;
@@ -311,6 +372,7 @@ static int fam15h_power_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
+	mutex_init(&data->acc_pwr_mutex);
 	data->pdev = pdev;
 
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev, "fam15h_power",
-- 
1.9.1