[PATCH v3] hwmon driver for ACPI 4.0 power meters

[PATCH v3] hwmon driver for ACPI 4.0 power meters

[Darrick J. Wong]

This driver exposes ACPI 4.0 compliant power meters as hardware monitoring
devices.  This second revision of the driver also exports the ACPI string
info as sysfs attributes, a list of the devices that the meter measures,
and will send ACPI notifications over the ACPI netlink socket.  This latest
revision only enables the power capping controls if it can be confirmed that
the power cap can be enforced by the hardware.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
---

 Documentation/hwmon/acpi_power_meter |   31 +
 drivers/acpi/Kconfig                 |   12 
 drivers/acpi/Makefile                |    1 
 drivers/acpi/power_meter.c           | 1017 ++++++++++++++++++++++++++++++++++
 4 files changed, 1061 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/hwmon/acpi_power_meter
 create mode 100644 drivers/acpi/power_meter.c


diff --git a/Documentation/hwmon/acpi_power_meter b/Documentation/hwmon/acpi_power_meter
new file mode 100644
index 0000000..b02ddaa
--- /dev/null
+++ b/Documentation/hwmon/acpi_power_meter
@@ -0,0 +1,31 @@
+Kernel driver power_meter
+=========================
+
+This driver talks to ACPI 4.0 power meters.
+
+Supported systems:
+  * Any recent system with ACPI 4.0.
+    Prefix: 'power_meter'
+    Datasheet: http://acpi.info/, section 10.4.
+
+Author: Darrick J. Wong
+
+Description
+-----------
+
+This driver implements sensor reading support for the power meters exposed in
+the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
+features--a power meter that returns average power use over a configurable
+interval, an optional capping mechanism, and a couple of trip points.
+
+Special Features
+----------------
+
+The power[1-*]_is_battery knob indicates if the power supply is a battery.
+Both power[1-*]_average_{min,max} must be set before the trip points will work.
+The power[1-*]_{model_number, serial_number, oem_info} fields display arbitrary
+strings that ACPI provides with the meter.
+The measures/ directory contains symlinks to the devices that this meter
+measures.
+ACPI events will be broadcast on the ACPI netlink event socket in addition to
+the poll notifications.
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 7ec7d88..8ac801d 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -82,6 +82,18 @@ config ACPI_PROCFS_POWER
 
 	  Say N to delete power /proc/acpi/ directories that have moved to /sys/
 
+config ACPI_POWER_METER
+	tristate "ACPI 4.0 power meter"
+	depends on HWMON
+	default m
+	help
+	  This driver exposes ACPI 4.0 power meters as hardware monitoring
+	  devices.  Say Y (or M) if you have an Intel or AMD computer with
+	  a power meter.
+
+	  To compile this driver as a module, choose M here:
+	  the module will be called power-meter.
+
 config ACPI_SYSFS_POWER
 	bool "Future power /sys interface"
 	select POWER_SUPPLY
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 03a985b..82cd49d 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_ACPI_HOTPLUG_MEMORY) += acpi_memhotplug.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
 obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
 obj-$(CONFIG_ACPI_SBS)		+= sbs.o
+obj-$(CONFIG_ACPI_POWER_METER)	+= power_meter.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_core.o processor_throttling.o
diff --git a/drivers/acpi/power_meter.c b/drivers/acpi/power_meter.c
new file mode 100644
index 0000000..696091d
--- /dev/null
+++ b/drivers/acpi/power_meter.c
@@ -0,0 +1,1017 @@
+/*
+ * A hwmon driver for ACPI 4.0 power meters
+ * Copyright (C) 2009 IBM
+ *
+ * Author: Darrick J. Wong <djwong@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/jiffies.h>
+#include <linux/mutex.h>
+#include <linux/kdev_t.h>
+#include <linux/sched.h>
+#include <linux/time.h>
+#include <acpi/acpi_drivers.h>
+#include <acpi/acpi_bus.h>
+
+#define ACPI_POWER_METER_NAME		"power_meter"
+ACPI_MODULE_NAME(ACPI_POWER_METER_NAME);
+#define ACPI_POWER_METER_DEVICE_NAME	"Power Meter"
+#define ACPI_POWER_METER_CLASS		"power_meter_resource"
+
+#define NUM_SENSORS			17
+
+#define POWER_METER_CAN_MEASURE	(1 << 0)
+#define POWER_METER_CAN_TRIP	(1 << 1)
+#define POWER_METER_CAN_CAP	(1 << 2)
+#define POWER_METER_CAN_NOTIFY	(1 << 3)
+#define POWER_METER_IS_BATTERY	(1 << 8)
+#define UNKNOWN_HYSTERESIS	0xFFFFFFFF
+
+#define METER_NOTIFY_CONFIG	0x80
+#define METER_NOTIFY_TRIP	0x81
+#define METER_NOTIFY_CAP	0x82
+#define METER_NOTIFY_CAPPING	0x83
+#define METER_NOTIFY_INTERVAL	0x84
+
+#define POWER_AVERAGE_NAME	"power1_average"
+#define POWER_CAP_NAME		"power1_cap"
+#define POWER_AVG_INTERVAL_NAME	"power1_average_interval"
+#define POWER_ALARM_NAME	"power1_alarm"
+
+static int cap_in_hardware;
+static int force_cap_on;
+
+static int can_cap_in_hardware(void)
+{
+	return force_cap_on || cap_in_hardware;
+}
+
+static struct acpi_device_id power_meter_ids[] = {
+	{"ACPI000D", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, power_meter_ids);
+
+struct acpi_power_meter_capabilities {
+	acpi_integer		flags;
+	acpi_integer		units;
+	acpi_integer		type;
+	acpi_integer		accuracy;
+	acpi_integer		sampling_time;
+	acpi_integer		min_avg_interval;
+	acpi_integer		max_avg_interval;
+	acpi_integer		hysteresis;
+	acpi_integer		configurable_cap;
+	acpi_integer		min_cap;
+	acpi_integer		max_cap;
+};
+
+struct acpi_power_meter_resource {
+	struct acpi_device	*acpi_dev;
+	acpi_bus_id		name;
+	struct mutex		lock;
+	struct device		*hwmon_dev;
+	struct acpi_power_meter_capabilities	caps;
+	acpi_string		model_number;
+	acpi_string		serial_number;
+	acpi_string		oem_info;
+	acpi_integer		power;
+	acpi_integer		cap;
+	acpi_integer		avg_interval;
+	int			sensors_valid;
+	unsigned long		sensors_last_updated;
+	struct sensor_device_attribute	sensors[NUM_SENSORS];
+	int			num_sensors;
+	int			trip[2];
+	int			num_domain_devices;
+	struct acpi_device	**domain_devices;
+	struct kobject		*holders_dir;
+};
+
+struct ro_sensor_template {
+	char *label;
+	ssize_t (*show)(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf);
+	int index;
+};
+
+struct rw_sensor_template {
+	char *label;
+	ssize_t (*show)(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf);
+	ssize_t (*set)(struct device *dev,
+		       struct device_attribute *devattr,
+		       const char *buf, size_t count);
+	int index;
+};
+
+/* Averaging interval */
+static int update_avg_interval(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_GAI",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _GAI"));
+		return -ENODEV;
+	}
+
+	resource->avg_interval = data;
+	return 0;
+}
+
+static ssize_t show_avg_interval(struct device *dev,
+				 struct device_attribute *devattr,
+				 char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_avg_interval(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->avg_interval);
+}
+
+static ssize_t set_avg_interval(struct device *dev,
+				struct device_attribute *devattr,
+				const char *buf, size_t count)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+	int res;
+	unsigned long temp;
+	unsigned long long data;
+	acpi_status status;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	if (temp > resource->caps.max_avg_interval ||
+	    temp < resource->caps.min_avg_interval)
+		return -EINVAL;
+	arg0.integer.value = temp;
+
+	mutex_lock(&resource->lock);
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PAI",
+				       &args, &data);
+	if (!ACPI_FAILURE(status))
+		resource->avg_interval = temp;
+	mutex_unlock(&resource->lock);
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PAI"));
+		return -EINVAL;
+	}
+
+	/* _PAI returns 0 on success, nonzero otherwise */
+	if (data)
+		return -EINVAL;
+
+	return count;
+}
+
+/* Cap functions */
+static int update_cap(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_GHL",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _GHL"));
+		return -ENODEV;
+	}
+
+	resource->cap = data;
+	return 0;
+}
+
+static ssize_t show_cap(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_cap(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->cap * 1000);
+}
+
+static ssize_t set_cap(struct device *dev, struct device_attribute *devattr,
+		       const char *buf, size_t count)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+	int res;
+	unsigned long temp;
+	unsigned long long data;
+	acpi_status status;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	temp /= 1000;
+	if (temp > resource->caps.max_cap || temp < resource->caps.min_cap)
+		return -EINVAL;
+	arg0.integer.value = temp;
+
+	mutex_lock(&resource->lock);
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_SHL",
+				       &args, &data);
+	if (!ACPI_FAILURE(status))
+		resource->cap = temp;
+	mutex_unlock(&resource->lock);
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _SHL"));
+		return -EINVAL;
+	}
+
+	/* _SHL returns 0 on success, nonzero otherwise */
+	if (data)
+		return -EINVAL;
+
+	return count;
+}
+
+/* Power meter trip points */
+static int set_acpi_trip(struct acpi_power_meter_resource *resource)
+{
+	union acpi_object arg_objs[] = {
+		{ACPI_TYPE_INTEGER},
+		{ACPI_TYPE_INTEGER}
+	};
+	struct acpi_object_list args = { 2, arg_objs };
+	unsigned long long data;
+	acpi_status status;
+
+	/* Both trip levels must be set */
+	if (resource->trip[0] < 0 || resource->trip[1] < 0)
+		return 0;
+
+	/* This driver stores min, max; ACPI wants max, min. */
+	arg_objs[0].integer.value = resource->trip[1];
+	arg_objs[1].integer.value = resource->trip[0];
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PTP",
+				       &args, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PTP"));
+		return -EINVAL;
+	}
+
+	return data;
+}
+
+static ssize_t set_trip(struct device *dev, struct device_attribute *devattr,
+			const char *buf, size_t count)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	int res;
+	unsigned long temp;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	temp /= 1000;
+	if (temp < 0)
+		return -EINVAL;
+
+	mutex_lock(&resource->lock);
+	resource->trip[attr->index - 7] = temp;
+	res = set_acpi_trip(resource);
+	mutex_unlock(&resource->lock);
+
+	if (res)
+		return res;
+
+	return count;
+}
+
+/* Power meter */
+static int update_meter(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+	unsigned long local_jiffies = jiffies;
+
+	if (time_before(local_jiffies, resource->sensors_last_updated +
+			msecs_to_jiffies(resource->caps.sampling_time)) &&
+			resource->sensors_valid)
+		return 0;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PMM",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMM"));
+		return -ENODEV;
+	}
+
+	resource->power = data;
+	resource->sensors_valid = 1;
+	resource->sensors_last_updated = jiffies;
+	return 0;
+}
+
+static ssize_t show_power(struct device *dev,
+			  struct device_attribute *devattr,
+			  char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_meter(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->power * 1000);
+}
+
+/* Miscellaneous */
+static ssize_t show_str(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	acpi_string val;
+
+	switch (attr->index) {
+	case 0:
+		val = resource->model_number;
+		break;
+	case 1:
+		val = resource->serial_number;
+		break;
+	case 2:
+		val = resource->oem_info;
+		break;
+	default:
+		BUG();
+	}
+
+	return sprintf(buf, "%s\n", val);
+}
+
+static ssize_t show_val(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	acpi_integer val = 0;
+
+	switch (attr->index) {
+	case 0:
+		val = resource->caps.min_avg_interval;
+		break;
+	case 1:
+		val = resource->caps.max_avg_interval;
+		break;
+	case 2:
+		val = resource->caps.min_cap * 1000;
+		break;
+	case 3:
+		val = resource->caps.max_cap * 1000;
+		break;
+	case 4:
+		if (resource->caps.hysteresis == UNKNOWN_HYSTERESIS)
+			return sprintf(buf, "unknown\n");
+
+		val = resource->caps.hysteresis * 1000;
+		break;
+	case 5:
+		if (resource->caps.flags & POWER_METER_IS_BATTERY)
+			val = 1;
+		else
+			val = 0;
+		break;
+	case 6:
+		if (resource->power > resource->cap)
+			val = 1;
+		else
+			val = 0;
+		break;
+	case 7:
+	case 8:
+		if (resource->trip[attr->index - 7] < 0)
+			return sprintf(buf, "unknown\n");
+
+		val = resource->trip[attr->index - 7] * 1000;
+		break;
+	default:
+		BUG();
+	}
+
+	return sprintf(buf, "%llu\n", val);
+}
+
+static ssize_t show_accuracy(struct device *dev,
+			     struct device_attribute *devattr,
+			     char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	unsigned int acc = resource->caps.accuracy;
+
+	return sprintf(buf, "%u.%u%%\n", acc / 1000, acc % 1000);
+}
+
+static ssize_t show_name(struct device *dev,
+			 struct device_attribute *devattr,
+			 char *buf)
+{
+	return sprintf(buf, "%s\n", ACPI_POWER_METER_NAME);
+}
+
+/* Sensor descriptions.  If you add a sensor, update NUM_SENSORS above! */
+static struct ro_sensor_template meter_ro_attrs[] = {
+{POWER_AVERAGE_NAME, show_power, 0},
+{"power1_accuracy", show_accuracy, 0},
+{"power1_average_interval_min", show_val, 0},
+{"power1_average_interval_max", show_val, 1},
+{"power1_is_battery", show_val, 5},
+{NULL, NULL, 0},
+};
+
+static struct rw_sensor_template meter_rw_attrs[] = {
+{POWER_AVG_INTERVAL_NAME, show_avg_interval, set_avg_interval, 0},
+{NULL, NULL, NULL, 0},
+};
+
+static struct ro_sensor_template misc_cap_attrs[] = {
+{"power1_cap_min", show_val, 2},
+{"power1_cap_max", show_val, 3},
+{"power1_cap_hyst", show_val, 4},
+{POWER_ALARM_NAME, show_val, 6},
+{NULL, NULL, 0},
+};
+
+static struct ro_sensor_template ro_cap_attrs[] = {
+{POWER_CAP_NAME, show_cap, 0},
+{NULL, NULL, 0},
+};
+
+static struct rw_sensor_template rw_cap_attrs[] = {
+{POWER_CAP_NAME, show_cap, set_cap, 0},
+{NULL, NULL, NULL, 0},
+};
+
+static struct rw_sensor_template trip_attrs[] = {
+{"power1_average_min", show_val, set_trip, 7},
+{"power1_average_max", show_val, set_trip, 8},
+{NULL, NULL, NULL, 0},
+};
+
+static struct ro_sensor_template misc_attrs[] = {
+{"name", show_name, 0},
+{"power1_model_number", show_str, 0},
+{"power1_oem_info", show_str, 2},
+{"power1_serial_number", show_str, 1},
+{NULL, NULL, 0},
+};
+
+/* Read power domain data */
+static void remove_domain_devices(struct acpi_power_meter_resource *resource)
+{
+	int i;
+
+	if (!resource->num_domain_devices)
+		return;
+
+	for (i = 0; i < resource->num_domain_devices; i++) {
+		struct acpi_device *obj = resource->domain_devices[i];
+		if (!obj)
+			continue;
+
+		sysfs_remove_link(resource->holders_dir,
+				  kobject_name(&obj->dev.kobj));
+		put_device(&obj->dev);
+	}
+
+	kfree(resource->domain_devices);
+	kobject_put(resource->holders_dir);
+}
+
+static int read_domain_devices(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+	int i;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *pss;
+	acpi_status status;
+
+	status = acpi_evaluate_object(resource->acpi_dev->handle, "_PMD", NULL,
+				      &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMD"));
+		return -ENODEV;
+	}
+
+	pss = buffer.pointer;
+	if (!pss ||
+	    pss->type != ACPI_TYPE_PACKAGE) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Invalid _PMD data\n");
+		res = -EFAULT;
+		goto end;
+	}
+
+	if (!pss->package.count)
+		goto end;
+
+	resource->domain_devices = kzalloc(sizeof(struct acpi_device *) *
+					   pss->package.count, GFP_KERNEL);
+	if (!resource->domain_devices) {
+		res = -ENOMEM;
+		goto end;
+	}
+
+	resource->holders_dir = kobject_create_and_add("measures",
+					&resource->acpi_dev->dev.kobj);
+	if (!resource->holders_dir) {
+		res = -ENOMEM;
+		goto exit_free;
+	}
+
+	resource->num_domain_devices = pss->package.count;
+
+	for (i = 0; i < pss->package.count; i++) {
+		struct acpi_device *obj;
+		union acpi_object *element = &(pss->package.elements[i]);
+
+		/* Refuse non-references */
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE)
+			continue;
+
+		/* Create a symlink to domain objects */
+		resource->domain_devices[i] = NULL;
+		status = acpi_bus_get_device(element->reference.handle,
+					     &resource->domain_devices[i]);
+		if (ACPI_FAILURE(status))
+			continue;
+
+		obj = resource->domain_devices[i];
+		get_device(&obj->dev);
+
+		res = sysfs_create_link(resource->holders_dir, &obj->dev.kobj,
+				      kobject_name(&obj->dev.kobj));
+		if (res) {
+			put_device(&obj->dev);
+			resource->domain_devices[i] = NULL;
+		}
+	}
+
+	res = 0;
+	goto end;
+
+exit_free:
+	kfree(resource->domain_devices);
+end:
+	kfree(buffer.pointer);
+	return res;
+}
+
+/* Registration and deregistration */
+static int register_ro_attrs(struct acpi_power_meter_resource *resource,
+			     struct ro_sensor_template *ro)
+{
+	struct device *dev = &resource->acpi_dev->dev;
+	struct sensor_device_attribute *sensors =
+		&resource->sensors[resource->num_sensors];
+	int res = 0;
+
+	while (ro->label) {
+		sensors->dev_attr.attr.name = ro->label;
+		sensors->dev_attr.attr.mode = S_IRUGO;
+		sensors->dev_attr.show = ro->show;
+		sensors->index = ro->index;
+
+		res = device_create_file(dev, &sensors->dev_attr);
+		if (res) {
+			sensors->dev_attr.attr.name = NULL;
+			goto error;
+		}
+		sensors++;
+		resource->num_sensors++;
+		ro++;
+	}
+
+error:
+	return res;
+}
+
+static int register_rw_attrs(struct acpi_power_meter_resource *resource,
+			     struct rw_sensor_template *rw)
+{
+	struct device *dev = &resource->acpi_dev->dev;
+	struct sensor_device_attribute *sensors =
+		&resource->sensors[resource->num_sensors];
+	int res = 0;
+
+	while (rw->label) {
+		sensors->dev_attr.attr.name = rw->label;
+		sensors->dev_attr.attr.mode = S_IRUGO | S_IWUSR;
+		sensors->dev_attr.show = rw->show;
+		sensors->dev_attr.store = rw->set;
+		sensors->index = rw->index;
+
+		res = device_create_file(dev, &sensors->dev_attr);
+		if (res) {
+			sensors->dev_attr.attr.name = NULL;
+			goto error;
+		}
+		sensors++;
+		resource->num_sensors++;
+		rw++;
+	}
+
+error:
+	return res;
+}
+
+static void remove_attrs(struct acpi_power_meter_resource *resource)
+{
+	int i;
+
+	for (i = 0; i < resource->num_sensors; i++) {
+		if (!resource->sensors[i].dev_attr.attr.name)
+			continue;
+		device_remove_file(&resource->acpi_dev->dev,
+				   &resource->sensors[i].dev_attr);
+	}
+
+	remove_domain_devices(resource);
+
+	resource->num_sensors = 0;
+}
+
+static int setup_attrs(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+
+	res = read_domain_devices(resource);
+	if (res)
+		return res;
+
+	if (resource->caps.flags & POWER_METER_CAN_MEASURE) {
+		res = register_ro_attrs(resource, meter_ro_attrs);
+		if (res)
+			goto error;
+		res = register_rw_attrs(resource, meter_rw_attrs);
+		if (res)
+			goto error;
+	}
+
+	if (resource->caps.flags & POWER_METER_CAN_CAP) {
+		if (!can_cap_in_hardware()) {
+			dev_err(&resource->acpi_dev->dev,
+				"Ignoring unsafe software power cap!\n");
+			goto skip_unsafe_cap;
+		}
+
+		if (resource->caps.configurable_cap) {
+			res = register_rw_attrs(resource, rw_cap_attrs);
+			if (res)
+				goto error;
+		} else {
+			res = register_ro_attrs(resource, ro_cap_attrs);
+			if (res)
+				goto error;
+		}
+		res = register_ro_attrs(resource, misc_cap_attrs);
+		if (res)
+			goto error;
+	}
+skip_unsafe_cap:
+
+	if (resource->caps.flags & POWER_METER_CAN_TRIP) {
+		res = register_rw_attrs(resource, trip_attrs);
+		if (res)
+			goto error;
+	}
+
+	res = register_ro_attrs(resource, misc_attrs);
+	if (res)
+		goto error;
+
+	return res;
+error:
+	remove_domain_devices(resource);
+	remove_attrs(resource);
+	return res;
+}
+
+static void free_capabilities(struct acpi_power_meter_resource *resource)
+{
+	acpi_string *str;
+	int i;
+
+	str = &resource->model_number;
+	for (i = 0; i < 3; i++, str++)
+		kfree(*str);
+}
+
+static int read_capabilities(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+	int i;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer state = { 0, NULL };
+	struct acpi_buffer format = { sizeof("NNNNNNNNNNN"), "NNNNNNNNNNN" };
+	union acpi_object *pss;
+	acpi_string *str;
+	acpi_status status;
+
+	status = acpi_evaluate_object(resource->acpi_dev->handle, "_PMC", NULL,
+				      &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMC"));
+		return -ENODEV;
+	}
+
+	pss = buffer.pointer;
+	if (!pss ||
+	    pss->type != ACPI_TYPE_PACKAGE ||
+	    pss->package.count != 14) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Invalid _PMC data\n");
+		res = -EFAULT;
+		goto end;
+	}
+
+	/* Grab all the integer data at once */
+	state.length = sizeof(struct acpi_power_meter_capabilities);
+	state.pointer = &resource->caps;
+
+	status = acpi_extract_package(pss, &format, &state);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Invalid data"));
+		res = -EFAULT;
+		goto end;
+	}
+
+	if (resource->caps.units) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Unknown units %llu.\n",
+			resource->caps.units);
+		res = -EINVAL;
+		goto end;
+	}
+
+	/* Grab the string data */
+	str = &resource->model_number;
+
+	for (i = 11; i < 14; i++) {
+		union acpi_object *element = &(pss->package.elements[i]);
+
+		if (element->type != ACPI_TYPE_STRING) {
+			res = -EINVAL;
+			goto error;
+		}
+
+		*str = kzalloc(sizeof(u8) * (element->string.length + 1),
+			       GFP_KERNEL);
+		if (!*str) {
+			res = -ENOMEM;
+			goto error;
+		}
+
+		strncpy(*str, element->string.pointer, element->string.length);
+		str++;
+	}
+
+	dev_info(&resource->acpi_dev->dev, "Found ACPI power meter.\n");
+	goto end;
+error:
+	str = &resource->model_number;
+	for (i = 0; i < 3; i++, str++)
+		kfree(*str);
+end:
+	kfree(buffer.pointer);
+	return res;
+}
+
+/* Handle ACPI event notifications */
+static void acpi_power_meter_notify(struct acpi_device *device, u32 event)
+{
+	struct acpi_power_meter_resource *resource;
+	int res;
+
+	if (!device || !acpi_driver_data(device))
+		return;
+
+	resource = acpi_driver_data(device);
+
+	mutex_lock(&resource->lock);
+	switch (event) {
+	case METER_NOTIFY_CONFIG:
+		free_capabilities(resource);
+		res = read_capabilities(resource);
+		if (res)
+			break;
+
+		remove_attrs(resource);
+		setup_attrs(resource);
+		break;
+	case METER_NOTIFY_TRIP:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME);
+		update_meter(resource);
+		break;
+	case METER_NOTIFY_CAP:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME);
+		update_cap(resource);
+		break;
+	case METER_NOTIFY_INTERVAL:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME);
+		update_avg_interval(resource);
+		break;
+	case METER_NOTIFY_CAPPING:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME);
+		dev_info(&device->dev, "Capping in progress.\n");
+		break;
+	default:
+		BUG();
+	}
+	mutex_unlock(&resource->lock);
+
+	acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS,
+					dev_name(&device->dev), event, 0);
+}
+
+static int acpi_power_meter_add(struct acpi_device *device)
+{
+	int res;
+	struct acpi_power_meter_resource *resource;
+
+	if (!device)
+		return -EINVAL;
+
+	resource = kzalloc(sizeof(struct acpi_power_meter_resource),
+			   GFP_KERNEL);
+	if (!resource)
+		return -ENOMEM;
+
+	resource->sensors_valid = 0;
+	resource->acpi_dev = device;
+	mutex_init(&resource->lock);
+	strcpy(acpi_device_name(device), ACPI_POWER_METER_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_POWER_METER_CLASS);
+	device->driver_data = resource;
+
+	free_capabilities(resource);
+	res = read_capabilities(resource);
+	if (res)
+		goto exit_free;
+
+	resource->trip[0] = resource->trip[1] = -1;
+
+	res = setup_attrs(resource);
+	if (res)
+		goto exit_free;
+
+	resource->hwmon_dev = hwmon_device_register(&device->dev);
+	if (IS_ERR(resource->hwmon_dev)) {
+		res = PTR_ERR(resource->hwmon_dev);
+		goto exit_remove;
+	}
+
+	res = 0;
+	goto exit;
+
+exit_remove:
+	remove_attrs(resource);
+exit_free:
+	kfree(resource);
+exit:
+	return res;
+}
+
+static int acpi_power_meter_remove(struct acpi_device *device, int type)
+{
+	struct acpi_power_meter_resource *resource;
+
+	if (!device || !acpi_driver_data(device))
+		return -EINVAL;
+
+	resource = acpi_driver_data(device);
+	hwmon_device_unregister(resource->hwmon_dev);
+
+	free_capabilities(resource);
+	remove_attrs(resource);
+
+	kfree(resource);
+	return 0;
+}
+
+static int acpi_power_meter_resume(struct acpi_device *device)
+{
+	struct acpi_power_meter_resource *resource;
+
+	if (!device || !acpi_driver_data(device))
+		return -EINVAL;
+
+	resource = acpi_driver_data(device);
+	free_capabilities(resource);
+	read_capabilities(resource);
+
+	return 0;
+}
+
+static struct acpi_driver acpi_power_meter_driver = {
+	.name = "power_meter",
+	.class = ACPI_POWER_METER_CLASS,
+	.ids = power_meter_ids,
+	.ops = {
+		.add = acpi_power_meter_add,
+		.remove = acpi_power_meter_remove,
+		.resume = acpi_power_meter_resume,
+		.notify = acpi_power_meter_notify,
+		},
+};
+
+/* Module init/exit routines */
+static int __init enable_cap_knobs(const struct dmi_system_id *d)
+{
+	cap_in_hardware = 1;
+	return 0;
+}
+
+static struct dmi_system_id __initdata pm_dmi_table[] = {
+	{
+		enable_cap_knobs, "IBM Active Energy Manager",
+		{
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM")
+		},
+	},
+	{}
+};
+
+static int __init acpi_power_meter_init(void)
+{
+	int result;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	dmi_check_system(pm_dmi_table);
+
+	result = acpi_bus_register_driver(&acpi_power_meter_driver);
+	if (result < 0)
+		return -ENODEV;
+
+	return 0;
+}
+
+static void __exit acpi_power_meter_exit(void)
+{
+	acpi_bus_unregister_driver(&acpi_power_meter_driver);
+}
+
+MODULE_AUTHOR("Darrick J. Wong <djwong@us.ibm.com>");
+MODULE_DESCRIPTION("ACPI 4.0 power meter driver");
+MODULE_LICENSE("GPL");
+
+module_param(force_cap_on, bool, 0644);
+MODULE_PARM_DESC(force_cap_on, "Enable power cap even it is unsafe to do so.");
+
+module_init(acpi_power_meter_init);
+module_exit(acpi_power_meter_exit);

Re: [PATCH v3] hwmon driver for ACPI 4.0 power meters

[Pavel Machek]

Hi!

> diff --git a/Documentation/hwmon/acpi_power_meter b/Documentation/hwmon/acpi_power_meter
> new file mode 100644
> index 0000000..b02ddaa
> --- /dev/null
> +++ b/Documentation/hwmon/acpi_power_meter
> @@ -0,0 +1,31 @@
> +Kernel driver power_meter
> +=========================
> +
> +This driver talks to ACPI 4.0 power meters.
> +
> +Supported systems:
> +  * Any recent system with ACPI 4.0.
> +    Prefix: 'power_meter'
> +    Datasheet: http://acpi.info/, section 10.4.
> +
> +Author: Darrick J. Wong
> +
> +Description
> +-----------
> +
> +This driver implements sensor reading support for the power meters exposed in
> +the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
> +features--a power meter that returns average power use over a configurable
> +interval, an optional capping mechanism, and a couple of trip points.

So where do we get the average power?

> +Special Features
> +----------------
> +
> +The power[1-*]_is_battery knob indicates if the power supply is a battery.
> +Both power[1-*]_average_{min,max} must be set before the trip
> points will work.

How do trip points work? It is not explained here.


> +config ACPI_POWER_METER
> +	tristate "ACPI 4.0 power meter"
> +	depends on HWMON
> +	default m

default M is "evil".

> +	  devices.  Say Y (or M) if you have an Intel or AMD computer with
> +	  a power meter.

WTF? Neither Intel nor AMD makes _computers_.

> +	  To compile this driver as a module, choose M here:
> +	  the module will be called power-meter.

.ko.

> +#define POWER_CAP_NAME		"power1_cap"

I did not see power cap explained.

								Pavel

-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

Re: [PATCH v3] hwmon driver for ACPI 4.0 power meters

[Darrick J. Wong]

On Wed, Sep 09, 2009 at 10:06:38AM +0200, Pavel Machek wrote:

> > +Description
> > +-----------
> > +
> > +This driver implements sensor reading support for the power meters exposed in
> > +the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
> > +features--a power meter that returns average power use over a configurable
> > +interval, an optional capping mechanism, and a couple of trip points.
> 
> So where do we get the average power?

/sys/class/hwmon/hwmonX/device/powerX_average.  Most of the hwmon driver
documentation assumes the reader has read the contents of
Documentation/hwmon/sysfs-interface, but I suppose it wouldn't be too
difficult to call that out explicitly.

(Actually I think you're really supposed to use libsensors and not access sysfs
directly.)

> > +Special Features
> > +----------------
> > +
> > +The power[1-*]_is_battery knob indicates if the power supply is a battery.
> > +Both power[1-*]_average_{min,max} must be set before the trip
> > points will work.
> 
> How do trip points work? It is not explained here.

Will add that too.

> > +config ACPI_POWER_METER
> > +	tristate "ACPI 4.0 power meter"
> > +	depends on HWMON
> > +	default m
> 
> default M is "evil".

I'll change it to Y, but I wonder why you think default M is evil...?

> > +	  devices.  Say Y (or M) if you have an Intel or AMD computer with
> > +	  a power meter.
> 
> WTF? Neither Intel nor AMD makes _computers_.

I'll change that to "a computer with ACPI firmware."

> > +	  To compile this driver as a module, choose M here:
> > +	  the module will be called power-meter.
> 
> .ko.

The other config options in drivers/acpi/Kconfig omit the .ko; I was trying to
be consistent with them.

> > +#define POWER_CAP_NAME		"power1_cap"
> 
> I did not see power cap explained.

I'll add that, thanks for the continued review!

--D

Re: [PATCH v3] hwmon driver for ACPI 4.0 power meters

[Pavel Machek]

On Wed 2009-09-09 11:20:51, Darrick J. Wong wrote:
> On Wed, Sep 09, 2009 at 10:06:38AM +0200, Pavel Machek wrote:
> 
> > > +Description
> > > +-----------
> > > +
> > > +This driver implements sensor reading support for the power meters exposed in
> > > +the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
> > > +features--a power meter that returns average power use over a configurable
> > > +interval, an optional capping mechanism, and a couple of trip points.
> > 
> > So where do we get the average power?
> 
> /sys/class/hwmon/hwmonX/device/powerX_average.  Most of the hwmon driver
> documentation assumes the reader has read the contents of
> Documentation/hwmon/sysfs-interface, but I suppose it wouldn't be too
> difficult to call that out explicitly.

Ok, I did not realize that hwmon/sysfs-interface applies here. Maybe
mention that? Copyring info is probably not good.

> > > +config ACPI_POWER_METER
> > > +	tristate "ACPI 4.0 power meter"
> > > +	depends on HWMON
> > > +	default m
> > 
> > default M is "evil".
> 
> I'll change it to Y, but I wonder why you think default M is evil...?

See the archives. Anyway it should be default to N -- it is new driver
and it is not essential in any way. "default Y" is for features that
were always in and are now optional.

> > > +	  devices.  Say Y (or M) if you have an Intel or AMD computer with
> > > +	  a power meter.
> > 
> > WTF? Neither Intel nor AMD makes _computers_.
> 
> I'll change that to "a computer with ACPI firmware."

I'd add that it only makes sense on very new computers.

> > > +	  To compile this driver as a module, choose M here:
> > > +	  the module will be called power-meter.
> > 
> > .ko.
> 
> The other config options in drivers/acpi/Kconfig omit the .ko; I was trying to
> be consistent with them.

Probably my fault, sorry.

> > > +#define POWER_CAP_NAME		"power1_cap"
> > 
> > I did not see power cap explained.
> 
> I'll add that, thanks for the continued review!

You are welcome.
									Pavel

-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

Re: [PATCH v3] hwmon driver for ACPI 4.0 power meters

[Darrick J. Wong]

On Wed, Sep 09, 2009 at 11:27:52PM +0200, Pavel Machek wrote:

> See the archives. Anyway it should be default to N -- it is new driver
> and it is not essential in any way. "default Y" is for features that
> were always in and are now optional.
 
I suppose you have a point--it's not terribly essential.  I've just sent v5
with default N.

--D

[PATCH v4] hwmon driver for ACPI 4.0 power meters

[Darrick J. Wong]

This driver exposes ACPI 4.0 compliant power meters as hardware monitoring
devices.  This second revision of the driver also exports the ACPI string
info as sysfs attributes, a list of the devices that the meter measures,
and will send ACPI notifications over the ACPI netlink socket.  This latest
revision only enables the power capping controls if it can be confirmed that
the power cap can be enforced by the hardware and explains how the notification
interfaces work.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
---

 Documentation/hwmon/acpi_power_meter |   51 ++
 drivers/acpi/Kconfig                 |   12 
 drivers/acpi/Makefile                |    1 
 drivers/acpi/power_meter.c           | 1017 ++++++++++++++++++++++++++++++++++
 4 files changed, 1081 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/hwmon/acpi_power_meter
 create mode 100644 drivers/acpi/power_meter.c


diff --git a/Documentation/hwmon/acpi_power_meter b/Documentation/hwmon/acpi_power_meter
new file mode 100644
index 0000000..c80399a
--- /dev/null
+++ b/Documentation/hwmon/acpi_power_meter
@@ -0,0 +1,51 @@
+Kernel driver power_meter
+=========================
+
+This driver talks to ACPI 4.0 power meters.
+
+Supported systems:
+  * Any recent system with ACPI 4.0.
+    Prefix: 'power_meter'
+    Datasheet: http://acpi.info/, section 10.4.
+
+Author: Darrick J. Wong
+
+Description
+-----------
+
+This driver implements sensor reading support for the power meters exposed in
+the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
+features--a power meter that returns average power use over a configurable
+interval, an optional capping mechanism, and a couple of trip points.  The
+sysfs interface conforms with the specification outlined in the "Power" section
+of Documentation/hwmon/sysfs-interface.
+
+Special Features
+----------------
+
+The power[1-*]_is_battery knob indicates if the power supply is a battery.
+Both power[1-*]_average_{min,max} must be set before the trip points will work.
+When both of them are set, an ACPI event will be broadcast on the ACPI netlink
+socket and a poll notification will be sent to the appropriate
+power[1-*]_average sysfs file.
+
+The power[1-*]_{model_number, serial_number, oem_info} fields display arbitrary
+strings that ACPI provides with the meter.  The measures/ directory contains
+symlinks to the devices that this meter measures.
+
+Some computers have the ability to enforce a power cap in hardware.  If this is
+the case, the power[1-*]_cap and related sysfs files will appear.  When the
+average power consumption exceeds the cap, an ACPI event will be broadcast on
+the netlink event socket and a poll notification will be sent to the
+appropriate power[1-*]_alarm file to indicate that capping has begun, and the
+hardware has taken action to reduce power consumption.  Most likely this will
+result in reduced performance.
+
+There are a few other ACPI notifications that can be sent by the firmware.  In
+all cases the ACPI event will be broadcast on the ACPI netlink event socket as
+well as sent as a poll notification to a sysfs file.  The events are as
+follows:
+
+power[1-*]_cap will be notified if the firmware changes the power cap.
+power[1-*]_interval will be notified if the firmware changes the averaging
+interval.
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 7ec7d88..2b21b3c 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -82,6 +82,18 @@ config ACPI_PROCFS_POWER
 
 	  Say N to delete power /proc/acpi/ directories that have moved to /sys/
 
+config ACPI_POWER_METER
+	tristate "ACPI 4.0 power meter"
+	depends on HWMON
+	default y
+	help
+	  This driver exposes ACPI 4.0 power meters as hardware monitoring
+	  devices.  Say Y (or M) if you have a computer with ACPI 4.0 firmware
+	  and a power meter.
+
+	  To compile this driver as a module, choose M here:
+	  the module will be called power-meter.
+
 config ACPI_SYSFS_POWER
 	bool "Future power /sys interface"
 	select POWER_SUPPLY
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 03a985b..82cd49d 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_ACPI_HOTPLUG_MEMORY) += acpi_memhotplug.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
 obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
 obj-$(CONFIG_ACPI_SBS)		+= sbs.o
+obj-$(CONFIG_ACPI_POWER_METER)	+= power_meter.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_core.o processor_throttling.o
diff --git a/drivers/acpi/power_meter.c b/drivers/acpi/power_meter.c
new file mode 100644
index 0000000..696091d
--- /dev/null
+++ b/drivers/acpi/power_meter.c
@@ -0,0 +1,1017 @@
+/*
+ * A hwmon driver for ACPI 4.0 power meters
+ * Copyright (C) 2009 IBM
+ *
+ * Author: Darrick J. Wong <djwong@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/jiffies.h>
+#include <linux/mutex.h>
+#include <linux/kdev_t.h>
+#include <linux/sched.h>
+#include <linux/time.h>
+#include <acpi/acpi_drivers.h>
+#include <acpi/acpi_bus.h>
+
+#define ACPI_POWER_METER_NAME		"power_meter"
+ACPI_MODULE_NAME(ACPI_POWER_METER_NAME);
+#define ACPI_POWER_METER_DEVICE_NAME	"Power Meter"
+#define ACPI_POWER_METER_CLASS		"power_meter_resource"
+
+#define NUM_SENSORS			17
+
+#define POWER_METER_CAN_MEASURE	(1 << 0)
+#define POWER_METER_CAN_TRIP	(1 << 1)
+#define POWER_METER_CAN_CAP	(1 << 2)
+#define POWER_METER_CAN_NOTIFY	(1 << 3)
+#define POWER_METER_IS_BATTERY	(1 << 8)
+#define UNKNOWN_HYSTERESIS	0xFFFFFFFF
+
+#define METER_NOTIFY_CONFIG	0x80
+#define METER_NOTIFY_TRIP	0x81
+#define METER_NOTIFY_CAP	0x82
+#define METER_NOTIFY_CAPPING	0x83
+#define METER_NOTIFY_INTERVAL	0x84
+
+#define POWER_AVERAGE_NAME	"power1_average"
+#define POWER_CAP_NAME		"power1_cap"
+#define POWER_AVG_INTERVAL_NAME	"power1_average_interval"
+#define POWER_ALARM_NAME	"power1_alarm"
+
+static int cap_in_hardware;
+static int force_cap_on;
+
+static int can_cap_in_hardware(void)
+{
+	return force_cap_on || cap_in_hardware;
+}
+
+static struct acpi_device_id power_meter_ids[] = {
+	{"ACPI000D", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, power_meter_ids);
+
+struct acpi_power_meter_capabilities {
+	acpi_integer		flags;
+	acpi_integer		units;
+	acpi_integer		type;
+	acpi_integer		accuracy;
+	acpi_integer		sampling_time;
+	acpi_integer		min_avg_interval;
+	acpi_integer		max_avg_interval;
+	acpi_integer		hysteresis;
+	acpi_integer		configurable_cap;
+	acpi_integer		min_cap;
+	acpi_integer		max_cap;
+};
+
+struct acpi_power_meter_resource {
+	struct acpi_device	*acpi_dev;
+	acpi_bus_id		name;
+	struct mutex		lock;
+	struct device		*hwmon_dev;
+	struct acpi_power_meter_capabilities	caps;
+	acpi_string		model_number;
+	acpi_string		serial_number;
+	acpi_string		oem_info;
+	acpi_integer		power;
+	acpi_integer		cap;
+	acpi_integer		avg_interval;
+	int			sensors_valid;
+	unsigned long		sensors_last_updated;
+	struct sensor_device_attribute	sensors[NUM_SENSORS];
+	int			num_sensors;
+	int			trip[2];
+	int			num_domain_devices;
+	struct acpi_device	**domain_devices;
+	struct kobject		*holders_dir;
+};
+
+struct ro_sensor_template {
+	char *label;
+	ssize_t (*show)(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf);
+	int index;
+};
+
+struct rw_sensor_template {
+	char *label;
+	ssize_t (*show)(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf);
+	ssize_t (*set)(struct device *dev,
+		       struct device_attribute *devattr,
+		       const char *buf, size_t count);
+	int index;
+};
+
+/* Averaging interval */
+static int update_avg_interval(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_GAI",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _GAI"));
+		return -ENODEV;
+	}
+
+	resource->avg_interval = data;
+	return 0;
+}
+
+static ssize_t show_avg_interval(struct device *dev,
+				 struct device_attribute *devattr,
+				 char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_avg_interval(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->avg_interval);
+}
+
+static ssize_t set_avg_interval(struct device *dev,
+				struct device_attribute *devattr,
+				const char *buf, size_t count)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+	int res;
+	unsigned long temp;
+	unsigned long long data;
+	acpi_status status;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	if (temp > resource->caps.max_avg_interval ||
+	    temp < resource->caps.min_avg_interval)
+		return -EINVAL;
+	arg0.integer.value = temp;
+
+	mutex_lock(&resource->lock);
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PAI",
+				       &args, &data);
+	if (!ACPI_FAILURE(status))
+		resource->avg_interval = temp;
+	mutex_unlock(&resource->lock);
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PAI"));
+		return -EINVAL;
+	}
+
+	/* _PAI returns 0 on success, nonzero otherwise */
+	if (data)
+		return -EINVAL;
+
+	return count;
+}
+
+/* Cap functions */
+static int update_cap(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_GHL",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _GHL"));
+		return -ENODEV;
+	}
+
+	resource->cap = data;
+	return 0;
+}
+
+static ssize_t show_cap(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_cap(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->cap * 1000);
+}
+
+static ssize_t set_cap(struct device *dev, struct device_attribute *devattr,
+		       const char *buf, size_t count)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+	int res;
+	unsigned long temp;
+	unsigned long long data;
+	acpi_status status;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	temp /= 1000;
+	if (temp > resource->caps.max_cap || temp < resource->caps.min_cap)
+		return -EINVAL;
+	arg0.integer.value = temp;
+
+	mutex_lock(&resource->lock);
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_SHL",
+				       &args, &data);
+	if (!ACPI_FAILURE(status))
+		resource->cap = temp;
+	mutex_unlock(&resource->lock);
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _SHL"));
+		return -EINVAL;
+	}
+
+	/* _SHL returns 0 on success, nonzero otherwise */
+	if (data)
+		return -EINVAL;
+
+	return count;
+}
+
+/* Power meter trip points */
+static int set_acpi_trip(struct acpi_power_meter_resource *resource)
+{
+	union acpi_object arg_objs[] = {
+		{ACPI_TYPE_INTEGER},
+		{ACPI_TYPE_INTEGER}
+	};
+	struct acpi_object_list args = { 2, arg_objs };
+	unsigned long long data;
+	acpi_status status;
+
+	/* Both trip levels must be set */
+	if (resource->trip[0] < 0 || resource->trip[1] < 0)
+		return 0;
+
+	/* This driver stores min, max; ACPI wants max, min. */
+	arg_objs[0].integer.value = resource->trip[1];
+	arg_objs[1].integer.value = resource->trip[0];
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PTP",
+				       &args, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PTP"));
+		return -EINVAL;
+	}
+
+	return data;
+}
+
+static ssize_t set_trip(struct device *dev, struct device_attribute *devattr,
+			const char *buf, size_t count)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	int res;
+	unsigned long temp;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	temp /= 1000;
+	if (temp < 0)
+		return -EINVAL;
+
+	mutex_lock(&resource->lock);
+	resource->trip[attr->index - 7] = temp;
+	res = set_acpi_trip(resource);
+	mutex_unlock(&resource->lock);
+
+	if (res)
+		return res;
+
+	return count;
+}
+
+/* Power meter */
+static int update_meter(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+	unsigned long local_jiffies = jiffies;
+
+	if (time_before(local_jiffies, resource->sensors_last_updated +
+			msecs_to_jiffies(resource->caps.sampling_time)) &&
+			resource->sensors_valid)
+		return 0;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PMM",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMM"));
+		return -ENODEV;
+	}
+
+	resource->power = data;
+	resource->sensors_valid = 1;
+	resource->sensors_last_updated = jiffies;
+	return 0;
+}
+
+static ssize_t show_power(struct device *dev,
+			  struct device_attribute *devattr,
+			  char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_meter(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->power * 1000);
+}
+
+/* Miscellaneous */
+static ssize_t show_str(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	acpi_string val;
+
+	switch (attr->index) {
+	case 0:
+		val = resource->model_number;
+		break;
+	case 1:
+		val = resource->serial_number;
+		break;
+	case 2:
+		val = resource->oem_info;
+		break;
+	default:
+		BUG();
+	}
+
+	return sprintf(buf, "%s\n", val);
+}
+
+static ssize_t show_val(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	acpi_integer val = 0;
+
+	switch (attr->index) {
+	case 0:
+		val = resource->caps.min_avg_interval;
+		break;
+	case 1:
+		val = resource->caps.max_avg_interval;
+		break;
+	case 2:
+		val = resource->caps.min_cap * 1000;
+		break;
+	case 3:
+		val = resource->caps.max_cap * 1000;
+		break;
+	case 4:
+		if (resource->caps.hysteresis == UNKNOWN_HYSTERESIS)
+			return sprintf(buf, "unknown\n");
+
+		val = resource->caps.hysteresis * 1000;
+		break;
+	case 5:
+		if (resource->caps.flags & POWER_METER_IS_BATTERY)
+			val = 1;
+		else
+			val = 0;
+		break;
+	case 6:
+		if (resource->power > resource->cap)
+			val = 1;
+		else
+			val = 0;
+		break;
+	case 7:
+	case 8:
+		if (resource->trip[attr->index - 7] < 0)
+			return sprintf(buf, "unknown\n");
+
+		val = resource->trip[attr->index - 7] * 1000;
+		break;
+	default:
+		BUG();
+	}
+
+	return sprintf(buf, "%llu\n", val);
+}
+
+static ssize_t show_accuracy(struct device *dev,
+			     struct device_attribute *devattr,
+			     char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	unsigned int acc = resource->caps.accuracy;
+
+	return sprintf(buf, "%u.%u%%\n", acc / 1000, acc % 1000);
+}
+
+static ssize_t show_name(struct device *dev,
+			 struct device_attribute *devattr,
+			 char *buf)
+{
+	return sprintf(buf, "%s\n", ACPI_POWER_METER_NAME);
+}
+
+/* Sensor descriptions.  If you add a sensor, update NUM_SENSORS above! */
+static struct ro_sensor_template meter_ro_attrs[] = {
+{POWER_AVERAGE_NAME, show_power, 0},
+{"power1_accuracy", show_accuracy, 0},
+{"power1_average_interval_min", show_val, 0},
+{"power1_average_interval_max", show_val, 1},
+{"power1_is_battery", show_val, 5},
+{NULL, NULL, 0},
+};
+
+static struct rw_sensor_template meter_rw_attrs[] = {
+{POWER_AVG_INTERVAL_NAME, show_avg_interval, set_avg_interval, 0},
+{NULL, NULL, NULL, 0},
+};
+
+static struct ro_sensor_template misc_cap_attrs[] = {
+{"power1_cap_min", show_val, 2},
+{"power1_cap_max", show_val, 3},
+{"power1_cap_hyst", show_val, 4},
+{POWER_ALARM_NAME, show_val, 6},
+{NULL, NULL, 0},
+};
+
+static struct ro_sensor_template ro_cap_attrs[] = {
+{POWER_CAP_NAME, show_cap, 0},
+{NULL, NULL, 0},
+};
+
+static struct rw_sensor_template rw_cap_attrs[] = {
+{POWER_CAP_NAME, show_cap, set_cap, 0},
+{NULL, NULL, NULL, 0},
+};
+
+static struct rw_sensor_template trip_attrs[] = {
+{"power1_average_min", show_val, set_trip, 7},
+{"power1_average_max", show_val, set_trip, 8},
+{NULL, NULL, NULL, 0},
+};
+
+static struct ro_sensor_template misc_attrs[] = {
+{"name", show_name, 0},
+{"power1_model_number", show_str, 0},
+{"power1_oem_info", show_str, 2},
+{"power1_serial_number", show_str, 1},
+{NULL, NULL, 0},
+};
+
+/* Read power domain data */
+static void remove_domain_devices(struct acpi_power_meter_resource *resource)
+{
+	int i;
+
+	if (!resource->num_domain_devices)
+		return;
+
+	for (i = 0; i < resource->num_domain_devices; i++) {
+		struct acpi_device *obj = resource->domain_devices[i];
+		if (!obj)
+			continue;
+
+		sysfs_remove_link(resource->holders_dir,
+				  kobject_name(&obj->dev.kobj));
+		put_device(&obj->dev);
+	}
+
+	kfree(resource->domain_devices);
+	kobject_put(resource->holders_dir);
+}
+
+static int read_domain_devices(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+	int i;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *pss;
+	acpi_status status;
+
+	status = acpi_evaluate_object(resource->acpi_dev->handle, "_PMD", NULL,
+				      &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMD"));
+		return -ENODEV;
+	}
+
+	pss = buffer.pointer;
+	if (!pss ||
+	    pss->type != ACPI_TYPE_PACKAGE) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Invalid _PMD data\n");
+		res = -EFAULT;
+		goto end;
+	}
+
+	if (!pss->package.count)
+		goto end;
+
+	resource->domain_devices = kzalloc(sizeof(struct acpi_device *) *
+					   pss->package.count, GFP_KERNEL);
+	if (!resource->domain_devices) {
+		res = -ENOMEM;
+		goto end;
+	}
+
+	resource->holders_dir = kobject_create_and_add("measures",
+					&resource->acpi_dev->dev.kobj);
+	if (!resource->holders_dir) {
+		res = -ENOMEM;
+		goto exit_free;
+	}
+
+	resource->num_domain_devices = pss->package.count;
+
+	for (i = 0; i < pss->package.count; i++) {
+		struct acpi_device *obj;
+		union acpi_object *element = &(pss->package.elements[i]);
+
+		/* Refuse non-references */
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE)
+			continue;
+
+		/* Create a symlink to domain objects */
+		resource->domain_devices[i] = NULL;
+		status = acpi_bus_get_device(element->reference.handle,
+					     &resource->domain_devices[i]);
+		if (ACPI_FAILURE(status))
+			continue;
+
+		obj = resource->domain_devices[i];
+		get_device(&obj->dev);
+
+		res = sysfs_create_link(resource->holders_dir, &obj->dev.kobj,
+				      kobject_name(&obj->dev.kobj));
+		if (res) {
+			put_device(&obj->dev);
+			resource->domain_devices[i] = NULL;
+		}
+	}
+
+	res = 0;
+	goto end;
+
+exit_free:
+	kfree(resource->domain_devices);
+end:
+	kfree(buffer.pointer);
+	return res;
+}
+
+/* Registration and deregistration */
+static int register_ro_attrs(struct acpi_power_meter_resource *resource,
+			     struct ro_sensor_template *ro)
+{
+	struct device *dev = &resource->acpi_dev->dev;
+	struct sensor_device_attribute *sensors =
+		&resource->sensors[resource->num_sensors];
+	int res = 0;
+
+	while (ro->label) {
+		sensors->dev_attr.attr.name = ro->label;
+		sensors->dev_attr.attr.mode = S_IRUGO;
+		sensors->dev_attr.show = ro->show;
+		sensors->index = ro->index;
+
+		res = device_create_file(dev, &sensors->dev_attr);
+		if (res) {
+			sensors->dev_attr.attr.name = NULL;
+			goto error;
+		}
+		sensors++;
+		resource->num_sensors++;
+		ro++;
+	}
+
+error:
+	return res;
+}
+
+static int register_rw_attrs(struct acpi_power_meter_resource *resource,
+			     struct rw_sensor_template *rw)
+{
+	struct device *dev = &resource->acpi_dev->dev;
+	struct sensor_device_attribute *sensors =
+		&resource->sensors[resource->num_sensors];
+	int res = 0;
+
+	while (rw->label) {
+		sensors->dev_attr.attr.name = rw->label;
+		sensors->dev_attr.attr.mode = S_IRUGO | S_IWUSR;
+		sensors->dev_attr.show = rw->show;
+		sensors->dev_attr.store = rw->set;
+		sensors->index = rw->index;
+
+		res = device_create_file(dev, &sensors->dev_attr);
+		if (res) {
+			sensors->dev_attr.attr.name = NULL;
+			goto error;
+		}
+		sensors++;
+		resource->num_sensors++;
+		rw++;
+	}
+
+error:
+	return res;
+}
+
+static void remove_attrs(struct acpi_power_meter_resource *resource)
+{
+	int i;
+
+	for (i = 0; i < resource->num_sensors; i++) {
+		if (!resource->sensors[i].dev_attr.attr.name)
+			continue;
+		device_remove_file(&resource->acpi_dev->dev,
+				   &resource->sensors[i].dev_attr);
+	}
+
+	remove_domain_devices(resource);
+
+	resource->num_sensors = 0;
+}
+
+static int setup_attrs(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+
+	res = read_domain_devices(resource);
+	if (res)
+		return res;
+
+	if (resource->caps.flags & POWER_METER_CAN_MEASURE) {
+		res = register_ro_attrs(resource, meter_ro_attrs);
+		if (res)
+			goto error;
+		res = register_rw_attrs(resource, meter_rw_attrs);
+		if (res)
+			goto error;
+	}
+
+	if (resource->caps.flags & POWER_METER_CAN_CAP) {
+		if (!can_cap_in_hardware()) {
+			dev_err(&resource->acpi_dev->dev,
+				"Ignoring unsafe software power cap!\n");
+			goto skip_unsafe_cap;
+		}
+
+		if (resource->caps.configurable_cap) {
+			res = register_rw_attrs(resource, rw_cap_attrs);
+			if (res)
+				goto error;
+		} else {
+			res = register_ro_attrs(resource, ro_cap_attrs);
+			if (res)
+				goto error;
+		}
+		res = register_ro_attrs(resource, misc_cap_attrs);
+		if (res)
+			goto error;
+	}
+skip_unsafe_cap:
+
+	if (resource->caps.flags & POWER_METER_CAN_TRIP) {
+		res = register_rw_attrs(resource, trip_attrs);
+		if (res)
+			goto error;
+	}
+
+	res = register_ro_attrs(resource, misc_attrs);
+	if (res)
+		goto error;
+
+	return res;
+error:
+	remove_domain_devices(resource);
+	remove_attrs(resource);
+	return res;
+}
+
+static void free_capabilities(struct acpi_power_meter_resource *resource)
+{
+	acpi_string *str;
+	int i;
+
+	str = &resource->model_number;
+	for (i = 0; i < 3; i++, str++)
+		kfree(*str);
+}
+
+static int read_capabilities(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+	int i;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer state = { 0, NULL };
+	struct acpi_buffer format = { sizeof("NNNNNNNNNNN"), "NNNNNNNNNNN" };
+	union acpi_object *pss;
+	acpi_string *str;
+	acpi_status status;
+
+	status = acpi_evaluate_object(resource->acpi_dev->handle, "_PMC", NULL,
+				      &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMC"));
+		return -ENODEV;
+	}
+
+	pss = buffer.pointer;
+	if (!pss ||
+	    pss->type != ACPI_TYPE_PACKAGE ||
+	    pss->package.count != 14) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Invalid _PMC data\n");
+		res = -EFAULT;
+		goto end;
+	}
+
+	/* Grab all the integer data at once */
+	state.length = sizeof(struct acpi_power_meter_capabilities);
+	state.pointer = &resource->caps;
+
+	status = acpi_extract_package(pss, &format, &state);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Invalid data"));
+		res = -EFAULT;
+		goto end;
+	}
+
+	if (resource->caps.units) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Unknown units %llu.\n",
+			resource->caps.units);
+		res = -EINVAL;
+		goto end;
+	}
+
+	/* Grab the string data */
+	str = &resource->model_number;
+
+	for (i = 11; i < 14; i++) {
+		union acpi_object *element = &(pss->package.elements[i]);
+
+		if (element->type != ACPI_TYPE_STRING) {
+			res = -EINVAL;
+			goto error;
+		}
+
+		*str = kzalloc(sizeof(u8) * (element->string.length + 1),
+			       GFP_KERNEL);
+		if (!*str) {
+			res = -ENOMEM;
+			goto error;
+		}
+
+		strncpy(*str, element->string.pointer, element->string.length);
+		str++;
+	}
+
+	dev_info(&resource->acpi_dev->dev, "Found ACPI power meter.\n");
+	goto end;
+error:
+	str = &resource->model_number;
+	for (i = 0; i < 3; i++, str++)
+		kfree(*str);
+end:
+	kfree(buffer.pointer);
+	return res;
+}
+
+/* Handle ACPI event notifications */
+static void acpi_power_meter_notify(struct acpi_device *device, u32 event)
+{
+	struct acpi_power_meter_resource *resource;
+	int res;
+
+	if (!device || !acpi_driver_data(device))
+		return;
+
+	resource = acpi_driver_data(device);
+
+	mutex_lock(&resource->lock);
+	switch (event) {
+	case METER_NOTIFY_CONFIG:
+		free_capabilities(resource);
+		res = read_capabilities(resource);
+		if (res)
+			break;
+
+		remove_attrs(resource);
+		setup_attrs(resource);
+		break;
+	case METER_NOTIFY_TRIP:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME);
+		update_meter(resource);
+		break;
+	case METER_NOTIFY_CAP:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME);
+		update_cap(resource);
+		break;
+	case METER_NOTIFY_INTERVAL:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME);
+		update_avg_interval(resource);
+		break;
+	case METER_NOTIFY_CAPPING:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME);
+		dev_info(&device->dev, "Capping in progress.\n");
+		break;
+	default:
+		BUG();
+	}
+	mutex_unlock(&resource->lock);
+
+	acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS,
+					dev_name(&device->dev), event, 0);
+}
+
+static int acpi_power_meter_add(struct acpi_device *device)
+{
+	int res;
+	struct acpi_power_meter_resource *resource;
+
+	if (!device)
+		return -EINVAL;
+
+	resource = kzalloc(sizeof(struct acpi_power_meter_resource),
+			   GFP_KERNEL);
+	if (!resource)
+		return -ENOMEM;
+
+	resource->sensors_valid = 0;
+	resource->acpi_dev = device;
+	mutex_init(&resource->lock);
+	strcpy(acpi_device_name(device), ACPI_POWER_METER_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_POWER_METER_CLASS);
+	device->driver_data = resource;
+
+	free_capabilities(resource);
+	res = read_capabilities(resource);
+	if (res)
+		goto exit_free;
+
+	resource->trip[0] = resource->trip[1] = -1;
+
+	res = setup_attrs(resource);
+	if (res)
+		goto exit_free;
+
+	resource->hwmon_dev = hwmon_device_register(&device->dev);
+	if (IS_ERR(resource->hwmon_dev)) {
+		res = PTR_ERR(resource->hwmon_dev);
+		goto exit_remove;
+	}
+
+	res = 0;
+	goto exit;
+
+exit_remove:
+	remove_attrs(resource);
+exit_free:
+	kfree(resource);
+exit:
+	return res;
+}
+
+static int acpi_power_meter_remove(struct acpi_device *device, int type)
+{
+	struct acpi_power_meter_resource *resource;
+
+	if (!device || !acpi_driver_data(device))
+		return -EINVAL;
+
+	resource = acpi_driver_data(device);
+	hwmon_device_unregister(resource->hwmon_dev);
+
+	free_capabilities(resource);
+	remove_attrs(resource);
+
+	kfree(resource);
+	return 0;
+}
+
+static int acpi_power_meter_resume(struct acpi_device *device)
+{
+	struct acpi_power_meter_resource *resource;
+
+	if (!device || !acpi_driver_data(device))
+		return -EINVAL;
+
+	resource = acpi_driver_data(device);
+	free_capabilities(resource);
+	read_capabilities(resource);
+
+	return 0;
+}
+
+static struct acpi_driver acpi_power_meter_driver = {
+	.name = "power_meter",
+	.class = ACPI_POWER_METER_CLASS,
+	.ids = power_meter_ids,
+	.ops = {
+		.add = acpi_power_meter_add,
+		.remove = acpi_power_meter_remove,
+		.resume = acpi_power_meter_resume,
+		.notify = acpi_power_meter_notify,
+		},
+};
+
+/* Module init/exit routines */
+static int __init enable_cap_knobs(const struct dmi_system_id *d)
+{
+	cap_in_hardware = 1;
+	return 0;
+}
+
+static struct dmi_system_id __initdata pm_dmi_table[] = {
+	{
+		enable_cap_knobs, "IBM Active Energy Manager",
+		{
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM")
+		},
+	},
+	{}
+};
+
+static int __init acpi_power_meter_init(void)
+{
+	int result;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	dmi_check_system(pm_dmi_table);
+
+	result = acpi_bus_register_driver(&acpi_power_meter_driver);
+	if (result < 0)
+		return -ENODEV;
+
+	return 0;
+}
+
+static void __exit acpi_power_meter_exit(void)
+{
+	acpi_bus_unregister_driver(&acpi_power_meter_driver);
+}
+
+MODULE_AUTHOR("Darrick J. Wong <djwong@us.ibm.com>");
+MODULE_DESCRIPTION("ACPI 4.0 power meter driver");
+MODULE_LICENSE("GPL");
+
+module_param(force_cap_on, bool, 0644);
+MODULE_PARM_DESC(force_cap_on, "Enable power cap even it is unsafe to do so.");
+
+module_init(acpi_power_meter_init);
+module_exit(acpi_power_meter_exit);

Re: [PATCH v4] hwmon driver for ACPI 4.0 power meters

[Pavel Machek]

> +config ACPI_POWER_METER
> +	tristate "ACPI 4.0 power meter"
> +	depends on HWMON
> +	default y

Should not really be default y, see the other mail.

-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html

[PATCH v5] hwmon driver for ACPI 4.0 power meters

[Darrick J. Wong]

This driver exposes ACPI 4.0 compliant power meters as hardware monitoring
devices.  This second revision of the driver also exports the ACPI string
info as sysfs attributes, a list of the devices that the meter measures,
and will send ACPI notifications over the ACPI netlink socket.  This latest
revision only enables the power capping controls if it can be confirmed that
the power cap can be enforced by the hardware and explains how the notification
interfaces work.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
---

 Documentation/hwmon/acpi_power_meter |   51 ++
 drivers/acpi/Kconfig                 |   12 
 drivers/acpi/Makefile                |    1 
 drivers/acpi/power_meter.c           | 1017 ++++++++++++++++++++++++++++++++++
 4 files changed, 1081 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/hwmon/acpi_power_meter
 create mode 100644 drivers/acpi/power_meter.c


diff --git a/Documentation/hwmon/acpi_power_meter b/Documentation/hwmon/acpi_power_meter
new file mode 100644
index 0000000..c80399a
--- /dev/null
+++ b/Documentation/hwmon/acpi_power_meter
@@ -0,0 +1,51 @@
+Kernel driver power_meter
+=========================
+
+This driver talks to ACPI 4.0 power meters.
+
+Supported systems:
+  * Any recent system with ACPI 4.0.
+    Prefix: 'power_meter'
+    Datasheet: http://acpi.info/, section 10.4.
+
+Author: Darrick J. Wong
+
+Description
+-----------
+
+This driver implements sensor reading support for the power meters exposed in
+the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
+features--a power meter that returns average power use over a configurable
+interval, an optional capping mechanism, and a couple of trip points.  The
+sysfs interface conforms with the specification outlined in the "Power" section
+of Documentation/hwmon/sysfs-interface.
+
+Special Features
+----------------
+
+The power[1-*]_is_battery knob indicates if the power supply is a battery.
+Both power[1-*]_average_{min,max} must be set before the trip points will work.
+When both of them are set, an ACPI event will be broadcast on the ACPI netlink
+socket and a poll notification will be sent to the appropriate
+power[1-*]_average sysfs file.
+
+The power[1-*]_{model_number, serial_number, oem_info} fields display arbitrary
+strings that ACPI provides with the meter.  The measures/ directory contains
+symlinks to the devices that this meter measures.
+
+Some computers have the ability to enforce a power cap in hardware.  If this is
+the case, the power[1-*]_cap and related sysfs files will appear.  When the
+average power consumption exceeds the cap, an ACPI event will be broadcast on
+the netlink event socket and a poll notification will be sent to the
+appropriate power[1-*]_alarm file to indicate that capping has begun, and the
+hardware has taken action to reduce power consumption.  Most likely this will
+result in reduced performance.
+
+There are a few other ACPI notifications that can be sent by the firmware.  In
+all cases the ACPI event will be broadcast on the ACPI netlink event socket as
+well as sent as a poll notification to a sysfs file.  The events are as
+follows:
+
+power[1-*]_cap will be notified if the firmware changes the power cap.
+power[1-*]_interval will be notified if the firmware changes the averaging
+interval.
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 7ec7d88..274696a 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -82,6 +82,18 @@ config ACPI_PROCFS_POWER
 
 	  Say N to delete power /proc/acpi/ directories that have moved to /sys/
 
+config ACPI_POWER_METER
+	tristate "ACPI 4.0 power meter"
+	depends on HWMON
+	default n
+	help
+	  This driver exposes ACPI 4.0 power meters as hardware monitoring
+	  devices.  Say Y (or M) if you have a computer with ACPI 4.0 firmware
+	  and a power meter.
+
+	  To compile this driver as a module, choose M here:
+	  the module will be called power-meter.
+
 config ACPI_SYSFS_POWER
 	bool "Future power /sys interface"
 	select POWER_SUPPLY
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 03a985b..82cd49d 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_ACPI_HOTPLUG_MEMORY) += acpi_memhotplug.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
 obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
 obj-$(CONFIG_ACPI_SBS)		+= sbs.o
+obj-$(CONFIG_ACPI_POWER_METER)	+= power_meter.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_core.o processor_throttling.o
diff --git a/drivers/acpi/power_meter.c b/drivers/acpi/power_meter.c
new file mode 100644
index 0000000..696091d
--- /dev/null
+++ b/drivers/acpi/power_meter.c
@@ -0,0 +1,1017 @@
+/*
+ * A hwmon driver for ACPI 4.0 power meters
+ * Copyright (C) 2009 IBM
+ *
+ * Author: Darrick J. Wong <djwong@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/module.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/jiffies.h>
+#include <linux/mutex.h>
+#include <linux/kdev_t.h>
+#include <linux/sched.h>
+#include <linux/time.h>
+#include <acpi/acpi_drivers.h>
+#include <acpi/acpi_bus.h>
+
+#define ACPI_POWER_METER_NAME		"power_meter"
+ACPI_MODULE_NAME(ACPI_POWER_METER_NAME);
+#define ACPI_POWER_METER_DEVICE_NAME	"Power Meter"
+#define ACPI_POWER_METER_CLASS		"power_meter_resource"
+
+#define NUM_SENSORS			17
+
+#define POWER_METER_CAN_MEASURE	(1 << 0)
+#define POWER_METER_CAN_TRIP	(1 << 1)
+#define POWER_METER_CAN_CAP	(1 << 2)
+#define POWER_METER_CAN_NOTIFY	(1 << 3)
+#define POWER_METER_IS_BATTERY	(1 << 8)
+#define UNKNOWN_HYSTERESIS	0xFFFFFFFF
+
+#define METER_NOTIFY_CONFIG	0x80
+#define METER_NOTIFY_TRIP	0x81
+#define METER_NOTIFY_CAP	0x82
+#define METER_NOTIFY_CAPPING	0x83
+#define METER_NOTIFY_INTERVAL	0x84
+
+#define POWER_AVERAGE_NAME	"power1_average"
+#define POWER_CAP_NAME		"power1_cap"
+#define POWER_AVG_INTERVAL_NAME	"power1_average_interval"
+#define POWER_ALARM_NAME	"power1_alarm"
+
+static int cap_in_hardware;
+static int force_cap_on;
+
+static int can_cap_in_hardware(void)
+{
+	return force_cap_on || cap_in_hardware;
+}
+
+static struct acpi_device_id power_meter_ids[] = {
+	{"ACPI000D", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, power_meter_ids);
+
+struct acpi_power_meter_capabilities {
+	acpi_integer		flags;
+	acpi_integer		units;
+	acpi_integer		type;
+	acpi_integer		accuracy;
+	acpi_integer		sampling_time;
+	acpi_integer		min_avg_interval;
+	acpi_integer		max_avg_interval;
+	acpi_integer		hysteresis;
+	acpi_integer		configurable_cap;
+	acpi_integer		min_cap;
+	acpi_integer		max_cap;
+};
+
+struct acpi_power_meter_resource {
+	struct acpi_device	*acpi_dev;
+	acpi_bus_id		name;
+	struct mutex		lock;
+	struct device		*hwmon_dev;
+	struct acpi_power_meter_capabilities	caps;
+	acpi_string		model_number;
+	acpi_string		serial_number;
+	acpi_string		oem_info;
+	acpi_integer		power;
+	acpi_integer		cap;
+	acpi_integer		avg_interval;
+	int			sensors_valid;
+	unsigned long		sensors_last_updated;
+	struct sensor_device_attribute	sensors[NUM_SENSORS];
+	int			num_sensors;
+	int			trip[2];
+	int			num_domain_devices;
+	struct acpi_device	**domain_devices;
+	struct kobject		*holders_dir;
+};
+
+struct ro_sensor_template {
+	char *label;
+	ssize_t (*show)(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf);
+	int index;
+};
+
+struct rw_sensor_template {
+	char *label;
+	ssize_t (*show)(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf);
+	ssize_t (*set)(struct device *dev,
+		       struct device_attribute *devattr,
+		       const char *buf, size_t count);
+	int index;
+};
+
+/* Averaging interval */
+static int update_avg_interval(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_GAI",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _GAI"));
+		return -ENODEV;
+	}
+
+	resource->avg_interval = data;
+	return 0;
+}
+
+static ssize_t show_avg_interval(struct device *dev,
+				 struct device_attribute *devattr,
+				 char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_avg_interval(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->avg_interval);
+}
+
+static ssize_t set_avg_interval(struct device *dev,
+				struct device_attribute *devattr,
+				const char *buf, size_t count)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+	int res;
+	unsigned long temp;
+	unsigned long long data;
+	acpi_status status;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	if (temp > resource->caps.max_avg_interval ||
+	    temp < resource->caps.min_avg_interval)
+		return -EINVAL;
+	arg0.integer.value = temp;
+
+	mutex_lock(&resource->lock);
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PAI",
+				       &args, &data);
+	if (!ACPI_FAILURE(status))
+		resource->avg_interval = temp;
+	mutex_unlock(&resource->lock);
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PAI"));
+		return -EINVAL;
+	}
+
+	/* _PAI returns 0 on success, nonzero otherwise */
+	if (data)
+		return -EINVAL;
+
+	return count;
+}
+
+/* Cap functions */
+static int update_cap(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_GHL",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _GHL"));
+		return -ENODEV;
+	}
+
+	resource->cap = data;
+	return 0;
+}
+
+static ssize_t show_cap(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_cap(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->cap * 1000);
+}
+
+static ssize_t set_cap(struct device *dev, struct device_attribute *devattr,
+		       const char *buf, size_t count)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
+	struct acpi_object_list args = { 1, &arg0 };
+	int res;
+	unsigned long temp;
+	unsigned long long data;
+	acpi_status status;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	temp /= 1000;
+	if (temp > resource->caps.max_cap || temp < resource->caps.min_cap)
+		return -EINVAL;
+	arg0.integer.value = temp;
+
+	mutex_lock(&resource->lock);
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_SHL",
+				       &args, &data);
+	if (!ACPI_FAILURE(status))
+		resource->cap = temp;
+	mutex_unlock(&resource->lock);
+
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _SHL"));
+		return -EINVAL;
+	}
+
+	/* _SHL returns 0 on success, nonzero otherwise */
+	if (data)
+		return -EINVAL;
+
+	return count;
+}
+
+/* Power meter trip points */
+static int set_acpi_trip(struct acpi_power_meter_resource *resource)
+{
+	union acpi_object arg_objs[] = {
+		{ACPI_TYPE_INTEGER},
+		{ACPI_TYPE_INTEGER}
+	};
+	struct acpi_object_list args = { 2, arg_objs };
+	unsigned long long data;
+	acpi_status status;
+
+	/* Both trip levels must be set */
+	if (resource->trip[0] < 0 || resource->trip[1] < 0)
+		return 0;
+
+	/* This driver stores min, max; ACPI wants max, min. */
+	arg_objs[0].integer.value = resource->trip[1];
+	arg_objs[1].integer.value = resource->trip[0];
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PTP",
+				       &args, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PTP"));
+		return -EINVAL;
+	}
+
+	return data;
+}
+
+static ssize_t set_trip(struct device *dev, struct device_attribute *devattr,
+			const char *buf, size_t count)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	int res;
+	unsigned long temp;
+
+	res = strict_strtoul(buf, 10, &temp);
+	if (res)
+		return res;
+
+	temp /= 1000;
+	if (temp < 0)
+		return -EINVAL;
+
+	mutex_lock(&resource->lock);
+	resource->trip[attr->index - 7] = temp;
+	res = set_acpi_trip(resource);
+	mutex_unlock(&resource->lock);
+
+	if (res)
+		return res;
+
+	return count;
+}
+
+/* Power meter */
+static int update_meter(struct acpi_power_meter_resource *resource)
+{
+	unsigned long long data;
+	acpi_status status;
+	unsigned long local_jiffies = jiffies;
+
+	if (time_before(local_jiffies, resource->sensors_last_updated +
+			msecs_to_jiffies(resource->caps.sampling_time)) &&
+			resource->sensors_valid)
+		return 0;
+
+	status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PMM",
+				       NULL, &data);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMM"));
+		return -ENODEV;
+	}
+
+	resource->power = data;
+	resource->sensors_valid = 1;
+	resource->sensors_last_updated = jiffies;
+	return 0;
+}
+
+static ssize_t show_power(struct device *dev,
+			  struct device_attribute *devattr,
+			  char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+
+	mutex_lock(&resource->lock);
+	update_meter(resource);
+	mutex_unlock(&resource->lock);
+
+	return sprintf(buf, "%llu\n", resource->power * 1000);
+}
+
+/* Miscellaneous */
+static ssize_t show_str(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	acpi_string val;
+
+	switch (attr->index) {
+	case 0:
+		val = resource->model_number;
+		break;
+	case 1:
+		val = resource->serial_number;
+		break;
+	case 2:
+		val = resource->oem_info;
+		break;
+	default:
+		BUG();
+	}
+
+	return sprintf(buf, "%s\n", val);
+}
+
+static ssize_t show_val(struct device *dev,
+			struct device_attribute *devattr,
+			char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	acpi_integer val = 0;
+
+	switch (attr->index) {
+	case 0:
+		val = resource->caps.min_avg_interval;
+		break;
+	case 1:
+		val = resource->caps.max_avg_interval;
+		break;
+	case 2:
+		val = resource->caps.min_cap * 1000;
+		break;
+	case 3:
+		val = resource->caps.max_cap * 1000;
+		break;
+	case 4:
+		if (resource->caps.hysteresis == UNKNOWN_HYSTERESIS)
+			return sprintf(buf, "unknown\n");
+
+		val = resource->caps.hysteresis * 1000;
+		break;
+	case 5:
+		if (resource->caps.flags & POWER_METER_IS_BATTERY)
+			val = 1;
+		else
+			val = 0;
+		break;
+	case 6:
+		if (resource->power > resource->cap)
+			val = 1;
+		else
+			val = 0;
+		break;
+	case 7:
+	case 8:
+		if (resource->trip[attr->index - 7] < 0)
+			return sprintf(buf, "unknown\n");
+
+		val = resource->trip[attr->index - 7] * 1000;
+		break;
+	default:
+		BUG();
+	}
+
+	return sprintf(buf, "%llu\n", val);
+}
+
+static ssize_t show_accuracy(struct device *dev,
+			     struct device_attribute *devattr,
+			     char *buf)
+{
+	struct acpi_device *acpi_dev = to_acpi_device(dev);
+	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
+	unsigned int acc = resource->caps.accuracy;
+
+	return sprintf(buf, "%u.%u%%\n", acc / 1000, acc % 1000);
+}
+
+static ssize_t show_name(struct device *dev,
+			 struct device_attribute *devattr,
+			 char *buf)
+{
+	return sprintf(buf, "%s\n", ACPI_POWER_METER_NAME);
+}
+
+/* Sensor descriptions.  If you add a sensor, update NUM_SENSORS above! */
+static struct ro_sensor_template meter_ro_attrs[] = {
+{POWER_AVERAGE_NAME, show_power, 0},
+{"power1_accuracy", show_accuracy, 0},
+{"power1_average_interval_min", show_val, 0},
+{"power1_average_interval_max", show_val, 1},
+{"power1_is_battery", show_val, 5},
+{NULL, NULL, 0},
+};
+
+static struct rw_sensor_template meter_rw_attrs[] = {
+{POWER_AVG_INTERVAL_NAME, show_avg_interval, set_avg_interval, 0},
+{NULL, NULL, NULL, 0},
+};
+
+static struct ro_sensor_template misc_cap_attrs[] = {
+{"power1_cap_min", show_val, 2},
+{"power1_cap_max", show_val, 3},
+{"power1_cap_hyst", show_val, 4},
+{POWER_ALARM_NAME, show_val, 6},
+{NULL, NULL, 0},
+};
+
+static struct ro_sensor_template ro_cap_attrs[] = {
+{POWER_CAP_NAME, show_cap, 0},
+{NULL, NULL, 0},
+};
+
+static struct rw_sensor_template rw_cap_attrs[] = {
+{POWER_CAP_NAME, show_cap, set_cap, 0},
+{NULL, NULL, NULL, 0},
+};
+
+static struct rw_sensor_template trip_attrs[] = {
+{"power1_average_min", show_val, set_trip, 7},
+{"power1_average_max", show_val, set_trip, 8},
+{NULL, NULL, NULL, 0},
+};
+
+static struct ro_sensor_template misc_attrs[] = {
+{"name", show_name, 0},
+{"power1_model_number", show_str, 0},
+{"power1_oem_info", show_str, 2},
+{"power1_serial_number", show_str, 1},
+{NULL, NULL, 0},
+};
+
+/* Read power domain data */
+static void remove_domain_devices(struct acpi_power_meter_resource *resource)
+{
+	int i;
+
+	if (!resource->num_domain_devices)
+		return;
+
+	for (i = 0; i < resource->num_domain_devices; i++) {
+		struct acpi_device *obj = resource->domain_devices[i];
+		if (!obj)
+			continue;
+
+		sysfs_remove_link(resource->holders_dir,
+				  kobject_name(&obj->dev.kobj));
+		put_device(&obj->dev);
+	}
+
+	kfree(resource->domain_devices);
+	kobject_put(resource->holders_dir);
+}
+
+static int read_domain_devices(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+	int i;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *pss;
+	acpi_status status;
+
+	status = acpi_evaluate_object(resource->acpi_dev->handle, "_PMD", NULL,
+				      &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMD"));
+		return -ENODEV;
+	}
+
+	pss = buffer.pointer;
+	if (!pss ||
+	    pss->type != ACPI_TYPE_PACKAGE) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Invalid _PMD data\n");
+		res = -EFAULT;
+		goto end;
+	}
+
+	if (!pss->package.count)
+		goto end;
+
+	resource->domain_devices = kzalloc(sizeof(struct acpi_device *) *
+					   pss->package.count, GFP_KERNEL);
+	if (!resource->domain_devices) {
+		res = -ENOMEM;
+		goto end;
+	}
+
+	resource->holders_dir = kobject_create_and_add("measures",
+					&resource->acpi_dev->dev.kobj);
+	if (!resource->holders_dir) {
+		res = -ENOMEM;
+		goto exit_free;
+	}
+
+	resource->num_domain_devices = pss->package.count;
+
+	for (i = 0; i < pss->package.count; i++) {
+		struct acpi_device *obj;
+		union acpi_object *element = &(pss->package.elements[i]);
+
+		/* Refuse non-references */
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE)
+			continue;
+
+		/* Create a symlink to domain objects */
+		resource->domain_devices[i] = NULL;
+		status = acpi_bus_get_device(element->reference.handle,
+					     &resource->domain_devices[i]);
+		if (ACPI_FAILURE(status))
+			continue;
+
+		obj = resource->domain_devices[i];
+		get_device(&obj->dev);
+
+		res = sysfs_create_link(resource->holders_dir, &obj->dev.kobj,
+				      kobject_name(&obj->dev.kobj));
+		if (res) {
+			put_device(&obj->dev);
+			resource->domain_devices[i] = NULL;
+		}
+	}
+
+	res = 0;
+	goto end;
+
+exit_free:
+	kfree(resource->domain_devices);
+end:
+	kfree(buffer.pointer);
+	return res;
+}
+
+/* Registration and deregistration */
+static int register_ro_attrs(struct acpi_power_meter_resource *resource,
+			     struct ro_sensor_template *ro)
+{
+	struct device *dev = &resource->acpi_dev->dev;
+	struct sensor_device_attribute *sensors =
+		&resource->sensors[resource->num_sensors];
+	int res = 0;
+
+	while (ro->label) {
+		sensors->dev_attr.attr.name = ro->label;
+		sensors->dev_attr.attr.mode = S_IRUGO;
+		sensors->dev_attr.show = ro->show;
+		sensors->index = ro->index;
+
+		res = device_create_file(dev, &sensors->dev_attr);
+		if (res) {
+			sensors->dev_attr.attr.name = NULL;
+			goto error;
+		}
+		sensors++;
+		resource->num_sensors++;
+		ro++;
+	}
+
+error:
+	return res;
+}
+
+static int register_rw_attrs(struct acpi_power_meter_resource *resource,
+			     struct rw_sensor_template *rw)
+{
+	struct device *dev = &resource->acpi_dev->dev;
+	struct sensor_device_attribute *sensors =
+		&resource->sensors[resource->num_sensors];
+	int res = 0;
+
+	while (rw->label) {
+		sensors->dev_attr.attr.name = rw->label;
+		sensors->dev_attr.attr.mode = S_IRUGO | S_IWUSR;
+		sensors->dev_attr.show = rw->show;
+		sensors->dev_attr.store = rw->set;
+		sensors->index = rw->index;
+
+		res = device_create_file(dev, &sensors->dev_attr);
+		if (res) {
+			sensors->dev_attr.attr.name = NULL;
+			goto error;
+		}
+		sensors++;
+		resource->num_sensors++;
+		rw++;
+	}
+
+error:
+	return res;
+}
+
+static void remove_attrs(struct acpi_power_meter_resource *resource)
+{
+	int i;
+
+	for (i = 0; i < resource->num_sensors; i++) {
+		if (!resource->sensors[i].dev_attr.attr.name)
+			continue;
+		device_remove_file(&resource->acpi_dev->dev,
+				   &resource->sensors[i].dev_attr);
+	}
+
+	remove_domain_devices(resource);
+
+	resource->num_sensors = 0;
+}
+
+static int setup_attrs(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+
+	res = read_domain_devices(resource);
+	if (res)
+		return res;
+
+	if (resource->caps.flags & POWER_METER_CAN_MEASURE) {
+		res = register_ro_attrs(resource, meter_ro_attrs);
+		if (res)
+			goto error;
+		res = register_rw_attrs(resource, meter_rw_attrs);
+		if (res)
+			goto error;
+	}
+
+	if (resource->caps.flags & POWER_METER_CAN_CAP) {
+		if (!can_cap_in_hardware()) {
+			dev_err(&resource->acpi_dev->dev,
+				"Ignoring unsafe software power cap!\n");
+			goto skip_unsafe_cap;
+		}
+
+		if (resource->caps.configurable_cap) {
+			res = register_rw_attrs(resource, rw_cap_attrs);
+			if (res)
+				goto error;
+		} else {
+			res = register_ro_attrs(resource, ro_cap_attrs);
+			if (res)
+				goto error;
+		}
+		res = register_ro_attrs(resource, misc_cap_attrs);
+		if (res)
+			goto error;
+	}
+skip_unsafe_cap:
+
+	if (resource->caps.flags & POWER_METER_CAN_TRIP) {
+		res = register_rw_attrs(resource, trip_attrs);
+		if (res)
+			goto error;
+	}
+
+	res = register_ro_attrs(resource, misc_attrs);
+	if (res)
+		goto error;
+
+	return res;
+error:
+	remove_domain_devices(resource);
+	remove_attrs(resource);
+	return res;
+}
+
+static void free_capabilities(struct acpi_power_meter_resource *resource)
+{
+	acpi_string *str;
+	int i;
+
+	str = &resource->model_number;
+	for (i = 0; i < 3; i++, str++)
+		kfree(*str);
+}
+
+static int read_capabilities(struct acpi_power_meter_resource *resource)
+{
+	int res = 0;
+	int i;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer state = { 0, NULL };
+	struct acpi_buffer format = { sizeof("NNNNNNNNNNN"), "NNNNNNNNNNN" };
+	union acpi_object *pss;
+	acpi_string *str;
+	acpi_status status;
+
+	status = acpi_evaluate_object(resource->acpi_dev->handle, "_PMC", NULL,
+				      &buffer);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PMC"));
+		return -ENODEV;
+	}
+
+	pss = buffer.pointer;
+	if (!pss ||
+	    pss->type != ACPI_TYPE_PACKAGE ||
+	    pss->package.count != 14) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Invalid _PMC data\n");
+		res = -EFAULT;
+		goto end;
+	}
+
+	/* Grab all the integer data at once */
+	state.length = sizeof(struct acpi_power_meter_capabilities);
+	state.pointer = &resource->caps;
+
+	status = acpi_extract_package(pss, &format, &state);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Invalid data"));
+		res = -EFAULT;
+		goto end;
+	}
+
+	if (resource->caps.units) {
+		dev_err(&resource->acpi_dev->dev, ACPI_POWER_METER_NAME
+			"Unknown units %llu.\n",
+			resource->caps.units);
+		res = -EINVAL;
+		goto end;
+	}
+
+	/* Grab the string data */
+	str = &resource->model_number;
+
+	for (i = 11; i < 14; i++) {
+		union acpi_object *element = &(pss->package.elements[i]);
+
+		if (element->type != ACPI_TYPE_STRING) {
+			res = -EINVAL;
+			goto error;
+		}
+
+		*str = kzalloc(sizeof(u8) * (element->string.length + 1),
+			       GFP_KERNEL);
+		if (!*str) {
+			res = -ENOMEM;
+			goto error;
+		}
+
+		strncpy(*str, element->string.pointer, element->string.length);
+		str++;
+	}
+
+	dev_info(&resource->acpi_dev->dev, "Found ACPI power meter.\n");
+	goto end;
+error:
+	str = &resource->model_number;
+	for (i = 0; i < 3; i++, str++)
+		kfree(*str);
+end:
+	kfree(buffer.pointer);
+	return res;
+}
+
+/* Handle ACPI event notifications */
+static void acpi_power_meter_notify(struct acpi_device *device, u32 event)
+{
+	struct acpi_power_meter_resource *resource;
+	int res;
+
+	if (!device || !acpi_driver_data(device))
+		return;
+
+	resource = acpi_driver_data(device);
+
+	mutex_lock(&resource->lock);
+	switch (event) {
+	case METER_NOTIFY_CONFIG:
+		free_capabilities(resource);
+		res = read_capabilities(resource);
+		if (res)
+			break;
+
+		remove_attrs(resource);
+		setup_attrs(resource);
+		break;
+	case METER_NOTIFY_TRIP:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME);
+		update_meter(resource);
+		break;
+	case METER_NOTIFY_CAP:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME);
+		update_cap(resource);
+		break;
+	case METER_NOTIFY_INTERVAL:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME);
+		update_avg_interval(resource);
+		break;
+	case METER_NOTIFY_CAPPING:
+		sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME);
+		dev_info(&device->dev, "Capping in progress.\n");
+		break;
+	default:
+		BUG();
+	}
+	mutex_unlock(&resource->lock);
+
+	acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS,
+					dev_name(&device->dev), event, 0);
+}
+
+static int acpi_power_meter_add(struct acpi_device *device)
+{
+	int res;
+	struct acpi_power_meter_resource *resource;
+
+	if (!device)
+		return -EINVAL;
+
+	resource = kzalloc(sizeof(struct acpi_power_meter_resource),
+			   GFP_KERNEL);
+	if (!resource)
+		return -ENOMEM;
+
+	resource->sensors_valid = 0;
+	resource->acpi_dev = device;
+	mutex_init(&resource->lock);
+	strcpy(acpi_device_name(device), ACPI_POWER_METER_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_POWER_METER_CLASS);
+	device->driver_data = resource;
+
+	free_capabilities(resource);
+	res = read_capabilities(resource);
+	if (res)
+		goto exit_free;
+
+	resource->trip[0] = resource->trip[1] = -1;
+
+	res = setup_attrs(resource);
+	if (res)
+		goto exit_free;
+
+	resource->hwmon_dev = hwmon_device_register(&device->dev);
+	if (IS_ERR(resource->hwmon_dev)) {
+		res = PTR_ERR(resource->hwmon_dev);
+		goto exit_remove;
+	}
+
+	res = 0;
+	goto exit;
+
+exit_remove:
+	remove_attrs(resource);
+exit_free:
+	kfree(resource);
+exit:
+	return res;
+}
+
+static int acpi_power_meter_remove(struct acpi_device *device, int type)
+{
+	struct acpi_power_meter_resource *resource;
+
+	if (!device || !acpi_driver_data(device))
+		return -EINVAL;
+
+	resource = acpi_driver_data(device);
+	hwmon_device_unregister(resource->hwmon_dev);
+
+	free_capabilities(resource);
+	remove_attrs(resource);
+
+	kfree(resource);
+	return 0;
+}
+
+static int acpi_power_meter_resume(struct acpi_device *device)
+{
+	struct acpi_power_meter_resource *resource;
+
+	if (!device || !acpi_driver_data(device))
+		return -EINVAL;
+
+	resource = acpi_driver_data(device);
+	free_capabilities(resource);
+	read_capabilities(resource);
+
+	return 0;
+}
+
+static struct acpi_driver acpi_power_meter_driver = {
+	.name = "power_meter",
+	.class = ACPI_POWER_METER_CLASS,
+	.ids = power_meter_ids,
+	.ops = {
+		.add = acpi_power_meter_add,
+		.remove = acpi_power_meter_remove,
+		.resume = acpi_power_meter_resume,
+		.notify = acpi_power_meter_notify,
+		},
+};
+
+/* Module init/exit routines */
+static int __init enable_cap_knobs(const struct dmi_system_id *d)
+{
+	cap_in_hardware = 1;
+	return 0;
+}
+
+static struct dmi_system_id __initdata pm_dmi_table[] = {
+	{
+		enable_cap_knobs, "IBM Active Energy Manager",
+		{
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM")
+		},
+	},
+	{}
+};
+
+static int __init acpi_power_meter_init(void)
+{
+	int result;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	dmi_check_system(pm_dmi_table);
+
+	result = acpi_bus_register_driver(&acpi_power_meter_driver);
+	if (result < 0)
+		return -ENODEV;
+
+	return 0;
+}
+
+static void __exit acpi_power_meter_exit(void)
+{
+	acpi_bus_unregister_driver(&acpi_power_meter_driver);
+}
+
+MODULE_AUTHOR("Darrick J. Wong <djwong@us.ibm.com>");
+MODULE_DESCRIPTION("ACPI 4.0 power meter driver");
+MODULE_LICENSE("GPL");
+
+module_param(force_cap_on, bool, 0644);
+MODULE_PARM_DESC(force_cap_on, "Enable power cap even it is unsafe to do so.");
+
+module_init(acpi_power_meter_init);
+module_exit(acpi_power_meter_exit);