Commit fddc9fcb authored by Wu Hao's avatar Wu Hao Committed by Moritz Fischer

fpga: dfl: fme: add power management support

This patch adds support for power management private feature under
FPGA Management Engine (FME). This private feature driver registers
a hwmon for power (power1_input), thresholds information, e.g.
(power1_max / crit / max_alarm / crit_alarm) and also read-only sysfs
interfaces for other power management information. For configuration,
user could write threshold values via above power1_max / crit sysfs
interface under hwmon too.
Signed-off-by: default avatarLuwei Kang <luwei.kang@intel.com>
Signed-off-by: default avatarXu Yilun <yilun.xu@intel.com>
Signed-off-by: default avatarWu Hao <hao.wu@intel.com>
Acked-by: default avatarGuenter Roeck <linux@roeck-us.net>
Reviewed-by: default avatarMoritz Fischer <mdf@kernel.org>
Signed-off-by: default avatarMoritz Fischer <mdf@kernel.org>
parent 4284c65a
......@@ -114,6 +114,7 @@ Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. Read this file to get the name of hwmon device, it
supports values:
'dfl_fme_thermal' - thermal hwmon device name
'dfl_fme_power' - power hwmon device name
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/temp1_input
Date: October 2019
......@@ -170,3 +171,70 @@ Description: Read-Only. Read this file to get the policy of hardware threshold1
(see 'temp1_max'). It only supports two values (policies):
0 - AP2 state (90% throttling)
1 - AP1 state (50% throttling)
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_input
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. It returns current FPGA power consumption in uW.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_max
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Write. Read this file to get current hardware power
threshold1 in uW. If power consumption rises at or above
this threshold, hardware starts 50% throttling.
Write this file to set current hardware power threshold1 in uW.
As hardware only accepts values in Watts, so input value will
be round down per Watts (< 1 watts part will be discarded) and
clamped within the range from 0 to 127 Watts. Write fails with
-EINVAL if input parsing fails.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_crit
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Write. Read this file to get current hardware power
threshold2 in uW. If power consumption rises at or above
this threshold, hardware starts 90% throttling.
Write this file to set current hardware power threshold2 in uW.
As hardware only accepts values in Watts, so input value will
be round down per Watts (< 1 watts part will be discarded) and
clamped within the range from 0 to 127 Watts. Write fails with
-EINVAL if input parsing fails.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_max_alarm
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-only. It returns 1 if power consumption is currently at or
above hardware threshold1 (see 'power1_max'), otherwise 0.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_crit_alarm
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-only. It returns 1 if power consumption is currently at or
above hardware threshold2 (see 'power1_crit'), otherwise 0.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_xeon_limit
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. It returns power limit for XEON in uW.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_fpga_limit
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. It returns power limit for FPGA in uW.
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_ltr
Date: October 2019
KernelVersion: 5.5
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-only. Read this file to get current Latency Tolerance
Reporting (ltr) value. It returns 1 if all Accelerated
Function Units (AFUs) can tolerate latency >= 40us for memory
access or 0 if any AFU is latency sensitive (< 40us).
......@@ -355,6 +355,209 @@ static const struct dfl_feature_ops fme_thermal_mgmt_ops = {
.init = fme_thermal_mgmt_init,
};
#define FME_PWR_STATUS 0x8
#define FME_LATENCY_TOLERANCE BIT_ULL(18)
#define PWR_CONSUMED GENMASK_ULL(17, 0)
#define FME_PWR_THRESHOLD 0x10
#define PWR_THRESHOLD1 GENMASK_ULL(6, 0) /* in Watts */
#define PWR_THRESHOLD2 GENMASK_ULL(14, 8) /* in Watts */
#define PWR_THRESHOLD_MAX 0x7f /* in Watts */
#define PWR_THRESHOLD1_STATUS BIT_ULL(16)
#define PWR_THRESHOLD2_STATUS BIT_ULL(17)
#define FME_PWR_XEON_LIMIT 0x18
#define XEON_PWR_LIMIT GENMASK_ULL(14, 0) /* in 0.1 Watts */
#define XEON_PWR_EN BIT_ULL(15)
#define FME_PWR_FPGA_LIMIT 0x20
#define FPGA_PWR_LIMIT GENMASK_ULL(14, 0) /* in 0.1 Watts */
#define FPGA_PWR_EN BIT_ULL(15)
static int power_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
u32 attr, int channel, long *val)
{
struct dfl_feature *feature = dev_get_drvdata(dev);
u64 v;
switch (attr) {
case hwmon_power_input:
v = readq(feature->ioaddr + FME_PWR_STATUS);
*val = (long)(FIELD_GET(PWR_CONSUMED, v) * 1000000);
break;
case hwmon_power_max:
v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
*val = (long)(FIELD_GET(PWR_THRESHOLD1, v) * 1000000);
break;
case hwmon_power_crit:
v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
*val = (long)(FIELD_GET(PWR_THRESHOLD2, v) * 1000000);
break;
case hwmon_power_max_alarm:
v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
*val = (long)FIELD_GET(PWR_THRESHOLD1_STATUS, v);
break;
case hwmon_power_crit_alarm:
v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
*val = (long)FIELD_GET(PWR_THRESHOLD2_STATUS, v);
break;
default:
return -EOPNOTSUPP;
}
return 0;
}
static int power_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
u32 attr, int channel, long val)
{
struct dfl_feature_platform_data *pdata = dev_get_platdata(dev->parent);
struct dfl_feature *feature = dev_get_drvdata(dev);
int ret = 0;
u64 v;
val = clamp_val(val / 1000000, 0, PWR_THRESHOLD_MAX);
mutex_lock(&pdata->lock);
switch (attr) {
case hwmon_power_max:
v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
v &= ~PWR_THRESHOLD1;
v |= FIELD_PREP(PWR_THRESHOLD1, val);
writeq(v, feature->ioaddr + FME_PWR_THRESHOLD);
break;
case hwmon_power_crit:
v = readq(feature->ioaddr + FME_PWR_THRESHOLD);
v &= ~PWR_THRESHOLD2;
v |= FIELD_PREP(PWR_THRESHOLD2, val);
writeq(v, feature->ioaddr + FME_PWR_THRESHOLD);
break;
default:
ret = -EOPNOTSUPP;
break;
}
mutex_unlock(&pdata->lock);
return ret;
}
static umode_t power_hwmon_attrs_visible(const void *drvdata,
enum hwmon_sensor_types type,
u32 attr, int channel)
{
switch (attr) {
case hwmon_power_input:
case hwmon_power_max_alarm:
case hwmon_power_crit_alarm:
return 0444;
case hwmon_power_max:
case hwmon_power_crit:
return 0644;
}
return 0;
}
static const struct hwmon_ops power_hwmon_ops = {
.is_visible = power_hwmon_attrs_visible,
.read = power_hwmon_read,
.write = power_hwmon_write,
};
static const struct hwmon_channel_info *power_hwmon_info[] = {
HWMON_CHANNEL_INFO(power, HWMON_P_INPUT |
HWMON_P_MAX | HWMON_P_MAX_ALARM |
HWMON_P_CRIT | HWMON_P_CRIT_ALARM),
NULL
};
static const struct hwmon_chip_info power_hwmon_chip_info = {
.ops = &power_hwmon_ops,
.info = power_hwmon_info,
};
static ssize_t power1_xeon_limit_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dfl_feature *feature = dev_get_drvdata(dev);
u16 xeon_limit = 0;
u64 v;
v = readq(feature->ioaddr + FME_PWR_XEON_LIMIT);
if (FIELD_GET(XEON_PWR_EN, v))
xeon_limit = FIELD_GET(XEON_PWR_LIMIT, v);
return sprintf(buf, "%u\n", xeon_limit * 100000);
}
static ssize_t power1_fpga_limit_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dfl_feature *feature = dev_get_drvdata(dev);
u16 fpga_limit = 0;
u64 v;
v = readq(feature->ioaddr + FME_PWR_FPGA_LIMIT);
if (FIELD_GET(FPGA_PWR_EN, v))
fpga_limit = FIELD_GET(FPGA_PWR_LIMIT, v);
return sprintf(buf, "%u\n", fpga_limit * 100000);
}
static ssize_t power1_ltr_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dfl_feature *feature = dev_get_drvdata(dev);
u64 v;
v = readq(feature->ioaddr + FME_PWR_STATUS);
return sprintf(buf, "%u\n",
(unsigned int)FIELD_GET(FME_LATENCY_TOLERANCE, v));
}
static DEVICE_ATTR_RO(power1_xeon_limit);
static DEVICE_ATTR_RO(power1_fpga_limit);
static DEVICE_ATTR_RO(power1_ltr);
static struct attribute *power_extra_attrs[] = {
&dev_attr_power1_xeon_limit.attr,
&dev_attr_power1_fpga_limit.attr,
&dev_attr_power1_ltr.attr,
NULL
};
ATTRIBUTE_GROUPS(power_extra);
static int fme_power_mgmt_init(struct platform_device *pdev,
struct dfl_feature *feature)
{
struct device *hwmon;
hwmon = devm_hwmon_device_register_with_info(&pdev->dev,
"dfl_fme_power", feature,
&power_hwmon_chip_info,
power_extra_groups);
if (IS_ERR(hwmon)) {
dev_err(&pdev->dev, "Fail to register power hwmon\n");
return PTR_ERR(hwmon);
}
return 0;
}
static const struct dfl_feature_id fme_power_mgmt_id_table[] = {
{.id = FME_FEATURE_ID_POWER_MGMT,},
{0,}
};
static const struct dfl_feature_ops fme_power_mgmt_ops = {
.init = fme_power_mgmt_init,
};
static struct dfl_feature_driver fme_feature_drvs[] = {
{
.id_table = fme_hdr_id_table,
......@@ -372,6 +575,10 @@ static struct dfl_feature_driver fme_feature_drvs[] = {
.id_table = fme_thermal_mgmt_id_table,
.ops = &fme_thermal_mgmt_ops,
},
{
.id_table = fme_power_mgmt_id_table,
.ops = &fme_power_mgmt_ops,
},
{
.ops = NULL,
},
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment