Re: [PATCH v2] drm/i915/hwmon: expose package temperature

[Riana Tauro <riana.tauro@intel.com>]

Hi Raag

On 9/6/2024 3:01 PM, Raag Jadav wrote:
> Add hwmon support for temp1_input attribute, which will expose package
> temperature in millidegree Celsius. With this in place we can monitor
> package temperature using lm-sensors tool.
> 
> $ sensors
> i915-pci-0300
> Adapter: PCI adapter
> in0:         990.00 mV
> fan1:        1260 RPM
> temp1:        +45.0°C
> power1:           N/A  (max =  35.00 W)
> energy1:      12.62 kJ
> 
> v2: Use switch case (Anshuman)
> 
> Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11276
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
> ---
>   .../ABI/testing/sysfs-driver-intel-i915-hwmon |  8 ++++
>   drivers/gpu/drm/i915/i915_hwmon.c             | 40 +++++++++++++++++++
>   drivers/gpu/drm/i915/intel_mchbar_regs.h      |  4 ++
>   3 files changed, 52 insertions(+)
> 
> diff --git a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> index be4141a7522f..a885e5316d02 100644
> --- a/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> +++ b/Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
> @@ -83,3 +83,11 @@ Contact:	intel-gfx@lists.freedesktop.org
>   Description:	RO. Fan speed of device in RPM.
>   
>   		Only supported for particular Intel i915 graphics platforms.
> +
> +What:		/sys/bus/pci/drivers/i915/.../hwmon/hwmon<i>/temp1_input
> +Date:		November 2024
> +KernelVersion:	6.12
> +Contact:	intel-gfx@lists.freedesktop.org
> +Description:	RO. GPU package temperature in millidegree Celsius.
> +
> +		Only supported for particular Intel i915 graphics platforms.
> diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c
> index 17d30f6b84b0..0a9f483b4105 100644
> --- a/drivers/gpu/drm/i915/i915_hwmon.c
> +++ b/drivers/gpu/drm/i915/i915_hwmon.c
> @@ -7,6 +7,7 @@
>   #include <linux/hwmon-sysfs.h>
>   #include <linux/jiffies.h>
>   #include <linux/types.h>
> +#include <linux/units.h>
>   
>   #include "i915_drv.h"
>   #include "i915_hwmon.h"
> @@ -32,6 +33,7 @@
>   
>   struct hwm_reg {
>   	i915_reg_t gt_perf_status;
> +	i915_reg_t pkg_temp;
place it alphabetically after rapl_limit
>   	i915_reg_t pkg_power_sku_unit;
>   	i915_reg_t pkg_power_sku;
>   	i915_reg_t pkg_rapl_limit;
> @@ -280,6 +282,7 @@ static const struct attribute_group *hwm_groups[] = {
>   };
>   
>   static const struct hwmon_channel_info * const hwm_info[] = {
> +	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
>   	HWMON_CHANNEL_INFO(in, HWMON_I_INPUT),
>   	HWMON_CHANNEL_INFO(power, HWMON_P_MAX | HWMON_P_RATED_MAX | HWMON_P_CRIT),
>   	HWMON_CHANNEL_INFO(energy, HWMON_E_INPUT),
> @@ -310,6 +313,37 @@ static int hwm_pcode_write_i1(struct drm_i915_private *i915, u32 uval)
>   				  POWER_SETUP_SUBCOMMAND_WRITE_I1, 0, uval);
>   }
>   
> +static umode_t
> +hwm_temp_is_visible(const struct hwm_drvdata *ddat, u32 attr)
> +{
> +	struct i915_hwmon *hwmon = ddat->hwmon;
> +
> +	if (attr == hwmon_temp_input && i915_mmio_reg_valid(hwmon->rg.pkg_temp))
> +		return 0444;
> +
> +	return 0;
> +}
> +
> +static int
> +hwm_temp_read(struct hwm_drvdata *ddat, u32 attr, long *val)
> +{
> +	struct i915_hwmon *hwmon = ddat->hwmon;
> +	intel_wakeref_t wakeref;
> +	u32 reg_val;
> +
> +	switch (attr) {
> +	case hwmon_temp_input:
> +		with_intel_runtime_pm(ddat->uncore->rpm, wakeref)
> +			reg_val = intel_uncore_read(ddat->uncore, hwmon->rg.pkg_temp);
> +
> +		/* HW register value is in degrees, convert to millidegrees. */
use millidegree Celsius here

Thanks,
Riana
> +		*val = REG_FIELD_GET(TEMP_MASK, reg_val) * MILLIDEGREE_PER_DEGREE;
> +		return 0;
> +	default:
> +		return -EOPNOTSUPP;
> +	}
> +}
> +
>   static umode_t
>   hwm_in_is_visible(const struct hwm_drvdata *ddat, u32 attr)
>   {
> @@ -692,6 +726,8 @@ hwm_is_visible(const void *drvdata, enum hwmon_sensor_types type,
>   	struct hwm_drvdata *ddat = (struct hwm_drvdata *)drvdata;
>   
>   	switch (type) {
> +	case hwmon_temp:
> +		return hwm_temp_is_visible(ddat, attr);
>   	case hwmon_in:
>   		return hwm_in_is_visible(ddat, attr);
>   	case hwmon_power:
> @@ -714,6 +750,8 @@ hwm_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
>   	struct hwm_drvdata *ddat = dev_get_drvdata(dev);
>   
>   	switch (type) {
> +	case hwmon_temp:
> +		return hwm_temp_read(ddat, attr, val);
>   	case hwmon_in:
>   		return hwm_in_read(ddat, attr, val);
>   	case hwmon_power:
> @@ -810,6 +848,7 @@ hwm_get_preregistration_info(struct drm_i915_private *i915)
>   	hwmon->rg.gt_perf_status = GEN12_RPSTAT1;
>   
>   	if (IS_DG1(i915) || IS_DG2(i915)) {
> +		hwmon->rg.pkg_temp = PCU_PACKAGE_TEMPERATURE;
>   		hwmon->rg.pkg_power_sku_unit = PCU_PACKAGE_POWER_SKU_UNIT;
>   		hwmon->rg.pkg_power_sku = PCU_PACKAGE_POWER_SKU;
>   		hwmon->rg.pkg_rapl_limit = PCU_PACKAGE_RAPL_LIMIT;
> @@ -817,6 +856,7 @@ hwm_get_preregistration_info(struct drm_i915_private *i915)
>   		hwmon->rg.energy_status_tile = INVALID_MMIO_REG;
>   		hwmon->rg.fan_speed = PCU_PWM_FAN_SPEED;
>   	} else {
> +		hwmon->rg.pkg_temp = INVALID_MMIO_REG;
>   		hwmon->rg.pkg_power_sku_unit = INVALID_MMIO_REG;
>   		hwmon->rg.pkg_power_sku = INVALID_MMIO_REG;
>   		hwmon->rg.pkg_rapl_limit = INVALID_MMIO_REG;
> diff --git a/drivers/gpu/drm/i915/intel_mchbar_regs.h b/drivers/gpu/drm/i915/intel_mchbar_regs.h
> index 73900c098d59..dc2477179c3e 100644
> --- a/drivers/gpu/drm/i915/intel_mchbar_regs.h
> +++ b/drivers/gpu/drm/i915/intel_mchbar_regs.h
> @@ -207,6 +207,10 @@
>   #define PCU_PACKAGE_ENERGY_STATUS              _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x593c)
>   
>   #define GEN6_GT_PERF_STATUS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5948)
> +
> +#define PCU_PACKAGE_TEMPERATURE			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5978)
> +#define   TEMP_MASK				REG_GENMASK(7, 0)
> +
>   #define GEN6_RP_STATE_LIMITS			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5994)
>   #define GEN6_RP_STATE_CAP			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998)
>   #define   RP0_CAP_MASK				REG_GENMASK(7, 0)