Please do not change the output temperature granularity.
Although it seems a little weird. It's required by hwmon interfaces design and has to be in millidegrees Celsius (@Deucher, Alexander, right?).
* hwmon interfaces for GPU temperature:
*
* - temp[1-3]_input: the on die GPU temperature in millidegrees Celsius
* - temp2_input and temp3_input are supported on SOC15 dGPUs only
*
* - temp[1-3]_label: temperature channel label
* - temp2_label and temp3_label are supported on SOC15 dGPUs only
*
* - temp[1-3]_crit: temperature critical max value in millidegrees Celsius
* - temp2_crit and temp3_crit are supported on SOC15 dGPUs only
*
* - temp[1-3]_crit_hyst: temperature hysteresis for critical limit in millidegrees Celsius
* - temp2_crit_hyst and temp3_crit_hyst are supported on SOC15 dGPUs only
*
* - temp[1-3]_emergency: temperature emergency max value(asic shutdown) in millidegrees Celsius
* - these are supported on SOC15 dGPUs only
Regards,
Evan
> -----Original Message-----
> From: amd-gfx <amd-gfx-bounces@xxxxxxxxxxxxxxxxxxxxx> On Behalf Of
> Wang, Kevin(Yang)
> Sent: Tuesday, July 23, 2019 5:32 PM
> To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx
> Cc: Huang, Ray <Ray.Huang@xxxxxxx>; Feng, Kenneth
> <Kenneth.Feng@xxxxxxx>; Wang, Kevin(Yang) <Kevin1.Wang@xxxxxxx>
> Subject: [PATCH] drm/amd/powerplay: add callback function of
> get_thermal_temperature_range
>
> 1. the thermal temperature is asic related data, move the code logic to
> xxx_ppt.c.
> 2. replace data structure PP_TemperatureRange with
> smu_temperature_range.
> 3. change temperature uint from temp*1000 to temp (temperature uint).
>
> Signed-off-by: Kevin Wang <kevin1.wang@xxxxxxx>
> Signed-off-by: Kenneth Feng <kenneth.feng@xxxxxxx>
> Acked-by: Huang Rui <ray.huang@xxxxxxx>
> ---
> .../gpu/drm/amd/powerplay/inc/amdgpu_smu.h | 1 -
> drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 17 ++++++++++
> drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 18 ++++++----
> drivers/gpu/drm/amd/powerplay/vega20_ppt.c | 34 ++++++-------------
> 4 files changed, 40 insertions(+), 30 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
> b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
> index 34093ddca105..7105f8041088 100644
> --- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
> +++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
> @@ -439,7 +439,6 @@ struct smu_table_context
> struct smu_table *tables;
> uint32_t table_count;
> struct smu_table memory_pool;
> - uint16_t software_shutdown_temp;
> uint8_t thermal_controller_type;
> uint16_t TDPODLimit;
>
> diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
> b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
> index 46e2913e4af4..a4c4d4997189 100644
> --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
> +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
> @@ -1638,6 +1638,22 @@ static int navi10_set_performance_level(struct
> smu_context *smu, enum amd_dpm_fo
> return ret;
> }
>
> +static int navi10_get_thermal_temperature_range(struct smu_context
> *smu,
> + struct
> smu_temperature_range *range) {
> + struct smu_table_context *table_context = &smu->smu_table;
> + struct smu_11_0_powerplay_table *powerplay_table =
> +table_context->power_play_table;
> +
> + if (!range || !powerplay_table)
> + return -EINVAL;
> +
> + /* The unit is temperature */
> + range->min = 0;
> + range->max = powerplay_table->software_shutdown_temp;
> +
> + return 0;
> +}
> +
> static const struct pptable_funcs navi10_ppt_funcs = {
> .tables_init = navi10_tables_init,
> .alloc_dpm_context = navi10_allocate_dpm_context, @@ -1674,6
> +1690,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
> .get_ppfeature_status = navi10_get_ppfeature_status,
> .set_ppfeature_status = navi10_set_ppfeature_status,
> .set_performance_level = navi10_set_performance_level,
> + .get_thermal_temperature_range =
> navi10_get_thermal_temperature_range,
> };
>
> void navi10_set_ppt_funcs(struct smu_context *smu) diff --git
> a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
> b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
> index 76bc157525d0..4ad9e0c5a637 100644
> --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
> +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
> @@ -1147,10 +1147,8 @@ static int smu_v11_0_set_thermal_range(struct
> smu_context *smu,
> struct smu_temperature_range *range) {
> struct amdgpu_device *adev = smu->adev;
> - int low = SMU_THERMAL_MINIMUM_ALERT_TEMP *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> - int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> + int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
> + int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
> uint32_t val;
>
> if (!range)
> @@ -1161,6 +1159,9 @@ static int smu_v11_0_set_thermal_range(struct
> smu_context *smu,
> if (high > range->max)
> high = range->max;
>
> + low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP, range->min);
> + high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP, range->max);
> +
> if (low > high)
> return -EINVAL;
>
> @@ -1169,8 +1170,8 @@ static int smu_v11_0_set_thermal_range(struct
> smu_context *smu,
> val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> THERM_IH_HW_ENA, 1);
> val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> THERM_INTH_MASK, 0);
> val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> THERM_INTL_MASK, 0);
> - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> DIG_THERM_INTH, (high /
> SMU_TEMPERATURE_UNITS_PER_CENTIGRADES));
> - val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> DIG_THERM_INTL, (low / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES));
> + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> DIG_THERM_INTH, (high & 0xff));
> + val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL,
> DIG_THERM_INTL, (low &
> +0xff));
> val = val &
> (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
>
> WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val); @@ -
> 1209,7 +1210,10 @@ static int smu_v11_0_start_thermal_control(struct
> smu_context *smu)
>
> if (!smu->pm_enabled)
> return ret;
> +
> ret = smu_get_thermal_temperature_range(smu, &range);
> + if (ret)
> + return ret;
>
> if (smu->smu_table.thermal_controller_type) {
> ret = smu_v11_0_set_thermal_range(smu, &range); @@ -
> 1234,6 +1238,8 @@ static int smu_v11_0_start_thermal_control(struct
> smu_context *smu)
> adev->pm.dpm.thermal.min_mem_temp = range.mem_min;
> adev->pm.dpm.thermal.max_mem_crit_temp =
> range.mem_crit_max;
> adev->pm.dpm.thermal.max_mem_emergency_temp =
> range.mem_emergency_max;
> + adev->pm.dpm.thermal.min_temp = range.min *
> SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> + adev->pm.dpm.thermal.max_temp = range.max *
> +SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
>
> return ret;
> }
> diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
> b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
> index bcd0efaf7bbd..deb102ffedc2 100644
> --- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
> +++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
> @@ -463,7 +463,6 @@ static int vega20_store_powerplay_table(struct
> smu_context *smu)
> memcpy(table_context->driver_pptable, &powerplay_table-
> >smcPPTable,
> sizeof(PPTable_t));
>
> - table_context->software_shutdown_temp = powerplay_table-
> >usSoftwareShutdownTemp;
> table_context->thermal_controller_type = powerplay_table-
> >ucThermalControllerType;
> table_context->TDPODLimit = le32_to_cpu(powerplay_table-
> >OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPER
> CENTAGE]);
>
> @@ -3235,35 +3234,24 @@ static int vega20_set_watermarks_table(struct
> smu_context *smu,
> return 0;
> }
>
> -static const struct smu_temperature_range vega20_thermal_policy[] = -{
> - {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
> - { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000,
> 120000},
> -};
> -
> static int vega20_get_thermal_temperature_range(struct smu_context
> *smu,
> struct
> smu_temperature_range*range) {
> -
> + struct smu_table_context *table_context = &smu->smu_table;
> + ATOM_Vega20_POWERPLAYTABLE *powerplay_table =
> +table_context->power_play_table;
> PPTable_t *pptable = smu->smu_table.driver_pptable;
>
> - if (!range)
> + if (!range || !powerplay_table)
> return -EINVAL;
>
> - memcpy(range, &vega20_thermal_policy[0], sizeof(struct
> smu_temperature_range));
> -
> - range->max = pptable->TedgeLimit *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> - range->edge_emergency_max = (pptable->TedgeLimit +
> CTF_OFFSET_EDGE) *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> - range->hotspot_crit_max = pptable->ThotspotLimit *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> - range->hotspot_emergency_max = (pptable->ThotspotLimit +
> CTF_OFFSET_HOTSPOT) *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> - range->mem_crit_max = pptable->ThbmLimit *
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> - range->mem_emergency_max = (pptable->ThbmLimit +
> CTF_OFFSET_HBM)*
> - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
> + /* The unit is temperature */
> + range->min = 0;
> + range->max = powerplay_table->usSoftwareShutdownTemp;
> + range->edge_emergency_max = (pptable->TedgeLimit +
> CTF_OFFSET_EDGE);
> + range->hotspot_crit_max = pptable->ThotspotLimit;
> + range->hotspot_emergency_max = (pptable->ThotspotLimit +
> CTF_OFFSET_HOTSPOT);
> + range->mem_crit_max = pptable->ThbmLimit;
> + range->mem_emergency_max = (pptable->ThbmLimit +
> CTF_OFFSET_HBM);
>
>
> return 0;
> --
> 2.22.0
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@xxxxxxxxxxxxxxxxxxxxx
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
