From: Evan Quan <evan.quan@xxxxxxx>
commit 064329c595da56eff6d7a7e7760660c726433139 upstream.
Preparation for coming optimization which eliminates the influence of
GPU temperature momentary fluctuation.
Signed-off-by: Evan Quan <evan.quan@xxxxxxx>
Reviewed-by: Lijo Lazar <lijo.lazar@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Mario Limonciello <mario.limonciello@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h | 2 ++
drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c | 4 +++-
drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 2 ++
drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 10 ++++++++++
drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c | 4 ++++
drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c | 4 ++++
drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h | 1 +
7 files changed, 26 insertions(+), 1 deletion(-)
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -89,6 +89,8 @@ struct amdgpu_dpm_thermal {
int max_mem_crit_temp;
/* memory max emergency(shutdown) temp */
int max_mem_emergency_temp;
+ /* SWCTF threshold */
+ int sw_ctf_threshold;
/* was last interrupt low to high or high to low */
bool high_to_low;
/* interrupt source */
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
@@ -241,7 +241,8 @@ int phm_start_thermal_controller(struct
TEMP_RANGE_MAX,
TEMP_RANGE_MIN,
TEMP_RANGE_MAX,
- TEMP_RANGE_MAX};
+ TEMP_RANGE_MAX,
+ 0};
struct amdgpu_device *adev = hwmgr->adev;
if (!hwmgr->not_vf)
@@ -265,6 +266,7 @@ int phm_start_thermal_controller(struct
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.sw_ctf_threshold = range.sw_ctf_threshold;
return ret;
}
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -5432,6 +5432,8 @@ static int smu7_get_thermal_temperature_
thermal_data->max = data->thermal_temp_setting.temperature_shutdown *
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ thermal_data->sw_ctf_threshold = thermal_data->max;
+
return 0;
}
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -5241,6 +5241,9 @@ static int vega10_get_thermal_temperatur
{
struct vega10_hwmgr *data = hwmgr->backend;
PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+ struct phm_ppt_v2_information *pp_table_info =
+ (struct phm_ppt_v2_information *)(hwmgr->pptable);
+ struct phm_tdp_table *tdp_table = pp_table_info->tdp_table;
memcpy(thermal_data, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange));
@@ -5257,6 +5260,13 @@ static int vega10_get_thermal_temperatur
thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ if (tdp_table->usSoftwareShutdownTemp > pp_table->ThotspotLimit &&
+ tdp_table->usSoftwareShutdownTemp < VEGA10_THERMAL_MAXIMUM_ALERT_TEMP)
+ thermal_data->sw_ctf_threshold = tdp_table->usSoftwareShutdownTemp;
+ else
+ thermal_data->sw_ctf_threshold = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP;
+ thermal_data->sw_ctf_threshold *= PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
return 0;
}
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2763,6 +2763,8 @@ static int vega12_notify_cac_buffer_info
static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
struct PP_TemperatureRange *thermal_data)
{
+ struct phm_ppt_v3_information *pptable_information =
+ (struct phm_ppt_v3_information *)hwmgr->pptable;
struct vega12_hwmgr *data =
(struct vega12_hwmgr *)(hwmgr->backend);
PPTable_t *pp_table = &(data->smc_state_table.pp_table);
@@ -2781,6 +2783,8 @@ static int vega12_get_thermal_temperatur
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
return 0;
}
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -4206,6 +4206,8 @@ static int vega20_notify_cac_buffer_info
static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
struct PP_TemperatureRange *thermal_data)
{
+ struct phm_ppt_v3_information *pptable_information =
+ (struct phm_ppt_v3_information *)hwmgr->pptable;
struct vega20_hwmgr *data =
(struct vega20_hwmgr *)(hwmgr->backend);
PPTable_t *pp_table = &(data->smc_state_table.pp_table);
@@ -4224,6 +4226,8 @@ static int vega20_get_thermal_temperatur
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
return 0;
}
--- a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
@@ -131,6 +131,7 @@ struct PP_TemperatureRange {
int mem_min;
int mem_crit_max;
int mem_emergency_max;
+ int sw_ctf_threshold;
};
struct PP_StateValidationBlock {
