From: Mario Limonciello <mario.limonciello@amd.com>
To: <stable@vger.kernel.org>
Cc: Mario Limonciello <mario.limonciello@amd.com>
Subject: [PATCH 6.4.y 1/2] drm/amd/pm: expose swctf threshold setting for legacy powerplay
Date: Fri, 11 Aug 2023 11:39:50 -0500 [thread overview]
Message-ID: <20230811163951.24631-2-mario.limonciello@amd.com> (raw)
In-Reply-To: <20230811163951.24631-1-mario.limonciello@amd.com>
From: Evan Quan <evan.quan@amd.com>
Preparation for coming optimization which eliminates the influence of
GPU temperature momentary fluctuation.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 064329c595da56eff6d7a7e7760660c726433139)
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h | 2 ++
.../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(-)
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index d178f3f44081..42172b00be66 100644
--- 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 */
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
index 981dc8c7112d..90452b66e107 100644
--- 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 pp_hwmgr *hwmgr)
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 pp_hwmgr *hwmgr)
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;
}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index e10cc5e7928e..6841a4bce186 100644
--- 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_range(struct pp_hwmgr *hwmgr,
thermal_data->max = data->thermal_temp_setting.temperature_shutdown *
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ thermal_data->sw_ctf_threshold = thermal_data->max;
+
return 0;
}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 99cd2e63afdd..c51dd4c74fe9 100644
--- 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_temperature_range(struct pp_hwmgr *hwmgr,
{
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_temperature_range(struct pp_hwmgr *hwmgr,
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;
}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index e9db137cd1c6..1937be1cf5b4 100644
--- 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(struct pp_hwmgr *hwmgr,
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_temperature_range(struct pp_hwmgr *hwmgr,
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;
}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 0d4d4811527c..4e19ccbdb807 100644
--- 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(struct pp_hwmgr *hwmgr,
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_temperature_range(struct pp_hwmgr *hwmgr,
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;
}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
index a5f2227a3971..0ffc2347829d 100644
--- 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 {
--
2.34.1
next prev parent reply other threads:[~2023-08-11 16:40 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-11 16:39 [PATCH 6.4.y 0/2] Solve abrupt shutdowns from momentarily fluctuations Mario Limonciello
2023-08-11 16:39 ` Mario Limonciello [this message]
2023-08-11 16:39 ` [PATCH 6.4.y 2/2] drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation Mario Limonciello
2023-08-12 7:45 ` [PATCH 6.4.y 0/2] Solve abrupt shutdowns from momentarily fluctuations Greg KH
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230811163951.24631-2-mario.limonciello@amd.com \
--to=mario.limonciello@amd.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox