All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
@ 2019-08-16  9:31 Evan Quan
       [not found] ` <20190816093144.21892-1-evan.quan-5C7GfCeVMHo@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Evan Quan @ 2019-08-16  9:31 UTC (permalink / raw)
  To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW; +Cc: Evan Quan

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan@amd.com>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
 	return ret;
 }
 
-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-	{-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-	{ 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
 						struct smu_temperature_range *range)
 {
-
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 
 	if (!range)
 		return -EINVAL;
 
-	memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
 	range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
 		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
 	[profile] = {1, (workload)}
 
+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+	{-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+	{ 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
 	int	valid_mapping;
 	int	map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
 	if (!range || !powerplay_table)
 		return -EINVAL;
 
-	/* The unit is temperature */
-	range->min = 0;
-	range->max = powerplay_table->software_shutdown_temp;
+	range->max = powerplay_table->software_shutdown_temp *
+		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }
 
 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-				       struct smu_temperature_range *range)
+				       struct smu_temperature_range range)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
 	int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
 
-	if (!range)
-		return -EINVAL;
-
-	if (low < range->min)
-		low = range->min;
-	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);
+	low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+			range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+	high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+			range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
 
 	if (low > high)
 		return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
 	int ret = 0;
-	struct smu_temperature_range range = {
-		TEMP_RANGE_MIN,
-		TEMP_RANGE_MAX,
-		TEMP_RANGE_MAX,
-		TEMP_RANGE_MIN,
-		TEMP_RANGE_MAX,
-		TEMP_RANGE_MAX,
-		TEMP_RANGE_MIN,
-		TEMP_RANGE_MAX,
-		TEMP_RANGE_MAX};
+	struct smu_temperature_range range;
 	struct amdgpu_device *adev = smu->adev;
 
 	if (!smu->pm_enabled)
 		return ret;
 
+	memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
 	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);
+		ret = smu_v11_0_set_thermal_range(smu, range);
 		if (ret)
 			return ret;
 
@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 			return ret;
 	}
 
-	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;
-	adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-	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;
+	adev->pm.dpm.thermal.min_temp = range.min;
+	adev->pm.dpm.thermal.max_temp = range.max;
+	adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+	adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+	adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+	adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+	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;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
 	if (!range || !powerplay_table)
 		return -EINVAL;
 
-	/* 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);
+	range->max = powerplay_table->usSoftwareShutdownTemp *
+		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;
 
 
 	return 0;
-- 
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found] ` <20190816093144.21892-1-evan.quan-5C7GfCeVMHo@public.gmane.org>
@ 2019-08-16 11:04   ` Wang, Kevin(Yang)
       [not found]     ` <MN2PR12MB3296E3E1C79504DD56058410A2AF0-rweVpJHSKTqAm9ToKNQgFgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Wang, Kevin(Yang) @ 2019-08-16 11:04 UTC (permalink / raw)
  To: Quan, Evan, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 10994 bytes --]

Hi Evan,

the temperature min value should be 0, not -273 on smu11.
you can refrence window driver code or register spec.
        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;
and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.
so there is something wrong with this patch.

Best Regards,
Kevin
________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 21053 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]     ` <MN2PR12MB3296E3E1C79504DD56058410A2AF0-rweVpJHSKTqAm9ToKNQgFgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-19  2:16       ` Quan, Evan
       [not found]         ` <MN2PR12MB3344E88B19DF4DA83279BBF2E4A80-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Quan, Evan @ 2019-08-19  2:16 UTC (permalink / raw)
  To: Wang, Kevin(Yang), amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 11949 bytes --]

Comment inline

From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,

the temperature min value should be 0, not -273 on smu11.
you can refrence window driver code or register spec.
        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;
[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.
All the existing and coming ASICs should  follow this design.
and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.
[Quan, Evan] That is still honored, no violation here.
so there is something wrong with this patch.

Best Regards,
Kevin
________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 24320 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]         ` <MN2PR12MB3344E88B19DF4DA83279BBF2E4A80-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-19  5:11           ` Feng, Kenneth
       [not found]             ` <MN2PR12MB35981C5C1B0A12B8C8C1CD468EA80-rweVpJHSKTohWwLleUddgQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Feng, Kenneth @ 2019-08-19  5:11 UTC (permalink / raw)
  To: Quan, Evan, Wang, Kevin(Yang), amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 12815 bytes --]

Hi Evan,
So due to the below code, we don't get a chance to set -273.15, right?
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);


From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

[CAUTION: External Email]
Comment inline

From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,

the temperature min value should be 0, not -273 on smu11.
you can refrence window driver code or register spec.
        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;
[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.
All the existing and coming ASICs should  follow this design.
and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.
[Quan, Evan] That is still honored, no violation here.
so there is something wrong with this patch.

Best Regards,
Kevin
________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 26320 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]             ` <MN2PR12MB35981C5C1B0A12B8C8C1CD468EA80-rweVpJHSKTohWwLleUddgQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-19  5:26               ` Quan, Evan
       [not found]                 ` <MN2PR12MB334468A94B93D7D848596611E4A80-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Quan, Evan @ 2019-08-19  5:26 UTC (permalink / raw)
  To: Feng, Kenneth, Wang, Kevin(Yang),
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 13365 bytes --]

Yes, the lowest settings for thermal controller is 0.

Regards
Evan
From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>
Sent: Monday, August 19, 2019 1:12 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,
So due to the below code, we don't get a chance to set -273.15, right?
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

[CAUTION: External Email]
Comment inline

From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,

the temperature min value should be 0, not -273 on smu11.
you can refrence window driver code or register spec.
        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;
[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.
All the existing and coming ASICs should  follow this design.
and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.
[Quan, Evan] That is still honored, no violation here.
so there is something wrong with this patch.

Best Regards,
Kevin
________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 27620 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]                 ` <MN2PR12MB334468A94B93D7D848596611E4A80-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-20  2:09                   ` Quan, Evan
       [not found]                     ` <MN2PR12MB334407D4ABFF5E4F1CC02518E4AB0-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Quan, Evan @ 2019-08-20  2:09 UTC (permalink / raw)
  To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW; +Cc: Wang, Kevin(Yang), Feng, Kenneth


[-- Attachment #1.1: Type: text/plain, Size: 13890 bytes --]

Ping..

From: Quan, Evan
Sent: Monday, August 19, 2019 1:27 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>; Wang, Kevin(Yang) <Kevin1.Wang@amd.com>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Yes, the lowest settings for thermal controller is 0.

Regards
Evan
From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Monday, August 19, 2019 1:12 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,
So due to the below code, we don't get a chance to set -273.15, right?
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

[CAUTION: External Email]
Comment inline

From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,

the temperature min value should be 0, not -273 on smu11.
you can refrence window driver code or register spec.
        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;
[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.
All the existing and coming ASICs should  follow this design.
and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.
[Quan, Evan] That is still honored, no violation here.
so there is something wrong with this patch.

Best Regards,
Kevin
________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 28712 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]                     ` <MN2PR12MB334407D4ABFF5E4F1CC02518E4AB0-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-20  2:51                       ` Feng, Kenneth
       [not found]                         ` <MN2PR12MB3598713DC8A8803F63886E758EAB0-rweVpJHSKTohWwLleUddgQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Feng, Kenneth @ 2019-08-20  2:51 UTC (permalink / raw)
  To: Quan, Evan, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW; +Cc: Wang, Kevin(Yang)


[-- Attachment #1.1: Type: text/plain, Size: 14482 bytes --]

Reviewed-by: Kenneth Feng <kenneth.feng-5C7GfCeVMHo@public.gmane.org<mailto:kenneth.feng-5C7GfCeVMHo@public.gmane.org>>


From: Quan, Evan
Sent: Tuesday, August 20, 2019 10:10 AM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Cc: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>; Wang, Kevin(Yang) <Kevin1.Wang@amd.com>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Ping..

From: Quan, Evan
Sent: Monday, August 19, 2019 1:27 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Yes, the lowest settings for thermal controller is 0.

Regards
Evan
From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Monday, August 19, 2019 1:12 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,
So due to the below code, we don't get a chance to set -273.15, right?
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

[CAUTION: External Email]
Comment inline

From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Hi Evan,

the temperature min value should be 0, not -273 on smu11.
you can refrence window driver code or register spec.
        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;
[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.
All the existing and coming ASICs should  follow this design.
and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.
[Quan, Evan] That is still honored, no violation here.
so there is something wrong with this patch.

Best Regards,
Kevin
________________________________
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 30275 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]                         ` <MN2PR12MB3598713DC8A8803F63886E758EAB0-rweVpJHSKTohWwLleUddgQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-20  5:44                           ` Wang, Kevin(Yang)
       [not found]                             ` <MN2PR12MB3296F5F765F20B96B8B82F1EA2AB0-rweVpJHSKTqAm9ToKNQgFgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Wang, Kevin(Yang) @ 2019-08-20  5:44 UTC (permalink / raw)
  To: Feng, Kenneth, Quan, Evan, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 15285 bytes --]

I don't recommend it.

each asic maybe has different thermal policy, you can custom this value in asic file <arcturus_ppt.c> .
and your patch define a new array in smu_v11_0.h header file.
it's never done that before, and the code looks is not clearly.

Best Regards,
Kevin
________________________________
From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>
Sent: Tuesday, August 20, 2019 10:51 AM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org <amd-gfx@lists.freedesktop.org>
Cc: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings


Reviewed-by: Kenneth Feng <kenneth.feng-5C7GfCeVMHo@public.gmane.org<mailto:kenneth.feng-5C7GfCeVMHo@public.gmane.org>>





From: Quan, Evan
Sent: Tuesday, August 20, 2019 10:10 AM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Cc: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>; Wang, Kevin(Yang) <Kevin1.Wang@amd.com>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Ping..



From: Quan, Evan
Sent: Monday, August 19, 2019 1:27 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Yes, the lowest settings for thermal controller is 0.



Regards

Evan

From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Monday, August 19, 2019 1:12 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Hi Evan,

So due to the below code, we don’t get a chance to set -273.15, right?

+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);



From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



[CAUTION: External Email]

Comment inline



From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Hi Evan,



the temperature min value should be 0, not -273 on smu11.

you can refrence window driver code or register spec.

        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;

[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.

All the existing and coming ASICs should  follow this design.

and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.

[Quan, Evan] That is still honored, no violation here.

so there is something wrong with this patch.



Best Regards,
Kevin

________________________________

From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 30776 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]                             ` <MN2PR12MB3296F5F765F20B96B8B82F1EA2AB0-rweVpJHSKTqAm9ToKNQgFgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-20  6:50                               ` Quan, Evan
       [not found]                                 ` <BN8PR12MB3329E1BF400EDECDCBDB70F2E4AB0-h6+T2+wrnx3WSNCBJ7MpiAdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
  0 siblings, 1 reply; 10+ messages in thread
From: Quan, Evan @ 2019-08-20  6:50 UTC (permalink / raw)
  To: Wang, Kevin(Yang),
	Feng, Kenneth, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 17249 bytes --]

Hi Kevin,

smu11_thermal_policy provides the default thermal policy if the ASIC does not provide its own(e.g. Navi10). It's not ASIC specific.

Btw I think we should have enough information to provide Navi10's own settings(for temp2/3) in navi10_get_thermal_temperature_range().
Can you help to add them?

Please refer to the following descriptions for those thermal interfaces.

* - 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
From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>
Sent: Tuesday, August 20, 2019 1:44 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>; Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings

I don't recommend it.

each asic maybe has different thermal policy, you can custom this value in asic file <arcturus_ppt.c> .
and your patch define a new array in smu_v11_0.h header file.
it's never done that before, and the code looks is not clearly.

Best Regards,
Kevin
________________________________
From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Tuesday, August 20, 2019 10:51 AM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings


Reviewed-by: Kenneth Feng <kenneth.feng-5C7GfCeVMHo@public.gmane.org<mailto:kenneth.feng-5C7GfCeVMHo@public.gmane.org>>





From: Quan, Evan
Sent: Tuesday, August 20, 2019 10:10 AM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Cc: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Ping..



From: Quan, Evan
Sent: Monday, August 19, 2019 1:27 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Yes, the lowest settings for thermal controller is 0.



Regards

Evan

From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Monday, August 19, 2019 1:12 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Hi Evan,

So due to the below code, we don't get a chance to set -273.15, right?

+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);



From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



[CAUTION: External Email]

Comment inline



From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Hi Evan,



the temperature min value should be 0, not -273 on smu11.

you can refrence window driver code or register spec.

        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;

[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.

All the existing and coming ASICs should  follow this design.

and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.

[Quan, Evan] That is still honored, no violation here.

so there is something wrong with this patch.



Best Regards,
Kevin

________________________________

From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 36290 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
* Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings
       [not found]                                 ` <BN8PR12MB3329E1BF400EDECDCBDB70F2E4AB0-h6+T2+wrnx3WSNCBJ7MpiAdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
@ 2019-08-20  8:13                                   ` Wang, Kevin(Yang)
  0 siblings, 0 replies; 10+ messages in thread
From: Wang, Kevin(Yang) @ 2019-08-20  8:13 UTC (permalink / raw)
  To: Quan, Evan, Feng, Kenneth, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW


[-- Attachment #1.1: Type: text/plain, Size: 18723 bytes --]

Hi Evan,

thank you for explaining this background reason.
you want to support more hwmon sensor in smu driver.
but in this patch, I have a few different opinions

  1.  could you move smu11_thermal_policy from smu_11_0.h to smu_v11_0.c, i think shouldn't define any data in header file.
  2.  +static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000}, //not used in this patch, why do you want to do?
+};
  3.  the smu driver will use 0 as min temperature to set hardware register, but it will show 273.15 as min value. in hwmon sensor
I think there is something wrong with this.
  4.  memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
although I know the meaning of this code, but I think this is not very good.

Best Regards,
Kevin
________________________________
From: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>
Sent: Tuesday, August 20, 2019 2:50 PM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>; Feng, Kenneth <Kenneth.Feng@amd.com>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings


Hi Kevin,



smu11_thermal_policy provides the default thermal policy if the ASIC does not provide its own(e.g. Navi10). It’s not ASIC specific.



Btw I think we should have enough information to provide Navi10’s own settings(for temp2/3) in navi10_get_thermal_temperature_range().

Can you help to add them?



Please refer to the following descriptions for those thermal interfaces.



* - 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

From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>
Sent: Tuesday, August 20, 2019 1:44 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>; Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



I don't recommend it.



each asic maybe has different thermal policy, you can custom this value in asic file <arcturus_ppt.c> .

and your patch define a new array in smu_v11_0.h header file.

it's never done that before, and the code looks is not clearly.



Best Regards,
Kevin

________________________________

From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Tuesday, August 20, 2019 10:51 AM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Reviewed-by: Kenneth Feng <kenneth.feng-5C7GfCeVMHo@public.gmane.org<mailto:kenneth.feng-5C7GfCeVMHo@public.gmane.org>>





From: Quan, Evan
Sent: Tuesday, August 20, 2019 10:10 AM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Cc: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Ping..



From: Quan, Evan
Sent: Monday, August 19, 2019 1:27 PM
To: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Yes, the lowest settings for thermal controller is 0.



Regards

Evan

From: Feng, Kenneth <Kenneth.Feng-5C7GfCeVMHo@public.gmane.org<mailto:Kenneth.Feng-5C7GfCeVMHo@public.gmane.org>>
Sent: Monday, August 19, 2019 1:12 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32mMSPqsTGOZug@public.gmane.orgesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Hi Evan,

So due to the below code, we don’t get a chance to set -273.15, right?

+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);



From: amd-gfx [mailto:amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org] On Behalf Of Quan, Evan
Sent: Monday, August 19, 2019 10:16 AM
To: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>; amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: RE: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



[CAUTION: External Email]

Comment inline



From: Wang, Kevin(Yang) <Kevin1.Wang-5C7GfCeVMHo@public.gmane.org<mailto:Kevin1.Wang-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 7:04 PM
To: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>; amd-gfx@lists.freedesktop.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Hi Evan,



the temperature min value should be 0, not -273 on smu11.

you can refrence window driver code or register spec.

        output_ptr->operating_temperature_min_Limit = 0;
        output_ptr->operating_temperature_max_Limit = ppt_info->software_shutdown_temp;

[Quan, Evan] There was a discussion over the min value(0 or -273.15) and we decided to use the later considering the OD case.

All the existing and coming ASICs should  follow this design.

and in smu11, the thermal control has a 8bit register to set min and max value, and the unit is temperature.

[Quan, Evan] That is still honored, no violation here.

so there is something wrong with this patch.



Best Regards,
Kevin

________________________________

From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-bounces@lists.freedesktop.org>> on behalf of Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
Sent: Friday, August 16, 2019 5:31 PM
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> <amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>>
Cc: Quan, Evan <Evan.Quan-5C7GfCeVMHo@public.gmane.org<mailto:Evan.Quan-5C7GfCeVMHo@public.gmane.org>>
Subject: [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings



Problems with current settings:
1. The min value was overrided to 0 on Vega20 & Navi10. While
   the expected should be -273.15 C.
2. The thermal min/max threshold was output in wrong unit on
   Navi10 & Arcturus. As TEMP_RANGE_MIN/MAX is already in
   millicelsius. And "*1000" in smu_v11_0_start_thermal_control
   makes the output wrongly.

Change-Id: I2f1866edd1baf264f521310343f492eaede26c33
Signed-off-by: Evan Quan <evan.quan-5C7GfCeVMHo@public.gmane.org<mailto:evan.quan-5C7GfCeVMHo@public.gmane.org>>
---
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c  | 10 ----
 drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h |  6 +++
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c    |  5 +-
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c     | 51 +++++++------------
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c    | 20 +++++---
 5 files changed, 38 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 4060607fbb35..1a1f64a9e1e0 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -880,23 +880,14 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
         return ret;
 }

-static const struct smu_temperature_range arcturus_thermal_policy[] =
-{
-       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
-       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
 static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
                                                 struct smu_temperature_range *range)
 {
-
         PPTable_t *pptable = smu->smu_table.driver_pptable;

         if (!range)
                 return -EINVAL;

-       memcpy(range, &arcturus_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) *
@@ -910,7 +901,6 @@ static int arcturus_get_thermal_temperature_range(struct smu_context *smu,
         range->mem_emergency_max = (pptable->TmemLimit + CTF_OFFSET_HBM)*
                 SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

-
         return 0;
 }

diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 0a22fa48ff5a..59b2045e37e4 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -64,6 +64,12 @@
 #define WORKLOAD_MAP(profile, workload) \
         [profile] = {1, (workload)}

+static const struct smu_temperature_range smu11_thermal_policy[] =
+{
+       {-273150,  99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
+       { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
+};
+
 struct smu_11_0_cmn2aisc_mapping {
         int     valid_mapping;
         int     map_to;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index d7d4186b762f..e804d18f61d0 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1505,9 +1505,8 @@ static int navi10_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* The unit is temperature */
-       range->min = 0;
-       range->max = powerplay_table->software_shutdown_temp;
+       range->max = powerplay_table->software_shutdown_temp *
+               SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;

         return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index df7b65360ac7..5f5fd3a88e48 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1125,23 +1125,17 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 }

 static int smu_v11_0_set_thermal_range(struct smu_context *smu,
-                                      struct smu_temperature_range *range)
+                                      struct smu_temperature_range range)
 {
         struct amdgpu_device *adev = smu->adev;
         int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
         int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
         uint32_t val;

-       if (!range)
-               return -EINVAL;
-
-       if (low < range->min)
-               low = range->min;
-       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);
+       low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
+                       range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+       high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
+                       range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);

         if (low > high)
                 return -EINVAL;
@@ -1177,27 +1171,20 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
         int ret = 0;
-       struct smu_temperature_range range = {
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MIN,
-               TEMP_RANGE_MAX,
-               TEMP_RANGE_MAX};
+       struct smu_temperature_range range;
         struct amdgpu_device *adev = smu->adev;

         if (!smu->pm_enabled)
                 return ret;

+       memcpy(&range, &smu11_thermal_policy[0], sizeof(struct smu_temperature_range));
+
         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);
+               ret = smu_v11_0_set_thermal_range(smu, range);
                 if (ret)
                         return ret;

@@ -1210,17 +1197,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
                         return ret;
         }

-       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;
-       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
-       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;
+       adev->pm.dpm.thermal.min_temp = range.min;
+       adev->pm.dpm.thermal.max_temp = range.max;
+       adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
+       adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
+       adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
+       adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
+       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;

         return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index acf075393c13..e14363182691 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3113,14 +3113,18 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
         if (!range || !powerplay_table)
                 return -EINVAL;

-       /* 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);
+       range->max = powerplay_table->usSoftwareShutdownTemp *
+               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;


         return 0;
--
2.22.0

_______________________________________________
amd-gfx mailing list
amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org<mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[-- Attachment #1.2: Type: text/html, Size: 42160 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

^ permalink raw reply related	[flat|nested] 10+ messages in thread
end of thread, other threads:[~2019-08-20  8:13 UTC | newest]

Thread overview: 10+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-08-16  9:31 [PATCH] drm/amd/powerplay: correct SW smu11 thermal range settings Evan Quan
     [not found] ` <20190816093144.21892-1-evan.quan-5C7GfCeVMHo@public.gmane.org>
2019-08-16 11:04   ` Wang, Kevin(Yang)
     [not found]     ` <MN2PR12MB3296E3E1C79504DD56058410A2AF0-rweVpJHSKTqAm9ToKNQgFgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-19  2:16       ` Quan, Evan
     [not found]         ` <MN2PR12MB3344E88B19DF4DA83279BBF2E4A80-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-19  5:11           ` Feng, Kenneth
     [not found]             ` <MN2PR12MB35981C5C1B0A12B8C8C1CD468EA80-rweVpJHSKTohWwLleUddgQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-19  5:26               ` Quan, Evan
     [not found]                 ` <MN2PR12MB334468A94B93D7D848596611E4A80-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-20  2:09                   ` Quan, Evan
     [not found]                     ` <MN2PR12MB334407D4ABFF5E4F1CC02518E4AB0-rweVpJHSKToDMgCC8P//OwdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-20  2:51                       ` Feng, Kenneth
     [not found]                         ` <MN2PR12MB3598713DC8A8803F63886E758EAB0-rweVpJHSKTohWwLleUddgQdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-20  5:44                           ` Wang, Kevin(Yang)
     [not found]                             ` <MN2PR12MB3296F5F765F20B96B8B82F1EA2AB0-rweVpJHSKTqAm9ToKNQgFgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-20  6:50                               ` Quan, Evan
     [not found]                                 ` <BN8PR12MB3329E1BF400EDECDCBDB70F2E4AB0-h6+T2+wrnx3WSNCBJ7MpiAdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2019-08-20  8:13                                   ` Wang, Kevin(Yang)

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.