1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
|
From 2e6bb4502481a177bfe58849fe6b43e6f8189aaf Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Tue, 14 May 2019 11:46:27 +0800
Subject: [PATCH 1961/2940] drm/amd/powerplay: support sw smu hotspot and
memory temperature retrieval
Support hotspot and memory temperature retrieval on sw smu routine.
Change-Id: If2ed1e2835f4b158a4a6d93aee8b358af18b9bfc
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h | 3 +
drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 74 ++++++++++++++++---
2 files changed, 66 insertions(+), 11 deletions(-)
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 aa8d81f4111e..02c965d64256 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -36,6 +36,9 @@
#define smnMP0_FW_INTF 0x30101c0
#define smnMP1_PUB_CTRL 0x3010b14
+#define TEMP_RANGE_MIN (0)
+#define TEMP_RANGE_MAX (80 * 1000)
+
struct smu_11_0_max_sustainable_clocks {
uint32_t display_clock;
uint32_t phy_clock;
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index 93ad3997becc..da59a0972b8e 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1011,9 +1011,20 @@ static int smu_v11_0_get_current_clk_freq(struct smu_context *smu, uint32_t clk_
static int smu_v11_0_get_thermal_range(struct smu_context *smu,
struct PP_TemperatureRange *range)
{
+ PPTable_t *pptable = smu->smu_table.driver_pptable;
memcpy(range, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange));
- range->max = smu->smu_table.software_shutdown_temp *
+ range->max = pptable->TedgeLimit *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE) *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ range->hotspot_crit_max = pptable->ThotspotLimit *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT) *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ range->mem_crit_max = pptable->ThbmLimit *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM)*
PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
return 0;
@@ -1078,7 +1089,16 @@ static int smu_v11_0_set_thermal_fan_table(struct smu_context *smu)
static int smu_v11_0_start_thermal_control(struct smu_context *smu)
{
int ret = 0;
- struct PP_TemperatureRange range;
+ struct PP_TemperatureRange 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 amdgpu_device *adev = smu->adev;
smu_v11_0_get_thermal_range(smu, &range);
@@ -1098,6 +1118,13 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
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;
}
@@ -1151,22 +1178,45 @@ static int smu_v11_0_get_current_activity_percent(struct smu_context *smu,
return 0;
}
-static int smu_v11_0_thermal_get_temperature(struct smu_context *smu, uint32_t *value)
+static int smu_v11_0_thermal_get_temperature(struct smu_context *smu,
+ enum amd_pp_sensors sensor,
+ uint32_t *value)
{
struct amdgpu_device *adev = smu->adev;
+ SmuMetrics_t metrics;
uint32_t temp = 0;
+ int ret = 0;
if (!value)
return -EINVAL;
- temp = RREG32_SOC15(THM, 0, mmCG_MULT_THERMAL_STATUS);
- temp = (temp & CG_MULT_THERMAL_STATUS__CTF_TEMP_MASK) >>
- CG_MULT_THERMAL_STATUS__CTF_TEMP__SHIFT;
+ ret = smu_v11_0_get_metrics_table(smu, &metrics);
+ if (ret)
+ return ret;
+
+ switch (sensor) {
+ case AMDGPU_PP_SENSOR_HOTSPOT_TEMP:
+ temp = RREG32_SOC15(THM, 0, mmCG_MULT_THERMAL_STATUS);
+ temp = (temp & CG_MULT_THERMAL_STATUS__CTF_TEMP_MASK) >>
+ CG_MULT_THERMAL_STATUS__CTF_TEMP__SHIFT;
- temp = temp & 0x1ff;
- temp *= SMU11_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ temp = temp & 0x1ff;
+ temp *= SMU11_TEMPERATURE_UNITS_PER_CENTIGRADES;
- *value = temp;
+ *value = temp;
+ break;
+ case AMDGPU_PP_SENSOR_EDGE_TEMP:
+ *value = metrics.TemperatureEdge *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ break;
+ case AMDGPU_PP_SENSOR_MEM_TEMP:
+ *value = metrics.TemperatureHBM *
+ PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ break;
+ default:
+ pr_err("Invalid sensor for retrieving temp\n");
+ return -EINVAL;
+ }
return 0;
}
@@ -1235,8 +1285,10 @@ static int smu_v11_0_read_sensor(struct smu_context *smu,
ret = smu_get_current_clk_freq(smu, PPCLK_GFXCLK, (uint32_t *)data);
*size = 4;
break;
- case AMDGPU_PP_SENSOR_GPU_TEMP:
- ret = smu_v11_0_thermal_get_temperature(smu, (uint32_t *)data);
+ case AMDGPU_PP_SENSOR_HOTSPOT_TEMP:
+ case AMDGPU_PP_SENSOR_EDGE_TEMP:
+ case AMDGPU_PP_SENSOR_MEM_TEMP:
+ ret = smu_v11_0_thermal_get_temperature(smu, sensor, (uint32_t *)data);
*size = 4;
break;
case AMDGPU_PP_SENSOR_GPU_POWER:
--
2.17.1
|
