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
|
From aa69b8c4902268b4cc26a99362ff758d03c2710c Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Tue, 5 Nov 2019 15:15:33 +0800
Subject: [PATCH 4363/4736] drm/amdgpu: perform p-state switch after the whole
hive initialized
P-state switch should be performed after all devices from the hive
get initialized.
Change-Id: Ifc7cac9ef0cf250447d2a412da35d601e2ac79ec
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Jonathan Kim <Jonathan.Kim at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 47 ++++++++++++++++------
1 file changed, 35 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index edc11fb2bf24..21ff9f6da355 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2057,6 +2057,7 @@ static int amdgpu_device_enable_mgpu_fan_boost(void)
*/
static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
{
+ struct amdgpu_gpu_instance *gpu_instance;
int i = 0, r;
for (i = 0; i < adev->num_ip_blocks; i++) {
@@ -2082,6 +2083,40 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
if (r)
DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
+
+ if (adev->gmc.xgmi.num_physical_nodes > 1) {
+ mutex_lock(&mgpu_info.mutex);
+
+ /*
+ * Reset device p-state to low as this was booted with high.
+ *
+ * This should be performed only after all devices from the same
+ * hive get initialized.
+ *
+ * However, it's unknown how many device in the hive in advance.
+ * As this is counted one by one during devices initializations.
+ *
+ * So, we wait for all XGMI interlinked devices initialized.
+ * This may bring some delays as those devices may come from
+ * different hives. But that should be OK.
+ */
+ if (mgpu_info.num_dgpu == adev->gmc.xgmi.num_physical_nodes) {
+ for (i = 0; i < mgpu_info.num_gpu; i++) {
+ gpu_instance = &(mgpu_info.gpu_ins[i]);
+ if (gpu_instance->adev->flags & AMD_IS_APU)
+ continue;
+
+ r = amdgpu_xgmi_set_pstate(gpu_instance->adev, 0);
+ if (r) {
+ DRM_ERROR("pstate setting failed (%d).\n", r);
+ break;
+ }
+ }
+ }
+
+ mutex_unlock(&mgpu_info.mutex);
+ }
+
return 0;
}
@@ -2193,18 +2228,6 @@ static void amdgpu_device_delayed_init_work_handler(struct work_struct *work)
r = amdgpu_ib_ring_tests(adev);
if (r)
DRM_ERROR("ib ring test failed (%d).\n", r);
-
- /*
- * set to low pstate by default
- * This should be performed after all devices from
- * XGMI finish their initializations. Thus it's moved
- * to here.
- * The time delay is 2S. TODO: confirm whether that
- * is enough for all possible XGMI setups.
- */
- r = amdgpu_xgmi_set_pstate(adev, 0);
- if (r)
- DRM_ERROR("pstate setting failed (%d).\n", r);
}
static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
--
2.17.1
|
