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
158
159
160
161
|
From 13413ecc53f6937a2e945f4f81f786663de3770e Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Thu, 19 Oct 2017 14:54:16 +0800
Subject: [PATCH 1070/4131] Revert "Revert "drm/amdgpu: Program ring for vce
instance 1 at its register space""
This reverts commit b65f7dba6f8642e644080549095f3ed6fc53ac12.
---
drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 95 +++++++++++++++++++++++++----------
1 file changed, 68 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 9ef8145..242dfb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -77,13 +77,26 @@ static int vce_v3_0_set_clockgating_state(void *handle,
static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
+ u32 v;
+
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (adev->vce.harvest_config == 0 ||
+ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
+ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
if (ring == &adev->vce.ring[0])
- return RREG32(mmVCE_RB_RPTR);
+ v = RREG32(mmVCE_RB_RPTR);
else if (ring == &adev->vce.ring[1])
- return RREG32(mmVCE_RB_RPTR2);
+ v = RREG32(mmVCE_RB_RPTR2);
else
- return RREG32(mmVCE_RB_RPTR3);
+ v = RREG32(mmVCE_RB_RPTR3);
+
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+ mutex_unlock(&adev->grbm_idx_mutex);
+
+ return v;
}
/**
@@ -96,13 +109,26 @@ static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
+ u32 v;
+
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (adev->vce.harvest_config == 0 ||
+ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
+ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
if (ring == &adev->vce.ring[0])
- return RREG32(mmVCE_RB_WPTR);
+ v = RREG32(mmVCE_RB_WPTR);
else if (ring == &adev->vce.ring[1])
- return RREG32(mmVCE_RB_WPTR2);
+ v = RREG32(mmVCE_RB_WPTR2);
else
- return RREG32(mmVCE_RB_WPTR3);
+ v = RREG32(mmVCE_RB_WPTR3);
+
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+ mutex_unlock(&adev->grbm_idx_mutex);
+
+ return v;
}
/**
@@ -116,12 +142,22 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
+ mutex_lock(&adev->grbm_idx_mutex);
+ if (adev->vce.harvest_config == 0 ||
+ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
+ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
+ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
+
if (ring == &adev->vce.ring[0])
WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
else if (ring == &adev->vce.ring[1])
WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
else
WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
+
+ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
+ mutex_unlock(&adev->grbm_idx_mutex);
}
static void vce_v3_0_override_vce_clock_gating(struct amdgpu_device *adev, bool override)
@@ -231,33 +267,38 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
struct amdgpu_ring *ring;
int idx, r;
- ring = &adev->vce.ring[0];
- WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
- WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
- WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
-
- ring = &adev->vce.ring[1];
- WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
- WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
- WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
-
- ring = &adev->vce.ring[2];
- WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
- WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr);
- WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr));
- WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4);
-
mutex_lock(&adev->grbm_idx_mutex);
for (idx = 0; idx < 2; ++idx) {
if (adev->vce.harvest_config & (1 << idx))
continue;
WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
+
+ /* Program instance 0 reg space for two instances or instance 0 case
+ program instance 1 reg space for only instance 1 available case */
+ if (idx != 1 || adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) {
+ ring = &adev->vce.ring[0];
+ WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
+ WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+ WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
+
+ ring = &adev->vce.ring[1];
+ WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
+ WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+ WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
+
+ ring = &adev->vce.ring[2];
+ WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
+ WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr);
+ WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr));
+ WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4);
+ }
+
vce_v3_0_mc_resume(adev, idx);
WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1);
--
2.7.4
|
