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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
/*
* Copyright 2016 Advanced Micro Devices, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*
*/
#ifndef __AMDGPU_VCN_H__
#define __AMDGPU_VCN_H__
#define AMDGPU_VCN_STACK_SIZE (128*1024)
#define AMDGPU_VCN_CONTEXT_SIZE (512*1024)
#define AMDGPU_VCN_FIRMWARE_OFFSET 256
#define AMDGPU_VCN_MAX_ENC_RINGS 3
#define VCN_DEC_CMD_FENCE 0x00000000
#define VCN_DEC_CMD_TRAP 0x00000001
#define VCN_DEC_CMD_WRITE_REG 0x00000004
#define VCN_DEC_CMD_REG_READ_COND_WAIT 0x00000006
#define VCN_DEC_CMD_PACKET_START 0x0000000a
#define VCN_DEC_CMD_PACKET_END 0x0000000b
#define VCN_ENC_CMD_NO_OP 0x00000000
#define VCN_ENC_CMD_END 0x00000001
#define VCN_ENC_CMD_IB 0x00000002
#define VCN_ENC_CMD_FENCE 0x00000003
#define VCN_ENC_CMD_TRAP 0x00000004
#define VCN_ENC_CMD_REG_WRITE 0x0000000b
#define VCN_ENC_CMD_REG_WAIT 0x0000000c
#define VCN_VID_SOC_ADDRESS_2_0 0x1fa00
#define VCN_AON_SOC_ADDRESS_2_0 0x1f800
#define VCN_VID_IP_ADDRESS_2_0 0x0
#define VCN_AON_IP_ADDRESS_2_0 0x30000
#define RREG32_SOC15_DPG_MODE(ip, inst, reg, mask, sram_sel) \
({ WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_MASK, mask); \
WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_CTL, \
UVD_DPG_LMA_CTL__MASK_EN_MASK | \
((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) \
<< UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT) | \
(sram_sel << UVD_DPG_LMA_CTL__SRAM_SEL__SHIFT)); \
RREG32_SOC15(ip, inst, mmUVD_DPG_LMA_DATA); \
})
#define WREG32_SOC15_DPG_MODE(ip, inst, reg, value, mask, sram_sel) \
do { \
WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_DATA, value); \
WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_MASK, mask); \
WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_CTL, \
UVD_DPG_LMA_CTL__READ_WRITE_MASK | \
((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) \
<< UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT) | \
(sram_sel << UVD_DPG_LMA_CTL__SRAM_SEL__SHIFT)); \
} while (0)
#define SOC15_DPG_MODE_OFFSET_2_0(ip, inst, reg) \
({ \
uint32_t internal_reg_offset, addr; \
bool video_range, aon_range; \
\
addr = (adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
addr <<= 2; \
video_range = ((((0xFFFFF & addr) >= (VCN_VID_SOC_ADDRESS_2_0)) && \
((0xFFFFF & addr) < ((VCN_VID_SOC_ADDRESS_2_0 + 0x2600))))); \
aon_range = ((((0xFFFFF & addr) >= (VCN_AON_SOC_ADDRESS_2_0)) && \
((0xFFFFF & addr) < ((VCN_AON_SOC_ADDRESS_2_0 + 0x600))))); \
if (video_range) \
internal_reg_offset = ((0xFFFFF & addr) - (VCN_VID_SOC_ADDRESS_2_0) + \
(VCN_VID_IP_ADDRESS_2_0)); \
else if (aon_range) \
internal_reg_offset = ((0xFFFFF & addr) - (VCN_AON_SOC_ADDRESS_2_0) + \
(VCN_AON_IP_ADDRESS_2_0)); \
else \
internal_reg_offset = (0xFFFFF & addr); \
\
internal_reg_offset >>= 2; \
})
#define RREG32_SOC15_DPG_MODE_2_0(offset, mask_en) \
({ \
WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_CTL, \
(0x0 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT | \
mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT | \
offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT)); \
RREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_DATA); \
})
#define WREG32_SOC15_DPG_MODE_2_0(offset, value, mask_en, indirect) \
do { \
if (!indirect) { \
WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_DATA, value); \
WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_CTL, \
(0x1 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT | \
mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT | \
offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT)); \
} else { \
*adev->vcn.dpg_sram_curr_addr++ = offset; \
*adev->vcn.dpg_sram_curr_addr++ = value; \
} \
} while (0)
enum engine_status_constants {
UVD_PGFSM_STATUS__UVDM_UVDU_PWR_ON = 0x2AAAA0,
UVD_PGFSM_STATUS__UVDM_UVDU_PWR_ON_2_0 = 0xAAAA0,
UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON = 0x00000002,
UVD_STATUS__UVD_BUSY = 0x00000004,
GB_ADDR_CONFIG_DEFAULT = 0x26010011,
UVD_STATUS__IDLE = 0x2,
UVD_STATUS__BUSY = 0x5,
UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF = 0x1,
UVD_STATUS__RBC_BUSY = 0x1,
UVD_PGFSM_STATUS_UVDJ_PWR_ON = 0,
};
enum internal_dpg_state {
VCN_DPG_STATE__UNPAUSE = 0,
VCN_DPG_STATE__PAUSE,
};
struct dpg_pause_state {
enum internal_dpg_state fw_based;
enum internal_dpg_state jpeg;
};
struct amdgpu_vcn_reg{
unsigned data0;
unsigned data1;
unsigned cmd;
unsigned nop;
unsigned scratch9;
unsigned jpeg_pitch;
};
struct amdgpu_vcn {
struct amdgpu_bo *vcpu_bo;
void *cpu_addr;
uint64_t gpu_addr;
unsigned fw_version;
void *saved_bo;
struct delayed_work idle_work;
const struct firmware *fw; /* VCN firmware */
struct amdgpu_ring ring_dec;
struct amdgpu_ring ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
struct amdgpu_ring ring_jpeg;
struct amdgpu_irq_src irq;
unsigned num_enc_rings;
enum amd_powergating_state cur_state;
struct dpg_pause_state pause_state;
struct amdgpu_vcn_reg internal, external;
int (*pause_dpg_mode)(struct amdgpu_device *adev,
struct dpg_pause_state *new_state);
bool indirect_sram;
struct amdgpu_bo *dpg_sram_bo;
void *dpg_sram_cpu_addr;
uint64_t dpg_sram_gpu_addr;
uint32_t *dpg_sram_curr_addr;
};
int amdgpu_vcn_sw_init(struct amdgpu_device *adev);
int amdgpu_vcn_sw_fini(struct amdgpu_device *adev);
int amdgpu_vcn_suspend(struct amdgpu_device *adev);
int amdgpu_vcn_resume(struct amdgpu_device *adev);
void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring);
void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring);
int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring);
int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring);
int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring);
int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout);
#endif
|