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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
|
/*
* 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 __SOC15_COMMON_H__
#define __SOC15_COMMON_H__
/* GET_INST returns the physical instance corresponding to a logical instance */
#define GET_INST(ip, inst) \
(adev->ip_map.logical_to_dev_inst ? \
adev->ip_map.logical_to_dev_inst(adev, ip##_HWIP, inst) : inst)
#define GET_MASK(ip, mask) \
(adev->ip_map.logical_to_dev_mask ? \
adev->ip_map.logical_to_dev_mask(adev, ip##_HWIP, mask) : mask)
/* Register Access Macros */
#define SOC15_REG_OFFSET(ip, inst, reg) (adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg)
#define SOC15_REG_OFFSET1(ip, inst, reg, offset) \
(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + (reg)+(offset))
#define __WREG32_SOC15_RLC__(reg, value, flag, hwip, inst) \
((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.rlcg_reg_access_supported) ? \
amdgpu_sriov_wreg(adev, reg, value, flag, hwip, inst) : \
WREG32(reg, value))
#define __RREG32_SOC15_RLC__(reg, flag, hwip, inst) \
((amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs && adev->gfx.rlc.rlcg_reg_access_supported) ? \
amdgpu_sriov_rreg(adev, reg, flag, hwip, inst) : \
RREG32(reg))
#define WREG32_FIELD15(ip, idx, reg, field, val) \
__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg, \
(__RREG32_SOC15_RLC__( \
adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg, \
0, ip##_HWIP, idx) & \
~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field), \
0, ip##_HWIP, idx)
#define WREG32_FIELD15_PREREG(ip, idx, reg_name, field, val) \
__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][idx][reg##reg_name##_BASE_IDX] + reg##reg_name, \
(__RREG32_SOC15_RLC__( \
adev->reg_offset[ip##_HWIP][idx][reg##reg_name##_BASE_IDX] + reg##reg_name, \
0, ip##_HWIP, idx) & \
~REG_FIELD_MASK(reg_name, field)) | (val) << REG_FIELD_SHIFT(reg_name, field), \
0, ip##_HWIP, idx)
#define RREG32_SOC15(ip, inst, reg) \
__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
0, ip##_HWIP, inst)
#define RREG32_SOC15_IP(ip, reg) __RREG32_SOC15_RLC__(reg, 0, ip##_HWIP, 0)
#define RREG32_SOC15_IP_NO_KIQ(ip, reg, inst) __RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
#define RREG32_SOC15_NO_KIQ(ip, inst, reg) \
__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
#define RREG32_SOC15_OFFSET(ip, inst, reg, offset) \
__RREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + (reg)) + \
(offset), 0, ip##_HWIP, inst)
#define WREG32_SOC15(ip, inst, reg, value) \
__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), \
value, 0, ip##_HWIP, inst)
#define WREG32_SOC15_IP(ip, reg, value) \
__WREG32_SOC15_RLC__(reg, value, 0, ip##_HWIP, 0)
#define WREG32_SOC15_IP_NO_KIQ(ip, reg, value, inst) \
__WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
#define WREG32_SOC15_NO_KIQ(ip, inst, reg, value) \
__WREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, \
value, AMDGPU_REGS_NO_KIQ, ip##_HWIP, inst)
#define WREG32_SOC15_OFFSET(ip, inst, reg, offset, value) \
__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, \
value, 0, ip##_HWIP, inst)
#define SOC15_WAIT_ON_RREG(ip, inst, reg, expected_value, mask) \
amdgpu_device_wait_on_rreg(adev, inst, \
(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + (reg)), \
#reg, expected_value, mask)
#define SOC15_WAIT_ON_RREG_OFFSET(ip, inst, reg, offset, expected_value, mask) \
amdgpu_device_wait_on_rreg(adev, inst, \
(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + (reg) + (offset)), \
#reg, expected_value, mask)
#define WREG32_RLC(reg, value) \
__WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_RLC, GC_HWIP, 0)
#define WREG32_RLC_EX(prefix, reg, value, inst) \
do { \
if (amdgpu_sriov_fullaccess(adev)) { \
uint32_t i = 0; \
uint32_t retries = 50000; \
uint32_t r0 = adev->reg_offset[GC_HWIP][inst][prefix##SCRATCH_REG0_BASE_IDX] + prefix##SCRATCH_REG0; \
uint32_t r1 = adev->reg_offset[GC_HWIP][inst][prefix##SCRATCH_REG1_BASE_IDX] + prefix##SCRATCH_REG1; \
uint32_t spare_int = adev->reg_offset[GC_HWIP][inst][prefix##RLC_SPARE_INT_BASE_IDX] + prefix##RLC_SPARE_INT; \
WREG32(r0, value); \
WREG32(r1, (reg | 0x80000000)); \
WREG32(spare_int, 0x1); \
for (i = 0; i < retries; i++) { \
u32 tmp = RREG32(r1); \
if (!(tmp & 0x80000000)) \
break; \
udelay(10); \
} \
if (i >= retries) \
pr_err("timeout: rlcg program reg:0x%05x failed !\n", reg); \
} else { \
WREG32(reg, value); \
} \
} while (0)
/* shadow the registers in the callback function */
#define WREG32_SOC15_RLC_SHADOW(ip, inst, reg, value) \
__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg), value, AMDGPU_REGS_RLC, GC_HWIP, inst)
/* for GC only */
#define RREG32_RLC(reg) \
__RREG32_SOC15_RLC__(reg, AMDGPU_REGS_RLC, GC_HWIP, 0)
#define WREG32_RLC_NO_KIQ(reg, value, hwip) \
__WREG32_SOC15_RLC__(reg, value, AMDGPU_REGS_NO_KIQ | AMDGPU_REGS_RLC, hwip, 0)
#define RREG32_RLC_NO_KIQ(reg, hwip) \
__RREG32_SOC15_RLC__(reg, AMDGPU_REGS_NO_KIQ | AMDGPU_REGS_RLC, hwip, 0)
#define WREG32_SOC15_RLC_SHADOW_EX(prefix, ip, inst, reg, value) \
do { \
uint32_t target_reg = adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg;\
if (amdgpu_sriov_fullaccess(adev)) { \
uint32_t r2 = adev->reg_offset[GC_HWIP][inst][prefix##SCRATCH_REG1_BASE_IDX] + prefix##SCRATCH_REG2; \
uint32_t r3 = adev->reg_offset[GC_HWIP][inst][prefix##SCRATCH_REG1_BASE_IDX] + prefix##SCRATCH_REG3; \
uint32_t grbm_cntl = adev->reg_offset[GC_HWIP][inst][prefix##GRBM_GFX_CNTL_BASE_IDX] + prefix##GRBM_GFX_CNTL; \
uint32_t grbm_idx = adev->reg_offset[GC_HWIP][inst][prefix##GRBM_GFX_INDEX_BASE_IDX] + prefix##GRBM_GFX_INDEX; \
if (target_reg == grbm_cntl) \
WREG32(r2, value); \
else if (target_reg == grbm_idx) \
WREG32(r3, value); \
WREG32(target_reg, value); \
} else { \
WREG32(target_reg, value); \
} \
} while (0)
#define RREG32_SOC15_RLC(ip, inst, reg) \
__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg, AMDGPU_REGS_RLC, ip##_HWIP, inst)
#define WREG32_SOC15_RLC(ip, inst, reg, value) \
do { \
uint32_t target_reg = adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg;\
__WREG32_SOC15_RLC__(target_reg, value, AMDGPU_REGS_RLC, ip##_HWIP, inst); \
} while (0)
#define WREG32_SOC15_RLC_EX(prefix, ip, inst, reg, value) \
do { \
uint32_t target_reg = adev->reg_offset[GC_HWIP][inst][reg##_BASE_IDX] + reg;\
WREG32_RLC_EX(prefix, target_reg, value, inst); \
} while (0)
#define WREG32_FIELD15_RLC(ip, idx, reg, field, val) \
__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg), \
(__RREG32_SOC15_RLC__(adev->reg_offset[ip##_HWIP][idx][mm##reg##_BASE_IDX] + mm##reg, \
AMDGPU_REGS_RLC, ip##_HWIP, idx) & \
~REG_FIELD_MASK(reg, field)) | (val) << REG_FIELD_SHIFT(reg, field), \
AMDGPU_REGS_RLC, ip##_HWIP, idx)
#define WREG32_SOC15_OFFSET_RLC(ip, inst, reg, offset, value) \
__WREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, value, AMDGPU_REGS_RLC, ip##_HWIP, inst)
#define RREG32_SOC15_OFFSET_RLC(ip, inst, reg, offset) \
__RREG32_SOC15_RLC__((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) + offset, AMDGPU_REGS_RLC, ip##_HWIP, inst)
/* inst equals to ext for some IPs */
#define RREG32_SOC15_EXT(ip, inst, reg, ext) \
RREG32_PCIE_EXT((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) * 4 \
+ adev->asic_funcs->encode_ext_smn_addressing(ext)) \
#define WREG32_SOC15_EXT(ip, inst, reg, ext, value) \
WREG32_PCIE_EXT((adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg) * 4 \
+ adev->asic_funcs->encode_ext_smn_addressing(ext), \
value) \
#define RREG64_MCA(ext, mca_base, idx) \
RREG64_PCIE_EXT(adev->asic_funcs->encode_ext_smn_addressing(ext) + mca_base + (idx * 8))
#define WREG64_MCA(ext, mca_base, idx, val) \
WREG64_PCIE_EXT(adev->asic_funcs->encode_ext_smn_addressing(ext) + mca_base + (idx * 8), val)
#endif
|
