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
214
215
216
217
218
|
/*
* Copyright 2019 Advanced Micro Devices, Inc.
* All Rights Reserved.
*
* 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, sub license, 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 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 NON-INFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS 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.
*
* The above copyright notice and this permission notice (including the
* next paragraph) shall be included in all copies or substantial portions
* of the Software.
*
*/
#include "amdgpu.h"
#include "amdgpu_jpeg.h"
#include "amdgpu_pm.h"
#include "soc15d.h"
#include "soc15_common.h"
#define JPEG_IDLE_TIMEOUT msecs_to_jiffies(1000)
static void amdgpu_jpeg_idle_work_handler(struct work_struct *work);
int amdgpu_jpeg_sw_init(struct amdgpu_device *adev)
{
INIT_DELAYED_WORK(&adev->jpeg.idle_work, amdgpu_jpeg_idle_work_handler);
mutex_init(&adev->jpeg.jpeg_pg_lock);
atomic_set(&adev->jpeg.total_submission_cnt, 0);
return 0;
}
int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
{
int i;
for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
if (adev->jpeg.harvest_config & (1 << i))
continue;
amdgpu_ring_fini(&adev->jpeg.inst[i].ring_dec);
}
mutex_destroy(&adev->jpeg.jpeg_pg_lock);
return 0;
}
int amdgpu_jpeg_suspend(struct amdgpu_device *adev)
{
cancel_delayed_work_sync(&adev->jpeg.idle_work);
return 0;
}
int amdgpu_jpeg_resume(struct amdgpu_device *adev)
{
return 0;
}
static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
{
struct amdgpu_device *adev =
container_of(work, struct amdgpu_device, jpeg.idle_work.work);
unsigned int fences = 0;
unsigned int i;
for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
if (adev->jpeg.harvest_config & (1 << i))
continue;
fences += amdgpu_fence_count_emitted(&adev->jpeg.inst[i].ring_dec);
}
if (!fences && !atomic_read(&adev->jpeg.total_submission_cnt))
amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
AMD_PG_STATE_GATE);
else
schedule_delayed_work(&adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
}
void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
atomic_inc(&adev->jpeg.total_submission_cnt);
cancel_delayed_work_sync(&adev->jpeg.idle_work);
mutex_lock(&adev->jpeg.jpeg_pg_lock);
amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
AMD_PG_STATE_UNGATE);
mutex_unlock(&adev->jpeg.jpeg_pg_lock);
}
void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring)
{
atomic_dec(&ring->adev->jpeg.total_submission_cnt);
schedule_delayed_work(&ring->adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
}
int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
uint32_t tmp = 0;
unsigned i;
int r;
WREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch, 0xCAFEDEAD);
r = amdgpu_ring_alloc(ring, 3);
if (r)
return r;
amdgpu_ring_write(ring, PACKET0(adev->jpeg.internal.jpeg_pitch, 0));
amdgpu_ring_write(ring, 0xDEADBEEF);
amdgpu_ring_commit(ring);
for (i = 0; i < adev->usec_timeout; i++) {
tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch);
if (tmp == 0xDEADBEEF)
break;
udelay(1);
}
if (i >= adev->usec_timeout)
r = -ETIMEDOUT;
return r;
}
static int amdgpu_jpeg_dec_set_reg(struct amdgpu_ring *ring, uint32_t handle,
struct dma_fence **fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
const unsigned ib_size_dw = 16;
int i, r;
r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4,
AMDGPU_IB_POOL_DIRECT, &job);
if (r)
return r;
ib = &job->ibs[0];
ib->ptr[0] = PACKETJ(adev->jpeg.internal.jpeg_pitch, 0, 0, PACKETJ_TYPE0);
ib->ptr[1] = 0xDEADBEEF;
for (i = 2; i < 16; i += 2) {
ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
ib->ptr[i+1] = 0;
}
ib->length_dw = 16;
r = amdgpu_job_submit_direct(job, ring, &f);
if (r)
goto err;
if (fence)
*fence = dma_fence_get(f);
dma_fence_put(f);
return 0;
err:
amdgpu_job_free(job);
return r;
}
int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
{
struct amdgpu_device *adev = ring->adev;
uint32_t tmp = 0;
unsigned i;
struct dma_fence *fence = NULL;
long r = 0;
r = amdgpu_jpeg_dec_set_reg(ring, 1, &fence);
if (r)
goto error;
r = dma_fence_wait_timeout(fence, false, timeout);
if (r == 0) {
r = -ETIMEDOUT;
goto error;
} else if (r < 0) {
goto error;
} else {
r = 0;
}
for (i = 0; i < adev->usec_timeout; i++) {
tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch);
if (tmp == 0xDEADBEEF)
break;
udelay(1);
}
if (i >= adev->usec_timeout)
r = -ETIMEDOUT;
dma_fence_put(fence);
error:
return r;
}
|
