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
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
|
/*
* 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.
*
* Authors: Christian König
*/
#ifndef __AMDGPU_RING_H__
#define __AMDGPU_RING_H__
#include <drm/amdgpu_drm.h>
#include <drm/gpu_scheduler.h>
#include <drm/drm_print.h>
#include <drm/drm_suballoc.h>
struct amdgpu_device;
struct amdgpu_ring;
struct amdgpu_ib;
struct amdgpu_cs_parser;
struct amdgpu_job;
struct amdgpu_vm;
/* max number of rings */
#define AMDGPU_MAX_RINGS 28
#define AMDGPU_MAX_HWIP_RINGS 8
#define AMDGPU_MAX_GFX_RINGS 2
#define AMDGPU_MAX_SW_GFX_RINGS 2
#define AMDGPU_MAX_COMPUTE_RINGS 8
#define AMDGPU_MAX_VCE_RINGS 3
#define AMDGPU_MAX_UVD_ENC_RINGS 2
enum amdgpu_ring_priority_level {
AMDGPU_RING_PRIO_0,
AMDGPU_RING_PRIO_1,
AMDGPU_RING_PRIO_DEFAULT = 1,
AMDGPU_RING_PRIO_2,
AMDGPU_RING_PRIO_MAX
};
/* some special values for the owner field */
#define AMDGPU_FENCE_OWNER_UNDEFINED ((void *)0ul)
#define AMDGPU_FENCE_OWNER_VM ((void *)1ul)
#define AMDGPU_FENCE_OWNER_KFD ((void *)2ul)
#define AMDGPU_FENCE_FLAG_64BIT (1 << 0)
#define AMDGPU_FENCE_FLAG_INT (1 << 1)
#define AMDGPU_FENCE_FLAG_TC_WB_ONLY (1 << 2)
#define AMDGPU_FENCE_FLAG_EXEC (1 << 3)
#define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
#define AMDGPU_IB_POOL_SIZE (1024 * 1024)
enum amdgpu_ring_type {
AMDGPU_RING_TYPE_GFX = AMDGPU_HW_IP_GFX,
AMDGPU_RING_TYPE_COMPUTE = AMDGPU_HW_IP_COMPUTE,
AMDGPU_RING_TYPE_SDMA = AMDGPU_HW_IP_DMA,
AMDGPU_RING_TYPE_UVD = AMDGPU_HW_IP_UVD,
AMDGPU_RING_TYPE_VCE = AMDGPU_HW_IP_VCE,
AMDGPU_RING_TYPE_UVD_ENC = AMDGPU_HW_IP_UVD_ENC,
AMDGPU_RING_TYPE_VCN_DEC = AMDGPU_HW_IP_VCN_DEC,
AMDGPU_RING_TYPE_VCN_ENC = AMDGPU_HW_IP_VCN_ENC,
AMDGPU_RING_TYPE_VCN_JPEG = AMDGPU_HW_IP_VCN_JPEG,
AMDGPU_RING_TYPE_KIQ,
AMDGPU_RING_TYPE_MES
};
enum amdgpu_ib_pool_type {
/* Normal submissions to the top of the pipeline. */
AMDGPU_IB_POOL_DELAYED,
/* Immediate submissions to the bottom of the pipeline. */
AMDGPU_IB_POOL_IMMEDIATE,
/* Direct submission to the ring buffer during init and reset. */
AMDGPU_IB_POOL_DIRECT,
AMDGPU_IB_POOL_MAX
};
struct amdgpu_ib {
struct drm_suballoc *sa_bo;
uint32_t length_dw;
uint64_t gpu_addr;
uint32_t *ptr;
uint32_t flags;
};
struct amdgpu_sched {
u32 num_scheds;
struct drm_gpu_scheduler *sched[AMDGPU_MAX_HWIP_RINGS];
};
/*
* Fences.
*/
struct amdgpu_fence_driver {
uint64_t gpu_addr;
volatile uint32_t *cpu_addr;
/* sync_seq is protected by ring emission lock */
uint32_t sync_seq;
atomic_t last_seq;
bool initialized;
struct amdgpu_irq_src *irq_src;
unsigned irq_type;
struct timer_list fallback_timer;
unsigned num_fences_mask;
spinlock_t lock;
struct dma_fence **fences;
};
extern const struct drm_sched_backend_ops amdgpu_sched_ops;
void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
struct amdgpu_irq_src *irq_src,
unsigned irq_type);
void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev);
int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev);
void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev);
int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence, struct amdgpu_job *job,
unsigned flags);
int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
uint32_t timeout);
bool amdgpu_fence_process(struct amdgpu_ring *ring);
int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,
uint32_t wait_seq,
signed long timeout);
unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring);
void amdgpu_fence_driver_isr_toggle(struct amdgpu_device *adev, bool stop);
u64 amdgpu_fence_last_unsignaled_time_us(struct amdgpu_ring *ring);
void amdgpu_fence_update_start_timestamp(struct amdgpu_ring *ring, uint32_t seq,
ktime_t timestamp);
/*
* Rings.
*/
/* provided by hw blocks that expose a ring buffer for commands */
struct amdgpu_ring_funcs {
enum amdgpu_ring_type type;
uint32_t align_mask;
u32 nop;
bool support_64bit_ptrs;
bool no_user_fence;
bool secure_submission_supported;
unsigned vmhub;
unsigned extra_dw;
/* ring read/write ptr handling */
u64 (*get_rptr)(struct amdgpu_ring *ring);
u64 (*get_wptr)(struct amdgpu_ring *ring);
void (*set_wptr)(struct amdgpu_ring *ring);
/* validating and patching of IBs */
int (*parse_cs)(struct amdgpu_cs_parser *p,
struct amdgpu_job *job,
struct amdgpu_ib *ib);
int (*patch_cs_in_place)(struct amdgpu_cs_parser *p,
struct amdgpu_job *job,
struct amdgpu_ib *ib);
/* constants to calculate how many DW are needed for an emit */
unsigned emit_frame_size;
unsigned emit_ib_size;
/* command emit functions */
void (*emit_ib)(struct amdgpu_ring *ring,
struct amdgpu_job *job,
struct amdgpu_ib *ib,
uint32_t flags);
void (*emit_fence)(struct amdgpu_ring *ring, uint64_t addr,
uint64_t seq, unsigned flags);
void (*emit_pipeline_sync)(struct amdgpu_ring *ring);
void (*emit_vm_flush)(struct amdgpu_ring *ring, unsigned vmid,
uint64_t pd_addr);
void (*emit_hdp_flush)(struct amdgpu_ring *ring);
void (*emit_gds_switch)(struct amdgpu_ring *ring, uint32_t vmid,
uint32_t gds_base, uint32_t gds_size,
uint32_t gws_base, uint32_t gws_size,
uint32_t oa_base, uint32_t oa_size);
/* testing functions */
int (*test_ring)(struct amdgpu_ring *ring);
int (*test_ib)(struct amdgpu_ring *ring, long timeout);
/* insert NOP packets */
void (*insert_nop)(struct amdgpu_ring *ring, uint32_t count);
void (*insert_start)(struct amdgpu_ring *ring);
void (*insert_end)(struct amdgpu_ring *ring);
/* pad the indirect buffer to the necessary number of dw */
void (*pad_ib)(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
unsigned (*init_cond_exec)(struct amdgpu_ring *ring);
void (*patch_cond_exec)(struct amdgpu_ring *ring, unsigned offset);
/* note usage for clock and power gating */
void (*begin_use)(struct amdgpu_ring *ring);
void (*end_use)(struct amdgpu_ring *ring);
void (*emit_switch_buffer) (struct amdgpu_ring *ring);
void (*emit_cntxcntl) (struct amdgpu_ring *ring, uint32_t flags);
void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg,
uint32_t reg_val_offs);
void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
void (*emit_reg_wait)(struct amdgpu_ring *ring, uint32_t reg,
uint32_t val, uint32_t mask);
void (*emit_reg_write_reg_wait)(struct amdgpu_ring *ring,
uint32_t reg0, uint32_t reg1,
uint32_t ref, uint32_t mask);
void (*emit_frame_cntl)(struct amdgpu_ring *ring, bool start,
bool secure);
/* Try to soft recover the ring to make the fence signal */
void (*soft_recovery)(struct amdgpu_ring *ring, unsigned vmid);
int (*preempt_ib)(struct amdgpu_ring *ring);
void (*emit_mem_sync)(struct amdgpu_ring *ring);
void (*emit_wave_limit)(struct amdgpu_ring *ring, bool enable);
};
struct amdgpu_ring {
struct amdgpu_device *adev;
const struct amdgpu_ring_funcs *funcs;
struct amdgpu_fence_driver fence_drv;
struct drm_gpu_scheduler sched;
struct amdgpu_bo *ring_obj;
volatile uint32_t *ring;
unsigned rptr_offs;
u64 rptr_gpu_addr;
volatile u32 *rptr_cpu_addr;
u64 wptr;
u64 wptr_old;
unsigned ring_size;
unsigned max_dw;
int count_dw;
uint64_t gpu_addr;
uint64_t ptr_mask;
uint32_t buf_mask;
u32 idx;
u32 me;
u32 pipe;
u32 queue;
struct amdgpu_bo *mqd_obj;
uint64_t mqd_gpu_addr;
void *mqd_ptr;
uint64_t eop_gpu_addr;
u32 doorbell_index;
bool use_doorbell;
bool use_pollmem;
unsigned wptr_offs;
u64 wptr_gpu_addr;
volatile u32 *wptr_cpu_addr;
unsigned fence_offs;
u64 fence_gpu_addr;
volatile u32 *fence_cpu_addr;
uint64_t current_ctx;
char name[16];
u32 trail_seq;
unsigned trail_fence_offs;
u64 trail_fence_gpu_addr;
volatile u32 *trail_fence_cpu_addr;
unsigned cond_exe_offs;
u64 cond_exe_gpu_addr;
volatile u32 *cond_exe_cpu_addr;
unsigned vm_inv_eng;
struct dma_fence *vmid_wait;
bool has_compute_vm_bug;
bool no_scheduler;
int hw_prio;
unsigned num_hw_submission;
atomic_t *sched_score;
/* used for mes */
bool is_mes_queue;
uint32_t hw_queue_id;
struct amdgpu_mes_ctx_data *mes_ctx;
bool is_sw_ring;
unsigned int entry_index;
};
#define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib)))
#define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib)))
#define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0)
#define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
#define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
#define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
#define amdgpu_ring_emit_ib(r, job, ib, flags) ((r)->funcs->emit_ib((r), (job), (ib), (flags)))
#define amdgpu_ring_emit_pipeline_sync(r) (r)->funcs->emit_pipeline_sync((r))
#define amdgpu_ring_emit_vm_flush(r, vmid, addr) (r)->funcs->emit_vm_flush((r), (vmid), (addr))
#define amdgpu_ring_emit_fence(r, addr, seq, flags) (r)->funcs->emit_fence((r), (addr), (seq), (flags))
#define amdgpu_ring_emit_gds_switch(r, v, db, ds, wb, ws, ab, as) (r)->funcs->emit_gds_switch((r), (v), (db), (ds), (wb), (ws), (ab), (as))
#define amdgpu_ring_emit_hdp_flush(r) (r)->funcs->emit_hdp_flush((r))
#define amdgpu_ring_emit_switch_buffer(r) (r)->funcs->emit_switch_buffer((r))
#define amdgpu_ring_emit_cntxcntl(r, d) (r)->funcs->emit_cntxcntl((r), (d))
#define amdgpu_ring_emit_rreg(r, d, o) (r)->funcs->emit_rreg((r), (d), (o))
#define amdgpu_ring_emit_wreg(r, d, v) (r)->funcs->emit_wreg((r), (d), (v))
#define amdgpu_ring_emit_reg_wait(r, d, v, m) (r)->funcs->emit_reg_wait((r), (d), (v), (m))
#define amdgpu_ring_emit_reg_write_reg_wait(r, d0, d1, v, m) (r)->funcs->emit_reg_write_reg_wait((r), (d0), (d1), (v), (m))
#define amdgpu_ring_emit_frame_cntl(r, b, s) (r)->funcs->emit_frame_cntl((r), (b), (s))
#define amdgpu_ring_pad_ib(r, ib) ((r)->funcs->pad_ib((r), (ib)))
#define amdgpu_ring_init_cond_exec(r) (r)->funcs->init_cond_exec((r))
#define amdgpu_ring_patch_cond_exec(r,o) (r)->funcs->patch_cond_exec((r),(o))
#define amdgpu_ring_preempt_ib(r) (r)->funcs->preempt_ib(r)
int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw);
void amdgpu_ring_ib_begin(struct amdgpu_ring *ring);
void amdgpu_ring_ib_end(struct amdgpu_ring *ring);
void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count);
void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
void amdgpu_ring_commit(struct amdgpu_ring *ring);
void amdgpu_ring_undo(struct amdgpu_ring *ring);
int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
unsigned int max_dw, struct amdgpu_irq_src *irq_src,
unsigned int irq_type, unsigned int hw_prio,
atomic_t *sched_score);
void amdgpu_ring_fini(struct amdgpu_ring *ring);
void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring,
uint32_t reg0, uint32_t val0,
uint32_t reg1, uint32_t val1);
bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
struct dma_fence *fence);
static inline void amdgpu_ring_set_preempt_cond_exec(struct amdgpu_ring *ring,
bool cond_exec)
{
*ring->cond_exe_cpu_addr = cond_exec;
}
static inline void amdgpu_ring_clear_ring(struct amdgpu_ring *ring)
{
int i = 0;
while (i <= ring->buf_mask)
ring->ring[i++] = ring->funcs->nop;
}
static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v)
{
if (ring->count_dw <= 0)
DRM_ERROR("amdgpu: writing more dwords to the ring than expected!\n");
ring->ring[ring->wptr++ & ring->buf_mask] = v;
ring->wptr &= ring->ptr_mask;
ring->count_dw--;
}
static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring,
void *src, int count_dw)
{
unsigned occupied, chunk1, chunk2;
void *dst;
if (unlikely(ring->count_dw < count_dw))
DRM_ERROR("amdgpu: writing more dwords to the ring than expected!\n");
occupied = ring->wptr & ring->buf_mask;
dst = (void *)&ring->ring[occupied];
chunk1 = ring->buf_mask + 1 - occupied;
chunk1 = (chunk1 >= count_dw) ? count_dw: chunk1;
chunk2 = count_dw - chunk1;
chunk1 <<= 2;
chunk2 <<= 2;
if (chunk1)
memcpy(dst, src, chunk1);
if (chunk2) {
src += chunk1;
dst = (void *)ring->ring;
memcpy(dst, src, chunk2);
}
ring->wptr += count_dw;
ring->wptr &= ring->ptr_mask;
ring->count_dw -= count_dw;
}
#define amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset) \
(ring->is_mes_queue && ring->mes_ctx ? \
(ring->mes_ctx->meta_data_gpu_addr + offset) : 0)
#define amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset) \
(ring->is_mes_queue && ring->mes_ctx ? \
(void *)((uint8_t *)(ring->mes_ctx->meta_data_ptr) + offset) : \
NULL)
int amdgpu_ring_test_helper(struct amdgpu_ring *ring);
void amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
struct amdgpu_ring *ring);
int amdgpu_ring_init_mqd(struct amdgpu_ring *ring);
static inline u32 amdgpu_ib_get_value(struct amdgpu_ib *ib, int idx)
{
return ib->ptr[idx];
}
static inline void amdgpu_ib_set_value(struct amdgpu_ib *ib, int idx,
uint32_t value)
{
ib->ptr[idx] = value;
}
int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
unsigned size,
enum amdgpu_ib_pool_type pool,
struct amdgpu_ib *ib);
void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
struct dma_fence *f);
int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
struct amdgpu_ib *ibs, struct amdgpu_job *job,
struct dma_fence **f);
int amdgpu_ib_pool_init(struct amdgpu_device *adev);
void amdgpu_ib_pool_fini(struct amdgpu_device *adev);
int amdgpu_ib_ring_tests(struct amdgpu_device *adev);
#endif
|