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
|
/*
* Copyright 2008 Advanced Micro Devices, Inc.
* Copyright 2008 Red Hat Inc.
* Copyright 2009 Jerome Glisse.
*
* 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: Dave Airlie
* Alex Deucher
* Jerome Glisse
* Christian König
*/
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <drm/amdgpu_drm.h>
#include <drm/drm_debugfs.h>
#include "amdgpu.h"
#include "atom.h"
#include "amdgpu_trace.h"
#define AMDGPU_IB_TEST_TIMEOUT msecs_to_jiffies(1000)
#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT msecs_to_jiffies(2000)
/*
* IB
* IBs (Indirect Buffers) and areas of GPU accessible memory where
* commands are stored. You can put a pointer to the IB in the
* command ring and the hw will fetch the commands from the IB
* and execute them. Generally userspace acceleration drivers
* produce command buffers which are send to the kernel and
* put in IBs for execution by the requested ring.
*/
/**
* amdgpu_ib_get - request an IB (Indirect Buffer)
*
* @ring: ring index the IB is associated with
* @size: requested IB size
* @ib: IB object returned
*
* Request an IB (all asics). IBs are allocated using the
* suballocator.
* Returns 0 on success, error on failure.
*/
int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
unsigned size, struct amdgpu_ib *ib)
{
int r;
if (size) {
r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
&ib->sa_bo, size, 256);
if (r) {
dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
return r;
}
ib->ptr = amdgpu_sa_bo_cpu_addr(ib->sa_bo);
if (!vm)
ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
}
return 0;
}
/**
* amdgpu_ib_free - free an IB (Indirect Buffer)
*
* @adev: amdgpu_device pointer
* @ib: IB object to free
* @f: the fence SA bo need wait on for the ib alloation
*
* Free an IB (all asics).
*/
void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
struct dma_fence *f)
{
amdgpu_sa_bo_free(adev, &ib->sa_bo, f);
}
/**
* amdgpu_ib_schedule - schedule an IB (Indirect Buffer) on the ring
*
* @adev: amdgpu_device pointer
* @num_ibs: number of IBs to schedule
* @ibs: IB objects to schedule
* @f: fence created during this submission
*
* Schedule an IB on the associated ring (all asics).
* Returns 0 on success, error on failure.
*
* On SI, there are two parallel engines fed from the primary ring,
* the CE (Constant Engine) and the DE (Drawing Engine). Since
* resource descriptors have moved to memory, the CE allows you to
* prime the caches while the DE is updating register state so that
* the resource descriptors will be already in cache when the draw is
* processed. To accomplish this, the userspace driver submits two
* IBs, one for the CE and one for the DE. If there is a CE IB (called
* a CONST_IB), it will be put on the ring prior to the DE IB. Prior
* to SI there was just a DE IB.
*/
int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
struct amdgpu_ib *ibs, struct amdgpu_job *job,
struct dma_fence **f)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_ib *ib = &ibs[0];
struct dma_fence *tmp = NULL;
bool skip_preamble, need_ctx_switch;
unsigned patch_offset = ~0;
struct amdgpu_vm *vm;
uint64_t fence_ctx;
uint32_t status = 0, alloc_size;
unsigned fence_flags = 0;
unsigned i;
int r = 0;
bool need_pipe_sync = false;
if (num_ibs == 0)
return -EINVAL;
/* ring tests don't use a job */
if (job) {
vm = job->vm;
fence_ctx = job->base.s_fence ?
job->base.s_fence->scheduled.context : 0;
} else {
vm = NULL;
fence_ctx = 0;
}
if (!ring->sched.ready) {
dev_err(adev->dev, "couldn't schedule ib on ring <%s>\n", ring->name);
return -EINVAL;
}
if (vm && !job->vmid) {
dev_err(adev->dev, "VM IB without ID\n");
return -EINVAL;
}
alloc_size = ring->funcs->emit_frame_size + num_ibs *
ring->funcs->emit_ib_size;
r = amdgpu_ring_alloc(ring, alloc_size);
if (r) {
dev_err(adev->dev, "scheduling IB failed (%d).\n", r);
return r;
}
need_ctx_switch = ring->current_ctx != fence_ctx;
if (ring->funcs->emit_pipeline_sync && job &&
((tmp = amdgpu_sync_get_fence(&job->sched_sync, NULL)) ||
(amdgpu_sriov_vf(adev) && need_ctx_switch) ||
amdgpu_vm_need_pipeline_sync(ring, job))) {
need_pipe_sync = true;
if (tmp)
trace_amdgpu_ib_pipe_sync(job, tmp);
dma_fence_put(tmp);
}
if (ring->funcs->insert_start)
ring->funcs->insert_start(ring);
if (job) {
r = amdgpu_vm_flush(ring, job, need_pipe_sync);
if (r) {
amdgpu_ring_undo(ring);
return r;
}
}
if (job && ring->funcs->init_cond_exec)
patch_offset = amdgpu_ring_init_cond_exec(ring);
#ifdef CONFIG_X86_64
if (!(adev->flags & AMD_IS_APU))
#endif
{
if (ring->funcs->emit_hdp_flush)
amdgpu_ring_emit_hdp_flush(ring);
else
amdgpu_asic_flush_hdp(adev, ring);
}
if (need_ctx_switch)
status |= AMDGPU_HAVE_CTX_SWITCH;
skip_preamble = ring->current_ctx == fence_ctx;
if (job && ring->funcs->emit_cntxcntl) {
status |= job->preamble_status;
status |= job->preemption_status;
amdgpu_ring_emit_cntxcntl(ring, status);
}
for (i = 0; i < num_ibs; ++i) {
ib = &ibs[i];
/* drop preamble IBs if we don't have a context switch */
if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
skip_preamble &&
!(status & AMDGPU_PREAMBLE_IB_PRESENT_FIRST) &&
!amdgpu_mcbp &&
!amdgpu_sriov_vf(adev)) /* for SRIOV preemption, Preamble CE ib must be inserted anyway */
continue;
amdgpu_ring_emit_ib(ring, job, ib, status);
status &= ~AMDGPU_HAVE_CTX_SWITCH;
}
if (ring->funcs->emit_tmz)
amdgpu_ring_emit_tmz(ring, false);
#ifdef CONFIG_X86_64
if (!(adev->flags & AMD_IS_APU))
#endif
amdgpu_asic_invalidate_hdp(adev, ring);
if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
/* wrap the last IB with fence */
if (job && job->uf_addr) {
amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
fence_flags | AMDGPU_FENCE_FLAG_64BIT);
}
r = amdgpu_fence_emit(ring, f, fence_flags);
if (r) {
dev_err(adev->dev, "failed to emit fence (%d)\n", r);
if (job && job->vmid)
amdgpu_vmid_reset(adev, ring->funcs->vmhub, job->vmid);
amdgpu_ring_undo(ring);
return r;
}
if (ring->funcs->insert_end)
ring->funcs->insert_end(ring);
if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
amdgpu_ring_patch_cond_exec(ring, patch_offset);
ring->current_ctx = fence_ctx;
if (vm && ring->funcs->emit_switch_buffer)
amdgpu_ring_emit_switch_buffer(ring);
amdgpu_ring_commit(ring);
return 0;
}
/**
* amdgpu_ib_pool_init - Init the IB (Indirect Buffer) pool
*
* @adev: amdgpu_device pointer
*
* Initialize the suballocator to manage a pool of memory
* for use as IBs (all asics).
* Returns 0 on success, error on failure.
*/
int amdgpu_ib_pool_init(struct amdgpu_device *adev)
{
int r;
if (adev->ib_pool_ready) {
return 0;
}
r = amdgpu_sa_bo_manager_init(adev, &adev->ring_tmp_bo,
AMDGPU_IB_POOL_SIZE*64*1024,
AMDGPU_GPU_PAGE_SIZE,
AMDGPU_GEM_DOMAIN_GTT);
if (r) {
return r;
}
adev->ib_pool_ready = true;
return 0;
}
/**
* amdgpu_ib_pool_fini - Free the IB (Indirect Buffer) pool
*
* @adev: amdgp
|