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
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
|
/*
* Copyright 2015 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.
*
*/
/**
* DOC: Overview
*
* The GPU scheduler provides entities which allow userspace to push jobs
* into software queues which are then scheduled on a hardware run queue.
* The software queues have a priority among them. The scheduler selects the entities
* from the run queue using a FIFO. The scheduler provides dependency handling
* features among jobs. The driver is supposed to provide callback functions for
* backend operations to the scheduler like submitting a job to hardware run queue,
* returning the dependencies of a job etc.
*
* The organisation of the scheduler is the following:
*
* 1. Each hw run queue has one scheduler
* 2. Each scheduler has multiple run queues with different priorities
* (e.g., HIGH_HW,HIGH_SW, KERNEL, NORMAL)
* 3. Each scheduler run queue has a queue of entities to schedule
* 4. Entities themselves maintain a queue of jobs that will be scheduled on
* the hardware.
*
* The jobs in a entity are always scheduled in the order that they were pushed.
*/
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <uapi/linux/sched/types.h>
#include <drm/drmP.h>
#include <drm/gpu_scheduler.h>
#include <drm/spsc_queue.h>
#define CREATE_TRACE_POINTS
#include "gpu_scheduler_trace.h"
#define to_drm_sched_job(sched_job) \
container_of((sched_job), struct drm_sched_job, queue_node)
static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
/**
* drm_sched_rq_init - initialize a given run queue struct
*
* @rq: scheduler run queue
*
* Initializes a scheduler runqueue.
*/
static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
struct drm_sched_rq *rq)
{
spin_lock_init(&rq->lock);
INIT_LIST_HEAD(&rq->entities);
rq->current_entity = NULL;
rq->sched = sched;
}
/**
* drm_sched_rq_add_entity - add an entity
*
* @rq: scheduler run queue
* @entity: scheduler entity
*
* Adds a scheduler entity to the run queue.
*/
void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
struct drm_sched_entity *entity)
{
if (!list_empty(&entity->list))
return;
spin_lock(&rq->lock);
list_add_tail(&entity->list, &rq->entities);
spin_unlock(&rq->lock);
}
/**
* drm_sched_rq_remove_entity - remove an entity
*
* @rq: scheduler run queue
* @entity: scheduler entity
*
* Removes a scheduler entity from the run queue.
*/
void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
struct drm_sched_entity *entity)
{
if (list_empty(&entity->list))
return;
spin_lock(&rq->lock);
list_del_init(&entity->list);
if (rq->current_entity == entity)
rq->current_entity = NULL;
spin_unlock(&rq->lock);
}
/**
* drm_sched_rq_select_entity - Select an entity which could provide a job to run
*
* @rq: scheduler run queue to check.
*
* Try to find a ready entity, returns NULL if none found.
*/
static struct drm_sched_entity *
drm_sched_rq_select_entity(struct drm_sched_rq *rq)
{
struct drm_sched_entity *entity;
spin_lock(&rq->lock);
entity = rq->current_entity;
if (entity) {
list_for_each_entry_continue(entity, &rq->entities, list) {
if (drm_sched_entity_is_ready(entity)) {
rq->current_entity = entity;
spin_unlock(&rq->lock);
return entity;
}
}
}
list_for_each_entry(entity, &rq->entities, list) {
if (drm_sched_entity_is_ready(entity)) {
rq->current_entity = entity;
spin_unlock(&rq->lock);
return entity;
}
if (entity == rq->current_entity)
break;
}
spin_unlock(&rq->lock);
return NULL;
}
/**
* drm_sched_dependency_optimized
*
* @fence: the dependency fence
* @entity: the entity which depends on the above fence
*
* Returns true if the dependency can be optimized and false otherwise
*/
bool drm_sched_dependency_optimized(struct dma_fence* fence,
struct drm_sched_entity *entity)
{
struct drm_gpu_scheduler *sched = entity->rq->sched;
struct drm_sched_fence *s_fence;
if (!fence || dma_fence_is_signaled(fence))
return false;
if (fence->context == entity->fence_context)
return true;
s_fence = to_drm_sched_fence(fence);
if (s_fence && s_fence->sched == sched)
return true;
return false;
}
EXPORT_SYMBOL(drm_sched_dependency_optimized);
/**
* drm_sched_start_timeout - start timeout for reset worker
*
* @sched: scheduler instance to start the worker for
*
* Start the timeout for the given scheduler.
*/
static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
{
if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
!list_empty(&sched->ring_mirror_list))
schedule_delayed_work(&sched->work_tdr, sched->timeout);
}
/**
* drm_sched_fault - immediately start timeout handler
*
* @sched: scheduler where the timeout handling should be started.
*
* Start timeout handling immediately when the driver detects a hardware fault.
*/
void drm_sched_fault(struct drm_gpu_scheduler *sched)
{
mod_delayed_work(system_wq, &sched->work_tdr, 0);
}
EXPORT_SYMBOL(drm_sched_fault);
/* job_finish is called after hw fence signaled
*/
static void drm_sched_job_finish(struct work_struct *work)
{
struct drm_sched_job *s_job = container_of(work, struct drm_sched_job,
finish_work);
struct drm_gpu_scheduler *sched = s_job->sched;
/*
* Canceling the timeout without removing our job from the ring mirror
* list is safe, as we will only end up in this worker if our jobs
* finished fence has been signaled. So even if some another worker
* manages to find this job as the next job in the list, the fence
* signaled check below will prevent the timeout to be restarted.
*/
cancel_delayed_work_sync(&sched->work_tdr);
spin_lock(&sched->job_list_lock);
/* remove job from ring_mirror_list */
list_del(&s_job->node);
/* queue TDR for next job */
drm_sched_start_timeout(sched);
spin_unlock(&sched->job_list_lock);
dma_fence_put(&s_job->s_fence->finished);
sched->ops->free_job(s_job);
}
static void drm_sched_job_finish_cb(struct dma_fence *f,
struct dma_fence_cb *cb)
{
struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
finish_cb);
schedule_work(&job->finish_work);
}
static void drm_sched_job_begin(struct drm_sched_job *s_job)
{
struct drm_gpu_scheduler *sched = s_job->sched;
dma_fence_add_callback(&s_job->s_fence->finished, &s_job->finish_cb,
drm_sched_job_finish_cb);
spin_lock(&sched->job_list_lock);
list_add_tail(&s_job->node, &sched->ring_mirror_list);
drm_sched_start_timeout(sched);
spin_unlock(&sched->job_list_lock);
}
static void drm_sched_job_timedout(struct work_struct *work)
{
struct drm_gpu_scheduler *sched;
struct drm_sched_job *job;
int r;
sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
spin_lock(&sched->job_list_lock);
list_for_each_entry_reverse(job, &sched->ring_mirror_list, node) {
struct drm_sched_fence *fence = job->s_fence;
if (!dma_fence_remove_callback(fence->parent, &fence->cb))
goto already_signaled;
}
job = list_first_entry_or_null(&sched->ring_mirror_list,
struct drm_sched_job, node);
spin_unlock(&sched->job_list_lock);
if (job)
sched->ops->timedout_job(job);
spin_lock(&sched->job_list_lock);
list_for_each_entry(job, &sched->ring_mirror_list, node) {
struct drm_sched_fence *fence = job->s_fence;
if (!fence->parent || !list_empty(&fence->cb.node))
continue;
r = dma_fence_add_callback(fence->parent, &fence->cb,
drm_sched_process_job);
if (r)
drm_sched_process_job(fence->parent, &fence->cb);
already_signaled:
;
}
drm_sched_start_timeout(sched);
spin_unlock(&sched->job_list_lock);
}
/**
* drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
*
* @sched: scheduler instance
* @bad: bad scheduler job
*
*/
void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
{
struct drm_sched_job *s_job;
struct drm_sched_entity *entity, *tmp;
int i;
spin_lock(&sched->job_list_lock);
list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
if (s_job->s_fence->parent &&
dma_fence_remove_callback(s_job->s_fence->parent,
&s_job->s_fence->cb)) {
dma_fence_put(s_job->s_fence->parent);
s_job->s_fence->parent = NULL;
atomic_dec(&sched->hw_rq_count);
}
}
spin_unlock(&sched->job_list_lock);
if (bad && bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
atomic_inc(&bad->karma);
/* don't increase @bad's karma if it's from KERNEL RQ,
* becuase sometimes GPU hang would cause kernel jobs (like VM updating jobs)
* corrupt but keep in mind that kernel jobs always considered good.
*/
for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; i++ ) {
struct drm_sched_rq *rq = &sched->sched_rq[i];
spin_lock(&rq->lock);
list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
if (bad->s_fence->scheduled.context == entity->fence_context) {
if (atomic_read(&bad->karma) > bad->sched->hang_limit)
if (entity->guilty)
atomic_set(entity->guilty, 1);
break;
}
}
spin_unlock(&rq->lock);
if (&entity->list != &rq->entities)
break;
}
}
}
EXPORT_SYMBOL(drm_sched_hw_job_reset);
/**
* drm_sched_job_recovery - recover jobs after a reset
*
* @sched: scheduler instance
*
*/
void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
{
struct drm_sched_job *s_job, *tmp;
bool found_guilty = false;
int r;
spin_lock(&sched->job_list_lock);
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
struct drm_sched_fence *s_fence = s_job->s_fence;
struct dma_fence *fence;
uint64_t guilty_context;
if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
found_guilty = true;
guilty_context = s_job->s_fence->scheduled.context;
}
if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
dma_fence_set_error(&s_fence->finished, -ECANCELED);
spin_unlock(&sched->job_list_lock);
fence = sched->ops->run_job(s_job);
atomic_inc(&sched->hw_rq_count);
if (fence) {
s_fence->parent = dma_fence_get(fence);
r = dma_fence_add_callback(fence, &s_fence->cb,
drm_sched_process_job);
if (r == -ENOENT)
drm_sched_process_job(fence, &s_fence->cb);
else if (r)
DRM_ERROR("fence add callback failed (%d)\n",
r);
dma_fence_put(fence);
} else {
drm_sched_process_job(NULL, &s_fence->cb);
}
spin_lock(&sched->job_list_lock);
}
drm_sched_start_timeout(sched);
spin_unlock(&sched->job_list_lock);
}
EXPORT_SYMBOL(drm_sched_job_recovery);
/**
* drm_sched_job_init - init a scheduler job
*
* @job: scheduler job to init
* @entity: scheduler entity to use
* @owner: job owner for debugging
*
* Refer to drm_sched_entity_push_job() documentation
* for locking considerations.
*
* Returns 0 for success, negative error code otherwise.
*/
int drm_sched_job_init(struct drm_sched_job *job,
struct drm_sched_entity *entity,
void *owner)
{
struct drm_gpu_scheduler *sched;
drm_sched_entity_select_rq(entity);
if (!entity->rq)
return -ENOENT;
sched = entity->rq->sched;
job->sched = sched;
job->entity = entity;
job->s_priority = entity->rq - sched->sched_rq;
job->s_fence = drm_sched_fence_create(entity, owner);
if (!job->s_fence)
return -ENOMEM;
job->id = atomic64_inc_return(&sched->job_id_count);
INIT_WORK(&job->finish_work, drm_sched_job_finish);
INIT_LIST_HEAD(&job->node);
return 0;
}
EXPORT_SYMBOL(drm_sched_job_init);
/**
* drm_sched_ready - is the scheduler ready
*
* @sched: scheduler instance
*
* Return true if we can push more jobs to the hw, otherwise false.
*/
static bool drm_sched_ready(struct drm_gpu_scheduler *sched)
{
return atomic_read(&sched->hw_rq_count) <
sched->hw_submission_limit;
}
/**
* drm_sched_wakeup - Wake up the scheduler when it is ready
*
* @sched: scheduler instance
*
*/
void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
{
if (drm_sched_ready(sched))
wake_up_interruptible(&sched->wake_up_worker);
}
/**
* drm_sched_select_entity - Select next entity to process
*
* @sched: scheduler instance
*
* Returns the entity to process or NULL if none are found.
*/
static struct drm_sched_entity *
drm_sched_select_entity(struct drm_gpu_scheduler *sched)
{
struct drm_sched_entity *entity;
int i;
if (!drm_sched_ready(sched))
return NULL;
/* Kernel run queue has higher priority than normal run queue*/
for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
entity = drm_sched_rq_select_entity(&sched->sched_rq[i]);
if (entity)
break;
}
return entity;
}
/**
* drm_sched_process_job - process a job
*
* @f: fence
* @cb: fence callbacks
*
* Called after job has finished execution.
*/
static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
{
struct drm_sched_fence *s_fence =
container_of(cb, struct drm_sched_fence, cb);
struct drm_gpu_scheduler *sched = s_fence->sched;
dma_fence_get(&s_fence->finished);
atomic_dec(&sched->hw_rq_count);
atomic_dec(&sched->num_jobs);
drm_sched_fence_finished(s_fence);
trace_drm_sched_process_job(s_fence);
dma_fence_put(&s_fence->finished);
wake_up_interruptible(&sched->wake_up_worker);
}
/**
* drm_sched_blocked - check if the scheduler is blocked
*
* @sched: scheduler instance
*
* Returns true if blocked, otherwise false.
*/
static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
{
if (kthread_should_park()) {
kthread_parkme();
return true;
}
return false;
}
/**
* drm_sched_main - main scheduler thread
*
* @param: scheduler instance
*
* Returns 0.
*/
static int drm_sched_main(void *param)
{
struct sched_param sparam = {.sched_priority = 1};
struct drm_gpu_scheduler *sched = (struct drm_gpu_scheduler *)param;
int r;
sched_setscheduler(current, SCHED_FIFO, &sparam);
while (!kthread_should_stop()) {
struct drm_sched_entity *entity = NULL;
struct drm_sched_fence *s_fence;
struct drm_sched_job *sched_job;
struct dma_fence *fence;
wait_event_interruptible(sched->wake_up_worker,
(!drm_sched_blocked(sched) &&
(entity = drm_sched_select_entity(sched))) ||
kthread_should_stop());
if (!entity)
continue;
sched_job = drm_sched_entity_pop_job(entity);
if (!sched_job)
continue;
s_fence = sched_job->s_fence;
atomic_inc(&sched->hw_rq_count);
drm_sched_job_begin(sched_job);
fence = sched->ops->run_job(sched_job);
drm_sched_fence_scheduled(s_fence);
if (fence) {
s_fence->parent = dma_fence_get(fence);
r = dma_fence_add_callback(fence, &s_fence->cb,
drm_sched_process_job);
if (r == -ENOENT)
drm_sched_process_job(fence, &s_fence->cb);
else if (r)
DRM_ERROR("fence add callback failed (%d)\n",
r);
dma_fence_put(fence);
} else {
drm_sched_process_job(NULL, &s_fence->cb);
}
wake_up(&sched->job_scheduled);
}
return 0;
}
/**
* drm_sched_init - Init a gpu scheduler instance
*
* @sched: scheduler instance
* @ops: backend operations for this scheduler
* @hw_submission: number of hw submissions that can be in flight
* @hang_limit: number of times to allow a job to hang before dropping it
* @timeout: timeout value in jiffies for the scheduler
* @name: name used for debugging
*
* Return 0 on success, otherwise error code.
*/
int drm_sched_init(struct drm_gpu_scheduler *sched,
const struct drm_sched_backend_ops *ops,
unsigned hw_submission,
unsigned hang_limit,
long timeout,
const char *name)
{
int i;
sched->ops = ops;
sched->hw_submission_limit = hw_submission;
sched->name = name;
sched->timeout = timeout;
sched->hang_limit = hang_limit;
for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
drm_sched_rq_init(sched, &sched->sched_rq[i]);
init_waitqueue_head(&sched->wake_up_worker);
init_waitqueue_head(&sched->job_scheduled);
INIT_LIST_HEAD(&sched->ring_mirror_list);
spin_lock_init(&sched->job_list_lock);
atomic_set(&sched->hw_rq_count, 0);
INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
atomic_set(&sched->num_jobs, 0);
atomic64_set(&sched->job_id_count, 0);
/* Each scheduler will run on a seperate kernel thread */
sched->thread = kthread_run(drm_sched_main, sched, sched->name);
if (IS_ERR(sched->thread)) {
DRM_ERROR("Failed to create scheduler for %s.\n", name);
return PTR_ERR(sched->thread);
}
sched->ready = true;
return 0;
}
EXPORT_SYMBOL(drm_sched_init);
/**
* drm_sched_fini - Destroy a gpu scheduler
*
* @sched: scheduler instance
*
* Tears down and cleans up the scheduler.
*/
void drm_sched_fini(struct drm_gpu_scheduler *sched)
{
if (sched->thread)
kthread_stop(sched->thread);
sched->ready = false;
}
EXPORT_SYMBOL(drm_sched_fini);
|