summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_context.c
blob: a2f1245741bbf2e3e46d999e97f5d76387ae0628 (plain)
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
// SPDX-License-Identifier: MIT
/*
 * Copyright © 2019 Intel Corporation
 */

#include "gem/i915_gem_context.h"
#include "gem/i915_gem_pm.h"

#include "i915_drm_client.h"
#include "i915_drv.h"
#include "i915_trace.h"

#include "intel_context.h"
#include "intel_engine.h"
#include "intel_engine_pm.h"
#include "intel_ring.h"

static struct kmem_cache *slab_ce;

static struct intel_context *intel_context_alloc(void)
{
	return kmem_cache_zalloc(slab_ce, GFP_KERNEL);
}

static void rcu_context_free(struct rcu_head *rcu)
{
	struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);

	trace_intel_context_free(ce);
	kmem_cache_free(slab_ce, ce);
}

void intel_context_free(struct intel_context *ce)
{
	call_rcu(&ce->rcu, rcu_context_free);
}

struct intel_context *
intel_context_create(struct intel_engine_cs *engine)
{
	struct intel_context *ce;

	ce = intel_context_alloc();
	if (!ce)
		return ERR_PTR(-ENOMEM);

	intel_context_init(ce, engine);
	trace_intel_context_create(ce);
	return ce;
}

int intel_context_alloc_state(struct intel_context *ce)
{
	struct i915_gem_context *ctx;
	int err = 0;

	if (mutex_lock_interruptible(&ce->pin_mutex))
		return -EINTR;

	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
		if (intel_context_is_banned(ce)) {
			err = -EIO;
			goto unlock;
		}

		err = ce->ops->alloc(ce);
		if (unlikely(err))
			goto unlock;

		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);

		rcu_read_lock();
		ctx = rcu_dereference(ce->gem_context);
		if (ctx && !kref_get_unless_zero(&ctx->ref))
			ctx = NULL;
		rcu_read_unlock();
		if (ctx) {
			if (ctx->client)
				i915_drm_client_add_context_objects(ctx->client,
								    ce);
			i915_gem_context_put(ctx);
		}
	}

unlock:
	mutex_unlock(&ce->pin_mutex);
	return err;
}

static int intel_context_active_acquire(struct intel_context *ce)
{
	int err;

	__i915_active_acquire(&ce->active);

	if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine) ||
	    intel_context_is_parallel(ce))
		return 0;

	/* Preallocate tracking nodes */
	err = i915_active_acquire_preallocate_barrier(&ce->active,
						      ce->engine);
	if (err)
		i915_active_release(&ce->active);

	return err;
}

static void intel_context_active_release(struct intel_context *ce)
{
	/* Nodes preallocated in intel_context_active() */
	i915_active_acquire_barrier(&ce->active);
	i915_active_release(&ce->active);
}

static int __context_pin_state(struct i915_vma *vma, struct i915_gem_ww_ctx *ww)
{
	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
	int err;

	err = i915_ggtt_pin(vma, ww, 0, bias | PIN_HIGH);
	if (err)
		return err;

	err = i915_active_acquire(&vma->active);
	if (err)
		goto err_unpin;

	/*
	 * And mark it as a globally pinned object to let the shrinker know
	 * it cannot reclaim the object until we release it.
	 */
	i915_vma_make_unshrinkable(vma);
	vma->obj->mm.dirty = true;

	return 0;

err_unpin:
	i915_vma_unpin(vma);
	return err;
}

static void __context_unpin_state(struct i915_vma *vma)
{
	i915_vma_make_shrinkable(vma);
	i915_active_release(&vma->active);
	__i915_vma_unpin(vma);
}

static int __ring_active(struct intel_ring *ring,
			 struct i915_gem_ww_ctx *ww)
{
	int err;

	err = intel_ring_pin(ring, ww);
	if (err)
		return err;

	err = i915_active_acquire(&ring->vma->active);
	if (err)
		goto err_pin;

	return 0;

err_pin:
	intel_ring_unpin(ring);
	return err;
}

static void __ring_retire(struct intel_ring *ring)
{
	i915_active_release(&ring->vma->active);
	intel_ring_unpin(ring);
}

static int intel_context_pre_pin(struct intel_context *ce,
				 struct i915_gem_ww_ctx *ww)
{
	int err;

	CE_TRACE(ce, "active\n");

	err = __ring_active(ce->ring, ww);
	if (err)
		return err;

	err = intel_timeline_pin(ce->timeline, ww);
	if (err)
		goto err_ring;

	if (!ce->state)
		return 0;

	err = __context_pin_state(ce->state, ww);
	if (err)
		goto err_timeline;


	return 0;

err_timeline:
	intel_timeline_unpin(ce->timeline);
err_ring:
	__ring_retire(ce->ring);
	return err;
}

static void intel_context_post_unpin(struct intel_context *ce)
{
	if (ce->state)
		__context_unpin_state(ce->state);

	intel_timeline_unpin(ce->timeline);
	__ring_retire(ce->ring);
}

int __intel_context_do_pin_ww(struct intel_context *ce,
			      struct i915_gem_ww_ctx *ww)
{
	bool handoff = false;
	void *vaddr;
	int err = 0;

	if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
		err = intel_context_alloc_state(ce);
		if (err)
			return err;
	}

	/*
	 * We always pin the context/ring/timeline here, to ensure a pin
	 * refcount for __intel_context_active(), which prevent a lock
	 * inversion of ce->pin_mutex vs dma_resv_lock().
	 */

	err = i915_gem_object_lock(ce->timeline->hwsp_ggtt->obj, ww);
	if (!err)
		err = i915_gem_object_lock(ce->ring->vma->obj, ww);
	if (!err && ce->state)
		err = i915_gem_object_lock(ce->state->obj, ww);
	if (!err)
		err = intel_context_pre_pin(ce, ww);
	if (err)
		return err;

	err = ce->ops->pre_pin(ce, ww, &vaddr);
	if (err)
		goto err_ctx_unpin;

	err = i915_active_acquire(&ce->active);
	if (err)
		goto err_post_unpin;

	err = mutex_lock_interruptible(&ce->pin_mutex);
	if (err)
		goto err_release;

	intel_engine_pm_might_get(ce->engine);

	if (unlikely(intel_context_is_closed(ce))) {
		err = -ENOENT;
		goto err_unlock;
	}

	if (likely(!atomic_add_unless(&ce->pin_count, 1, 0))) {
		err = intel_context_active_acquire(ce);
		if (unlikely(err))
			goto err_unlock;

		err = ce->ops->pin(ce, vaddr);
		if (err) {
			intel_context_active_release(ce);
			goto err_unlock;
		}

		CE_TRACE(ce, "pin ring:{start:%08x, head:%04x, tail:%04x}\n",
			 i915_ggtt_offset(ce->ring->vma),
			 ce->ring->head, ce->ring->tail);

		handoff = true;
		smp_mb__before_atomic(); /* flush pin before it is visible */
		atomic_inc(&ce->pin_count);
	}

	GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */

	trace_intel_context_do_pin(ce);

err_unlock:
	mutex_unlock(&ce->pin_mutex);
err_release:
	i915_active_release(&ce->active);
err_post_unpin:
	if (!handoff)
		ce->ops->post_unpin(ce);
err_ctx_unpin:
	intel_context_post_unpin(ce);

	/*
	 * Unlock the hwsp_ggtt object since it's shared.
	 * In principle we can unlock all the global state locked above
	 * since it's pinned and doesn't need fencing, and will
	 * thus remain resident until it is explicitly unpinned.
	 */
	i915_gem_ww_unlock_single(ce->timeline->hwsp_ggtt->obj);

	return err;
}

int __intel_context_do_pin(struct intel_context *ce)
{
	struct i915_gem_ww_ctx ww;
	int err;

	i915_gem_ww_ctx_init(&ww, true);
retry:
	err = __intel_context_do_pin_ww(ce, &ww);
	if (err == -EDEADLK) {
		err = i915_gem_ww_ctx_backoff(&ww);
		if (!err)
			goto retry;
	}
	i915_gem_ww_ctx_fini(&ww);
	return err;
}

void __intel_context_do_unpin(struct intel_context *ce, int sub)
{
	if (!atomic_sub_and_test(sub, &ce->pin_count))
		return;

	CE_TRACE(ce, "unpin\n");
	ce->ops->unpin(ce);
	ce->ops->post_unpin(ce);

	/*
	 * Once released, we may asynchronously drop the active reference.
	 * As that may be the only reference keeping the context alive,
	 * take an extra now so that it is not freed before we finish
	 * dereferencing it.
	 */
	intel_context_get(ce);
	intel_context_active_release(ce);
	trace_intel_context_do_unpin(ce);
	intel_context_put(ce);
}

static void __intel_context_retire(struct i915_active *active)
{
	struct intel_context *ce = container_of(active, typeof(*ce), active);

	CE_TRACE(ce, "retire runtime: { total:%lluns, avg:%lluns }\n",
		 intel_context_get_total_runtime_ns(ce),
		 intel_context_get_avg_runtime_ns(ce));

	set_bit(CONTEXT_VALID_BIT, &ce->flags);
	intel_context_post_unpin(ce);
	intel_context_put(ce);
}

static int __intel_context_active(struct i915_active *active)
{
	struct intel_context *ce = container_of(active, typeof(*ce), active);

	intel_context_get(ce);

	/* everything should already be activated by intel_context_pre_pin() */
	GEM_WARN_ON(!i915_active_acquire_if_busy(&ce->ring->vma->active));
	__intel_ring_pin(ce->ring);

	__intel_timeline_pin(ce->timeline);

	if (ce->state) {
		GEM_WARN_ON(!i915_active_acquire_if_busy(&ce->state->active));
		__i915_vma_pin(ce->state);
		i915_vma_make_unshrinkable(ce->state);
	}

	return 0;
}

static int
sw_fence_dummy_notify(struct i915_sw_fence *sf,
		      enum i915_sw_fence_notify state)
{
	return NOTIFY_DONE;
}

void
intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
{
	GEM_BUG_ON(!engine->cops);
	GEM_BUG_ON(!engine->gt->vm);

	kref_init(&ce->ref);

	ce->engine = engine;
	ce->ops = engine->cops;
	ce->sseu = engine->sseu;
	ce->ring = NULL;
	ce->ring_size = SZ_4K;

	ewma_runtime_init(&ce->stats.runtime.avg);

	ce->vm = i915_vm_get(engine->gt->vm);

	/* NB ce->signal_link/lock is used under RCU */
	spin_lock_init(&ce->signal_lock);
	INIT_LIST_HEAD(&ce->signals);

	mutex_init(&ce->pin_mutex);

	spin_lock_init(&ce->guc_state.lock);
	INIT_LIST_HEAD(&ce->guc_state.fences);
	INIT_LIST_HEAD(&ce->guc_state.requests);

	ce->guc_id.id = GUC_INVALID_CONTEXT_ID;
	INIT_LIST_HEAD(&ce->guc_id.link);

	INIT_LIST_HEAD(&ce->destroyed_link);

	INIT_LIST_HEAD(&ce->parallel.child_list);

	/*
	 * Initialize fence to be complete as this is expected to be complete
	 * unless there is a pending schedule disable outstanding.
	 */
	i915_sw_fence_init(&ce->guc_state.blocked,
			   sw_fence_dummy_notify);
	i915_sw_fence_commit(&ce->guc_state.blocked);

	i915_active_init(&ce->active,
			 __intel_context_active, __intel_context_retire, 0);
}

void intel_context_fini(struct intel_context *ce)
{
	struct intel_context *child, *next;

	if (ce->timeline)
		intel_timeline_put(ce->timeline);
	i915_vm_put(ce->vm);

	/* Need to put the creation ref for the children */
	if (intel_context_is_parent(ce))
		for_each_child_safe(ce, child, next)
			intel_context_put(child);

	mutex_destroy(&ce->pin_mutex);
	i915_active_fini(&ce->active);
	i915_sw_fence_fini(&ce->guc_state.blocked);
}

void i915_context_module_exit(void)
{
	kmem_cache_destroy(slab_ce);
}

int __init i915_context_module_init(void)
{
	slab_ce = KMEM_CACHE(intel_context, SLAB_HWCACHE_ALIGN);
	if (!slab_ce)
		return -ENOMEM;

	return 0;
}

void intel_context_enter_engine(struct intel_context *ce)
{
	intel_engine_pm_get(ce->engine);
	intel_timeline_enter(ce->timeline);
}

void intel_context_exit_engine(struct intel_context *ce)
{
	intel_timeline_exit(ce->timeline);
	intel_engine_pm_put(ce->engine);
}

int intel_context_prepare_remote_request(struct intel_context *ce,
					 struct i915_request *rq)
{
	struct intel_timeline *tl = ce->timeline;
	int err;

	/* Only suitable for use in remotely modifying this context */
	GEM_BUG_ON(rq->context == ce);

	if (rcu_access_pointer(rq->timeline) != tl) { /* timeline sharing! */
		/* Queue this switch after current activity by this context. */
		err = i915_active_fence_set(&tl->last_request, rq);
		if (err)
			return err;
	}

	/*
	 * Guarantee context image and the timeline remains pinned until the
	 * modifying request is retired by setting the ce activity tracker.
	 *
	 * But we only need to take one pin on the account of it. Or in other
	 * words transfer the pinned ce object to tracked active request.
	 */
	GEM_BUG_ON(i915_active_is_idle(&ce->active));
	return i915_active_add_request(&ce->active, rq);
}

struct i915_request *intel_context_create_request(struct intel_context *ce)
{
	struct i915_gem_ww_ctx ww;
	struct i915_request *rq;
	int err;

	i915_gem_ww_ctx_init(&ww, true);
retry:
	err = intel_context_pin_ww(ce, &ww);
	if (!err) {
		rq = i915_request_create(ce);
		intel_context_unpin(ce);
	} else if (err == -EDEADLK) {
		err = i915_gem_ww_ctx_backoff(&ww);
		if (!err)
			goto retry;
		rq = ERR_PTR(err);
	} else {
		rq = ERR_PTR(err);
	}

	i915_gem_ww_ctx_fini(&ww);

	if (IS_ERR(rq))
		return rq;

	/*
	 * timeline->mutex should be the inner lock, but is used as outer lock.
	 * Hack around this to shut up lockdep in selftests..
	 */
	lockdep_unpin_lock(&ce->timeline->mutex, rq->cookie);
	mutex_release(&ce->timeline->mutex.dep_map, _RET_IP_);
	mutex_acquire(&ce->timeline->mutex.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_);
	rq->cookie = lockdep_pin_lock(&ce->timeline->mutex);

	return rq;
}

struct i915_request *intel_context_get_active_request(struct intel_context *ce)
{
	struct intel_context *parent = intel_context_to_parent(ce);
	struct i915_request *rq, *active = NULL;
	unsigned long flags;

	GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));

	/*
	 * We search the parent list to find an active request on the submitted
	 * context. The parent list contains the requests for all the contexts
	 * in the relationship so we have to do a compare of each request's
	 * context.
	 */
	spin_lock_irqsave(&parent->guc_state.lock, flags);
	list_for_each_entry_reverse(rq, &parent->guc_state.requests,
				    sched.link) {
		if (rq->context != ce)
			continue;
		if (i915_request_completed(rq))
			break;

		active = rq;
	}
	if (active)
		active = i915_request_get_rcu(active);
	spin_unlock_irqrestore(&parent->guc_state.lock, flags);

	return active;
}

void intel_context_bind_parent_child(struct intel_context *parent,
				     struct intel_context *child)
{
	/*
	 * Callers responsibility to validate that this function is used
	 * correctly but we use GEM_BUG_ON here ensure that they do.
	 */
	GEM_BUG_ON(intel_context_is_pinned(parent));
	GEM_BUG_ON(intel_context_is_child(parent));
	GEM_BUG_ON(intel_context_is_pinned(child));
	GEM_BUG_ON(intel_context_is_child(child));
	GEM_BUG_ON(intel_context_is_parent(child));

	parent->parallel.child_index = parent->parallel.number_children++;
	list_add_tail(&child->parallel.child_link,
		      &parent->parallel.child_list);
	child->parallel.parent = parent;
}

u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
{
	u64 total, active;

	if (ce->ops->update_stats)
		ce->ops->update_stats(ce);

	total = ce->stats.runtime.total;
	if (ce->ops->flags & COPS_RUNTIME_CYCLES)
		total *= ce->engine->gt->clock_period_ns;

	active = READ_ONCE(ce->stats.active);
	if (active)
		active = intel_context_clock() - active;

	return total + active;
}

u64 intel_context_get_avg_runtime_ns(struct intel_context *ce)
{
	u64 avg = ewma_runtime_read(&ce->stats.runtime.avg);

	if (ce->ops->flags & COPS_RUNTIME_CYCLES)
		avg *= ce->engine->gt->clock_period_ns;

	return avg;
}

bool intel_context_ban(struct intel_context *ce, struct i915_request *rq)
{
	bool ret = intel_context_set_banned(ce);

	trace_intel_context_ban(ce);

	if (ce->ops->revoke)
		ce->ops->revoke(ce, rq,
				INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS);

	return ret;
}

bool intel_context_revoke(struct intel_context *ce)
{
	bool ret = intel_context_set_exiting(ce);

	if (ce->ops->revoke)
		ce->ops->revoke(ce, NULL, ce->engine->props.preempt_timeout_ms);

	return ret;
}

#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_context.c"
#endif