summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
blob: 02e52a146ed86e0c67587070fed32cfe053f5897 (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
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
/*
 * Copyright © 2016 Intel Corporation
 *
 * 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 (including the next
 * paragraph) 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 AUTHORS OR COPYRIGHT HOLDERS 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.
 *
 */

#include <linux/kthread.h>

#include "../i915_selftest.h"

#include "mock_context.h"
#include "mock_drm.h"

struct hang {
	struct drm_i915_private *i915;
	struct drm_i915_gem_object *hws;
	struct drm_i915_gem_object *obj;
	u32 *seqno;
	u32 *batch;
};

static int hang_init(struct hang *h, struct drm_i915_private *i915)
{
	void *vaddr;
	int err;

	memset(h, 0, sizeof(*h));
	h->i915 = i915;

	h->hws = i915_gem_object_create_internal(i915, PAGE_SIZE);
	if (IS_ERR(h->hws))
		return PTR_ERR(h->hws);

	h->obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
	if (IS_ERR(h->obj)) {
		err = PTR_ERR(h->obj);
		goto err_hws;
	}

	i915_gem_object_set_cache_level(h->hws, I915_CACHE_LLC);
	vaddr = i915_gem_object_pin_map(h->hws, I915_MAP_WB);
	if (IS_ERR(vaddr)) {
		err = PTR_ERR(vaddr);
		goto err_obj;
	}
	h->seqno = memset(vaddr, 0xff, PAGE_SIZE);

	vaddr = i915_gem_object_pin_map(h->obj,
					HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC);
	if (IS_ERR(vaddr)) {
		err = PTR_ERR(vaddr);
		goto err_unpin_hws;
	}
	h->batch = vaddr;

	return 0;

err_unpin_hws:
	i915_gem_object_unpin_map(h->hws);
err_obj:
	i915_gem_object_put(h->obj);
err_hws:
	i915_gem_object_put(h->hws);
	return err;
}

static u64 hws_address(const struct i915_vma *hws,
		       const struct drm_i915_gem_request *rq)
{
	return hws->node.start + offset_in_page(sizeof(u32)*rq->fence.context);
}

static int emit_recurse_batch(struct hang *h,
			      struct drm_i915_gem_request *rq)
{
	struct drm_i915_private *i915 = h->i915;
	struct i915_address_space *vm = rq->ctx->ppgtt ? &rq->ctx->ppgtt->base : &i915->ggtt.base;
	struct i915_vma *hws, *vma;
	unsigned int flags;
	u32 *batch;
	int err;

	vma = i915_vma_instance(h->obj, vm, NULL);
	if (IS_ERR(vma))
		return PTR_ERR(vma);

	hws = i915_vma_instance(h->hws, vm, NULL);
	if (IS_ERR(hws))
		return PTR_ERR(hws);

	err = i915_vma_pin(vma, 0, 0, PIN_USER);
	if (err)
		return err;

	err = i915_vma_pin(hws, 0, 0, PIN_USER);
	if (err)
		goto unpin_vma;

	err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
	if (err)
		goto unpin_hws;

	err = i915_switch_context(rq);
	if (err)
		goto unpin_hws;

	i915_vma_move_to_active(vma, rq, 0);
	if (!i915_gem_object_has_active_reference(vma->obj)) {
		i915_gem_object_get(vma->obj);
		i915_gem_object_set_active_reference(vma->obj);
	}

	i915_vma_move_to_active(hws, rq, 0);
	if (!i915_gem_object_has_active_reference(hws->obj)) {
		i915_gem_object_get(hws->obj);
		i915_gem_object_set_active_reference(hws->obj);
	}

	batch = h->batch;
	if (INTEL_GEN(i915) >= 8) {
		*batch++ = MI_STORE_DWORD_IMM_GEN4;
		*batch++ = lower_32_bits(hws_address(hws, rq));
		*batch++ = upper_32_bits(hws_address(hws, rq));
		*batch++ = rq->fence.seqno;
		*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
		*batch++ = lower_32_bits(vma->node.start);
		*batch++ = upper_32_bits(vma->node.start);
	} else if (INTEL_GEN(i915) >= 6) {
		*batch++ = MI_STORE_DWORD_IMM_GEN4;
		*batch++ = 0;
		*batch++ = lower_32_bits(hws_address(hws, rq));
		*batch++ = rq->fence.seqno;
		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
		*batch++ = lower_32_bits(vma->node.start);
	} else if (INTEL_GEN(i915) >= 4) {
		*batch++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
		*batch++ = 0;
		*batch++ = lower_32_bits(hws_address(hws, rq));
		*batch++ = rq->fence.seqno;
		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
		*batch++ = lower_32_bits(vma->node.start);
	} else {
		*batch++ = MI_STORE_DWORD_IMM;
		*batch++ = lower_32_bits(hws_address(hws, rq));
		*batch++ = rq->fence.seqno;
		*batch++ = MI_BATCH_BUFFER_START | 2 << 6 | 1;
		*batch++ = lower_32_bits(vma->node.start);
	}
	*batch++ = MI_BATCH_BUFFER_END; /* not reached */

	flags = 0;
	if (INTEL_GEN(vm->i915) <= 5)
		flags |= I915_DISPATCH_SECURE;

	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);

unpin_hws:
	i915_vma_unpin(hws);
unpin_vma:
	i915_vma_unpin(vma);
	return err;
}

static struct drm_i915_gem_request *
hang_create_request(struct hang *h,
		    struct intel_engine_cs *engine,
		    struct i915_gem_context *ctx)
{
	struct drm_i915_gem_request *rq;
	int err;

	if (i915_gem_object_is_active(h->obj)) {
		struct drm_i915_gem_object *obj;
		void *vaddr;

		obj = i915_gem_object_create_internal(h->i915, PAGE_SIZE);
		if (IS_ERR(obj))
			return ERR_CAST(obj);

		vaddr = i915_gem_object_pin_map(obj,
						HAS_LLC(h->i915) ? I915_MAP_WB : I915_MAP_WC);
		if (IS_ERR(vaddr)) {
			i915_gem_object_put(obj);
			return ERR_CAST(vaddr);
		}

		i915_gem_object_unpin_map(h->obj);
		i915_gem_object_put(h->obj);

		h->obj = obj;
		h->batch = vaddr;
	}

	rq = i915_gem_request_alloc(engine, ctx);
	if (IS_ERR(rq))
		return rq;

	err = emit_recurse_batch(h, rq);
	if (err) {
		__i915_add_request(rq, false);
		return ERR_PTR(err);
	}

	return rq;
}

static u32 hws_seqno(const struct hang *h,
		     const struct drm_i915_gem_request *rq)
{
	return READ_ONCE(h->seqno[rq->fence.context % (PAGE_SIZE/sizeof(u32))]);
}

static void hang_fini(struct hang *h)
{
	*h->batch = MI_BATCH_BUFFER_END;
	wmb();

	i915_gem_object_unpin_map(h->obj);
	i915_gem_object_put(h->obj);

	i915_gem_object_unpin_map(h->hws);
	i915_gem_object_put(h->hws);

	i915_gem_wait_for_idle(h->i915, I915_WAIT_LOCKED);
}

static int igt_hang_sanitycheck(void *arg)
{
	struct drm_i915_private *i915 = arg;
	struct drm_i915_gem_request *rq;
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
	struct hang h;
	int err;

	/* Basic check that we can execute our hanging batch */

	mutex_lock(&i915->drm.struct_mutex);
	err = hang_init(&h, i915);
	if (err)
		goto unlock;

	for_each_engine(engine, i915, id) {
		long timeout;

		if (!intel_engine_can_store_dword(engine))
			continue;

		rq = hang_create_request(&h, engine, i915->kernel_context);
		if (IS_ERR(rq)) {
			err = PTR_ERR(rq);
			pr_err("Failed to create request for %s, err=%d\n",
			       engine->name, err);
			goto fini;
		}

		i915_gem_request_get(rq);

		*h.batch = MI_BATCH_BUFFER_END;
		__i915_add_request(rq, true);

		timeout = i915_wait_request(rq,
					    I915_WAIT_LOCKED,
					    MAX_SCHEDULE_TIMEOUT);
		i915_gem_request_put(rq);

		if (timeout < 0) {
			err = timeout;
			pr_err("Wait for request failed on %s, err=%d\n",
			       engine->name, err);
			goto fini;
		}
	}

fini:
	hang_fini(&h);
unlock:
	mutex_unlock(&i915->drm.struct_mutex);
	return err;
}

static void global_reset_lock(struct drm_i915_private *i915)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags))
		wait_event(i915->gpu_error.reset_queue,
			   !test_bit(I915_RESET_BACKOFF,
				     &i915->gpu_error.flags));

	for_each_engine(engine, i915, id) {
		while (test_and_set_bit(I915_RESET_ENGINE + id,
					&i915->gpu_error.flags))
			wait_on_bit(&i915->gpu_error.flags,
				    I915_RESET_ENGINE + id,
				    TASK_UNINTERRUPTIBLE);
	}
}

static void global_reset_unlock(struct drm_i915_private *i915)
{
	struct intel_engine_cs *engine;
	enum intel_engine_id id;

	for_each_engine(engine, i915, id)
		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);

	clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags);
	wake_up_all(&i915->gpu_error.reset_queue);
}

static int igt_global_reset(void *arg)
{
	struct drm_i915_private *i915 = arg;
	unsigned int reset_count;
	int err = 0;

	/* Check that we can issue a global GPU reset */

	global_reset_lock(i915);
	set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags);

	mutex_lock(&i915->drm.struct_mutex);
	reset_count = i915_reset_count(&i915->gpu_error);

	i915_reset(i915, I915_RESET_QUIET);

	if (i915_reset_count(&i915->gpu_error) == reset_count) {
		pr_err("No GPU reset recorded!\n");
		err = -EINVAL;
	}
	mutex_unlock(&i915->drm.struct_mutex);

	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
	global_reset_unlock(i915);

	if (i915_terminally_wedged(&i915->gpu_error))
		err = -EIO;

	return err;
}

static int igt_reset_engine(void *arg)
{
	struct drm_i915_private *i915 = arg;
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
	unsigned int reset_count, reset_engine_count;
	int err = 0;

	/* Check that we can issue a global GPU and engine reset */

	if (!intel_has_reset_engine(i915))
		return 0;

	for_each_engine(engine, i915, id) {
		set_bit(I915_RESET_ENGINE + engine->id, &i915->gpu_error.flags);
		reset_count = i915_reset_count(&i915->gpu_error);
		reset_engine_count = i915_reset_engine_count(&i915->gpu_error,
							     engine);

		err = i915_reset_engine(engine, I915_RESET_QUIET);
		if (err) {
			pr_err("i915_reset_engine failed\n");
			break;
		}

		if (i915_reset_count(&i915->gpu_error) != reset_count) {
			pr_err("Full GPU reset recorded! (engine reset expected)\n");
			err = -EINVAL;
			break;
		}

		if (i915_reset_engine_count(&i915->gpu_error, engine) ==
		    reset_engine_count) {
			pr_err("No %s engine reset recorded!\n", engine->name);
			err = -EINVAL;
			break;
		}

		clear_bit(I915_RESET_ENGINE + engine->id,
			  &i915->gpu_error.flags);
	}

	if (i915_terminally_wedged(&i915->gpu_error))
		err = -EIO;

	return err;
}

static int active_engine(void *data)
{
	struct intel_engine_cs *engine = data;
	struct drm_i915_gem_request *rq[2] = {};
	struct i915_gem_context *ctx[2];
	struct drm_file *file;
	unsigned long count = 0;
	int err = 0;

	file = mock_file(engine->i915);
	if (IS_ERR(file))
		return PTR_ERR(file);

	mutex_lock(&engine->i915->drm.struct_mutex);
	ctx[0] = live_context(engine->i915, file);
	mutex_unlock(&engine->i915->drm.struct_mutex);
	if (IS_ERR(ctx[0])) {
		err = PTR_ERR(ctx[0]);
		goto err_file;
	}

	mutex_lock(&engine->i915->drm.struct_mutex);
	ctx[1] = live_context(engine->i915, file);
	mutex_unlock(&engine->i915->drm.struct_mutex);
	if (IS_ERR(ctx[1])) {
		err = PTR_ERR(ctx[1]);
		i915_gem_context_put(ctx[0]);
		goto err_file;
	}

	while (!kthread_should_stop()) {
		unsigned int idx = count++ & 1;
		struct drm_i915_gem_request *old = rq[idx];
		struct drm_i915_gem_request *new;

		mutex_lock(&engine->i915->drm.struct_mutex);
		new = i915_gem_request_alloc(engine, ctx[idx]);
		if (IS_ERR(new)) {
			mutex_unlock(&engine->i915->drm.struct_mutex);
			err = PTR_ERR(new);
			break;
		}

		rq[idx] = i915_gem_request_get(new);
		i915_add_request(new);
		mutex_unlock(&engine->i915->drm.struct_mutex);

		if (old) {
			i915_wait_request(old, 0, MAX_SCHEDULE_TIMEOUT);
			i915_gem_request_put(old);
		}
	}

	for (count = 0; count < ARRAY_SIZE(rq); count++)
		i915_gem_request_put(rq[count]);

err_file:
	mock_file_free(engine->i915, file);
	return err;
}

static int igt_reset_active_engines(void *arg)
{
	struct drm_i915_private *i915 = arg;
	struct intel_engine_cs *engine, *active;
	enum intel_engine_id id, tmp;
	int err = 0;

	/* Check that issuing a reset on one engine does not interfere
	 * with any other engine.
	 */

	if (!intel_has_reset_engine(i915))
		return 0;

	for_each_engine(engine, i915, id) {
		struct task_struct *threads[I915_NUM_ENGINES];
		unsigned long resets[I915_NUM_ENGINES];
		unsigned long global = i915_reset_count(&i915->gpu_error);
		IGT_TIMEOUT(end_time);

		memset(threads, 0, sizeof(threads));
		for_each_engine(active, i915, tmp) {
			struct task_struct *tsk;

			if (active == engine)
				continue;

			resets[tmp] = i915_reset_engine_count(&i915->gpu_error,
							      active);

			tsk = kthread_run(active_engine, active,
					  "igt/%s", active->name);
			if (IS_ERR(tsk)) {
				err = PTR_ERR(tsk);
				goto unwind;
			}

			threads[tmp] = tsk;
			get_task_struct(tsk);
		}

		set_bit(I915_RESET_ENGINE + engine->id, &i915->gpu_error.flags);
		do {
			err = i915_reset_engine(engine, I915_RESET_QUIET);
			if (err) {
				pr_err("i915_reset_engine(%s) failed, err=%d\n",
				       engine->name, err);
				break;
			}
		} while (time_before(jiffies, end_time));
		clear_bit(I915_RESET_ENGINE + engine->id,
			  &i915->gpu_error.flags);

unwind:
		for_each_engine(active, i915, tmp) {
			int ret;

			if (!threads[tmp])
				continue;

			ret = kthread_stop(threads[tmp]);
			if (ret) {
				pr_err("kthread for active engine %s failed, err=%d\n",
				       active->name, ret);
				if (!err)
					err = ret;
			}
			put_task_struct(threads[tmp]);

			if (resets[tmp] != i915_reset_engine_count(&i915->gpu_error,
								   active)) {
				pr_err("Innocent engine %s was reset (count=%ld)\n",
				       active->name,
				       i915_reset_engine_count(&i915->gpu_error,
							       active) - resets[tmp]);
				err = -EIO;
			}
		}

		if (global != i915_reset_count(&i915->gpu_error)) {
			pr_err("Global reset (count=%ld)!\n",
			       i915_reset_count(&i915->gpu_error) - global);
			err = -EIO;
		}

		if (err)
			break;

		cond_resched();
	}

	if (i915_terminally_wedged(&i915->gpu_error))
		err = -EIO;

	return err;
}

static u32 fake_hangcheck(struct drm_i915_gem_request *rq)
{
	u32 reset_count;

	rq->engine->hangcheck.stalled = true;
	rq->engine->hangcheck.seqno = intel_engine_get_seqno(rq->engine);

	reset_count = i915_reset_count(&rq->i915->gpu_error);

	set_bit(I915_RESET_HANDOFF, &rq->i915->gpu_error.flags);
	wake_up_all(&rq->i915->gpu_error.wait_queue);

	return reset_count;
}

static bool wait_for_hang(struct hang *h, struct drm_i915_gem_request *rq)
{
	return !(wait_for_us(i915_seqno_passed(hws_seqno(h, rq),
					       rq->fence.seqno),
			     10) &&
		 wait_for(i915_seqno_passed(hws_seqno(h, rq),
					    rq->fence.seqno),
			  1000));
}

static int igt_wait_reset(void *arg)
{
	struct drm_i915_private *i915 = arg;
	struct drm_i915_gem_request *rq;
	unsigned int reset_count;
	struct hang h;
	long timeout;
	int err;

	if (!intel_engine_can_store_dword(i915->engine[RCS]))
		return 0;

	/* Check that we detect a stuck waiter and issue a reset */

	global_reset_lock(i915);

	mutex_lock(&i915->drm.struct_mutex);
	err = hang_init(&h, i915);
	if (err)
		goto unlock;

	rq = hang_create_request(&h, i915->engine[RCS], i915->kernel_context);
	if (IS_ERR(rq)) {
		err = PTR_ERR(rq);
		goto fini;
	}

	i915_gem_request_get(rq);
	__i915_add_request(rq, true);

	if (!wait_for_hang(&h, rq)) {
		pr_err("Failed to start request %x\n", rq->fence.seqno);
		err = -EIO;
		goto out_rq;
	}

	reset_count = fake_hangcheck(rq);

	timeout = i915_wait_request(rq, I915_WAIT_LOCKED, 10);
	if (timeout < 0) {
		pr_err("i915_wait_request failed on a stuck request: err=%ld\n",
		       timeout);
		err = timeout;
		goto out_rq;
	}

	GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags));
	if (i915_reset_count(&i915->gpu_error) == reset_count) {
		pr_err("No GPU reset recorded!\n");
		err = -EINVAL;
		goto out_rq;
	}

out_rq:
	i915_gem_request_put(rq);
fini:
	hang_fini(&h);
unlock:
	mutex_unlock(&i915->drm.struct_mutex);
	global_reset_unlock(i915);

	if (i915_terminally_wedged(&i915->gpu_error))
		return -EIO;

	return err;
}

static int igt_reset_queue(void *arg)
{
	struct drm_i915_private *i915 = arg;
	struct intel_engine_cs *engine;
	enum intel_engine_id id;
	struct hang h;
	int err;

	/* Check that we replay pending requests following a hang */

	global_reset_lock(i915);

	mutex_lock(&i915->drm.struct_mutex);
	err = hang_init(&h, i915);
	if (err)
		goto unlock;

	for_each_engine(engine, i915, id) {
		struct drm_i915_gem_request *prev;
		IGT_TIMEOUT(end_time);
		unsigned int count;

		if (!intel_engine_can_store_dword(engine))
			continue;

		prev = hang_create_request(&h, engine, i915->kernel_context);
		if (IS_ERR(prev)) {
			err = PTR_ERR(prev);
			goto fini;
		}

		i915_gem_request_get(prev);
		__i915_add_request(prev, true);

		count = 0;
		do {
			struct drm_i915_gem_request *rq;
			unsigned int reset_count;

			rq = hang_create_request(&h,
						 engine,
						 i915->kernel_context);
			if (IS_ERR(rq)) {
				err = PTR_ERR(rq);
				goto fini;
			}

			i915_gem_request_get(rq);
			__i915_add_request(rq, true);

			if (!wait_for_hang(&h, prev)) {
				pr_err("Failed to start request %x\n",
				       prev->fence.seqno);
				i915_gem_request_put(rq);
				i915_gem_request_put(prev);
				err = -EIO;
				goto fini;
			}

			reset_count = fake_hangcheck(prev);

			i915_reset(i915, I915_RESET_QUIET);

			GEM_BUG_ON(test_bit(I915_RESET_HANDOFF,
					    &i915->gpu_error.flags));

			if (prev->fence.error != -EIO) {
				pr_err("GPU reset not recorded on hanging request [fence.error=%d]!\n",
				       prev->fence.error);
				i915_gem_request_put(rq);
				i915_gem_request_put(prev);
				err = -EINVAL;
				goto fini;
			}

			if (rq->fence.error) {
				pr_err("Fence error status not zero [%d] after unrelated reset\n",
				       rq->fence.error);
				i915_gem_request_put(rq);
				i915_gem_request_put(prev);
				err = -EINVAL;
				goto fini;
			}

			if (i915_reset_count(&i915->gpu_error) == reset_count) {
				pr_err("No GPU reset recorded!\n");
				i915_gem_request_put(rq);
				i915_gem_request_put(prev);
				err = -EINVAL;
				goto fini;
			}

			i915_gem_request_put(prev);
			prev = rq;
			count++;
		} while (time_before(jiffies, end_time));
		pr_info("%s: Completed %d resets\n", engine->name, count);

		*h.batch = MI_BATCH_BUFFER_END;
		wmb();

		i915_gem_request_put(prev);
	}

fini:
	hang_fini(&h);
unlock:
	mutex_unlock(&i915->drm.struct_mutex);
	global_reset_unlock(i915);

	if (i915_terminally_wedged(&i915->gpu_error))
		return -EIO;

	return err;
}

static int igt_handle_error(void *arg)
{
	struct drm_i915_private *i915 = arg;
	struct intel_engine_cs *engine = i915->engine[RCS];
	struct hang h;
	struct drm_i915_gem_request *rq;
	struct i915_gpu_state *error;
	int err;

	/* Check that we can issue a global GPU and engine reset */

	if (!intel_has_reset_engine(i915))
		return 0;

	if (!intel_engine_can_store_dword(i915->engine[RCS]))
		return 0;

	mutex_lock(&i915->drm.struct_mutex);

	err = hang_init(&h, i915);
	if (err)
		goto err_unlock;

	rq = hang_create_request(&h, engine, i915->kernel_context);
	if (IS_ERR(rq)) {
		err = PTR_ERR(rq);
		goto err_fini;
	}

	i915_gem_request_get(rq);
	__i915_add_request(rq, true);

	if (!wait_for_hang(&h, rq)) {
		pr_err("Failed to start request %x\n", rq->fence.seqno);
		err = -EIO;
		goto err_request;
	}

	mutex_unlock(&i915->drm.struct_mutex);

	/* Temporarily disable error capture */
	error = xchg(&i915->gpu_error.first_error, (void *)-1);

	engine->hangcheck.stalled = true;
	engine->hangcheck.seqno = intel_engine_get_seqno(engine);

	i915_handle_error(i915, intel_engine_flag(engine), "%s", __func__);

	xchg(&i915->gpu_error.first_error, error);

	mutex_lock(&i915->drm.struct_mutex);

	if (rq->fence.error != -EIO) {
		pr_err("Guilty request not identified!\n");
		err = -EINVAL;
		goto err_request;
	}

err_request:
	i915_gem_request_put(rq);
err_fini:
	hang_fini(&h);
err_unlock:
	mutex_unlock(&i915->drm.struct_mutex);
	return err;
}

int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
{
	static const struct i915_subtest tests[] = {
		SUBTEST(igt_hang_sanitycheck),
		SUBTEST(igt_global_reset),
		SUBTEST(igt_reset_engine),
		SUBTEST(igt_reset_active_engines),
		SUBTEST(igt_wait_reset),
		SUBTEST(igt_reset_queue),
		SUBTEST(igt_handle_error),
	};

	if (!intel_has_gpu_reset(i915))
		return 0;

	return i915_subtests(tests, i915);
}