summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd/kfd_events.c
blob: 93aae5c1e78bf7a37a4e885a262f9de0b21981a4 (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
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
/*
 * Copyright 2014 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.
 */

#include <linux/mm_types.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/mman.h>
#include <linux/memory.h>
#include "kfd_priv.h"
#include "kfd_events.h"
#include <linux/device.h>

/*
 * Wrapper around wait_queue_entry_t
 */
struct kfd_event_waiter {
	wait_queue_entry_t wait;
	struct kfd_event *event; /* Event to wait for */
	bool activated;		 /* Becomes true when event is signaled */
};

/*
 * Each signal event needs a 64-bit signal slot where the signaler will write
 * a 1 before sending an interrupt. (This is needed because some interrupts
 * do not contain enough spare data bits to identify an event.)
 * We get whole pages and map them to the process VA.
 * Individual signal events use their event_id as slot index.
 */
struct kfd_signal_page {
	uint64_t *kernel_address;
	uint64_t __user *user_address;
};


static uint64_t *page_slots(struct kfd_signal_page *page)
{
	return page->kernel_address;
}

static struct kfd_signal_page *allocate_signal_page(struct kfd_process *p)
{
	void *backing_store;
	struct kfd_signal_page *page;

	page = kzalloc(sizeof(*page), GFP_KERNEL);
	if (!page)
		return NULL;

	backing_store = (void *) __get_free_pages(GFP_KERNEL,
					get_order(KFD_SIGNAL_EVENT_LIMIT * 8));
	if (!backing_store)
		goto fail_alloc_signal_store;

	/* Initialize all events to unsignaled */
	memset(backing_store, (uint8_t) UNSIGNALED_EVENT_SLOT,
	       KFD_SIGNAL_EVENT_LIMIT * 8);

	page->kernel_address = backing_store;
	pr_debug("Allocated new event signal page at %p, for process %p\n",
			page, p);

	return page;

fail_alloc_signal_store:
	kfree(page);
	return NULL;
}

static int allocate_event_notification_slot(struct kfd_process *p,
					    struct kfd_event *ev)
{
	int id;

	if (!p->signal_page) {
		p->signal_page = allocate_signal_page(p);
		if (!p->signal_page)
			return -ENOMEM;
		/* Oldest user mode expects 256 event slots */
		p->signal_mapped_size = 256*8;
	}

	/*
	 * Compatibility with old user mode: Only use signal slots
	 * user mode has mapped, may be less than
	 * KFD_SIGNAL_EVENT_LIMIT. This also allows future increase
	 * of the event limit without breaking user mode.
	 */
	id = idr_alloc(&p->event_idr, ev, 0, p->signal_mapped_size / 8,
		       GFP_KERNEL);
	if (id < 0)
		return id;

	ev->event_id = id;
	page_slots(p->signal_page)[id] = UNSIGNALED_EVENT_SLOT;

	return 0;
}

/*
 * Assumes that p->event_mutex is held and of course that p is not going
 * away (current or locked).
 */
static struct kfd_event *lookup_event_by_id(struct kfd_process *p, uint32_t id)
{
	return idr_find(&p->event_idr, id);
}

/**
 * lookup_signaled_event_by_partial_id - Lookup signaled event from partial ID
 * @p:     Pointer to struct kfd_process
 * @id:    ID to look up
 * @bits:  Number of valid bits in @id
 *
 * Finds the first signaled event with a matching partial ID. If no
 * matching signaled event is found, returns NULL. In that case the
 * caller should assume that the partial ID is invalid and do an
 * exhaustive search of all siglaned events.
 *
 * If multiple events with the same partial ID signal at the same
 * time, they will be found one interrupt at a time, not necessarily
 * in the same order the interrupts occurred. As long as the number of
 * interrupts is correct, all signaled events will be seen by the
 * driver.
 */
static struct kfd_event *lookup_signaled_event_by_partial_id(
	struct kfd_process *p, uint32_t id, uint32_t bits)
{
	struct kfd_event *ev;

	if (!p->signal_page || id >= KFD_SIGNAL_EVENT_LIMIT)
		return NULL;

	/* Fast path for the common case that @id is not a partial ID
	 * and we only need a single lookup.
	 */
	if (bits > 31 || (1U << bits) >= KFD_SIGNAL_EVENT_LIMIT) {
		if (page_slots(p->signal_page)[id] == UNSIGNALED_EVENT_SLOT)
			return NULL;

		return idr_find(&p->event_idr, id);
	}

	/* General case for partial IDs: Iterate over all matching IDs
	 * and find the first one that has signaled.
	 */
	for (ev = NULL; id < KFD_SIGNAL_EVENT_LIMIT && !ev; id += 1U << bits) {
		if (page_slots(p->signal_page)[id] == UNSIGNALED_EVENT_SLOT)
			continue;

		ev = idr_find(&p->event_idr, id);
	}

	return ev;
}

static int create_signal_event(struct file *devkfd,
				struct kfd_process *p,
				struct kfd_event *ev)
{
	int ret;

	if (p->signal_mapped_size &&
	    p->signal_event_count == p->signal_mapped_size / 8) {
		if (!p->signal_event_limit_reached) {
			pr_warn("Signal event wasn't created because limit was reached\n");
			p->signal_event_limit_reached = true;
		}
		return -ENOSPC;
	}

	ret = allocate_event_notification_slot(p, ev);
	if (ret) {
		pr_warn("Signal event wasn't created because out of kernel memory\n");
		return ret;
	}

	p->signal_event_count++;

	ev->user_signal_address = &p->signal_page->user_address[ev->event_id];
	pr_debug("Signal event number %zu created with id %d, address %p\n",
			p->signal_event_count, ev->event_id,
			ev->user_signal_address);

	return 0;
}

static int create_other_event(struct kfd_process *p, struct kfd_event *ev)
{
	/* Cast KFD_LAST_NONSIGNAL_EVENT to uint32_t. This allows an
	 * intentional integer overflow to -1 without a compiler
	 * warning. idr_alloc treats a negative value as "maximum
	 * signed integer".
	 */
	int id = idr_alloc(&p->event_idr, ev, KFD_FIRST_NONSIGNAL_EVENT_ID,
			   (uint32_t)KFD_LAST_NONSIGNAL_EVENT_ID + 1,
			   GFP_KERNEL);

	if (id < 0)
		return id;
	ev->event_id = id;

	return 0;
}

void kfd_event_init_process(struct kfd_process *p)
{
	mutex_init(&p->event_mutex);
	idr_init(&p->event_idr);
	p->signal_page = NULL;
	p->signal_event_count = 0;
}

static void destroy_event(struct kfd_process *p, struct kfd_event *ev)
{
	struct kfd_event_waiter *waiter;

	/* Wake up pending waiters. They will return failure */
	list_for_each_entry(waiter, &ev->wq.head, wait.entry)
		waiter->event = NULL;
	wake_up_all(&ev->wq);

	if (ev->type == KFD_EVENT_TYPE_SIGNAL ||
	    ev->type == KFD_EVENT_TYPE_DEBUG)
		p->signal_event_count--;

	idr_remove(&p->event_idr, ev->event_id);
	kfree(ev);
}

static void destroy_events(struct kfd_process *p)
{
	struct kfd_event *ev;
	uint32_t id;

	idr_for_each_entry(&p->event_idr, ev, id)
		destroy_event(p, ev);
	idr_destroy(&p->event_idr);
}

/*
 * We assume that the process is being destroyed and there is no need to
 * unmap the pages or keep bookkeeping data in order.
 */
static void shutdown_signal_page(struct kfd_process *p)
{
	struct kfd_signal_page *page = p->signal_page;

	if (page) {
		free_pages((unsigned long)page->kernel_address,
				get_order(KFD_SIGNAL_EVENT_LIMIT * 8));
		kfree(page);
	}
}

void kfd_event_free_process(struct kfd_process *p)
{
	destroy_events(p);
	shutdown_signal_page(p);
}

static bool event_can_be_gpu_signaled(const struct kfd_event *ev)
{
	return ev->type == KFD_EVENT_TYPE_SIGNAL ||
					ev->type == KFD_EVENT_TYPE_DEBUG;
}

static bool event_can_be_cpu_signaled(const struct kfd_event *ev)
{
	return ev->type == KFD_EVENT_TYPE_SIGNAL;
}

int kfd_event_create(struct file *devkfd, struct kfd_process *p,
		     uint32_t event_type, bool auto_reset, uint32_t node_id,
		     uint32_t *event_id, uint32_t *event_trigger_data,
		     uint64_t *event_page_offset, uint32_t *event_slot_index)
{
	int ret = 0;
	struct kfd_event *ev = kzalloc(sizeof(*ev), GFP_KERNEL);

	if (!ev)
		return -ENOMEM;

	ev->type = event_type;
	ev->auto_reset = auto_reset;
	ev->signaled = false;

	init_waitqueue_head(&ev->wq);

	*event_page_offset = 0;

	mutex_lock(&p->event_mutex);

	switch (event_type) {
	case KFD_EVENT_TYPE_SIGNAL:
	case KFD_EVENT_TYPE_DEBUG:
		ret = create_signal_event(devkfd, p, ev);
		if (!ret) {
			*event_page_offset = KFD_MMAP_EVENTS_MASK;
			*event_page_offset <<= PAGE_SHIFT;
			*event_slot_index = ev->event_id;
		}
		break;
	default:
		ret = create_other_event(p, ev);
		break;
	}

	if (!ret) {
		*event_id = ev->event_id;
		*event_trigger_data = ev->event_id;
	} else {
		kfree(ev);
	}

	mutex_unlock(&p->event_mutex);

	return ret;
}

/* Assumes that p is current. */
int kfd_event_destroy(struct kfd_process *p, uint32_t event_id)
{
	struct kfd_event *ev;
	int ret = 0;

	mutex_lock(&p->event_mutex);

	ev = lookup_event_by_id(p, event_id);

	if (ev)
		destroy_event(p, ev);
	else
		ret = -EINVAL;

	mutex_unlock(&p->event_mutex);
	return ret;
}

static void set_event(struct kfd_event *ev)
{
	struct kfd_event_waiter *waiter;

	/* Auto reset if the list is non-empty and we're waking
	 * someone. waitqueue_active is safe here because we're
	 * protected by the p->event_mutex, which is also held when
	 * updating the wait queues in kfd_wait_on_events.
	 */
	ev->signaled = !ev->auto_reset || !waitqueue_active(&ev->wq);

	list_for_each_entry(waiter, &ev->wq.head, wait.entry)
		waiter->activated = true;

	wake_up_all(&ev->wq);
}

/* Assumes that p is current. */
int kfd_set_event(struct kfd_process *p, uint32_t event_id)
{
	int ret = 0;
	struct kfd_event *ev;

	mutex_lock(&p->event_mutex);

	ev = lookup_event_by_id(p, event_id);

	if (ev && event_can_be_cpu_signaled(ev))
		set_event(ev);
	else
		ret = -EINVAL;

	mutex_unlock(&p->event_mutex);
	return ret;
}

static void reset_event(struct kfd_event *ev)
{
	ev->signaled = false;
}

/* Assumes that p is current. */
int kfd_reset_event(struct kfd_process *p, uint32_t event_id)
{
	int ret = 0;
	struct kfd_event *ev;

	mutex_lock(&p->event_mutex);

	ev = lookup_event_by_id(p, event_id);

	if (ev && event_can_be_cpu_signaled(ev))
		reset_event(ev);
	else
		ret = -EINVAL;

	mutex_unlock(&p->event_mutex);
	return ret;

}

static void acknowledge_signal(struct kfd_process *p, struct kfd_event *ev)
{
	page_slots(p->signal_page)[ev->event_id] = UNSIGNALED_EVENT_SLOT;
}

static void set_event_from_interrupt(struct kfd_process *p,
					struct kfd_event *ev)
{
	if (ev && event_can_be_gpu_signaled(ev)) {
		acknowledge_signal(p, ev);
		set_event(ev);
	}
}

void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
				uint32_t valid_id_bits)
{
	struct kfd_event *ev = NULL;

	/*
	 * Because we are called from arbitrary context (workqueue) as opposed
	 * to process context, kfd_process could attempt to exit while we are
	 * running so the lookup function increments the process ref count.
	 */
	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);

	if (!p)
		return; /* Presumably process exited. */

	mutex_lock(&p->event_mutex);

	if (valid_id_bits)
		ev = lookup_signaled_event_by_partial_id(p, partial_id,
							 valid_id_bits);
	if (ev) {
		set_event_from_interrupt(p, ev);
	} else if (p->signal_page) {
		/*
		 * Partial ID lookup failed. Assume that the event ID
		 * in the interrupt payload was invalid and do an
		 * exhaustive search of signaled events.
		 */
		uint64_t *slots = page_slots(p->signal_page);
		uint32_t id;

		if (valid_id_bits)
			pr_debug_ratelimited("Partial ID invalid: %u (%u valid bits)\n",
					     partial_id, valid_id_bits);

		if (p->signal_event_count < KFD_SIGNAL_EVENT_LIMIT/2) {
			/* With relatively few events, it's faster to
			 * iterate over the event IDR
			 */
			idr_for_each_entry(&p->event_idr, ev, id) {
				if (id >= KFD_SIGNAL_EVENT_LIMIT)
					break;

				if (slots[id] != UNSIGNALED_EVENT_SLOT)
					set_event_from_interrupt(p, ev);
			}
		} else {
			/* With relatively many events, it's faster to
			 * iterate over the signal slots and lookup
			 * only signaled events from the IDR.
			 */
			for (id = 0; id < KFD_SIGNAL_EVENT_LIMIT; id++)
				if (slots[id] != UNSIGNALED_EVENT_SLOT) {
					ev = lookup_event_by_id(p, id);
					set_event_from_interrupt(p, ev);
				}
		}
	}

	mutex_unlock(&p->event_mutex);
	kfd_unref_process(p);
}

static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events)
{
	struct kfd_event_waiter *event_waiters;
	uint32_t i;

	event_waiters = kmalloc_array(num_events,
					sizeof(struct kfd_event_waiter),
					GFP_KERNEL);

	for (i = 0; (event_waiters) && (i < num_events) ; i++) {
		init_wait(&event_waiters[i].wait);
		event_waiters[i].activated = false;
	}

	return event_waiters;
}

static int init_event_waiter_get_status(struct kfd_process *p,
		struct kfd_event_waiter *waiter,
		uint32_t event_id)
{
	struct kfd_event *ev = lookup_event_by_id(p, event_id);

	if (!ev)
		return -EINVAL;

	waiter->event = ev;
	waiter->activated = ev->signaled;
	ev->signaled = ev->signaled && !ev->auto_reset;

	return 0;
}

static void init_event_waiter_add_to_waitlist(struct kfd_event_waiter *waiter)
{
	struct kfd_event *ev = waiter->event;

	/* Only add to the wait list if we actually need to
	 * wait on this event.
	 */
	if (!waiter->activated)
		add_wait_queue(&ev->wq, &waiter->wait);
}

/* test_event_condition - Test condition of events being waited for
 * @all:           Return completion only if all events have signaled
 * @num_events:    Number of events to wait for
 * @event_waiters: Array of event waiters, one per event
 *
 * Returns KFD_IOC_WAIT_RESULT_COMPLETE if all (or one) event(s) have
 * signaled. Returns KFD_IOC_WAIT_RESULT_TIMEOUT if no (or not all)
 * events have signaled. Returns KFD_IOC_WAIT_RESULT_FAIL if any of
 * the events have been destroyed.
 */
static uint32_t test_event_condition(bool all, uint32_t num_events,
				struct kfd_event_waiter *event_waiters)
{
	uint32_t i;
	uint32_t activated_count = 0;

	for (i = 0; i < num_events; i++) {
		if (!event_waiters[i].event)
			return KFD_IOC_WAIT_RESULT_FAIL;

		if (event_waiters[i].activated) {
			if (!all)
				return KFD_IOC_WAIT_RESULT_COMPLETE;

			activated_count++;
		}
	}

	return activated_count == num_events ?
		KFD_IOC_WAIT_RESULT_COMPLETE : KFD_IOC_WAIT_RESULT_TIMEOUT;
}

/*
 * Copy event specific data, if defined.
 * Currently only memory exception events have additional data to copy to user
 */
static int copy_signaled_event_data(uint32_t num_events,
		struct kfd_event_waiter *event_waiters,
		struct kfd_event_data __user *data)
{
	struct kfd_hsa_memory_exception_data *src;
	struct kfd_hsa_memory_exception_data __user *dst;
	struct kfd_event_waiter *waiter;
	struct kfd_event *event;
	uint32_t i;

	for (i = 0; i < num_events; i++) {
		waiter = &event_waiters[i];
		event = waiter->event;
		if (waiter->activated && event->type == KFD_EVENT_TYPE_MEMORY) {
			dst = &data[i].memory_exception_data;
			src = &event->memory_exception_data;
			if (copy_to_user(dst, src,
				sizeof(struct kfd_hsa_memory_exception_data)))
				return -EFAULT;
		}
	}

	return 0;

}



static long user_timeout_to_jiffies(uint32_t user_timeout_ms)
{
	if (user_timeout_ms == KFD_EVENT_TIMEOUT_IMMEDIATE)
		return 0;

	if (user_timeout_ms == KFD_EVENT_TIMEOUT_INFINITE)
		return MAX_SCHEDULE_TIMEOUT;

	/*
	 * msecs_to_jiffies interprets all values above 2^31-1 as infinite,
	 * but we consider them finite.
	 * This hack is wrong, but nobody is likely to notice.
	 */
	user_timeout_ms = min_t(uint32_t, user_timeout_ms, 0x7FFFFFFF);

	return msecs_to_jiffies(user_timeout_ms) + 1;
}

static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
{
	uint32_t i;

	for (i = 0; i < num_events; i++)
		if (waiters[i].event)
			remove_wait_queue(&waiters[i].event->wq,
					  &waiters[i].wait);

	kfree(waiters);
}

int kfd_wait_on_events(struct kfd_process *p,
		       uint32_t num_events, void __user *data,
		       bool all, uint32_t user_timeout_ms,
		       uint32_t *wait_result)
{
	struct kfd_event_data __user *events =
			(struct kfd_event_data __user *) data;
	uint32_t i;
	int ret = 0;

	struct kfd_event_waiter *event_waiters = NULL;
	long timeout = user_timeout_to_jiffies(user_timeout_ms);

	event_waiters = alloc_event_waiters(num_events);
	if (!event_waiters) {
		ret = -ENOMEM;
		goto out;
	}

	mutex_lock(&p->event_mutex);

	for (i = 0; i < num_events; i++) {
		struct kfd_event_data event_data;

		if (copy_from_user(&event_data, &events[i],
				sizeof(struct kfd_event_data))) {
			ret = -EFAULT;
			goto out_unlock;
		}

		ret = init_event_waiter_get_status(p, &event_waiters[i],
				event_data.event_id);
		if (ret)
			goto out_unlock;
	}

	/* Check condition once. */
	*wait_result = test_event_condition(all, num_events, event_waiters);
	if (*wait_result == KFD_IOC_WAIT_RESULT_COMPLETE) {
		ret = copy_signaled_event_data(num_events,
					       event_waiters, events);
		goto out_unlock;
	} else if (WARN_ON(*wait_result == KFD_IOC_WAIT_RESULT_FAIL)) {
		/* This should not happen. Events shouldn't be
		 * destroyed while we're holding the event_mutex
		 */
		goto out_unlock;
	}

	/* Add to wait lists if we need to wait. */
	for (i = 0; i < num_events; i++)
		init_event_waiter_add_to_waitlist(&event_waiters[i]);

	mutex_unlock(&p->event_mutex);

	while (true) {
		if (fatal_signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		if (signal_pending(current)) {
			/*
			 * This is wrong when a nonzero, non-infinite timeout
			 * is specified. We need to use
			 * ERESTARTSYS_RESTARTBLOCK, but struct restart_block
			 * contains a union with data for each user and it's
			 * in generic kernel code that I don't want to
			 * touch yet.
			 */
			ret = -ERESTARTSYS;
			break;
		}

		/* Set task state to interruptible sleep before
		 * checking wake-up conditions. A concurrent wake-up
		 * will put the task back into runnable state. In that
		 * case schedule_timeout will not put the task to
		 * sleep and we'll get a chance to re-check the
		 * updated conditions almost immediately. Otherwise,
		 * this race condition would lead to a soft hang or a
		 * very long sleep.
		 */
		set_current_state(TASK_INTERRUPTIBLE);

		*wait_result = test_event_condition(all, num_events,
						    event_waiters);
		if (*wait_result != KFD_IOC_WAIT_RESULT_TIMEOUT)
			break;

		if (timeout <= 0)
			break;

		timeout = schedule_timeout(timeout);
	}
	__set_current_state(TASK_RUNNING);

	/* copy_signaled_event_data may sleep. So this has to happen
	 * after the task state is set back to RUNNING.
	 */
	if (!ret && *wait_result == KFD_IOC_WAIT_RESULT_COMPLETE)
		ret = copy_signaled_event_data(num_events,
					       event_waiters, events);

	mutex_lock(&p->event_mutex);
out_unlock:
	free_waiters(num_events, event_waiters);
	mutex_unlock(&p->event_mutex);
out:
	if (ret)
		*wait_result = KFD_IOC_WAIT_RESULT_FAIL;
	else if (*wait_result == KFD_IOC_WAIT_RESULT_FAIL)
		ret = -EIO;

	return ret;
}

int kfd_event_mmap(struct kfd_process *p, struct vm_area_struct *vma)
{
	unsigned long pfn;
	struct kfd_signal_page *page;
	int ret;

	/* check required size doesn't exceed the allocated size */
	if (get_order(KFD_SIGNAL_EVENT_LIMIT * 8) <
			get_order(vma->vm_end - vma->vm_start)) {
		pr_err("Event page mmap requested illegal size\n");
		return -EINVAL;
	}

	page = p->signal_page;
	if (!page) {
		/* Probably KFD bug, but mmap is user-accessible. */
		pr_debug("Signal page could not be found\n");
		return -EINVAL;
	}

	pfn = __pa(page->kernel_address);
	pfn >>= PAGE_SHIFT;

	vma->vm_flags |= VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_NORESERVE
		       | VM_DONTDUMP | VM_PFNMAP;

	pr_debug("Mapping signal page\n");
	pr_debug("     start user address  == 0x%08lx\n", vma->vm_start);
	pr_debug("     end user address    == 0x%08lx\n", vma->vm_end);
	pr_debug("     pfn                 == 0x%016lX\n", pfn);
	pr_debug("     vm_flags            == 0x%08lX\n", vma->vm_flags);
	pr_debug("     size                == 0x%08lX\n",
			vma->vm_end - vma->vm_start);

	page->user_address = (uint64_t __user *)vma->vm_start;

	/* mapping the page to user process */
	ret = remap_pfn_range(vma, vma->vm_start, pfn,
			vma->vm_end - vma->vm_start, vma->vm_page_prot);
	if (!ret)
		p->signal_mapped_size = vma->vm_end - vma->vm_start;

	return ret;
}

/*
 * Assumes that p->event_mutex is held and of course
 * that p is not going away (current or locked).
 */
static void lookup_events_by_type_and_signal(struct kfd_process *p,
		int type, void *event_data)
{
	struct kfd_hsa_memory_exception_data *ev_data;
	struct kfd_event *ev;
	uint32_t id;
	bool send_signal = true;

	ev_data = (struct kfd_hsa_memory_exception_data *) event_data;

	id = KFD_FIRST_NONSIGNAL_EVENT_ID;
	idr_for_each_entry_continue(&p->event_idr, ev, id)
		if (ev->type == type) {
			send_signal = false;
			dev_dbg(kfd_device,
					"Event found: id %X type %d",
					ev->event_id, ev->type);
			set_event(ev);
			if (ev->type == KFD_EVENT_TYPE_MEMORY && ev_data)
				ev->memory_exception_data = *ev_data;
		}

	/* Send SIGTERM no event of type "type" has been found*/
	if (send_signal) {
		if (send_sigterm) {
			dev_warn(kfd_device,
				"Sending SIGTERM to HSA Process with PID %d ",
					p->lead_thread->pid);
			send_sig(SIGTERM, p->lead_thread, 0);
		} else {
			dev_err(kfd_device,
				"HSA Process (PID %d) got unhandled exception",
				p->lead_thread->pid);
		}
	}
}

void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
		unsigned long address, bool is_write_requested,
		bool is_execute_requested)
{
	struct kfd_hsa_memory_exception_data memory_exception_data;
	struct vm_area_struct *vma;

	/*
	 * Because we are called from arbitrary context (workqueue) as opposed
	 * to process context, kfd_process could attempt to exit while we are
	 * running so the lookup function increments the process ref count.
	 */
	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
	struct mm_struct *mm;

	if (!p)
		return; /* Presumably process exited. */

	/* Take a safe reference to the mm_struct, which may otherwise
	 * disappear even while the kfd_process is still referenced.
	 */
	mm = get_task_mm(p->lead_thread);
	if (!mm) {
		kfd_unref_process(p);
		return; /* Process is exiting */
	}

	memset(&memory_exception_data, 0, sizeof(memory_exception_data));

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, address);

	memory_exception_data.gpu_id = dev->id;
	memory_exception_data.va = address;
	/* Set failure reason */
	memory_exception_data.failure.NotPresent = 1;
	memory_exception_data.failure.NoExecute = 0;
	memory_exception_data.failure.ReadOnly = 0;
	if (vma) {
		if (vma->vm_start > address) {
			memory_exception_data.failure.NotPresent = 1;
			memory_exception_data.failure.NoExecute = 0;
			memory_exception_data.failure.ReadOnly = 0;
		} else {
			memory_exception_data.failure.NotPresent = 0;
			if (is_write_requested && !(vma->vm_flags & VM_WRITE))
				memory_exception_data.failure.ReadOnly = 1;
			else
				memory_exception_data.failure.ReadOnly = 0;
			if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
				memory_exception_data.failure.NoExecute = 1;
			else
				memory_exception_data.failure.NoExecute = 0;
		}
	}

	up_read(&mm->mmap_sem);
	mmput(mm);

	mutex_lock(&p->event_mutex);

	/* Lookup events by type and signal them */
	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
			&memory_exception_data);

	mutex_unlock(&p->event_mutex);
	kfd_unref_process(p);
}

void kfd_signal_hw_exception_event(unsigned int pasid)
{
	/*
	 * Because we are called from arbitrary context (workqueue) as opposed
	 * to process context, kfd_process could attempt to exit while we are
	 * running so the lookup function increments the process ref count.
	 */
	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);

	if (!p)
		return; /* Presumably process exited. */

	mutex_lock(&p->event_mutex);

	/* Lookup events by type and signal them */
	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_HW_EXCEPTION, NULL);

	mutex_unlock(&p->event_mutex);
	kfd_unref_process(p);
}