summaryrefslogtreecommitdiff
path: root/mm/hmm.c
blob: 6111c0a3c12d733c6062787bb30c741ad9a010ba (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
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright 2013 Red Hat Inc.
 *
 * Authors: Jérôme Glisse <jglisse@redhat.com>
 */
/*
 * Refer to include/linux/hmm.h for information about heterogeneous memory
 * management or HMM for short.
 */
#include <linux/mm.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/sched/mm.h>
#include <linux/jump_label.h>
#include <linux/dma-mapping.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>

static const struct mmu_notifier_ops hmm_mmu_notifier_ops;

/**
 * hmm_get_or_create - register HMM against an mm (HMM internal)
 *
 * @mm: mm struct to attach to
 * Return: an HMM object, either by referencing the existing
 *          (per-process) object, or by creating a new one.
 *
 * This is not intended to be used directly by device drivers. If mm already
 * has an HMM struct then it get a reference on it and returns it. Otherwise
 * it allocates an HMM struct, initializes it, associate it with the mm and
 * returns it.
 */
static struct hmm *hmm_get_or_create(struct mm_struct *mm)
{
	struct hmm *hmm;

	lockdep_assert_held_write(&mm->mmap_sem);

	/* Abuse the page_table_lock to also protect mm->hmm. */
	spin_lock(&mm->page_table_lock);
	hmm = mm->hmm;
	if (mm->hmm && kref_get_unless_zero(&mm->hmm->kref))
		goto out_unlock;
	spin_unlock(&mm->page_table_lock);

	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
	if (!hmm)
		return NULL;
	init_waitqueue_head(&hmm->wq);
	INIT_LIST_HEAD(&hmm->mirrors);
	init_rwsem(&hmm->mirrors_sem);
	hmm->mmu_notifier.ops = NULL;
	INIT_LIST_HEAD(&hmm->ranges);
	spin_lock_init(&hmm->ranges_lock);
	kref_init(&hmm->kref);
	hmm->notifiers = 0;
	hmm->mm = mm;

	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
	if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
		kfree(hmm);
		return NULL;
	}

	mmgrab(hmm->mm);

	/*
	 * We hold the exclusive mmap_sem here so we know that mm->hmm is
	 * still NULL or 0 kref, and is safe to update.
	 */
	spin_lock(&mm->page_table_lock);
	mm->hmm = hmm;

out_unlock:
	spin_unlock(&mm->page_table_lock);
	return hmm;
}

static void hmm_free_rcu(struct rcu_head *rcu)
{
	struct hmm *hmm = container_of(rcu, struct hmm, rcu);

	mmdrop(hmm->mm);
	kfree(hmm);
}

static void hmm_free(struct kref *kref)
{
	struct hmm *hmm = container_of(kref, struct hmm, kref);

	spin_lock(&hmm->mm->page_table_lock);
	if (hmm->mm->hmm == hmm)
		hmm->mm->hmm = NULL;
	spin_unlock(&hmm->mm->page_table_lock);

	mmu_notifier_unregister_no_release(&hmm->mmu_notifier, hmm->mm);
	mmu_notifier_call_srcu(&hmm->rcu, hmm_free_rcu);
}

static inline void hmm_put(struct hmm *hmm)
{
	kref_put(&hmm->kref, hmm_free);
}

static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
	struct hmm_mirror *mirror;

	/* Bail out if hmm is in the process of being freed */
	if (!kref_get_unless_zero(&hmm->kref))
		return;

	/*
	 * Since hmm_range_register() holds the mmget() lock hmm_release() is
	 * prevented as long as a range exists.
	 */
	WARN_ON(!list_empty_careful(&hmm->ranges));

	down_read(&hmm->mirrors_sem);
	list_for_each_entry(mirror, &hmm->mirrors, list) {
		/*
		 * Note: The driver is not allowed to trigger
		 * hmm_mirror_unregister() from this thread.
		 */
		if (mirror->ops->release)
			mirror->ops->release(mirror);
	}
	up_read(&hmm->mirrors_sem);

	hmm_put(hmm);
}

static void notifiers_decrement(struct hmm *hmm)
{
	unsigned long flags;

	spin_lock_irqsave(&hmm->ranges_lock, flags);
	hmm->notifiers--;
	if (!hmm->notifiers) {
		struct hmm_range *range;

		list_for_each_entry(range, &hmm->ranges, list) {
			if (range->valid)
				continue;
			range->valid = true;
		}
		wake_up_all(&hmm->wq);
	}
	spin_unlock_irqrestore(&hmm->ranges_lock, flags);
}

static int hmm_invalidate_range_start(struct mmu_notifier *mn,
			const struct mmu_notifier_range *nrange)
{
	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
	struct hmm_mirror *mirror;
	struct hmm_range *range;
	unsigned long flags;
	int ret = 0;

	if (!kref_get_unless_zero(&hmm->kref))
		return 0;

	spin_lock_irqsave(&hmm->ranges_lock, flags);
	hmm->notifiers++;
	list_for_each_entry(range, &hmm->ranges, list) {
		if (nrange->end < range->start || nrange->start >= range->end)
			continue;

		range->valid = false;
	}
	spin_unlock_irqrestore(&hmm->ranges_lock, flags);

	if (mmu_notifier_range_blockable(nrange))
		down_read(&hmm->mirrors_sem);
	else if (!down_read_trylock(&hmm->mirrors_sem)) {
		ret = -EAGAIN;
		goto out;
	}

	list_for_each_entry(mirror, &hmm->mirrors, list) {
		int rc;

		rc = mirror->ops->sync_cpu_device_pagetables(mirror, nrange);
		if (rc) {
			if (WARN_ON(mmu_notifier_range_blockable(nrange) ||
			    rc != -EAGAIN))
				continue;
			ret = -EAGAIN;
			break;
		}
	}
	up_read(&hmm->mirrors_sem);

out:
	if (ret)
		notifiers_decrement(hmm);
	hmm_put(hmm);
	return ret;
}

static void hmm_invalidate_range_end(struct mmu_notifier *mn,
			const struct mmu_notifier_range *nrange)
{
	struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);

	if (!kref_get_unless_zero(&hmm->kref))
		return;

	notifiers_decrement(hmm);
	hmm_put(hmm);
}

static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
	.release		= hmm_release,
	.invalidate_range_start	= hmm_invalidate_range_start,
	.invalidate_range_end	= hmm_invalidate_range_end,
};

/*
 * hmm_mirror_register() - register a mirror against an mm
 *
 * @mirror: new mirror struct to register
 * @mm: mm to register against
 * Return: 0 on success, -ENOMEM if no memory, -EINVAL if invalid arguments
 *
 * To start mirroring a process address space, the device driver must register
 * an HMM mirror struct.
 */
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
{
	lockdep_assert_held_write(&mm->mmap_sem);

	/* Sanity check */
	if (!mm || !mirror || !mirror->ops)
		return -EINVAL;

	mirror->hmm = hmm_get_or_create(mm);
	if (!mirror->hmm)
		return -ENOMEM;

	down_write(&mirror->hmm->mirrors_sem);
	list_add(&mirror->list, &mirror->hmm->mirrors);
	up_write(&mirror->hmm->mirrors_sem);

	return 0;
}
EXPORT_SYMBOL(hmm_mirror_register);

/*
 * hmm_mirror_unregister() - unregister a mirror
 *
 * @mirror: mirror struct to unregister
 *
 * Stop mirroring a process address space, and cleanup.
 */
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
	struct hmm *hmm = mirror->hmm;

	down_write(&hmm->mirrors_sem);
	list_del(&mirror->list);
	up_write(&hmm->mirrors_sem);
	hmm_put(hmm);
}
EXPORT_SYMBOL(hmm_mirror_unregister);

struct hmm_vma_walk {
	struct hmm_range	*range;
	struct dev_pagemap	*pgmap;
	unsigned long		last;
	unsigned int		flags;
};

static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
			    bool write_fault, uint64_t *pfn)
{
	unsigned int flags = FAULT_FLAG_REMOTE;
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	struct vm_area_struct *vma = walk->vma;
	vm_fault_t ret;

	if (hmm_vma_walk->flags & HMM_FAULT_ALLOW_RETRY)
		flags |= FAULT_FLAG_ALLOW_RETRY;
	if (write_fault)
		flags |= FAULT_FLAG_WRITE;

	ret = handle_mm_fault(vma, addr, flags);
	if (ret & VM_FAULT_RETRY) {
		/* Note, handle_mm_fault did up_read(&mm->mmap_sem)) */
		return -EAGAIN;
	}
	if (ret & VM_FAULT_ERROR) {
		*pfn = range->values[HMM_PFN_ERROR];
		return -EFAULT;
	}

	return -EBUSY;
}

static int hmm_pfns_bad(unsigned long addr,
			unsigned long end,
			struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	uint64_t *pfns = range->pfns;
	unsigned long i;

	i = (addr - range->start) >> PAGE_SHIFT;
	for (; addr < end; addr += PAGE_SIZE, i++)
		pfns[i] = range->values[HMM_PFN_ERROR];

	return 0;
}

/*
 * hmm_vma_walk_hole_() - handle a range lacking valid pmd or pte(s)
 * @addr: range virtual start address (inclusive)
 * @end: range virtual end address (exclusive)
 * @fault: should we fault or not ?
 * @write_fault: write fault ?
 * @walk: mm_walk structure
 * Return: 0 on success, -EBUSY after page fault, or page fault error
 *
 * This function will be called whenever pmd_none() or pte_none() returns true,
 * or whenever there is no page directory covering the virtual address range.
 */
static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
			      bool fault, bool write_fault,
			      struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	uint64_t *pfns = range->pfns;
	unsigned long i, page_size;

	hmm_vma_walk->last = addr;
	page_size = hmm_range_page_size(range);
	i = (addr - range->start) >> range->page_shift;

	for (; addr < end; addr += page_size, i++) {
		pfns[i] = range->values[HMM_PFN_NONE];
		if (fault || write_fault) {
			int ret;

			ret = hmm_vma_do_fault(walk, addr, write_fault,
					       &pfns[i]);
			if (ret != -EBUSY)
				return ret;
		}
	}

	return (fault || write_fault) ? -EBUSY : 0;
}

static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
				      uint64_t pfns, uint64_t cpu_flags,
				      bool *fault, bool *write_fault)
{
	struct hmm_range *range = hmm_vma_walk->range;

	if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT)
		return;

	/*
	 * So we not only consider the individual per page request we also
	 * consider the default flags requested for the range. The API can
	 * be used 2 ways. The first one where the HMM user coalesces
	 * multiple page faults into one request and sets flags per pfn for
	 * those faults. The second one where the HMM user wants to pre-
	 * fault a range with specific flags. For the latter one it is a
	 * waste to have the user pre-fill the pfn arrays with a default
	 * flags value.
	 */
	pfns = (pfns & range->pfn_flags_mask) | range->default_flags;

	/* We aren't ask to do anything ... */
	if (!(pfns & range->flags[HMM_PFN_VALID]))
		return;
	/* If this is device memory then only fault if explicitly requested */
	if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRIVATE])) {
		/* Do we fault on device memory ? */
		if (pfns & range->flags[HMM_PFN_DEVICE_PRIVATE]) {
			*write_fault = pfns & range->flags[HMM_PFN_WRITE];
			*fault = true;
		}
		return;
	}

	/* If CPU page table is not valid then we need to fault */
	*fault = !(cpu_flags & range->flags[HMM_PFN_VALID]);
	/* Need to write fault ? */
	if ((pfns & range->flags[HMM_PFN_WRITE]) &&
	    !(cpu_flags & range->flags[HMM_PFN_WRITE])) {
		*write_fault = true;
		*fault = true;
	}
}

static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
				 const uint64_t *pfns, unsigned long npages,
				 uint64_t cpu_flags, bool *fault,
				 bool *write_fault)
{
	unsigned long i;

	if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) {
		*fault = *write_fault = false;
		return;
	}

	*fault = *write_fault = false;
	for (i = 0; i < npages; ++i) {
		hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags,
				   fault, write_fault);
		if ((*write_fault))
			return;
	}
}

static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
			     struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	bool fault, write_fault;
	unsigned long i, npages;
	uint64_t *pfns;

	i = (addr - range->start) >> PAGE_SHIFT;
	npages = (end - addr) >> PAGE_SHIFT;
	pfns = &range->pfns[i];
	hmm_range_need_fault(hmm_vma_walk, pfns, npages,
			     0, &fault, &write_fault);
	return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
}

static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
{
	if (pmd_protnone(pmd))
		return 0;
	return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
				range->flags[HMM_PFN_WRITE] :
				range->flags[HMM_PFN_VALID];
}

static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
{
	if (!pud_present(pud))
		return 0;
	return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
				range->flags[HMM_PFN_WRITE] :
				range->flags[HMM_PFN_VALID];
}

static int hmm_vma_handle_pmd(struct mm_walk *walk,
			      unsigned long addr,
			      unsigned long end,
			      uint64_t *pfns,
			      pmd_t pmd)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned long pfn, npages, i;
	bool fault, write_fault;
	uint64_t cpu_flags;

	npages = (end - addr) >> PAGE_SHIFT;
	cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
	hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags,
			     &fault, &write_fault);

	if (pmd_protnone(pmd) || fault || write_fault)
		return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);

	pfn = pmd_pfn(pmd) + pte_index(addr);
	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
		if (pmd_devmap(pmd)) {
			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
					      hmm_vma_walk->pgmap);
			if (unlikely(!hmm_vma_walk->pgmap))
				return -EBUSY;
		}
		pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
	}
	if (hmm_vma_walk->pgmap) {
		put_dev_pagemap(hmm_vma_walk->pgmap);
		hmm_vma_walk->pgmap = NULL;
	}
	hmm_vma_walk->last = end;
	return 0;
#else
	/* If THP is not enabled then we should never reach this code ! */
	return -EINVAL;
#endif
}

static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
{
	if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
		return 0;
	return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
				range->flags[HMM_PFN_WRITE] :
				range->flags[HMM_PFN_VALID];
}

static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
			      unsigned long end, pmd_t *pmdp, pte_t *ptep,
			      uint64_t *pfn)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	bool fault, write_fault;
	uint64_t cpu_flags;
	pte_t pte = *ptep;
	uint64_t orig_pfn = *pfn;

	*pfn = range->values[HMM_PFN_NONE];
	fault = write_fault = false;

	if (pte_none(pte)) {
		hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0,
				   &fault, &write_fault);
		if (fault || write_fault)
			goto fault;
		return 0;
	}

	if (!pte_present(pte)) {
		swp_entry_t entry = pte_to_swp_entry(pte);

		if (!non_swap_entry(entry)) {
			if (fault || write_fault)
				goto fault;
			return 0;
		}

		/*
		 * This is a special swap entry, ignore migration, use
		 * device and report anything else as error.
		 */
		if (is_device_private_entry(entry)) {
			cpu_flags = range->flags[HMM_PFN_VALID] |
				range->flags[HMM_PFN_DEVICE_PRIVATE];
			cpu_flags |= is_write_device_private_entry(entry) ?
				range->flags[HMM_PFN_WRITE] : 0;
			hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
					   &fault, &write_fault);
			if (fault || write_fault)
				goto fault;
			*pfn = hmm_device_entry_from_pfn(range,
					    swp_offset(entry));
			*pfn |= cpu_flags;
			return 0;
		}

		if (is_migration_entry(entry)) {
			if (fault || write_fault) {
				pte_unmap(ptep);
				hmm_vma_walk->last = addr;
				migration_entry_wait(walk->mm, pmdp, addr);
				return -EBUSY;
			}
			return 0;
		}

		/* Report error for everything else */
		*pfn = range->values[HMM_PFN_ERROR];
		return -EFAULT;
	} else {
		cpu_flags = pte_to_hmm_pfn_flags(range, pte);
		hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
				   &fault, &write_fault);
	}

	if (fault || write_fault)
		goto fault;

	if (pte_devmap(pte)) {
		hmm_vma_walk->pgmap = get_dev_pagemap(pte_pfn(pte),
					      hmm_vma_walk->pgmap);
		if (unlikely(!hmm_vma_walk->pgmap))
			return -EBUSY;
	} else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) {
		*pfn = range->values[HMM_PFN_SPECIAL];
		return -EFAULT;
	}

	*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
	return 0;

fault:
	if (hmm_vma_walk->pgmap) {
		put_dev_pagemap(hmm_vma_walk->pgmap);
		hmm_vma_walk->pgmap = NULL;
	}
	pte_unmap(ptep);
	/* Fault any virtual address we were asked to fault */
	return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
}

static int hmm_vma_walk_pmd(pmd_t *pmdp,
			    unsigned long start,
			    unsigned long end,
			    struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	uint64_t *pfns = range->pfns;
	unsigned long addr = start, i;
	pte_t *ptep;
	pmd_t pmd;

again:
	pmd = READ_ONCE(*pmdp);
	if (pmd_none(pmd))
		return hmm_vma_walk_hole(start, end, walk);

	if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
		bool fault, write_fault;
		unsigned long npages;
		uint64_t *pfns;

		i = (addr - range->start) >> PAGE_SHIFT;
		npages = (end - addr) >> PAGE_SHIFT;
		pfns = &range->pfns[i];

		hmm_range_need_fault(hmm_vma_walk, pfns, npages,
				     0, &fault, &write_fault);
		if (fault || write_fault) {
			hmm_vma_walk->last = addr;
			pmd_migration_entry_wait(walk->mm, pmdp);
			return -EBUSY;
		}
		return 0;
	} else if (!pmd_present(pmd))
		return hmm_pfns_bad(start, end, walk);

	if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
		/*
		 * No need to take pmd_lock here, even if some other thread
		 * is splitting the huge pmd we will get that event through
		 * mmu_notifier callback.
		 *
		 * So just read pmd value and check again it's a transparent
		 * huge or device mapping one and compute corresponding pfn
		 * values.
		 */
		pmd = pmd_read_atomic(pmdp);
		barrier();
		if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
			goto again;

		i = (addr - range->start) >> PAGE_SHIFT;
		return hmm_vma_handle_pmd(walk, addr, end, &pfns[i], pmd);
	}

	/*
	 * We have handled all the valid cases above ie either none, migration,
	 * huge or transparent huge. At this point either it is a valid pmd
	 * entry pointing to pte directory or it is a bad pmd that will not
	 * recover.
	 */
	if (pmd_bad(pmd))
		return hmm_pfns_bad(start, end, walk);

	ptep = pte_offset_map(pmdp, addr);
	i = (addr - range->start) >> PAGE_SHIFT;
	for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
		int r;

		r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, &pfns[i]);
		if (r) {
			/* hmm_vma_handle_pte() did unmap pte directory */
			hmm_vma_walk->last = addr;
			return r;
		}
	}
	if (hmm_vma_walk->pgmap) {
		/*
		 * We do put_dev_pagemap() here and not in hmm_vma_handle_pte()
		 * so that we can leverage get_dev_pagemap() optimization which
		 * will not re-take a reference on a pgmap if we already have
		 * one.
		 */
		put_dev_pagemap(hmm_vma_walk->pgmap);
		hmm_vma_walk->pgmap = NULL;
	}
	pte_unmap(ptep - 1);

	hmm_vma_walk->last = addr;
	return 0;
}

static int hmm_vma_walk_pud(pud_t *pudp,
			    unsigned long start,
			    unsigned long end,
			    struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned long addr = start, next;
	pmd_t *pmdp;
	pud_t pud;
	int ret;

again:
	pud = READ_ONCE(*pudp);
	if (pud_none(pud))
		return hmm_vma_walk_hole(start, end, walk);

	if (pud_huge(pud) && pud_devmap(pud)) {
		unsigned long i, npages, pfn;
		uint64_t *pfns, cpu_flags;
		bool fault, write_fault;

		if (!pud_present(pud))
			return hmm_vma_walk_hole(start, end, walk);

		i = (addr - range->start) >> PAGE_SHIFT;
		npages = (end - addr) >> PAGE_SHIFT;
		pfns = &range->pfns[i];

		cpu_flags = pud_to_hmm_pfn_flags(range, pud);
		hmm_range_need_fault(hmm_vma_walk, pfns, npages,
				     cpu_flags, &fault, &write_fault);
		if (fault || write_fault)
			return hmm_vma_walk_hole_(addr, end, fault,
						write_fault, walk);

		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
		for (i = 0; i < npages; ++i, ++pfn) {
			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
					      hmm_vma_walk->pgmap);
			if (unlikely(!hmm_vma_walk->pgmap))
				return -EBUSY;
			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
				  cpu_flags;
		}
		if (hmm_vma_walk->pgmap) {
			put_dev_pagemap(hmm_vma_walk->pgmap);
			hmm_vma_walk->pgmap = NULL;
		}
		hmm_vma_walk->last = end;
		return 0;
	}

	split_huge_pud(walk->vma, pudp, addr);
	if (pud_none(*pudp))
		goto again;

	pmdp = pmd_offset(pudp, addr);
	do {
		next = pmd_addr_end(addr, end);
		ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
		if (ret)
			return ret;
	} while (pmdp++, addr = next, addr != end);

	return 0;
}

static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
				      unsigned long start, unsigned long end,
				      struct mm_walk *walk)
{
#ifdef CONFIG_HUGETLB_PAGE
	unsigned long addr = start, i, pfn, mask, size, pfn_inc;
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	struct vm_area_struct *vma = walk->vma;
	struct hstate *h = hstate_vma(vma);
	uint64_t orig_pfn, cpu_flags;
	bool fault, write_fault;
	spinlock_t *ptl;
	pte_t entry;
	int ret = 0;

	size = huge_page_size(h);
	mask = size - 1;
	if (range->page_shift != PAGE_SHIFT) {
		/* Make sure we are looking at a full page. */
		if (start & mask)
			return -EINVAL;
		if (end < (start + size))
			return -EINVAL;
		pfn_inc = size >> PAGE_SHIFT;
	} else {
		pfn_inc = 1;
		size = PAGE_SIZE;
	}

	ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
	entry = huge_ptep_get(pte);

	i = (start - range->start) >> range->page_shift;
	orig_pfn = range->pfns[i];
	range->pfns[i] = range->values[HMM_PFN_NONE];
	cpu_flags = pte_to_hmm_pfn_flags(range, entry);
	fault = write_fault = false;
	hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
			   &fault, &write_fault);
	if (fault || write_fault) {
		ret = -ENOENT;
		goto unlock;
	}

	pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift);
	for (; addr < end; addr += size, i++, pfn += pfn_inc)
		range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
				 cpu_flags;
	hmm_vma_walk->last = end;

unlock:
	spin_unlock(ptl);

	if (ret == -ENOENT)
		return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);

	return ret;
#else /* CONFIG_HUGETLB_PAGE */
	return -EINVAL;
#endif
}

static void hmm_pfns_clear(struct hmm_range *range,
			   uint64_t *pfns,
			   unsigned long addr,
			   unsigned long end)
{
	for (; addr < end; addr += PAGE_SIZE, pfns++)
		*pfns = range->values[HMM_PFN_NONE];
}

/*
 * hmm_range_register() - start tracking change to CPU page table over a range
 * @range: range
 * @mm: the mm struct for the range of virtual address
 * @start: start virtual address (inclusive)
 * @end: end virtual address (exclusive)
 * @page_shift: expect page shift for the range
 * Return: 0 on success, -EFAULT if the address space is no longer valid
 *
 * Track updates to the CPU page table see include/linux/hmm.h
 */
int hmm_range_register(struct hmm_range *range,
		       struct hmm_mirror *mirror,
		       unsigned long start,
		       unsigned long end,
		       unsigned page_shift)
{
	unsigned long mask = ((1UL << page_shift) - 1UL);
	struct hmm *hmm = mirror->hmm;
	unsigned long flags;

	range->valid = false;
	range->hmm = NULL;

	if ((start & mask) || (end & mask))
		return -EINVAL;
	if (start >= end)
		return -EINVAL;

	range->page_shift = page_shift;
	range->start = start;
	range->end = end;

	/* Prevent hmm_release() from running while the range is valid */
	if (!mmget_not_zero(hmm->mm))
		return -EFAULT;

	/* Initialize range to track CPU page table updates. */
	spin_lock_irqsave(&hmm->ranges_lock, flags);

	range->hmm = hmm;
	kref_get(&hmm->kref);
	list_add(&range->list, &hmm->ranges);

	/*
	 * If there are any concurrent notifiers we have to wait for them for
	 * the range to be valid (see hmm_range_wait_until_valid()).
	 */
	if (!hmm->notifiers)
		range->valid = true;
	spin_unlock_irqrestore(&hmm->ranges_lock, flags);

	return 0;
}
EXPORT_SYMBOL(hmm_range_register);

/*
 * hmm_range_unregister() - stop tracking change to CPU page table over a range
 * @range: range
 *
 * Range struct is used to track updates to the CPU page table after a call to
 * hmm_range_register(). See include/linux/hmm.h for how to use it.
 */
void hmm_range_unregister(struct hmm_range *range)
{
	struct hmm *hmm = range->hmm;
	unsigned long flags;

	spin_lock_irqsave(&hmm->ranges_lock, flags);
	list_del_init(&range->list);
	spin_unlock_irqrestore(&hmm->ranges_lock, flags);

	/* Drop reference taken by hmm_range_register() */
	mmput(hmm->mm);
	hmm_put(hmm);

	/*
	 * The range is now invalid and the ref on the hmm is dropped, so
	 * poison the pointer.  Leave other fields in place, for the caller's
	 * use.
	 */
	range->valid = false;
	memset(&range->hmm, POISON_INUSE, sizeof(range->hmm));
}
EXPORT_SYMBOL(hmm_range_unregister);

/**
 * hmm_range_fault - try to fault some address in a virtual address range
 * @range:	range being faulted
 * @flags:	HMM_FAULT_* flags
 *
 * Return: the number of valid pages in range->pfns[] (from range start
 * address), which may be zero.  On error one of the following status codes
 * can be returned:
 *
 * -EINVAL:	Invalid arguments or mm or virtual address is in an invalid vma
 *		(e.g., device file vma).
 * -ENOMEM:	Out of memory.
 * -EPERM:	Invalid permission (e.g., asking for write and range is read
 *		only).
 * -EAGAIN:	A page fault needs to be retried and mmap_sem was dropped.
 * -EBUSY:	The range has been invalidated and the caller needs to wait for
 *		the invalidation to finish.
 * -EFAULT:	Invalid (i.e., either no valid vma or it is illegal to access
 *		that range) number of valid pages in range->pfns[] (from
 *              range start address).
 *
 * This is similar to a regular CPU page fault except that it will not trigger
 * any memory migration if the memory being faulted is not accessible by CPUs
 * and caller does not ask for migration.
 *
 * On error, for one virtual address in the range, the function will mark the
 * corresponding HMM pfn entry with an error flag.
 */
long hmm_range_fault(struct hmm_range *range, unsigned int flags)
{
	const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
	unsigned long start = range->start, end;
	struct hmm_vma_walk hmm_vma_walk;
	struct hmm *hmm = range->hmm;
	struct vm_area_struct *vma;
	struct mm_walk mm_walk;
	int ret;

	lockdep_assert_held(&hmm->mm->mmap_sem);

	do {
		/* If range is no longer valid force retry. */
		if (!range->valid)
			return -EBUSY;

		vma = find_vma(hmm->mm, start);
		if (vma == NULL || (vma->vm_flags & device_vma))
			return -EFAULT;

		if (is_vm_hugetlb_page(vma)) {
			if (huge_page_shift(hstate_vma(vma)) !=
			    range->page_shift &&
			    range->page_shift != PAGE_SHIFT)
				return -EINVAL;
		} else {
			if (range->page_shift != PAGE_SHIFT)
				return -EINVAL;
		}

		if (!(vma->vm_flags & VM_READ)) {
			/*
			 * If vma do not allow read access, then assume that it
			 * does not allow write access, either. HMM does not
			 * support architecture that allow write without read.
			 */
			hmm_pfns_clear(range, range->pfns,
				range->start, range->end);
			return -EPERM;
		}

		range->vma = vma;
		hmm_vma_walk.pgmap = NULL;
		hmm_vma_walk.last = start;
		hmm_vma_walk.flags = flags;
		hmm_vma_walk.range = range;
		mm_walk.private = &hmm_vma_walk;
		end = min(range->end, vma->vm_end);

		mm_walk.vma = vma;
		mm_walk.mm = vma->vm_mm;
		mm_walk.pte_entry = NULL;
		mm_walk.test_walk = NULL;
		mm_walk.hugetlb_entry = NULL;
		mm_walk.pud_entry = hmm_vma_walk_pud;
		mm_walk.pmd_entry = hmm_vma_walk_pmd;
		mm_walk.pte_hole = hmm_vma_walk_hole;
		mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;

		do {
			ret = walk_page_range(start, end, &mm_walk);
			start = hmm_vma_walk.last;

			/* Keep trying while the range is valid. */
		} while (ret == -EBUSY && range->valid);

		if (ret) {
			unsigned long i;

			i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
			hmm_pfns_clear(range, &range->pfns[i],
				hmm_vma_walk.last, range->end);
			return ret;
		}
		start = end;

	} while (start < range->end);

	return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
EXPORT_SYMBOL(hmm_range_fault);

/**
 * hmm_range_dma_map - hmm_range_fault() and dma map page all in one.
 * @range:	range being faulted
 * @device:	device to map page to
 * @daddrs:	array of dma addresses for the mapped pages
 * @flags:	HMM_FAULT_*
 *
 * Return: the number of pages mapped on success (including zero), or any
 * status return from hmm_range_fault() otherwise.
 */
long hmm_range_dma_map(struct hmm_range *range, struct device *device,
		dma_addr_t *daddrs, unsigned int flags)
{
	unsigned long i, npages, mapped;
	long ret;

	ret = hmm_range_fault(range, flags);
	if (ret <= 0)
		return ret ? ret : -EBUSY;

	npages = (range->end - range->start) >> PAGE_SHIFT;
	for (i = 0, mapped = 0; i < npages; ++i) {
		enum dma_data_direction dir = DMA_TO_DEVICE;
		struct page *page;

		/*
		 * FIXME need to update DMA API to provide invalid DMA address
		 * value instead of a function to test dma address value. This
		 * would remove lot of dumb code duplicated accross many arch.
		 *
		 * For now setting it to 0 here is good enough as the pfns[]
		 * value is what is use to check what is valid and what isn't.
		 */
		daddrs[i] = 0;

		page = hmm_device_entry_to_page(range, range->pfns[i]);
		if (page == NULL)
			continue;

		/* Check if range is being invalidated */
		if (!range->valid) {
			ret = -EBUSY;
			goto unmap;
		}

		/* If it is read and write than map bi-directional. */
		if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
			dir = DMA_BIDIRECTIONAL;

		daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
		if (dma_mapping_error(device, daddrs[i])) {
			ret = -EFAULT;
			goto unmap;
		}

		mapped++;
	}

	return mapped;

unmap:
	for (npages = i, i = 0; (i < npages) && mapped; ++i) {
		enum dma_data_direction dir = DMA_TO_DEVICE;
		struct page *page;

		page = hmm_device_entry_to_page(range, range->pfns[i]);
		if (page == NULL)
			continue;

		if (dma_mapping_error(device, daddrs[i]))
			continue;

		/* If it is read and write than map bi-directional. */
		if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
			dir = DMA_BIDIRECTIONAL;

		dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
		mapped--;
	}

	return ret;
}
EXPORT_SYMBOL(hmm_range_dma_map);

/**
 * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
 * @range: range being unmapped
 * @vma: the vma against which the range (optional)
 * @device: device against which dma map was done
 * @daddrs: dma address of mapped pages
 * @dirty: dirty page if it had the write flag set
 * Return: number of page unmapped on success, -EINVAL otherwise
 *
 * Note that caller MUST abide by mmu notifier or use HMM mirror and abide
 * to the sync_cpu_device_pagetables() callback so that it is safe here to
 * call set_page_dirty(). Caller must also take appropriate locks to avoid
 * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress.
 */
long hmm_range_dma_unmap(struct hmm_range *range,
			 struct vm_area_struct *vma,
			 struct device *device,
			 dma_addr_t *daddrs,
			 bool dirty)
{
	unsigned long i, npages;
	long cpages = 0;

	/* Sanity check. */
	if (range->end <= range->start)
		return -EINVAL;
	if (!daddrs)
		return -EINVAL;
	if (!range->pfns)
		return -EINVAL;

	npages = (range->end - range->start) >> PAGE_SHIFT;
	for (i = 0; i < npages; ++i) {
		enum dma_data_direction dir = DMA_TO_DEVICE;
		struct page *page;

		page = hmm_device_entry_to_page(range, range->pfns[i]);
		if (page == NULL)
			continue;

		/* If it is read and write than map bi-directional. */
		if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) {
			dir = DMA_BIDIRECTIONAL;

			/*
			 * See comments in function description on why it is
			 * safe here to call set_page_dirty()
			 */
			if (dirty)
				set_page_dirty(page);
		}

		/* Unmap and clear pfns/dma address */
		dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
		range->pfns[i] = range->values[HMM_PFN_NONE];
		/* FIXME see comments in hmm_vma_dma_map() */
		daddrs[i] = 0;
		cpages++;
	}

	return cpages;
}
EXPORT_SYMBOL(hmm_range_dma_unmap);