summaryrefslogtreecommitdiff
path: root/drivers/iommu/iova.c
blob: b6cf5f16123bdb678548ed2f1fb077efd467a300 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright © 2006-2009, Intel Corporation.
 *
 * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 */

#include <linux/iova.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/bitops.h>
#include <linux/cpu.h>

/* The anchor node sits above the top of the usable address space */
#define IOVA_ANCHOR	~0UL

static bool iova_rcache_insert(struct iova_domain *iovad,
			       unsigned long pfn,
			       unsigned long size);
static unsigned long iova_rcache_get(struct iova_domain *iovad,
				     unsigned long size,
				     unsigned long limit_pfn);
static void init_iova_rcaches(struct iova_domain *iovad);
static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
static void free_iova_rcaches(struct iova_domain *iovad);
static void fq_destroy_all_entries(struct iova_domain *iovad);
static void fq_flush_timeout(struct timer_list *t);

static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
{
	struct iova_domain *iovad;

	iovad = hlist_entry_safe(node, struct iova_domain, cpuhp_dead);

	free_cpu_cached_iovas(cpu, iovad);
	return 0;
}

static void free_global_cached_iovas(struct iova_domain *iovad);

static struct iova *to_iova(struct rb_node *node)
{
	return rb_entry(node, struct iova, node);
}

void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
	unsigned long start_pfn)
{
	/*
	 * IOVA granularity will normally be equal to the smallest
	 * supported IOMMU page size; both *must* be capable of
	 * representing individual CPU pages exactly.
	 */
	BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));

	spin_lock_init(&iovad->iova_rbtree_lock);
	iovad->rbroot = RB_ROOT;
	iovad->cached_node = &iovad->anchor.node;
	iovad->cached32_node = &iovad->anchor.node;
	iovad->granule = granule;
	iovad->start_pfn = start_pfn;
	iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
	iovad->max32_alloc_size = iovad->dma_32bit_pfn;
	iovad->flush_cb = NULL;
	iovad->fq = NULL;
	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
	cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, &iovad->cpuhp_dead);
	init_iova_rcaches(iovad);
}
EXPORT_SYMBOL_GPL(init_iova_domain);

static bool has_iova_flush_queue(struct iova_domain *iovad)
{
	return !!iovad->fq;
}

static void free_iova_flush_queue(struct iova_domain *iovad)
{
	if (!has_iova_flush_queue(iovad))
		return;

	if (timer_pending(&iovad->fq_timer))
		del_timer(&iovad->fq_timer);

	fq_destroy_all_entries(iovad);

	free_percpu(iovad->fq);

	iovad->fq         = NULL;
	iovad->flush_cb   = NULL;
	iovad->entry_dtor = NULL;
}

int init_iova_flush_queue(struct iova_domain *iovad,
			  iova_flush_cb flush_cb, iova_entry_dtor entry_dtor)
{
	struct iova_fq __percpu *queue;
	int cpu;

	atomic64_set(&iovad->fq_flush_start_cnt,  0);
	atomic64_set(&iovad->fq_flush_finish_cnt, 0);

	queue = alloc_percpu(struct iova_fq);
	if (!queue)
		return -ENOMEM;

	iovad->flush_cb   = flush_cb;
	iovad->entry_dtor = entry_dtor;

	for_each_possible_cpu(cpu) {
		struct iova_fq *fq;

		fq = per_cpu_ptr(queue, cpu);
		fq->head = 0;
		fq->tail = 0;

		spin_lock_init(&fq->lock);
	}

	smp_wmb();

	iovad->fq = queue;

	timer_setup(&iovad->fq_timer, fq_flush_timeout, 0);
	atomic_set(&iovad->fq_timer_on, 0);

	return 0;
}

static struct rb_node *
__get_cached_rbnode(struct iova_domain *iovad, unsigned long limit_pfn)
{
	if (limit_pfn <= iovad->dma_32bit_pfn)
		return iovad->cached32_node;

	return iovad->cached_node;
}

static void
__cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
{
	if (new->pfn_hi < iovad->dma_32bit_pfn)
		iovad->cached32_node = &new->node;
	else
		iovad->cached_node = &new->node;
}

static void
__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
{
	struct iova *cached_iova;

	cached_iova = to_iova(iovad->cached32_node);
	if (free == cached_iova ||
	    (free->pfn_hi < iovad->dma_32bit_pfn &&
	     free->pfn_lo >= cached_iova->pfn_lo)) {
		iovad->cached32_node = rb_next(&free->node);
		iovad->max32_alloc_size = iovad->dma_32bit_pfn;
	}

	cached_iova = to_iova(iovad->cached_node);
	if (free->pfn_lo >= cached_iova->pfn_lo)
		iovad->cached_node = rb_next(&free->node);
}

static struct rb_node *iova_find_limit(struct iova_domain *iovad, unsigned long limit_pfn)
{
	struct rb_node *node, *next;
	/*
	 * Ideally what we'd like to judge here is whether limit_pfn is close
	 * enough to the highest-allocated IOVA that starting the allocation
	 * walk from the anchor node will be quicker than this initial work to
	 * find an exact starting point (especially if that ends up being the
	 * anchor node anyway). This is an incredibly crude approximation which
	 * only really helps the most likely case, but is at least trivially easy.
	 */
	if (limit_pfn > iovad->dma_32bit_pfn)
		return &iovad->anchor.node;

	node = iovad->rbroot.rb_node;
	while (to_iova(node)->pfn_hi < limit_pfn)
		node = node->rb_right;

search_left:
	while (node->rb_left && to_iova(node->rb_left)->pfn_lo >= limit_pfn)
		node = node->rb_left;

	if (!node->rb_left)
		return node;

	next = node->rb_left;
	while (next->rb_right) {
		next = next->rb_right;
		if (to_iova(next)->pfn_lo >= limit_pfn) {
			node = next;
			goto search_left;
		}
	}

	return node;
}

/* Insert the iova into domain rbtree by holding writer lock */
static void
iova_insert_rbtree(struct rb_root *root, struct iova *iova,
		   struct rb_node *start)
{
	struct rb_node **new, *parent = NULL;

	new = (start) ? &start : &(root->rb_node);
	/* Figure out where to put new node */
	while (*new) {
		struct iova *this = to_iova(*new);

		parent = *new;

		if (iova->pfn_lo < this->pfn_lo)
			new = &((*new)->rb_left);
		else if (iova->pfn_lo > this->pfn_lo)
			new = &((*new)->rb_right);
		else {
			WARN_ON(1); /* this should not happen */
			return;
		}
	}
	/* Add new node and rebalance tree. */
	rb_link_node(&iova->node, parent, new);
	rb_insert_color(&iova->node, root);
}

static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
		unsigned long size, unsigned long limit_pfn,
			struct iova *new, bool size_aligned)
{
	struct rb_node *curr, *prev;
	struct iova *curr_iova;
	unsigned long flags;
	unsigned long new_pfn, retry_pfn;
	unsigned long align_mask = ~0UL;
	unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;

	if (size_aligned)
		align_mask <<= fls_long(size - 1);

	/* Walk the tree backwards */
	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
	if (limit_pfn <= iovad->dma_32bit_pfn &&
			size >= iovad->max32_alloc_size)
		goto iova32_full;

	curr = __get_cached_rbnode(iovad, limit_pfn);
	curr_iova = to_iova(curr);
	retry_pfn = curr_iova->pfn_hi + 1;

retry:
	do {
		high_pfn = min(high_pfn, curr_iova->pfn_lo);
		new_pfn = (high_pfn - size) & align_mask;
		prev = curr;
		curr = rb_prev(curr);
		curr_iova = to_iova(curr);
	} while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);

	if (high_pfn < size || new_pfn < low_pfn) {
		if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
			high_pfn = limit_pfn;
			low_pfn = retry_pfn;
			curr = iova_find_limit(iovad, limit_pfn);
			curr_iova = to_iova(curr);
			goto retry;
		}
		iovad->max32_alloc_size = size;
		goto iova32_full;
	}

	/* pfn_lo will point to size aligned address if size_aligned is set */
	new->pfn_lo = new_pfn;
	new->pfn_hi = new->pfn_lo + size - 1;

	/* If we have 'prev', it's a valid place to start the insertion. */
	iova_insert_rbtree(&iovad->rbroot, new, prev);
	__cached_rbnode_insert_update(iovad, new);

	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
	return 0;

iova32_full:
	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
	return -ENOMEM;
}

static struct kmem_cache *iova_cache;
static unsigned int iova_cache_users;
static DEFINE_MUTEX(iova_cache_mutex);

static struct iova *alloc_iova_mem(void)
{
	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
}

static void free_iova_mem(struct iova *iova)
{
	if (iova->pfn_lo != IOVA_ANCHOR)
		kmem_cache_free(iova_cache, iova);
}

int iova_cache_get(void)
{
	mutex_lock(&iova_cache_mutex);
	if (!iova_cache_users) {
		int ret;

		ret = cpuhp_setup_state_multi(CPUHP_IOMMU_IOVA_DEAD, "iommu/iova:dead", NULL,
					iova_cpuhp_dead);
		if (ret) {
			mutex_unlock(&iova_cache_mutex);
			pr_err("Couldn't register cpuhp handler\n");
			return ret;
		}

		iova_cache = kmem_cache_create(
			"iommu_iova", sizeof(struct iova), 0,
			SLAB_HWCACHE_ALIGN, NULL);
		if (!iova_cache) {
			cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
			mutex_unlock(&iova_cache_mutex);
			pr_err("Couldn't create iova cache\n");
			return -ENOMEM;
		}
	}

	iova_cache_users++;
	mutex_unlock(&iova_cache_mutex);

	return 0;
}
EXPORT_SYMBOL_GPL(iova_cache_get);

void iova_cache_put(void)
{
	mutex_lock(&iova_cache_mutex);
	if (WARN_ON(!iova_cache_users)) {
		mutex_unlock(&iova_cache_mutex);
		return;
	}
	iova_cache_users--;
	if (!iova_cache_users) {
		cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
		kmem_cache_destroy(iova_cache);
	}
	mutex_unlock(&iova_cache_mutex);
}
EXPORT_SYMBOL_GPL(iova_cache_put);

/**
 * alloc_iova - allocates an iova
 * @iovad: - iova domain in question
 * @size: - size of page frames to allocate
 * @limit_pfn: - max limit address
 * @size_aligned: - set if size_aligned address range is required
 * This function allocates an iova in the range iovad->start_pfn to limit_pfn,
 * searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
 * flag is set then the allocated address iova->pfn_lo will be naturally
 * aligned on roundup_power_of_two(size).
 */
struct iova *
alloc_iova(struct iova_domain *iovad, unsigned long size,
	unsigned long limit_pfn,
	bool size_aligned)
{
	struct iova *new_iova;
	int ret;

	new_iova = alloc_iova_mem();
	if (!new_iova)
		return NULL;

	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn + 1,
			new_iova, size_aligned);

	if (ret) {
		free_iova_mem(new_iova);
		return NULL;
	}

	return new_iova;
}
EXPORT_SYMBOL_GPL(alloc_iova);

static struct iova *
private_find_iova(struct iova_domain *iovad, unsigned long pfn)
{
	struct rb_node *node = iovad->rbroot.rb_node;

	assert_spin_locked(&iovad->iova_rbtree_lock);

	while (node) {
		struct iova *iova = to_iova(node);

		if (pfn < iova->pfn_lo)
			node = node->rb_left;
		else if (pfn > iova->pfn_hi)
			node = node->rb_right;
		else
			return iova;	/* pfn falls within iova's range */
	}

	return NULL;
}

static void remove_iova(struct iova_domain *iovad, struct iova *iova)
{
	assert_spin_locked(&iovad->iova_rbtree_lock);
	__cached_rbnode_delete_update(iovad, iova);
	rb_erase(&iova->node, &iovad->rbroot);
}

/**
 * find_iova - finds an iova for a given pfn
 * @iovad: - iova domain in question.
 * @pfn: - page frame number
 * This function finds and returns an iova belonging to the
 * given domain which matches the given pfn.
 */
struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
{
	unsigned long flags;
	struct iova *iova;

	/* Take the lock so that no other thread is manipulating the rbtree */
	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
	iova = private_find_iova(iovad, pfn);
	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
	return iova;
}
EXPORT_SYMBOL_GPL(find_iova);

/**
 * __free_iova - frees the given iova
 * @iovad: iova domain in question.
 * @iova: iova in question.
 * Frees the given iova belonging to the giving domain
 */
void
__free_iova(struct iova_domain *iovad, struct iova *iova)
{
	unsigned long flags;

	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
	remove_iova(iovad, iova);
	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
	free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(__free_iova);

/**
 * free_iova - finds and frees the iova for a given pfn
 * @iovad: - iova domain in question.
 * @pfn: - pfn that is allocated previously
 * This functions finds an iova for a given pfn and then
 * frees the iova from that domain.
 */
void
free_iova(struct iova_domain *iovad, unsigned long pfn)
{
	unsigned long flags;
	struct iova *iova;

	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
	iova = private_find_iova(iovad, pfn);
	if (!iova) {
		spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
		return;
	}
	remove_iova(iovad, iova);
	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
	free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(free_iova);

/**
 * alloc_iova_fast - allocates an iova from rcache
 * @iovad: - iova domain in question
 * @size: - size of page frames to allocate
 * @limit_pfn: - max limit address
 * @flush_rcache: - set to flush rcache on regular allocation failure
 * This function tries to satisfy an iova allocation from the rcache,
 * and falls back to regular allocation on failure. If regular allocation
 * fails too and the flush_rcache flag is set then the rcache will be flushed.
*/
unsigned long
alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
		unsigned long limit_pfn, bool flush_rcache)
{
	unsigned long iova_pfn;
	struct iova *new_iova;

	iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
	if (iova_pfn)
		return iova_pfn;

retry:
	new_iova = alloc_iova(iovad, size, limit_pfn, true);
	if (!new_iova) {
		unsigned int cpu;

		if (!flush_rcache)
			return 0;

		/* Try replenishing IOVAs by flushing rcache. */
		flush_rcache = false;
		for_each_online_cpu(cpu)
			free_cpu_cached_iovas(cpu, iovad);
		free_global_cached_iovas(iovad);
		goto retry;
	}

	return new_iova->pfn_lo;
}

/**
 * free_iova_fast - free iova pfn range into rcache
 * @iovad: - iova domain in question.
 * @pfn: - pfn that is allocated previously
 * @size: - # of pages in range
 * This functions frees an iova range by trying to put it into the rcache,
 * falling back to regular iova deallocation via free_iova() if this fails.
 */
void
free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
{
	if (iova_rcache_insert(iovad, pfn, size))
		return;

	free_iova(iovad, pfn);
}

#define fq_ring_for_each(i, fq) \
	for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)

static inline bool fq_full(struct iova_fq *fq)
{
	assert_spin_locked(&fq->lock);
	return (((fq->tail + 1) % IOVA_FQ_SIZE) == fq->head);
}

static inline unsigned fq_ring_add(struct iova_fq *fq)
{
	unsigned idx = fq->tail;

	assert_spin_locked(&fq->lock);

	fq->tail = (idx + 1) % IOVA_FQ_SIZE;

	return idx;
}

static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq)
{
	u64 counter = atomic64_read(&iovad->fq_flush_finish_cnt);
	unsigned idx;

	assert_spin_locked(&fq->lock);

	fq_ring_for_each(idx, fq) {

		if (fq->entries[idx].counter >= counter)
			break;

		if (iovad->entry_dtor)
			iovad->entry_dtor(fq->entries[idx].data);

		free_iova_fast(iovad,
			       fq->entries[idx].iova_pfn,
			       fq->entries[idx].pages);

		fq->head = (fq->head + 1) % IOVA_FQ_SIZE;
	}
}

static void iova_domain_flush(struct iova_domain *iovad)
{
	atomic64_inc(&iovad->fq_flush_start_cnt);
	iovad->flush_cb(iovad);
	atomic64_inc(&iovad->fq_flush_finish_cnt);
}

static void fq_destroy_all_entries(struct iova_domain *iovad)
{
	int cpu;

	/*
	 * This code runs when the iova_domain is being detroyed, so don't
	 * bother to free iovas, just call the entry_dtor on all remaining
	 * entries.
	 */
	if (!iovad->entry_dtor)
		return;

	for_each_possible_cpu(cpu) {
		struct iova_fq *fq = per_cpu_ptr(iovad->fq, cpu);
		int idx;

		fq_ring_for_each(idx, fq)
			iovad->entry_dtor(fq->entries[idx].data);
	}
}

static void fq_flush_timeout(struct timer_list *t)
{
	struct iova_domain *iovad = from_timer(iovad, t, fq_timer);
	int cpu;

	atomic_set(&iovad->fq_timer_on, 0);
	iova_domain_flush(iovad);

	for_each_possible_cpu(cpu) {
		unsigned long flags;
		struct iova_fq *fq;

		fq = per_cpu_ptr(iovad->fq, cpu);
		spin_lock_irqsave(&fq->lock, flags);
		fq_ring_free(iovad, fq);
		spin_unlock_irqrestore(&fq->lock, flags);
	}
}

void queue_iova(struct iova_domain *iovad,
		unsigned long pfn, unsigned long pages,
		unsigned long data)
{
	struct iova_fq *fq = raw_cpu_ptr(iovad->fq);
	unsigned long flags;
	unsigned idx;

	spin_lock_irqsave(&fq->lock, flags);

	/*
	 * First remove all entries from the flush queue that have already been
	 * flushed out on another CPU. This makes the fq_full() check below less
	 * likely to be true.
	 */
	fq_ring_free(iovad, fq);

	if (fq_full(fq)) {
		iova_domain_flush(iovad);
		fq_ring_free(iovad, fq);
	}

	idx = fq_ring_add(fq);

	fq->entries[idx].iova_pfn = pfn;
	fq->entries[idx].pages    = pages;
	fq->entries[idx].data     = data;
	fq->entries[idx].counter  = atomic64_read(&iovad->fq_flush_start_cnt);

	spin_unlock_irqrestore(&fq->lock, flags);

	/* Avoid false sharing as much as possible. */
	if (!atomic_read(&iovad->fq_timer_on) &&
	    !atomic_xchg(&iovad->fq_timer_on, 1))
		mod_timer(&iovad->fq_timer,
			  jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
}

/**
 * put_iova_domain - destroys the iova domain
 * @iovad: - iova domain in question.
 * All the iova's in that domain are destroyed.
 */
void put_iova_domain(struct iova_domain *iovad)
{
	struct iova *iova, *tmp;

	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
					    &iovad->cpuhp_dead);

	free_iova_flush_queue(iovad);
	free_iova_rcaches(iovad);
	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
		free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(put_iova_domain);

static int
__is_range_overlap(struct rb_node *node,
	unsigned long pfn_lo, unsigned long pfn_hi)
{
	struct iova *iova = to_iova(node);

	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
		return 1;
	return 0;
}

static inline struct iova *
alloc_and_init_iova(unsigned long pfn_lo, unsigned long pfn_hi)
{
	struct iova *iova;

	iova = alloc_iova_mem();
	if (iova) {
		iova->pfn_lo = pfn_lo;
		iova->pfn_hi = pfn_hi;
	}

	return iova;
}

static struct iova *
__insert_new_range(struct iova_domain *iovad,
	unsigned long pfn_lo, unsigned long pfn_hi)
{
	struct iova *iova;

	iova = alloc_and_init_iova(pfn_lo, pfn_hi);
	if (iova)
		iova_insert_rbtree(&iovad->rbroot, iova, NULL);

	return iova;
}

static void
__adjust_overlap_range(struct iova *iova,
	unsigned long *pfn_lo, unsigned long *pfn_hi)
{
	if (*pfn_lo < iova->pfn_lo)
		iova->pfn_lo = *pfn_lo;
	if (*pfn_hi > iova->pfn_hi)
		*pfn_lo = iova->pfn_hi + 1;
}

/**
 * reserve_iova - reserves an iova in the given range
 * @iovad: - iova domain pointer
 * @pfn_lo: - lower page frame address
 * @pfn_hi:- higher pfn adderss
 * This function allocates reserves the address range from pfn_lo to pfn_hi so
 * that this address is not dished out as part of alloc_iova.
 */
struct iova *
reserve_iova(struct iova_domain *iovad,
	unsigned long pfn_lo, unsigned long pfn_hi)
{
	struct rb_node *node;
	unsigned long flags;
	struct iova *iova;
	unsigned int overlap = 0;

	/* Don't allow nonsensical pfns */
	if (WARN_ON((pfn_hi | pfn_lo) > (ULLONG_MAX >> iova_shift(iovad))))
		return NULL;

	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
			iova = to_iova(node);
			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
			if ((pfn_lo >= iova->pfn_lo) &&
				(pfn_hi <= iova->pfn_hi))
				goto finish;
			overlap = 1;

		} else if (overlap)
				break;
	}

	/* We are here either because this is the first reserver node
	 * or need to insert remaining non overlap addr range
	 */
	iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
finish:

	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
	return iova;
}
EXPORT_SYMBOL_GPL(reserve_iova);

/*
 * Magazine caches for IOVA ranges.  For an introduction to magazines,
 * see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab
 * Allocator to Many CPUs and Arbitrary Resources" by Bonwick and Adams.
 * For simplicity, we use a static magazine size and don't implement the
 * dynamic size tuning described in the paper.
 */

#define IOVA_MAG_SIZE 128

struct iova_magazine {
	unsigned long size;
	unsigned long pfns[IOVA_MAG_SIZE];
};

struct iova_cpu_rcache {
	spinlock_t lock;
	struct iova_magazine *loaded;
	struct iova_magazine *prev;
};

static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
{
	return kzalloc(sizeof(struct iova_magazine), flags);
}

static void iova_magazine_free(struct iova_magazine *mag)
{
	kfree(mag);
}

static void
iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad)
{
	unsigned long flags;
	int i;

	if (!mag)
		return;

	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);

	for (i = 0 ; i < mag->size; ++i) {
		struct iova *iova = private_find_iova(iovad, mag->pfns[i]);

		if (WARN_ON(!iova))
			continue;

		remove_iova(iovad, iova);
		free_iova_mem(iova);
	}

	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);

	mag->size = 0;
}

static bool iova_magazine_full(struct iova_magazine *mag)
{
	return (mag && mag->size == IOVA_MAG_SIZE);
}

static bool iova_magazine_empty(struct iova_magazine *mag)
{
	return (!mag || mag->size == 0);
}

static unsigned long iova_magazine_pop(struct iova_magazine *mag,
				       unsigned long limit_pfn)
{
	int i;
	unsigned long pfn;

	BUG_ON(iova_magazine_empty(mag));

	/* Only fall back to the rbtree if we have no suitable pfns at all */
	for (i = mag->size - 1; mag->pfns[i] > limit_pfn; i--)
		if (i == 0)
			return 0;

	/* Swap it to pop it */
	pfn = mag->pfns[i];
	mag->pfns[i] = mag->pfns[--mag->size];

	return pfn;
}

static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
{
	BUG_ON(iova_magazine_full(mag));

	mag->pfns[mag->size++] = pfn;
}

static void init_iova_rcaches(struct iova_domain *iovad)
{
	struct iova_cpu_rcache *cpu_rcache;
	struct iova_rcache *rcache;
	unsigned int cpu;
	int i;

	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
		rcache = &iovad->rcaches[i];
		spin_lock_init(&rcache->lock);
		rcache->depot_size = 0;
		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), cache_line_size());
		if (WARN_ON(!rcache->cpu_rcaches))
			continue;
		for_each_possible_cpu(cpu) {
			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
			spin_lock_init(&cpu_rcache->lock);
			cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
			cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
		}
	}
}

/*
 * Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and
 * return true on success.  Can fail if rcache is full and we can't free
 * space, and free_iova() (our only caller) will then return the IOVA
 * range to the rbtree instead.
 */
static bool __iova_rcache_insert(struct iova_domain *iovad,
				 struct iova_rcache *rcache,
				 unsigned long iova_pfn)
{
	struct iova_magazine *mag_to_free = NULL;
	struct iova_cpu_rcache *cpu_rcache;
	bool can_insert = false;
	unsigned long flags;

	cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
	spin_lock_irqsave(&cpu_rcache->lock, flags);

	if (!iova_magazine_full(cpu_rcache->loaded)) {
		can_insert = true;
	} else if (!iova_magazine_full(cpu_rcache->prev)) {
		swap(cpu_rcache->prev, cpu_rcache->loaded);
		can_insert = true;
	} else {
		struct iova_magazine *new_mag = iova_magazine_alloc(GFP_ATOMIC);

		if (new_mag) {
			spin_lock(&rcache->lock);
			if (rcache->depot_size < MAX_GLOBAL_MAGS) {
				rcache->depot[rcache->depot_size++] =
						cpu_rcache->loaded;
			} else {
				mag_to_free = cpu_rcache->loaded;
			}
			spin_unlock(&rcache->lock);

			cpu_rcache->loaded = new_mag;
			can_insert = true;
		}
	}

	if (can_insert)
		iova_magazine_push(cpu_rcache->loaded, iova_pfn);

	spin_unlock_irqrestore(&cpu_rcache->lock, flags);

	if (mag_to_free) {
		iova_magazine_free_pfns(mag_to_free, iovad);
		iova_magazine_free(mag_to_free);
	}

	return can_insert;
}

static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn,
			       unsigned long size)
{
	unsigned int log_size = order_base_2(size);

	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
		return false;

	return __iova_rcache_insert(iovad, &iovad->rcaches[log_size], pfn);
}

/*
 * Caller wants to allocate a new IOVA range from 'rcache'.  If we can
 * satisfy the request, return a matching non-NULL range and remove
 * it from the 'rcache'.
 */
static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
				       unsigned long limit_pfn)
{
	struct iova_cpu_rcache *cpu_rcache;
	unsigned long iova_pfn = 0;
	bool has_pfn = false;
	unsigned long flags;

	cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
	spin_lock_irqsave(&cpu_rcache->lock, flags);

	if (!iova_magazine_empty(cpu_rcache->loaded)) {
		has_pfn = true;
	} else if (!iova_magazine_empty(cpu_rcache->prev)) {
		swap(cpu_rcache->prev, cpu_rcache->loaded);
		has_pfn = true;
	} else {
		spin_lock(&rcache->lock);
		if (rcache->depot_size > 0) {
			iova_magazine_free(cpu_rcache->loaded);
			cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
			has_pfn = true;
		}
		spin_unlock(&rcache->lock);
	}

	if (has_pfn)
		iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);

	spin_unlock_irqrestore(&cpu_rcache->lock, flags);

	return iova_pfn;
}

/*
 * Try to satisfy IOVA allocation range from rcache.  Fail if requested
 * size is too big or the DMA limit we are given isn't satisfied by the
 * top element in the magazine.
 */
static unsigned long iova_rcache_get(struct iova_domain *iovad,
				     unsigned long size,
				     unsigned long limit_pfn)
{
	unsigned int log_size = order_base_2(size);

	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
		return 0;

	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
}

/*
 * free rcache data structures.
 */
static void free_iova_rcaches(struct iova_domain *iovad)
{
	struct iova_rcache *rcache;
	struct iova_cpu_rcache *cpu_rcache;
	unsigned int cpu;
	int i, j;

	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
		rcache = &iovad->rcaches[i];
		for_each_possible_cpu(cpu) {
			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
			iova_magazine_free(cpu_rcache->loaded);
			iova_magazine_free(cpu_rcache->prev);
		}
		free_percpu(rcache->cpu_rcaches);
		for (j = 0; j < rcache->depot_size; ++j)
			iova_magazine_free(rcache->depot[j]);
	}
}

/*
 * free all the IOVA ranges cached by a cpu (used when cpu is unplugged)
 */
static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
{
	struct iova_cpu_rcache *cpu_rcache;
	struct iova_rcache *rcache;
	unsigned long flags;
	int i;

	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
		rcache = &iovad->rcaches[i];
		cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
		spin_lock_irqsave(&cpu_rcache->lock, flags);
		iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
		iova_magazine_free_pfns(cpu_rcache->prev, iovad);
		spin_unlock_irqrestore(&cpu_rcache->lock, flags);
	}
}

/*
 * free all the IOVA ranges of global cache
 */
static void free_global_cached_iovas(struct iova_domain *iovad)
{
	struct iova_rcache *rcache;
	unsigned long flags;
	int i, j;

	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
		rcache = &iovad->rcaches[i];
		spin_lock_irqsave(&rcache->lock, flags);
		for (j = 0; j < rcache->depot_size; ++j) {
			iova_magazine_free_pfns(rcache->depot[j], iovad);
			iova_magazine_free(rcache->depot[j]);
		}
		rcache->depot_size = 0;
		spin_unlock_irqrestore(&rcache->lock, flags);
	}
}
MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
MODULE_LICENSE("GPL");