summaryrefslogtreecommitdiff
path: root/kernel/dma/swiotlb.c
blob: af2e304c672c43cf31cc8fcd78c99b337b844658 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Dynamic DMA mapping support.
 *
 * This implementation is a fallback for platforms that do not support
 * I/O TLBs (aka DMA address translation hardware).
 * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
 * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
 * Copyright (C) 2000, 2003 Hewlett-Packard Co
 *	David Mosberger-Tang <davidm@hpl.hp.com>
 *
 * 03/05/07 davidm	Switch from PCI-DMA to generic device DMA API.
 * 00/12/13 davidm	Rename to swiotlb.c and add mark_clean() to avoid
 *			unnecessary i-cache flushing.
 * 04/07/.. ak		Better overflow handling. Assorted fixes.
 * 05/09/10 linville	Add support for syncing ranges, support syncing for
 *			DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
 * 08/12/11 beckyb	Add highmem support
 */

#define pr_fmt(fmt) "software IO TLB: " fmt

#include <linux/cache.h>
#include <linux/cc_platform.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/io.h>
#include <linux/iommu-helper.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/pfn.h>
#include <linux/scatterlist.h>
#include <linux/set_memory.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/swiotlb.h>
#include <linux/types.h>
#ifdef CONFIG_DMA_RESTRICTED_POOL
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/of_reserved_mem.h>
#include <linux/slab.h>
#endif

#define CREATE_TRACE_POINTS
#include <trace/events/swiotlb.h>

#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))

/*
 * Minimum IO TLB size to bother booting with.  Systems with mainly
 * 64bit capable cards will only lightly use the swiotlb.  If we can't
 * allocate a contiguous 1MB, we're probably in trouble anyway.
 */
#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)

#define INVALID_PHYS_ADDR (~(phys_addr_t)0)

struct io_tlb_slot {
	phys_addr_t orig_addr;
	size_t alloc_size;
	unsigned int list;
};

static bool swiotlb_force_bounce;
static bool swiotlb_force_disable;

struct io_tlb_mem io_tlb_default_mem;

static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
static unsigned long default_nareas;

/**
 * struct io_tlb_area - IO TLB memory area descriptor
 *
 * This is a single area with a single lock.
 *
 * @used:	The number of used IO TLB block.
 * @index:	The slot index to start searching in this area for next round.
 * @lock:	The lock to protect the above data structures in the map and
 *		unmap calls.
 */
struct io_tlb_area {
	unsigned long used;
	unsigned int index;
	spinlock_t lock;
};

/*
 * Round up number of slabs to the next power of 2. The last area is going
 * be smaller than the rest if default_nslabs is not power of two.
 * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE,
 * otherwise a segment may span two or more areas. It conflicts with free
 * contiguous slots tracking: free slots are treated contiguous no matter
 * whether they cross an area boundary.
 *
 * Return true if default_nslabs is rounded up.
 */
static bool round_up_default_nslabs(void)
{
	if (!default_nareas)
		return false;

	if (default_nslabs < IO_TLB_SEGSIZE * default_nareas)
		default_nslabs = IO_TLB_SEGSIZE * default_nareas;
	else if (is_power_of_2(default_nslabs))
		return false;
	default_nslabs = roundup_pow_of_two(default_nslabs);
	return true;
}

static void swiotlb_adjust_nareas(unsigned int nareas)
{
	/* use a single area when non is specified */
	if (!nareas)
		nareas = 1;
	else if (!is_power_of_2(nareas))
		nareas = roundup_pow_of_two(nareas);

	default_nareas = nareas;

	pr_info("area num %d.\n", nareas);
	if (round_up_default_nslabs())
		pr_info("SWIOTLB bounce buffer size roundup to %luMB",
			(default_nslabs << IO_TLB_SHIFT) >> 20);
}

static int __init
setup_io_tlb_npages(char *str)
{
	if (isdigit(*str)) {
		/* avoid tail segment of size < IO_TLB_SEGSIZE */
		default_nslabs =
			ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE);
	}
	if (*str == ',')
		++str;
	if (isdigit(*str))
		swiotlb_adjust_nareas(simple_strtoul(str, &str, 0));
	if (*str == ',')
		++str;
	if (!strcmp(str, "force"))
		swiotlb_force_bounce = true;
	else if (!strcmp(str, "noforce"))
		swiotlb_force_disable = true;

	return 0;
}
early_param("swiotlb", setup_io_tlb_npages);

unsigned long swiotlb_size_or_default(void)
{
	return default_nslabs << IO_TLB_SHIFT;
}

void __init swiotlb_adjust_size(unsigned long size)
{
	/*
	 * If swiotlb parameter has not been specified, give a chance to
	 * architectures such as those supporting memory encryption to
	 * adjust/expand SWIOTLB size for their use.
	 */
	if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT)
		return;

	size = ALIGN(size, IO_TLB_SIZE);
	default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
	if (round_up_default_nslabs())
		size = default_nslabs << IO_TLB_SHIFT;
	pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
}

void swiotlb_print_info(void)
{
	struct io_tlb_mem *mem = &io_tlb_default_mem;

	if (!mem->nslabs) {
		pr_warn("No low mem\n");
		return;
	}

	pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end,
	       (mem->nslabs << IO_TLB_SHIFT) >> 20);
}

static inline unsigned long io_tlb_offset(unsigned long val)
{
	return val & (IO_TLB_SEGSIZE - 1);
}

static inline unsigned long nr_slots(u64 val)
{
	return DIV_ROUND_UP(val, IO_TLB_SIZE);
}

/*
 * Early SWIOTLB allocation may be too early to allow an architecture to
 * perform the desired operations.  This function allows the architecture to
 * call SWIOTLB when the operations are possible.  It needs to be called
 * before the SWIOTLB memory is used.
 */
void __init swiotlb_update_mem_attributes(void)
{
	struct io_tlb_mem *mem = &io_tlb_default_mem;
	unsigned long bytes;

	if (!mem->nslabs || mem->late_alloc)
		return;
	bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
	set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT);
}

static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start,
		unsigned long nslabs, unsigned int flags,
		bool late_alloc, unsigned int nareas)
{
	void *vaddr = phys_to_virt(start);
	unsigned long bytes = nslabs << IO_TLB_SHIFT, i;

	mem->nslabs = nslabs;
	mem->start = start;
	mem->end = mem->start + bytes;
	mem->late_alloc = late_alloc;
	mem->nareas = nareas;
	mem->area_nslabs = nslabs / mem->nareas;

	mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE);

	for (i = 0; i < mem->nareas; i++) {
		spin_lock_init(&mem->areas[i].lock);
		mem->areas[i].index = 0;
		mem->areas[i].used = 0;
	}

	for (i = 0; i < mem->nslabs; i++) {
		mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
		mem->slots[i].alloc_size = 0;
	}

	memset(vaddr, 0, bytes);
	mem->vaddr = vaddr;
	return;
}

static void __init *swiotlb_memblock_alloc(unsigned long nslabs,
		unsigned int flags,
		int (*remap)(void *tlb, unsigned long nslabs))
{
	size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT);
	void *tlb;

	/*
	 * By default allocate the bounce buffer memory from low memory, but
	 * allow to pick a location everywhere for hypervisors with guest
	 * memory encryption.
	 */
	if (flags & SWIOTLB_ANY)
		tlb = memblock_alloc(bytes, PAGE_SIZE);
	else
		tlb = memblock_alloc_low(bytes, PAGE_SIZE);

	if (!tlb) {
		pr_warn("%s: Failed to allocate %zu bytes tlb structure\n",
			__func__, bytes);
		return NULL;
	}

	if (remap && remap(tlb, nslabs) < 0) {
		memblock_free(tlb, PAGE_ALIGN(bytes));
		pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes);
		return NULL;
	}

	return tlb;
}

/*
 * Statically reserve bounce buffer space and initialize bounce buffer data
 * structures for the software IO TLB used to implement the DMA API.
 */
void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
		int (*remap)(void *tlb, unsigned long nslabs))
{
	struct io_tlb_mem *mem = &io_tlb_default_mem;
	unsigned long nslabs;
	size_t alloc_size;
	void *tlb;

	if (!addressing_limit && !swiotlb_force_bounce)
		return;
	if (swiotlb_force_disable)
		return;

	/*
	 * default_nslabs maybe changed when adjust area number.
	 * So allocate bounce buffer after adjusting area number.
	 */
	if (!default_nareas)
		swiotlb_adjust_nareas(num_possible_cpus());

	nslabs = default_nslabs;
	while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) {
		if (nslabs <= IO_TLB_MIN_SLABS)
			return;
		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
	}

	if (default_nslabs != nslabs) {
		pr_info("SWIOTLB bounce buffer size adjusted %lu -> %lu slabs",
			default_nslabs, nslabs);
		default_nslabs = nslabs;
	}

	alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
	mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
	if (!mem->slots) {
		pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n",
			__func__, alloc_size, PAGE_SIZE);
		return;
	}

	mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
		default_nareas), SMP_CACHE_BYTES);
	if (!mem->areas) {
		pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
		return;
	}

	swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false,
				default_nareas);

	if (flags & SWIOTLB_VERBOSE)
		swiotlb_print_info();
}

void __init swiotlb_init(bool addressing_limit, unsigned int flags)
{
	swiotlb_init_remap(addressing_limit, flags, NULL);
}

/*
 * Systems with larger DMA zones (those that don't support ISA) can
 * initialize the swiotlb later using the slab allocator if needed.
 * This should be just like above, but with some error catching.
 */
int swiotlb_init_late(size_t size, gfp_t gfp_mask,
		int (*remap)(void *tlb, unsigned long nslabs))
{
	struct io_tlb_mem *mem = &io_tlb_default_mem;
	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
	unsigned char *vstart = NULL;
	unsigned int order, area_order;
	bool retried = false;
	int rc = 0;

	if (swiotlb_force_disable)
		return 0;

retry:
	order = get_order(nslabs << IO_TLB_SHIFT);
	nslabs = SLABS_PER_PAGE << order;

	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
		vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
						  order);
		if (vstart)
			break;
		order--;
		nslabs = SLABS_PER_PAGE << order;
		retried = true;
	}

	if (!vstart)
		return -ENOMEM;

	if (remap)
		rc = remap(vstart, nslabs);
	if (rc) {
		free_pages((unsigned long)vstart, order);

		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
		if (nslabs < IO_TLB_MIN_SLABS)
			return rc;
		retried = true;
		goto retry;
	}

	if (retried) {
		pr_warn("only able to allocate %ld MB\n",
			(PAGE_SIZE << order) >> 20);
	}

	if (!default_nareas)
		swiotlb_adjust_nareas(num_possible_cpus());

	area_order = get_order(array_size(sizeof(*mem->areas),
		default_nareas));
	mem->areas = (struct io_tlb_area *)
		__get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order);
	if (!mem->areas)
		goto error_area;

	mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
		get_order(array_size(sizeof(*mem->slots), nslabs)));
	if (!mem->slots)
		goto error_slots;

	set_memory_decrypted((unsigned long)vstart,
			     (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true,
				default_nareas);

	swiotlb_print_info();
	return 0;

error_slots:
	free_pages((unsigned long)mem->areas, area_order);
error_area:
	free_pages((unsigned long)vstart, order);
	return -ENOMEM;
}

void __init swiotlb_exit(void)
{
	struct io_tlb_mem *mem = &io_tlb_default_mem;
	unsigned long tbl_vaddr;
	size_t tbl_size, slots_size;
	unsigned int area_order;

	if (swiotlb_force_bounce)
		return;

	if (!mem->nslabs)
		return;

	pr_info("tearing down default memory pool\n");
	tbl_vaddr = (unsigned long)phys_to_virt(mem->start);
	tbl_size = PAGE_ALIGN(mem->end - mem->start);
	slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs));

	set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
	if (mem->late_alloc) {
		area_order = get_order(array_size(sizeof(*mem->areas),
			mem->nareas));
		free_pages((unsigned long)mem->areas, area_order);
		free_pages(tbl_vaddr, get_order(tbl_size));
		free_pages((unsigned long)mem->slots, get_order(slots_size));
	} else {
		memblock_free_late(__pa(mem->areas),
			array_size(sizeof(*mem->areas), mem->nareas));
		memblock_free_late(mem->start, tbl_size);
		memblock_free_late(__pa(mem->slots), slots_size);
	}

	memset(mem, 0, sizeof(*mem));
}

/*
 * Return the offset into a iotlb slot required to keep the device happy.
 */
static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
{
	return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
}

/*
 * Bounce: copy the swiotlb buffer from or back to the original dma location
 */
static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size,
			   enum dma_data_direction dir)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
	int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT;
	phys_addr_t orig_addr = mem->slots[index].orig_addr;
	size_t alloc_size = mem->slots[index].alloc_size;
	unsigned long pfn = PFN_DOWN(orig_addr);
	unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
	unsigned int tlb_offset, orig_addr_offset;

	if (orig_addr == INVALID_PHYS_ADDR)
		return;

	tlb_offset = tlb_addr & (IO_TLB_SIZE - 1);
	orig_addr_offset = swiotlb_align_offset(dev, orig_addr);
	if (tlb_offset < orig_addr_offset) {
		dev_WARN_ONCE(dev, 1,
			"Access before mapping start detected. orig offset %u, requested offset %u.\n",
			orig_addr_offset, tlb_offset);
		return;
	}

	tlb_offset -= orig_addr_offset;
	if (tlb_offset > alloc_size) {
		dev_WARN_ONCE(dev, 1,
			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n",
			alloc_size, size, tlb_offset);
		return;
	}

	orig_addr += tlb_offset;
	alloc_size -= tlb_offset;

	if (size > alloc_size) {
		dev_WARN_ONCE(dev, 1,
			"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n",
			alloc_size, size);
		size = alloc_size;
	}

	if (PageHighMem(pfn_to_page(pfn))) {
		unsigned int offset = orig_addr & ~PAGE_MASK;
		struct page *page;
		unsigned int sz = 0;
		unsigned long flags;

		while (size) {
			sz = min_t(size_t, PAGE_SIZE - offset, size);

			local_irq_save(flags);
			page = pfn_to_page(pfn);
			if (dir == DMA_TO_DEVICE)
				memcpy_from_page(vaddr, page, offset, sz);
			else
				memcpy_to_page(page, offset, vaddr, sz);
			local_irq_restore(flags);

			size -= sz;
			pfn++;
			vaddr += sz;
			offset = 0;
		}
	} else if (dir == DMA_TO_DEVICE) {
		memcpy(vaddr, phys_to_virt(orig_addr), size);
	} else {
		memcpy(phys_to_virt(orig_addr), vaddr, size);
	}
}

static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
{
	return start + (idx << IO_TLB_SHIFT);
}

/*
 * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
 */
static inline unsigned long get_max_slots(unsigned long boundary_mask)
{
	if (boundary_mask == ~0UL)
		return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
	return nr_slots(boundary_mask + 1);
}

static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index)
{
	if (index >= mem->area_nslabs)
		return 0;
	return index;
}

/*
 * Track the total used slots with a global atomic value in order to have
 * correct information to determine the high water mark. The mem_used()
 * function gives imprecise results because there's no locking across
 * multiple areas.
 */
#ifdef CONFIG_DEBUG_FS
static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
{
	unsigned long old_hiwater, new_used;

	new_used = atomic_long_add_return(nslots, &mem->total_used);
	old_hiwater = atomic_long_read(&mem->used_hiwater);
	do {
		if (new_used <= old_hiwater)
			break;
	} while (!atomic_long_try_cmpxchg(&mem->used_hiwater,
					  &old_hiwater, new_used));
}

static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
{
	atomic_long_sub(nslots, &mem->total_used);
}

#else /* !CONFIG_DEBUG_FS */
static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
{
}
static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
{
}
#endif /* CONFIG_DEBUG_FS */

/*
 * Find a suitable number of IO TLB entries size that will fit this request and
 * allocate a buffer from that IO TLB pool.
 */
static int swiotlb_do_find_slots(struct device *dev, int area_index,
		phys_addr_t orig_addr, size_t alloc_size,
		unsigned int alloc_align_mask)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
	struct io_tlb_area *area = mem->areas + area_index;
	unsigned long boundary_mask = dma_get_seg_boundary(dev);
	dma_addr_t tbl_dma_addr =
		phys_to_dma_unencrypted(dev, mem->start) & boundary_mask;
	unsigned long max_slots = get_max_slots(boundary_mask);
	unsigned int iotlb_align_mask =
		dma_get_min_align_mask(dev) | alloc_align_mask;
	unsigned int nslots = nr_slots(alloc_size), stride;
	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
	unsigned int index, slots_checked, count = 0, i;
	unsigned long flags;
	unsigned int slot_base;
	unsigned int slot_index;

	BUG_ON(!nslots);
	BUG_ON(area_index >= mem->nareas);

	/*
	 * For allocations of PAGE_SIZE or larger only look for page aligned
	 * allocations.
	 */
	if (alloc_size >= PAGE_SIZE)
		iotlb_align_mask |= ~PAGE_MASK;
	iotlb_align_mask &= ~(IO_TLB_SIZE - 1);

	/*
	 * For mappings with an alignment requirement don't bother looping to
	 * unaligned slots once we found an aligned one.
	 */
	stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;

	spin_lock_irqsave(&area->lock, flags);
	if (unlikely(nslots > mem->area_nslabs - area->used))
		goto not_found;

	slot_base = area_index * mem->area_nslabs;
	index = area->index;

	for (slots_checked = 0; slots_checked < mem->area_nslabs; ) {
		slot_index = slot_base + index;

		if (orig_addr &&
		    (slot_addr(tbl_dma_addr, slot_index) &
		     iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
			index = wrap_area_index(mem, index + 1);
			slots_checked++;
			continue;
		}

		/*
		 * If we find a slot that indicates we have 'nslots' number of
		 * contiguous buffers, we allocate the buffers from that slot
		 * and mark the entries as '0' indicating unavailable.
		 */
		if (!iommu_is_span_boundary(slot_index, nslots,
					    nr_slots(tbl_dma_addr),
					    max_slots)) {
			if (mem->slots[slot_index].list >= nslots)
				goto found;
		}
		index = wrap_area_index(mem, index + stride);
		slots_checked += stride;
	}

not_found:
	spin_unlock_irqrestore(&area->lock, flags);
	return -1;

found:
	for (i = slot_index; i < slot_index + nslots; i++) {
		mem->slots[i].list = 0;
		mem->slots[i].alloc_size = alloc_size - (offset +
				((i - slot_index) << IO_TLB_SHIFT));
	}
	for (i = slot_index - 1;
	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
	     mem->slots[i].list; i--)
		mem->slots[i].list = ++count;

	/*
	 * Update the indices to avoid searching in the next round.
	 */
	area->index = wrap_area_index(mem, index + nslots);
	area->used += nslots;
	spin_unlock_irqrestore(&area->lock, flags);

	inc_used_and_hiwater(mem, nslots);
	return slot_index;
}

static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
		size_t alloc_size, unsigned int alloc_align_mask)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
	int start = raw_smp_processor_id() & (mem->nareas - 1);
	int i = start, index;

	do {
		index = swiotlb_do_find_slots(dev, i, orig_addr, alloc_size,
					      alloc_align_mask);
		if (index >= 0)
			return index;
		if (++i >= mem->nareas)
			i = 0;
	} while (i != start);

	return -1;
}

static unsigned long mem_used(struct io_tlb_mem *mem)
{
	int i;
	unsigned long used = 0;

	for (i = 0; i < mem->nareas; i++)
		used += mem->areas[i].used;
	return used;
}

phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
		size_t mapping_size, size_t alloc_size,
		unsigned int alloc_align_mask, enum dma_data_direction dir,
		unsigned long attrs)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
	unsigned int offset = swiotlb_align_offset(dev, orig_addr);
	unsigned int i;
	int index;
	phys_addr_t tlb_addr;

	if (!mem || !mem->nslabs) {
		dev_warn_ratelimited(dev,
			"Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
		return (phys_addr_t)DMA_MAPPING_ERROR;
	}

	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
		pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");

	if (mapping_size > alloc_size) {
		dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
			      mapping_size, alloc_size);
		return (phys_addr_t)DMA_MAPPING_ERROR;
	}

	index = swiotlb_find_slots(dev, orig_addr,
				   alloc_size + offset, alloc_align_mask);
	if (index == -1) {
		if (!(attrs & DMA_ATTR_NO_WARN))
			dev_warn_ratelimited(dev,
	"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
				 alloc_size, mem->nslabs, mem_used(mem));
		return (phys_addr_t)DMA_MAPPING_ERROR;
	}

	/*
	 * Save away the mapping from the original address to the DMA address.
	 * This is needed when we sync the memory.  Then we sync the buffer if
	 * needed.
	 */
	for (i = 0; i < nr_slots(alloc_size + offset); i++)
		mem->slots[index + i].orig_addr = slot_addr(orig_addr, i);
	tlb_addr = slot_addr(mem->start, index) + offset;
	/*
	 * When dir == DMA_FROM_DEVICE we could omit the copy from the orig
	 * to the tlb buffer, if we knew for sure the device will
	 * overwrite the entire current content. But we don't. Thus
	 * unconditional bounce may prevent leaking swiotlb content (i.e.
	 * kernel memory) to user-space.
	 */
	swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
	return tlb_addr;
}

static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
	unsigned long flags;
	unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
	int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
	int nslots = nr_slots(mem->slots[index].alloc_size + offset);
	int aindex = index / mem->area_nslabs;
	struct io_tlb_area *area = &mem->areas[aindex];
	int count, i;

	/*
	 * Return the buffer to the free list by setting the corresponding
	 * entries to indicate the number of contiguous entries available.
	 * While returning the entries to the free list, we merge the entries
	 * with slots below and above the pool being returned.
	 */
	BUG_ON(aindex >= mem->nareas);

	spin_lock_irqsave(&area->lock, flags);
	if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
		count = mem->slots[index + nslots].list;
	else
		count = 0;

	/*
	 * Step 1: return the slots to the free list, merging the slots with
	 * superceeding slots
	 */
	for (i = index + nslots - 1; i >= index; i--) {
		mem->slots[i].list = ++count;
		mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
		mem->slots[i].alloc_size = 0;
	}

	/*
	 * Step 2: merge the returned slots with the preceding slots, if
	 * available (non zero)
	 */
	for (i = index - 1;
	     io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list;
	     i--)
		mem->slots[i].list = ++count;
	area->used -= nslots;
	spin_unlock_irqrestore(&area->lock, flags);

	dec_used(mem, nslots);
}

/*
 * tlb_addr is the physical address of the bounce buffer to unmap.
 */
void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr,
			      size_t mapping_size, enum dma_data_direction dir,
			      unsigned long attrs)
{
	/*
	 * First, sync the memory before unmapping the entry
	 */
	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
	    (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
		swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_FROM_DEVICE);

	swiotlb_release_slots(dev, tlb_addr);
}

void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr,
		size_t size, enum dma_data_direction dir)
{
	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
		swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE);
	else
		BUG_ON(dir != DMA_FROM_DEVICE);
}

void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr,
		size_t size, enum dma_data_direction dir)
{
	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
		swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE);
	else
		BUG_ON(dir != DMA_TO_DEVICE);
}

/*
 * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
 * to the device copy the data into it as well.
 */
dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
		enum dma_data_direction dir, unsigned long attrs)
{
	phys_addr_t swiotlb_addr;
	dma_addr_t dma_addr;

	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size);

	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
			attrs);
	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
		return DMA_MAPPING_ERROR;

	/* Ensure that the address returned is DMA'ble */
	dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir,
			attrs | DMA_ATTR_SKIP_CPU_SYNC);
		dev_WARN_ONCE(dev, 1,
			"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
		return DMA_MAPPING_ERROR;
	}

	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
		arch_sync_dma_for_device(swiotlb_addr, size, dir);
	return dma_addr;
}

size_t swiotlb_max_mapping_size(struct device *dev)
{
	int min_align_mask = dma_get_min_align_mask(dev);
	int min_align = 0;

	/*
	 * swiotlb_find_slots() skips slots according to
	 * min align mask. This affects max mapping size.
	 * Take it into acount here.
	 */
	if (min_align_mask)
		min_align = roundup(min_align_mask, IO_TLB_SIZE);

	return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align;
}

bool is_swiotlb_active(struct device *dev)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;

	return mem && mem->nslabs;
}
EXPORT_SYMBOL_GPL(is_swiotlb_active);

#ifdef CONFIG_DEBUG_FS

static int io_tlb_used_get(void *data, u64 *val)
{
	struct io_tlb_mem *mem = data;

	*val = mem_used(mem);
	return 0;
}

static int io_tlb_hiwater_get(void *data, u64 *val)
{
	struct io_tlb_mem *mem = data;

	*val = atomic_long_read(&mem->used_hiwater);
	return 0;
}

static int io_tlb_hiwater_set(void *data, u64 val)
{
	struct io_tlb_mem *mem = data;

	/* Only allow setting to zero */
	if (val != 0)
		return -EINVAL;

	atomic_long_set(&mem->used_hiwater, val);
	return 0;
}

DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n");
DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get,
				io_tlb_hiwater_set, "%llu\n");

static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
					 const char *dirname)
{
	atomic_long_set(&mem->total_used, 0);
	atomic_long_set(&mem->used_hiwater, 0);

	mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
	if (!mem->nslabs)
		return;

	debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
	debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem,
			&fops_io_tlb_used);
	debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
			&fops_io_tlb_hiwater);
}

static int __init swiotlb_create_default_debugfs(void)
{
	swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb");
	return 0;
}

late_initcall(swiotlb_create_default_debugfs);

#else  /* !CONFIG_DEBUG_FS */

static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
						const char *dirname)
{
}

#endif	/* CONFIG_DEBUG_FS */

#ifdef CONFIG_DMA_RESTRICTED_POOL

struct page *swiotlb_alloc(struct device *dev, size_t size)
{
	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
	phys_addr_t tlb_addr;
	int index;

	if (!mem)
		return NULL;

	index = swiotlb_find_slots(dev, 0, size, 0);
	if (index == -1)
		return NULL;

	tlb_addr = slot_addr(mem->start, index);

	return pfn_to_page(PFN_DOWN(tlb_addr));
}

bool swiotlb_free(struct device *dev, struct page *page, size_t size)
{
	phys_addr_t tlb_addr = page_to_phys(page);

	if (!is_swiotlb_buffer(dev, tlb_addr))
		return false;

	swiotlb_release_slots(dev, tlb_addr);

	return true;
}

static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
				    struct device *dev)
{
	struct io_tlb_mem *mem = rmem->priv;
	unsigned long nslabs = rmem->size >> IO_TLB_SHIFT;

	/* Set Per-device io tlb area to one */
	unsigned int nareas = 1;

	if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) {
		dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping.");
		return -EINVAL;
	}

	/*
	 * Since multiple devices can share the same pool, the private data,
	 * io_tlb_mem struct, will be initialized by the first device attached
	 * to it.
	 */
	if (!mem) {
		mem = kzalloc(sizeof(*mem), GFP_KERNEL);
		if (!mem)
			return -ENOMEM;

		mem->slots = kcalloc(nslabs, sizeof(*mem->slots), GFP_KERNEL);
		if (!mem->slots) {
			kfree(mem);
			return -ENOMEM;
		}

		mem->areas = kcalloc(nareas, sizeof(*mem->areas),
				GFP_KERNEL);
		if (!mem->areas) {
			kfree(mem->slots);
			kfree(mem);
			return -ENOMEM;
		}

		set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
				     rmem->size >> PAGE_SHIFT);
		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE,
					false, nareas);
		mem->for_alloc = true;

		rmem->priv = mem;

		swiotlb_create_debugfs_files(mem, rmem->name);
	}

	dev->dma_io_tlb_mem = mem;

	return 0;
}

static void rmem_swiotlb_device_release(struct reserved_mem *rmem,
					struct device *dev)
{
	dev->dma_io_tlb_mem = &io_tlb_default_mem;
}

static const struct reserved_mem_ops rmem_swiotlb_ops = {
	.device_init = rmem_swiotlb_device_init,
	.device_release = rmem_swiotlb_device_release,
};

static int __init rmem_swiotlb_setup(struct reserved_mem *rmem)
{
	unsigned long node = rmem->fdt_node;

	if (of_get_flat_dt_prop(node, "reusable", NULL) ||
	    of_get_flat_dt_prop(node, "linux,cma-default", NULL) ||
	    of_get_flat_dt_prop(node, "linux,dma-default", NULL) ||
	    of_get_flat_dt_prop(node, "no-map", NULL))
		return -EINVAL;

	rmem->ops = &rmem_swiotlb_ops;
	pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n",
		&rmem->base, (unsigned long)rmem->size / SZ_1M);
	return 0;
}

RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", rmem_swiotlb_setup);
#endif /* CONFIG_DMA_RESTRICTED_POOL */