summaryrefslogtreecommitdiffstats
path: root/drivers/iommu/dma-iommu.c
blob: 60c7e9e9901e90767ce82e055e2c2ffd9b80b7ff (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
/*
 * A fairly generic DMA-API to IOMMU-API glue layer.
 *
 * Copyright (C) 2014-2015 ARM Ltd.
 *
 * based in part on arch/arm/mm/dma-mapping.c:
 * Copyright (C) 2000-2004 Russell King
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/acpi_iort.h>
#include <linux/device.h>
#include <linux/dma-iommu.h>
#include <linux/gfp.h>
#include <linux/huge_mm.h>
#include <linux/iommu.h>
#include <linux/iova.h>
#include <linux/irq.h>
#include <linux/mm.h>
#include <linux/pci.h>
#include <linux/scatterlist.h>
#include <linux/vmalloc.h>

struct iommu_dma_msi_page {
	struct list_head	list;
	dma_addr_t		iova;
	phys_addr_t		phys;
};

enum iommu_dma_cookie_type {
	IOMMU_DMA_IOVA_COOKIE,
	IOMMU_DMA_MSI_COOKIE,
};

struct iommu_dma_cookie {
	enum iommu_dma_cookie_type	type;
	union {
		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
		struct iova_domain	iovad;
		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
		dma_addr_t		msi_iova;
	};
	struct list_head		msi_page_list;
	spinlock_t			msi_lock;

	/* Domain for flush queue callback; NULL if flush queue not in use */
	struct iommu_domain		*fq_domain;
};

static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
{
	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
		return cookie->iovad.granule;
	return PAGE_SIZE;
}

static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
{
	struct iommu_dma_cookie *cookie;

	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
	if (cookie) {
		spin_lock_init(&cookie->msi_lock);
		INIT_LIST_HEAD(&cookie->msi_page_list);
		cookie->type = type;
	}
	return cookie;
}

int iommu_dma_init(void)
{
	return iova_cache_get();
}

/**
 * iommu_get_dma_cookie - Acquire DMA-API resources for a domain
 * @domain: IOMMU domain to prepare for DMA-API usage
 *
 * IOMMU drivers should normally call this from their domain_alloc
 * callback when domain->type == IOMMU_DOMAIN_DMA.
 */
int iommu_get_dma_cookie(struct iommu_domain *domain)
{
	if (domain->iova_cookie)
		return -EEXIST;

	domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
	if (!domain->iova_cookie)
		return -ENOMEM;

	return 0;
}
EXPORT_SYMBOL(iommu_get_dma_cookie);

/**
 * iommu_get_msi_cookie - Acquire just MSI remapping resources
 * @domain: IOMMU domain to prepare
 * @base: Start address of IOVA region for MSI mappings
 *
 * Users who manage their own IOVA allocation and do not want DMA API support,
 * but would still like to take advantage of automatic MSI remapping, can use
 * this to initialise their own domain appropriately. Users should reserve a
 * contiguous IOVA region, starting at @base, large enough to accommodate the
 * number of PAGE_SIZE mappings necessary to cover every MSI doorbell address
 * used by the devices attached to @domain.
 */
int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
{
	struct iommu_dma_cookie *cookie;

	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
		return -EINVAL;

	if (domain->iova_cookie)
		return -EEXIST;

	cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
	if (!cookie)
		return -ENOMEM;

	cookie->msi_iova = base;
	domain->iova_cookie = cookie;
	return 0;
}
EXPORT_SYMBOL(iommu_get_msi_cookie);

/**
 * iommu_put_dma_cookie - Release a domain's DMA mapping resources
 * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
 *          iommu_get_msi_cookie()
 *
 * IOMMU drivers should normally call this from their domain_free callback.
 */
void iommu_put_dma_cookie(struct iommu_domain *domain)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iommu_dma_msi_page *msi, *tmp;

	if (!cookie)
		return;

	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
		put_iova_domain(&cookie->iovad);

	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
		list_del(&msi->list);
		kfree(msi);
	}
	kfree(cookie);
	domain->iova_cookie = NULL;
}
EXPORT_SYMBOL(iommu_put_dma_cookie);

/**
 * iommu_dma_get_resv_regions - Reserved region driver helper
 * @dev: Device from iommu_get_resv_regions()
 * @list: Reserved region list from iommu_get_resv_regions()
 *
 * IOMMU drivers can use this to implement their .get_resv_regions callback
 * for general non-IOMMU-specific reservations. Currently, this covers GICv3
 * ITS region reservation on ACPI based ARM platforms that may require HW MSI
 * reservation.
 */
void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
{

	if (!is_of_node(dev->iommu_fwspec->iommu_fwnode))
		iort_iommu_msi_get_resv_regions(dev, list);

}
EXPORT_SYMBOL(iommu_dma_get_resv_regions);

static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
		phys_addr_t start, phys_addr_t end)
{
	struct iova_domain *iovad = &cookie->iovad;
	struct iommu_dma_msi_page *msi_page;
	int i, num_pages;

	start -= iova_offset(iovad, start);
	num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);

	msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL);
	if (!msi_page)
		return -ENOMEM;

	for (i = 0; i < num_pages; i++) {
		msi_page[i].phys = start;
		msi_page[i].iova = start;
		INIT_LIST_HEAD(&msi_page[i].list);
		list_add(&msi_page[i].list, &cookie->msi_page_list);
		start += iovad->granule;
	}

	return 0;
}

static void iova_reserve_pci_windows(struct pci_dev *dev,
		struct iova_domain *iovad)
{
	struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
	struct resource_entry *window;
	unsigned long lo, hi;

	resource_list_for_each_entry(window, &bridge->windows) {
		if (resource_type(window->res) != IORESOURCE_MEM)
			continue;

		lo = iova_pfn(iovad, window->res->start - window->offset);
		hi = iova_pfn(iovad, window->res->end - window->offset);
		reserve_iova(iovad, lo, hi);
	}
}

static int iova_reserve_iommu_regions(struct device *dev,
		struct iommu_domain *domain)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iova_domain *iovad = &cookie->iovad;
	struct iommu_resv_region *region;
	LIST_HEAD(resv_regions);
	int ret = 0;

	if (dev_is_pci(dev))
		iova_reserve_pci_windows(to_pci_dev(dev), iovad);

	iommu_get_resv_regions(dev, &resv_regions);
	list_for_each_entry(region, &resv_regions, list) {
		unsigned long lo, hi;

		/* We ARE the software that manages these! */
		if (region->type == IOMMU_RESV_SW_MSI)
			continue;

		lo = iova_pfn(iovad, region->start);
		hi = iova_pfn(iovad, region->start + region->length - 1);
		reserve_iova(iovad, lo, hi);

		if (region->type == IOMMU_RESV_MSI)
			ret = cookie_init_hw_msi_region(cookie, region->start,
					region->start + region->length);
		if (ret)
			break;
	}
	iommu_put_resv_regions(dev, &resv_regions);

	return ret;
}

static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad)
{
	struct iommu_dma_cookie *cookie;
	struct iommu_domain *domain;

	cookie = container_of(iovad, struct iommu_dma_cookie, iovad);
	domain = cookie->fq_domain;
	/*
	 * The IOMMU driver supporting DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE
	 * implies that ops->flush_iotlb_all must be non-NULL.
	 */
	domain->ops->flush_iotlb_all(domain);
}

/**
 * iommu_dma_init_domain - Initialise a DMA mapping domain
 * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
 * @base: IOVA at which the mappable address space starts
 * @size: Size of IOVA space
 * @dev: Device the domain is being initialised for
 *
 * @base and @size should be exact multiples of IOMMU page granularity to
 * avoid rounding surprises. If necessary, we reserve the page at address 0
 * to ensure it is an invalid IOVA. It is safe to reinitialise a domain, but
 * any change which could make prior IOVAs invalid will fail.
 */
int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
		u64 size, struct device *dev)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iova_domain *iovad = &cookie->iovad;
	unsigned long order, base_pfn, end_pfn;
	int attr;

	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
		return -EINVAL;

	/* Use the smallest supported page size for IOVA granularity */
	order = __ffs(domain->pgsize_bitmap);
	base_pfn = max_t(unsigned long, 1, base >> order);
	end_pfn = (base + size - 1) >> order;

	/* Check the domain allows at least some access to the device... */
	if (domain->geometry.force_aperture) {
		if (base > domain->geometry.aperture_end ||
		    base + size <= domain->geometry.aperture_start) {
			pr_warn("specified DMA range outside IOMMU capability\n");
			return -EFAULT;
		}
		/* ...then finally give it a kicking to make sure it fits */
		base_pfn = max_t(unsigned long, base_pfn,
				domain->geometry.aperture_start >> order);
	}

	/* start_pfn is always nonzero for an already-initialised domain */
	if (iovad->start_pfn) {
		if (1UL << order != iovad->granule ||
		    base_pfn != iovad->start_pfn) {
			pr_warn("Incompatible range for DMA domain\n");
			return -EFAULT;
		}

		return 0;
	}

	init_iova_domain(iovad, 1UL << order, base_pfn);

	if (!cookie->fq_domain && !iommu_domain_get_attr(domain,
			DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) {
		cookie->fq_domain = domain;
		init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, NULL);
	}

	if (!dev)
		return 0;

	return iova_reserve_iommu_regions(dev, domain);
}
EXPORT_SYMBOL(iommu_dma_init_domain);

/**
 * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
 *                    page flags.
 * @dir: Direction of DMA transfer
 * @coherent: Is the DMA master cache-coherent?
 * @attrs: DMA attributes for the mapping
 *
 * Return: corresponding IOMMU API page protection flags
 */
int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
		     unsigned long attrs)
{
	int prot = coherent ? IOMMU_CACHE : 0;

	if (attrs & DMA_ATTR_PRIVILEGED)
		prot |= IOMMU_PRIV;

	switch (dir) {
	case DMA_BIDIRECTIONAL:
		return prot | IOMMU_READ | IOMMU_WRITE;
	case DMA_TO_DEVICE:
		return prot | IOMMU_READ;
	case DMA_FROM_DEVICE:
		return prot | IOMMU_WRITE;
	default:
		return 0;
	}
}

static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
		size_t size, dma_addr_t dma_limit, struct device *dev)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iova_domain *iovad = &cookie->iovad;
	unsigned long shift, iova_len, iova = 0;

	if (cookie->type == IOMMU_DMA_MSI_COOKIE) {
		cookie->msi_iova += size;
		return cookie->msi_iova - size;
	}

	shift = iova_shift(iovad);
	iova_len = size >> shift;
	/*
	 * Freeing non-power-of-two-sized allocations back into the IOVA caches
	 * will come back to bite us badly, so we have to waste a bit of space
	 * rounding up anything cacheable to make sure that can't happen. The
	 * order of the unadjusted size will still match upon freeing.
	 */
	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
		iova_len = roundup_pow_of_two(iova_len);

	if (dev->bus_dma_mask)
		dma_limit &= dev->bus_dma_mask;

	if (domain->geometry.force_aperture)
		dma_limit = min(dma_limit, domain->geometry.aperture_end);

	/* Try to get PCI devices a SAC address */
	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
		iova = alloc_iova_fast(iovad, iova_len,
				       DMA_BIT_MASK(32) >> shift, false);

	if (!iova)
		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
				       true);

	return (dma_addr_t)iova << shift;
}

static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
		dma_addr_t iova, size_t size)
{
	struct iova_domain *iovad = &cookie->iovad;

	/* The MSI case is only ever cleaning up its most recent allocation */
	if (cookie->type == IOMMU_DMA_MSI_COOKIE)
		cookie->msi_iova -= size;
	else if (cookie->fq_domain)	/* non-strict mode */
		queue_iova(iovad, iova_pfn(iovad, iova),
				size >> iova_shift(iovad), 0);
	else
		free_iova_fast(iovad, iova_pfn(iovad, iova),
				size >> iova_shift(iovad));
}

static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr,
		size_t size)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iova_domain *iovad = &cookie->iovad;
	size_t iova_off = iova_offset(iovad, dma_addr);

	dma_addr -= iova_off;
	size = iova_align(iovad, size + iova_off);

	WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size);
	if (!cookie->fq_domain)
		iommu_tlb_sync(domain);
	iommu_dma_free_iova(cookie, dma_addr, size);
}

static void __iommu_dma_free_pages(struct page **pages, int count)
{
	while (count--)
		__free_page(pages[count]);
	kvfree(pages);
}

static struct page **__iommu_dma_alloc_pages(unsigned int count,
		unsigned long order_mask, gfp_t gfp)
{
	struct page **pages;
	unsigned int i = 0, array_size = count * sizeof(*pages);

	order_mask &= (2U << MAX_ORDER) - 1;
	if (!order_mask)
		return NULL;

	if (array_size <= PAGE_SIZE)
		pages = kzalloc(array_size, GFP_KERNEL);
	else
		pages = vzalloc(array_size);
	if (!pages)
		return NULL;

	/* IOMMU can map any pages, so himem can also be used here */
	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;

	while (count) {
		struct page *page = NULL;
		unsigned int order_size;

		/*
		 * Higher-order allocations are a convenience rather
		 * than a necessity, hence using __GFP_NORETRY until
		 * falling back to minimum-order allocations.
		 */
		for (order_mask &= (2U << __fls(count)) - 1;
		     order_mask; order_mask &= ~order_size) {
			unsigned int order = __fls(order_mask);

			order_size = 1U << order;
			page = alloc_pages((order_mask - order_size) ?
					   gfp | __GFP_NORETRY : gfp, order);
			if (!page)
				continue;
			if (!order)
				break;
			if (!PageCompound(page)) {
				split_page(page, order);
				break;
			} else if (!split_huge_page(page)) {
				break;
			}
			__free_pages(page, order);
		}
		if (!page) {
			__iommu_dma_free_pages(pages, i);
			return NULL;
		}
		count -= order_size;
		while (order_size--)
			pages[i++] = page++;
	}
	return pages;
}

/**
 * iommu_dma_free - Free a buffer allocated by iommu_dma_alloc()
 * @dev: Device which owns this buffer
 * @pages: Array of buffer pages as returned by iommu_dma_alloc()
 * @size: Size of buffer in bytes
 * @handle: DMA address of buffer
 *
 * Frees both the pages associated with the buffer, and the array
 * describing them
 */
void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
		dma_addr_t *handle)
{
	__iommu_dma_unmap(iommu_get_dma_domain(dev), *handle, size);
	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
	*handle = DMA_MAPPING_ERROR;
}

/**
 * iommu_dma_alloc - Allocate and map a buffer contiguous in IOVA space
 * @dev: Device to allocate memory for. Must be a real device
 *	 attached to an iommu_dma_domain
 * @size: Size of buffer in bytes
 * @gfp: Allocation flags
 * @attrs: DMA attributes for this allocation
 * @prot: IOMMU mapping flags
 * @handle: Out argument for allocated DMA handle
 * @flush_page: Arch callback which must ensure PAGE_SIZE bytes from the
 *		given VA/PA are visible to the given non-coherent device.
 *
 * If @size is less than PAGE_SIZE, then a full CPU page will be allocated,
 * but an IOMMU which supports smaller pages might not map the whole thing.
 *
 * Return: Array of struct page pointers describing the buffer,
 *	   or NULL on failure.
 */
struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
		unsigned long attrs, int prot, dma_addr_t *handle,
		void (*flush_page)(struct device *, const void *, phys_addr_t))
{
	struct iommu_domain *domain = iommu_get_dma_domain(dev);
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iova_domain *iovad = &cookie->iovad;
	struct page **pages;
	struct sg_table sgt;
	dma_addr_t iova;
	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;

	*handle = DMA_MAPPING_ERROR;

	min_size = alloc_sizes & -alloc_sizes;
	if (min_size < PAGE_SIZE) {
		min_size = PAGE_SIZE;
		alloc_sizes |= PAGE_SIZE;
	} else {
		size = ALIGN(size, min_size);
	}
	if (attrs & DMA_ATTR_ALLOC_SINGLE_PAGES)
		alloc_sizes = min_size;

	count = PAGE_ALIGN(size) >> PAGE_SHIFT;
	pages = __iommu_dma_alloc_pages(count, alloc_sizes >> PAGE_SHIFT, gfp);
	if (!pages)
		return NULL;

	size = iova_align(iovad, size);
	iova = iommu_dma_alloc_iova(domain, size, dev->coherent_dma_mask, dev);
	if (!iova)
		goto out_free_pages;

	if (sg_alloc_table_from_pages(&sgt, pages, count, 0, size, GFP_KERNEL))
		goto out_free_iova;

	if (!(prot & IOMMU_CACHE)) {
		struct sg_mapping_iter miter;
		/*
		 * The CPU-centric flushing implied by SG_MITER_TO_SG isn't
		 * sufficient here, so skip it by using the "wrong" direction.
		 */
		sg_miter_start(&miter, sgt.sgl, sgt.orig_nents, SG_MITER_FROM_SG);
		while (sg_miter_next(&miter))
			flush_page(dev, miter.addr, page_to_phys(miter.page));
		sg_miter_stop(&miter);
	}

	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, prot)
			< size)
		goto out_free_sg;

	*handle = iova;
	sg_free_table(&sgt);
	return pages;

out_free_sg:
	sg_free_table(&sgt);
out_free_iova:
	iommu_dma_free_iova(cookie, iova, size);
out_free_pages:
	__iommu_dma_free_pages(pages, count);
	return NULL;
}

/**
 * iommu_dma_mmap - Map a buffer into provided user VMA
 * @pages: Array representing buffer from iommu_dma_alloc()
 * @size: Size of buffer in bytes
 * @vma: VMA describing requested userspace mapping
 *
 * Maps the pages of the buffer in @pages into @vma. The caller is responsible
 * for verifying the correct size and protection of @vma beforehand.
 */

int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma)
{
	unsigned long uaddr = vma->vm_start;
	unsigned int i, count = PAGE_ALIGN(size) >> PAGE_SHIFT;
	int ret = -ENXIO;

	for (i = vma->vm_pgoff; i < count && uaddr < vma->vm_end; i++) {
		ret = vm_insert_page(vma, uaddr, pages[i]);
		if (ret)
			break;
		uaddr += PAGE_SIZE;
	}
	return ret;
}

static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
		size_t size, int prot, struct iommu_domain *domain)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	size_t iova_off = 0;
	dma_addr_t iova;

	if (cookie->type == IOMMU_DMA_IOVA_COOKIE) {
		iova_off = iova_offset(&cookie->iovad, phys);
		size = iova_align(&cookie->iovad, size + iova_off);
	}

	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
	if (!iova)
		return DMA_MAPPING_ERROR;

	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
		iommu_dma_free_iova(cookie, iova, size);
		return DMA_MAPPING_ERROR;
	}
	return iova + iova_off;
}

dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
		unsigned long offset, size_t size, int prot)
{
	return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot,
			iommu_get_dma_domain(dev));
}

void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
		enum dma_data_direction dir, unsigned long attrs)
{
	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
}

/*
 * Prepare a successfully-mapped scatterlist to give back to the caller.
 *
 * At this point the segments are already laid out by iommu_dma_map_sg() to
 * avoid individually crossing any boundaries, so we merely need to check a
 * segment's start address to avoid concatenating across one.
 */
static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
		dma_addr_t dma_addr)
{
	struct scatterlist *s, *cur = sg;
	unsigned long seg_mask = dma_get_seg_boundary(dev);
	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
	int i, count = 0;

	for_each_sg(sg, s, nents, i) {
		/* Restore this segment's original unaligned fields first */
		unsigned int s_iova_off = sg_dma_address(s);
		unsigned int s_length = sg_dma_len(s);
		unsigned int s_iova_len = s->length;

		s->offset += s_iova_off;
		s->length = s_length;
		sg_dma_address(s) = DMA_MAPPING_ERROR;
		sg_dma_len(s) = 0;

		/*
		 * Now fill in the real DMA data. If...
		 * - there is a valid output segment to append to
		 * - and this segment starts on an IOVA page boundary
		 * - but doesn't fall at a segment boundary
		 * - and wouldn't make the resulting output segment too long
		 */
		if (cur_len && !s_iova_off && (dma_addr & seg_mask) &&
		    (cur_len + s_length <= max_len)) {
			/* ...then concatenate it with the previous one */
			cur_len += s_length;
		} else {
			/* Otherwise start the next output segment */
			if (i > 0)
				cur = sg_next(cur);
			cur_len = s_length;
			count++;

			sg_dma_address(cur) = dma_addr + s_iova_off;
		}

		sg_dma_len(cur) = cur_len;
		dma_addr += s_iova_len;

		if (s_length + s_iova_off < s_iova_len)
			cur_len = 0;
	}
	return count;
}

/*
 * If mapping failed, then just restore the original list,
 * but making sure the DMA fields are invalidated.
 */
static void __invalidate_sg(struct scatterlist *sg, int nents)
{
	struct scatterlist *s;
	int i;

	for_each_sg(sg, s, nents, i) {
		if (sg_dma_address(s) != DMA_MAPPING_ERROR)
			s->offset += sg_dma_address(s);
		if (sg_dma_len(s))
			s->length = sg_dma_len(s);
		sg_dma_address(s) = DMA_MAPPING_ERROR;
		sg_dma_len(s) = 0;
	}
}

/*
 * The DMA API client is passing in a scatterlist which could describe
 * any old buffer layout, but the IOMMU API requires everything to be
 * aligned to IOMMU pages. Hence the need for this complicated bit of
 * impedance-matching, to be able to hand off a suitably-aligned list,
 * but still preserve the original offsets and sizes for the caller.
 */
int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
		int nents, int prot)
{
	struct iommu_domain *domain = iommu_get_dma_domain(dev);
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iova_domain *iovad = &cookie->iovad;
	struct scatterlist *s, *prev = NULL;
	dma_addr_t iova;
	size_t iova_len = 0;
	unsigned long mask = dma_get_seg_boundary(dev);
	int i;

	/*
	 * Work out how much IOVA space we need, and align the segments to
	 * IOVA granules for the IOMMU driver to handle. With some clever
	 * trickery we can modify the list in-place, but reversibly, by
	 * stashing the unaligned parts in the as-yet-unused DMA fields.
	 */
	for_each_sg(sg, s, nents, i) {
		size_t s_iova_off = iova_offset(iovad, s->offset);
		size_t s_length = s->length;
		size_t pad_len = (mask - iova_len + 1) & mask;

		sg_dma_address(s) = s_iova_off;
		sg_dma_len(s) = s_length;
		s->offset -= s_iova_off;
		s_length = iova_align(iovad, s_length + s_iova_off);
		s->length = s_length;

		/*
		 * Due to the alignment of our single IOVA allocation, we can
		 * depend on these assumptions about the segment boundary mask:
		 * - If mask size >= IOVA size, then the IOVA range cannot
		 *   possibly fall across a boundary, so we don't care.
		 * - If mask size < IOVA size, then the IOVA range must start
		 *   exactly on a boundary, therefore we can lay things out
		 *   based purely on segment lengths without needing to know
		 *   the actual addresses beforehand.
		 * - The mask must be a power of 2, so pad_len == 0 if
		 *   iova_len == 0, thus we cannot dereference prev the first
		 *   time through here (i.e. before it has a meaningful value).
		 */
		if (pad_len && pad_len < s_length - 1) {
			prev->length += pad_len;
			iova_len += pad_len;
		}

		iova_len += s_length;
		prev = s;
	}

	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
	if (!iova)
		goto out_restore_sg;

	/*
	 * We'll leave any physical concatenation to the IOMMU driver's
	 * implementation - it knows better than we do.
	 */
	if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len)
		goto out_free_iova;

	return __finalise_sg(dev, sg, nents, iova);

out_free_iova:
	iommu_dma_free_iova(cookie, iova, iova_len);
out_restore_sg:
	__invalidate_sg(sg, nents);
	return 0;
}

void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
		enum dma_data_direction dir, unsigned long attrs)
{
	dma_addr_t start, end;
	struct scatterlist *tmp;
	int i;
	/*
	 * The scatterlist segments are mapped into a single
	 * contiguous IOVA allocation, so this is incredibly easy.
	 */
	start = sg_dma_address(sg);
	for_each_sg(sg_next(sg), tmp, nents - 1, i) {
		if (sg_dma_len(tmp) == 0)
			break;
		sg = tmp;
	}
	end = sg_dma_address(sg) + sg_dma_len(sg);
	__iommu_dma_unmap(iommu_get_dma_domain(dev), start, end - start);
}

dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
		size_t size, enum dma_data_direction dir, unsigned long attrs)
{
	return __iommu_dma_map(dev, phys, size,
			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
			iommu_get_dma_domain(dev));
}

void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
		size_t size, enum dma_data_direction dir, unsigned long attrs)
{
	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
}

static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
		phys_addr_t msi_addr, struct iommu_domain *domain)
{
	struct iommu_dma_cookie *cookie = domain->iova_cookie;
	struct iommu_dma_msi_page *msi_page;
	dma_addr_t iova;
	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
	size_t size = cookie_msi_granule(cookie);

	msi_addr &= ~(phys_addr_t)(size - 1);
	list_for_each_entry(msi_page, &cookie->msi_page_list, list)
		if (msi_page->phys == msi_addr)
			return msi_page;

	msi_page = kzalloc(sizeof(*msi_page), GFP_ATOMIC);
	if (!msi_page)
		return NULL;

	iova = __iommu_dma_map(dev, msi_addr, size, prot, domain);
	if (iova == DMA_MAPPING_ERROR)
		goto out_free_page;

	INIT_LIST_HEAD(&msi_page->list);
	msi_page->phys = msi_addr;
	msi_page->iova = iova;
	list_add(&msi_page->list, &cookie->msi_page_list);
	return msi_page;

out_free_page:
	kfree(msi_page);
	return NULL;
}

void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
{
	struct device *dev = msi_desc_to_dev(irq_get_msi_desc(irq));
	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
	struct iommu_dma_cookie *cookie;
	struct iommu_dma_msi_page *msi_page;
	phys_addr_t msi_addr = (u64)msg->address_hi << 32 | msg->address_lo;
	unsigned long flags;

	if (!domain || !domain->iova_cookie)
		return;

	cookie = domain->iova_cookie;

	/*
	 * We disable IRQs to rule out a possible inversion against
	 * irq_desc_lock if, say, someone tries to retarget the affinity
	 * of an MSI from within an IPI handler.
	 */
	spin_lock_irqsave(&cookie->msi_lock, flags);
	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
	spin_unlock_irqrestore(&cookie->msi_lock, flags);

	if (WARN_ON(!msi_page)) {
		/*
		 * We're called from a void callback, so the best we can do is
		 * 'fail' by filling the message with obviously bogus values.
		 * Since we got this far due to an IOMMU being present, it's
		 * not like the existing address would have worked anyway...
		 */
		msg->address_hi = ~0U;
		msg->address_lo = ~0U;
		msg->data = ~0U;
	} else {
		msg->address_hi = upper_32_bits(msi_page->iova);
		msg->address_lo &= cookie_msi_granule(cookie) - 1;
		msg->address_lo += lower_32_bits(msi_page->iova);
	}
}