summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/dma-mapping.c
blob: c566ec83719f6bb07fe909f02900a8ab885698de (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
/*
 * SWIOTLB-based DMA API implementation
 *
 * Copyright (C) 2012 ARM Ltd.
 * Author: Catalin Marinas <catalin.marinas@arm.com>
 *
 * 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/gfp.h>
#include <linux/acpi.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/genalloc.h>
#include <linux/dma-mapping.h>
#include <linux/dma-contiguous.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>

#include <asm/cacheflush.h>

static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
				 bool coherent)
{
	if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
		return pgprot_writecombine(prot);
	return prot;
}

static struct gen_pool *atomic_pool;

#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;

static int __init early_coherent_pool(char *p)
{
	atomic_pool_size = memparse(p, &p);
	return 0;
}
early_param("coherent_pool", early_coherent_pool);

static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
{
	unsigned long val;
	void *ptr = NULL;

	if (!atomic_pool) {
		WARN(1, "coherent pool not initialised!\n");
		return NULL;
	}

	val = gen_pool_alloc(atomic_pool, size);
	if (val) {
		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);

		*ret_page = phys_to_page(phys);
		ptr = (void *)val;
		memset(ptr, 0, size);
	}

	return ptr;
}

static bool __in_atomic_pool(void *start, size_t size)
{
	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
}

static int __free_from_pool(void *start, size_t size)
{
	if (!__in_atomic_pool(start, size))
		return 0;

	gen_pool_free(atomic_pool, (unsigned long)start, size);

	return 1;
}

static void *__dma_alloc_coherent(struct device *dev, size_t size,
				  dma_addr_t *dma_handle, gfp_t flags,
				  struct dma_attrs *attrs)
{
	if (dev == NULL) {
		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
		return NULL;
	}

	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
		flags |= GFP_DMA;
	if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) {
		struct page *page;
		void *addr;

		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
							get_order(size));
		if (!page)
			return NULL;

		*dma_handle = phys_to_dma(dev, page_to_phys(page));
		addr = page_address(page);
		memset(addr, 0, size);
		return addr;
	} else {
		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
	}
}

static void __dma_free_coherent(struct device *dev, size_t size,
				void *vaddr, dma_addr_t dma_handle,
				struct dma_attrs *attrs)
{
	bool freed;
	phys_addr_t paddr = dma_to_phys(dev, dma_handle);

	if (dev == NULL) {
		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
		return;
	}

	freed = dma_release_from_contiguous(dev,
					phys_to_page(paddr),
					size >> PAGE_SHIFT);
	if (!freed)
		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
}

static void *__dma_alloc(struct device *dev, size_t size,
			 dma_addr_t *dma_handle, gfp_t flags,
			 struct dma_attrs *attrs)
{
	struct page *page;
	void *ptr, *coherent_ptr;
	bool coherent = is_device_dma_coherent(dev);
	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);

	size = PAGE_ALIGN(size);

	if (!coherent && !gfpflags_allow_blocking(flags)) {
		struct page *page = NULL;
		void *addr = __alloc_from_pool(size, &page, flags);

		if (addr)
			*dma_handle = phys_to_dma(dev, page_to_phys(page));

		return addr;
	}

	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
	if (!ptr)
		goto no_mem;

	/* no need for non-cacheable mapping if coherent */
	if (coherent)
		return ptr;

	/* remove any dirty cache lines on the kernel alias */
	__dma_flush_range(ptr, ptr + size);

	/* create a coherent mapping */
	page = virt_to_page(ptr);
	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
						   prot, NULL);
	if (!coherent_ptr)
		goto no_map;

	return coherent_ptr;

no_map:
	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
no_mem:
	*dma_handle = DMA_ERROR_CODE;
	return NULL;
}

static void __dma_free(struct device *dev, size_t size,
		       void *vaddr, dma_addr_t dma_handle,
		       struct dma_attrs *attrs)
{
	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));

	size = PAGE_ALIGN(size);

	if (!is_device_dma_coherent(dev)) {
		if (__free_from_pool(vaddr, size))
			return;
		vunmap(vaddr);
	}
	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
}

static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
				     unsigned long offset, size_t size,
				     enum dma_data_direction dir,
				     struct dma_attrs *attrs)
{
	dma_addr_t dev_addr;

	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
	if (!is_device_dma_coherent(dev))
		__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);

	return dev_addr;
}


static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
				 size_t size, enum dma_data_direction dir,
				 struct dma_attrs *attrs)
{
	if (!is_device_dma_coherent(dev))
		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
}

static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
				  int nelems, enum dma_data_direction dir,
				  struct dma_attrs *attrs)
{
	struct scatterlist *sg;
	int i, ret;

	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
	if (!is_device_dma_coherent(dev))
		for_each_sg(sgl, sg, ret, i)
			__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
				       sg->length, dir);

	return ret;
}

static void __swiotlb_unmap_sg_attrs(struct device *dev,
				     struct scatterlist *sgl, int nelems,
				     enum dma_data_direction dir,
				     struct dma_attrs *attrs)
{
	struct scatterlist *sg;
	int i;

	if (!is_device_dma_coherent(dev))
		for_each_sg(sgl, sg, nelems, i)
			__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
					 sg->length, dir);
	swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
}

static void __swiotlb_sync_single_for_cpu(struct device *dev,
					  dma_addr_t dev_addr, size_t size,
					  enum dma_data_direction dir)
{
	if (!is_device_dma_coherent(dev))
		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
	swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
}

static void __swiotlb_sync_single_for_device(struct device *dev,
					     dma_addr_t dev_addr, size_t size,
					     enum dma_data_direction dir)
{
	swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
	if (!is_device_dma_coherent(dev))
		__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
}

static void __swiotlb_sync_sg_for_cpu(struct device *dev,
				      struct scatterlist *sgl, int nelems,
				      enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	if (!is_device_dma_coherent(dev))
		for_each_sg(sgl, sg, nelems, i)
			__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
					 sg->length, dir);
	swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
}

static void __swiotlb_sync_sg_for_device(struct device *dev,
					 struct scatterlist *sgl, int nelems,
					 enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
	if (!is_device_dma_coherent(dev))
		for_each_sg(sgl, sg, nelems, i)
			__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
				       sg->length, dir);
}

static int __swiotlb_mmap(struct device *dev,
			  struct vm_area_struct *vma,
			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
			  struct dma_attrs *attrs)
{
	int ret = -ENXIO;
	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
					PAGE_SHIFT;
	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
	unsigned long off = vma->vm_pgoff;

	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
					     is_device_dma_coherent(dev));

	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
		return ret;

	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
		ret = remap_pfn_range(vma, vma->vm_start,
				      pfn + off,
				      vma->vm_end - vma->vm_start,
				      vma->vm_page_prot);
	}

	return ret;
}

static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
				 void *cpu_addr, dma_addr_t handle, size_t size,
				 struct dma_attrs *attrs)
{
	int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);

	if (!ret)
		sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)),
			    PAGE_ALIGN(size), 0);

	return ret;
}

static struct dma_map_ops swiotlb_dma_ops = {
	.alloc = __dma_alloc,
	.free = __dma_free,
	.mmap = __swiotlb_mmap,
	.get_sgtable = __swiotlb_get_sgtable,
	.map_page = __swiotlb_map_page,
	.unmap_page = __swiotlb_unmap_page,
	.map_sg = __swiotlb_map_sg_attrs,
	.unmap_sg = __swiotlb_unmap_sg_attrs,
	.sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
	.sync_single_for_device = __swiotlb_sync_single_for_device,
	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
	.dma_supported = swiotlb_dma_supported,
	.mapping_error = swiotlb_dma_mapping_error,
};

static int __init atomic_pool_init(void)
{
	pgprot_t prot = __pgprot(PROT_NORMAL_NC);
	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
	struct page *page;
	void *addr;
	unsigned int pool_size_order = get_order(atomic_pool_size);

	if (dev_get_cma_area(NULL))
		page = dma_alloc_from_contiguous(NULL, nr_pages,
							pool_size_order);
	else
		page = alloc_pages(GFP_DMA, pool_size_order);

	if (page) {
		int ret;
		void *page_addr = page_address(page);

		memset(page_addr, 0, atomic_pool_size);
		__dma_flush_range(page_addr, page_addr + atomic_pool_size);

		atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
		if (!atomic_pool)
			goto free_page;

		addr = dma_common_contiguous_remap(page, atomic_pool_size,
					VM_USERMAP, prot, atomic_pool_init);

		if (!addr)
			goto destroy_genpool;

		ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
					page_to_phys(page),
					atomic_pool_size, -1);
		if (ret)
			goto remove_mapping;

		gen_pool_set_algo(atomic_pool,
				  gen_pool_first_fit_order_align,
				  (void *)PAGE_SHIFT);

		pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
			atomic_pool_size / 1024);
		return 0;
	}
	goto out;

remove_mapping:
	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
destroy_genpool:
	gen_pool_destroy(atomic_pool);
	atomic_pool = NULL;
free_page:
	if (!dma_release_from_contiguous(NULL, page, nr_pages))
		__free_pages(page, pool_size_order);
out:
	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
		atomic_pool_size / 1024);
	return -ENOMEM;
}

/********************************************
 * The following APIs are for dummy DMA ops *
 ********************************************/

static void *__dummy_alloc(struct device *dev, size_t size,
			   dma_addr_t *dma_handle, gfp_t flags,
			   struct dma_attrs *attrs)
{
	return NULL;
}

static void __dummy_free(struct device *dev, size_t size,
			 void *vaddr, dma_addr_t dma_handle,
			 struct dma_attrs *attrs)
{
}

static int __dummy_mmap(struct device *dev,
			struct vm_area_struct *vma,
			void *cpu_addr, dma_addr_t dma_addr, size_t size,
			struct dma_attrs *attrs)
{
	return -ENXIO;
}

static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
				   unsigned long offset, size_t size,
				   enum dma_data_direction dir,
				   struct dma_attrs *attrs)
{
	return DMA_ERROR_CODE;
}

static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
			       size_t size, enum dma_data_direction dir,
			       struct dma_attrs *attrs)
{
}

static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl,
			  int nelems, enum dma_data_direction dir,
			  struct dma_attrs *attrs)
{
	return 0;
}

static void __dummy_unmap_sg(struct device *dev,
			     struct scatterlist *sgl, int nelems,
			     enum dma_data_direction dir,
			     struct dma_attrs *attrs)
{
}

static void __dummy_sync_single(struct device *dev,
				dma_addr_t dev_addr, size_t size,
				enum dma_data_direction dir)
{
}

static void __dummy_sync_sg(struct device *dev,
			    struct scatterlist *sgl, int nelems,
			    enum dma_data_direction dir)
{
}

static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
{
	return 1;
}

static int __dummy_dma_supported(struct device *hwdev, u64 mask)
{
	return 0;
}

struct dma_map_ops dummy_dma_ops = {
	.alloc                  = __dummy_alloc,
	.free                   = __dummy_free,
	.mmap                   = __dummy_mmap,
	.map_page               = __dummy_map_page,
	.unmap_page             = __dummy_unmap_page,
	.map_sg                 = __dummy_map_sg,
	.unmap_sg               = __dummy_unmap_sg,
	.sync_single_for_cpu    = __dummy_sync_single,
	.sync_single_for_device = __dummy_sync_single,
	.sync_sg_for_cpu        = __dummy_sync_sg,
	.sync_sg_for_device     = __dummy_sync_sg,
	.mapping_error          = __dummy_mapping_error,
	.dma_supported          = __dummy_dma_supported,
};
EXPORT_SYMBOL(dummy_dma_ops);

static int __init arm64_dma_init(void)
{
	return atomic_pool_init();
}
arch_initcall(arm64_dma_init);

#define PREALLOC_DMA_DEBUG_ENTRIES	4096

static int __init dma_debug_do_init(void)
{
	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
	return 0;
}
fs_initcall(dma_debug_do_init);


#ifdef CONFIG_IOMMU_DMA
#include <linux/dma-iommu.h>
#include <linux/platform_device.h>
#include <linux/amba/bus.h>

/* Thankfully, all cache ops are by VA so we can ignore phys here */
static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
{
	__dma_flush_range(virt, virt + PAGE_SIZE);
}

static void *__iommu_alloc_attrs(struct device *dev, size_t size,
				 dma_addr_t *handle, gfp_t gfp,
				 struct dma_attrs *attrs)
{
	bool coherent = is_device_dma_coherent(dev);
	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
	size_t iosize = size;
	void *addr;

	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
		return NULL;

	size = PAGE_ALIGN(size);

	/*
	 * Some drivers rely on this, and we probably don't want the
	 * possibility of stale kernel data being read by devices anyway.
	 */
	gfp |= __GFP_ZERO;

	if (gfpflags_allow_blocking(gfp)) {
		struct page **pages;
		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);

		pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
					handle, flush_page);
		if (!pages)
			return NULL;

		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
					      __builtin_return_address(0));
		if (!addr)
			iommu_dma_free(dev, pages, iosize, handle);
	} else {
		struct page *page;
		/*
		 * In atomic context we can't remap anything, so we'll only
		 * get the virtually contiguous buffer we need by way of a
		 * physically contiguous allocation.
		 */
		if (coherent) {
			page = alloc_pages(gfp, get_order(size));
			addr = page ? page_address(page) : NULL;
		} else {
			addr = __alloc_from_pool(size, &page, gfp);
		}
		if (!addr)
			return NULL;

		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
		if (iommu_dma_mapping_error(dev, *handle)) {
			if (coherent)
				__free_pages(page, get_order(size));
			else
				__free_from_pool(addr, size);
			addr = NULL;
		}
	}
	return addr;
}

static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
			       dma_addr_t handle, struct dma_attrs *attrs)
{
	size_t iosize = size;

	size = PAGE_ALIGN(size);
	/*
	 * @cpu_addr will be one of 3 things depending on how it was allocated:
	 * - A remapped array of pages from iommu_dma_alloc(), for all
	 *   non-atomic allocations.
	 * - A non-cacheable alias from the atomic pool, for atomic
	 *   allocations by non-coherent devices.
	 * - A normal lowmem address, for atomic allocations by
	 *   coherent devices.
	 * Hence how dodgy the below logic looks...
	 */
	if (__in_atomic_pool(cpu_addr, size)) {
		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
		__free_from_pool(cpu_addr, size);
	} else if (is_vmalloc_addr(cpu_addr)){
		struct vm_struct *area = find_vm_area(cpu_addr);

		if (WARN_ON(!area || !area->pages))
			return;
		iommu_dma_free(dev, area->pages, iosize, &handle);
		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
	} else {
		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
		__free_pages(virt_to_page(cpu_addr), get_order(size));
	}
}

static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
			      void *cpu_addr, dma_addr_t dma_addr, size_t size,
			      struct dma_attrs *attrs)
{
	struct vm_struct *area;
	int ret;

	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
					     is_device_dma_coherent(dev));

	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
		return ret;

	area = find_vm_area(cpu_addr);
	if (WARN_ON(!area || !area->pages))
		return -ENXIO;

	return iommu_dma_mmap(area->pages, size, vma);
}

static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
			       void *cpu_addr, dma_addr_t dma_addr,
			       size_t size, struct dma_attrs *attrs)
{
	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
	struct vm_struct *area = find_vm_area(cpu_addr);

	if (WARN_ON(!area || !area->pages))
		return -ENXIO;

	return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
					 GFP_KERNEL);
}

static void __iommu_sync_single_for_cpu(struct device *dev,
					dma_addr_t dev_addr, size_t size,
					enum dma_data_direction dir)
{
	phys_addr_t phys;

	if (is_device_dma_coherent(dev))
		return;

	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
	__dma_unmap_area(phys_to_virt(phys), size, dir);
}

static void __iommu_sync_single_for_device(struct device *dev,
					   dma_addr_t dev_addr, size_t size,
					   enum dma_data_direction dir)
{
	phys_addr_t phys;

	if (is_device_dma_coherent(dev))
		return;

	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
	__dma_map_area(phys_to_virt(phys), size, dir);
}

static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
				   unsigned long offset, size_t size,
				   enum dma_data_direction dir,
				   struct dma_attrs *attrs)
{
	bool coherent = is_device_dma_coherent(dev);
	int prot = dma_direction_to_prot(dir, coherent);
	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);

	if (!iommu_dma_mapping_error(dev, dev_addr) &&
	    !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
		__iommu_sync_single_for_device(dev, dev_addr, size, dir);

	return dev_addr;
}

static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr,
			       size_t size, enum dma_data_direction dir,
			       struct dma_attrs *attrs)
{
	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
		__iommu_sync_single_for_cpu(dev, dev_addr, size, dir);

	iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs);
}

static void __iommu_sync_sg_for_cpu(struct device *dev,
				    struct scatterlist *sgl, int nelems,
				    enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	if (is_device_dma_coherent(dev))
		return;

	for_each_sg(sgl, sg, nelems, i)
		__dma_unmap_area(sg_virt(sg), sg->length, dir);
}

static void __iommu_sync_sg_for_device(struct device *dev,
				       struct scatterlist *sgl, int nelems,
				       enum dma_data_direction dir)
{
	struct scatterlist *sg;
	int i;

	if (is_device_dma_coherent(dev))
		return;

	for_each_sg(sgl, sg, nelems, i)
		__dma_map_area(sg_virt(sg), sg->length, dir);
}

static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
				int nelems, enum dma_data_direction dir,
				struct dma_attrs *attrs)
{
	bool coherent = is_device_dma_coherent(dev);

	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);

	return iommu_dma_map_sg(dev, sgl, nelems,
			dma_direction_to_prot(dir, coherent));
}

static void __iommu_unmap_sg_attrs(struct device *dev,
				   struct scatterlist *sgl, int nelems,
				   enum dma_data_direction dir,
				   struct dma_attrs *attrs)
{
	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
		__iommu_sync_sg_for_cpu(dev, sgl, nelems, dir);

	iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs);
}

static struct dma_map_ops iommu_dma_ops = {
	.alloc = __iommu_alloc_attrs,
	.free = __iommu_free_attrs,
	.mmap = __iommu_mmap_attrs,
	.get_sgtable = __iommu_get_sgtable,
	.map_page = __iommu_map_page,
	.unmap_page = __iommu_unmap_page,
	.map_sg = __iommu_map_sg_attrs,
	.unmap_sg = __iommu_unmap_sg_attrs,
	.sync_single_for_cpu = __iommu_sync_single_for_cpu,
	.sync_single_for_device = __iommu_sync_single_for_device,
	.sync_sg_for_cpu = __iommu_sync_sg_for_cpu,
	.sync_sg_for_device = __iommu_sync_sg_for_device,
	.dma_supported = iommu_dma_supported,
	.mapping_error = iommu_dma_mapping_error,
};

/*
 * TODO: Right now __iommu_setup_dma_ops() gets called too early to do
 * everything it needs to - the device is only partially created and the
 * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we
 * need this delayed attachment dance. Once IOMMU probe ordering is sorted
 * to move the arch_setup_dma_ops() call later, all the notifier bits below
 * become unnecessary, and will go away.
 */
struct iommu_dma_notifier_data {
	struct list_head list;
	struct device *dev;
	const struct iommu_ops *ops;
	u64 dma_base;
	u64 size;
};
static LIST_HEAD(iommu_dma_masters);
static DEFINE_MUTEX(iommu_dma_notifier_lock);

static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
			   u64 dma_base, u64 size)
{
	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);

	/*
	 * If the IOMMU driver has the DMA domain support that we require,
	 * then the IOMMU core will have already configured a group for this
	 * device, and allocated the default domain for that group.
	 */
	if (!domain || iommu_dma_init_domain(domain, dma_base, size)) {
		pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
			dev_name(dev));
		return false;
	}

	dev->archdata.dma_ops = &iommu_dma_ops;
	return true;
}

static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
			      u64 dma_base, u64 size)
{
	struct iommu_dma_notifier_data *iommudata;

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

	iommudata->dev = dev;
	iommudata->ops = ops;
	iommudata->dma_base = dma_base;
	iommudata->size = size;

	mutex_lock(&iommu_dma_notifier_lock);
	list_add(&iommudata->list, &iommu_dma_masters);
	mutex_unlock(&iommu_dma_notifier_lock);
}

static int __iommu_attach_notifier(struct notifier_block *nb,
				   unsigned long action, void *data)
{
	struct iommu_dma_notifier_data *master, *tmp;

	if (action != BUS_NOTIFY_ADD_DEVICE)
		return 0;

	mutex_lock(&iommu_dma_notifier_lock);
	list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
		if (do_iommu_attach(master->dev, master->ops,
				master->dma_base, master->size)) {
			list_del(&master->list);
			kfree(master);
		}
	}
	mutex_unlock(&iommu_dma_notifier_lock);
	return 0;
}

static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
{
	struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
	int ret;

	if (!nb)
		return -ENOMEM;
	/*
	 * The device must be attached to a domain before the driver probe
	 * routine gets a chance to start allocating DMA buffers. However,
	 * the IOMMU driver also needs a chance to configure the iommu_group
	 * via its add_device callback first, so we need to make the attach
	 * happen between those two points. Since the IOMMU core uses a bus
	 * notifier with default priority for add_device, do the same but
	 * with a lower priority to ensure the appropriate ordering.
	 */
	nb->notifier_call = __iommu_attach_notifier;
	nb->priority = -100;

	ret = bus_register_notifier(bus, nb);
	if (ret) {
		pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n",
			bus->name);
		kfree(nb);
	}
	return ret;
}

static int __init __iommu_dma_init(void)
{
	int ret;

	ret = iommu_dma_init();
	if (!ret)
		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
	if (!ret)
		ret = register_iommu_dma_ops_notifier(&amba_bustype);
#ifdef CONFIG_PCI
	if (!ret)
		ret = register_iommu_dma_ops_notifier(&pci_bus_type);
#endif

	/* handle devices queued before this arch_initcall */
	if (!ret)
		__iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
	return ret;
}
arch_initcall(__iommu_dma_init);

static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
				  const struct iommu_ops *ops)
{
	struct iommu_group *group;

	if (!ops)
		return;
	/*
	 * TODO: As a concession to the future, we're ready to handle being
	 * called both early and late (i.e. after bus_add_device). Once all
	 * the platform bus code is reworked to call us late and the notifier
	 * junk above goes away, move the body of do_iommu_attach here.
	 */
	group = iommu_group_get(dev);
	if (group) {
		do_iommu_attach(dev, ops, dma_base, size);
		iommu_group_put(group);
	} else {
		queue_iommu_attach(dev, ops, dma_base, size);
	}
}

void arch_teardown_dma_ops(struct device *dev)
{
	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);

	if (WARN_ON(domain))
		iommu_detach_device(domain, dev);

	dev->archdata.dma_ops = NULL;
}

#else

static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
				  const struct iommu_ops *iommu)
{ }

#endif  /* CONFIG_IOMMU_DMA */

void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
			const struct iommu_ops *iommu, bool coherent)
{
	if (!dev->archdata.dma_ops)
		dev->archdata.dma_ops = &swiotlb_dma_ops;

	dev->archdata.dma_coherent = coherent;
	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
}