aboutsummaryrefslogtreecommitdiff
path: root/lib/swiotlb.c
blob: 5f60157f31d8cccd342c3389b45153f76dce29a5 (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
/*
 * 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
 */

#include <linux/cache.h>
#include <linux/dma-mapping.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/swiotlb.h>
#include <linux/pfn.h>
#include <linux/types.h>
#include <linux/ctype.h>
#include <linux/highmem.h>
#include <linux/gfp.h>

#include <asm/io.h>
#include <asm/dma.h>
#include <asm/scatterlist.h>

#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/iommu-helper.h>

#define OFFSET(val,align) ((unsigned long)	\
	                   ( (val) & ( (align) - 1)))

#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)

/*
 * Enumeration for sync targets
 */
enum dma_sync_target {
	SYNC_FOR_CPU = 0,
	SYNC_FOR_DEVICE = 1,
};

int swiotlb_force;

/*
 * Used to do a quick range check in swiotlb_tbl_unmap_single and
 * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
 * API.
 */
static char *io_tlb_start, *io_tlb_end;

/*
 * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and
 * io_tlb_end.  This is command line adjustable via setup_io_tlb_npages.
 */
static unsigned long io_tlb_nslabs;

/*
 * When the IOMMU overflows we return a fallback buffer. This sets the size.
 */
static unsigned long io_tlb_overflow = 32*1024;

void *io_tlb_overflow_buffer;

/*
 * This is a free list describing the number of free entries available from
 * each index
 */
static unsigned int *io_tlb_list;
static unsigned int io_tlb_index;

/*
 * We need to save away the original address corresponding to a mapped entry
 * for the sync operations.
 */
static phys_addr_t *io_tlb_orig_addr;

/*
 * Protect the above data structures in the map and unmap calls
 */
static DEFINE_SPINLOCK(io_tlb_lock);

static int late_alloc;

static int __init
setup_io_tlb_npages(char *str)
{
	if (isdigit(*str)) {
		io_tlb_nslabs = simple_strtoul(str, &str, 0);
		/* avoid tail segment of size < IO_TLB_SEGSIZE */
		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
	}
	if (*str == ',')
		++str;
	if (!strcmp(str, "force"))
		swiotlb_force = 1;

	return 1;
}
__setup("swiotlb=", setup_io_tlb_npages);
/* make io_tlb_overflow tunable too? */

/* Note that this doesn't work with highmem page */
static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
				      volatile void *address)
{
	return phys_to_dma(hwdev, virt_to_phys(address));
}

void swiotlb_print_info(void)
{
	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
	phys_addr_t pstart, pend;

	pstart = virt_to_phys(io_tlb_start);
	pend = virt_to_phys(io_tlb_end);

	printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
	       bytes >> 20, io_tlb_start, io_tlb_end);
	printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
	       (unsigned long long)pstart,
	       (unsigned long long)pend);
}

void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
{
	unsigned long i, bytes;

	bytes = nslabs << IO_TLB_SHIFT;

	io_tlb_nslabs = nslabs;
	io_tlb_start = tlb;
	io_tlb_end = io_tlb_start + bytes;

	/*
	 * Allocate and initialize the free list array.  This array is used
	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
	 * between io_tlb_start and io_tlb_end.
	 */
	io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
	for (i = 0; i < io_tlb_nslabs; i++)
 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
	io_tlb_index = 0;
	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(phys_addr_t));

	/*
	 * Get the overflow emergency buffer
	 */
	io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
	if (!io_tlb_overflow_buffer)
		panic("Cannot allocate SWIOTLB overflow buffer!\n");
	if (verbose)
		swiotlb_print_info();
}

/*
 * 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_with_default_size(size_t default_size, int verbose)
{
	unsigned long bytes;

	if (!io_tlb_nslabs) {
		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
	}

	bytes = io_tlb_nslabs << IO_TLB_SHIFT;

	/*
	 * Get IO TLB memory from the low pages
	 */
	io_tlb_start = alloc_bootmem_low_pages(bytes);
	if (!io_tlb_start)
		panic("Cannot allocate SWIOTLB buffer");

	swiotlb_init_with_tbl(io_tlb_start, io_tlb_nslabs, verbose);
}

void __init
swiotlb_init(int verbose)
{
	swiotlb_init_with_default_size(64 * (1<<20), verbose);	/* default to 64MB */
}

/*
 * 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_late_init_with_default_size(size_t default_size)
{
	unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
	unsigned int order;

	if (!io_tlb_nslabs) {
		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
	}

	/*
	 * Get IO TLB memory from the low pages
	 */
	order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
	io_tlb_nslabs = SLABS_PER_PAGE << order;
	bytes = io_tlb_nslabs << IO_TLB_SHIFT;

	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
		io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
							order);
		if (io_tlb_start)
			break;
		order--;
	}

	if (!io_tlb_start)
		goto cleanup1;

	if (order != get_order(bytes)) {
		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
		io_tlb_nslabs = SLABS_PER_PAGE << order;
		bytes = io_tlb_nslabs << IO_TLB_SHIFT;
	}
	io_tlb_end = io_tlb_start + bytes;
	memset(io_tlb_start, 0, bytes);

	/*
	 * Allocate and initialize the free list array.  This array is used
	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
	 * between io_tlb_start and io_tlb_end.
	 */
	io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
	                              get_order(io_tlb_nslabs * sizeof(int)));
	if (!io_tlb_list)
		goto cleanup2;

	for (i = 0; i < io_tlb_nslabs; i++)
 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
	io_tlb_index = 0;

	io_tlb_orig_addr = (phys_addr_t *)
		__get_free_pages(GFP_KERNEL,
				 get_order(io_tlb_nslabs *
					   sizeof(phys_addr_t)));
	if (!io_tlb_orig_addr)
		goto cleanup3;

	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(phys_addr_t));

	/*
	 * Get the overflow emergency buffer
	 */
	io_tlb_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
	                                          get_order(io_tlb_overflow));
	if (!io_tlb_overflow_buffer)
		goto cleanup4;

	swiotlb_print_info();

	late_alloc = 1;

	return 0;

cleanup4:
	free_pages((unsigned long)io_tlb_orig_addr,
		   get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
	io_tlb_orig_addr = NULL;
cleanup3:
	free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
	                                                 sizeof(int)));
	io_tlb_list = NULL;
cleanup2:
	io_tlb_end = NULL;
	free_pages((unsigned long)io_tlb_start, order);
	io_tlb_start = NULL;
cleanup1:
	io_tlb_nslabs = req_nslabs;
	return -ENOMEM;
}

void __init swiotlb_free(void)
{
	if (!io_tlb_overflow_buffer)
		return;

	if (late_alloc) {
		free_pages((unsigned long)io_tlb_overflow_buffer,
			   get_order(io_tlb_overflow));
		free_pages((unsigned long)io_tlb_orig_addr,
			   get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
		free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
								 sizeof(int)));
		free_pages((unsigned long)io_tlb_start,
			   get_order(io_tlb_nslabs << IO_TLB_SHIFT));
	} else {
		free_bootmem_late(__pa(io_tlb_overflow_buffer),
				  io_tlb_overflow);
		free_bootmem_late(__pa(io_tlb_orig_addr),
				  io_tlb_nslabs * sizeof(phys_addr_t));
		free_bootmem_late(__pa(io_tlb_list),
				  io_tlb_nslabs * sizeof(int));
		free_bootmem_late(__pa(io_tlb_start),
				  io_tlb_nslabs << IO_TLB_SHIFT);
	}
}

static int is_swiotlb_buffer(phys_addr_t paddr)
{
	return paddr >= virt_to_phys(io_tlb_start) &&
		paddr < virt_to_phys(io_tlb_end);
}

/*
 * Bounce: copy the swiotlb buffer back to the original dma location
 */
static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
			   enum dma_data_direction dir)
{
	unsigned long pfn = PFN_DOWN(phys);

	if (PageHighMem(pfn_to_page(pfn))) {
		/* The buffer does not have a mapping.  Map it in and copy */
		unsigned int offset = phys & ~PAGE_MASK;
		char *buffer;
		unsigned int sz = 0;
		unsigned long flags;

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

			local_irq_save(flags);
			buffer = kmap_atomic(pfn_to_page(pfn),
					     KM_BOUNCE_READ);
			if (dir == DMA_TO_DEVICE)
				memcpy(dma_addr, buffer + offset, sz);
			else
				memcpy(buffer + offset, dma_addr, sz);
			kunmap_atomic(buffer, KM_BOUNCE_READ);
			local_irq_restore(flags);

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

void *swiotlb_tbl_map_single(struct device *hwdev, dma_addr_t tbl_dma_addr,
			     phys_addr_t phys, size_t size,
			     enum dma_data_direction dir)
{
	unsigned long flags;
	char *dma_addr;
	unsigned int nslots, stride, index, wrap;
	int i;
	unsigned long mask;
	unsigned long offset_slots;
	unsigned long max_slots;

	mask = dma_get_seg_boundary(hwdev);

	tbl_dma_addr &= mask;

	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;

	/*
 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
 	 */
	max_slots = mask + 1
		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);

	/*
	 * For mappings greater than a page, we limit the stride (and
	 * hence alignment) to a page size.
	 */
	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
	if (size > PAGE_SIZE)
		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
	else
		stride = 1;

	BUG_ON(!nslots);

	/*
	 * Find suitable number of IO TLB entries size that will fit this
	 * request and allocate a buffer from that IO TLB pool.
	 */
	spin_lock_irqsave(&io_tlb_lock, flags);
	index = ALIGN(io_tlb_index, stride);
	if (index >= io_tlb_nslabs)
		index = 0;
	wrap = index;

	do {
		while (iommu_is_span_boundary(index, nslots, offset_slots,
					      max_slots)) {
			index += stride;
			if (index >= io_tlb_nslabs)
				index = 0;
			if (index == wrap)
				goto not_found;
		}

		/*
		 * 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 (io_tlb_list[index] >= nslots) {
			int count = 0;

			for (i = index; i < (int) (index + nslots); i++)
				io_tlb_list[i] = 0;
			for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
				io_tlb_list[i] = ++count;
			dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);

			/*
			 * Update the indices to avoid searching in the next
			 * round.
			 */
			io_tlb_index = ((index + nslots) < io_tlb_nslabs
					? (index + nslots) : 0);

			goto found;
		}
		index += stride;
		if (index >= io_tlb_nslabs)
			index = 0;
	} while (index != wrap);

not_found:
	spin_unlock_irqrestore(&io_tlb_lock, flags);
	return NULL;
found:
	spin_unlock_irqrestore(&io_tlb_lock, flags);

	/*
	 * 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 < nslots; i++)
		io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT);
	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
		swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);

	return dma_addr;
}

/*
 * Allocates bounce buffer and returns its kernel virtual address.
 */

static void *
map_single(struct device *hwdev, phys_addr_t phys, size_t size,
	   enum dma_data_direction dir)
{
	dma_addr_t start_dma_addr = swiotlb_virt_to_bus(hwdev, io_tlb_start);

	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir);
}

/*
 * dma_addr is the kernel virtual address of the bounce buffer to unmap.
 */
static void
swiotlb_tbl_unmap_single(struct device *hwdev, char *dma_addr, size_t size,
			enum dma_data_direction dir)
{
	unsigned long flags;
	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
	phys_addr_t phys = io_tlb_orig_addr[index];

	/*
	 * First, sync the memory before unmapping the entry
	 */
	if (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
		swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);

	/*
	 * 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.
	 */
	spin_lock_irqsave(&io_tlb_lock, flags);
	{
		count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
			 io_tlb_list[index + nslots] : 0);
		/*
		 * Step 1: return the slots to the free list, merging the
		 * slots with superceeding slots
		 */
		for (i = index + nslots - 1; i >= index; i--)
			io_tlb_list[i] = ++count;
		/*
		 * Step 2: merge the returned slots with the preceding slots,
		 * if available (non zero)
		 */
		for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
			io_tlb_list[i] = ++count;
	}
	spin_unlock_irqrestore(&io_tlb_lock, flags);
}

static void
swiotlb_tbl_sync_single(struct device *hwdev, char *dma_addr, size_t size,
	    enum dma_data_direction dir, int target)
{
	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
	phys_addr_t phys = io_tlb_orig_addr[index];

	phys += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));

	switch (target) {
	case SYNC_FOR_CPU:
		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
			swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
		else
			BUG_ON(dir != DMA_TO_DEVICE);
		break;
	case SYNC_FOR_DEVICE:
		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
			swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
		else
			BUG_ON(dir != DMA_FROM_DEVICE);
		break;
	default:
		BUG();
	}
}

void *
swiotlb_alloc_coherent(struct device *hwdev, size_t size,
		       dma_addr_t *dma_handle, gfp_t flags)
{
	dma_addr_t dev_addr;
	void *ret;
	int order = get_order(size);
	u64 dma_mask = DMA_BIT_MASK(32);

	if (hwdev && hwdev->coherent_dma_mask)
		dma_mask = hwdev->coherent_dma_mask;

	ret = (void *)__get_free_pages(flags, order);
	if (ret && swiotlb_virt_to_bus(hwdev, ret) + size - 1 > dma_mask) {
		/*
		 * The allocated memory isn't reachable by the device.
		 */
		free_pages((unsigned long) ret, order);
		ret = NULL;
	}
	if (!ret) {
		/*
		 * We are either out of memory or the device can't DMA to
		 * GFP_DMA memory; fall back on map_single(), which
		 * will grab memory from the lowest available address range.
		 */
		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
		if (!ret)
			return NULL;
	}

	memset(ret, 0, size);
	dev_addr = swiotlb_virt_to_bus(hwdev, ret);

	/* Confirm address can be DMA'd by device */
	if (dev_addr + size - 1 > dma_mask) {
		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
		       (unsigned long long)dma_mask,
		       (unsigned long long)dev_addr);

		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
		swiotlb_tbl_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
		return NULL;
	}
	*dma_handle = dev_addr;
	return ret;
}
EXPORT_SYMBOL(swiotlb_alloc_coherent);

void
swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
		      dma_addr_t dev_addr)
{
	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);

	WARN_ON(irqs_disabled());
	if (!is_swiotlb_buffer(paddr))
		free_pages((unsigned long)vaddr, get_order(size));
	else
		/* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */
		swiotlb_tbl_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
}
EXPORT_SYMBOL(swiotlb_free_coherent);

static void
swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
	     int do_panic)
{
	/*
	 * Ran out of IOMMU space for this operation. This is very bad.
	 * Unfortunately the drivers cannot handle this operation properly.
	 * unless they check for dma_mapping_error (most don't)
	 * When the mapping is small enough return a static buffer to limit
	 * the damage, or panic when the transfer is too big.
	 */
	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
	       "device %s\n", size, dev ? dev_name(dev) : "?");

	if (size <= io_tlb_overflow || !do_panic)
		return;

	if (dir == DMA_BIDIRECTIONAL)
		panic("DMA: Random memory could be DMA accessed\n");
	if (dir == DMA_FROM_DEVICE)
		panic("DMA: Random memory could be DMA written\n");
	if (dir == DMA_TO_DEVICE)
		panic("DMA: Random memory could be DMA read\n");
}

/*
 * Map a single buffer of the indicated size for DMA in streaming mode.  The
 * physical address to use is returned.
 *
 * Once the device is given the dma address, the device owns this memory until
 * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
 */
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)
{
	phys_addr_t phys = page_to_phys(page) + offset;
	dma_addr_t dev_addr = phys_to_dma(dev, phys);
	void *map;

	BUG_ON(dir == DMA_NONE);
	/*
	 * If the address happens to be in the device's DMA window,
	 * we can safely return the device addr and not worry about bounce
	 * buffering it.
	 */
	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
		return dev_addr;

	/*
	 * Oh well, have to allocate and map a bounce buffer.
	 */
	map = map_single(dev, phys, size, dir);
	if (!map) {
		swiotlb_full(dev, size, dir, 1);
		map = io_tlb_overflow_buffer;
	}

	dev_addr = swiotlb_virt_to_bus(dev, map);

	/*
	 * Ensure that the address returned is DMA'ble
	 */
	if (!dma_capable(dev, dev_addr, size))
		panic("map_single: bounce buffer is not DMA'ble");

	return dev_addr;
}
EXPORT_SYMBOL_GPL(swiotlb_map_page);

/*
 * Unmap a single streaming mode DMA translation.  The dma_addr and size must
 * match what was provided for in a previous swiotlb_map_page call.  All
 * other usages are undefined.
 *
 * After this call, reads by the cpu to the buffer are guaranteed to see
 * whatever the device wrote there.
 */
static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
			 size_t size, enum dma_data_direction dir)
{
	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);

	BUG_ON(dir == DMA_NONE);

	if (is_swiotlb_buffer(paddr)) {
		swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
		return;
	}

	if (dir != DMA_FROM_DEVICE)
		return;

	/*
	 * phys_to_virt doesn't work with hihgmem page but we could
	 * call dma_mark_clean() with hihgmem page here. However, we
	 * are fine since dma_mark_clean() is null on POWERPC. We can
	 * make dma_mark_clean() take a physical address if necessary.
	 */
	dma_mark_clean(phys_to_virt(paddr), size);
}

void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
			size_t size, enum dma_data_direction dir,
			struct dma_attrs *attrs)
{
	unmap_single(hwdev, dev_addr, size, dir);
}
EXPORT_SYMBOL_GPL(swiotlb_unmap_page);

/*
 * Make physical memory consistent for a single streaming mode DMA translation
 * after a transfer.
 *
 * If you perform a swiotlb_map_page() but wish to interrogate the buffer
 * using the cpu, yet do not wish to teardown the dma mapping, you must
 * call this function before doing so.  At the next point you give the dma
 * address back to the card, you must first perform a
 * swiotlb_dma_sync_for_device, and then the device again owns the buffer
 */
static void
swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
		    size_t size, enum dma_data_direction dir, int target)
{
	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);

	BUG_ON(dir == DMA_NONE);

	if (is_swiotlb_buffer(paddr)) {
		swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir,
				       target);
		return;
	}

	if (dir != DMA_FROM_DEVICE)
		return;

	dma_mark_clean(phys_to_virt(paddr), size);
}

void
swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
			    size_t size, enum dma_data_direction dir)
{
	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);

void
swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
			       size_t size, enum dma_data_direction dir)
{
	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
}
EXPORT_SYMBOL(swiotlb_sync_single_for_device);

/*
 * Map a set of buffers described by scatterlist in streaming mode for DMA.
 * This is the scatter-gather version of the above swiotlb_map_page
 * interface.  Here the scatter gather list elements are each tagged with the
 * appropriate dma address and length.  They are obtained via
 * sg_dma_{address,length}(SG).
 *
 * NOTE: An implementation may be able to use a smaller number of
 *       DMA address/length pairs than there are SG table elements.
 *       (for example via virtual mapping capabilities)
 *       The routine returns the number of addr/length pairs actually
 *       used, at most nents.
 *
 * Device ownership issues as mentioned above for swiotlb_map_page are the
 * same here.
 */
int
swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
		     enum dma_data_direction dir, struct dma_attrs *attrs)
{
	struct scatterlist *sg;
	int i;

	BUG_ON(dir == DMA_NONE);

	for_each_sg(sgl, sg, nelems, i) {
		phys_addr_t paddr = sg_phys(sg);
		dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);

		if (swiotlb_force ||
		    !dma_capable(hwdev, dev_addr, sg->length)) {
			void *map = map_single(hwdev, sg_phys(sg),
					       sg->length, dir);
			if (!map) {
				/* Don't panic here, we expect map_sg users
				   to do proper error handling. */
				swiotlb_full(hwdev, sg->length, dir, 0);
				swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
						       attrs);
				sgl[0].dma_length = 0;
				return 0;
			}
			sg->dma_address = swiotlb_virt_to_bus(hwdev, map);
		} else
			sg->dma_address = dev_addr;
		sg->dma_length = sg->length;
	}
	return nelems;
}
EXPORT_SYMBOL(swiotlb_map_sg_attrs);

int
swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
	       enum dma_data_direction dir)
{
	return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
}
EXPORT_SYMBOL(swiotlb_map_sg);

/*
 * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
 * concerning calls here are the same as for swiotlb_unmap_page() above.
 */
void
swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
		       int nelems, enum dma_data_direction dir, struct dma_attrs *attrs)
{
	struct scatterlist *sg;
	int i;

	BUG_ON(dir == DMA_NONE);

	for_each_sg(sgl, sg, nelems, i)
		unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);

}
EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);

void
swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
		 enum dma_data_direction dir)
{
	return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
}
EXPORT_SYMBOL(swiotlb_unmap_sg);

/*
 * Make physical memory consistent for a set of streaming mode DMA translations
 * after a transfer.
 *
 * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
 * and usage.
 */
static void
swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
		int nelems, enum dma_data_direction dir, int target)
{
	struct scatterlist *sg;
	int i;

	for_each_sg(sgl, sg, nelems, i)
		swiotlb_sync_single(hwdev, sg->dma_address,
				    sg->dma_length, dir, target);
}

void
swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
			int nelems, enum dma_data_direction dir)
{
	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);

void
swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
			   int nelems, enum dma_data_direction dir)
{
	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
}
EXPORT_SYMBOL(swiotlb_sync_sg_for_device);

int
swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
{
	return (dma_addr == swiotlb_virt_to_bus(hwdev, io_tlb_overflow_buffer));
}
EXPORT_SYMBOL(swiotlb_dma_mapping_error);

/*
 * Return whether the given device DMA address mask can be supported
 * properly.  For example, if your device can only drive the low 24-bits
 * during bus mastering, then you would pass 0x00ffffff as the mask to
 * this function.
 */
int
swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
	return swiotlb_virt_to_bus(hwdev, io_tlb_end - 1) <= mask;
}
EXPORT_SYMBOL(swiotlb_dma_supported);