summaryrefslogtreecommitdiff
path: root/arch/s390/pci/pci_dma.c
blob: 2d9b01d7ca4c5c5333fdbe711e2655909655529d (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright IBM Corp. 2012
 *
 * Author(s):
 *   Jan Glauber <jang@linux.vnet.ibm.com>
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/iommu-helper.h>
#include <linux/dma-map-ops.h>
#include <linux/vmalloc.h>
#include <linux/pci.h>
#include <asm/pci_dma.h>

static struct kmem_cache *dma_region_table_cache;
static struct kmem_cache *dma_page_table_cache;
static int s390_iommu_strict;
static u64 s390_iommu_aperture;
static u32 s390_iommu_aperture_factor = 1;

static int zpci_refresh_global(struct zpci_dev *zdev)
{
	return zpci_refresh_trans((u64) zdev->fh << 32, zdev->start_dma,
				  zdev->iommu_pages * PAGE_SIZE);
}

unsigned long *dma_alloc_cpu_table(gfp_t gfp)
{
	unsigned long *table, *entry;

	table = kmem_cache_alloc(dma_region_table_cache, gfp);
	if (!table)
		return NULL;

	for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++)
		*entry = ZPCI_TABLE_INVALID;
	return table;
}

static void dma_free_cpu_table(void *table)
{
	kmem_cache_free(dma_region_table_cache, table);
}

static unsigned long *dma_alloc_page_table(gfp_t gfp)
{
	unsigned long *table, *entry;

	table = kmem_cache_alloc(dma_page_table_cache, gfp);
	if (!table)
		return NULL;

	for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++)
		*entry = ZPCI_PTE_INVALID;
	return table;
}

static void dma_free_page_table(void *table)
{
	kmem_cache_free(dma_page_table_cache, table);
}

static unsigned long *dma_get_seg_table_origin(unsigned long *rtep, gfp_t gfp)
{
	unsigned long old_rte, rte;
	unsigned long *sto;

	rte = READ_ONCE(*rtep);
	if (reg_entry_isvalid(rte)) {
		sto = get_rt_sto(rte);
	} else {
		sto = dma_alloc_cpu_table(gfp);
		if (!sto)
			return NULL;

		set_rt_sto(&rte, virt_to_phys(sto));
		validate_rt_entry(&rte);
		entry_clr_protected(&rte);

		old_rte = cmpxchg(rtep, ZPCI_TABLE_INVALID, rte);
		if (old_rte != ZPCI_TABLE_INVALID) {
			/* Somone else was faster, use theirs */
			dma_free_cpu_table(sto);
			sto = get_rt_sto(old_rte);
		}
	}
	return sto;
}

static unsigned long *dma_get_page_table_origin(unsigned long *step, gfp_t gfp)
{
	unsigned long old_ste, ste;
	unsigned long *pto;

	ste = READ_ONCE(*step);
	if (reg_entry_isvalid(ste)) {
		pto = get_st_pto(ste);
	} else {
		pto = dma_alloc_page_table(gfp);
		if (!pto)
			return NULL;
		set_st_pto(&ste, virt_to_phys(pto));
		validate_st_entry(&ste);
		entry_clr_protected(&ste);

		old_ste = cmpxchg(step, ZPCI_TABLE_INVALID, ste);
		if (old_ste != ZPCI_TABLE_INVALID) {
			/* Somone else was faster, use theirs */
			dma_free_page_table(pto);
			pto = get_st_pto(old_ste);
		}
	}
	return pto;
}

unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr,
				  gfp_t gfp)
{
	unsigned long *sto, *pto;
	unsigned int rtx, sx, px;

	rtx = calc_rtx(dma_addr);
	sto = dma_get_seg_table_origin(&rto[rtx], gfp);
	if (!sto)
		return NULL;

	sx = calc_sx(dma_addr);
	pto = dma_get_page_table_origin(&sto[sx], gfp);
	if (!pto)
		return NULL;

	px = calc_px(dma_addr);
	return &pto[px];
}

void dma_update_cpu_trans(unsigned long *ptep, phys_addr_t page_addr, int flags)
{
	unsigned long pte;

	pte = READ_ONCE(*ptep);
	if (flags & ZPCI_PTE_INVALID) {
		invalidate_pt_entry(&pte);
	} else {
		set_pt_pfaa(&pte, page_addr);
		validate_pt_entry(&pte);
	}

	if (flags & ZPCI_TABLE_PROTECTED)
		entry_set_protected(&pte);
	else
		entry_clr_protected(&pte);

	xchg(ptep, pte);
}

static int __dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa,
			      dma_addr_t dma_addr, size_t size, int flags)
{
	unsigned int nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
	phys_addr_t page_addr = (pa & PAGE_MASK);
	unsigned long *entry;
	int i, rc = 0;

	if (!nr_pages)
		return -EINVAL;

	if (!zdev->dma_table)
		return -EINVAL;

	for (i = 0; i < nr_pages; i++) {
		entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr,
					   GFP_ATOMIC);
		if (!entry) {
			rc = -ENOMEM;
			goto undo_cpu_trans;
		}
		dma_update_cpu_trans(entry, page_addr, flags);
		page_addr += PAGE_SIZE;
		dma_addr += PAGE_SIZE;
	}

undo_cpu_trans:
	if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) {
		flags = ZPCI_PTE_INVALID;
		while (i-- > 0) {
			page_addr -= PAGE_SIZE;
			dma_addr -= PAGE_SIZE;
			entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr,
						   GFP_ATOMIC);
			if (!entry)
				break;
			dma_update_cpu_trans(entry, page_addr, flags);
		}
	}
	return rc;
}

static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
			   size_t size, int flags)
{
	unsigned long irqflags;
	int ret;

	/*
	 * With zdev->tlb_refresh == 0, rpcit is not required to establish new
	 * translations when previously invalid translation-table entries are
	 * validated. With lazy unmap, rpcit is skipped for previously valid
	 * entries, but a global rpcit is then required before any address can
	 * be re-used, i.e. after each iommu bitmap wrap-around.
	 */
	if ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID) {
		if (!zdev->tlb_refresh)
			return 0;
	} else {
		if (!s390_iommu_strict)
			return 0;
	}

	ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
				 PAGE_ALIGN(size));
	if (ret == -ENOMEM && !s390_iommu_strict) {
		/* enable the hypervisor to free some resources */
		if (zpci_refresh_global(zdev))
			goto out;

		spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags);
		bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap,
			      zdev->lazy_bitmap, zdev->iommu_pages);
		bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages);
		spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags);
		ret = 0;
	}
out:
	return ret;
}

static int dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa,
			    dma_addr_t dma_addr, size_t size, int flags)
{
	int rc;

	rc = __dma_update_trans(zdev, pa, dma_addr, size, flags);
	if (rc)
		return rc;

	rc = __dma_purge_tlb(zdev, dma_addr, size, flags);
	if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID))
		__dma_update_trans(zdev, pa, dma_addr, size, ZPCI_PTE_INVALID);

	return rc;
}

void dma_free_seg_table(unsigned long entry)
{
	unsigned long *sto = get_rt_sto(entry);
	int sx;

	for (sx = 0; sx < ZPCI_TABLE_ENTRIES; sx++)
		if (reg_entry_isvalid(sto[sx]))
			dma_free_page_table(get_st_pto(sto[sx]));

	dma_free_cpu_table(sto);
}

void dma_cleanup_tables(unsigned long *table)
{
	int rtx;

	if (!table)
		return;

	for (rtx = 0; rtx < ZPCI_TABLE_ENTRIES; rtx++)
		if (reg_entry_isvalid(table[rtx]))
			dma_free_seg_table(table[rtx]);

	dma_free_cpu_table(table);
}

static unsigned long __dma_alloc_iommu(struct device *dev,
				       unsigned long start, int size)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));

	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
				start, size, zdev->start_dma >> PAGE_SHIFT,
				dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT),
				0);
}

static dma_addr_t dma_alloc_address(struct device *dev, int size)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
	unsigned long offset, flags;

	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
	offset = __dma_alloc_iommu(dev, zdev->next_bit, size);
	if (offset == -1) {
		if (!s390_iommu_strict) {
			/* global flush before DMA addresses are reused */
			if (zpci_refresh_global(zdev))
				goto out_error;

			bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap,
				      zdev->lazy_bitmap, zdev->iommu_pages);
			bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages);
		}
		/* wrap-around */
		offset = __dma_alloc_iommu(dev, 0, size);
		if (offset == -1)
			goto out_error;
	}
	zdev->next_bit = offset + size;
	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);

	return zdev->start_dma + offset * PAGE_SIZE;

out_error:
	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
	return DMA_MAPPING_ERROR;
}

static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
	unsigned long flags, offset;

	offset = (dma_addr - zdev->start_dma) >> PAGE_SHIFT;

	spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags);
	if (!zdev->iommu_bitmap)
		goto out;

	if (s390_iommu_strict)
		bitmap_clear(zdev->iommu_bitmap, offset, size);
	else
		bitmap_set(zdev->lazy_bitmap, offset, size);

out:
	spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags);
}

static inline void zpci_err_dma(unsigned long rc, unsigned long addr)
{
	struct {
		unsigned long rc;
		unsigned long addr;
	} __packed data = {rc, addr};

	zpci_err_hex(&data, sizeof(data));
}

static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
				     unsigned long offset, size_t size,
				     enum dma_data_direction direction,
				     unsigned long attrs)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
	unsigned long pa = page_to_phys(page) + offset;
	int flags = ZPCI_PTE_VALID;
	unsigned long nr_pages;
	dma_addr_t dma_addr;
	int ret;

	/* This rounds up number of pages based on size and offset */
	nr_pages = iommu_num_pages(pa, size, PAGE_SIZE);
	dma_addr = dma_alloc_address(dev, nr_pages);
	if (dma_addr == DMA_MAPPING_ERROR) {
		ret = -ENOSPC;
		goto out_err;
	}

	/* Use rounded up size */
	size = nr_pages * PAGE_SIZE;

	if (direction == DMA_NONE || direction == DMA_TO_DEVICE)
		flags |= ZPCI_TABLE_PROTECTED;

	ret = dma_update_trans(zdev, pa, dma_addr, size, flags);
	if (ret)
		goto out_free;

	atomic64_add(nr_pages, &zdev->mapped_pages);
	return dma_addr + (offset & ~PAGE_MASK);

out_free:
	dma_free_address(dev, dma_addr, nr_pages);
out_err:
	zpci_err("map error:\n");
	zpci_err_dma(ret, pa);
	return DMA_MAPPING_ERROR;
}

static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
				 size_t size, enum dma_data_direction direction,
				 unsigned long attrs)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
	int npages, ret;

	npages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
	dma_addr = dma_addr & PAGE_MASK;
	ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE,
			       ZPCI_PTE_INVALID);
	if (ret) {
		zpci_err("unmap error:\n");
		zpci_err_dma(ret, dma_addr);
		return;
	}

	atomic64_add(npages, &zdev->unmapped_pages);
	dma_free_address(dev, dma_addr, npages);
}

static void *s390_dma_alloc(struct device *dev, size_t size,
			    dma_addr_t *dma_handle, gfp_t flag,
			    unsigned long attrs)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
	struct page *page;
	phys_addr_t pa;
	dma_addr_t map;

	size = PAGE_ALIGN(size);
	page = alloc_pages(flag | __GFP_ZERO, get_order(size));
	if (!page)
		return NULL;

	pa = page_to_phys(page);
	map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, 0);
	if (dma_mapping_error(dev, map)) {
		__free_pages(page, get_order(size));
		return NULL;
	}

	atomic64_add(size / PAGE_SIZE, &zdev->allocated_pages);
	if (dma_handle)
		*dma_handle = map;
	return phys_to_virt(pa);
}

static void s390_dma_free(struct device *dev, size_t size,
			  void *vaddr, dma_addr_t dma_handle,
			  unsigned long attrs)
{
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));

	size = PAGE_ALIGN(size);
	atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages);
	s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, 0);
	free_pages((unsigned long)vaddr, get_order(size));
}

/* Map a segment into a contiguous dma address area */
static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
			     size_t size, dma_addr_t *handle,
			     enum dma_data_direction dir)
{
	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
	dma_addr_t dma_addr_base, dma_addr;
	int flags = ZPCI_PTE_VALID;
	struct scatterlist *s;
	phys_addr_t pa = 0;
	int ret;

	dma_addr_base = dma_alloc_address(dev, nr_pages);
	if (dma_addr_base == DMA_MAPPING_ERROR)
		return -ENOMEM;

	dma_addr = dma_addr_base;
	if (dir == DMA_NONE || dir == DMA_TO_DEVICE)
		flags |= ZPCI_TABLE_PROTECTED;

	for (s = sg; dma_addr < dma_addr_base + size; s = sg_next(s)) {
		pa = page_to_phys(sg_page(s));
		ret = __dma_update_trans(zdev, pa, dma_addr,
					 s->offset + s->length, flags);
		if (ret)
			goto unmap;

		dma_addr += s->offset + s->length;
	}
	ret = __dma_purge_tlb(zdev, dma_addr_base, size, flags);
	if (ret)
		goto unmap;

	*handle = dma_addr_base;
	atomic64_add(nr_pages, &zdev->mapped_pages);

	return ret;

unmap:
	dma_update_trans(zdev, 0, dma_addr_base, dma_addr - dma_addr_base,
			 ZPCI_PTE_INVALID);
	dma_free_address(dev, dma_addr_base, nr_pages);
	zpci_err("map error:\n");
	zpci_err_dma(ret, pa);
	return ret;
}

static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
			   int nr_elements, enum dma_data_direction dir,
			   unsigned long attrs)
{
	struct scatterlist *s = sg, *start = sg, *dma = sg;
	unsigned int max = dma_get_max_seg_size(dev);
	unsigned int size = s->offset + s->length;
	unsigned int offset = s->offset;
	int count = 0, i, ret;

	for (i = 1; i < nr_elements; i++) {
		s = sg_next(s);

		s->dma_length = 0;

		if (s->offset || (size & ~PAGE_MASK) ||
		    size + s->length > max) {
			ret = __s390_dma_map_sg(dev, start, size,
						&dma->dma_address, dir);
			if (ret)
				goto unmap;

			dma->dma_address += offset;
			dma->dma_length = size - offset;

			size = offset = s->offset;
			start = s;
			dma = sg_next(dma);
			count++;
		}
		size += s->length;
	}
	ret = __s390_dma_map_sg(dev, start, size, &dma->dma_address, dir);
	if (ret)
		goto unmap;

	dma->dma_address += offset;
	dma->dma_length = size - offset;

	return count + 1;
unmap:
	for_each_sg(sg, s, count, i)
		s390_dma_unmap_pages(dev, sg_dma_address(s), sg_dma_len(s),
				     dir, attrs);

	return ret;
}

static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
			      int nr_elements, enum dma_data_direction dir,
			      unsigned long attrs)
{
	struct scatterlist *s;
	int i;

	for_each_sg(sg, s, nr_elements, i) {
		if (s->dma_length)
			s390_dma_unmap_pages(dev, s->dma_address, s->dma_length,
					     dir, attrs);
		s->dma_address = 0;
		s->dma_length = 0;
	}
}
	
int zpci_dma_init_device(struct zpci_dev *zdev)
{
	u8 status;
	int rc;

	/*
	 * At this point, if the device is part of an IOMMU domain, this would
	 * be a strong hint towards a bug in the IOMMU API (common) code and/or
	 * simultaneous access via IOMMU and DMA API. So let's issue a warning.
	 */
	WARN_ON(zdev->s390_domain);

	spin_lock_init(&zdev->iommu_bitmap_lock);

	zdev->dma_table = dma_alloc_cpu_table(GFP_KERNEL);
	if (!zdev->dma_table) {
		rc = -ENOMEM;
		goto out;
	}

	/*
	 * Restrict the iommu bitmap size to the minimum of the following:
	 * - s390_iommu_aperture which defaults to high_memory
	 * - 3-level pagetable address limit minus start_dma offset
	 * - DMA address range allowed by the hardware (clp query pci fn)
	 *
	 * Also set zdev->end_dma to the actual end address of the usable
	 * range, instead of the theoretical maximum as reported by hardware.
	 *
	 * This limits the number of concurrently usable DMA mappings since
	 * for each DMA mapped memory address we need a DMA address including
	 * extra DMA addresses for multiple mappings of the same memory address.
	 */
	zdev->start_dma = PAGE_ALIGN(zdev->start_dma);
	zdev->iommu_size = min3(s390_iommu_aperture,
				ZPCI_TABLE_SIZE_RT - zdev->start_dma,
				zdev->end_dma - zdev->start_dma + 1);
	zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
	zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
	zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
	if (!zdev->iommu_bitmap) {
		rc = -ENOMEM;
		goto free_dma_table;
	}
	if (!s390_iommu_strict) {
		zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8);
		if (!zdev->lazy_bitmap) {
			rc = -ENOMEM;
			goto free_bitmap;
		}

	}
	if (zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
			       virt_to_phys(zdev->dma_table), &status)) {
		rc = -EIO;
		goto free_bitmap;
	}

	return 0;
free_bitmap:
	vfree(zdev->iommu_bitmap);
	zdev->iommu_bitmap = NULL;
	vfree(zdev->lazy_bitmap);
	zdev->lazy_bitmap = NULL;
free_dma_table:
	dma_free_cpu_table(zdev->dma_table);
	zdev->dma_table = NULL;
out:
	return rc;
}

int zpci_dma_exit_device(struct zpci_dev *zdev)
{
	int cc = 0;

	/*
	 * At this point, if the device is part of an IOMMU domain, this would
	 * be a strong hint towards a bug in the IOMMU API (common) code and/or
	 * simultaneous access via IOMMU and DMA API. So let's issue a warning.
	 */
	WARN_ON(zdev->s390_domain);
	if (zdev_enabled(zdev))
		cc = zpci_unregister_ioat(zdev, 0);
	/*
	 * cc == 3 indicates the function is gone already. This can happen
	 * if the function was deconfigured/disabled suddenly and we have not
	 * received a new handle yet.
	 */
	if (cc && cc != 3)
		return -EIO;

	dma_cleanup_tables(zdev->dma_table);
	zdev->dma_table = NULL;
	vfree(zdev->iommu_bitmap);
	zdev->iommu_bitmap = NULL;
	vfree(zdev->lazy_bitmap);
	zdev->lazy_bitmap = NULL;
	zdev->next_bit = 0;
	return 0;
}

static int __init dma_alloc_cpu_table_caches(void)
{
	dma_region_table_cache = kmem_cache_create("PCI_DMA_region_tables",
					ZPCI_TABLE_SIZE, ZPCI_TABLE_ALIGN,
					0, NULL);
	if (!dma_region_table_cache)
		return -ENOMEM;

	dma_page_table_cache = kmem_cache_create("PCI_DMA_page_tables",
					ZPCI_PT_SIZE, ZPCI_PT_ALIGN,
					0, NULL);
	if (!dma_page_table_cache) {
		kmem_cache_destroy(dma_region_table_cache);
		return -ENOMEM;
	}
	return 0;
}

int __init zpci_dma_init(void)
{
	s390_iommu_aperture = (u64)virt_to_phys(high_memory);
	if (!s390_iommu_aperture_factor)
		s390_iommu_aperture = ULONG_MAX;
	else
		s390_iommu_aperture *= s390_iommu_aperture_factor;

	return dma_alloc_cpu_table_caches();
}

void zpci_dma_exit(void)
{
	kmem_cache_destroy(dma_page_table_cache);
	kmem_cache_destroy(dma_region_table_cache);
}

const struct dma_map_ops s390_pci_dma_ops = {
	.alloc		= s390_dma_alloc,
	.free		= s390_dma_free,
	.map_sg		= s390_dma_map_sg,
	.unmap_sg	= s390_dma_unmap_sg,
	.map_page	= s390_dma_map_pages,
	.unmap_page	= s390_dma_unmap_pages,
	.mmap		= dma_common_mmap,
	.get_sgtable	= dma_common_get_sgtable,
	.alloc_pages	= dma_common_alloc_pages,
	.free_pages	= dma_common_free_pages,
	/* dma_supported is unconditionally true without a callback */
};
EXPORT_SYMBOL_GPL(s390_pci_dma_ops);

static int __init s390_iommu_setup(char *str)
{
	if (!strcmp(str, "strict"))
		s390_iommu_strict = 1;
	return 1;
}

__setup("s390_iommu=", s390_iommu_setup);

static int __init s390_iommu_aperture_setup(char *str)
{
	if (kstrtou32(str, 10, &s390_iommu_aperture_factor))
		s390_iommu_aperture_factor = 1;
	return 1;
}

__setup("s390_iommu_aperture=", s390_iommu_aperture_setup);