summaryrefslogtreecommitdiff
path: root/drivers/iommu/exynos-iommu.c
blob: 6915235f9e8682cf91b6d90942fa3238b96db24d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
/* linux/drivers/iommu/exynos_iommu.c
 *
 * Copyright (c) 2011 Samsung Electronics Co., Ltd.
 *		http://www.samsung.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.
 */

#ifdef CONFIG_EXYNOS_IOMMU_DEBUG
#define DEBUG
#endif

#include <linux/io.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
#include <linux/clk.h>
#include <linux/err.h>
#include <linux/mm.h>
#include <linux/iommu.h>
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/memblock.h>
#include <linux/export.h>

#include <asm/cacheflush.h>
#include <asm/pgtable.h>

/* We does not consider super section mapping (16MB) */
#define SECT_ORDER 20
#define LPAGE_ORDER 16
#define SPAGE_ORDER 12

#define SECT_SIZE (1 << SECT_ORDER)
#define LPAGE_SIZE (1 << LPAGE_ORDER)
#define SPAGE_SIZE (1 << SPAGE_ORDER)

#define SECT_MASK (~(SECT_SIZE - 1))
#define LPAGE_MASK (~(LPAGE_SIZE - 1))
#define SPAGE_MASK (~(SPAGE_SIZE - 1))

#define lv1ent_fault(sent) (((*(sent) & 3) == 0) || ((*(sent) & 3) == 3))
#define lv1ent_page(sent) ((*(sent) & 3) == 1)
#define lv1ent_section(sent) ((*(sent) & 3) == 2)

#define lv2ent_fault(pent) ((*(pent) & 3) == 0)
#define lv2ent_small(pent) ((*(pent) & 2) == 2)
#define lv2ent_large(pent) ((*(pent) & 3) == 1)

#define section_phys(sent) (*(sent) & SECT_MASK)
#define section_offs(iova) ((iova) & 0xFFFFF)
#define lpage_phys(pent) (*(pent) & LPAGE_MASK)
#define lpage_offs(iova) ((iova) & 0xFFFF)
#define spage_phys(pent) (*(pent) & SPAGE_MASK)
#define spage_offs(iova) ((iova) & 0xFFF)

#define lv1ent_offset(iova) ((iova) >> SECT_ORDER)
#define lv2ent_offset(iova) (((iova) & 0xFF000) >> SPAGE_ORDER)

#define NUM_LV1ENTRIES 4096
#define NUM_LV2ENTRIES 256

#define LV2TABLE_SIZE (NUM_LV2ENTRIES * sizeof(long))

#define SPAGES_PER_LPAGE (LPAGE_SIZE / SPAGE_SIZE)

#define lv2table_base(sent) (*(sent) & 0xFFFFFC00)

#define mk_lv1ent_sect(pa) ((pa) | 2)
#define mk_lv1ent_page(pa) ((pa) | 1)
#define mk_lv2ent_lpage(pa) ((pa) | 1)
#define mk_lv2ent_spage(pa) ((pa) | 2)

#define CTRL_ENABLE	0x5
#define CTRL_BLOCK	0x7
#define CTRL_DISABLE	0x0

#define REG_MMU_CTRL		0x000
#define REG_MMU_CFG		0x004
#define REG_MMU_STATUS		0x008
#define REG_MMU_FLUSH		0x00C
#define REG_MMU_FLUSH_ENTRY	0x010
#define REG_PT_BASE_ADDR	0x014
#define REG_INT_STATUS		0x018
#define REG_INT_CLEAR		0x01C

#define REG_PAGE_FAULT_ADDR	0x024
#define REG_AW_FAULT_ADDR	0x028
#define REG_AR_FAULT_ADDR	0x02C
#define REG_DEFAULT_SLAVE_ADDR	0x030

#define REG_MMU_VERSION		0x034

#define REG_PB0_SADDR		0x04C
#define REG_PB0_EADDR		0x050
#define REG_PB1_SADDR		0x054
#define REG_PB1_EADDR		0x058

static struct kmem_cache *lv2table_kmem_cache;

static unsigned long *section_entry(unsigned long *pgtable, unsigned long iova)
{
	return pgtable + lv1ent_offset(iova);
}

static unsigned long *page_entry(unsigned long *sent, unsigned long iova)
{
	return (unsigned long *)phys_to_virt(
				lv2table_base(sent)) + lv2ent_offset(iova);
}

enum exynos_sysmmu_inttype {
	SYSMMU_PAGEFAULT,
	SYSMMU_AR_MULTIHIT,
	SYSMMU_AW_MULTIHIT,
	SYSMMU_BUSERROR,
	SYSMMU_AR_SECURITY,
	SYSMMU_AR_ACCESS,
	SYSMMU_AW_SECURITY,
	SYSMMU_AW_PROTECTION, /* 7 */
	SYSMMU_FAULT_UNKNOWN,
	SYSMMU_FAULTS_NUM
};

/*
 * @itype: type of fault.
 * @pgtable_base: the physical address of page table base. This is 0 if @itype
 *                is SYSMMU_BUSERROR.
 * @fault_addr: the device (virtual) address that the System MMU tried to
 *             translated. This is 0 if @itype is SYSMMU_BUSERROR.
 */
typedef int (*sysmmu_fault_handler_t)(enum exynos_sysmmu_inttype itype,
			phys_addr_t pgtable_base, unsigned long fault_addr);

static unsigned short fault_reg_offset[SYSMMU_FAULTS_NUM] = {
	REG_PAGE_FAULT_ADDR,
	REG_AR_FAULT_ADDR,
	REG_AW_FAULT_ADDR,
	REG_DEFAULT_SLAVE_ADDR,
	REG_AR_FAULT_ADDR,
	REG_AR_FAULT_ADDR,
	REG_AW_FAULT_ADDR,
	REG_AW_FAULT_ADDR
};

static char *sysmmu_fault_name[SYSMMU_FAULTS_NUM] = {
	"PAGE FAULT",
	"AR MULTI-HIT FAULT",
	"AW MULTI-HIT FAULT",
	"BUS ERROR",
	"AR SECURITY PROTECTION FAULT",
	"AR ACCESS PROTECTION FAULT",
	"AW SECURITY PROTECTION FAULT",
	"AW ACCESS PROTECTION FAULT",
	"UNKNOWN FAULT"
};

struct exynos_iommu_domain {
	struct list_head clients; /* list of sysmmu_drvdata.node */
	unsigned long *pgtable; /* lv1 page table, 16KB */
	short *lv2entcnt; /* free lv2 entry counter for each section */
	spinlock_t lock; /* lock for this structure */
	spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
};

struct sysmmu_drvdata {
	struct list_head node; /* entry of exynos_iommu_domain.clients */
	struct device *sysmmu;	/* System MMU's device descriptor */
	struct device *dev;	/* Owner of system MMU */
	char *dbgname;
	void __iomem *sfrbase;
	struct clk *clk;
	int activations;
	rwlock_t lock;
	struct iommu_domain *domain;
	sysmmu_fault_handler_t fault_handler;
	phys_addr_t pgtable;
};

static bool set_sysmmu_active(struct sysmmu_drvdata *data)
{
	/* return true if the System MMU was not active previously
	   and it needs to be initialized */
	return ++data->activations == 1;
}

static bool set_sysmmu_inactive(struct sysmmu_drvdata *data)
{
	/* return true if the System MMU is needed to be disabled */
	BUG_ON(data->activations < 1);
	return --data->activations == 0;
}

static bool is_sysmmu_active(struct sysmmu_drvdata *data)
{
	return data->activations > 0;
}

static void sysmmu_unblock(void __iomem *sfrbase)
{
	__raw_writel(CTRL_ENABLE, sfrbase + REG_MMU_CTRL);
}

static bool sysmmu_block(void __iomem *sfrbase)
{
	int i = 120;

	__raw_writel(CTRL_BLOCK, sfrbase + REG_MMU_CTRL);
	while ((i > 0) && !(__raw_readl(sfrbase + REG_MMU_STATUS) & 1))
		--i;

	if (!(__raw_readl(sfrbase + REG_MMU_STATUS) & 1)) {
		sysmmu_unblock(sfrbase);
		return false;
	}

	return true;
}

static void __sysmmu_tlb_invalidate(void __iomem *sfrbase)
{
	__raw_writel(0x1, sfrbase + REG_MMU_FLUSH);
}

static void __sysmmu_tlb_invalidate_entry(void __iomem *sfrbase,
				unsigned long iova, unsigned int num_inv)
{
	unsigned int i;
	for (i = 0; i < num_inv; i++) {
		__raw_writel((iova & SPAGE_MASK) | 1,
				sfrbase + REG_MMU_FLUSH_ENTRY);
		iova += SPAGE_SIZE;
	}
}

static void __sysmmu_set_ptbase(void __iomem *sfrbase,
				       unsigned long pgd)
{
	__raw_writel(0x1, sfrbase + REG_MMU_CFG); /* 16KB LV1, LRU */
	__raw_writel(pgd, sfrbase + REG_PT_BASE_ADDR);

	__sysmmu_tlb_invalidate(sfrbase);
}

static void __set_fault_handler(struct sysmmu_drvdata *data,
					sysmmu_fault_handler_t handler)
{
	unsigned long flags;

	write_lock_irqsave(&data->lock, flags);
	data->fault_handler = handler;
	write_unlock_irqrestore(&data->lock, flags);
}

void exynos_sysmmu_set_fault_handler(struct device *dev,
					sysmmu_fault_handler_t handler)
{
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);

	__set_fault_handler(data, handler);
}

static int default_fault_handler(enum exynos_sysmmu_inttype itype,
			phys_addr_t pgtable_base, unsigned long fault_addr)
{
	unsigned long *ent;

	if ((itype >= SYSMMU_FAULTS_NUM) || (itype < SYSMMU_PAGEFAULT))
		itype = SYSMMU_FAULT_UNKNOWN;

	pr_err("%s occurred at 0x%lx(Page table base: %pa)\n",
			sysmmu_fault_name[itype], fault_addr, &pgtable_base);

	ent = section_entry(phys_to_virt(pgtable_base), fault_addr);
	pr_err("\tLv1 entry: 0x%lx\n", *ent);

	if (lv1ent_page(ent)) {
		ent = page_entry(ent, fault_addr);
		pr_err("\t Lv2 entry: 0x%lx\n", *ent);
	}

	pr_err("Generating Kernel OOPS... because it is unrecoverable.\n");

	BUG();

	return 0;
}

static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
{
	/* SYSMMU is in blocked when interrupt occurred. */
	struct sysmmu_drvdata *data = dev_id;
	enum exynos_sysmmu_inttype itype;
	unsigned long addr = -1;
	int ret = -ENOSYS;

	read_lock(&data->lock);

	WARN_ON(!is_sysmmu_active(data));

	itype = (enum exynos_sysmmu_inttype)
		__ffs(__raw_readl(data->sfrbase + REG_INT_STATUS));
	if (WARN_ON(!((itype >= 0) && (itype < SYSMMU_FAULT_UNKNOWN))))
		itype = SYSMMU_FAULT_UNKNOWN;
	else
		addr = __raw_readl(data->sfrbase + fault_reg_offset[itype]);

	if (data->domain)
		ret = report_iommu_fault(data->domain, data->dev, addr, itype);

	if ((ret == -ENOSYS) && data->fault_handler) {
		unsigned long base = data->pgtable;
		if (itype != SYSMMU_FAULT_UNKNOWN)
			base = __raw_readl(data->sfrbase + REG_PT_BASE_ADDR);
		ret = data->fault_handler(itype, base, addr);
	}

	if (!ret && (itype != SYSMMU_FAULT_UNKNOWN))
		__raw_writel(1 << itype, data->sfrbase + REG_INT_CLEAR);
	else
		dev_dbg(data->sysmmu, "(%s) %s is not handled.\n",
				data->dbgname, sysmmu_fault_name[itype]);

	if (itype != SYSMMU_FAULT_UNKNOWN)
		sysmmu_unblock(data->sfrbase);

	read_unlock(&data->lock);

	return IRQ_HANDLED;
}

static bool __exynos_sysmmu_disable(struct sysmmu_drvdata *data)
{
	unsigned long flags;
	bool disabled = false;

	write_lock_irqsave(&data->lock, flags);

	if (!set_sysmmu_inactive(data))
		goto finish;

	__raw_writel(CTRL_DISABLE, data->sfrbase + REG_MMU_CTRL);

	if (!IS_ERR(data->clk))
		clk_disable(data->clk);

	disabled = true;
	data->pgtable = 0;
	data->domain = NULL;
finish:
	write_unlock_irqrestore(&data->lock, flags);

	if (disabled)
		dev_dbg(data->sysmmu, "(%s) Disabled\n", data->dbgname);
	else
		dev_dbg(data->sysmmu, "(%s) %d times left to be disabled\n",
					data->dbgname, data->activations);

	return disabled;
}

/* __exynos_sysmmu_enable: Enables System MMU
 *
 * returns -error if an error occurred and System MMU is not enabled,
 * 0 if the System MMU has been just enabled and 1 if System MMU was already
 * enabled before.
 */
static int __exynos_sysmmu_enable(struct sysmmu_drvdata *data,
			unsigned long pgtable, struct iommu_domain *domain)
{
	int ret = 0;
	unsigned long flags;

	write_lock_irqsave(&data->lock, flags);

	if (!set_sysmmu_active(data)) {
		if (WARN_ON(pgtable != data->pgtable)) {
			ret = -EBUSY;
			set_sysmmu_inactive(data);
		} else {
			ret = 1;
		}

		dev_dbg(data->sysmmu, "(%s) Already enabled\n", data->dbgname);
		goto finish;
	}

	if (!IS_ERR(data->clk))
		clk_enable(data->clk);

	data->pgtable = pgtable;

	__sysmmu_set_ptbase(data->sfrbase, pgtable);

	__raw_writel(CTRL_ENABLE, data->sfrbase + REG_MMU_CTRL);

	data->domain = domain;

	dev_dbg(data->sysmmu, "(%s) Enabled\n", data->dbgname);
finish:
	write_unlock_irqrestore(&data->lock, flags);

	return ret;
}

int exynos_sysmmu_enable(struct device *dev, unsigned long pgtable)
{
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
	int ret;

	BUG_ON(!memblock_is_memory(pgtable));

	ret = pm_runtime_get_sync(data->sysmmu);
	if (ret < 0) {
		dev_dbg(data->sysmmu, "(%s) Failed to enable\n", data->dbgname);
		return ret;
	}

	ret = __exynos_sysmmu_enable(data, pgtable, NULL);
	if (WARN_ON(ret < 0)) {
		pm_runtime_put(data->sysmmu);
		dev_err(data->sysmmu,
			"(%s) Already enabled with page table %#x\n",
			data->dbgname, data->pgtable);
	} else {
		data->dev = dev;
	}

	return ret;
}

static bool exynos_sysmmu_disable(struct device *dev)
{
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
	bool disabled;

	disabled = __exynos_sysmmu_disable(data);
	pm_runtime_put(data->sysmmu);

	return disabled;
}

static void sysmmu_tlb_invalidate_entry(struct device *dev, unsigned long iova,
					size_t size)
{
	unsigned long flags;
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);

	read_lock_irqsave(&data->lock, flags);

	if (is_sysmmu_active(data)) {
		unsigned int maj;
		unsigned int num_inv = 1;
		maj = __raw_readl(data->sfrbase + REG_MMU_VERSION);
		/*
		 * L2TLB invalidation required
		 * 4KB page: 1 invalidation
		 * 64KB page: 16 invalidation
		 * 1MB page: 64 invalidation
		 * because it is set-associative TLB
		 * with 8-way and 64 sets.
		 * 1MB page can be cached in one of all sets.
		 * 64KB page can be one of 16 consecutive sets.
		 */
		if ((maj >> 28) == 2) /* major version number */
			num_inv = min_t(unsigned int, size / PAGE_SIZE, 64);

		if (sysmmu_block(data->sfrbase)) {
			__sysmmu_tlb_invalidate_entry(
				data->sfrbase, iova, num_inv);
			sysmmu_unblock(data->sfrbase);
		}
	} else {
		dev_dbg(data->sysmmu,
			"(%s) Disabled. Skipping invalidating TLB.\n",
			data->dbgname);
	}

	read_unlock_irqrestore(&data->lock, flags);
}

void exynos_sysmmu_tlb_invalidate(struct device *dev)
{
	unsigned long flags;
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);

	read_lock_irqsave(&data->lock, flags);

	if (is_sysmmu_active(data)) {
		if (sysmmu_block(data->sfrbase)) {
			__sysmmu_tlb_invalidate(data->sfrbase);
			sysmmu_unblock(data->sfrbase);
		}
	} else {
		dev_dbg(data->sysmmu,
			"(%s) Disabled. Skipping invalidating TLB.\n",
			data->dbgname);
	}

	read_unlock_irqrestore(&data->lock, flags);
}

static int exynos_sysmmu_probe(struct platform_device *pdev)
{
	int ret;
	struct device *dev = &pdev->dev;
	struct sysmmu_drvdata *data;
	struct resource *res;

	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data) {
		dev_dbg(dev, "Not enough memory\n");
		ret = -ENOMEM;
		goto err_alloc;
	}

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (!res) {
		dev_dbg(dev, "Unable to find IOMEM region\n");
		ret = -ENOENT;
		goto err_init;
	}

	data->sfrbase = ioremap(res->start, resource_size(res));
	if (!data->sfrbase) {
		dev_dbg(dev, "Unable to map IOMEM @ PA:%#x\n", res->start);
		ret = -ENOENT;
		goto err_res;
	}

	ret = platform_get_irq(pdev, 0);
	if (ret <= 0) {
		dev_dbg(dev, "Unable to find IRQ resource\n");
		goto err_irq;
	}

	ret = request_irq(ret, exynos_sysmmu_irq, 0,
				dev_name(dev), data);
	if (ret) {
		dev_dbg(dev, "Unabled to register interrupt handler\n");
		goto err_irq;
	}

	if (dev_get_platdata(dev)) {
		data->clk = clk_get(dev, "sysmmu");
		if (IS_ERR(data->clk))
			dev_dbg(dev, "No clock descriptor registered\n");
	}

	data->sysmmu = dev;
	rwlock_init(&data->lock);
	INIT_LIST_HEAD(&data->node);

	__set_fault_handler(data, &default_fault_handler);

	platform_set_drvdata(pdev, data);

	if (dev->parent)
		pm_runtime_enable(dev);

	dev_dbg(dev, "(%s) Initialized\n", data->dbgname);
	return 0;
err_irq:
	free_irq(platform_get_irq(pdev, 0), data);
err_res:
	iounmap(data->sfrbase);
err_init:
	kfree(data);
err_alloc:
	dev_err(dev, "Failed to initialize\n");
	return ret;
}

static struct platform_driver exynos_sysmmu_driver = {
	.probe		= exynos_sysmmu_probe,
	.driver		= {
		.owner		= THIS_MODULE,
		.name		= "exynos-sysmmu",
	}
};

static inline void pgtable_flush(void *vastart, void *vaend)
{
	dmac_flush_range(vastart, vaend);
	outer_flush_range(virt_to_phys(vastart),
				virt_to_phys(vaend));
}

static int exynos_iommu_domain_init(struct iommu_domain *domain)
{
	struct exynos_iommu_domain *priv;

	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (!priv)
		return -ENOMEM;

	priv->pgtable = (unsigned long *)__get_free_pages(
						GFP_KERNEL | __GFP_ZERO, 2);
	if (!priv->pgtable)
		goto err_pgtable;

	priv->lv2entcnt = (short *)__get_free_pages(
						GFP_KERNEL | __GFP_ZERO, 1);
	if (!priv->lv2entcnt)
		goto err_counter;

	pgtable_flush(priv->pgtable, priv->pgtable + NUM_LV1ENTRIES);

	spin_lock_init(&priv->lock);
	spin_lock_init(&priv->pgtablelock);
	INIT_LIST_HEAD(&priv->clients);

	domain->geometry.aperture_start = 0;
	domain->geometry.aperture_end   = ~0UL;
	domain->geometry.force_aperture = true;

	domain->priv = priv;
	return 0;

err_counter:
	free_pages((unsigned long)priv->pgtable, 2);
err_pgtable:
	kfree(priv);
	return -ENOMEM;
}

static void exynos_iommu_domain_destroy(struct iommu_domain *domain)
{
	struct exynos_iommu_domain *priv = domain->priv;
	struct sysmmu_drvdata *data;
	unsigned long flags;
	int i;

	WARN_ON(!list_empty(&priv->clients));

	spin_lock_irqsave(&priv->lock, flags);

	list_for_each_entry(data, &priv->clients, node) {
		while (!exynos_sysmmu_disable(data->dev))
			; /* until System MMU is actually disabled */
	}

	spin_unlock_irqrestore(&priv->lock, flags);

	for (i = 0; i < NUM_LV1ENTRIES; i++)
		if (lv1ent_page(priv->pgtable + i))
			kmem_cache_free(lv2table_kmem_cache,
				phys_to_virt(lv2table_base(priv->pgtable + i)));

	free_pages((unsigned long)priv->pgtable, 2);
	free_pages((unsigned long)priv->lv2entcnt, 1);
	kfree(domain->priv);
	domain->priv = NULL;
}

static int exynos_iommu_attach_device(struct iommu_domain *domain,
				   struct device *dev)
{
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
	struct exynos_iommu_domain *priv = domain->priv;
	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
	unsigned long flags;
	int ret;

	ret = pm_runtime_get_sync(data->sysmmu);
	if (ret < 0)
		return ret;

	ret = 0;

	spin_lock_irqsave(&priv->lock, flags);

	ret = __exynos_sysmmu_enable(data, pagetable, domain);

	if (ret == 0) {
		/* 'data->node' must not be appeared in priv->clients */
		BUG_ON(!list_empty(&data->node));
		data->dev = dev;
		list_add_tail(&data->node, &priv->clients);
	}

	spin_unlock_irqrestore(&priv->lock, flags);

	if (ret < 0) {
		dev_err(dev, "%s: Failed to attach IOMMU with pgtable %pa\n",
					__func__, &pagetable);
		pm_runtime_put(data->sysmmu);
		return ret;
	}

	dev_dbg(dev, "%s: Attached IOMMU with pgtable %pa %s\n",
		__func__, &pagetable, (ret == 0) ? "" : ", again");

	return ret;
}

static void exynos_iommu_detach_device(struct iommu_domain *domain,
				    struct device *dev)
{
	struct sysmmu_drvdata *data = dev_get_drvdata(dev->archdata.iommu);
	struct exynos_iommu_domain *priv = domain->priv;
	struct list_head *pos;
	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
	unsigned long flags;
	bool found = false;

	spin_lock_irqsave(&priv->lock, flags);

	list_for_each(pos, &priv->clients) {
		if (list_entry(pos, struct sysmmu_drvdata, node) == data) {
			found = true;
			break;
		}
	}

	if (!found)
		goto finish;

	if (__exynos_sysmmu_disable(data)) {
		dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n",
					__func__, &pagetable);
		list_del_init(&data->node);

	} else {
		dev_dbg(dev, "%s: Detaching IOMMU with pgtable %pa delayed",
					__func__, &pagetable);
	}

finish:
	spin_unlock_irqrestore(&priv->lock, flags);

	if (found)
		pm_runtime_put(data->sysmmu);
}

static unsigned long *alloc_lv2entry(unsigned long *sent, unsigned long iova,
					short *pgcounter)
{
	if (lv1ent_section(sent)) {
		WARN(1, "Trying mapping on %#08lx mapped with 1MiB page", iova);
		return ERR_PTR(-EADDRINUSE);
	}

	if (lv1ent_fault(sent)) {
		unsigned long *pent;

		pent = kmem_cache_zalloc(lv2table_kmem_cache, GFP_ATOMIC);
		BUG_ON((unsigned long)pent & (LV2TABLE_SIZE - 1));
		if (!pent)
			return ERR_PTR(-ENOMEM);

		*sent = mk_lv1ent_page(virt_to_phys(pent));
		*pgcounter = NUM_LV2ENTRIES;
		pgtable_flush(pent, pent + NUM_LV2ENTRIES);
		pgtable_flush(sent, sent + 1);
	}

	return page_entry(sent, iova);
}

static int lv1set_section(unsigned long *sent, unsigned long iova,
			  phys_addr_t paddr, short *pgcnt)
{
	if (lv1ent_section(sent)) {
		WARN(1, "Trying mapping on 1MiB@%#08lx that is mapped",
			iova);
		return -EADDRINUSE;
	}

	if (lv1ent_page(sent)) {
		if (*pgcnt != NUM_LV2ENTRIES) {
			WARN(1, "Trying mapping on 1MiB@%#08lx that is mapped",
				iova);
			return -EADDRINUSE;
		}

		kmem_cache_free(lv2table_kmem_cache, page_entry(sent, 0));
		*pgcnt = 0;
	}

	*sent = mk_lv1ent_sect(paddr);

	pgtable_flush(sent, sent + 1);

	return 0;
}

static int lv2set_page(unsigned long *pent, phys_addr_t paddr, size_t size,
								short *pgcnt)
{
	if (size == SPAGE_SIZE) {
		if (!lv2ent_fault(pent)) {
			WARN(1, "Trying mapping on 4KiB where mapping exists");
			return -EADDRINUSE;
		}

		*pent = mk_lv2ent_spage(paddr);
		pgtable_flush(pent, pent + 1);
		*pgcnt -= 1;
	} else { /* size == LPAGE_SIZE */
		int i;
		for (i = 0; i < SPAGES_PER_LPAGE; i++, pent++) {
			if (!lv2ent_fault(pent)) {
				WARN(1,
				"Trying mapping on 64KiB where mapping exists");
				if (i > 0)
					memset(pent - i, 0, sizeof(*pent) * i);
				return -EADDRINUSE;
			}

			*pent = mk_lv2ent_lpage(paddr);
		}
		pgtable_flush(pent - SPAGES_PER_LPAGE, pent);
		*pgcnt -= SPAGES_PER_LPAGE;
	}

	return 0;
}

static int exynos_iommu_map(struct iommu_domain *domain, unsigned long iova,
			 phys_addr_t paddr, size_t size, int prot)
{
	struct exynos_iommu_domain *priv = domain->priv;
	unsigned long *entry;
	unsigned long flags;
	int ret = -ENOMEM;

	BUG_ON(priv->pgtable == NULL);

	spin_lock_irqsave(&priv->pgtablelock, flags);

	entry = section_entry(priv->pgtable, iova);

	if (size == SECT_SIZE) {
		ret = lv1set_section(entry, iova, paddr,
					&priv->lv2entcnt[lv1ent_offset(iova)]);
	} else {
		unsigned long *pent;

		pent = alloc_lv2entry(entry, iova,
					&priv->lv2entcnt[lv1ent_offset(iova)]);

		if (IS_ERR(pent))
			ret = PTR_ERR(pent);
		else
			ret = lv2set_page(pent, paddr, size,
					&priv->lv2entcnt[lv1ent_offset(iova)]);
	}

	if (ret)
		pr_debug("%s: Failed to map iova 0x%lx/0x%x bytes\n",
							__func__, iova, size);

	spin_unlock_irqrestore(&priv->pgtablelock, flags);

	return ret;
}

static size_t exynos_iommu_unmap(struct iommu_domain *domain,
					       unsigned long iova, size_t size)
{
	struct exynos_iommu_domain *priv = domain->priv;
	struct sysmmu_drvdata *data;
	unsigned long flags;
	unsigned long *ent;
	size_t err_pgsize;

	BUG_ON(priv->pgtable == NULL);

	spin_lock_irqsave(&priv->pgtablelock, flags);

	ent = section_entry(priv->pgtable, iova);

	if (lv1ent_section(ent)) {
		if (size < SECT_SIZE) {
			err_pgsize = SECT_SIZE;
			goto err;
		}

		*ent = 0;
		pgtable_flush(ent, ent + 1);
		size = SECT_SIZE;
		goto done;
	}

	if (unlikely(lv1ent_fault(ent))) {
		if (size > SECT_SIZE)
			size = SECT_SIZE;
		goto done;
	}

	/* lv1ent_page(sent) == true here */

	ent = page_entry(ent, iova);

	if (unlikely(lv2ent_fault(ent))) {
		size = SPAGE_SIZE;
		goto done;
	}

	if (lv2ent_small(ent)) {
		*ent = 0;
		size = SPAGE_SIZE;
		pgtable_flush(ent, ent + 1);
		priv->lv2entcnt[lv1ent_offset(iova)] += 1;
		goto done;
	}

	/* lv1ent_large(ent) == true here */
	if (size < LPAGE_SIZE) {
		err_pgsize = LPAGE_SIZE;
		goto err;
	}

	memset(ent, 0, sizeof(*ent) * SPAGES_PER_LPAGE);
	pgtable_flush(ent, ent + SPAGES_PER_LPAGE);

	size = LPAGE_SIZE;
	priv->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
done:
	spin_unlock_irqrestore(&priv->pgtablelock, flags);

	spin_lock_irqsave(&priv->lock, flags);
	list_for_each_entry(data, &priv->clients, node)
		sysmmu_tlb_invalidate_entry(data->dev, iova, size);
	spin_unlock_irqrestore(&priv->lock, flags);

	return size;
err:
	spin_unlock_irqrestore(&priv->pgtablelock, flags);

	WARN(1,
	"%s: Failed due to size(%#x) @ %#08lx is smaller than page size %#x\n",
	__func__, size, iova, err_pgsize);

	return 0;
}

static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
					  dma_addr_t iova)
{
	struct exynos_iommu_domain *priv = domain->priv;
	unsigned long *entry;
	unsigned long flags;
	phys_addr_t phys = 0;

	spin_lock_irqsave(&priv->pgtablelock, flags);

	entry = section_entry(priv->pgtable, iova);

	if (lv1ent_section(entry)) {
		phys = section_phys(entry) + section_offs(iova);
	} else if (lv1ent_page(entry)) {
		entry = page_entry(entry, iova);

		if (lv2ent_large(entry))
			phys = lpage_phys(entry) + lpage_offs(iova);
		else if (lv2ent_small(entry))
			phys = spage_phys(entry) + spage_offs(iova);
	}

	spin_unlock_irqrestore(&priv->pgtablelock, flags);

	return phys;
}

static struct iommu_ops exynos_iommu_ops = {
	.domain_init = &exynos_iommu_domain_init,
	.domain_destroy = &exynos_iommu_domain_destroy,
	.attach_dev = &exynos_iommu_attach_device,
	.detach_dev = &exynos_iommu_detach_device,
	.map = &exynos_iommu_map,
	.unmap = &exynos_iommu_unmap,
	.iova_to_phys = &exynos_iommu_iova_to_phys,
	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
};

static int __init exynos_iommu_init(void)
{
	int ret;

	lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
				LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
	if (!lv2table_kmem_cache) {
		pr_err("%s: Failed to create kmem cache\n", __func__);
		return -ENOMEM;
	}

	ret = platform_driver_register(&exynos_sysmmu_driver);
	if (ret) {
		pr_err("%s: Failed to register driver\n", __func__);
		goto err_reg_driver;
	}

	ret = bus_set_iommu(&platform_bus_type, &exynos_iommu_ops);
	if (ret) {
		pr_err("%s: Failed to register exynos-iommu driver.\n",
								__func__);
		goto err_set_iommu;
	}

	return 0;
err_set_iommu:
	platform_driver_unregister(&exynos_sysmmu_driver);
err_reg_driver:
	kmem_cache_destroy(lv2table_kmem_cache);
	return ret;
}
subsys_initcall(exynos_iommu_init);