summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/iommu.c
blob: 88e3ec6e1d965a38ade11ecff745e8c029e84ced (plain) (blame)
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
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
/*
 * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
 * 
 * Rewrite, cleanup, new allocation schemes, virtual merging: 
 * Copyright (C) 2004 Olof Johansson, IBM Corporation
 *               and  Ben. Herrenschmidt, IBM Corporation
 *
 * Dynamic DMA mapping support, bus-independent parts.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 * 
 * 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, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 */


#include <linux/init.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/dma-mapping.h>
#include <linux/bitmap.h>
#include <linux/iommu-helper.h>
#include <linux/crash_dump.h>
#include <linux/hash.h>
#include <linux/fault-inject.h>
#include <linux/pci.h>
#include <linux/iommu.h>
#include <linux/sched.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/iommu.h>
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
#include <asm/kdump.h>
#include <asm/fadump.h>
#include <asm/vio.h>
#include <asm/tce.h>

#define DBG(...)

static int novmerge;

static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int);

static int __init setup_iommu(char *str)
{
	if (!strcmp(str, "novmerge"))
		novmerge = 1;
	else if (!strcmp(str, "vmerge"))
		novmerge = 0;
	return 1;
}

__setup("iommu=", setup_iommu);

static DEFINE_PER_CPU(unsigned int, iommu_pool_hash);

/*
 * We precalculate the hash to avoid doing it on every allocation.
 *
 * The hash is important to spread CPUs across all the pools. For example,
 * on a POWER7 with 4 way SMT we want interrupts on the primary threads and
 * with 4 pools all primary threads would map to the same pool.
 */
static int __init setup_iommu_pool_hash(void)
{
	unsigned int i;

	for_each_possible_cpu(i)
		per_cpu(iommu_pool_hash, i) = hash_32(i, IOMMU_POOL_HASHBITS);

	return 0;
}
subsys_initcall(setup_iommu_pool_hash);

#ifdef CONFIG_FAIL_IOMMU

static DECLARE_FAULT_ATTR(fail_iommu);

static int __init setup_fail_iommu(char *str)
{
	return setup_fault_attr(&fail_iommu, str);
}
__setup("fail_iommu=", setup_fail_iommu);

static bool should_fail_iommu(struct device *dev)
{
	return dev->archdata.fail_iommu && should_fail(&fail_iommu, 1);
}

static int __init fail_iommu_debugfs(void)
{
	struct dentry *dir = fault_create_debugfs_attr("fail_iommu",
						       NULL, &fail_iommu);

	return PTR_ERR_OR_ZERO(dir);
}
late_initcall(fail_iommu_debugfs);

static ssize_t fail_iommu_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", dev->archdata.fail_iommu);
}

static ssize_t fail_iommu_store(struct device *dev,
				struct device_attribute *attr, const char *buf,
				size_t count)
{
	int i;

	if (count > 0 && sscanf(buf, "%d", &i) > 0)
		dev->archdata.fail_iommu = (i == 0) ? 0 : 1;

	return count;
}

static DEVICE_ATTR(fail_iommu, S_IRUGO|S_IWUSR, fail_iommu_show,
		   fail_iommu_store);

static int fail_iommu_bus_notify(struct notifier_block *nb,
				 unsigned long action, void *data)
{
	struct device *dev = data;

	if (action == BUS_NOTIFY_ADD_DEVICE) {
		if (device_create_file(dev, &dev_attr_fail_iommu))
			pr_warn("Unable to create IOMMU fault injection sysfs "
				"entries\n");
	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
		device_remove_file(dev, &dev_attr_fail_iommu);
	}

	return 0;
}

static struct notifier_block fail_iommu_bus_notifier = {
	.notifier_call = fail_iommu_bus_notify
};

static int __init fail_iommu_setup(void)
{
#ifdef CONFIG_PCI
	bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier);
#endif
#ifdef CONFIG_IBMVIO
	bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier);
#endif

	return 0;
}
/*
 * Must execute after PCI and VIO subsystem have initialised but before
 * devices are probed.
 */
arch_initcall(fail_iommu_setup);
#else
static inline bool should_fail_iommu(struct device *dev)
{
	return false;
}
#endif

static unsigned long iommu_range_alloc(struct device *dev,
				       struct iommu_table *tbl,
                                       unsigned long npages,
                                       unsigned long *handle,
                                       unsigned long mask,
                                       unsigned int align_order)
{ 
	unsigned long n, end, start;
	unsigned long limit;
	int largealloc = npages > 15;
	int pass = 0;
	unsigned long align_mask;
	unsigned long boundary_size;
	unsigned long flags;
	unsigned int pool_nr;
	struct iommu_pool *pool;

	align_mask = 0xffffffffffffffffl >> (64 - align_order);

	/* This allocator was derived from x86_64's bit string search */

	/* Sanity check */
	if (unlikely(npages == 0)) {
		if (printk_ratelimit())
			WARN_ON(1);
		return DMA_ERROR_CODE;
	}

	if (should_fail_iommu(dev))
		return DMA_ERROR_CODE;

	/*
	 * We don't need to disable preemption here because any CPU can
	 * safely use any IOMMU pool.
	 */
	pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1);

	if (largealloc)
		pool = &(tbl->large_pool);
	else
		pool = &(tbl->pools[pool_nr]);

	spin_lock_irqsave(&(pool->lock), flags);

again:
	if ((pass == 0) && handle && *handle &&
	    (*handle >= pool->start) && (*handle < pool->end))
		start = *handle;
	else
		start = pool->hint;

	limit = pool->end;

	/* The case below can happen if we have a small segment appended
	 * to a large, or when the previous alloc was at the very end of
	 * the available space. If so, go back to the initial start.
	 */
	if (start >= limit)
		start = pool->start;

	if (limit + tbl->it_offset > mask) {
		limit = mask - tbl->it_offset + 1;
		/* If we're constrained on address range, first try
		 * at the masked hint to avoid O(n) search complexity,
		 * but on second pass, start at 0 in pool 0.
		 */
		if ((start & mask) >= limit || pass > 0) {
			spin_unlock(&(pool->lock));
			pool = &(tbl->pools[0]);
			spin_lock(&(pool->lock));
			start = pool->start;
		} else {
			start &= mask;
		}
	}

	if (dev)
		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
				      1 << tbl->it_page_shift);
	else
		boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */

	n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
			     boundary_size >> tbl->it_page_shift, align_mask);
	if (n == -1) {
		if (likely(pass == 0)) {
			/* First try the pool from the start */
			pool->hint = pool->start;
			pass++;
			goto again;

		} else if (pass <= tbl->nr_pools) {
			/* Now try scanning all the other pools */
			spin_unlock(&(pool->lock));
			pool_nr = (pool_nr + 1) & (tbl->nr_pools - 1);
			pool = &tbl->pools[pool_nr];
			spin_lock(&(pool->lock));
			pool->hint = pool->start;
			pass++;
			goto again;

		} else {
			/* Give up */
			spin_unlock_irqrestore(&(pool->lock), flags);
			return DMA_ERROR_CODE;
		}
	}

	end = n + npages;

	/* Bump the hint to a new block for small allocs. */
	if (largealloc) {
		/* Don't bump to new block to avoid fragmentation */
		pool->hint = end;
	} else {
		/* Overflow will be taken care of at the next allocation */
		pool->hint = (end + tbl->it_blocksize - 1) &
		                ~(tbl->it_blocksize - 1);
	}

	/* Update handle for SG allocations */
	if (handle)
		*handle = end;

	spin_unlock_irqrestore(&(pool->lock), flags);

	return n;
}

static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
			      void *page, unsigned int npages,
			      enum dma_data_direction direction,
			      unsigned long mask, unsigned int align_order,
			      struct dma_attrs *attrs)
{
	unsigned long entry;
	dma_addr_t ret = DMA_ERROR_CODE;
	int build_fail;

	entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);

	if (unlikely(entry == DMA_ERROR_CODE))
		return DMA_ERROR_CODE;

	entry += tbl->it_offset;	/* Offset into real TCE table */
	ret = entry << tbl->it_page_shift;	/* Set the return dma address */

	/* Put the TCEs in the HW table */
	build_fail = ppc_md.tce_build(tbl, entry, npages,
				      (unsigned long)page &
				      IOMMU_PAGE_MASK(tbl), direction, attrs);

	/* ppc_md.tce_build() only returns non-zero for transient errors.
	 * Clean up the table bitmap in this case and return
	 * DMA_ERROR_CODE. For all other errors the functionality is
	 * not altered.
	 */
	if (unlikely(build_fail)) {
		__iommu_free(tbl, ret, npages);
		return DMA_ERROR_CODE;
	}

	/* Flush/invalidate TLB caches if necessary */
	if (ppc_md.tce_flush)
		ppc_md.tce_flush(tbl);

	/* Make sure updates are seen by hardware */
	mb();

	return ret;
}

static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr,
			     unsigned int npages)
{
	unsigned long entry, free_entry;

	entry = dma_addr >> tbl->it_page_shift;
	free_entry = entry - tbl->it_offset;

	if (((free_entry + npages) > tbl->it_size) ||
	    (entry < tbl->it_offset)) {
		if (printk_ratelimit()) {
			printk(KERN_INFO "iommu_free: invalid entry\n");
			printk(KERN_INFO "\tentry     = 0x%lx\n", entry); 
			printk(KERN_INFO "\tdma_addr  = 0x%llx\n", (u64)dma_addr);
			printk(KERN_INFO "\tTable     = 0x%llx\n", (u64)tbl);
			printk(KERN_INFO "\tbus#      = 0x%llx\n", (u64)tbl->it_busno);
			printk(KERN_INFO "\tsize      = 0x%llx\n", (u64)tbl->it_size);
			printk(KERN_INFO "\tstartOff  = 0x%llx\n", (u64)tbl->it_offset);
			printk(KERN_INFO "\tindex     = 0x%llx\n", (u64)tbl->it_index);
			WARN_ON(1);
		}

		return false;
	}

	return true;
}

static struct iommu_pool *get_pool(struct iommu_table *tbl,
				   unsigned long entry)
{
	struct iommu_pool *p;
	unsigned long largepool_start = tbl->large_pool.start;

	/* The large pool is the last pool at the top of the table */
	if (entry >= largepool_start) {
		p = &tbl->large_pool;
	} else {
		unsigned int pool_nr = entry / tbl->poolsize;

		BUG_ON(pool_nr > tbl->nr_pools);
		p = &tbl->pools[pool_nr];
	}

	return p;
}

static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
			 unsigned int npages)
{
	unsigned long entry, free_entry;
	unsigned long flags;
	struct iommu_pool *pool;

	entry = dma_addr >> tbl->it_page_shift;
	free_entry = entry - tbl->it_offset;

	pool = get_pool(tbl, free_entry);

	if (!iommu_free_check(tbl, dma_addr, npages))
		return;

	ppc_md.tce_free(tbl, entry, npages);

	spin_lock_irqsave(&(pool->lock), flags);
	bitmap_clear(tbl->it_map, free_entry, npages);
	spin_unlock_irqrestore(&(pool->lock), flags);
}

static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
		unsigned int npages)
{
	__iommu_free(tbl, dma_addr, npages);

	/* Make sure TLB cache is flushed if the HW needs it. We do
	 * not do an mb() here on purpose, it is not needed on any of
	 * the current platforms.
	 */
	if (ppc_md.tce_flush)
		ppc_md.tce_flush(tbl);
}

int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
		 struct scatterlist *sglist, int nelems,
		 unsigned long mask, enum dma_data_direction direction,
		 struct dma_attrs *attrs)
{
	dma_addr_t dma_next = 0, dma_addr;
	struct scatterlist *s, *outs, *segstart;
	int outcount, incount, i, build_fail = 0;
	unsigned int align;
	unsigned long handle;
	unsigned int max_seg_size;

	BUG_ON(direction == DMA_NONE);

	if ((nelems == 0) || !tbl)
		return 0;

	outs = s = segstart = &sglist[0];
	outcount = 1;
	incount = nelems;
	handle = 0;

	/* Init first segment length for backout at failure */
	outs->dma_length = 0;

	DBG("sg mapping %d elements:\n", nelems);

	max_seg_size = dma_get_max_seg_size(dev);
	for_each_sg(sglist, s, nelems, i) {
		unsigned long vaddr, npages, entry, slen;

		slen = s->length;
		/* Sanity check */
		if (slen == 0) {
			dma_next = 0;
			continue;
		}
		/* Allocate iommu entries for that segment */
		vaddr = (unsigned long) sg_virt(s);
		npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl));
		align = 0;
		if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE &&
		    (vaddr & ~PAGE_MASK) == 0)
			align = PAGE_SHIFT - tbl->it_page_shift;
		entry = iommu_range_alloc(dev, tbl, npages, &handle,
					  mask >> tbl->it_page_shift, align);

		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);

		/* Handle failure */
		if (unlikely(entry == DMA_ERROR_CODE)) {
			if (printk_ratelimit())
				dev_info(dev, "iommu_alloc failed, tbl %p "
					 "vaddr %lx npages %lu\n", tbl, vaddr,
					 npages);
			goto failure;
		}

		/* Convert entry to a dma_addr_t */
		entry += tbl->it_offset;
		dma_addr = entry << tbl->it_page_shift;
		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));

		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
			    npages, entry, dma_addr);

		/* Insert into HW table */
		build_fail = ppc_md.tce_build(tbl, entry, npages,
					      vaddr & IOMMU_PAGE_MASK(tbl),
					      direction, attrs);
		if(unlikely(build_fail))
			goto failure;

		/* If we are in an open segment, try merging */
		if (segstart != s) {
			DBG("  - trying merge...\n");
			/* We cannot merge if:
			 * - allocated dma_addr isn't contiguous to previous allocation
			 */
			if (novmerge || (dma_addr != dma_next) ||
			    (outs->dma_length + s->length > max_seg_size)) {
				/* Can't merge: create a new segment */
				segstart = s;
				outcount++;
				outs = sg_next(outs);
				DBG("    can't merge, new segment.\n");
			} else {
				outs->dma_length += s->length;
				DBG("    merged, new len: %ux\n", outs->dma_length);
			}
		}

		if (segstart == s) {
			/* This is a new segment, fill entries */
			DBG("  - filling new segment.\n");
			outs->dma_address = dma_addr;
			outs->dma_length = slen;
		}

		/* Calculate next page pointer for contiguous check */
		dma_next = dma_addr + slen;

		DBG("  - dma next is: %lx\n", dma_next);
	}

	/* Flush/invalidate TLB caches if necessary */
	if (ppc_md.tce_flush)
		ppc_md.tce_flush(tbl);

	DBG("mapped %d elements:\n", outcount);

	/* For the sake of iommu_unmap_sg, we clear out the length in the
	 * next entry of the sglist if we didn't fill the list completely
	 */
	if (outcount < incount) {
		outs = sg_next(outs);
		outs->dma_address = DMA_ERROR_CODE;
		outs->dma_length = 0;
	}

	/* Make sure updates are seen by hardware */
	mb();

	return outcount;

 failure:
	for_each_sg(sglist, s, nelems, i) {
		if (s->dma_length != 0) {
			unsigned long vaddr, npages;

			vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl);
			npages = iommu_num_pages(s->dma_address, s->dma_length,
						 IOMMU_PAGE_SIZE(tbl));
			__iommu_free(tbl, vaddr, npages);
			s->dma_address = DMA_ERROR_CODE;
			s->dma_length = 0;
		}
		if (s == outs)
			break;
	}
	return 0;
}


void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
		int nelems, enum dma_data_direction direction,
		struct dma_attrs *attrs)
{
	struct scatterlist *sg;

	BUG_ON(direction == DMA_NONE);

	if (!tbl)
		return;

	sg = sglist;
	while (nelems--) {
		unsigned int npages;
		dma_addr_t dma_handle = sg->dma_address;

		if (sg->dma_length == 0)
			break;
		npages = iommu_num_pages(dma_handle, sg->dma_length,
					 IOMMU_PAGE_SIZE(tbl));
		__iommu_free(tbl, dma_handle, npages);
		sg = sg_next(sg);
	}

	/* Flush/invalidate TLBs if necessary. As for iommu_free(), we
	 * do not do an mb() here, the affected platforms do not need it
	 * when freeing.
	 */
	if (ppc_md.tce_flush)
		ppc_md.tce_flush(tbl);
}

static void iommu_table_clear(struct iommu_table *tbl)
{
	/*
	 * In case of firmware assisted dump system goes through clean
	 * reboot process at the time of system crash. Hence it's safe to
	 * clear the TCE entries if firmware assisted dump is active.
	 */
	if (!is_kdump_kernel() || is_fadump_active()) {
		/* Clear the table in case firmware left allocations in it */
		ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
		return;
	}

#ifdef CONFIG_CRASH_DUMP
	if (ppc_md.tce_get) {
		unsigned long index, tceval, tcecount = 0;

		/* Reserve the existing mappings left by the first kernel. */
		for (index = 0; index < tbl->it_size; index++) {
			tceval = ppc_md.tce_get(tbl, index + tbl->it_offset);
			/*
			 * Freed TCE entry contains 0x7fffffffffffffff on JS20
			 */
			if (tceval && (tceval != 0x7fffffffffffffffUL)) {
				__set_bit(index, tbl->it_map);
				tcecount++;
			}
		}

		if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) {
			printk(KERN_WARNING "TCE table is full; freeing ");
			printk(KERN_WARNING "%d entries for the kdump boot\n",
				KDUMP_MIN_TCE_ENTRIES);
			for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES;
				index < tbl->it_size; index++)
				__clear_bit(index, tbl->it_map);
		}
	}
#endif
}

/*
 * Build a iommu_table structure.  This contains a bit map which
 * is used to manage allocation of the tce space.
 */
struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
{
	unsigned long sz;
	static int welcomed = 0;
	struct page *page;
	unsigned int i;
	struct iommu_pool *p;

	/* number of bytes needed for the bitmap */
	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);

	page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
	if (!page)
		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
	tbl->it_map = page_address(page);
	memset(tbl->it_map, 0, sz);

	/*
	 * Reserve page 0 so it will not be used for any mappings.
	 * This avoids buggy drivers that consider page 0 to be invalid
	 * to crash the machine or even lose data.
	 */
	if (tbl->it_offset == 0)
		set_bit(0, tbl->it_map);

	/* We only split the IOMMU table if we have 1GB or more of space */
	if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024))
		tbl->nr_pools = IOMMU_NR_POOLS;
	else
		tbl->nr_pools = 1;

	/* We reserve the top 1/4 of the table for large allocations */
	tbl->poolsize = (tbl->it_size * 3 / 4) / tbl->nr_pools;

	for (i = 0; i < tbl->nr_pools; i++) {
		p = &tbl->pools[i];
		spin_lock_init(&(p->lock));
		p->start = tbl->poolsize * i;
		p->hint = p->start;
		p->end = p->start + tbl->poolsize;
	}

	p = &tbl->large_pool;
	spin_lock_init(&(p->lock));
	p->start = tbl->poolsize * i;
	p->hint = p->start;
	p->end = tbl->it_size;

	iommu_table_clear(tbl);

	if (!welcomed) {
		printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
		       novmerge ? "disabled" : "enabled");
		welcomed = 1;
	}

	return tbl;
}

void iommu_free_table(struct iommu_table *tbl, const char *node_name)
{
	unsigned long bitmap_sz;
	unsigned int order;

	if (!tbl || !tbl->it_map) {
		printk(KERN_ERR "%s: expected TCE map for %s\n", __func__,
				node_name);
		return;
	}

	/*
	 * In case we have reserved the first bit, we should not emit
	 * the warning below.
	 */
	if (tbl->it_offset == 0)
		clear_bit(0, tbl->it_map);

#ifdef CONFIG_IOMMU_API
	if (tbl->it_group) {
		iommu_group_put(tbl->it_group);
		BUG_ON(tbl->it_group);
	}
#endif

	/* verify that table contains no entries */
	if (!bitmap_empty(tbl->it_map, tbl->it_size))
		pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);

	/* calculate bitmap size in bytes */
	bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);

	/* free bitmap */
	order = get_order(bitmap_sz);
	free_pages((unsigned long) tbl->it_map, order);

	/* free table */
	kfree(tbl);
}

/* Creates TCEs for a user provided buffer.  The user buffer must be
 * contiguous real kernel storage (not vmalloc).  The address passed here
 * comprises a page address and offset into that page. The dma_addr_t
 * returned will point to the same byte within the page as was passed in.
 */
dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
			  struct page *page, unsigned long offset, size_t size,
			  unsigned long mask, enum dma_data_direction direction,
			  struct dma_attrs *attrs)
{
	dma_addr_t dma_handle = DMA_ERROR_CODE;
	void *vaddr;
	unsigned long uaddr;
	unsigned int npages, align;

	BUG_ON(direction == DMA_NONE);

	vaddr = page_address(page) + offset;
	uaddr = (unsigned long)vaddr;
	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl));

	if (tbl) {
		align = 0;
		if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE &&
		    ((unsigned long)vaddr & ~PAGE_MASK) == 0)
			align = PAGE_SHIFT - tbl->it_page_shift;

		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
					 mask >> tbl->it_page_shift, align,
					 attrs);
		if (dma_handle == DMA_ERROR_CODE) {
			if (printk_ratelimit())  {
				dev_info(dev, "iommu_alloc failed, tbl %p "
					 "vaddr %p npages %d\n", tbl, vaddr,
					 npages);
			}
		} else
			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl));
	}

	return dma_handle;
}

void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
		      size_t size, enum dma_data_direction direction,
		      struct dma_attrs *attrs)
{
	unsigned int npages;

	BUG_ON(direction == DMA_NONE);

	if (tbl) {
		npages = iommu_num_pages(dma_handle, size,
					 IOMMU_PAGE_SIZE(tbl));
		iommu_free(tbl, dma_handle, npages);
	}
}

/* Allocates a contiguous real buffer and creates mappings over it.
 * Returns the virtual address of the buffer and sets dma_handle
 * to the dma address (mapping) of the first page.
 */
void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
			   size_t size,	dma_addr_t *dma_handle,
			   unsigned long mask, gfp_t flag, int node)
{
	void *ret = NULL;
	dma_addr_t mapping;
	unsigned int order;
	unsigned int nio_pages, io_order;
	struct page *page;

	size = PAGE_ALIGN(size);
	order = get_order(size);

 	/*
	 * Client asked for way too much space.  This is checked later
	 * anyway.  It is easier to debug here for the drivers than in
	 * the tce tables.
	 */
	if (order >= IOMAP_MAX_ORDER) {
		dev_info(dev, "iommu_alloc_consistent size too large: 0x%lx\n",
			 size);
		return NULL;
	}

	if (!tbl)
		return NULL;

	/* Alloc enough pages (and possibly more) */
	page = alloc_pages_node(node, flag, order);
	if (!page)
		return NULL;
	ret = page_address(page);
	memset(ret, 0, size);

	/* Set up tces to cover the allocated range */
	nio_pages = size >> tbl->it_page_shift;
	io_order = get_iommu_order(size, tbl);
	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
			      mask >> tbl->it_page_shift, io_order, NULL);
	if (mapping == DMA_ERROR_CODE) {
		free_pages((unsigned long)ret, order);
		return NULL;
	}
	*dma_handle = mapping;
	return ret;
}

void iommu_free_coherent(struct iommu_table *tbl, size_t size,
			 void *vaddr, dma_addr_t dma_handle)
{
	if (tbl) {
		unsigned int nio_pages;

		size = PAGE_ALIGN(size);
		nio_pages = size >> tbl->it_page_shift;
		iommu_free(tbl, dma_handle, nio_pages);
		size = PAGE_ALIGN(size);
		free_pages((unsigned long)vaddr, get_order(size));
	}
}

#ifdef CONFIG_IOMMU_API
/*
 * SPAPR TCE API
 */
static void group_release(void *iommu_data)
{
	struct iommu_table *tbl = iommu_data;
	tbl->it_group = NULL;
}

void iommu_register_group(struct iommu_table *tbl,
		int pci_domain_number, unsigned long pe_num)
{
	struct iommu_group *grp;
	char *name;

	grp = iommu_group_alloc();
	if (IS_ERR(grp)) {
		pr_warn("powerpc iommu api: cannot create new group, err=%ld\n",
				PTR_ERR(grp));
		return;
	}
	tbl->it_group = grp;
	iommu_group_set_iommudata(grp, tbl, group_release);
	name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
			pci_domain_number, pe_num);
	if (!name)
		return;
	iommu_group_set_name(grp, name);
	kfree(name);
}

enum dma_data_direction iommu_tce_direction(unsigned long tce)
{
	if ((tce & TCE_PCI_READ) && (tce & TCE_PCI_WRITE))
		return DMA_BIDIRECTIONAL;
	else if (tce & TCE_PCI_READ)
		return DMA_TO_DEVICE;
	else if (tce & TCE_PCI_WRITE)
		return DMA_FROM_DEVICE;
	else
		return DMA_NONE;
}
EXPORT_SYMBOL_GPL(iommu_tce_direction);

void iommu_flush_tce(struct iommu_table *tbl)
{
	/* Flush/invalidate TLB caches if necessary */
	if (ppc_md.tce_flush)
		ppc_md.tce_flush(tbl);

	/* Make sure updates are seen by hardware */
	mb();
}
EXPORT_SYMBOL_GPL(iommu_flush_tce);

int iommu_tce_clear_param_check(struct iommu_table *tbl,
		unsigned long ioba, unsigned long tce_value,
		unsigned long npages)
{
	/* ppc_md.tce_free() does not support any value but 0 */
	if (tce_value)
		return -EINVAL;

	if (ioba & ~IOMMU_PAGE_MASK(tbl))
		return -EINVAL;

	ioba >>= tbl->it_page_shift;
	if (ioba < tbl->it_offset)
		return -EINVAL;

	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
		return -EINVAL;

	return 0;
}
EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);

int iommu_tce_put_param_check(struct iommu_table *tbl,
		unsigned long ioba, unsigned long tce)
{
	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
		return -EINVAL;

	if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ))
		return -EINVAL;

	if (ioba & ~IOMMU_PAGE_MASK(tbl))
		return -EINVAL;

	ioba >>= tbl->it_page_shift;
	if (ioba < tbl->it_offset)
		return -EINVAL;

	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
		return -EINVAL;

	return 0;
}
EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);

unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
{
	unsigned long oldtce;
	struct iommu_pool *pool = get_pool(tbl, entry);

	spin_lock(&(pool->lock));

	oldtce = ppc_md.tce_get(tbl, entry);
	if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
		ppc_md.tce_free(tbl, entry, 1);
	else
		oldtce = 0;

	spin_unlock(&(pool->lock));

	return oldtce;
}
EXPORT_SYMBOL_GPL(iommu_clear_tce);

int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
		unsigned long entry, unsigned long pages)
{
	unsigned long oldtce;
	struct page *page;

	for ( ; pages; --pages, ++entry) {
		oldtce = iommu_clear_tce(tbl, entry);
		if (!oldtce)
			continue;

		page = pfn_to_page(oldtce >> PAGE_SHIFT);
		WARN_ON(!page);
		if (page) {
			if (oldtce & TCE_PCI_WRITE)
				SetPageDirty(page);
			put_page(page);
		}
	}

	return 0;
}
EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);

/*
 * hwaddr is a kernel virtual address here (0xc... bazillion),
 * tce_build converts it to a physical address.
 */
int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
		unsigned long hwaddr, enum dma_data_direction direction)
{
	int ret = -EBUSY;
	unsigned long oldtce;
	struct iommu_pool *pool = get_pool(tbl, entry);

	spin_lock(&(pool->lock));

	oldtce = ppc_md.tce_get(tbl, entry);
	/* Add new entry if it is not busy */
	if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
		ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);

	spin_unlock(&(pool->lock));

	/* if (unlikely(ret))
		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
			__func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl),
				hwaddr, ret); */

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_tce_build);

int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
		unsigned long tce)
{
	int ret;
	struct page *page = NULL;
	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
	enum dma_data_direction direction = iommu_tce_direction(tce);

	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
			direction != DMA_TO_DEVICE, &page);
	if (unlikely(ret != 1)) {
		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
				tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */
		return -EFAULT;
	}
	hwaddr = (unsigned long) page_address(page) + offset;

	ret = iommu_tce_build(tbl, entry, hwaddr, direction);
	if (ret)
		put_page(page);

	if (ret < 0)
		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
			__func__, entry << tbl->it_page_shift, tce, ret);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);

int iommu_take_ownership(struct iommu_table *tbl)
{
	unsigned long sz = (tbl->it_size + 7) >> 3;

	if (tbl->it_offset == 0)
		clear_bit(0, tbl->it_map);

	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
		pr_err("iommu_tce: it_map is not empty");
		return -EBUSY;
	}

	memset(tbl->it_map, 0xff, sz);
	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);

	/*
	 * Disable iommu bypass, otherwise the user can DMA to all of
	 * our physical memory via the bypass window instead of just
	 * the pages that has been explicitly mapped into the iommu
	 */
	if (tbl->set_bypass)
		tbl->set_bypass(tbl, false);

	return 0;
}
EXPORT_SYMBOL_GPL(iommu_take_ownership);

void iommu_release_ownership(struct iommu_table *tbl)
{
	unsigned long sz = (tbl->it_size + 7) >> 3;

	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
	memset(tbl->it_map, 0, sz);

	/* Restore bit#0 set by iommu_init_table() */
	if (tbl->it_offset == 0)
		set_bit(0, tbl->it_map);

	/* The kernel owns the device now, we can restore the iommu bypass */
	if (tbl->set_bypass)
		tbl->set_bypass(tbl, true);
}
EXPORT_SYMBOL_GPL(iommu_release_ownership);

int iommu_add_device(struct device *dev)
{
	struct iommu_table *tbl;
	int ret = 0;

	if (WARN_ON(dev->iommu_group)) {
		pr_warn("iommu_tce: device %s is already in iommu group %d, skipping\n",
				dev_name(dev),
				iommu_group_id(dev->iommu_group));
		return -EBUSY;
	}

	tbl = get_iommu_table_base(dev);
	if (!tbl || !tbl->it_group) {
		pr_debug("iommu_tce: skipping device %s with no tbl\n",
				dev_name(dev));
		return 0;
	}

	pr_debug("iommu_tce: adding %s to iommu group %d\n",
			dev_name(dev), iommu_group_id(tbl->it_group));

	if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) {
		pr_err("iommu_tce: unsupported iommu page size.");
		pr_err("%s has not been added\n", dev_name(dev));
		return -EINVAL;
	}

	ret = iommu_group_add_device(tbl->it_group, dev);
	if (ret < 0)
		pr_err("iommu_tce: %s has not been added, ret=%d\n",
				dev_name(dev), ret);

	return ret;
}
EXPORT_SYMBOL_GPL(iommu_add_device);

void iommu_del_device(struct device *dev)
{
	/*
	 * Some devices might not have IOMMU table and group
	 * and we needn't detach them from the associated
	 * IOMMU groups
	 */
	if (!dev->iommu_group) {
		pr_debug("iommu_tce: skipping device %s with no tbl\n",
			 dev_name(dev));
		return;
	}

	iommu_group_remove_device(dev);
}
EXPORT_SYMBOL_GPL(iommu_del_device);

#endif /* CONFIG_IOMMU_API */