Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: b30926e11d8789e88204196f957112c0f13693e9 (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
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
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
/*
 * VFIO: IOMMU DMA mapping support for TCE on POWER
 *
 * Copyright (C) 2013 IBM Corp.  All rights reserved.
 *     Author: Alexey Kardashevskiy <aik@ozlabs.ru>
 *
 * 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.
 *
 * Derived from original vfio_iommu_type1.c:
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 */

#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/err.h>
#include <linux/vfio.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>

#include <asm/iommu.h>
#include <asm/tce.h>
#include <asm/mmu_context.h>

#define DRIVER_VERSION  "0.1"
#define DRIVER_AUTHOR   "aik@ozlabs.ru"
#define DRIVER_DESC     "VFIO IOMMU SPAPR TCE"

static void tce_iommu_detach_group(void *iommu_data,
		struct iommu_group *iommu_group);

static long try_increment_locked_vm(struct mm_struct *mm, long npages)
{
	long ret = 0, locked, lock_limit;

	if (WARN_ON_ONCE(!mm))
		return -EPERM;

	if (!npages)
		return 0;

	down_write(&mm->mmap_sem);
	locked = mm->locked_vm + npages;
	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
		ret = -ENOMEM;
	else
		mm->locked_vm += npages;

	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
			npages << PAGE_SHIFT,
			mm->locked_vm << PAGE_SHIFT,
			rlimit(RLIMIT_MEMLOCK),
			ret ? " - exceeded" : "");

	up_write(&mm->mmap_sem);

	return ret;
}

static void decrement_locked_vm(struct mm_struct *mm, long npages)
{
	if (!mm || !npages)
		return;

	down_write(&mm->mmap_sem);
	if (WARN_ON_ONCE(npages > mm->locked_vm))
		npages = mm->locked_vm;
	mm->locked_vm -= npages;
	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
			npages << PAGE_SHIFT,
			mm->locked_vm << PAGE_SHIFT,
			rlimit(RLIMIT_MEMLOCK));
	up_write(&mm->mmap_sem);
}

/*
 * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
 *
 * This code handles mapping and unmapping of user data buffers
 * into DMA'ble space using the IOMMU
 */

struct tce_iommu_group {
	struct list_head next;
	struct iommu_group *grp;
};

/*
 * A container needs to remember which preregistered region  it has
 * referenced to do proper cleanup at the userspace process exit.
 */
struct tce_iommu_prereg {
	struct list_head next;
	struct mm_iommu_table_group_mem_t *mem;
};

/*
 * The container descriptor supports only a single group per container.
 * Required by the API as the container is not supplied with the IOMMU group
 * at the moment of initialization.
 */
struct tce_container {
	struct mutex lock;
	bool enabled;
	bool v2;
	bool def_window_pending;
	unsigned long locked_pages;
	struct mm_struct *mm;
	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
	struct list_head group_list;
	struct list_head prereg_list;
};

static long tce_iommu_mm_set(struct tce_container *container)
{
	if (container->mm) {
		if (container->mm == current->mm)
			return 0;
		return -EPERM;
	}
	BUG_ON(!current->mm);
	container->mm = current->mm;
	atomic_inc(&container->mm->mm_count);

	return 0;
}

static long tce_iommu_prereg_free(struct tce_container *container,
		struct tce_iommu_prereg *tcemem)
{
	long ret;

	ret = mm_iommu_put(container->mm, tcemem->mem);
	if (ret)
		return ret;

	list_del(&tcemem->next);
	kfree(tcemem);

	return 0;
}

static long tce_iommu_unregister_pages(struct tce_container *container,
		__u64 vaddr, __u64 size)
{
	struct mm_iommu_table_group_mem_t *mem;
	struct tce_iommu_prereg *tcemem;
	bool found = false;

	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK))
		return -EINVAL;

	mem = mm_iommu_find(container->mm, vaddr, size >> PAGE_SHIFT);
	if (!mem)
		return -ENOENT;

	list_for_each_entry(tcemem, &container->prereg_list, next) {
		if (tcemem->mem == mem) {
			found = true;
			break;
		}
	}

	if (!found)
		return -ENOENT;

	return tce_iommu_prereg_free(container, tcemem);
}

static long tce_iommu_register_pages(struct tce_container *container,
		__u64 vaddr, __u64 size)
{
	long ret = 0;
	struct mm_iommu_table_group_mem_t *mem = NULL;
	struct tce_iommu_prereg *tcemem;
	unsigned long entries = size >> PAGE_SHIFT;

	if ((vaddr & ~PAGE_MASK) || (size & ~PAGE_MASK) ||
			((vaddr + size) < vaddr))
		return -EINVAL;

	mem = mm_iommu_find(container->mm, vaddr, entries);
	if (mem) {
		list_for_each_entry(tcemem, &container->prereg_list, next) {
			if (tcemem->mem == mem)
				return -EBUSY;
		}
	}

	ret = mm_iommu_get(container->mm, vaddr, entries, &mem);
	if (ret)
		return ret;

	tcemem = kzalloc(sizeof(*tcemem), GFP_KERNEL);
	if (!tcemem) {
		mm_iommu_put(container->mm, mem);
		return -ENOMEM;
	}

	tcemem->mem = mem;
	list_add(&tcemem->next, &container->prereg_list);

	container->enabled = true;

	return 0;
}

static bool tce_page_is_contained(struct page *page, unsigned page_shift)
{
	/*
	 * Check that the TCE table granularity is not bigger than the size of
	 * a page we just found. Otherwise the hardware can get access to
	 * a bigger memory chunk that it should.
	 */
	return (PAGE_SHIFT + compound_order(compound_head(page))) >= page_shift;
}

static inline bool tce_groups_attached(struct tce_container *container)
{
	return !list_empty(&container->group_list);
}

static long tce_iommu_find_table(struct tce_container *container,
		phys_addr_t ioba, struct iommu_table **ptbl)
{
	long i;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = container->tables[i];

		if (tbl) {
			unsigned long entry = ioba >> tbl->it_page_shift;
			unsigned long start = tbl->it_offset;
			unsigned long end = start + tbl->it_size;

			if ((start <= entry) && (entry < end)) {
				*ptbl = tbl;
				return i;
			}
		}
	}

	return -1;
}

static int tce_iommu_find_free_table(struct tce_container *container)
{
	int i;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		if (!container->tables[i])
			return i;
	}

	return -ENOSPC;
}

static int tce_iommu_enable(struct tce_container *container)
{
	int ret = 0;
	unsigned long locked;
	struct iommu_table_group *table_group;
	struct tce_iommu_group *tcegrp;

	if (container->enabled)
		return -EBUSY;

	/*
	 * When userspace pages are mapped into the IOMMU, they are effectively
	 * locked memory, so, theoretically, we need to update the accounting
	 * of locked pages on each map and unmap.  For powerpc, the map unmap
	 * paths can be very hot, though, and the accounting would kill
	 * performance, especially since it would be difficult to impossible
	 * to handle the accounting in real mode only.
	 *
	 * To address that, rather than precisely accounting every page, we
	 * instead account for a worst case on locked memory when the iommu is
	 * enabled and disabled.  The worst case upper bound on locked memory
	 * is the size of the whole iommu window, which is usually relatively
	 * small (compared to total memory sizes) on POWER hardware.
	 *
	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
	 * that would effectively kill the guest at random points, much better
	 * enforcing the limit based on the max that the guest can map.
	 *
	 * Unfortunately at the moment it counts whole tables, no matter how
	 * much memory the guest has. I.e. for 4GB guest and 4 IOMMU groups
	 * each with 2GB DMA window, 8GB will be counted here. The reason for
	 * this is that we cannot tell here the amount of RAM used by the guest
	 * as this information is only available from KVM and VFIO is
	 * KVM agnostic.
	 *
	 * So we do not allow enabling a container without a group attached
	 * as there is no way to know how much we should increment
	 * the locked_vm counter.
	 */
	if (!tce_groups_attached(container))
		return -ENODEV;

	tcegrp = list_first_entry(&container->group_list,
			struct tce_iommu_group, next);
	table_group = iommu_group_get_iommudata(tcegrp->grp);
	if (!table_group)
		return -ENODEV;

	if (!table_group->tce32_size)
		return -EPERM;

	ret = tce_iommu_mm_set(container);
	if (ret)
		return ret;

	locked = table_group->tce32_size >> PAGE_SHIFT;
	ret = try_increment_locked_vm(container->mm, locked);
	if (ret)
		return ret;

	container->locked_pages = locked;

	container->enabled = true;

	return ret;
}

static void tce_iommu_disable(struct tce_container *container)
{
	if (!container->enabled)
		return;

	container->enabled = false;

	BUG_ON(!container->mm);
	decrement_locked_vm(container->mm, container->locked_pages);
}

static void *tce_iommu_open(unsigned long arg)
{
	struct tce_container *container;

	if ((arg != VFIO_SPAPR_TCE_IOMMU) && (arg != VFIO_SPAPR_TCE_v2_IOMMU)) {
		pr_err("tce_vfio: Wrong IOMMU type\n");
		return ERR_PTR(-EINVAL);
	}

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

	mutex_init(&container->lock);
	INIT_LIST_HEAD_RCU(&container->group_list);
	INIT_LIST_HEAD_RCU(&container->prereg_list);

	container->v2 = arg == VFIO_SPAPR_TCE_v2_IOMMU;

	return container;
}

static int tce_iommu_clear(struct tce_container *container,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long pages);
static void tce_iommu_free_table(struct tce_container *container,
		struct iommu_table *tbl);

static void tce_iommu_release(void *iommu_data)
{
	struct tce_container *container = iommu_data;
	struct tce_iommu_group *tcegrp;
	long i;

	while (tce_groups_attached(container)) {
		tcegrp = list_first_entry(&container->group_list,
				struct tce_iommu_group, next);
		tce_iommu_detach_group(iommu_data, tcegrp->grp);
	}

	/*
	 * If VFIO created a table, it was not disposed
	 * by tce_iommu_detach_group() so do it now.
	 */
	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = container->tables[i];

		if (!tbl)
			continue;

		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
		tce_iommu_free_table(container, tbl);
	}

	while (!list_empty(&container->prereg_list)) {
		struct tce_iommu_prereg *tcemem;

		tcemem = list_first_entry(&container->prereg_list,
				struct tce_iommu_prereg, next);
		WARN_ON_ONCE(tce_iommu_prereg_free(container, tcemem));
	}

	tce_iommu_disable(container);
	if (container->mm)
		mmdrop(container->mm);
	mutex_destroy(&container->lock);

	kfree(container);
}

static void tce_iommu_unuse_page(struct tce_container *container,
		unsigned long hpa)
{
	struct page *page;

	page = pfn_to_page(hpa >> PAGE_SHIFT);
	put_page(page);
}

static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
		unsigned long tce, unsigned long shift,
		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
{
	long ret = 0;
	struct mm_iommu_table_group_mem_t *mem;

	mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
	if (!mem)
		return -EINVAL;

	ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
	if (ret)
		return -EINVAL;

	*pmem = mem;

	return 0;
}

static void tce_iommu_unuse_page_v2(struct tce_container *container,
		struct iommu_table *tbl, unsigned long entry)
{
	struct mm_iommu_table_group_mem_t *mem = NULL;
	int ret;
	unsigned long hpa = 0;
	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);

	if (!pua)
		return;

	ret = tce_iommu_prereg_ua_to_hpa(container, be64_to_cpu(*pua),
			tbl->it_page_shift, &hpa, &mem);
	if (ret)
		pr_debug("%s: tce %llx at #%lx was not cached, ret=%d\n",
				__func__, be64_to_cpu(*pua), entry, ret);
	if (mem)
		mm_iommu_mapped_dec(mem);

	*pua = cpu_to_be64(0);
}

static int tce_iommu_clear(struct tce_container *container,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long pages)
{
	unsigned long oldhpa;
	long ret;
	enum dma_data_direction direction;
	unsigned long lastentry = entry + pages;

	for ( ; entry < lastentry; ++entry) {
		if (tbl->it_indirect_levels && tbl->it_userspace) {
			/*
			 * For multilevel tables, we can take a shortcut here
			 * and skip some TCEs as we know that the userspace
			 * addresses cache is a mirror of the real TCE table
			 * and if it is missing some indirect levels, then
			 * the hardware table does not have them allocated
			 * either and therefore does not require updating.
			 */
			__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl,
					entry);
			if (!pua) {
				/* align to level_size which is power of two */
				entry |= tbl->it_level_size - 1;
				continue;
			}
		}

		cond_resched();

		direction = DMA_NONE;
		oldhpa = 0;
		ret = iommu_tce_xchg(tbl, entry, &oldhpa, &direction);
		if (ret)
			continue;

		if (direction == DMA_NONE)
			continue;

		if (container->v2) {
			tce_iommu_unuse_page_v2(container, tbl, entry);
			continue;
		}

		tce_iommu_unuse_page(container, oldhpa);
	}

	return 0;
}

static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
{
	struct page *page = NULL;
	enum dma_data_direction direction = iommu_tce_direction(tce);

	if (get_user_pages_fast(tce & PAGE_MASK, 1,
			direction != DMA_TO_DEVICE, &page) != 1)
		return -EFAULT;

	*hpa = __pa((unsigned long) page_address(page));

	return 0;
}

static long tce_iommu_build(struct tce_container *container,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long tce, unsigned long pages,
		enum dma_data_direction direction)
{
	long i, ret = 0;
	struct page *page;
	unsigned long hpa;
	enum dma_data_direction dirtmp;

	for (i = 0; i < pages; ++i) {
		unsigned long offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;

		ret = tce_iommu_use_page(tce, &hpa);
		if (ret)
			break;

		page = pfn_to_page(hpa >> PAGE_SHIFT);
		if (!tce_page_is_contained(page, tbl->it_page_shift)) {
			ret = -EPERM;
			break;
		}

		hpa |= offset;
		dirtmp = direction;
		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
		if (ret) {
			tce_iommu_unuse_page(container, hpa);
			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
					__func__, entry << tbl->it_page_shift,
					tce, ret);
			break;
		}

		if (dirtmp != DMA_NONE)
			tce_iommu_unuse_page(container, hpa);

		tce += IOMMU_PAGE_SIZE(tbl);
	}

	if (ret)
		tce_iommu_clear(container, tbl, entry, i);

	return ret;
}

static long tce_iommu_build_v2(struct tce_container *container,
		struct iommu_table *tbl,
		unsigned long entry, unsigned long tce, unsigned long pages,
		enum dma_data_direction direction)
{
	long i, ret = 0;
	struct page *page;
	unsigned long hpa;
	enum dma_data_direction dirtmp;

	for (i = 0; i < pages; ++i) {
		struct mm_iommu_table_group_mem_t *mem = NULL;
		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry + i);

		ret = tce_iommu_prereg_ua_to_hpa(container,
				tce, tbl->it_page_shift, &hpa, &mem);
		if (ret)
			break;

		page = pfn_to_page(hpa >> PAGE_SHIFT);
		if (!tce_page_is_contained(page, tbl->it_page_shift)) {
			ret = -EPERM;
			break;
		}

		/* Preserve offset within IOMMU page */
		hpa |= tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
		dirtmp = direction;

		/* The registered region is being unregistered */
		if (mm_iommu_mapped_inc(mem))
			break;

		ret = iommu_tce_xchg(tbl, entry + i, &hpa, &dirtmp);
		if (ret) {
			/* dirtmp cannot be DMA_NONE here */
			tce_iommu_unuse_page_v2(container, tbl, entry + i);
			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
					__func__, entry << tbl->it_page_shift,
					tce, ret);
			break;
		}

		if (dirtmp != DMA_NONE)
			tce_iommu_unuse_page_v2(container, tbl, entry + i);

		*pua = cpu_to_be64(tce);

		tce += IOMMU_PAGE_SIZE(tbl);
	}

	if (ret)
		tce_iommu_clear(container, tbl, entry, i);

	return ret;
}

static long tce_iommu_create_table(struct tce_container *container,
			struct iommu_table_group *table_group,
			int num,
			__u32 page_shift,
			__u64 window_size,
			__u32 levels,
			struct iommu_table **ptbl)
{
	long ret, table_size;

	table_size = table_group->ops->get_table_size(page_shift, window_size,
			levels);
	if (!table_size)
		return -EINVAL;

	ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
	if (ret)
		return ret;

	ret = table_group->ops->create_table(table_group, num,
			page_shift, window_size, levels, ptbl);

	WARN_ON(!ret && !(*ptbl)->it_ops->free);
	WARN_ON(!ret && ((*ptbl)->it_allocated_size > table_size));

	return ret;
}

static void tce_iommu_free_table(struct tce_container *container,
		struct iommu_table *tbl)
{
	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;

	iommu_tce_table_put(tbl);
	decrement_locked_vm(container->mm, pages);
}

static long tce_iommu_create_window(struct tce_container *container,
		__u32 page_shift, __u64 window_size, __u32 levels,
		__u64 *start_addr)
{
	struct tce_iommu_group *tcegrp;
	struct iommu_table_group *table_group;
	struct iommu_table *tbl = NULL;
	long ret, num;

	num = tce_iommu_find_free_table(container);
	if (num < 0)
		return num;

	/* Get the first group for ops::create_table */
	tcegrp = list_first_entry(&container->group_list,
			struct tce_iommu_group, next);
	table_group = iommu_group_get_iommudata(tcegrp->grp);
	if (!table_group)
		return -EFAULT;

	if (!(table_group->pgsizes & (1ULL << page_shift)))
		return -EINVAL;

	if (!table_group->ops->set_window || !table_group->ops->unset_window ||
			!table_group->ops->get_table_size ||
			!table_group->ops->create_table)
		return -EPERM;

	/* Create TCE table */
	ret = tce_iommu_create_table(container, table_group, num,
			page_shift, window_size, levels, &tbl);
	if (ret)
		return ret;

	BUG_ON(!tbl->it_ops->free);

	/*
	 * Program the table to every group.
	 * Groups have been tested for compatibility at the attach time.
	 */
	list_for_each_entry(tcegrp, &container->group_list, next) {
		table_group = iommu_group_get_iommudata(tcegrp->grp);

		ret = table_group->ops->set_window(table_group, num, tbl);
		if (ret)
			goto unset_exit;
	}

	container->tables[num] = tbl;

	/* Return start address assigned by platform in create_table() */
	*start_addr = tbl->it_offset << tbl->it_page_shift;

	return 0;

unset_exit:
	list_for_each_entry(tcegrp, &container->group_list, next) {
		table_group = iommu_group_get_iommudata(tcegrp->grp);
		table_group->ops->unset_window(table_group, num);
	}
	tce_iommu_free_table(container, tbl);

	return ret;
}

static long tce_iommu_remove_window(struct tce_container *container,
		__u64 start_addr)
{
	struct iommu_table_group *table_group = NULL;
	struct iommu_table *tbl;
	struct tce_iommu_group *tcegrp;
	int num;

	num = tce_iommu_find_table(container, start_addr, &tbl);
	if (num < 0)
		return -EINVAL;

	BUG_ON(!tbl->it_size);

	/* Detach groups from IOMMUs */
	list_for_each_entry(tcegrp, &container->group_list, next) {
		table_group = iommu_group_get_iommudata(tcegrp->grp);

		/*
		 * SPAPR TCE IOMMU exposes the default DMA window to
		 * the guest via dma32_window_start/size of
		 * VFIO_IOMMU_SPAPR_TCE_GET_INFO. Some platforms allow
		 * the userspace to remove this window, some do not so
		 * here we check for the platform capability.
		 */
		if (!table_group->ops || !table_group->ops->unset_window)
			return -EPERM;

		table_group->ops->unset_window(table_group, num);
	}

	/* Free table */
	tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
	tce_iommu_free_table(container, tbl);
	container->tables[num] = NULL;

	return 0;
}

static long tce_iommu_create_default_window(struct tce_container *container)
{
	long ret;
	__u64 start_addr = 0;
	struct tce_iommu_group *tcegrp;
	struct iommu_table_group *table_group;

	if (!container->def_window_pending)
		return 0;

	if (!tce_groups_attached(container))
		return -ENODEV;

	tcegrp = list_first_entry(&container->group_list,
			struct tce_iommu_group, next);
	table_group = iommu_group_get_iommudata(tcegrp->grp);
	if (!table_group)
		return -ENODEV;

	ret = tce_iommu_create_window(container, IOMMU_PAGE_SHIFT_4K,
			table_group->tce32_size, 1, &start_addr);
	WARN_ON_ONCE(!ret && start_addr);

	if (!ret)
		container->def_window_pending = false;

	return ret;
}

static long tce_iommu_ioctl(void *iommu_data,
				 unsigned int cmd, unsigned long arg)
{
	struct tce_container *container = iommu_data;
	unsigned long minsz, ddwsz;
	long ret;

	switch (cmd) {
	case VFIO_CHECK_EXTENSION:
		switch (arg) {
		case VFIO_SPAPR_TCE_IOMMU:
		case VFIO_SPAPR_TCE_v2_IOMMU:
			ret = 1;
			break;
		default:
			ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg);
			break;
		}

		return (ret < 0) ? 0 : ret;
	}

	/*
	 * Sanity check to prevent one userspace from manipulating
	 * another userspace mm.
	 */
	BUG_ON(!container);
	if (container->mm && container->mm != current->mm)
		return -EPERM;

	switch (cmd) {
	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
		struct vfio_iommu_spapr_tce_info info;
		struct tce_iommu_group *tcegrp;
		struct iommu_table_group *table_group;

		if (!tce_groups_attached(container))
			return -ENXIO;

		tcegrp = list_first_entry(&container->group_list,
				struct tce_iommu_group, next);
		table_group = iommu_group_get_iommudata(tcegrp->grp);

		if (!table_group)
			return -ENXIO;

		minsz = offsetofend(struct vfio_iommu_spapr_tce_info,
				dma32_window_size);

		if (copy_from_user(&info, (void __user *)arg, minsz))
			return -EFAULT;

		if (info.argsz < minsz)
			return -EINVAL;

		info.dma32_window_start = table_group->tce32_start;
		info.dma32_window_size = table_group->tce32_size;
		info.flags = 0;
		memset(&info.ddw, 0, sizeof(info.ddw));

		if (table_group->max_dynamic_windows_supported &&
				container->v2) {
			info.flags |= VFIO_IOMMU_SPAPR_INFO_DDW;
			info.ddw.pgsizes = table_group->pgsizes;
			info.ddw.max_dynamic_windows_supported =
				table_group->max_dynamic_windows_supported;
			info.ddw.levels = table_group->max_levels;
		}

		ddwsz = offsetofend(struct vfio_iommu_spapr_tce_info, ddw);

		if (info.argsz >= ddwsz)
			minsz = ddwsz;

		if (copy_to_user((void __user *)arg, &info, minsz))
			return -EFAULT;

		return 0;
	}
	case VFIO_IOMMU_MAP_DMA: {
		struct vfio_iommu_type1_dma_map param;
		struct iommu_table *tbl = NULL;
		long num;
		enum dma_data_direction direction;

		if (!container->enabled)
			return -EPERM;

		minsz = offsetofend(struct vfio_iommu_type1_dma_map, size);

		if (copy_from_user(&param, (void __user *)arg, minsz))
			return -EFAULT;

		if (param.argsz < minsz)
			return -EINVAL;

		if (param.flags & ~(VFIO_DMA_MAP_FLAG_READ |
				VFIO_DMA_MAP_FLAG_WRITE))
			return -EINVAL;

		ret = tce_iommu_create_default_window(container);
		if (ret)
			return ret;

		num = tce_iommu_find_table(container, param.iova, &tbl);
		if (num < 0)
			return -ENXIO;

		if ((param.size & ~IOMMU_PAGE_MASK(tbl)) ||
				(param.vaddr & ~IOMMU_PAGE_MASK(tbl)))
			return -EINVAL;

		/* iova is checked by the IOMMU API */
		if (param.flags & VFIO_DMA_MAP_FLAG_READ) {
			if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
				direction = DMA_BIDIRECTIONAL;
			else
				direction = DMA_TO_DEVICE;
		} else {
			if (param.flags & VFIO_DMA_MAP_FLAG_WRITE)
				direction = DMA_FROM_DEVICE;
			else
				return -EINVAL;
		}

		ret = iommu_tce_put_param_check(tbl, param.iova, param.vaddr);
		if (ret)
			return ret;

		if (container->v2)
			ret = tce_iommu_build_v2(container, tbl,
					param.iova >> tbl->it_page_shift,
					param.vaddr,
					param.size >> tbl->it_page_shift,
					direction);
		else
			ret = tce_iommu_build(container, tbl,
					param.iova >> tbl->it_page_shift,
					param.vaddr,
					param.size >> tbl->it_page_shift,
					direction);

		iommu_flush_tce(tbl);

		return ret;
	}
	case VFIO_IOMMU_UNMAP_DMA: {
		struct vfio_iommu_type1_dma_unmap param;
		struct iommu_table *tbl = NULL;
		long num;

		if (!container->enabled)
			return -EPERM;

		minsz = offsetofend(struct vfio_iommu_type1_dma_unmap,
				size);

		if (copy_from_user(&param, (void __user *)arg, minsz))
			return -EFAULT;

		if (param.argsz < minsz)
			return -EINVAL;

		/* No flag is supported now */
		if (param.flags)
			return -EINVAL;

		ret = tce_iommu_create_default_window(container);
		if (ret)
			return ret;

		num = tce_iommu_find_table(container, param.iova, &tbl);
		if (num < 0)
			return -ENXIO;

		if (param.size & ~IOMMU_PAGE_MASK(tbl))
			return -EINVAL;

		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
				param.size >> tbl->it_page_shift);
		if (ret)
			return ret;

		ret = tce_iommu_clear(container, tbl,
				param.iova >> tbl->it_page_shift,
				param.size >> tbl->it_page_shift);
		iommu_flush_tce(tbl);

		return ret;
	}
	case VFIO_IOMMU_SPAPR_REGISTER_MEMORY: {
		struct vfio_iommu_spapr_register_memory param;

		if (!container->v2)
			break;

		minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
				size);

		ret = tce_iommu_mm_set(container);
		if (ret)
			return ret;

		if (copy_from_user(&param, (void __user *)arg, minsz))
			return -EFAULT;

		if (param.argsz < minsz)
			return -EINVAL;

		/* No flag is supported now */
		if (param.flags)
			return -EINVAL;

		mutex_lock(&container->lock);
		ret = tce_iommu_register_pages(container, param.vaddr,
				param.size);
		mutex_unlock(&container->lock);

		return ret;
	}
	case VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY: {
		struct vfio_iommu_spapr_register_memory param;

		if (!container->v2)
			break;

		if (!container->mm)
			return -EPERM;

		minsz = offsetofend(struct vfio_iommu_spapr_register_memory,
				size);

		if (copy_from_user(&param, (void __user *)arg, minsz))
			return -EFAULT;

		if (param.argsz < minsz)
			return -EINVAL;

		/* No flag is supported now */
		if (param.flags)
			return -EINVAL;

		mutex_lock(&container->lock);
		ret = tce_iommu_unregister_pages(container, param.vaddr,
				param.size);
		mutex_unlock(&container->lock);

		return ret;
	}
	case VFIO_IOMMU_ENABLE:
		if (container->v2)
			break;

		mutex_lock(&container->lock);
		ret = tce_iommu_enable(container);
		mutex_unlock(&container->lock);
		return ret;


	case VFIO_IOMMU_DISABLE:
		if (container->v2)
			break;

		mutex_lock(&container->lock);
		tce_iommu_disable(container);
		mutex_unlock(&container->lock);
		return 0;

	case VFIO_EEH_PE_OP: {
		struct tce_iommu_group *tcegrp;

		ret = 0;
		list_for_each_entry(tcegrp, &container->group_list, next) {
			ret = vfio_spapr_iommu_eeh_ioctl(tcegrp->grp,
					cmd, arg);
			if (ret)
				return ret;
		}
		return ret;
	}

	case VFIO_IOMMU_SPAPR_TCE_CREATE: {
		struct vfio_iommu_spapr_tce_create create;

		if (!container->v2)
			break;

		ret = tce_iommu_mm_set(container);
		if (ret)
			return ret;

		if (!tce_groups_attached(container))
			return -ENXIO;

		minsz = offsetofend(struct vfio_iommu_spapr_tce_create,
				start_addr);

		if (copy_from_user(&create, (void __user *)arg, minsz))
			return -EFAULT;

		if (create.argsz < minsz)
			return -EINVAL;

		if (create.flags)
			return -EINVAL;

		mutex_lock(&container->lock);

		ret = tce_iommu_create_default_window(container);
		if (!ret)
			ret = tce_iommu_create_window(container,
					create.page_shift,
					create.window_size, create.levels,
					&create.start_addr);

		mutex_unlock(&container->lock);

		if (!ret && copy_to_user((void __user *)arg, &create, minsz))
			ret = -EFAULT;

		return ret;
	}
	case VFIO_IOMMU_SPAPR_TCE_REMOVE: {
		struct vfio_iommu_spapr_tce_remove remove;

		if (!container->v2)
			break;

		ret = tce_iommu_mm_set(container);
		if (ret)
			return ret;

		if (!tce_groups_attached(container))
			return -ENXIO;

		minsz = offsetofend(struct vfio_iommu_spapr_tce_remove,
				start_addr);

		if (copy_from_user(&remove, (void __user *)arg, minsz))
			return -EFAULT;

		if (remove.argsz < minsz)
			return -EINVAL;

		if (remove.flags)
			return -EINVAL;

		if (container->def_window_pending && !remove.start_addr) {
			container->def_window_pending = false;
			return 0;
		}

		mutex_lock(&container->lock);

		ret = tce_iommu_remove_window(container, remove.start_addr);

		mutex_unlock(&container->lock);

		return ret;
	}
	}

	return -ENOTTY;
}

static void tce_iommu_release_ownership(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	int i;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = container->tables[i];

		if (!tbl)
			continue;

		tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
		if (tbl->it_map)
			iommu_release_ownership(tbl);

		container->tables[i] = NULL;
	}
}

static int tce_iommu_take_ownership(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	int i, j, rc = 0;

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = table_group->tables[i];

		if (!tbl || !tbl->it_map)
			continue;

		rc = iommu_take_ownership(tbl);
		if (rc) {
			for (j = 0; j < i; ++j)
				iommu_release_ownership(
						table_group->tables[j]);

			return rc;
		}
	}

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
		container->tables[i] = table_group->tables[i];

	return 0;
}

static void tce_iommu_release_ownership_ddw(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	long i;

	if (!table_group->ops->unset_window) {
		WARN_ON_ONCE(1);
		return;
	}

	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
		table_group->ops->unset_window(table_group, i);

	table_group->ops->release_ownership(table_group);
}

static long tce_iommu_take_ownership_ddw(struct tce_container *container,
		struct iommu_table_group *table_group)
{
	long i, ret = 0;

	if (!table_group->ops->create_table || !table_group->ops->set_window ||
			!table_group->ops->release_ownership) {
		WARN_ON_ONCE(1);
		return -EFAULT;
	}

	table_group->ops->take_ownership(table_group);

	/* Set all windows to the new group */
	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
		struct iommu_table *tbl = container->tables[i];

		if (!tbl)
			continue;

		ret = table_group->ops->set_window(table_group, i, tbl);
		if (ret)
			goto release_exit;
	}

	return 0;

release_exit:
	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
		table_group->ops->unset_window(table_group, i);

	table_group->ops->release_ownership(table_group);

	return ret;
}

static int tce_iommu_attach_group(void *iommu_data,
		struct iommu_group *iommu_group)
{
	int ret;
	struct tce_container *container = iommu_data;
	struct iommu_table_group *table_group;
	struct tce_iommu_group *tcegrp = NULL;

	mutex_lock(&container->lock);

	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
			iommu_group_id(iommu_group), iommu_group); */
	table_group = iommu_group_get_iommudata(iommu_group);
	if (!table_group) {
		ret = -ENODEV;
		goto unlock_exit;
	}

	if (tce_groups_attached(container) && (!table_group->ops ||
			!table_group->ops->take_ownership ||
			!table_group->ops->release_ownership)) {
		ret = -EBUSY;
		goto unlock_exit;
	}

	/* Check if new group has the same iommu_ops (i.e. compatible) */
	list_for_each_entry(tcegrp, &container->group_list, next) {
		struct iommu_table_group *table_group_tmp;

		if (tcegrp->grp == iommu_group) {
			pr_warn("tce_vfio: Group %d is already attached\n",
					iommu_group_id(iommu_group));
			ret = -EBUSY;
			goto unlock_exit;
		}
		table_group_tmp = iommu_group_get_iommudata(tcegrp->grp);
		if (table_group_tmp->ops->create_table !=
				table_group->ops->create_table) {
			pr_warn("tce_vfio: Group %d is incompatible with group %d\n",
					iommu_group_id(iommu_group),
					iommu_group_id(tcegrp->grp));
			ret = -EPERM;
			goto unlock_exit;
		}
	}

	tcegrp = kzalloc(sizeof(*tcegrp), GFP_KERNEL);
	if (!tcegrp) {
		ret = -ENOMEM;
		goto unlock_exit;
	}

	if (!table_group->ops || !table_group->ops->take_ownership ||
			!table_group->ops->release_ownership) {
		if (container->v2) {
			ret = -EPERM;
			goto unlock_exit;
		}
		ret = tce_iommu_take_ownership(container, table_group);
	} else {
		if (!container->v2) {
			ret = -EPERM;
			goto unlock_exit;
		}
		ret = tce_iommu_take_ownership_ddw(container, table_group);
		if (!tce_groups_attached(container) && !container->tables[0])
			container->def_window_pending = true;
	}

	if (!ret) {
		tcegrp->grp = iommu_group;
		list_add(&tcegrp->next, &container->group_list);
	}

unlock_exit:
	if (ret && tcegrp)
		kfree(tcegrp);

	mutex_unlock(&container->lock);

	return ret;
}

static void tce_iommu_detach_group(void *iommu_data,
		struct iommu_group *iommu_group)
{
	struct tce_container *container = iommu_data;
	struct iommu_table_group *table_group;
	bool found = false;
	struct tce_iommu_group *tcegrp;

	mutex_lock(&container->lock);

	list_for_each_entry(tcegrp, &container->group_list, next) {
		if (tcegrp->grp == iommu_group) {
			found = true;
			break;
		}
	}

	if (!found) {
		pr_warn("tce_vfio: detaching unattached group #%u\n",
				iommu_group_id(iommu_group));
		goto unlock_exit;
	}

	list_del(&tcegrp->next);
	kfree(tcegrp);

	table_group = iommu_group_get_iommudata(iommu_group);
	BUG_ON(!table_group);

	if (!table_group->ops || !table_group->ops->release_ownership)
		tce_iommu_release_ownership(container, table_group);
	else
		tce_iommu_release_ownership_ddw(container, table_group);

unlock_exit:
	mutex_unlock(&container->lock);
}

const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
	.name		= "iommu-vfio-powerpc",
	.owner		= THIS_MODULE,
	.open		= tce_iommu_open,
	.release	= tce_iommu_release,
	.ioctl		= tce_iommu_ioctl,
	.attach_group	= tce_iommu_attach_group,
	.detach_group	= tce_iommu_detach_group,
};

static int __init tce_iommu_init(void)
{
	return vfio_register_iommu_driver(&tce_iommu_driver_ops);
}

static void __exit tce_iommu_cleanup(void)
{
	vfio_unregister_iommu_driver(&tce_iommu_driver_ops);
}

module_init(tce_iommu_init);
module_exit(tce_iommu_cleanup);

MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);