aboutsummaryrefslogtreecommitdiff
path: root/arch/s390/mm/pgtable.c
blob: 16154720bdb60749163ec8ae33b4c451aa044c21 (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
1412
1413
1414
/*
 *    Copyright IBM Corp. 2007, 2011
 *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
 */

#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/quicklist.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/sysctl.h>
#include <linux/ksm.h>
#include <linux/mman.h>

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>

#define ALLOC_ORDER	2
#define FRAG_MASK	0x03

unsigned int HPAGE_SHIFT;

unsigned long *crst_table_alloc(struct mm_struct *mm)
{
	struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);

	if (!page)
		return NULL;
	return (unsigned long *) page_to_phys(page);
}

void crst_table_free(struct mm_struct *mm, unsigned long *table)
{
	free_pages((unsigned long) table, ALLOC_ORDER);
}

static void __crst_table_upgrade(void *arg)
{
	struct mm_struct *mm = arg;

	if (current->active_mm == mm) {
		clear_user_asce();
		set_user_asce(mm);
	}
	__tlb_flush_local();
}

int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
{
	unsigned long *table, *pgd;
	unsigned long entry;
	int flush;

	BUG_ON(limit > (1UL << 53));
	flush = 0;
repeat:
	table = crst_table_alloc(mm);
	if (!table)
		return -ENOMEM;
	spin_lock_bh(&mm->page_table_lock);
	if (mm->context.asce_limit < limit) {
		pgd = (unsigned long *) mm->pgd;
		if (mm->context.asce_limit <= (1UL << 31)) {
			entry = _REGION3_ENTRY_EMPTY;
			mm->context.asce_limit = 1UL << 42;
			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
						_ASCE_USER_BITS |
						_ASCE_TYPE_REGION3;
		} else {
			entry = _REGION2_ENTRY_EMPTY;
			mm->context.asce_limit = 1UL << 53;
			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
						_ASCE_USER_BITS |
						_ASCE_TYPE_REGION2;
		}
		crst_table_init(table, entry);
		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
		mm->pgd = (pgd_t *) table;
		mm->task_size = mm->context.asce_limit;
		table = NULL;
		flush = 1;
	}
	spin_unlock_bh(&mm->page_table_lock);
	if (table)
		crst_table_free(mm, table);
	if (mm->context.asce_limit < limit)
		goto repeat;
	if (flush)
		on_each_cpu(__crst_table_upgrade, mm, 0);
	return 0;
}

void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
{
	pgd_t *pgd;

	if (current->active_mm == mm) {
		clear_user_asce();
		__tlb_flush_mm(mm);
	}
	while (mm->context.asce_limit > limit) {
		pgd = mm->pgd;
		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
		case _REGION_ENTRY_TYPE_R2:
			mm->context.asce_limit = 1UL << 42;
			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
						_ASCE_USER_BITS |
						_ASCE_TYPE_REGION3;
			break;
		case _REGION_ENTRY_TYPE_R3:
			mm->context.asce_limit = 1UL << 31;
			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
						_ASCE_USER_BITS |
						_ASCE_TYPE_SEGMENT;
			break;
		default:
			BUG();
		}
		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
		mm->task_size = mm->context.asce_limit;
		crst_table_free(mm, (unsigned long *) pgd);
	}
	if (current->active_mm == mm)
		set_user_asce(mm);
}

#ifdef CONFIG_PGSTE

/**
 * gmap_alloc - allocate a guest address space
 * @mm: pointer to the parent mm_struct
 * @limit: maximum size of the gmap address space
 *
 * Returns a guest address space structure.
 */
struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
{
	struct gmap *gmap;
	struct page *page;
	unsigned long *table;
	unsigned long etype, atype;

	if (limit < (1UL << 31)) {
		limit = (1UL << 31) - 1;
		atype = _ASCE_TYPE_SEGMENT;
		etype = _SEGMENT_ENTRY_EMPTY;
	} else if (limit < (1UL << 42)) {
		limit = (1UL << 42) - 1;
		atype = _ASCE_TYPE_REGION3;
		etype = _REGION3_ENTRY_EMPTY;
	} else if (limit < (1UL << 53)) {
		limit = (1UL << 53) - 1;
		atype = _ASCE_TYPE_REGION2;
		etype = _REGION2_ENTRY_EMPTY;
	} else {
		limit = -1UL;
		atype = _ASCE_TYPE_REGION1;
		etype = _REGION1_ENTRY_EMPTY;
	}
	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL);
	if (!gmap)
		goto out;
	INIT_LIST_HEAD(&gmap->crst_list);
	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL);
	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
	spin_lock_init(&gmap->guest_table_lock);
	gmap->mm = mm;
	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
	if (!page)
		goto out_free;
	page->index = 0;
	list_add(&page->lru, &gmap->crst_list);
	table = (unsigned long *) page_to_phys(page);
	crst_table_init(table, etype);
	gmap->table = table;
	gmap->asce = atype | _ASCE_TABLE_LENGTH |
		_ASCE_USER_BITS | __pa(table);
	gmap->asce_end = limit;
	down_write(&mm->mmap_sem);
	list_add(&gmap->list, &mm->context.gmap_list);
	up_write(&mm->mmap_sem);
	return gmap;

out_free:
	kfree(gmap);
out:
	return NULL;
}
EXPORT_SYMBOL_GPL(gmap_alloc);

static void gmap_flush_tlb(struct gmap *gmap)
{
	if (MACHINE_HAS_IDTE)
		__tlb_flush_asce(gmap->mm, gmap->asce);
	else
		__tlb_flush_global();
}

static void gmap_radix_tree_free(struct radix_tree_root *root)
{
	struct radix_tree_iter iter;
	unsigned long indices[16];
	unsigned long index;
	void **slot;
	int i, nr;

	/* A radix tree is freed by deleting all of its entries */
	index = 0;
	do {
		nr = 0;
		radix_tree_for_each_slot(slot, root, &iter, index) {
			indices[nr] = iter.index;
			if (++nr == 16)
				break;
		}
		for (i = 0; i < nr; i++) {
			index = indices[i];
			radix_tree_delete(root, index);
		}
	} while (nr > 0);
}

/**
 * gmap_free - free a guest address space
 * @gmap: pointer to the guest address space structure
 */
void gmap_free(struct gmap *gmap)
{
	struct page *page, *next;

	/* Flush tlb. */
	if (MACHINE_HAS_IDTE)
		__tlb_flush_asce(gmap->mm, gmap->asce);
	else
		__tlb_flush_global();

	/* Free all segment & region tables. */
	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
		__free_pages(page, ALLOC_ORDER);
	gmap_radix_tree_free(&gmap->guest_to_host);
	gmap_radix_tree_free(&gmap->host_to_guest);
	down_write(&gmap->mm->mmap_sem);
	list_del(&gmap->list);
	up_write(&gmap->mm->mmap_sem);
	kfree(gmap);
}
EXPORT_SYMBOL_GPL(gmap_free);

/**
 * gmap_enable - switch primary space to the guest address space
 * @gmap: pointer to the guest address space structure
 */
void gmap_enable(struct gmap *gmap)
{
	S390_lowcore.gmap = (unsigned long) gmap;
}
EXPORT_SYMBOL_GPL(gmap_enable);

/**
 * gmap_disable - switch back to the standard primary address space
 * @gmap: pointer to the guest address space structure
 */
void gmap_disable(struct gmap *gmap)
{
	S390_lowcore.gmap = 0UL;
}
EXPORT_SYMBOL_GPL(gmap_disable);

/*
 * gmap_alloc_table is assumed to be called with mmap_sem held
 */
static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
			    unsigned long init, unsigned long gaddr)
{
	struct page *page;
	unsigned long *new;

	/* since we dont free the gmap table until gmap_free we can unlock */
	page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
	if (!page)
		return -ENOMEM;
	new = (unsigned long *) page_to_phys(page);
	crst_table_init(new, init);
	spin_lock(&gmap->mm->page_table_lock);
	if (*table & _REGION_ENTRY_INVALID) {
		list_add(&page->lru, &gmap->crst_list);
		*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
			(*table & _REGION_ENTRY_TYPE_MASK);
		page->index = gaddr;
		page = NULL;
	}
	spin_unlock(&gmap->mm->page_table_lock);
	if (page)
		__free_pages(page, ALLOC_ORDER);
	return 0;
}

/**
 * __gmap_segment_gaddr - find virtual address from segment pointer
 * @entry: pointer to a segment table entry in the guest address space
 *
 * Returns the virtual address in the guest address space for the segment
 */
static unsigned long __gmap_segment_gaddr(unsigned long *entry)
{
	struct page *page;
	unsigned long offset, mask;

	offset = (unsigned long) entry / sizeof(unsigned long);
	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
	mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
	page = virt_to_page((void *)((unsigned long) entry & mask));
	return page->index + offset;
}

/**
 * __gmap_unlink_by_vmaddr - unlink a single segment via a host address
 * @gmap: pointer to the guest address space structure
 * @vmaddr: address in the host process address space
 *
 * Returns 1 if a TLB flush is required
 */
static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
{
	unsigned long *entry;
	int flush = 0;

	spin_lock(&gmap->guest_table_lock);
	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
	if (entry) {
		flush = (*entry != _SEGMENT_ENTRY_INVALID);
		*entry = _SEGMENT_ENTRY_INVALID;
	}
	spin_unlock(&gmap->guest_table_lock);
	return flush;
}

/**
 * __gmap_unmap_by_gaddr - unmap a single segment via a guest address
 * @gmap: pointer to the guest address space structure
 * @gaddr: address in the guest address space
 *
 * Returns 1 if a TLB flush is required
 */
static int __gmap_unmap_by_gaddr(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long vmaddr;

	vmaddr = (unsigned long) radix_tree_delete(&gmap->guest_to_host,
						   gaddr >> PMD_SHIFT);
	return vmaddr ? __gmap_unlink_by_vmaddr(gmap, vmaddr) : 0;
}

/**
 * gmap_unmap_segment - unmap segment from the guest address space
 * @gmap: pointer to the guest address space structure
 * @to: address in the guest address space
 * @len: length of the memory area to unmap
 *
 * Returns 0 if the unmap succeeded, -EINVAL if not.
 */
int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
{
	unsigned long off;
	int flush;

	if ((to | len) & (PMD_SIZE - 1))
		return -EINVAL;
	if (len == 0 || to + len < to)
		return -EINVAL;

	flush = 0;
	down_write(&gmap->mm->mmap_sem);
	for (off = 0; off < len; off += PMD_SIZE)
		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
	up_write(&gmap->mm->mmap_sem);
	if (flush)
		gmap_flush_tlb(gmap);
	return 0;
}
EXPORT_SYMBOL_GPL(gmap_unmap_segment);

/**
 * gmap_mmap_segment - map a segment to the guest address space
 * @gmap: pointer to the guest address space structure
 * @from: source address in the parent address space
 * @to: target address in the guest address space
 * @len: length of the memory area to map
 *
 * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not.
 */
int gmap_map_segment(struct gmap *gmap, unsigned long from,
		     unsigned long to, unsigned long len)
{
	unsigned long off;
	int flush;

	if ((from | to | len) & (PMD_SIZE - 1))
		return -EINVAL;
	if (len == 0 || from + len < from || to + len < to ||
	    from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
		return -EINVAL;

	flush = 0;
	down_write(&gmap->mm->mmap_sem);
	for (off = 0; off < len; off += PMD_SIZE) {
		/* Remove old translation */
		flush |= __gmap_unmap_by_gaddr(gmap, to + off);
		/* Store new translation */
		if (radix_tree_insert(&gmap->guest_to_host,
				      (to + off) >> PMD_SHIFT,
				      (void *) from + off))
			break;
	}
	up_write(&gmap->mm->mmap_sem);
	if (flush)
		gmap_flush_tlb(gmap);
	if (off >= len)
		return 0;
	gmap_unmap_segment(gmap, to, len);
	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(gmap_map_segment);

/**
 * __gmap_translate - translate a guest address to a user space address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 *
 * Returns user space address which corresponds to the guest address or
 * -EFAULT if no such mapping exists.
 * This function does not establish potentially missing page table entries.
 * The mmap_sem of the mm that belongs to the address space must be held
 * when this function gets called.
 */
unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long vmaddr;

	vmaddr = (unsigned long)
		radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT);
	return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT;
}
EXPORT_SYMBOL_GPL(__gmap_translate);

/**
 * gmap_translate - translate a guest address to a user space address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 *
 * Returns user space address which corresponds to the guest address or
 * -EFAULT if no such mapping exists.
 * This function does not establish potentially missing page table entries.
 */
unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long rc;

	down_read(&gmap->mm->mmap_sem);
	rc = __gmap_translate(gmap, gaddr);
	up_read(&gmap->mm->mmap_sem);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_translate);

/**
 * gmap_unlink - disconnect a page table from the gmap shadow tables
 * @gmap: pointer to guest mapping meta data structure
 * @table: pointer to the host page table
 * @vmaddr: vm address associated with the host page table
 */
static void gmap_unlink(struct mm_struct *mm, unsigned long *table,
			unsigned long vmaddr)
{
	struct gmap *gmap;
	int flush;

	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
		flush = __gmap_unlink_by_vmaddr(gmap, vmaddr);
		if (flush)
			gmap_flush_tlb(gmap);
	}
}

/**
 * gmap_link - set up shadow page tables to connect a host to a guest address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 * @vmaddr: vm address
 *
 * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
 * if the vm address is already mapped to a different guest segment.
 * The mmap_sem of the mm that belongs to the address space must be held
 * when this function gets called.
 */
int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
{
	struct mm_struct *mm;
	unsigned long *table;
	spinlock_t *ptl;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	int rc;

	/* Create higher level tables in the gmap page table */
	table = gmap->table;
	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) {
		table += (gaddr >> 53) & 0x7ff;
		if ((*table & _REGION_ENTRY_INVALID) &&
		    gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY,
				     gaddr & 0xffe0000000000000UL))
			return -ENOMEM;
		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
	}
	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION2) {
		table += (gaddr >> 42) & 0x7ff;
		if ((*table & _REGION_ENTRY_INVALID) &&
		    gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY,
				     gaddr & 0xfffffc0000000000UL))
			return -ENOMEM;
		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
	}
	if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION3) {
		table += (gaddr >> 31) & 0x7ff;
		if ((*table & _REGION_ENTRY_INVALID) &&
		    gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY,
				     gaddr & 0xffffffff80000000UL))
			return -ENOMEM;
		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
	}
	table += (gaddr >> 20) & 0x7ff;
	/* Walk the parent mm page table */
	mm = gmap->mm;
	pgd = pgd_offset(mm, vmaddr);
	VM_BUG_ON(pgd_none(*pgd));
	pud = pud_offset(pgd, vmaddr);
	VM_BUG_ON(pud_none(*pud));
	pmd = pmd_offset(pud, vmaddr);
	VM_BUG_ON(pmd_none(*pmd));
	/* large pmds cannot yet be handled */
	if (pmd_large(*pmd))
		return -EFAULT;
	/* Link gmap segment table entry location to page table. */
	rc = radix_tree_preload(GFP_KERNEL);
	if (rc)
		return rc;
	ptl = pmd_lock(mm, pmd);
	spin_lock(&gmap->guest_table_lock);
	if (*table == _SEGMENT_ENTRY_INVALID) {
		rc = radix_tree_insert(&gmap->host_to_guest,
				       vmaddr >> PMD_SHIFT, table);
		if (!rc)
			*table = pmd_val(*pmd);
	} else
		rc = 0;
	spin_unlock(&gmap->guest_table_lock);
	spin_unlock(ptl);
	radix_tree_preload_end();
	return rc;
}

/**
 * gmap_fault - resolve a fault on a guest address
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: guest address
 * @fault_flags: flags to pass down to handle_mm_fault()
 *
 * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT
 * if the vm address is already mapped to a different guest segment.
 */
int gmap_fault(struct gmap *gmap, unsigned long gaddr,
	       unsigned int fault_flags)
{
	unsigned long vmaddr;
	int rc;

	down_read(&gmap->mm->mmap_sem);
	vmaddr = __gmap_translate(gmap, gaddr);
	if (IS_ERR_VALUE(vmaddr)) {
		rc = vmaddr;
		goto out_up;
	}
	if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags)) {
		rc = -EFAULT;
		goto out_up;
	}
	rc = __gmap_link(gmap, gaddr, vmaddr);
out_up:
	up_read(&gmap->mm->mmap_sem);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_fault);

static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
{
	if (!non_swap_entry(entry))
		dec_mm_counter(mm, MM_SWAPENTS);
	else if (is_migration_entry(entry)) {
		struct page *page = migration_entry_to_page(entry);

		if (PageAnon(page))
			dec_mm_counter(mm, MM_ANONPAGES);
		else
			dec_mm_counter(mm, MM_FILEPAGES);
	}
	free_swap_and_cache(entry);
}

/*
 * this function is assumed to be called with mmap_sem held
 */
void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
{
	unsigned long vmaddr, ptev, pgstev;
	pte_t *ptep, pte;
	spinlock_t *ptl;
	pgste_t pgste;

	/* Find the vm address for the guest address */
	vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host,
						   gaddr >> PMD_SHIFT);
	if (!vmaddr)
		return;
	vmaddr |= gaddr & ~PMD_MASK;
	/* Get pointer to the page table entry */
	ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
	if (unlikely(!ptep))
		return;
	pte = *ptep;
	if (!pte_swap(pte))
		goto out_pte;
	/* Zap unused and logically-zero pages */
	pgste = pgste_get_lock(ptep);
	pgstev = pgste_val(pgste);
	ptev = pte_val(pte);
	if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) ||
	    ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID))) {
		gmap_zap_swap_entry(pte_to_swp_entry(pte), gmap->mm);
		pte_clear(gmap->mm, vmaddr, ptep);
	}
	pgste_set_unlock(ptep, pgste);
out_pte:
	pte_unmap_unlock(ptep, ptl);
}
EXPORT_SYMBOL_GPL(__gmap_zap);

void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
{
	unsigned long gaddr, vmaddr, size;
	struct vm_area_struct *vma;

	down_read(&gmap->mm->mmap_sem);
	for (gaddr = from; gaddr < to;
	     gaddr = (gaddr + PMD_SIZE) & PMD_MASK) {
		/* Find the vm address for the guest address */
		vmaddr = (unsigned long)
			radix_tree_lookup(&gmap->guest_to_host,
					  gaddr >> PMD_SHIFT);
		if (!vmaddr)
			continue;
		vmaddr |= gaddr & ~PMD_MASK;
		/* Find vma in the parent mm */
		vma = find_vma(gmap->mm, vmaddr);
		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
		zap_page_range(vma, vmaddr, size, NULL);
	}
	up_read(&gmap->mm->mmap_sem);
}
EXPORT_SYMBOL_GPL(gmap_discard);

static LIST_HEAD(gmap_notifier_list);
static DEFINE_SPINLOCK(gmap_notifier_lock);

/**
 * gmap_register_ipte_notifier - register a pte invalidation callback
 * @nb: pointer to the gmap notifier block
 */
void gmap_register_ipte_notifier(struct gmap_notifier *nb)
{
	spin_lock(&gmap_notifier_lock);
	list_add(&nb->list, &gmap_notifier_list);
	spin_unlock(&gmap_notifier_lock);
}
EXPORT_SYMBOL_GPL(gmap_register_ipte_notifier);

/**
 * gmap_unregister_ipte_notifier - remove a pte invalidation callback
 * @nb: pointer to the gmap notifier block
 */
void gmap_unregister_ipte_notifier(struct gmap_notifier *nb)
{
	spin_lock(&gmap_notifier_lock);
	list_del_init(&nb->list);
	spin_unlock(&gmap_notifier_lock);
}
EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier);

/**
 * gmap_ipte_notify - mark a range of ptes for invalidation notification
 * @gmap: pointer to guest mapping meta data structure
 * @gaddr: virtual address in the guest address space
 * @len: size of area
 *
 * Returns 0 if for each page in the given range a gmap mapping exists and
 * the invalidation notification could be set. If the gmap mapping is missing
 * for one or more pages -EFAULT is returned. If no memory could be allocated
 * -ENOMEM is returned. This function establishes missing page table entries.
 */
int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
{
	unsigned long addr;
	spinlock_t *ptl;
	pte_t *ptep, entry;
	pgste_t pgste;
	int rc = 0;

	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK))
		return -EINVAL;
	down_read(&gmap->mm->mmap_sem);
	while (len) {
		/* Convert gmap address and connect the page tables */
		addr = __gmap_translate(gmap, gaddr);
		if (IS_ERR_VALUE(addr)) {
			rc = addr;
			break;
		}
		/* Get the page mapped */
		if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) {
			rc = -EFAULT;
			break;
		}
		rc = __gmap_link(gmap, gaddr, addr);
		if (rc)
			break;
		/* Walk the process page table, lock and get pte pointer */
		ptep = get_locked_pte(gmap->mm, addr, &ptl);
		VM_BUG_ON(!ptep);
		/* Set notification bit in the pgste of the pte */
		entry = *ptep;
		if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
			pgste = pgste_get_lock(ptep);
			pgste_val(pgste) |= PGSTE_IN_BIT;
			pgste_set_unlock(ptep, pgste);
			gaddr += PAGE_SIZE;
			len -= PAGE_SIZE;
		}
		pte_unmap_unlock(ptep, ptl);
	}
	up_read(&gmap->mm->mmap_sem);
	return rc;
}
EXPORT_SYMBOL_GPL(gmap_ipte_notify);

/**
 * gmap_do_ipte_notify - call all invalidation callbacks for a specific pte.
 * @mm: pointer to the process mm_struct
 * @addr: virtual address in the process address space
 * @pte: pointer to the page table entry
 *
 * This function is assumed to be called with the page table lock held
 * for the pte to notify.
 */
void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte)
{
	unsigned long offset, gaddr;
	unsigned long *table;
	struct gmap_notifier *nb;
	struct gmap *gmap;

	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
	offset = offset * (4096 / sizeof(pte_t));
	spin_lock(&gmap_notifier_lock);
	list_for_each_entry(gmap, &mm->context.gmap_list, list) {
		table = radix_tree_lookup(&gmap->host_to_guest,
					  vmaddr >> PMD_SHIFT);
		if (!table)
			continue;
		gaddr = __gmap_segment_gaddr(table) + offset;
		list_for_each_entry(nb, &gmap_notifier_list, list)
			nb->notifier_call(gmap, gaddr);
	}
	spin_unlock(&gmap_notifier_lock);
}
EXPORT_SYMBOL_GPL(gmap_do_ipte_notify);

static inline int page_table_with_pgste(struct page *page)
{
	return atomic_read(&page->_mapcount) == 0;
}

static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
{
	struct page *page;
	unsigned long *table;

	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
	if (!page)
		return NULL;
	if (!pgtable_page_ctor(page)) {
		__free_page(page);
		return NULL;
	}
	atomic_set(&page->_mapcount, 0);
	table = (unsigned long *) page_to_phys(page);
	clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
	return table;
}

static inline void page_table_free_pgste(unsigned long *table)
{
	struct page *page;

	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
	pgtable_page_dtor(page);
	atomic_set(&page->_mapcount, -1);
	__free_page(page);
}

int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
			  unsigned long key, bool nq)
{
	spinlock_t *ptl;
	pgste_t old, new;
	pte_t *ptep;

	down_read(&mm->mmap_sem);
retry:
	ptep = get_locked_pte(mm, addr, &ptl);
	if (unlikely(!ptep)) {
		up_read(&mm->mmap_sem);
		return -EFAULT;
	}
	if (!(pte_val(*ptep) & _PAGE_INVALID) &&
	     (pte_val(*ptep) & _PAGE_PROTECT)) {
		pte_unmap_unlock(ptep, ptl);
		if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) {
			up_read(&mm->mmap_sem);
			return -EFAULT;
		}
		goto retry;
	}

	new = old = pgste_get_lock(ptep);
	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
	pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
	pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
		unsigned long address, bits, skey;

		address = pte_val(*ptep) & PAGE_MASK;
		skey = (unsigned long) page_get_storage_key(address);
		bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
		skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
		/* Set storage key ACC and FP */
		page_set_storage_key(address, skey, !nq);
		/* Merge host changed & referenced into pgste  */
		pgste_val(new) |= bits << 52;
	}
	/* changing the guest storage key is considered a change of the page */
	if ((pgste_val(new) ^ pgste_val(old)) &
	    (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
		pgste_val(new) |= PGSTE_UC_BIT;

	pgste_set_unlock(ptep, new);
	pte_unmap_unlock(ptep, ptl);
	up_read(&mm->mmap_sem);
	return 0;
}
EXPORT_SYMBOL(set_guest_storage_key);

unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
{
	spinlock_t *ptl;
	pgste_t pgste;
	pte_t *ptep;
	uint64_t physaddr;
	unsigned long key = 0;

	down_read(&mm->mmap_sem);
	ptep = get_locked_pte(mm, addr, &ptl);
	if (unlikely(!ptep)) {
		up_read(&mm->mmap_sem);
		return -EFAULT;
	}
	pgste = pgste_get_lock(ptep);

	if (pte_val(*ptep) & _PAGE_INVALID) {
		key |= (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
		key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
		key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
		key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
	} else {
		physaddr = pte_val(*ptep) & PAGE_MASK;
		key = page_get_storage_key(physaddr);

		/* Reflect guest's logical view, not physical */
		if (pgste_val(pgste) & PGSTE_GR_BIT)
			key |= _PAGE_REFERENCED;
		if (pgste_val(pgste) & PGSTE_GC_BIT)
			key |= _PAGE_CHANGED;
	}

	pgste_set_unlock(ptep, pgste);
	pte_unmap_unlock(ptep, ptl);
	up_read(&mm->mmap_sem);
	return key;
}
EXPORT_SYMBOL(get_guest_storage_key);

static int page_table_allocate_pgste_min = 0;
static int page_table_allocate_pgste_max = 1;
int page_table_allocate_pgste = 0;
EXPORT_SYMBOL(page_table_allocate_pgste);

static struct ctl_table page_table_sysctl[] = {
	{
		.procname	= "allocate_pgste",
		.data		= &page_table_allocate_pgste,
		.maxlen		= sizeof(int),
		.mode		= S_IRUGO | S_IWUSR,
		.proc_handler	= proc_dointvec,
		.extra1		= &page_table_allocate_pgste_min,
		.extra2		= &page_table_allocate_pgste_max,
	},
	{ }
};

static struct ctl_table page_table_sysctl_dir[] = {
	{
		.procname	= "vm",
		.maxlen		= 0,
		.mode		= 0555,
		.child		= page_table_sysctl,
	},
	{ }
};

static int __init page_table_register_sysctl(void)
{
	return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM;
}
__initcall(page_table_register_sysctl);

#else /* CONFIG_PGSTE */

static inline int page_table_with_pgste(struct page *page)
{
	return 0;
}

static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
{
	return NULL;
}

static inline void page_table_free_pgste(unsigned long *table)
{
}

static inline void gmap_unlink(struct mm_struct *mm, unsigned long *table,
			unsigned long vmaddr)
{
}

#endif /* CONFIG_PGSTE */

static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
{
	unsigned int old, new;

	do {
		old = atomic_read(v);
		new = old ^ bits;
	} while (atomic_cmpxchg(v, old, new) != old);
	return new;
}

/*
 * page table entry allocation/free routines.
 */
unsigned long *page_table_alloc(struct mm_struct *mm)
{
	unsigned long *uninitialized_var(table);
	struct page *uninitialized_var(page);
	unsigned int mask, bit;

	if (mm_alloc_pgste(mm))
		return page_table_alloc_pgste(mm);
	/* Allocate fragments of a 4K page as 1K/2K page table */
	spin_lock_bh(&mm->context.list_lock);
	mask = FRAG_MASK;
	if (!list_empty(&mm->context.pgtable_list)) {
		page = list_first_entry(&mm->context.pgtable_list,
					struct page, lru);
		table = (unsigned long *) page_to_phys(page);
		mask = atomic_read(&page->_mapcount);
		mask = mask | (mask >> 4);
	}
	if ((mask & FRAG_MASK) == FRAG_MASK) {
		spin_unlock_bh(&mm->context.list_lock);
		page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
		if (!page)
			return NULL;
		if (!pgtable_page_ctor(page)) {
			__free_page(page);
			return NULL;
		}
		atomic_set(&page->_mapcount, 1);
		table = (unsigned long *) page_to_phys(page);
		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
		spin_lock_bh(&mm->context.list_lock);
		list_add(&page->lru, &mm->context.pgtable_list);
	} else {
		for (bit = 1; mask & bit; bit <<= 1)
			table += PTRS_PER_PTE;
		mask = atomic_xor_bits(&page->_mapcount, bit);
		if ((mask & FRAG_MASK) == FRAG_MASK)
			list_del(&page->lru);
	}
	spin_unlock_bh(&mm->context.list_lock);
	return table;
}

void page_table_free(struct mm_struct *mm, unsigned long *table)
{
	struct page *page;
	unsigned int bit, mask;

	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
	if (page_table_with_pgste(page))
		return page_table_free_pgste(table);
	/* Free 1K/2K page table fragment of a 4K page */
	bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
	spin_lock_bh(&mm->context.list_lock);
	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
		list_del(&page->lru);
	mask = atomic_xor_bits(&page->_mapcount, bit);
	if (mask & FRAG_MASK)
		list_add(&page->lru, &mm->context.pgtable_list);
	spin_unlock_bh(&mm->context.list_lock);
	if (mask == 0) {
		pgtable_page_dtor(page);
		atomic_set(&page->_mapcount, -1);
		__free_page(page);
	}
}

static void __page_table_free_rcu(void *table, unsigned bit)
{
	struct page *page;

	if (bit == FRAG_MASK)
		return page_table_free_pgste(table);
	/* Free 1K/2K page table fragment of a 4K page */
	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
	if (atomic_xor_bits(&page->_mapcount, bit) == 0) {
		pgtable_page_dtor(page);
		atomic_set(&page->_mapcount, -1);
		__free_page(page);
	}
}

void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
			 unsigned long vmaddr)
{
	struct mm_struct *mm;
	struct page *page;
	unsigned int bit, mask;

	mm = tlb->mm;
	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
	if (page_table_with_pgste(page)) {
		gmap_unlink(mm, table, vmaddr);
		table = (unsigned long *) (__pa(table) | FRAG_MASK);
		tlb_remove_table(tlb, table);
		return;
	}
	bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)));
	spin_lock_bh(&mm->context.list_lock);
	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
		list_del(&page->lru);
	mask = atomic_xor_bits(&page->_mapcount, bit | (bit << 4));
	if (mask & FRAG_MASK)
		list_add_tail(&page->lru, &mm->context.pgtable_list);
	spin_unlock_bh(&mm->context.list_lock);
	table = (unsigned long *) (__pa(table) | (bit << 4));
	tlb_remove_table(tlb, table);
}

static void __tlb_remove_table(void *_table)
{
	const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK;
	void *table = (void *)((unsigned long) _table & ~mask);
	unsigned type = (unsigned long) _table & mask;

	if (type)
		__page_table_free_rcu(table, type);
	else
		free_pages((unsigned long) table, ALLOC_ORDER);
}

static void tlb_remove_table_smp_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

static void tlb_remove_table_one(void *table)
{
	/*
	 * This isn't an RCU grace period and hence the page-tables cannot be
	 * assumed to be actually RCU-freed.
	 *
	 * It is however sufficient for software page-table walkers that rely
	 * on IRQ disabling. See the comment near struct mmu_table_batch.
	 */
	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
	__tlb_remove_table(table);
}

static void tlb_remove_table_rcu(struct rcu_head *head)
{
	struct mmu_table_batch *batch;
	int i;

	batch = container_of(head, struct mmu_table_batch, rcu);

	for (i = 0; i < batch->nr; i++)
		__tlb_remove_table(batch->tables[i]);

	free_page((unsigned long)batch);
}

void tlb_table_flush(struct mmu_gather *tlb)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch) {
		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
		*batch = NULL;
	}
}

void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
	struct mmu_table_batch **batch = &tlb->batch;

	tlb->mm->context.flush_mm = 1;
	if (*batch == NULL) {
		*batch = (struct mmu_table_batch *)
			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
		if (*batch == NULL) {
			__tlb_flush_mm_lazy(tlb->mm);
			tlb_remove_table_one(table);
			return;
		}
		(*batch)->nr = 0;
	}
	(*batch)->tables[(*batch)->nr++] = table;
	if ((*batch)->nr == MAX_TABLE_BATCH)
		tlb_flush_mmu(tlb);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline void thp_split_vma(struct vm_area_struct *vma)
{
	unsigned long addr;

	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE)
		follow_page(vma, addr, FOLL_SPLIT);
}

static inline void thp_split_mm(struct mm_struct *mm)
{
	struct vm_area_struct *vma;

	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
		thp_split_vma(vma);
		vma->vm_flags &= ~VM_HUGEPAGE;
		vma->vm_flags |= VM_NOHUGEPAGE;
	}
	mm->def_flags |= VM_NOHUGEPAGE;
}
#else
static inline void thp_split_mm(struct mm_struct *mm)
{
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/*
 * switch on pgstes for its userspace process (for kvm)
 */
int s390_enable_sie(void)
{
	struct mm_struct *mm = current->mm;

	/* Do we have pgstes? if yes, we are done */
	if (mm_has_pgste(mm))
		return 0;
	/* Fail if the page tables are 2K */
	if (!mm_alloc_pgste(mm))
		return -EINVAL;
	down_write(&mm->mmap_sem);
	mm->context.has_pgste = 1;
	/* split thp mappings and disable thp for future mappings */
	thp_split_mm(mm);
	up_write(&mm->mmap_sem);
	return 0;
}
EXPORT_SYMBOL_GPL(s390_enable_sie);

/*
 * Enable storage key handling from now on and initialize the storage
 * keys with the default key.
 */
static int __s390_enable_skey(pte_t *pte, unsigned long addr,
			      unsigned long next, struct mm_walk *walk)
{
	unsigned long ptev;
	pgste_t pgste;

	pgste = pgste_get_lock(pte);
	/*
	 * Remove all zero page mappings,
	 * after establishing a policy to forbid zero page mappings
	 * following faults for that page will get fresh anonymous pages
	 */
	if (is_zero_pfn(pte_pfn(*pte))) {
		ptep_flush_direct(walk->mm, addr, pte);
		pte_val(*pte) = _PAGE_INVALID;
	}
	/* Clear storage key */
	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
			      PGSTE_GR_BIT | PGSTE_GC_BIT);
	ptev = pte_val(*pte);
	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
	pgste_set_unlock(pte, pgste);
	return 0;
}

int s390_enable_skey(void)
{
	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	int rc = 0;

	down_write(&mm->mmap_sem);
	if (mm_use_skey(mm))
		goto out_up;

	mm->context.use_skey = 1;
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
				MADV_UNMERGEABLE, &vma->vm_flags)) {
			mm->context.use_skey = 0;
			rc = -ENOMEM;
			goto out_up;
		}
	}
	mm->def_flags &= ~VM_MERGEABLE;

	walk.mm = mm;
	walk_page_range(0, TASK_SIZE, &walk);

out_up:
	up_write(&mm->mmap_sem);
	return rc;
}
EXPORT_SYMBOL_GPL(s390_enable_skey);

/*
 * Reset CMMA state, make all pages stable again.
 */
static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
			     unsigned long next, struct mm_walk *walk)
{
	pgste_t pgste;

	pgste = pgste_get_lock(pte);
	pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
	pgste_set_unlock(pte, pgste);
	return 0;
}

void s390_reset_cmma(struct mm_struct *mm)
{
	struct mm_walk walk = { .pte_entry = __s390_reset_cmma };

	down_write(&mm->mmap_sem);
	walk.mm = mm;
	walk_page_range(0, TASK_SIZE, &walk);
	up_write(&mm->mmap_sem);
}
EXPORT_SYMBOL_GPL(s390_reset_cmma);

/*
 * Test and reset if a guest page is dirty
 */
bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap)
{
	pte_t *pte;
	spinlock_t *ptl;
	bool dirty = false;

	pte = get_locked_pte(gmap->mm, address, &ptl);
	if (unlikely(!pte))
		return false;

	if (ptep_test_and_clear_user_dirty(gmap->mm, address, pte))
		dirty = true;

	spin_unlock(ptl);
	return dirty;
}
EXPORT_SYMBOL_GPL(gmap_test_and_clear_dirty);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address,
			   pmd_t *pmdp)
{
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	/* No need to flush TLB
	 * On s390 reference bits are in storage key and never in TLB */
	return pmdp_test_and_clear_young(vma, address, pmdp);
}

int pmdp_set_access_flags(struct vm_area_struct *vma,
			  unsigned long address, pmd_t *pmdp,
			  pmd_t entry, int dirty)
{
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);

	entry = pmd_mkyoung(entry);
	if (dirty)
		entry = pmd_mkdirty(entry);
	if (pmd_same(*pmdp, entry))
		return 0;
	pmdp_invalidate(vma, address, pmdp);
	set_pmd_at(vma->vm_mm, address, pmdp, entry);
	return 1;
}

static void pmdp_splitting_flush_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
			  pmd_t *pmdp)
{
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	if (!test_and_set_bit(_SEGMENT_ENTRY_SPLIT_BIT,
			      (unsigned long *) pmdp)) {
		/* need to serialize against gup-fast (IRQ disabled) */
		smp_call_function(pmdp_splitting_flush_sync, NULL, 1);
	}
}

void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				pgtable_t pgtable)
{
	struct list_head *lh = (struct list_head *) pgtable;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	if (!pmd_huge_pte(mm, pmdp))
		INIT_LIST_HEAD(lh);
	else
		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
	pmd_huge_pte(mm, pmdp) = pgtable;
}

pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
	struct list_head *lh;
	pgtable_t pgtable;
	pte_t *ptep;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	pgtable = pmd_huge_pte(mm, pmdp);
	lh = (struct list_head *) pgtable;
	if (list_empty(lh))
		pmd_huge_pte(mm, pmdp) = NULL;
	else {
		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
		list_del(lh);
	}
	ptep = (pte_t *) pgtable;
	pte_val(*ptep) = _PAGE_INVALID;
	ptep++;
	pte_val(*ptep) = _PAGE_INVALID;
	return pgtable;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */