summaryrefslogtreecommitdiffstats
path: root/arch/s390/include/asm/pgtable.h
blob: 97de1200c849275088acffc2a53c546f52ca5524 (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
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
/*
 *  S390 version
 *    Copyright IBM Corp. 1999, 2000
 *    Author(s): Hartmut Penner (hp@de.ibm.com)
 *               Ulrich Weigand (weigand@de.ibm.com)
 *               Martin Schwidefsky (schwidefsky@de.ibm.com)
 *
 *  Derived from "include/asm-i386/pgtable.h"
 */

#ifndef _ASM_S390_PGTABLE_H
#define _ASM_S390_PGTABLE_H

/*
 * The Linux memory management assumes a three-level page table setup. For
 * s390 31 bit we "fold" the mid level into the top-level page table, so
 * that we physically have the same two-level page table as the s390 mmu
 * expects in 31 bit mode. For s390 64 bit we use three of the five levels
 * the hardware provides (region first and region second tables are not
 * used).
 *
 * The "pgd_xxx()" functions are trivial for a folded two-level
 * setup: the pgd is never bad, and a pmd always exists (as it's folded
 * into the pgd entry)
 *
 * This file contains the functions and defines necessary to modify and use
 * the S390 page table tree.
 */
#ifndef __ASSEMBLY__
#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <asm/bug.h>
#include <asm/page.h>

extern pgd_t swapper_pg_dir[] __attribute__ ((aligned (4096)));
extern void paging_init(void);
extern void vmem_map_init(void);

/*
 * The S390 doesn't have any external MMU info: the kernel page
 * tables contain all the necessary information.
 */
#define update_mmu_cache(vma, address, ptep)     do { } while (0)
#define update_mmu_cache_pmd(vma, address, ptep) do { } while (0)

/*
 * ZERO_PAGE is a global shared page that is always zero; used
 * for zero-mapped memory areas etc..
 */

extern unsigned long empty_zero_page;
extern unsigned long zero_page_mask;

#define ZERO_PAGE(vaddr) \
	(virt_to_page((void *)(empty_zero_page + \
	 (((unsigned long)(vaddr)) &zero_page_mask))))
#define __HAVE_COLOR_ZERO_PAGE

#endif /* !__ASSEMBLY__ */

/*
 * PMD_SHIFT determines the size of the area a second-level page
 * table can map
 * PGDIR_SHIFT determines what a third-level page table entry can map
 */
#ifndef CONFIG_64BIT
# define PMD_SHIFT	20
# define PUD_SHIFT	20
# define PGDIR_SHIFT	20
#else /* CONFIG_64BIT */
# define PMD_SHIFT	20
# define PUD_SHIFT	31
# define PGDIR_SHIFT	42
#endif /* CONFIG_64BIT */

#define PMD_SIZE        (1UL << PMD_SHIFT)
#define PMD_MASK        (~(PMD_SIZE-1))
#define PUD_SIZE	(1UL << PUD_SHIFT)
#define PUD_MASK	(~(PUD_SIZE-1))
#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
#define PGDIR_MASK	(~(PGDIR_SIZE-1))

/*
 * entries per page directory level: the S390 is two-level, so
 * we don't really have any PMD directory physically.
 * for S390 segment-table entries are combined to one PGD
 * that leads to 1024 pte per pgd
 */
#define PTRS_PER_PTE	256
#ifndef CONFIG_64BIT
#define PTRS_PER_PMD	1
#define PTRS_PER_PUD	1
#else /* CONFIG_64BIT */
#define PTRS_PER_PMD	2048
#define PTRS_PER_PUD	2048
#endif /* CONFIG_64BIT */
#define PTRS_PER_PGD	2048

#define FIRST_USER_ADDRESS  0

#define pte_ERROR(e) \
	printk("%s:%d: bad pte %p.\n", __FILE__, __LINE__, (void *) pte_val(e))
#define pmd_ERROR(e) \
	printk("%s:%d: bad pmd %p.\n", __FILE__, __LINE__, (void *) pmd_val(e))
#define pud_ERROR(e) \
	printk("%s:%d: bad pud %p.\n", __FILE__, __LINE__, (void *) pud_val(e))
#define pgd_ERROR(e) \
	printk("%s:%d: bad pgd %p.\n", __FILE__, __LINE__, (void *) pgd_val(e))

#ifndef __ASSEMBLY__
/*
 * The vmalloc and module area will always be on the topmost area of the kernel
 * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc and modules.
 * On 64 bit kernels we have a 2GB area at the top of the vmalloc area where
 * modules will reside. That makes sure that inter module branches always
 * happen without trampolines and in addition the placement within a 2GB frame
 * is branch prediction unit friendly.
 */
extern unsigned long VMALLOC_START;
extern unsigned long VMALLOC_END;
extern struct page *vmemmap;

#define VMEM_MAX_PHYS ((unsigned long) vmemmap)

#ifdef CONFIG_64BIT
extern unsigned long MODULES_VADDR;
extern unsigned long MODULES_END;
#define MODULES_VADDR	MODULES_VADDR
#define MODULES_END	MODULES_END
#define MODULES_LEN	(1UL << 31)
#endif

/*
 * A 31 bit pagetable entry of S390 has following format:
 *  |   PFRA          |    |  OS  |
 * 0                   0IP0
 * 00000000001111111111222222222233
 * 01234567890123456789012345678901
 *
 * I Page-Invalid Bit:    Page is not available for address-translation
 * P Page-Protection Bit: Store access not possible for page
 *
 * A 31 bit segmenttable entry of S390 has following format:
 *  |   P-table origin      |  |PTL
 * 0                         IC
 * 00000000001111111111222222222233
 * 01234567890123456789012345678901
 *
 * I Segment-Invalid Bit:    Segment is not available for address-translation
 * C Common-Segment Bit:     Segment is not private (PoP 3-30)
 * PTL Page-Table-Length:    Page-table length (PTL+1*16 entries -> up to 256)
 *
 * The 31 bit segmenttable origin of S390 has following format:
 *
 *  |S-table origin   |     | STL |
 * X                   **GPS
 * 00000000001111111111222222222233
 * 01234567890123456789012345678901
 *
 * X Space-Switch event:
 * G Segment-Invalid Bit:     *
 * P Private-Space Bit:       Segment is not private (PoP 3-30)
 * S Storage-Alteration:
 * STL Segment-Table-Length:  Segment-table length (STL+1*16 entries -> up to 2048)
 *
 * A 64 bit pagetable entry of S390 has following format:
 * |			 PFRA			      |0IPC|  OS  |
 * 0000000000111111111122222222223333333333444444444455555555556666
 * 0123456789012345678901234567890123456789012345678901234567890123
 *
 * I Page-Invalid Bit:    Page is not available for address-translation
 * P Page-Protection Bit: Store access not possible for page
 * C Change-bit override: HW is not required to set change bit
 *
 * A 64 bit segmenttable entry of S390 has following format:
 * |        P-table origin                              |      TT
 * 0000000000111111111122222222223333333333444444444455555555556666
 * 0123456789012345678901234567890123456789012345678901234567890123
 *
 * I Segment-Invalid Bit:    Segment is not available for address-translation
 * C Common-Segment Bit:     Segment is not private (PoP 3-30)
 * P Page-Protection Bit: Store access not possible for page
 * TT Type 00
 *
 * A 64 bit region table entry of S390 has following format:
 * |        S-table origin                             |   TF  TTTL
 * 0000000000111111111122222222223333333333444444444455555555556666
 * 0123456789012345678901234567890123456789012345678901234567890123
 *
 * I Segment-Invalid Bit:    Segment is not available for address-translation
 * TT Type 01
 * TF
 * TL Table length
 *
 * The 64 bit regiontable origin of S390 has following format:
 * |      region table origon                          |       DTTL
 * 0000000000111111111122222222223333333333444444444455555555556666
 * 0123456789012345678901234567890123456789012345678901234567890123
 *
 * X Space-Switch event:
 * G Segment-Invalid Bit:  
 * P Private-Space Bit:    
 * S Storage-Alteration:
 * R Real space
 * TL Table-Length:
 *
 * A storage key has the following format:
 * | ACC |F|R|C|0|
 *  0   3 4 5 6 7
 * ACC: access key
 * F  : fetch protection bit
 * R  : referenced bit
 * C  : changed bit
 */

/* Hardware bits in the page table entry */
#define _PAGE_CO	0x100		/* HW Change-bit override */
#define _PAGE_RO	0x200		/* HW read-only bit  */
#define _PAGE_INVALID	0x400		/* HW invalid bit    */

/* Software bits in the page table entry */
#define _PAGE_SWT	0x001		/* SW pte type bit t */
#define _PAGE_SWX	0x002		/* SW pte type bit x */
#define _PAGE_SWC	0x004		/* SW pte changed bit */
#define _PAGE_SWR	0x008		/* SW pte referenced bit */
#define _PAGE_SWW	0x010		/* SW pte write bit */
#define _PAGE_SPECIAL	0x020		/* SW associated with special page */
#define __HAVE_ARCH_PTE_SPECIAL

/* Set of bits not changed in pte_modify */
#define _PAGE_CHG_MASK		(PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \
				 _PAGE_SWC | _PAGE_SWR)

/* Six different types of pages. */
#define _PAGE_TYPE_EMPTY	0x400
#define _PAGE_TYPE_NONE		0x401
#define _PAGE_TYPE_SWAP		0x403
#define _PAGE_TYPE_FILE		0x601	/* bit 0x002 is used for offset !! */
#define _PAGE_TYPE_RO		0x200
#define _PAGE_TYPE_RW		0x000

/*
 * Only four types for huge pages, using the invalid bit and protection bit
 * of a segment table entry.
 */
#define _HPAGE_TYPE_EMPTY	0x020	/* _SEGMENT_ENTRY_INV */
#define _HPAGE_TYPE_NONE	0x220
#define _HPAGE_TYPE_RO		0x200	/* _SEGMENT_ENTRY_RO  */
#define _HPAGE_TYPE_RW		0x000

/*
 * PTE type bits are rather complicated. handle_pte_fault uses pte_present,
 * pte_none and pte_file to find out the pte type WITHOUT holding the page
 * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to
 * invalidate a given pte. ipte sets the hw invalid bit and clears all tlbs
 * for the page. The page table entry is set to _PAGE_TYPE_EMPTY afterwards.
 * This change is done while holding the lock, but the intermediate step
 * of a previously valid pte with the hw invalid bit set can be observed by
 * handle_pte_fault. That makes it necessary that all valid pte types with
 * the hw invalid bit set must be distinguishable from the four pte types
 * empty, none, swap and file.
 *
 *			irxt  ipte  irxt
 * _PAGE_TYPE_EMPTY	1000   ->   1000
 * _PAGE_TYPE_NONE	1001   ->   1001
 * _PAGE_TYPE_SWAP	1011   ->   1011
 * _PAGE_TYPE_FILE	11?1   ->   11?1
 * _PAGE_TYPE_RO	0100   ->   1100
 * _PAGE_TYPE_RW	0000   ->   1000
 *
 * pte_none is true for bits combinations 1000, 1010, 1100, 1110
 * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001
 * pte_file is true for bits combinations 1101, 1111
 * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid.
 */

#ifndef CONFIG_64BIT

/* Bits in the segment table address-space-control-element */
#define _ASCE_SPACE_SWITCH	0x80000000UL	/* space switch event	    */
#define _ASCE_ORIGIN_MASK	0x7ffff000UL	/* segment table origin	    */
#define _ASCE_PRIVATE_SPACE	0x100	/* private space control	    */
#define _ASCE_ALT_EVENT		0x80	/* storage alteration event control */
#define _ASCE_TABLE_LENGTH	0x7f	/* 128 x 64 entries = 8k	    */

/* Bits in the segment table entry */
#define _SEGMENT_ENTRY_ORIGIN	0x7fffffc0UL	/* page table origin	    */
#define _SEGMENT_ENTRY_RO	0x200	/* page protection bit		    */
#define _SEGMENT_ENTRY_INV	0x20	/* invalid segment table entry	    */
#define _SEGMENT_ENTRY_COMMON	0x10	/* common segment bit		    */
#define _SEGMENT_ENTRY_PTL	0x0f	/* page table length		    */

#define _SEGMENT_ENTRY		(_SEGMENT_ENTRY_PTL)
#define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)

/* Page status table bits for virtualization */
#define RCP_ACC_BITS	0xf0000000UL
#define RCP_FP_BIT	0x08000000UL
#define RCP_PCL_BIT	0x00800000UL
#define RCP_HR_BIT	0x00400000UL
#define RCP_HC_BIT	0x00200000UL
#define RCP_GR_BIT	0x00040000UL
#define RCP_GC_BIT	0x00020000UL

/* User dirty / referenced bit for KVM's migration feature */
#define KVM_UR_BIT	0x00008000UL
#define KVM_UC_BIT	0x00004000UL

#else /* CONFIG_64BIT */

/* Bits in the segment/region table address-space-control-element */
#define _ASCE_ORIGIN		~0xfffUL/* segment table origin		    */
#define _ASCE_PRIVATE_SPACE	0x100	/* private space control	    */
#define _ASCE_ALT_EVENT		0x80	/* storage alteration event control */
#define _ASCE_SPACE_SWITCH	0x40	/* space switch event		    */
#define _ASCE_REAL_SPACE	0x20	/* real space control		    */
#define _ASCE_TYPE_MASK		0x0c	/* asce table type mask		    */
#define _ASCE_TYPE_REGION1	0x0c	/* region first table type	    */
#define _ASCE_TYPE_REGION2	0x08	/* region second table type	    */
#define _ASCE_TYPE_REGION3	0x04	/* region third table type	    */
#define _ASCE_TYPE_SEGMENT	0x00	/* segment table type		    */
#define _ASCE_TABLE_LENGTH	0x03	/* region table length		    */

/* Bits in the region table entry */
#define _REGION_ENTRY_ORIGIN	~0xfffUL/* region/segment table origin	    */
#define _REGION_ENTRY_RO	0x200	/* region protection bit	    */
#define _REGION_ENTRY_INV	0x20	/* invalid region table entry	    */
#define _REGION_ENTRY_TYPE_MASK	0x0c	/* region/segment table type mask   */
#define _REGION_ENTRY_TYPE_R1	0x0c	/* region first table type	    */
#define _REGION_ENTRY_TYPE_R2	0x08	/* region second table type	    */
#define _REGION_ENTRY_TYPE_R3	0x04	/* region third table type	    */
#define _REGION_ENTRY_LENGTH	0x03	/* region third length		    */

#define _REGION1_ENTRY		(_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_LENGTH)
#define _REGION1_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INV)
#define _REGION2_ENTRY		(_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_LENGTH)
#define _REGION2_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INV)
#define _REGION3_ENTRY		(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
#define _REGION3_ENTRY_EMPTY	(_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV)

#define _REGION3_ENTRY_LARGE	0x400	/* RTTE-format control, large page  */

/* Bits in the segment table entry */
#define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* segment table origin		    */
#define _SEGMENT_ENTRY_RO	0x200	/* page protection bit		    */
#define _SEGMENT_ENTRY_INV	0x20	/* invalid segment table entry	    */

#define _SEGMENT_ENTRY		(0)
#define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)

#define _SEGMENT_ENTRY_LARGE	0x400	/* STE-format control, large page   */
#define _SEGMENT_ENTRY_CO	0x100	/* change-recording override   */
#define _SEGMENT_ENTRY_SPLIT_BIT 0	/* THP splitting bit number */
#define _SEGMENT_ENTRY_SPLIT	(1UL << _SEGMENT_ENTRY_SPLIT_BIT)

/* Set of bits not changed in pmd_modify */
#define _SEGMENT_CHG_MASK	(_SEGMENT_ENTRY_ORIGIN | _SEGMENT_ENTRY_LARGE \
				 | _SEGMENT_ENTRY_SPLIT | _SEGMENT_ENTRY_CO)

/* Page status table bits for virtualization */
#define RCP_ACC_BITS	0xf000000000000000UL
#define RCP_FP_BIT	0x0800000000000000UL
#define RCP_PCL_BIT	0x0080000000000000UL
#define RCP_HR_BIT	0x0040000000000000UL
#define RCP_HC_BIT	0x0020000000000000UL
#define RCP_GR_BIT	0x0004000000000000UL
#define RCP_GC_BIT	0x0002000000000000UL

/* User dirty / referenced bit for KVM's migration feature */
#define KVM_UR_BIT	0x0000800000000000UL
#define KVM_UC_BIT	0x0000400000000000UL

#endif /* CONFIG_64BIT */

/*
 * A user page table pointer has the space-switch-event bit, the
 * private-space-control bit and the storage-alteration-event-control
 * bit set. A kernel page table pointer doesn't need them.
 */
#define _ASCE_USER_BITS		(_ASCE_SPACE_SWITCH | _ASCE_PRIVATE_SPACE | \
				 _ASCE_ALT_EVENT)

/*
 * Page protection definitions.
 */
#define PAGE_NONE	__pgprot(_PAGE_TYPE_NONE)
#define PAGE_RO		__pgprot(_PAGE_TYPE_RO)
#define PAGE_RW		__pgprot(_PAGE_TYPE_RO | _PAGE_SWW)
#define PAGE_RWC	__pgprot(_PAGE_TYPE_RW | _PAGE_SWW | _PAGE_SWC)

#define PAGE_KERNEL	PAGE_RWC
#define PAGE_SHARED	PAGE_KERNEL
#define PAGE_COPY	PAGE_RO

/*
 * On s390 the page table entry has an invalid bit and a read-only bit.
 * Read permission implies execute permission and write permission
 * implies read permission.
 */
         /*xwr*/
#define __P000	PAGE_NONE
#define __P001	PAGE_RO
#define __P010	PAGE_RO
#define __P011	PAGE_RO
#define __P100	PAGE_RO
#define __P101	PAGE_RO
#define __P110	PAGE_RO
#define __P111	PAGE_RO

#define __S000	PAGE_NONE
#define __S001	PAGE_RO
#define __S010	PAGE_RW
#define __S011	PAGE_RW
#define __S100	PAGE_RO
#define __S101	PAGE_RO
#define __S110	PAGE_RW
#define __S111	PAGE_RW

static inline int mm_exclusive(struct mm_struct *mm)
{
	return likely(mm == current->active_mm &&
		      atomic_read(&mm->context.attach_count) <= 1);
}

static inline int mm_has_pgste(struct mm_struct *mm)
{
#ifdef CONFIG_PGSTE
	if (unlikely(mm->context.has_pgste))
		return 1;
#endif
	return 0;
}
/*
 * pgd/pmd/pte query functions
 */
#ifndef CONFIG_64BIT

static inline int pgd_present(pgd_t pgd) { return 1; }
static inline int pgd_none(pgd_t pgd)    { return 0; }
static inline int pgd_bad(pgd_t pgd)     { return 0; }

static inline int pud_present(pud_t pud) { return 1; }
static inline int pud_none(pud_t pud)	 { return 0; }
static inline int pud_large(pud_t pud)	 { return 0; }
static inline int pud_bad(pud_t pud)	 { return 0; }

#else /* CONFIG_64BIT */

static inline int pgd_present(pgd_t pgd)
{
	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
		return 1;
	return (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) != 0UL;
}

static inline int pgd_none(pgd_t pgd)
{
	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
		return 0;
	return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL;
}

static inline int pgd_bad(pgd_t pgd)
{
	/*
	 * With dynamic page table levels the pgd can be a region table
	 * entry or a segment table entry. Check for the bit that are
	 * invalid for either table entry.
	 */
	unsigned long mask =
		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
	return (pgd_val(pgd) & mask) != 0;
}

static inline int pud_present(pud_t pud)
{
	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
		return 1;
	return (pud_val(pud) & _REGION_ENTRY_ORIGIN) != 0UL;
}

static inline int pud_none(pud_t pud)
{
	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
		return 0;
	return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL;
}

static inline int pud_large(pud_t pud)
{
	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) != _REGION_ENTRY_TYPE_R3)
		return 0;
	return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
}

static inline int pud_bad(pud_t pud)
{
	/*
	 * With dynamic page table levels the pud can be a region table
	 * entry or a segment table entry. Check for the bit that are
	 * invalid for either table entry.
	 */
	unsigned long mask =
		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
	return (pud_val(pud) & mask) != 0;
}

#endif /* CONFIG_64BIT */

static inline int pmd_present(pmd_t pmd)
{
	unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO;
	return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE ||
	       !(pmd_val(pmd) & _SEGMENT_ENTRY_INV);
}

static inline int pmd_none(pmd_t pmd)
{
	return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) &&
	       !(pmd_val(pmd) & _SEGMENT_ENTRY_RO);
}

static inline int pmd_large(pmd_t pmd)
{
#ifdef CONFIG_64BIT
	return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE);
#else
	return 0;
#endif
}

static inline int pmd_bad(pmd_t pmd)
{
	unsigned long mask = ~_SEGMENT_ENTRY_ORIGIN & ~_SEGMENT_ENTRY_INV;
	return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY;
}

#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
extern void pmdp_splitting_flush(struct vm_area_struct *vma,
				 unsigned long addr, pmd_t *pmdp);

#define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pmd_t *pmdp,
				 pmd_t entry, int dirty);

#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
				  unsigned long address, pmd_t *pmdp);

#define __HAVE_ARCH_PMD_WRITE
static inline int pmd_write(pmd_t pmd)
{
	return (pmd_val(pmd) & _SEGMENT_ENTRY_RO) == 0;
}

static inline int pmd_young(pmd_t pmd)
{
	return 0;
}

static inline int pte_none(pte_t pte)
{
	return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT);
}

static inline int pte_present(pte_t pte)
{
	unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT | _PAGE_SWX;
	return (pte_val(pte) & mask) == _PAGE_TYPE_NONE ||
		(!(pte_val(pte) & _PAGE_INVALID) &&
		 !(pte_val(pte) & _PAGE_SWT));
}

static inline int pte_file(pte_t pte)
{
	unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT;
	return (pte_val(pte) & mask) == _PAGE_TYPE_FILE;
}

static inline int pte_special(pte_t pte)
{
	return (pte_val(pte) & _PAGE_SPECIAL);
}

#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t a, pte_t b)
{
	return pte_val(a) == pte_val(b);
}

static inline pgste_t pgste_get_lock(pte_t *ptep)
{
	unsigned long new = 0;
#ifdef CONFIG_PGSTE
	unsigned long old;

	preempt_disable();
	asm(
		"	lg	%0,%2\n"
		"0:	lgr	%1,%0\n"
		"	nihh	%0,0xff7f\n"	/* clear RCP_PCL_BIT in old */
		"	oihh	%1,0x0080\n"	/* set RCP_PCL_BIT in new */
		"	csg	%0,%1,%2\n"
		"	jl	0b\n"
		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
		: "Q" (ptep[PTRS_PER_PTE]) : "cc");
#endif
	return __pgste(new);
}

static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
	asm(
		"	nihh	%1,0xff7f\n"	/* clear RCP_PCL_BIT */
		"	stg	%1,%0\n"
		: "=Q" (ptep[PTRS_PER_PTE])
		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) : "cc");
	preempt_enable();
#endif
}

static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
	unsigned long address, bits;
	unsigned char skey;

	if (!pte_present(*ptep))
		return pgste;
	address = pte_val(*ptep) & PAGE_MASK;
	skey = page_get_storage_key(address);
	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
	/* Clear page changed & referenced bit in the storage key */
	if (bits & _PAGE_CHANGED)
		page_set_storage_key(address, skey ^ bits, 0);
	else if (bits)
		page_reset_referenced(address);
	/* Transfer page changed & referenced bit to guest bits in pgste */
	pgste_val(pgste) |= bits << 48;		/* RCP_GR_BIT & RCP_GC_BIT */
	/* Get host changed & referenced bits from pgste */
	bits |= (pgste_val(pgste) & (RCP_HR_BIT | RCP_HC_BIT)) >> 52;
	/* Transfer page changed & referenced bit to kvm user bits */
	pgste_val(pgste) |= bits << 45;		/* KVM_UR_BIT & KVM_UC_BIT */
	/* Clear relevant host bits in pgste. */
	pgste_val(pgste) &= ~(RCP_HR_BIT | RCP_HC_BIT);
	pgste_val(pgste) &= ~(RCP_ACC_BITS | RCP_FP_BIT);
	/* Copy page access key and fetch protection bit to pgste */
	pgste_val(pgste) |=
		(unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
	/* Transfer referenced bit to pte */
	pte_val(*ptep) |= (bits & _PAGE_REFERENCED) << 1;
#endif
	return pgste;

}

static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
	int young;

	if (!pte_present(*ptep))
		return pgste;
	/* Get referenced bit from storage key */
	young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
	if (young)
		pgste_val(pgste) |= RCP_GR_BIT;
	/* Get host referenced bit from pgste */
	if (pgste_val(pgste) & RCP_HR_BIT) {
		pgste_val(pgste) &= ~RCP_HR_BIT;
		young = 1;
	}
	/* Transfer referenced bit to kvm user bits and pte */
	if (young) {
		pgste_val(pgste) |= KVM_UR_BIT;
		pte_val(*ptep) |= _PAGE_SWR;
	}
#endif
	return pgste;
}

static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
{
#ifdef CONFIG_PGSTE
	unsigned long address;
	unsigned long okey, nkey;

	if (!pte_present(entry))
		return;
	address = pte_val(entry) & PAGE_MASK;
	okey = nkey = page_get_storage_key(address);
	nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
	/* Set page access key and fetch protection bit from pgste */
	nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
	if (okey != nkey)
		page_set_storage_key(address, nkey, 0);
#endif
}

static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
{
	if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_SWW)) {
		/*
		 * Without enhanced suppression-on-protection force
		 * the dirty bit on for all writable ptes.
		 */
		pte_val(entry) |= _PAGE_SWC;
		pte_val(entry) &= ~_PAGE_RO;
	}
	*ptep = entry;
}

/**
 * struct gmap_struct - guest address space
 * @mm: pointer to the parent mm_struct
 * @table: pointer to the page directory
 * @asce: address space control element for gmap page table
 * @crst_list: list of all crst tables used in the guest address space
 */
struct gmap {
	struct list_head list;
	struct mm_struct *mm;
	unsigned long *table;
	unsigned long asce;
	struct list_head crst_list;
};

/**
 * struct gmap_rmap - reverse mapping for segment table entries
 * @next: pointer to the next gmap_rmap structure in the list
 * @entry: pointer to a segment table entry
 */
struct gmap_rmap {
	struct list_head list;
	unsigned long *entry;
};

/**
 * struct gmap_pgtable - gmap information attached to a page table
 * @vmaddr: address of the 1MB segment in the process virtual memory
 * @mapper: list of segment table entries maping a page table
 */
struct gmap_pgtable {
	unsigned long vmaddr;
	struct list_head mapper;
};

struct gmap *gmap_alloc(struct mm_struct *mm);
void gmap_free(struct gmap *gmap);
void gmap_enable(struct gmap *gmap);
void gmap_disable(struct gmap *gmap);
int gmap_map_segment(struct gmap *gmap, unsigned long from,
		     unsigned long to, unsigned long length);
int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
unsigned long __gmap_fault(unsigned long address, struct gmap *);
unsigned long gmap_fault(unsigned long address, struct gmap *);
void gmap_discard(unsigned long from, unsigned long to, struct gmap *);

/*
 * Certain architectures need to do special things when PTEs
 * within a page table are directly modified.  Thus, the following
 * hook is made available.
 */
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
			      pte_t *ptep, pte_t entry)
{
	pgste_t pgste;

	if (mm_has_pgste(mm)) {
		pgste = pgste_get_lock(ptep);
		pgste_set_key(ptep, pgste, entry);
		pgste_set_pte(ptep, entry);
		pgste_set_unlock(ptep, pgste);
	} else {
		if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1)
			pte_val(entry) |= _PAGE_CO;
		*ptep = entry;
	}
}

/*
 * query functions pte_write/pte_dirty/pte_young only work if
 * pte_present() is true. Undefined behaviour if not..
 */
static inline int pte_write(pte_t pte)
{
	return (pte_val(pte) & _PAGE_SWW) != 0;
}

static inline int pte_dirty(pte_t pte)
{
	return (pte_val(pte) & _PAGE_SWC) != 0;
}

static inline int pte_young(pte_t pte)
{
#ifdef CONFIG_PGSTE
	if (pte_val(pte) & _PAGE_SWR)
		return 1;
#endif
	return 0;
}

/*
 * pgd/pmd/pte modification functions
 */

static inline void pgd_clear(pgd_t *pgd)
{
#ifdef CONFIG_64BIT
	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
		pgd_val(*pgd) = _REGION2_ENTRY_EMPTY;
#endif
}

static inline void pud_clear(pud_t *pud)
{
#ifdef CONFIG_64BIT
	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
		pud_val(*pud) = _REGION3_ENTRY_EMPTY;
#endif
}

static inline void pmd_clear(pmd_t *pmdp)
{
	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
}

static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
}

/*
 * The following pte modification functions only work if
 * pte_present() is true. Undefined behaviour if not..
 */
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	pte_val(pte) &= _PAGE_CHG_MASK;
	pte_val(pte) |= pgprot_val(newprot);
	if ((pte_val(pte) & _PAGE_SWC) && (pte_val(pte) & _PAGE_SWW))
		pte_val(pte) &= ~_PAGE_RO;
	return pte;
}

static inline pte_t pte_wrprotect(pte_t pte)
{
	pte_val(pte) &= ~_PAGE_SWW;
	/* Do not clobber _PAGE_TYPE_NONE pages!  */
	if (!(pte_val(pte) & _PAGE_INVALID))
		pte_val(pte) |= _PAGE_RO;
	return pte;
}

static inline pte_t pte_mkwrite(pte_t pte)
{
	pte_val(pte) |= _PAGE_SWW;
	if (pte_val(pte) & _PAGE_SWC)
		pte_val(pte) &= ~_PAGE_RO;
	return pte;
}

static inline pte_t pte_mkclean(pte_t pte)
{
	pte_val(pte) &= ~_PAGE_SWC;
	/* Do not clobber _PAGE_TYPE_NONE pages!  */
	if (!(pte_val(pte) & _PAGE_INVALID))
		pte_val(pte) |= _PAGE_RO;
	return pte;
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	pte_val(pte) |= _PAGE_SWC;
	if (pte_val(pte) & _PAGE_SWW)
		pte_val(pte) &= ~_PAGE_RO;
	return pte;
}

static inline pte_t pte_mkold(pte_t pte)
{
#ifdef CONFIG_PGSTE
	pte_val(pte) &= ~_PAGE_SWR;
#endif
	return pte;
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return pte;
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	pte_val(pte) |= _PAGE_SPECIAL;
	return pte;
}

#ifdef CONFIG_HUGETLB_PAGE
static inline pte_t pte_mkhuge(pte_t pte)
{
	/*
	 * PROT_NONE needs to be remapped from the pte type to the ste type.
	 * The HW invalid bit is also different for pte and ste. The pte
	 * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE
	 * bit, so we don't have to clear it.
	 */
	if (pte_val(pte) & _PAGE_INVALID) {
		if (pte_val(pte) & _PAGE_SWT)
			pte_val(pte) |= _HPAGE_TYPE_NONE;
		pte_val(pte) |= _SEGMENT_ENTRY_INV;
	}
	/*
	 * Clear SW pte bits, there are no SW bits in a segment table entry.
	 */
	pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX | _PAGE_SWC |
			  _PAGE_SWR | _PAGE_SWW);
	/*
	 * Also set the change-override bit because we don't need dirty bit
	 * tracking for hugetlbfs pages.
	 */
	pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
	return pte;
}
#endif

/*
 * Get (and clear) the user dirty bit for a pte.
 */
static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
						 pte_t *ptep)
{
	pgste_t pgste;
	int dirty = 0;

	if (mm_has_pgste(mm)) {
		pgste = pgste_get_lock(ptep);
		pgste = pgste_update_all(ptep, pgste);
		dirty = !!(pgste_val(pgste) & KVM_UC_BIT);
		pgste_val(pgste) &= ~KVM_UC_BIT;
		pgste_set_unlock(ptep, pgste);
		return dirty;
	}
	return dirty;
}

/*
 * Get (and clear) the user referenced bit for a pte.
 */
static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
						 pte_t *ptep)
{
	pgste_t pgste;
	int young = 0;

	if (mm_has_pgste(mm)) {
		pgste = pgste_get_lock(ptep);
		pgste = pgste_update_young(ptep, pgste);
		young = !!(pgste_val(pgste) & KVM_UR_BIT);
		pgste_val(pgste) &= ~KVM_UR_BIT;
		pgste_set_unlock(ptep, pgste);
	}
	return young;
}

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long addr, pte_t *ptep)
{
	pgste_t pgste;
	pte_t pte;

	if (mm_has_pgste(vma->vm_mm)) {
		pgste = pgste_get_lock(ptep);
		pgste = pgste_update_young(ptep, pgste);
		pte = *ptep;
		*ptep = pte_mkold(pte);
		pgste_set_unlock(ptep, pgste);
		return pte_young(pte);
	}
	return 0;
}

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
					 unsigned long address, pte_t *ptep)
{
	/* No need to flush TLB
	 * On s390 reference bits are in storage key and never in TLB
	 * With virtualization we handle the reference bit, without we
	 * we can simply return */
	return ptep_test_and_clear_young(vma, address, ptep);
}

static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
{
	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
#ifndef CONFIG_64BIT
		/* pto must point to the start of the segment table */
		pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
#else
		/* ipte in zarch mode can do the math */
		pte_t *pto = ptep;
#endif
		asm volatile(
			"	ipte	%2,%3"
			: "=m" (*ptep) : "m" (*ptep),
			  "a" (pto), "a" (address));
	}
}

/*
 * This is hard to understand. ptep_get_and_clear and ptep_clear_flush
 * both clear the TLB for the unmapped pte. The reason is that
 * ptep_get_and_clear is used in common code (e.g. change_pte_range)
 * to modify an active pte. The sequence is
 *   1) ptep_get_and_clear
 *   2) set_pte_at
 *   3) flush_tlb_range
 * On s390 the tlb needs to get flushed with the modification of the pte
 * if the pte is active. The only way how this can be implemented is to
 * have ptep_get_and_clear do the tlb flush. In exchange flush_tlb_range
 * is a nop.
 */
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
				       unsigned long address, pte_t *ptep)
{
	pgste_t pgste;
	pte_t pte;

	mm->context.flush_mm = 1;
	if (mm_has_pgste(mm))
		pgste = pgste_get_lock(ptep);

	pte = *ptep;
	if (!mm_exclusive(mm))
		__ptep_ipte(address, ptep);
	pte_val(*ptep) = _PAGE_TYPE_EMPTY;

	if (mm_has_pgste(mm)) {
		pgste = pgste_update_all(&pte, pgste);
		pgste_set_unlock(ptep, pgste);
	}
	return pte;
}

#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
					   unsigned long address,
					   pte_t *ptep)
{
	pte_t pte;

	mm->context.flush_mm = 1;
	if (mm_has_pgste(mm))
		pgste_get_lock(ptep);

	pte = *ptep;
	if (!mm_exclusive(mm))
		__ptep_ipte(address, ptep);
	return pte;
}

static inline void ptep_modify_prot_commit(struct mm_struct *mm,
					   unsigned long address,
					   pte_t *ptep, pte_t pte)
{
	if (mm_has_pgste(mm)) {
		pgste_set_pte(ptep, pte);
		pgste_set_unlock(ptep, *(pgste_t *)(ptep + PTRS_PER_PTE));
	} else
		*ptep = pte;
}

#define __HAVE_ARCH_PTEP_CLEAR_FLUSH
static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
				     unsigned long address, pte_t *ptep)
{
	pgste_t pgste;
	pte_t pte;

	if (mm_has_pgste(vma->vm_mm))
		pgste = pgste_get_lock(ptep);

	pte = *ptep;
	__ptep_ipte(address, ptep);
	pte_val(*ptep) = _PAGE_TYPE_EMPTY;

	if (mm_has_pgste(vma->vm_mm)) {
		pgste = pgste_update_all(&pte, pgste);
		pgste_set_unlock(ptep, pgste);
	}
	return pte;
}

/*
 * The batched pte unmap code uses ptep_get_and_clear_full to clear the
 * ptes. Here an optimization is possible. tlb_gather_mmu flushes all
 * tlbs of an mm if it can guarantee that the ptes of the mm_struct
 * cannot be accessed while the batched unmap is running. In this case
 * full==1 and a simple pte_clear is enough. See tlb.h.
 */
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
					    unsigned long address,
					    pte_t *ptep, int full)
{
	pgste_t pgste;
	pte_t pte;

	if (mm_has_pgste(mm))
		pgste = pgste_get_lock(ptep);

	pte = *ptep;
	if (!full)
		__ptep_ipte(address, ptep);
	pte_val(*ptep) = _PAGE_TYPE_EMPTY;

	if (mm_has_pgste(mm)) {
		pgste = pgste_update_all(&pte, pgste);
		pgste_set_unlock(ptep, pgste);
	}
	return pte;
}

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
				       unsigned long address, pte_t *ptep)
{
	pgste_t pgste;
	pte_t pte = *ptep;

	if (pte_write(pte)) {
		mm->context.flush_mm = 1;
		if (mm_has_pgste(mm))
			pgste = pgste_get_lock(ptep);

		if (!mm_exclusive(mm))
			__ptep_ipte(address, ptep);
		pte = pte_wrprotect(pte);

		if (mm_has_pgste(mm)) {
			pgste_set_pte(ptep, pte);
			pgste_set_unlock(ptep, pgste);
		} else
			*ptep = pte;
	}
	return pte;
}

#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
static inline int ptep_set_access_flags(struct vm_area_struct *vma,
					unsigned long address, pte_t *ptep,
					pte_t entry, int dirty)
{
	pgste_t pgste;

	if (pte_same(*ptep, entry))
		return 0;
	if (mm_has_pgste(vma->vm_mm))
		pgste = pgste_get_lock(ptep);

	__ptep_ipte(address, ptep);

	if (mm_has_pgste(vma->vm_mm)) {
		pgste_set_pte(ptep, entry);
		pgste_set_unlock(ptep, pgste);
	} else
		*ptep = entry;
	return 1;
}

/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
{
	pte_t __pte;
	pte_val(__pte) = physpage + pgprot_val(pgprot);
	return __pte;
}

static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
{
	unsigned long physpage = page_to_phys(page);
	pte_t __pte = mk_pte_phys(physpage, pgprot);

	if ((pte_val(__pte) & _PAGE_SWW) && PageDirty(page)) {
		pte_val(__pte) |= _PAGE_SWC;
		pte_val(__pte) &= ~_PAGE_RO;
	}
	return __pte;
}

#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))

#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
#define pgd_offset_k(address) pgd_offset(&init_mm, address)

#ifndef CONFIG_64BIT

#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
#define pud_deref(pmd) ({ BUG(); 0UL; })
#define pgd_deref(pmd) ({ BUG(); 0UL; })

#define pud_offset(pgd, address) ((pud_t *) pgd)
#define pmd_offset(pud, address) ((pmd_t *) pud + pmd_index(address))

#else /* CONFIG_64BIT */

#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
#define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)

static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
{
	pud_t *pud = (pud_t *) pgd;
	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
		pud = (pud_t *) pgd_deref(*pgd);
	return pud  + pud_index(address);
}

static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
	pmd_t *pmd = (pmd_t *) pud;
	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
		pmd = (pmd_t *) pud_deref(*pud);
	return pmd + pmd_index(address);
}

#endif /* CONFIG_64BIT */

#define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot))
#define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
#define pte_page(x) pfn_to_page(pte_pfn(x))

#define pmd_page(pmd) pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)

/* Find an entry in the lowest level page table.. */
#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
#define pte_offset_kernel(pmd, address) pte_offset(pmd,address)
#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
#define pte_unmap(pte) do { } while (0)

static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
{
	unsigned long sto = (unsigned long) pmdp -
			    pmd_index(address) * sizeof(pmd_t);

	if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) {
		asm volatile(
			"	.insn	rrf,0xb98e0000,%2,%3,0,0"
			: "=m" (*pmdp)
			: "m" (*pmdp), "a" (sto),
			  "a" ((address & HPAGE_MASK))
			: "cc"
		);
	}
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE

#define SEGMENT_NONE	__pgprot(_HPAGE_TYPE_NONE)
#define SEGMENT_RO	__pgprot(_HPAGE_TYPE_RO)
#define SEGMENT_RW	__pgprot(_HPAGE_TYPE_RW)

#define __HAVE_ARCH_PGTABLE_DEPOSIT
extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);

#define __HAVE_ARCH_PGTABLE_WITHDRAW
extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);

static inline int pmd_trans_splitting(pmd_t pmd)
{
	return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT;
}

static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
			      pmd_t *pmdp, pmd_t entry)
{
	if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1)
		pmd_val(entry) |= _SEGMENT_ENTRY_CO;
	*pmdp = entry;
}

static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
{
	/*
	 * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx)
	 * Convert to segment table entry format.
	 */
	if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
		return pgprot_val(SEGMENT_NONE);
	if (pgprot_val(pgprot) == pgprot_val(PAGE_RO))
		return pgprot_val(SEGMENT_RO);
	return pgprot_val(SEGMENT_RW);
}

static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
	pmd_val(pmd) &= _SEGMENT_CHG_MASK;
	pmd_val(pmd) |= massage_pgprot_pmd(newprot);
	return pmd;
}

static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
	pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
	return pmd;
}

static inline pmd_t pmd_mkwrite(pmd_t pmd)
{
	/* Do not clobber _HPAGE_TYPE_NONE pages! */
	if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV))
		pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO;
	return pmd;
}

static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
	pmd_val(pmd) |= _SEGMENT_ENTRY_RO;
	return pmd;
}

static inline pmd_t pmd_mkdirty(pmd_t pmd)
{
	/* No dirty bit in the segment table entry. */
	return pmd;
}

static inline pmd_t pmd_mkold(pmd_t pmd)
{
	/* No referenced bit in the segment table entry. */
	return pmd;
}

static inline pmd_t pmd_mkyoung(pmd_t pmd)
{
	/* No referenced bit in the segment table entry. */
	return pmd;
}

#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
					    unsigned long address, pmd_t *pmdp)
{
	unsigned long pmd_addr = pmd_val(*pmdp) & HPAGE_MASK;
	long tmp, rc;
	int counter;

	rc = 0;
	if (MACHINE_HAS_RRBM) {
		counter = PTRS_PER_PTE >> 6;
		asm volatile(
			"0:	.insn	rre,0xb9ae0000,%0,%3\n"	/* rrbm */
			"	ogr	%1,%0\n"
			"	la	%3,0(%4,%3)\n"
			"	brct	%2,0b\n"
			: "=&d" (tmp), "+&d" (rc), "+d" (counter),
			  "+a" (pmd_addr)
			: "a" (64 * 4096UL) : "cc");
		rc = !!rc;
	} else {
		counter = PTRS_PER_PTE;
		asm volatile(
			"0:	rrbe	0,%2\n"
			"	la	%2,0(%3,%2)\n"
			"	brc	12,1f\n"
			"	lhi	%0,1\n"
			"1:	brct	%1,0b\n"
			: "+d" (rc), "+d" (counter), "+a" (pmd_addr)
			: "a" (4096UL) : "cc");
	}
	return rc;
}

#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
				       unsigned long address, pmd_t *pmdp)
{
	pmd_t pmd = *pmdp;

	__pmd_idte(address, pmdp);
	pmd_clear(pmdp);
	return pmd;
}

#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
				     unsigned long address, pmd_t *pmdp)
{
	return pmdp_get_and_clear(vma->vm_mm, address, pmdp);
}

#define __HAVE_ARCH_PMDP_INVALIDATE
static inline void pmdp_invalidate(struct vm_area_struct *vma,
				   unsigned long address, pmd_t *pmdp)
{
	__pmd_idte(address, pmdp);
}

#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
				      unsigned long address, pmd_t *pmdp)
{
	pmd_t pmd = *pmdp;

	if (pmd_write(pmd)) {
		__pmd_idte(address, pmdp);
		set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd));
	}
}

static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot)
{
	pmd_t __pmd;
	pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot);
	return __pmd;
}

#define pfn_pmd(pfn, pgprot)	mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot))
#define mk_pmd(page, pgprot)	pfn_pmd(page_to_pfn(page), (pgprot))

static inline int pmd_trans_huge(pmd_t pmd)
{
	return pmd_val(pmd) & _SEGMENT_ENTRY_LARGE;
}

static inline int has_transparent_hugepage(void)
{
	return MACHINE_HAS_HPAGE ? 1 : 0;
}

static inline unsigned long pmd_pfn(pmd_t pmd)
{
	return pmd_val(pmd) >> PAGE_SHIFT;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/*
 * 31 bit swap entry format:
 * A page-table entry has some bits we have to treat in a special way.
 * Bits 0, 20 and bit 23 have to be zero, otherwise an specification
 * exception will occur instead of a page translation exception. The
 * specifiation exception has the bad habit not to store necessary
 * information in the lowcore.
 * Bit 21 and bit 22 are the page invalid bit and the page protection
 * bit. We set both to indicate a swapped page.
 * Bit 30 and 31 are used to distinguish the different page types. For
 * a swapped page these bits need to be zero.
 * This leaves the bits 1-19 and bits 24-29 to store type and offset.
 * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19
 * plus 24 for the offset.
 * 0|     offset        |0110|o|type |00|
 * 0 0000000001111111111 2222 2 22222 33
 * 0 1234567890123456789 0123 4 56789 01
 *
 * 64 bit swap entry format:
 * A page-table entry has some bits we have to treat in a special way.
 * Bits 52 and bit 55 have to be zero, otherwise an specification
 * exception will occur instead of a page translation exception. The
 * specifiation exception has the bad habit not to store necessary
 * information in the lowcore.
 * Bit 53 and bit 54 are the page invalid bit and the page protection
 * bit. We set both to indicate a swapped page.
 * Bit 62 and 63 are used to distinguish the different page types. For
 * a swapped page these bits need to be zero.
 * This leaves the bits 0-51 and bits 56-61 to store type and offset.
 * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51
 * plus 56 for the offset.
 * |                      offset                        |0110|o|type |00|
 *  0000000000111111111122222222223333333333444444444455 5555 5 55566 66
 *  0123456789012345678901234567890123456789012345678901 2345 6 78901 23
 */
#ifndef CONFIG_64BIT
#define __SWP_OFFSET_MASK (~0UL >> 12)
#else
#define __SWP_OFFSET_MASK (~0UL >> 11)
#endif
static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
{
	pte_t pte;
	offset &= __SWP_OFFSET_MASK;
	pte_val(pte) = _PAGE_TYPE_SWAP | ((type & 0x1f) << 2) |
		((offset & 1UL) << 7) | ((offset & ~1UL) << 11);
	return pte;
}

#define __swp_type(entry)	(((entry).val >> 2) & 0x1f)
#define __swp_offset(entry)	(((entry).val >> 11) | (((entry).val >> 7) & 1))
#define __swp_entry(type,offset) ((swp_entry_t) { pte_val(mk_swap_pte((type),(offset))) })

#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x)	((pte_t) { (x).val })

#ifndef CONFIG_64BIT
# define PTE_FILE_MAX_BITS	26
#else /* CONFIG_64BIT */
# define PTE_FILE_MAX_BITS	59
#endif /* CONFIG_64BIT */

#define pte_to_pgoff(__pte) \
	((((__pte).pte >> 12) << 7) + (((__pte).pte >> 1) & 0x7f))

#define pgoff_to_pte(__off) \
	((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \
		   | _PAGE_TYPE_FILE })

#endif /* !__ASSEMBLY__ */

#define kern_addr_valid(addr)   (1)

extern int vmem_add_mapping(unsigned long start, unsigned long size);
extern int vmem_remove_mapping(unsigned long start, unsigned long size);
extern int s390_enable_sie(void);

/*
 * No page table caches to initialise
 */
#define pgtable_cache_init()	do { } while (0)

#include <asm-generic/pgtable.h>

#endif /* _S390_PAGE_H */