summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/hash_utils_64.c
blob: ef3ae891a3db49a36cbe32e36fa8f3b243c93db9 (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
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
/*
 * PowerPC64 port by Mike Corrigan and Dave Engebretsen
 *   {mikejc|engebret}@us.ibm.com
 *
 *    Copyright (c) 2000 Mike Corrigan <mikejc@us.ibm.com>
 *
 * SMP scalability work:
 *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
 * 
 *    Module name: htab.c
 *
 *    Description:
 *      PowerPC Hashed Page Table functions
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#undef DEBUG
#undef DEBUG_LOW

#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/export.h>
#include <linux/ctype.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/signal.h>
#include <linux/memblock.h>
#include <linux/context_tracking.h>
#include <linux/libfdt.h>

#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
#include <asm/types.h>
#include <asm/uaccess.h>
#include <asm/machdep.h>
#include <asm/prom.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
#include <asm/eeh.h>
#include <asm/tlb.h>
#include <asm/cacheflush.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/copro.h>
#include <asm/udbg.h>
#include <asm/code-patching.h>
#include <asm/fadump.h>
#include <asm/firmware.h>
#include <asm/tm.h>
#include <asm/trace.h>
#include <asm/ps3.h>

#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif

#ifdef DEBUG_LOW
#define DBG_LOW(fmt...) udbg_printf(fmt)
#else
#define DBG_LOW(fmt...)
#endif

#define KB (1024)
#define MB (1024*KB)
#define GB (1024L*MB)

/*
 * Note:  pte   --> Linux PTE
 *        HPTE  --> PowerPC Hashed Page Table Entry
 *
 * Execution context:
 *   htab_initialize is called with the MMU off (of course), but
 *   the kernel has been copied down to zero so it can directly
 *   reference global data.  At this point it is very difficult
 *   to print debug info.
 *
 */

static unsigned long _SDR1;
struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
EXPORT_SYMBOL_GPL(mmu_psize_defs);

u8 hpte_page_sizes[1 << LP_BITS];
EXPORT_SYMBOL_GPL(hpte_page_sizes);

struct hash_pte *htab_address;
unsigned long htab_size_bytes;
unsigned long htab_hash_mask;
EXPORT_SYMBOL_GPL(htab_hash_mask);
int mmu_linear_psize = MMU_PAGE_4K;
EXPORT_SYMBOL_GPL(mmu_linear_psize);
int mmu_virtual_psize = MMU_PAGE_4K;
int mmu_vmalloc_psize = MMU_PAGE_4K;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
int mmu_vmemmap_psize = MMU_PAGE_4K;
#endif
int mmu_io_psize = MMU_PAGE_4K;
int mmu_kernel_ssize = MMU_SEGSIZE_256M;
EXPORT_SYMBOL_GPL(mmu_kernel_ssize);
int mmu_highuser_ssize = MMU_SEGSIZE_256M;
u16 mmu_slb_size = 64;
EXPORT_SYMBOL_GPL(mmu_slb_size);
#ifdef CONFIG_PPC_64K_PAGES
int mmu_ci_restrictions;
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
static u8 *linear_map_hash_slots;
static unsigned long linear_map_hash_count;
static DEFINE_SPINLOCK(linear_map_hash_lock);
#endif /* CONFIG_DEBUG_PAGEALLOC */
struct mmu_hash_ops mmu_hash_ops;
EXPORT_SYMBOL(mmu_hash_ops);

/* There are definitions of page sizes arrays to be used when none
 * is provided by the firmware.
 */

/* Pre-POWER4 CPUs (4k pages only)
 */
static struct mmu_psize_def mmu_psize_defaults_old[] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.sllp	= 0,
		.penc   = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
		.avpnm	= 0,
		.tlbiel = 0,
	},
};

/* POWER4, GPUL, POWER5
 *
 * Support for 16Mb large pages
 */
static struct mmu_psize_def mmu_psize_defaults_gp[] = {
	[MMU_PAGE_4K] = {
		.shift	= 12,
		.sllp	= 0,
		.penc   = {[MMU_PAGE_4K] = 0, [1 ... MMU_PAGE_COUNT - 1] = -1},
		.avpnm	= 0,
		.tlbiel = 1,
	},
	[MMU_PAGE_16M] = {
		.shift	= 24,
		.sllp	= SLB_VSID_L,
		.penc   = {[0 ... MMU_PAGE_16M - 1] = -1, [MMU_PAGE_16M] = 0,
			    [MMU_PAGE_16M + 1 ... MMU_PAGE_COUNT - 1] = -1 },
		.avpnm	= 0x1UL,
		.tlbiel = 0,
	},
};

/*
 * 'R' and 'C' update notes:
 *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
 *     create writeable HPTEs without C set, because the hcall H_PROTECT
 *     that we use in that case will not update C
 *  - The above is however not a problem, because we also don't do that
 *     fancy "no flush" variant of eviction and we use H_REMOVE which will
 *     do the right thing and thus we don't have the race I described earlier
 *
 *    - Under bare metal,  we do have the race, so we need R and C set
 *    - We make sure R is always set and never lost
 *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
 */
unsigned long htab_convert_pte_flags(unsigned long pteflags)
{
	unsigned long rflags = 0;

	/* _PAGE_EXEC -> NOEXEC */
	if ((pteflags & _PAGE_EXEC) == 0)
		rflags |= HPTE_R_N;
	/*
	 * PPP bits:
	 * Linux uses slb key 0 for kernel and 1 for user.
	 * kernel RW areas are mapped with PPP=0b000
	 * User area is mapped with PPP=0b010 for read/write
	 * or PPP=0b011 for read-only (including writeable but clean pages).
	 */
	if (pteflags & _PAGE_PRIVILEGED) {
		/*
		 * Kernel read only mapped with ppp bits 0b110
		 */
		if (!(pteflags & _PAGE_WRITE))
			rflags |= (HPTE_R_PP0 | 0x2);
	} else {
		if (pteflags & _PAGE_RWX)
			rflags |= 0x2;
		if (!((pteflags & _PAGE_WRITE) && (pteflags & _PAGE_DIRTY)))
			rflags |= 0x1;
	}
	/*
	 * We can't allow hardware to update hpte bits. Hence always
	 * set 'R' bit and set 'C' if it is a write fault
	 */
	rflags |=  HPTE_R_R;

	if (pteflags & _PAGE_DIRTY)
		rflags |= HPTE_R_C;
	/*
	 * Add in WIG bits
	 */

	if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT)
		rflags |= HPTE_R_I;
	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
		rflags |= (HPTE_R_I | HPTE_R_G);
	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
	else
		/*
		 * Add memory coherence if cache inhibited is not set
		 */
		rflags |= HPTE_R_M;

	return rflags;
}

int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
		      unsigned long pstart, unsigned long prot,
		      int psize, int ssize)
{
	unsigned long vaddr, paddr;
	unsigned int step, shift;
	int ret = 0;

	shift = mmu_psize_defs[psize].shift;
	step = 1 << shift;

	prot = htab_convert_pte_flags(prot);

	DBG("htab_bolt_mapping(%lx..%lx -> %lx (%lx,%d,%d)\n",
	    vstart, vend, pstart, prot, psize, ssize);

	for (vaddr = vstart, paddr = pstart; vaddr < vend;
	     vaddr += step, paddr += step) {
		unsigned long hash, hpteg;
		unsigned long vsid = get_kernel_vsid(vaddr, ssize);
		unsigned long vpn  = hpt_vpn(vaddr, vsid, ssize);
		unsigned long tprot = prot;

		/*
		 * If we hit a bad address return error.
		 */
		if (!vsid)
			return -1;
		/* Make kernel text executable */
		if (overlaps_kernel_text(vaddr, vaddr + step))
			tprot &= ~HPTE_R_N;

		/* Make kvm guest trampolines executable */
		if (overlaps_kvm_tmp(vaddr, vaddr + step))
			tprot &= ~HPTE_R_N;

		/*
		 * If relocatable, check if it overlaps interrupt vectors that
		 * are copied down to real 0. For relocatable kernel
		 * (e.g. kdump case) we copy interrupt vectors down to real
		 * address 0. Mark that region as executable. This is
		 * because on p8 system with relocation on exception feature
		 * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
		 * in order to execute the interrupt handlers in virtual
		 * mode the vector region need to be marked as executable.
		 */
		if ((PHYSICAL_START > MEMORY_START) &&
			overlaps_interrupt_vector_text(vaddr, vaddr + step))
				tprot &= ~HPTE_R_N;

		hash = hpt_hash(vpn, shift, ssize);
		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);

		BUG_ON(!mmu_hash_ops.hpte_insert);
		ret = mmu_hash_ops.hpte_insert(hpteg, vpn, paddr, tprot,
					       HPTE_V_BOLTED, psize, psize,
					       ssize);

		if (ret < 0)
			break;

#ifdef CONFIG_DEBUG_PAGEALLOC
		if (debug_pagealloc_enabled() &&
			(paddr >> PAGE_SHIFT) < linear_map_hash_count)
			linear_map_hash_slots[paddr >> PAGE_SHIFT] = ret | 0x80;
#endif /* CONFIG_DEBUG_PAGEALLOC */
	}
	return ret < 0 ? ret : 0;
}

int htab_remove_mapping(unsigned long vstart, unsigned long vend,
		      int psize, int ssize)
{
	unsigned long vaddr;
	unsigned int step, shift;
	int rc;
	int ret = 0;

	shift = mmu_psize_defs[psize].shift;
	step = 1 << shift;

	if (!mmu_hash_ops.hpte_removebolted)
		return -ENODEV;

	for (vaddr = vstart; vaddr < vend; vaddr += step) {
		rc = mmu_hash_ops.hpte_removebolted(vaddr, psize, ssize);
		if (rc == -ENOENT) {
			ret = -ENOENT;
			continue;
		}
		if (rc < 0)
			return rc;
	}

	return ret;
}

static bool disable_1tb_segments = false;

static int __init parse_disable_1tb_segments(char *p)
{
	disable_1tb_segments = true;
	return 0;
}
early_param("disable_1tb_segments", parse_disable_1tb_segments);

static int __init htab_dt_scan_seg_sizes(unsigned long node,
					 const char *uname, int depth,
					 void *data)
{
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	const __be32 *prop;
	int size = 0;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	prop = of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", &size);
	if (prop == NULL)
		return 0;
	for (; size >= 4; size -= 4, ++prop) {
		if (be32_to_cpu(prop[0]) == 40) {
			DBG("1T segment support detected\n");

			if (disable_1tb_segments) {
				DBG("1T segments disabled by command line\n");
				break;
			}

			cur_cpu_spec->mmu_features |= MMU_FTR_1T_SEGMENT;
			return 1;
		}
	}
	cur_cpu_spec->mmu_features &= ~MMU_FTR_NO_SLBIE_B;
	return 0;
}

static int __init get_idx_from_shift(unsigned int shift)
{
	int idx = -1;

	switch (shift) {
	case 0xc:
		idx = MMU_PAGE_4K;
		break;
	case 0x10:
		idx = MMU_PAGE_64K;
		break;
	case 0x14:
		idx = MMU_PAGE_1M;
		break;
	case 0x18:
		idx = MMU_PAGE_16M;
		break;
	case 0x22:
		idx = MMU_PAGE_16G;
		break;
	}
	return idx;
}

static int __init htab_dt_scan_page_sizes(unsigned long node,
					  const char *uname, int depth,
					  void *data)
{
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	const __be32 *prop;
	int size = 0;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	prop = of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size);
	if (!prop)
		return 0;

	pr_info("Page sizes from device-tree:\n");
	size /= 4;
	cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
	while(size > 0) {
		unsigned int base_shift = be32_to_cpu(prop[0]);
		unsigned int slbenc = be32_to_cpu(prop[1]);
		unsigned int lpnum = be32_to_cpu(prop[2]);
		struct mmu_psize_def *def;
		int idx, base_idx;

		size -= 3; prop += 3;
		base_idx = get_idx_from_shift(base_shift);
		if (base_idx < 0) {
			/* skip the pte encoding also */
			prop += lpnum * 2; size -= lpnum * 2;
			continue;
		}
		def = &mmu_psize_defs[base_idx];
		if (base_idx == MMU_PAGE_16M)
			cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;

		def->shift = base_shift;
		if (base_shift <= 23)
			def->avpnm = 0;
		else
			def->avpnm = (1 << (base_shift - 23)) - 1;
		def->sllp = slbenc;
		/*
		 * We don't know for sure what's up with tlbiel, so
		 * for now we only set it for 4K and 64K pages
		 */
		if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
			def->tlbiel = 1;
		else
			def->tlbiel = 0;

		while (size > 0 && lpnum) {
			unsigned int shift = be32_to_cpu(prop[0]);
			int penc  = be32_to_cpu(prop[1]);

			prop += 2; size -= 2;
			lpnum--;

			idx = get_idx_from_shift(shift);
			if (idx < 0)
				continue;

			if (penc == -1)
				pr_err("Invalid penc for base_shift=%d "
				       "shift=%d\n", base_shift, shift);

			def->penc[idx] = penc;
			pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
				" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
				base_shift, shift, def->sllp,
				def->avpnm, def->tlbiel, def->penc[idx]);
		}
	}

	return 1;
}

#ifdef CONFIG_HUGETLB_PAGE
/* Scan for 16G memory blocks that have been set aside for huge pages
 * and reserve those blocks for 16G huge pages.
 */
static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
					const char *uname, int depth,
					void *data) {
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	const __be64 *addr_prop;
	const __be32 *page_count_prop;
	unsigned int expected_pages;
	long unsigned int phys_addr;
	long unsigned int block_size;

	/* We are scanning "memory" nodes only */
	if (type == NULL || strcmp(type, "memory") != 0)
		return 0;

	/* This property is the log base 2 of the number of virtual pages that
	 * will represent this memory block. */
	page_count_prop = of_get_flat_dt_prop(node, "ibm,expected#pages", NULL);
	if (page_count_prop == NULL)
		return 0;
	expected_pages = (1 << be32_to_cpu(page_count_prop[0]));
	addr_prop = of_get_flat_dt_prop(node, "reg", NULL);
	if (addr_prop == NULL)
		return 0;
	phys_addr = be64_to_cpu(addr_prop[0]);
	block_size = be64_to_cpu(addr_prop[1]);
	if (block_size != (16 * GB))
		return 0;
	printk(KERN_INFO "Huge page(16GB) memory: "
			"addr = 0x%lX size = 0x%lX pages = %d\n",
			phys_addr, block_size, expected_pages);
	if (phys_addr + (16 * GB) <= memblock_end_of_DRAM()) {
		memblock_reserve(phys_addr, block_size * expected_pages);
		add_gpage(phys_addr, block_size, expected_pages);
	}
	return 0;
}
#endif /* CONFIG_HUGETLB_PAGE */

static void mmu_psize_set_default_penc(void)
{
	int bpsize, apsize;
	for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++)
		for (apsize = 0; apsize < MMU_PAGE_COUNT; apsize++)
			mmu_psize_defs[bpsize].penc[apsize] = -1;
}

#ifdef CONFIG_PPC_64K_PAGES

static bool might_have_hea(void)
{
	/*
	 * The HEA ethernet adapter requires awareness of the
	 * GX bus. Without that awareness we can easily assume
	 * we will never see an HEA ethernet device.
	 */
#ifdef CONFIG_IBMEBUS
	return !cpu_has_feature(CPU_FTR_ARCH_207S) &&
		!firmware_has_feature(FW_FEATURE_SPLPAR);
#else
	return false;
#endif
}

#endif /* #ifdef CONFIG_PPC_64K_PAGES */

static void __init htab_scan_page_sizes(void)
{
	int rc;

	/* se the invalid penc to -1 */
	mmu_psize_set_default_penc();

	/* Default to 4K pages only */
	memcpy(mmu_psize_defs, mmu_psize_defaults_old,
	       sizeof(mmu_psize_defaults_old));

	/*
	 * Try to find the available page sizes in the device-tree
	 */
	rc = of_scan_flat_dt(htab_dt_scan_page_sizes, NULL);
	if (rc == 0 && early_mmu_has_feature(MMU_FTR_16M_PAGE)) {
		/*
		 * Nothing in the device-tree, but the CPU supports 16M pages,
		 * so let's fallback on a known size list for 16M capable CPUs.
		 */
		memcpy(mmu_psize_defs, mmu_psize_defaults_gp,
		       sizeof(mmu_psize_defaults_gp));
	}

#ifdef CONFIG_HUGETLB_PAGE
	/* Reserve 16G huge page memory sections for huge pages */
	of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
#endif /* CONFIG_HUGETLB_PAGE */
}

/*
 * Fill in the hpte_page_sizes[] array.
 * We go through the mmu_psize_defs[] array looking for all the
 * supported base/actual page size combinations.  Each combination
 * has a unique pagesize encoding (penc) value in the low bits of
 * the LP field of the HPTE.  For actual page sizes less than 1MB,
 * some of the upper LP bits are used for RPN bits, meaning that
 * we need to fill in several entries in hpte_page_sizes[].
 *
 * In diagrammatic form, with r = RPN bits and z = page size bits:
 *        PTE LP     actual page size
 *    rrrr rrrz		>=8KB
 *    rrrr rrzz		>=16KB
 *    rrrr rzzz		>=32KB
 *    rrrr zzzz		>=64KB
 *    ...
 *
 * The zzzz bits are implementation-specific but are chosen so that
 * no encoding for a larger page size uses the same value in its
 * low-order N bits as the encoding for the 2^(12+N) byte page size
 * (if it exists).
 */
static void init_hpte_page_sizes(void)
{
	long int ap, bp;
	long int shift, penc;

	for (bp = 0; bp < MMU_PAGE_COUNT; ++bp) {
		if (!mmu_psize_defs[bp].shift)
			continue;	/* not a supported page size */
		for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) {
			penc = mmu_psize_defs[bp].penc[ap];
			if (penc == -1)
				continue;
			shift = mmu_psize_defs[ap].shift - LP_SHIFT;
			if (shift <= 0)
				continue;	/* should never happen */
			/*
			 * For page sizes less than 1MB, this loop
			 * replicates the entry for all possible values
			 * of the rrrr bits.
			 */
			while (penc < (1 << LP_BITS)) {
				hpte_page_sizes[penc] = (ap << 4) | bp;
				penc += 1 << shift;
			}
		}
	}
}

static void __init htab_init_page_sizes(void)
{
	init_hpte_page_sizes();

	if (!debug_pagealloc_enabled()) {
		/*
		 * Pick a size for the linear mapping. Currently, we only
		 * support 16M, 1M and 4K which is the default
		 */
		if (mmu_psize_defs[MMU_PAGE_16M].shift)
			mmu_linear_psize = MMU_PAGE_16M;
		else if (mmu_psize_defs[MMU_PAGE_1M].shift)
			mmu_linear_psize = MMU_PAGE_1M;
	}

#ifdef CONFIG_PPC_64K_PAGES
	/*
	 * Pick a size for the ordinary pages. Default is 4K, we support
	 * 64K for user mappings and vmalloc if supported by the processor.
	 * We only use 64k for ioremap if the processor
	 * (and firmware) support cache-inhibited large pages.
	 * If not, we use 4k and set mmu_ci_restrictions so that
	 * hash_page knows to switch processes that use cache-inhibited
	 * mappings to 4k pages.
	 */
	if (mmu_psize_defs[MMU_PAGE_64K].shift) {
		mmu_virtual_psize = MMU_PAGE_64K;
		mmu_vmalloc_psize = MMU_PAGE_64K;
		if (mmu_linear_psize == MMU_PAGE_4K)
			mmu_linear_psize = MMU_PAGE_64K;
		if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
			/*
			 * When running on pSeries using 64k pages for ioremap
			 * would stop us accessing the HEA ethernet. So if we
			 * have the chance of ever seeing one, stay at 4k.
			 */
			if (!might_have_hea())
				mmu_io_psize = MMU_PAGE_64K;
		} else
			mmu_ci_restrictions = 1;
	}
#endif /* CONFIG_PPC_64K_PAGES */

#ifdef CONFIG_SPARSEMEM_VMEMMAP
	/* We try to use 16M pages for vmemmap if that is supported
	 * and we have at least 1G of RAM at boot
	 */
	if (mmu_psize_defs[MMU_PAGE_16M].shift &&
	    memblock_phys_mem_size() >= 0x40000000)
		mmu_vmemmap_psize = MMU_PAGE_16M;
	else if (mmu_psize_defs[MMU_PAGE_64K].shift)
		mmu_vmemmap_psize = MMU_PAGE_64K;
	else
		mmu_vmemmap_psize = MMU_PAGE_4K;
#endif /* CONFIG_SPARSEMEM_VMEMMAP */

	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
	       "virtual = %d, io = %d"
#ifdef CONFIG_SPARSEMEM_VMEMMAP
	       ", vmemmap = %d"
#endif
	       "\n",
	       mmu_psize_defs[mmu_linear_psize].shift,
	       mmu_psize_defs[mmu_virtual_psize].shift,
	       mmu_psize_defs[mmu_io_psize].shift
#ifdef CONFIG_SPARSEMEM_VMEMMAP
	       ,mmu_psize_defs[mmu_vmemmap_psize].shift
#endif
	       );
}

static int __init htab_dt_scan_pftsize(unsigned long node,
				       const char *uname, int depth,
				       void *data)
{
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	const __be32 *prop;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	prop = of_get_flat_dt_prop(node, "ibm,pft-size", NULL);
	if (prop != NULL) {
		/* pft_size[0] is the NUMA CEC cookie */
		ppc64_pft_size = be32_to_cpu(prop[1]);
		return 1;
	}
	return 0;
}

unsigned htab_shift_for_mem_size(unsigned long mem_size)
{
	unsigned memshift = __ilog2(mem_size);
	unsigned pshift = mmu_psize_defs[mmu_virtual_psize].shift;
	unsigned pteg_shift;

	/* round mem_size up to next power of 2 */
	if ((1UL << memshift) < mem_size)
		memshift += 1;

	/* aim for 2 pages / pteg */
	pteg_shift = memshift - (pshift + 1);

	/*
	 * 2^11 PTEGS of 128 bytes each, ie. 2^18 bytes is the minimum htab
	 * size permitted by the architecture.
	 */
	return max(pteg_shift + 7, 18U);
}

static unsigned long __init htab_get_table_size(void)
{
	/* If hash size isn't already provided by the platform, we try to
	 * retrieve it from the device-tree. If it's not there neither, we
	 * calculate it now based on the total RAM size
	 */
	if (ppc64_pft_size == 0)
		of_scan_flat_dt(htab_dt_scan_pftsize, NULL);
	if (ppc64_pft_size)
		return 1UL << ppc64_pft_size;

	return 1UL << htab_shift_for_mem_size(memblock_phys_mem_size());
}

#ifdef CONFIG_MEMORY_HOTPLUG
int create_section_mapping(unsigned long start, unsigned long end)
{
	int rc = htab_bolt_mapping(start, end, __pa(start),
				   pgprot_val(PAGE_KERNEL), mmu_linear_psize,
				   mmu_kernel_ssize);

	if (rc < 0) {
		int rc2 = htab_remove_mapping(start, end, mmu_linear_psize,
					      mmu_kernel_ssize);
		BUG_ON(rc2 && (rc2 != -ENOENT));
	}
	return rc;
}

int remove_section_mapping(unsigned long start, unsigned long end)
{
	int rc = htab_remove_mapping(start, end, mmu_linear_psize,
				     mmu_kernel_ssize);
	WARN_ON(rc < 0);
	return rc;
}
#endif /* CONFIG_MEMORY_HOTPLUG */

static void __init hash_init_partition_table(phys_addr_t hash_table,
					     unsigned long htab_size)
{
	unsigned long ps_field;
	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;

	/*
	 * slb llp encoding for the page size used in VPM real mode.
	 * We can ignore that for lpid 0
	 */
	ps_field = 0;
	htab_size =  __ilog2(htab_size) - 18;

	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
						MEMBLOCK_ALLOC_ANYWHERE));

	/* Initialize the Partition Table with no entries */
	memset((void *)partition_tb, 0, patb_size);
	partition_tb->patb0 = cpu_to_be64(ps_field | hash_table | htab_size);
	/*
	 * FIXME!! This should be done via update_partition table
	 * For now UPRT is 0 for us.
	 */
	partition_tb->patb1 = 0;
	pr_info("Partition table %p\n", partition_tb);
	/*
	 * update partition table control register,
	 * 64 K size.
	 */
	mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));

}

static void __init htab_initialize(void)
{
	unsigned long table;
	unsigned long pteg_count;
	unsigned long prot;
	unsigned long base = 0, size = 0;
	struct memblock_region *reg;

	DBG(" -> htab_initialize()\n");

	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
		mmu_kernel_ssize = MMU_SEGSIZE_1T;
		mmu_highuser_ssize = MMU_SEGSIZE_1T;
		printk(KERN_INFO "Using 1TB segments\n");
	}

	/*
	 * Calculate the required size of the htab.  We want the number of
	 * PTEGs to equal one half the number of real pages.
	 */ 
	htab_size_bytes = htab_get_table_size();
	pteg_count = htab_size_bytes >> 7;

	htab_hash_mask = pteg_count - 1;

	if (firmware_has_feature(FW_FEATURE_LPAR) ||
	    firmware_has_feature(FW_FEATURE_PS3_LV1)) {
		/* Using a hypervisor which owns the htab */
		htab_address = NULL;
		_SDR1 = 0; 
#ifdef CONFIG_FA_DUMP
		/*
		 * If firmware assisted dump is active firmware preserves
		 * the contents of htab along with entire partition memory.
		 * Clear the htab if firmware assisted dump is active so
		 * that we dont end up using old mappings.
		 */
		if (is_fadump_active() && mmu_hash_ops.hpte_clear_all)
			mmu_hash_ops.hpte_clear_all();
#endif
	} else {
		unsigned long limit = MEMBLOCK_ALLOC_ANYWHERE;

#ifdef CONFIG_PPC_CELL
		/*
		 * Cell may require the hash table down low when using the
		 * Axon IOMMU in order to fit the dynamic region over it, see
		 * comments in cell/iommu.c
		 */
		if (fdt_subnode_offset(initial_boot_params, 0, "axon") > 0) {
			limit = 0x80000000;
			pr_info("Hash table forced below 2G for Axon IOMMU\n");
		}
#endif /* CONFIG_PPC_CELL */

		table = memblock_alloc_base(htab_size_bytes, htab_size_bytes,
					    limit);

		DBG("Hash table allocated at %lx, size: %lx\n", table,
		    htab_size_bytes);

		htab_address = __va(table);

		/* htab absolute addr + encoded htabsize */
		_SDR1 = table + __ilog2(htab_size_bytes) - 18;

		/* Initialize the HPT with no entries */
		memset((void *)table, 0, htab_size_bytes);

		if (!cpu_has_feature(CPU_FTR_ARCH_300))
			/* Set SDR1 */
			mtspr(SPRN_SDR1, _SDR1);
		else
			hash_init_partition_table(table, htab_size_bytes);
	}

	prot = pgprot_val(PAGE_KERNEL);

#ifdef CONFIG_DEBUG_PAGEALLOC
	if (debug_pagealloc_enabled()) {
		linear_map_hash_count = memblock_end_of_DRAM() >> PAGE_SHIFT;
		linear_map_hash_slots = __va(memblock_alloc_base(
				linear_map_hash_count, 1, ppc64_rma_size));
		memset(linear_map_hash_slots, 0, linear_map_hash_count);
	}
#endif /* CONFIG_DEBUG_PAGEALLOC */

	/* On U3 based machines, we need to reserve the DART area and
	 * _NOT_ map it to avoid cache paradoxes as it's remapped non
	 * cacheable later on
	 */

	/* create bolted the linear mapping in the hash table */
	for_each_memblock(memory, reg) {
		base = (unsigned long)__va(reg->base);
		size = reg->size;

		DBG("creating mapping for region: %lx..%lx (prot: %lx)\n",
		    base, size, prot);

		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
				prot, mmu_linear_psize, mmu_kernel_ssize));
	}
	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);

	/*
	 * If we have a memory_limit and we've allocated TCEs then we need to
	 * explicitly map the TCE area at the top of RAM. We also cope with the
	 * case that the TCEs start below memory_limit.
	 * tce_alloc_start/end are 16MB aligned so the mapping should work
	 * for either 4K or 16MB pages.
	 */
	if (tce_alloc_start) {
		tce_alloc_start = (unsigned long)__va(tce_alloc_start);
		tce_alloc_end = (unsigned long)__va(tce_alloc_end);

		if (base + size >= tce_alloc_start)
			tce_alloc_start = base + size + 1;

		BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end,
					 __pa(tce_alloc_start), prot,
					 mmu_linear_psize, mmu_kernel_ssize));
	}


	DBG(" <- htab_initialize()\n");
}
#undef KB
#undef MB

void __init hash__early_init_devtree(void)
{
	/* Initialize segment sizes */
	of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL);

	/* Initialize page sizes */
	htab_scan_page_sizes();
}

void __init hash__early_init_mmu(void)
{
	htab_init_page_sizes();

	/*
	 * initialize page table size
	 */
	__pte_frag_nr = H_PTE_FRAG_NR;
	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;

	__pte_index_size = H_PTE_INDEX_SIZE;
	__pmd_index_size = H_PMD_INDEX_SIZE;
	__pud_index_size = H_PUD_INDEX_SIZE;
	__pgd_index_size = H_PGD_INDEX_SIZE;
	__pmd_cache_index = H_PMD_CACHE_INDEX;
	__pte_table_size = H_PTE_TABLE_SIZE;
	__pmd_table_size = H_PMD_TABLE_SIZE;
	__pud_table_size = H_PUD_TABLE_SIZE;
	__pgd_table_size = H_PGD_TABLE_SIZE;
	/*
	 * 4k use hugepd format, so for hash set then to
	 * zero
	 */
	__pmd_val_bits = 0;
	__pud_val_bits = 0;
	__pgd_val_bits = 0;

	__kernel_virt_start = H_KERN_VIRT_START;
	__kernel_virt_size = H_KERN_VIRT_SIZE;
	__vmalloc_start = H_VMALLOC_START;
	__vmalloc_end = H_VMALLOC_END;
	vmemmap = (struct page *)H_VMEMMAP_BASE;
	ioremap_bot = IOREMAP_BASE;

#ifdef CONFIG_PCI
	pci_io_base = ISA_IO_BASE;
#endif

	/* Select appropriate backend */
	if (firmware_has_feature(FW_FEATURE_PS3_LV1))
		ps3_early_mm_init();
	else if (firmware_has_feature(FW_FEATURE_LPAR))
		hpte_init_pseries();
	else if (IS_ENABLED(CONFIG_PPC_NATIVE))
		hpte_init_native();

	if (!mmu_hash_ops.hpte_insert)
		panic("hash__early_init_mmu: No MMU hash ops defined!\n");

	/* Initialize the MMU Hash table and create the linear mapping
	 * of memory. Has to be done before SLB initialization as this is
	 * currently where the page size encoding is obtained.
	 */
	htab_initialize();

	pr_info("Initializing hash mmu with SLB\n");
	/* Initialize SLB management */
	slb_initialize();
}

#ifdef CONFIG_SMP
void hash__early_init_mmu_secondary(void)
{
	/* Initialize hash table for that CPU */
	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
		if (!cpu_has_feature(CPU_FTR_ARCH_300))
			mtspr(SPRN_SDR1, _SDR1);
		else
			mtspr(SPRN_PTCR,
			      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
	}
	/* Initialize SLB */
	slb_initialize();
}
#endif /* CONFIG_SMP */

/*
 * Called by asm hashtable.S for doing lazy icache flush
 */
unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
{
	struct page *page;

	if (!pfn_valid(pte_pfn(pte)))
		return pp;

	page = pte_page(pte);

	/* page is dirty */
	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
		if (trap == 0x400) {
			flush_dcache_icache_page(page);
			set_bit(PG_arch_1, &page->flags);
		} else
			pp |= HPTE_R_N;
	}
	return pp;
}

#ifdef CONFIG_PPC_MM_SLICES
static unsigned int get_paca_psize(unsigned long addr)
{
	u64 lpsizes;
	unsigned char *hpsizes;
	unsigned long index, mask_index;

	if (addr < SLICE_LOW_TOP) {
		lpsizes = get_paca()->mm_ctx_low_slices_psize;
		index = GET_LOW_SLICE_INDEX(addr);
		return (lpsizes >> (index * 4)) & 0xF;
	}
	hpsizes = get_paca()->mm_ctx_high_slices_psize;
	index = GET_HIGH_SLICE_INDEX(addr);
	mask_index = index & 0x1;
	return (hpsizes[index >> 1] >> (mask_index * 4)) & 0xF;
}

#else
unsigned int get_paca_psize(unsigned long addr)
{
	return get_paca()->mm_ctx_user_psize;
}
#endif

/*
 * Demote a segment to using 4k pages.
 * For now this makes the whole process use 4k pages.
 */
#ifdef CONFIG_PPC_64K_PAGES
void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
{
	if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
		return;
	slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
	copro_flush_all_slbs(mm);
	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {

		copy_mm_to_paca(&mm->context);
		slb_flush_and_rebolt();
	}
}
#endif /* CONFIG_PPC_64K_PAGES */

#ifdef CONFIG_PPC_SUBPAGE_PROT
/*
 * This looks up a 2-bit protection code for a 4k subpage of a 64k page.
 * Userspace sets the subpage permissions using the subpage_prot system call.
 *
 * Result is 0: full permissions, _PAGE_RW: read-only,
 * _PAGE_RWX: no access.
 */
static int subpage_protection(struct mm_struct *mm, unsigned long ea)
{
	struct subpage_prot_table *spt = &mm->context.spt;
	u32 spp = 0;
	u32 **sbpm, *sbpp;

	if (ea >= spt->maxaddr)
		return 0;
	if (ea < 0x100000000UL) {
		/* addresses below 4GB use spt->low_prot */
		sbpm = spt->low_prot;
	} else {
		sbpm = spt->protptrs[ea >> SBP_L3_SHIFT];
		if (!sbpm)
			return 0;
	}
	sbpp = sbpm[(ea >> SBP_L2_SHIFT) & (SBP_L2_COUNT - 1)];
	if (!sbpp)
		return 0;
	spp = sbpp[(ea >> PAGE_SHIFT) & (SBP_L1_COUNT - 1)];

	/* extract 2-bit bitfield for this 4k subpage */
	spp >>= 30 - 2 * ((ea >> 12) & 0xf);

	/*
	 * 0 -> full premission
	 * 1 -> Read only
	 * 2 -> no access.
	 * We return the flag that need to be cleared.
	 */
	spp = ((spp & 2) ? _PAGE_RWX : 0) | ((spp & 1) ? _PAGE_WRITE : 0);
	return spp;
}

#else /* CONFIG_PPC_SUBPAGE_PROT */
static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
{
	return 0;
}
#endif

void hash_failure_debug(unsigned long ea, unsigned long access,
			unsigned long vsid, unsigned long trap,
			int ssize, int psize, int lpsize, unsigned long pte)
{
	if (!printk_ratelimit())
		return;
	pr_info("mm: Hashing failure ! EA=0x%lx access=0x%lx current=%s\n",
		ea, access, current->comm);
	pr_info("    trap=0x%lx vsid=0x%lx ssize=%d base psize=%d psize %d pte=0x%lx\n",
		trap, vsid, ssize, psize, lpsize, pte);
}

static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
			     int psize, bool user_region)
{
	if (user_region) {
		if (psize != get_paca_psize(ea)) {
			copy_mm_to_paca(&mm->context);
			slb_flush_and_rebolt();
		}
	} else if (get_paca()->vmalloc_sllp !=
		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
		get_paca()->vmalloc_sllp =
			mmu_psize_defs[mmu_vmalloc_psize].sllp;
		slb_vmalloc_update();
	}
}

/* Result code is:
 *  0 - handled
 *  1 - normal page fault
 * -1 - critical hash insertion error
 * -2 - access not permitted by subpage protection mechanism
 */
int hash_page_mm(struct mm_struct *mm, unsigned long ea,
		 unsigned long access, unsigned long trap,
		 unsigned long flags)
{
	bool is_thp;
	enum ctx_state prev_state = exception_enter();
	pgd_t *pgdir;
	unsigned long vsid;
	pte_t *ptep;
	unsigned hugeshift;
	const struct cpumask *tmp;
	int rc, user_region = 0;
	int psize, ssize;

	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
		ea, access, trap);
	trace_hash_fault(ea, access, trap);

	/* Get region & vsid */
 	switch (REGION_ID(ea)) {
	case USER_REGION_ID:
		user_region = 1;
		if (! mm) {
			DBG_LOW(" user region with no mm !\n");
			rc = 1;
			goto bail;
		}
		psize = get_slice_psize(mm, ea);
		ssize = user_segment_size(ea);
		vsid = get_vsid(mm->context.id, ea, ssize);
		break;
	case VMALLOC_REGION_ID:
		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
		if (ea < VMALLOC_END)
			psize = mmu_vmalloc_psize;
		else
			psize = mmu_io_psize;
		ssize = mmu_kernel_ssize;
		break;
	default:
		/* Not a valid range
		 * Send the problem up to do_page_fault 
		 */
		rc = 1;
		goto bail;
	}
	DBG_LOW(" mm=%p, mm->pgdir=%p, vsid=%016lx\n", mm, mm->pgd, vsid);

	/* Bad address. */
	if (!vsid) {
		DBG_LOW("Bad address!\n");
		rc = 1;
		goto bail;
	}
	/* Get pgdir */
	pgdir = mm->pgd;
	if (pgdir == NULL) {
		rc = 1;
		goto bail;
	}

	/* Check CPU locality */
	tmp = cpumask_of(smp_processor_id());
	if (user_region && cpumask_equal(mm_cpumask(mm), tmp))
		flags |= HPTE_LOCAL_UPDATE;

#ifndef CONFIG_PPC_64K_PAGES
	/* If we use 4K pages and our psize is not 4K, then we might
	 * be hitting a special driver mapping, and need to align the
	 * address before we fetch the PTE.
	 *
	 * It could also be a hugepage mapping, in which case this is
	 * not necessary, but it's not harmful, either.
	 */
	if (psize != MMU_PAGE_4K)
		ea &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
#endif /* CONFIG_PPC_64K_PAGES */

	/* Get PTE and page size from page tables */
	ptep = __find_linux_pte_or_hugepte(pgdir, ea, &is_thp, &hugeshift);
	if (ptep == NULL || !pte_present(*ptep)) {
		DBG_LOW(" no PTE !\n");
		rc = 1;
		goto bail;
	}

	/* Add _PAGE_PRESENT to the required access perm */
	access |= _PAGE_PRESENT;

	/* Pre-check access permissions (will be re-checked atomically
	 * in __hash_page_XX but this pre-check is a fast path
	 */
	if (!check_pte_access(access, pte_val(*ptep))) {
		DBG_LOW(" no access !\n");
		rc = 1;
		goto bail;
	}

	if (hugeshift) {
		if (is_thp)
			rc = __hash_page_thp(ea, access, vsid, (pmd_t *)ptep,
					     trap, flags, ssize, psize);
#ifdef CONFIG_HUGETLB_PAGE
		else
			rc = __hash_page_huge(ea, access, vsid, ptep, trap,
					      flags, ssize, hugeshift, psize);
#else
		else {
			/*
			 * if we have hugeshift, and is not transhuge with
			 * hugetlb disabled, something is really wrong.
			 */
			rc = 1;
			WARN_ON(1);
		}
#endif
		if (current->mm == mm)
			check_paca_psize(ea, mm, psize, user_region);

		goto bail;
	}

#ifndef CONFIG_PPC_64K_PAGES
	DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
#else
	DBG_LOW(" i-pte: %016lx %016lx\n", pte_val(*ptep),
		pte_val(*(ptep + PTRS_PER_PTE)));
#endif
	/* Do actual hashing */
#ifdef CONFIG_PPC_64K_PAGES
	/* If H_PAGE_4K_PFN is set, make sure this is a 4k segment */
	if ((pte_val(*ptep) & H_PAGE_4K_PFN) && psize == MMU_PAGE_64K) {
		demote_segment_4k(mm, ea);
		psize = MMU_PAGE_4K;
	}

	/* If this PTE is non-cacheable and we have restrictions on
	 * using non cacheable large pages, then we switch to 4k
	 */
	if (mmu_ci_restrictions && psize == MMU_PAGE_64K && pte_ci(*ptep)) {
		if (user_region) {
			demote_segment_4k(mm, ea);
			psize = MMU_PAGE_4K;
		} else if (ea < VMALLOC_END) {
			/*
			 * some driver did a non-cacheable mapping
			 * in vmalloc space, so switch vmalloc
			 * to 4k pages
			 */
			printk(KERN_ALERT "Reducing vmalloc segment "
			       "to 4kB pages because of "
			       "non-cacheable mapping\n");
			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
			copro_flush_all_slbs(mm);
		}
	}

#endif /* CONFIG_PPC_64K_PAGES */

	if (current->mm == mm)
		check_paca_psize(ea, mm, psize, user_region);

#ifdef CONFIG_PPC_64K_PAGES
	if (psize == MMU_PAGE_64K)
		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
				     flags, ssize);
	else
#endif /* CONFIG_PPC_64K_PAGES */
	{
		int spp = subpage_protection(mm, ea);
		if (access & spp)
			rc = -2;
		else
			rc = __hash_page_4K(ea, access, vsid, ptep, trap,
					    flags, ssize, spp);
	}

	/* Dump some info in case of hash insertion failure, they should
	 * never happen so it is really useful to know if/when they do
	 */
	if (rc == -1)
		hash_failure_debug(ea, access, vsid, trap, ssize, psize,
				   psize, pte_val(*ptep));
#ifndef CONFIG_PPC_64K_PAGES
	DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep));
#else
	DBG_LOW(" o-pte: %016lx %016lx\n", pte_val(*ptep),
		pte_val(*(ptep + PTRS_PER_PTE)));
#endif
	DBG_LOW(" -> rc=%d\n", rc);

bail:
	exception_exit(prev_state);
	return rc;
}
EXPORT_SYMBOL_GPL(hash_page_mm);

int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
	      unsigned long dsisr)
{
	unsigned long flags = 0;
	struct mm_struct *mm = current->mm;

	if (REGION_ID(ea) == VMALLOC_REGION_ID)
		mm = &init_mm;

	if (dsisr & DSISR_NOHPTE)
		flags |= HPTE_NOHPTE_UPDATE;

	return hash_page_mm(mm, ea, access, trap, flags);
}
EXPORT_SYMBOL_GPL(hash_page);

int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
		unsigned long dsisr)
{
	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
	unsigned long flags = 0;
	struct mm_struct *mm = current->mm;

	if (REGION_ID(ea) == VMALLOC_REGION_ID)
		mm = &init_mm;

	if (dsisr & DSISR_NOHPTE)
		flags |= HPTE_NOHPTE_UPDATE;

	if (dsisr & DSISR_ISSTORE)
		access |= _PAGE_WRITE;
	/*
	 * We set _PAGE_PRIVILEGED only when
	 * kernel mode access kernel space.
	 *
	 * _PAGE_PRIVILEGED is NOT set
	 * 1) when kernel mode access user space
	 * 2) user space access kernel space.
	 */
	access |= _PAGE_PRIVILEGED;
	if ((msr & MSR_PR) || (REGION_ID(ea) == USER_REGION_ID))
		access &= ~_PAGE_PRIVILEGED;

	if (trap == 0x400)
		access |= _PAGE_EXEC;

	return hash_page_mm(mm, ea, access, trap, flags);
}

#ifdef CONFIG_PPC_MM_SLICES
static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
{
	int psize = get_slice_psize(mm, ea);

	/* We only prefault standard pages for now */
	if (unlikely(psize != mm->context.user_psize))
		return false;

	/*
	 * Don't prefault if subpage protection is enabled for the EA.
	 */
	if (unlikely((psize == MMU_PAGE_4K) && subpage_protection(mm, ea)))
		return false;

	return true;
}
#else
static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
{
	return true;
}
#endif

void hash_preload(struct mm_struct *mm, unsigned long ea,
		  unsigned long access, unsigned long trap)
{
	int hugepage_shift;
	unsigned long vsid;
	pgd_t *pgdir;
	pte_t *ptep;
	unsigned long flags;
	int rc, ssize, update_flags = 0;

	BUG_ON(REGION_ID(ea) != USER_REGION_ID);

	if (!should_hash_preload(mm, ea))
		return;

	DBG_LOW("hash_preload(mm=%p, mm->pgdir=%p, ea=%016lx, access=%lx,"
		" trap=%lx\n", mm, mm->pgd, ea, access, trap);

	/* Get Linux PTE if available */
	pgdir = mm->pgd;
	if (pgdir == NULL)
		return;

	/* Get VSID */
	ssize = user_segment_size(ea);
	vsid = get_vsid(mm->context.id, ea, ssize);
	if (!vsid)
		return;
	/*
	 * Hash doesn't like irqs. Walking linux page table with irq disabled
	 * saves us from holding multiple locks.
	 */
	local_irq_save(flags);

	/*
	 * THP pages use update_mmu_cache_pmd. We don't do
	 * hash preload there. Hence can ignore THP here
	 */
	ptep = find_linux_pte_or_hugepte(pgdir, ea, NULL, &hugepage_shift);
	if (!ptep)
		goto out_exit;

	WARN_ON(hugepage_shift);
#ifdef CONFIG_PPC_64K_PAGES
	/* If either H_PAGE_4K_PFN or cache inhibited is set (and we are on
	 * a 64K kernel), then we don't preload, hash_page() will take
	 * care of it once we actually try to access the page.
	 * That way we don't have to duplicate all of the logic for segment
	 * page size demotion here
	 */
	if ((pte_val(*ptep) & H_PAGE_4K_PFN) || pte_ci(*ptep))
		goto out_exit;
#endif /* CONFIG_PPC_64K_PAGES */

	/* Is that local to this CPU ? */
	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
		update_flags |= HPTE_LOCAL_UPDATE;

	/* Hash it in */
#ifdef CONFIG_PPC_64K_PAGES
	if (mm->context.user_psize == MMU_PAGE_64K)
		rc = __hash_page_64K(ea, access, vsid, ptep, trap,
				     update_flags, ssize);
	else
#endif /* CONFIG_PPC_64K_PAGES */
		rc = __hash_page_4K(ea, access, vsid, ptep, trap, update_flags,
				    ssize, subpage_protection(mm, ea));

	/* Dump some info in case of hash insertion failure, they should
	 * never happen so it is really useful to know if/when they do
	 */
	if (rc == -1)
		hash_failure_debug(ea, access, vsid, trap, ssize,
				   mm->context.user_psize,
				   mm->context.user_psize,
				   pte_val(*ptep));
out_exit:
	local_irq_restore(flags);
}

/* WARNING: This is called from hash_low_64.S, if you change this prototype,
 *          do not forget to update the assembly call site !
 */
void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
		     unsigned long flags)
{
	unsigned long hash, index, shift, hidx, slot;
	int local = flags & HPTE_LOCAL_UPDATE;

	DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
	pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
		hash = hpt_hash(vpn, shift, ssize);
		hidx = __rpte_to_hidx(pte, index);
		if (hidx & _PTEIDX_SECONDARY)
			hash = ~hash;
		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
		slot += hidx & _PTEIDX_GROUP_IX;
		DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
		/*
		 * We use same base page size and actual psize, because we don't
		 * use these functions for hugepage
		 */
		mmu_hash_ops.hpte_invalidate(slot, vpn, psize, psize,
					     ssize, local);
	} pte_iterate_hashed_end();

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	/* Transactions are not aborted by tlbiel, only tlbie.
	 * Without, syncing a page back to a block device w/ PIO could pick up
	 * transactional data (bad!) so we force an abort here.  Before the
	 * sync the page will be made read-only, which will flush_hash_page.
	 * BIG ISSUE here: if the kernel uses a page from userspace without
	 * unmapping it first, it may see the speculated version.
	 */
	if (local && cpu_has_feature(CPU_FTR_TM) &&
	    current->thread.regs &&
	    MSR_TM_ACTIVE(current->thread.regs->msr)) {
		tm_enable();
		tm_abort(TM_CAUSE_TLBI);
	}
#endif
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
			 pmd_t *pmdp, unsigned int psize, int ssize,
			 unsigned long flags)
{
	int i, max_hpte_count, valid;
	unsigned long s_addr;
	unsigned char *hpte_slot_array;
	unsigned long hidx, shift, vpn, hash, slot;
	int local = flags & HPTE_LOCAL_UPDATE;

	s_addr = addr & HPAGE_PMD_MASK;
	hpte_slot_array = get_hpte_slot_array(pmdp);
	/*
	 * IF we try to do a HUGE PTE update after a withdraw is done.
	 * we will find the below NULL. This happens when we do
	 * split_huge_page_pmd
	 */
	if (!hpte_slot_array)
		return;

	if (mmu_hash_ops.hugepage_invalidate) {
		mmu_hash_ops.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
						 psize, ssize, local);
		goto tm_abort;
	}
	/*
	 * No bluk hpte removal support, invalidate each entry
	 */
	shift = mmu_psize_defs[psize].shift;
	max_hpte_count = HPAGE_PMD_SIZE >> shift;
	for (i = 0; i < max_hpte_count; i++) {
		/*
		 * 8 bits per each hpte entries
		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
		 */
		valid = hpte_valid(hpte_slot_array, i);
		if (!valid)
			continue;
		hidx =  hpte_hash_index(hpte_slot_array, i);

		/* get the vpn */
		addr = s_addr + (i * (1ul << shift));
		vpn = hpt_vpn(addr, vsid, ssize);
		hash = hpt_hash(vpn, shift, ssize);
		if (hidx & _PTEIDX_SECONDARY)
			hash = ~hash;

		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
		slot += hidx & _PTEIDX_GROUP_IX;
		mmu_hash_ops.hpte_invalidate(slot, vpn, psize,
					     MMU_PAGE_16M, ssize, local);
	}
tm_abort:
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	/* Transactions are not aborted by tlbiel, only tlbie.
	 * Without, syncing a page back to a block device w/ PIO could pick up
	 * transactional data (bad!) so we force an abort here.  Before the
	 * sync the page will be made read-only, which will flush_hash_page.
	 * BIG ISSUE here: if the kernel uses a page from userspace without
	 * unmapping it first, it may see the speculated version.
	 */
	if (local && cpu_has_feature(CPU_FTR_TM) &&
	    current->thread.regs &&
	    MSR_TM_ACTIVE(current->thread.regs->msr)) {
		tm_enable();
		tm_abort(TM_CAUSE_TLBI);
	}
#endif
	return;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

void flush_hash_range(unsigned long number, int local)
{
	if (mmu_hash_ops.flush_hash_range)
		mmu_hash_ops.flush_hash_range(number, local);
	else {
		int i;
		struct ppc64_tlb_batch *batch =
			this_cpu_ptr(&ppc64_tlb_batch);

		for (i = 0; i < number; i++)
			flush_hash_page(batch->vpn[i], batch->pte[i],
					batch->psize, batch->ssize, local);
	}
}

/*
 * low_hash_fault is called when we the low level hash code failed
 * to instert a PTE due to an hypervisor error
 */
void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc)
{
	enum ctx_state prev_state = exception_enter();

	if (user_mode(regs)) {
#ifdef CONFIG_PPC_SUBPAGE_PROT
		if (rc == -2)
			_exception(SIGSEGV, regs, SEGV_ACCERR, address);
		else
#endif
			_exception(SIGBUS, regs, BUS_ADRERR, address);
	} else
		bad_page_fault(regs, address, SIGBUS);

	exception_exit(prev_state);
}

long hpte_insert_repeating(unsigned long hash, unsigned long vpn,
			   unsigned long pa, unsigned long rflags,
			   unsigned long vflags, int psize, int ssize)
{
	unsigned long hpte_group;
	long slot;

repeat:
	hpte_group = ((hash & htab_hash_mask) *
		       HPTES_PER_GROUP) & ~0x7UL;

	/* Insert into the hash table, primary slot */
	slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags, vflags,
					psize, psize, ssize);

	/* Primary is full, try the secondary */
	if (unlikely(slot == -1)) {
		hpte_group = ((~hash & htab_hash_mask) *
			      HPTES_PER_GROUP) & ~0x7UL;
		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa, rflags,
						vflags | HPTE_V_SECONDARY,
						psize, psize, ssize);
		if (slot == -1) {
			if (mftb() & 0x1)
				hpte_group = ((hash & htab_hash_mask) *
					      HPTES_PER_GROUP)&~0x7UL;

			mmu_hash_ops.hpte_remove(hpte_group);
			goto repeat;
		}
	}

	return slot;
}

#ifdef CONFIG_DEBUG_PAGEALLOC
static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
{
	unsigned long hash;
	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
	unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL));
	long ret;

	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);

	/* Don't create HPTE entries for bad address */
	if (!vsid)
		return;

	ret = hpte_insert_repeating(hash, vpn, __pa(vaddr), mode,
				    HPTE_V_BOLTED,
				    mmu_linear_psize, mmu_kernel_ssize);

	BUG_ON (ret < 0);
	spin_lock(&linear_map_hash_lock);
	BUG_ON(linear_map_hash_slots[lmi] & 0x80);
	linear_map_hash_slots[lmi] = ret | 0x80;
	spin_unlock(&linear_map_hash_lock);
}

static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
{
	unsigned long hash, hidx, slot;
	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);

	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
	spin_lock(&linear_map_hash_lock);
	BUG_ON(!(linear_map_hash_slots[lmi] & 0x80));
	hidx = linear_map_hash_slots[lmi] & 0x7f;
	linear_map_hash_slots[lmi] = 0;
	spin_unlock(&linear_map_hash_lock);
	if (hidx & _PTEIDX_SECONDARY)
		hash = ~hash;
	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
	slot += hidx & _PTEIDX_GROUP_IX;
	mmu_hash_ops.hpte_invalidate(slot, vpn, mmu_linear_psize,
				     mmu_linear_psize,
				     mmu_kernel_ssize, 0);
}

void __kernel_map_pages(struct page *page, int numpages, int enable)
{
	unsigned long flags, vaddr, lmi;
	int i;

	local_irq_save(flags);
	for (i = 0; i < numpages; i++, page++) {
		vaddr = (unsigned long)page_address(page);
		lmi = __pa(vaddr) >> PAGE_SHIFT;
		if (lmi >= linear_map_hash_count)
			continue;
		if (enable)
			kernel_map_linear_page(vaddr, lmi);
		else
			kernel_unmap_linear_page(vaddr, lmi);
	}
	local_irq_restore(flags);
}
#endif /* CONFIG_DEBUG_PAGEALLOC */

void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
				phys_addr_t first_memblock_size)
{
	/* We don't currently support the first MEMBLOCK not mapping 0
	 * physical on those processors
	 */
	BUG_ON(first_memblock_base != 0);

	/* On LPAR systems, the first entry is our RMA region,
	 * non-LPAR 64-bit hash MMU systems don't have a limitation
	 * on real mode access, but using the first entry works well
	 * enough. We also clamp it to 1G to avoid some funky things
	 * such as RTAS bugs etc...
	 */
	ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);

	/* Finally limit subsequent allocations */
	memblock_set_current_limit(ppc64_rma_size);
}