summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/traps.c
blob: f23430adb68ad7fecb70a31e1443e8a02d75f824 (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
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  Copyright (C) 1995-1996  Gary Thomas (gdt@linuxppc.org)
 *  Copyright 2007-2010 Freescale Semiconductor, Inc.
 *
 *  Modified by Cort Dougan (cort@cs.nmt.edu)
 *  and Paul Mackerras (paulus@samba.org)
 */

/*
 * This file handles the architecture-dependent parts of hardware exceptions
 */

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/pkeys.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/extable.h>
#include <linux/module.h>	/* print_modules */
#include <linux/prctl.h>
#include <linux/delay.h>
#include <linux/kprobes.h>
#include <linux/kexec.h>
#include <linux/backlight.h>
#include <linux/bug.h>
#include <linux/kdebug.h>
#include <linux/ratelimit.h>
#include <linux/context_tracking.h>
#include <linux/smp.h>
#include <linux/console.h>
#include <linux/kmsg_dump.h>
#include <linux/debugfs.h>

#include <asm/emulated_ops.h>
#include <linux/uaccess.h>
#include <asm/interrupt.h>
#include <asm/io.h>
#include <asm/machdep.h>
#include <asm/rtas.h>
#include <asm/pmc.h>
#include <asm/reg.h>
#ifdef CONFIG_PMAC_BACKLIGHT
#include <asm/backlight.h>
#endif
#ifdef CONFIG_PPC64
#include <asm/firmware.h>
#include <asm/processor.h>
#endif
#include <asm/kexec.h>
#include <asm/ppc-opcode.h>
#include <asm/rio.h>
#include <asm/fadump.h>
#include <asm/switch_to.h>
#include <asm/tm.h>
#include <asm/debug.h>
#include <asm/asm-prototypes.h>
#include <asm/hmi.h>
#include <sysdev/fsl_pci.h>
#include <asm/kprobes.h>
#include <asm/stacktrace.h>
#include <asm/nmi.h>
#include <asm/disassemble.h>
#include <asm/udbg.h>

#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
int (*__debugger_ipi)(struct pt_regs *regs) __read_mostly;
int (*__debugger_bpt)(struct pt_regs *regs) __read_mostly;
int (*__debugger_sstep)(struct pt_regs *regs) __read_mostly;
int (*__debugger_iabr_match)(struct pt_regs *regs) __read_mostly;
int (*__debugger_break_match)(struct pt_regs *regs) __read_mostly;
int (*__debugger_fault_handler)(struct pt_regs *regs) __read_mostly;

EXPORT_SYMBOL(__debugger);
EXPORT_SYMBOL(__debugger_ipi);
EXPORT_SYMBOL(__debugger_bpt);
EXPORT_SYMBOL(__debugger_sstep);
EXPORT_SYMBOL(__debugger_iabr_match);
EXPORT_SYMBOL(__debugger_break_match);
EXPORT_SYMBOL(__debugger_fault_handler);
#endif

/* Transactional Memory trap debug */
#ifdef TM_DEBUG_SW
#define TM_DEBUG(x...) printk(KERN_INFO x)
#else
#define TM_DEBUG(x...) do { } while(0)
#endif

static const char *signame(int signr)
{
	switch (signr) {
	case SIGBUS:	return "bus error";
	case SIGFPE:	return "floating point exception";
	case SIGILL:	return "illegal instruction";
	case SIGSEGV:	return "segfault";
	case SIGTRAP:	return "unhandled trap";
	}

	return "unknown signal";
}

/*
 * Trap & Exception support
 */

#ifdef CONFIG_PMAC_BACKLIGHT
static void pmac_backlight_unblank(void)
{
	mutex_lock(&pmac_backlight_mutex);
	if (pmac_backlight) {
		struct backlight_properties *props;

		props = &pmac_backlight->props;
		props->brightness = props->max_brightness;
		props->power = FB_BLANK_UNBLANK;
		backlight_update_status(pmac_backlight);
	}
	mutex_unlock(&pmac_backlight_mutex);
}
#else
static inline void pmac_backlight_unblank(void) { }
#endif

/*
 * If oops/die is expected to crash the machine, return true here.
 *
 * This should not be expected to be 100% accurate, there may be
 * notifiers registered or other unexpected conditions that may bring
 * down the kernel. Or if the current process in the kernel is holding
 * locks or has other critical state, the kernel may become effectively
 * unusable anyway.
 */
bool die_will_crash(void)
{
	if (should_fadump_crash())
		return true;
	if (kexec_should_crash(current))
		return true;
	if (in_interrupt() || panic_on_oops ||
			!current->pid || is_global_init(current))
		return true;

	return false;
}

static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
static int die_owner = -1;
static unsigned int die_nest_count;
static int die_counter;

void panic_flush_kmsg_start(void)
{
	/*
	 * These are mostly taken from kernel/panic.c, but tries to do
	 * relatively minimal work. Don't use delay functions (TB may
	 * be broken), don't crash dump (need to set a firmware log),
	 * don't run notifiers. We do want to get some information to
	 * Linux console.
	 */
	console_verbose();
	bust_spinlocks(1);
}

void panic_flush_kmsg_end(void)
{
	kmsg_dump(KMSG_DUMP_PANIC);
	bust_spinlocks(0);
	debug_locks_off();
	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
}

static unsigned long oops_begin(struct pt_regs *regs)
{
	int cpu;
	unsigned long flags;

	oops_enter();

	/* racy, but better than risking deadlock. */
	raw_local_irq_save(flags);
	cpu = smp_processor_id();
	if (!arch_spin_trylock(&die_lock)) {
		if (cpu == die_owner)
			/* nested oops. should stop eventually */;
		else
			arch_spin_lock(&die_lock);
	}
	die_nest_count++;
	die_owner = cpu;
	console_verbose();
	bust_spinlocks(1);
	if (machine_is(powermac))
		pmac_backlight_unblank();
	return flags;
}
NOKPROBE_SYMBOL(oops_begin);

static void oops_end(unsigned long flags, struct pt_regs *regs,
			       int signr)
{
	bust_spinlocks(0);
	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
	die_nest_count--;
	oops_exit();
	printk("\n");
	if (!die_nest_count) {
		/* Nest count reaches zero, release the lock. */
		die_owner = -1;
		arch_spin_unlock(&die_lock);
	}
	raw_local_irq_restore(flags);

	/*
	 * system_reset_excption handles debugger, crash dump, panic, for 0x100
	 */
	if (TRAP(regs) == INTERRUPT_SYSTEM_RESET)
		return;

	crash_fadump(regs, "die oops");

	if (kexec_should_crash(current))
		crash_kexec(regs);

	if (!signr)
		return;

	/*
	 * While our oops output is serialised by a spinlock, output
	 * from panic() called below can race and corrupt it. If we
	 * know we are going to panic, delay for 1 second so we have a
	 * chance to get clean backtraces from all CPUs that are oopsing.
	 */
	if (in_interrupt() || panic_on_oops || !current->pid ||
	    is_global_init(current)) {
		mdelay(MSEC_PER_SEC);
	}

	if (panic_on_oops)
		panic("Fatal exception");
	make_task_dead(signr);
}
NOKPROBE_SYMBOL(oops_end);

static char *get_mmu_str(void)
{
	if (early_radix_enabled())
		return " MMU=Radix";
	if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
		return " MMU=Hash";
	return "";
}

static int __die(const char *str, struct pt_regs *regs, long err)
{
	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);

	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
	       PAGE_SIZE / 1024, get_mmu_str(),
	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
	       IS_ENABLED(CONFIG_NUMA) ? " NUMA" : "",
	       ppc_md.name ? ppc_md.name : "");

	if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP)
		return 1;

	print_modules();
	show_regs(regs);

	return 0;
}
NOKPROBE_SYMBOL(__die);

void die(const char *str, struct pt_regs *regs, long err)
{
	unsigned long flags;

	/*
	 * system_reset_excption handles debugger, crash dump, panic, for 0x100
	 */
	if (TRAP(regs) != INTERRUPT_SYSTEM_RESET) {
		if (debugger(regs))
			return;
	}

	flags = oops_begin(regs);
	if (__die(str, regs, err))
		err = 0;
	oops_end(flags, regs, err);
}
NOKPROBE_SYMBOL(die);

void user_single_step_report(struct pt_regs *regs)
{
	force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip);
}

static void show_signal_msg(int signr, struct pt_regs *regs, int code,
			    unsigned long addr)
{
	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
				      DEFAULT_RATELIMIT_BURST);

	if (!show_unhandled_signals)
		return;

	if (!unhandled_signal(current, signr))
		return;

	if (!__ratelimit(&rs))
		return;

	pr_info("%s[%d]: %s (%d) at %lx nip %lx lr %lx code %x",
		current->comm, current->pid, signame(signr), signr,
		addr, regs->nip, regs->link, code);

	print_vma_addr(KERN_CONT " in ", regs->nip);

	pr_cont("\n");

	show_user_instructions(regs);
}

static bool exception_common(int signr, struct pt_regs *regs, int code,
			      unsigned long addr)
{
	if (!user_mode(regs)) {
		die("Exception in kernel mode", regs, signr);
		return false;
	}

	/*
	 * Must not enable interrupts even for user-mode exception, because
	 * this can be called from machine check, which may be a NMI or IRQ
	 * which don't like interrupts being enabled. Could check for
	 * in_hardirq || in_nmi perhaps, but there doesn't seem to be a good
	 * reason why _exception() should enable irqs for an exception handler,
	 * the handlers themselves do that directly.
	 */

	show_signal_msg(signr, regs, code, addr);

	current->thread.trap_nr = code;

	return true;
}

void _exception_pkey(struct pt_regs *regs, unsigned long addr, int key)
{
	if (!exception_common(SIGSEGV, regs, SEGV_PKUERR, addr))
		return;

	force_sig_pkuerr((void __user *) addr, key);
}

void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
{
	if (!exception_common(signr, regs, code, addr))
		return;

	force_sig_fault(signr, code, (void __user *)addr);
}

/*
 * The interrupt architecture has a quirk in that the HV interrupts excluding
 * the NMIs (0x100 and 0x200) do not clear MSR[RI] at entry. The first thing
 * that an interrupt handler must do is save off a GPR into a scratch register,
 * and all interrupts on POWERNV (HV=1) use the HSPRG1 register as scratch.
 * Therefore an NMI can clobber an HV interrupt's live HSPRG1 without noticing
 * that it is non-reentrant, which leads to random data corruption.
 *
 * The solution is for NMI interrupts in HV mode to check if they originated
 * from these critical HV interrupt regions. If so, then mark them not
 * recoverable.
 *
 * An alternative would be for HV NMIs to use SPRG for scratch to avoid the
 * HSPRG1 clobber, however this would cause guest SPRG to be clobbered. Linux
 * guests should always have MSR[RI]=0 when its scratch SPRG is in use, so
 * that would work. However any other guest OS that may have the SPRG live
 * and MSR[RI]=1 could encounter silent corruption.
 *
 * Builds that do not support KVM could take this second option to increase
 * the recoverability of NMIs.
 */
noinstr void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
{
#ifdef CONFIG_PPC_POWERNV
	unsigned long kbase = (unsigned long)_stext;
	unsigned long nip = regs->nip;

	if (!(regs->msr & MSR_RI))
		return;
	if (!(regs->msr & MSR_HV))
		return;
	if (user_mode(regs))
		return;

	/*
	 * Now test if the interrupt has hit a range that may be using
	 * HSPRG1 without having RI=0 (i.e., an HSRR interrupt). The
	 * problem ranges all run un-relocated. Test real and virt modes
	 * at the same time by dropping the high bit of the nip (virt mode
	 * entry points still have the +0x4000 offset).
	 */
	nip &= ~0xc000000000000000ULL;
	if ((nip >= 0x500 && nip < 0x600) || (nip >= 0x4500 && nip < 0x4600))
		goto nonrecoverable;
	if ((nip >= 0x980 && nip < 0xa00) || (nip >= 0x4980 && nip < 0x4a00))
		goto nonrecoverable;
	if ((nip >= 0xe00 && nip < 0xec0) || (nip >= 0x4e00 && nip < 0x4ec0))
		goto nonrecoverable;
	if ((nip >= 0xf80 && nip < 0xfa0) || (nip >= 0x4f80 && nip < 0x4fa0))
		goto nonrecoverable;

	/* Trampoline code runs un-relocated so subtract kbase. */
	if (nip >= (unsigned long)(start_real_trampolines - kbase) &&
			nip < (unsigned long)(end_real_trampolines - kbase))
		goto nonrecoverable;
	if (nip >= (unsigned long)(start_virt_trampolines - kbase) &&
			nip < (unsigned long)(end_virt_trampolines - kbase))
		goto nonrecoverable;
	return;

nonrecoverable:
	regs->msr &= ~MSR_RI;
	local_paca->hsrr_valid = 0;
	local_paca->srr_valid = 0;
#endif
}
DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
{
	unsigned long hsrr0, hsrr1;
	bool saved_hsrrs = false;

	/*
	 * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
	 * The system reset interrupt itself may clobber HSRRs (e.g., to call
	 * OPAL), so save them here and restore them before returning.
	 *
	 * Machine checks don't need to save HSRRs, as the real mode handler
	 * is careful to avoid them, and the regular handler is not delivered
	 * as an NMI.
	 */
	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		hsrr0 = mfspr(SPRN_HSRR0);
		hsrr1 = mfspr(SPRN_HSRR1);
		saved_hsrrs = true;
	}

	hv_nmi_check_nonrecoverable(regs);

	__this_cpu_inc(irq_stat.sreset_irqs);

	/* See if any machine dependent calls */
	if (ppc_md.system_reset_exception) {
		if (ppc_md.system_reset_exception(regs))
			goto out;
	}

	if (debugger(regs))
		goto out;

	kmsg_dump(KMSG_DUMP_OOPS);
	/*
	 * A system reset is a request to dump, so we always send
	 * it through the crashdump code (if fadump or kdump are
	 * registered).
	 */
	crash_fadump(regs, "System Reset");

	crash_kexec(regs);

	/*
	 * We aren't the primary crash CPU. We need to send it
	 * to a holding pattern to avoid it ending up in the panic
	 * code.
	 */
	crash_kexec_secondary(regs);

	/*
	 * No debugger or crash dump registered, print logs then
	 * panic.
	 */
	die("System Reset", regs, SIGABRT);

	mdelay(2*MSEC_PER_SEC); /* Wait a little while for others to print */
	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
	nmi_panic(regs, "System Reset");

out:
#ifdef CONFIG_PPC_BOOK3S_64
	BUG_ON(get_paca()->in_nmi == 0);
	if (get_paca()->in_nmi > 1)
		die("Unrecoverable nested System Reset", regs, SIGABRT);
#endif
	/* Must die if the interrupt is not recoverable */
	if (regs_is_unrecoverable(regs)) {
		/* For the reason explained in die_mce, nmi_exit before die */
		nmi_exit();
		die("Unrecoverable System Reset", regs, SIGABRT);
	}

	if (saved_hsrrs) {
		mtspr(SPRN_HSRR0, hsrr0);
		mtspr(SPRN_HSRR1, hsrr1);
	}

	/* What should we do here? We could issue a shutdown or hard reset. */

	return 0;
}

/*
 * I/O accesses can cause machine checks on powermacs.
 * Check if the NIP corresponds to the address of a sync
 * instruction for which there is an entry in the exception
 * table.
 *  -- paulus.
 */
static inline int check_io_access(struct pt_regs *regs)
{
#ifdef CONFIG_PPC32
	unsigned long msr = regs->msr;
	const struct exception_table_entry *entry;
	unsigned int *nip = (unsigned int *)regs->nip;

	if (((msr & 0xffff0000) == 0 || (msr & (0x80000 | 0x40000)))
	    && (entry = search_exception_tables(regs->nip)) != NULL) {
		/*
		 * Check that it's a sync instruction, or somewhere
		 * in the twi; isync; nop sequence that inb/inw/inl uses.
		 * As the address is in the exception table
		 * we should be able to read the instr there.
		 * For the debug message, we look at the preceding
		 * load or store.
		 */
		if (*nip == PPC_RAW_NOP())
			nip -= 2;
		else if (*nip == PPC_RAW_ISYNC())
			--nip;
		if (*nip == PPC_RAW_SYNC() || get_op(*nip) == OP_TRAP) {
			unsigned int rb;

			--nip;
			rb = (*nip >> 11) & 0x1f;
			printk(KERN_DEBUG "%s bad port %lx at %p\n",
			       (*nip & 0x100)? "OUT to": "IN from",
			       regs->gpr[rb] - _IO_BASE, nip);
			regs_set_recoverable(regs);
			regs_set_return_ip(regs, extable_fixup(entry));
			return 1;
		}
	}
#endif /* CONFIG_PPC32 */
	return 0;
}

#ifdef CONFIG_PPC_ADV_DEBUG_REGS
/* On 4xx, the reason for the machine check or program exception
   is in the ESR. */
#define get_reason(regs)	((regs)->esr)
#define REASON_FP		ESR_FP
#define REASON_ILLEGAL		(ESR_PIL | ESR_PUO)
#define REASON_PRIVILEGED	ESR_PPR
#define REASON_TRAP		ESR_PTR
#define REASON_PREFIXED		0
#define REASON_BOUNDARY		0

/* single-step stuff */
#define single_stepping(regs)	(current->thread.debug.dbcr0 & DBCR0_IC)
#define clear_single_step(regs)	(current->thread.debug.dbcr0 &= ~DBCR0_IC)
#define clear_br_trace(regs)	do {} while(0)
#else
/* On non-4xx, the reason for the machine check or program
   exception is in the MSR. */
#define get_reason(regs)	((regs)->msr)
#define REASON_TM		SRR1_PROGTM
#define REASON_FP		SRR1_PROGFPE
#define REASON_ILLEGAL		SRR1_PROGILL
#define REASON_PRIVILEGED	SRR1_PROGPRIV
#define REASON_TRAP		SRR1_PROGTRAP
#define REASON_PREFIXED		SRR1_PREFIXED
#define REASON_BOUNDARY		SRR1_BOUNDARY

#define single_stepping(regs)	((regs)->msr & MSR_SE)
#define clear_single_step(regs)	(regs_set_return_msr((regs), (regs)->msr & ~MSR_SE))
#define clear_br_trace(regs)	(regs_set_return_msr((regs), (regs)->msr & ~MSR_BE))
#endif

#define inst_length(reason)	(((reason) & REASON_PREFIXED) ? 8 : 4)

#if defined(CONFIG_PPC_E500)
int machine_check_e500mc(struct pt_regs *regs)
{
	unsigned long mcsr = mfspr(SPRN_MCSR);
	unsigned long pvr = mfspr(SPRN_PVR);
	unsigned long reason = mcsr;
	int recoverable = 1;

	if (reason & MCSR_LD) {
		recoverable = fsl_rio_mcheck_exception(regs);
		if (recoverable == 1)
			goto silent_out;
	}

	printk("Machine check in kernel mode.\n");
	printk("Caused by (from MCSR=%lx): ", reason);

	if (reason & MCSR_MCP)
		pr_cont("Machine Check Signal\n");

	if (reason & MCSR_ICPERR) {
		pr_cont("Instruction Cache Parity Error\n");

		/*
		 * This is recoverable by invalidating the i-cache.
		 */
		mtspr(SPRN_L1CSR1, mfspr(SPRN_L1CSR1) | L1CSR1_ICFI);
		while (mfspr(SPRN_L1CSR1) & L1CSR1_ICFI)
			;

		/*
		 * This will generally be accompanied by an instruction
		 * fetch error report -- only treat MCSR_IF as fatal
		 * if it wasn't due to an L1 parity error.
		 */
		reason &= ~MCSR_IF;
	}

	if (reason & MCSR_DCPERR_MC) {
		pr_cont("Data Cache Parity Error\n");

		/*
		 * In write shadow mode we auto-recover from the error, but it
		 * may still get logged and cause a machine check.  We should
		 * only treat the non-write shadow case as non-recoverable.
		 */
		/* On e6500 core, L1 DCWS (Data cache write shadow mode) bit
		 * is not implemented but L1 data cache always runs in write
		 * shadow mode. Hence on data cache parity errors HW will
		 * automatically invalidate the L1 Data Cache.
		 */
		if (PVR_VER(pvr) != PVR_VER_E6500) {
			if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
				recoverable = 0;
		}
	}

	if (reason & MCSR_L2MMU_MHIT) {
		pr_cont("Hit on multiple TLB entries\n");
		recoverable = 0;
	}

	if (reason & MCSR_NMI)
		pr_cont("Non-maskable interrupt\n");

	if (reason & MCSR_IF) {
		pr_cont("Instruction Fetch Error Report\n");
		recoverable = 0;
	}

	if (reason & MCSR_LD) {
		pr_cont("Load Error Report\n");
		recoverable = 0;
	}

	if (reason & MCSR_ST) {
		pr_cont("Store Error Report\n");
		recoverable = 0;
	}

	if (reason & MCSR_LDG) {
		pr_cont("Guarded Load Error Report\n");
		recoverable = 0;
	}

	if (reason & MCSR_TLBSYNC)
		pr_cont("Simultaneous tlbsync operations\n");

	if (reason & MCSR_BSL2_ERR) {
		pr_cont("Level 2 Cache Error\n");
		recoverable = 0;
	}

	if (reason & MCSR_MAV) {
		u64 addr;

		addr = mfspr(SPRN_MCAR);
		addr |= (u64)mfspr(SPRN_MCARU) << 32;

		pr_cont("Machine Check %s Address: %#llx\n",
		       reason & MCSR_MEA ? "Effective" : "Physical", addr);
	}

silent_out:
	mtspr(SPRN_MCSR, mcsr);
	return mfspr(SPRN_MCSR) == 0 && recoverable;
}

int machine_check_e500(struct pt_regs *regs)
{
	unsigned long reason = mfspr(SPRN_MCSR);

	if (reason & MCSR_BUS_RBERR) {
		if (fsl_rio_mcheck_exception(regs))
			return 1;
		if (fsl_pci_mcheck_exception(regs))
			return 1;
	}

	printk("Machine check in kernel mode.\n");
	printk("Caused by (from MCSR=%lx): ", reason);

	if (reason & MCSR_MCP)
		pr_cont("Machine Check Signal\n");
	if (reason & MCSR_ICPERR)
		pr_cont("Instruction Cache Parity Error\n");
	if (reason & MCSR_DCP_PERR)
		pr_cont("Data Cache Push Parity Error\n");
	if (reason & MCSR_DCPERR)
		pr_cont("Data Cache Parity Error\n");
	if (reason & MCSR_BUS_IAERR)
		pr_cont("Bus - Instruction Address Error\n");
	if (reason & MCSR_BUS_RAERR)
		pr_cont("Bus - Read Address Error\n");
	if (reason & MCSR_BUS_WAERR)
		pr_cont("Bus - Write Address Error\n");
	if (reason & MCSR_BUS_IBERR)
		pr_cont("Bus - Instruction Data Error\n");
	if (reason & MCSR_BUS_RBERR)
		pr_cont("Bus - Read Data Bus Error\n");
	if (reason & MCSR_BUS_WBERR)
		pr_cont("Bus - Write Data Bus Error\n");
	if (reason & MCSR_BUS_IPERR)
		pr_cont("Bus - Instruction Parity Error\n");
	if (reason & MCSR_BUS_RPERR)
		pr_cont("Bus - Read Parity Error\n");

	return 0;
}

int machine_check_generic(struct pt_regs *regs)
{
	return 0;
}
#elif defined(CONFIG_PPC32)
int machine_check_generic(struct pt_regs *regs)
{
	unsigned long reason = regs->msr;

	printk("Machine check in kernel mode.\n");
	printk("Caused by (from SRR1=%lx): ", reason);
	switch (reason & 0x601F0000) {
	case 0x80000:
		pr_cont("Machine check signal\n");
		break;
	case 0x40000:
	case 0x140000:	/* 7450 MSS error and TEA */
		pr_cont("Transfer error ack signal\n");
		break;
	case 0x20000:
		pr_cont("Data parity error signal\n");
		break;
	case 0x10000:
		pr_cont("Address parity error signal\n");
		break;
	case 0x20000000:
		pr_cont("L1 Data Cache error\n");
		break;
	case 0x40000000:
		pr_cont("L1 Instruction Cache error\n");
		break;
	case 0x00100000:
		pr_cont("L2 data cache parity error\n");
		break;
	default:
		pr_cont("Unknown values in msr\n");
	}
	return 0;
}
#endif /* everything else */

void die_mce(const char *str, struct pt_regs *regs, long err)
{
	/*
	 * The machine check wants to kill the interrupted context,
	 * but make_task_dead() checks for in_interrupt() and panics
	 * in that case, so exit the irq/nmi before calling die.
	 */
	if (in_nmi())
		nmi_exit();
	else
		irq_exit();
	die(str, regs, err);
}

/*
 * BOOK3S_64 does not usually call this handler as a non-maskable interrupt
 * (it uses its own early real-mode handler to handle the MCE proper
 * and then raises irq_work to call this handler when interrupts are
 * enabled). The only time when this is not true is if the early handler
 * is unrecoverable, then it does call this directly to try to get a
 * message out.
 */
static void __machine_check_exception(struct pt_regs *regs)
{
	int recover = 0;

	__this_cpu_inc(irq_stat.mce_exceptions);

	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);

	/* See if any machine dependent calls. In theory, we would want
	 * to call the CPU first, and call the ppc_md. one if the CPU
	 * one returns a positive number. However there is existing code
	 * that assumes the board gets a first chance, so let's keep it
	 * that way for now and fix things later. --BenH.
	 */
	if (ppc_md.machine_check_exception)
		recover = ppc_md.machine_check_exception(regs);
	else if (cur_cpu_spec->machine_check)
		recover = cur_cpu_spec->machine_check(regs);

	if (recover > 0)
		goto bail;

	if (debugger_fault_handler(regs))
		goto bail;

	if (check_io_access(regs))
		goto bail;

	die_mce("Machine check", regs, SIGBUS);

bail:
	/* Must die if the interrupt is not recoverable */
	if (regs_is_unrecoverable(regs))
		die_mce("Unrecoverable Machine check", regs, SIGBUS);
}

#ifdef CONFIG_PPC_BOOK3S_64
DEFINE_INTERRUPT_HANDLER_RAW(machine_check_early_boot)
{
	udbg_printf("Machine check (early boot)\n");
	udbg_printf("SRR0=0x%016lx   SRR1=0x%016lx\n", regs->nip, regs->msr);
	udbg_printf(" DAR=0x%016lx  DSISR=0x%08lx\n", regs->dar, regs->dsisr);
	udbg_printf("  LR=0x%016lx     R1=0x%08lx\n", regs->link, regs->gpr[1]);
	udbg_printf("------\n");
	die("Machine check (early boot)", regs, SIGBUS);
	for (;;)
		;
	return 0;
}

DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async)
{
	__machine_check_exception(regs);
}
#endif
DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
{
	__machine_check_exception(regs);

	return 0;
}

DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
{
	die("System Management Interrupt", regs, SIGABRT);
}

#ifdef CONFIG_VSX
static void p9_hmi_special_emu(struct pt_regs *regs)
{
	unsigned int ra, rb, t, i, sel, instr, rc;
	const void __user *addr;
	u8 vbuf[16] __aligned(16), *vdst;
	unsigned long ea, msr, msr_mask;
	bool swap;

	if (__get_user(instr, (unsigned int __user *)regs->nip))
		return;

	/*
	 * lxvb16x	opcode: 0x7c0006d8
	 * lxvd2x	opcode: 0x7c000698
	 * lxvh8x	opcode: 0x7c000658
	 * lxvw4x	opcode: 0x7c000618
	 */
	if ((instr & 0xfc00073e) != 0x7c000618) {
		pr_devel("HMI vec emu: not vector CI %i:%s[%d] nip=%016lx"
			 " instr=%08x\n",
			 smp_processor_id(), current->comm, current->pid,
			 regs->nip, instr);
		return;
	}

	/* Grab vector registers into the task struct */
	msr = regs->msr; /* Grab msr before we flush the bits */
	flush_vsx_to_thread(current);
	enable_kernel_altivec();

	/*
	 * Is userspace running with a different endian (this is rare but
	 * not impossible)
	 */
	swap = (msr & MSR_LE) != (MSR_KERNEL & MSR_LE);

	/* Decode the instruction */
	ra = (instr >> 16) & 0x1f;
	rb = (instr >> 11) & 0x1f;
	t = (instr >> 21) & 0x1f;
	if (instr & 1)
		vdst = (u8 *)&current->thread.vr_state.vr[t];
	else
		vdst = (u8 *)&current->thread.fp_state.fpr[t][0];

	/* Grab the vector address */
	ea = regs->gpr[rb] + (ra ? regs->gpr[ra] : 0);
	if (is_32bit_task())
		ea &= 0xfffffffful;
	addr = (__force const void __user *)ea;

	/* Check it */
	if (!access_ok(addr, 16)) {
		pr_devel("HMI vec emu: bad access %i:%s[%d] nip=%016lx"
			 " instr=%08x addr=%016lx\n",
			 smp_processor_id(), current->comm, current->pid,
			 regs->nip, instr, (unsigned long)addr);
		return;
	}

	/* Read the vector */
	rc = 0;
	if ((unsigned long)addr & 0xfUL)
		/* unaligned case */
		rc = __copy_from_user_inatomic(vbuf, addr, 16);
	else
		__get_user_atomic_128_aligned(vbuf, addr, rc);
	if (rc) {
		pr_devel("HMI vec emu: page fault %i:%s[%d] nip=%016lx"
			 " instr=%08x addr=%016lx\n",
			 smp_processor_id(), current->comm, current->pid,
			 regs->nip, instr, (unsigned long)addr);
		return;
	}

	pr_devel("HMI vec emu: emulated vector CI %i:%s[%d] nip=%016lx"
		 " instr=%08x addr=%016lx\n",
		 smp_processor_id(), current->comm, current->pid, regs->nip,
		 instr, (unsigned long) addr);

	/* Grab instruction "selector" */
	sel = (instr >> 6) & 3;

	/*
	 * Check to make sure the facility is actually enabled. This
	 * could happen if we get a false positive hit.
	 *
	 * lxvd2x/lxvw4x always check MSR VSX sel = 0,2
	 * lxvh8x/lxvb16x check MSR VSX or VEC depending on VSR used sel = 1,3
	 */
	msr_mask = MSR_VSX;
	if ((sel & 1) && (instr & 1)) /* lxvh8x & lxvb16x + VSR >= 32 */
		msr_mask = MSR_VEC;
	if (!(msr & msr_mask)) {
		pr_devel("HMI vec emu: MSR fac clear %i:%s[%d] nip=%016lx"
			 " instr=%08x msr:%016lx\n",
			 smp_processor_id(), current->comm, current->pid,
			 regs->nip, instr, msr);
		return;
	}

	/* Do logging here before we modify sel based on endian */
	switch (sel) {
	case 0:	/* lxvw4x */
		PPC_WARN_EMULATED(lxvw4x, regs);
		break;
	case 1: /* lxvh8x */
		PPC_WARN_EMULATED(lxvh8x, regs);
		break;
	case 2: /* lxvd2x */
		PPC_WARN_EMULATED(lxvd2x, regs);
		break;
	case 3: /* lxvb16x */
		PPC_WARN_EMULATED(lxvb16x, regs);
		break;
	}

#ifdef __LITTLE_ENDIAN__
	/*
	 * An LE kernel stores the vector in the task struct as an LE
	 * byte array (effectively swapping both the components and
	 * the content of the components). Those instructions expect
	 * the components to remain in ascending address order, so we
	 * swap them back.
	 *
	 * If we are running a BE user space, the expectation is that
	 * of a simple memcpy, so forcing the emulation to look like
	 * a lxvb16x should do the trick.
	 */
	if (swap)
		sel = 3;

	switch (sel) {
	case 0:	/* lxvw4x */
		for (i = 0; i < 4; i++)
			((u32 *)vdst)[i] = ((u32 *)vbuf)[3-i];
		break;
	case 1: /* lxvh8x */
		for (i = 0; i < 8; i++)
			((u16 *)vdst)[i] = ((u16 *)vbuf)[7-i];
		break;
	case 2: /* lxvd2x */
		for (i = 0; i < 2; i++)
			((u64 *)vdst)[i] = ((u64 *)vbuf)[1-i];
		break;
	case 3: /* lxvb16x */
		for (i = 0; i < 16; i++)
			vdst[i] = vbuf[15-i];
		break;
	}
#else /* __LITTLE_ENDIAN__ */
	/* On a big endian kernel, a BE userspace only needs a memcpy */
	if (!swap)
		sel = 3;

	/* Otherwise, we need to swap the content of the components */
	switch (sel) {
	case 0:	/* lxvw4x */
		for (i = 0; i < 4; i++)
			((u32 *)vdst)[i] = cpu_to_le32(((u32 *)vbuf)[i]);
		break;
	case 1: /* lxvh8x */
		for (i = 0; i < 8; i++)
			((u16 *)vdst)[i] = cpu_to_le16(((u16 *)vbuf)[i]);
		break;
	case 2: /* lxvd2x */
		for (i = 0; i < 2; i++)
			((u64 *)vdst)[i] = cpu_to_le64(((u64 *)vbuf)[i]);
		break;
	case 3: /* lxvb16x */
		memcpy(vdst, vbuf, 16);
		break;
	}
#endif /* !__LITTLE_ENDIAN__ */

	/* Go to next instruction */
	regs_add_return_ip(regs, 4);
}
#endif /* CONFIG_VSX */

DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
{
	struct pt_regs *old_regs;

	old_regs = set_irq_regs(regs);

#ifdef CONFIG_VSX
	/* Real mode flagged P9 special emu is needed */
	if (local_paca->hmi_p9_special_emu) {
		local_paca->hmi_p9_special_emu = 0;

		/*
		 * We don't want to take page faults while doing the
		 * emulation, we just replay the instruction if necessary.
		 */
		pagefault_disable();
		p9_hmi_special_emu(regs);
		pagefault_enable();
	}
#endif /* CONFIG_VSX */

	if (ppc_md.handle_hmi_exception)
		ppc_md.handle_hmi_exception(regs);

	set_irq_regs(old_regs);
}

DEFINE_INTERRUPT_HANDLER(unknown_exception)
{
	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
	       regs->nip, regs->msr, regs->trap);

	_exception(SIGTRAP, regs, TRAP_UNK, 0);
}

DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
{
	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
	       regs->nip, regs->msr, regs->trap);

	_exception(SIGTRAP, regs, TRAP_UNK, 0);
}

DEFINE_INTERRUPT_HANDLER_NMI(unknown_nmi_exception)
{
	printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
	       regs->nip, regs->msr, regs->trap);

	_exception(SIGTRAP, regs, TRAP_UNK, 0);

	return 0;
}

DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
{
	if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
					5, SIGTRAP) == NOTIFY_STOP)
		return;
	if (debugger_iabr_match(regs))
		return;
	_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
}

DEFINE_INTERRUPT_HANDLER(RunModeException)
{
	_exception(SIGTRAP, regs, TRAP_UNK, 0);
}

static void __single_step_exception(struct pt_regs *regs)
{
	clear_single_step(regs);
	clear_br_trace(regs);

	if (kprobe_post_handler(regs))
		return;

	if (notify_die(DIE_SSTEP, "single_step", regs, 5,
					5, SIGTRAP) == NOTIFY_STOP)
		return;
	if (debugger_sstep(regs))
		return;

	_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
}

DEFINE_INTERRUPT_HANDLER(single_step_exception)
{
	__single_step_exception(regs);
}

/*
 * After we have successfully emulated an instruction, we have to
 * check if the instruction was being single-stepped, and if so,
 * pretend we got a single-step exception.  This was pointed out
 * by Kumar Gala.  -- paulus
 */
void emulate_single_step(struct pt_regs *regs)
{
	if (single_stepping(regs))
		__single_step_exception(regs);
}

#ifdef CONFIG_PPC_FPU_REGS
static inline int __parse_fpscr(unsigned long fpscr)
{
	int ret = FPE_FLTUNK;

	/* Invalid operation */
	if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX))
		ret = FPE_FLTINV;

	/* Overflow */
	else if ((fpscr & FPSCR_OE) && (fpscr & FPSCR_OX))
		ret = FPE_FLTOVF;

	/* Underflow */
	else if ((fpscr & FPSCR_UE) && (fpscr & FPSCR_UX))
		ret = FPE_FLTUND;

	/* Divide by zero */
	else if ((fpscr & FPSCR_ZE) && (fpscr & FPSCR_ZX))
		ret = FPE_FLTDIV;

	/* Inexact result */
	else if ((fpscr & FPSCR_XE) && (fpscr & FPSCR_XX))
		ret = FPE_FLTRES;

	return ret;
}
#endif

static void parse_fpe(struct pt_regs *regs)
{
	int code = 0;

	flush_fp_to_thread(current);

#ifdef CONFIG_PPC_FPU_REGS
	code = __parse_fpscr(current->thread.fp_state.fpscr);
#endif

	_exception(SIGFPE, regs, code, regs->nip);
}

/*
 * Illegal instruction emulation support.  Originally written to
 * provide the PVR to user applications using the mfspr rd, PVR.
 * Return non-zero if we can't emulate, or -EFAULT if the associated
 * memory access caused an access fault.  Return zero on success.
 *
 * There are a couple of ways to do this, either "decode" the instruction
 * or directly match lots of bits.  In this case, matching lots of
 * bits is faster and easier.
 *
 */
static int emulate_string_inst(struct pt_regs *regs, u32 instword)
{
	u8 rT = (instword >> 21) & 0x1f;
	u8 rA = (instword >> 16) & 0x1f;
	u8 NB_RB = (instword >> 11) & 0x1f;
	u32 num_bytes;
	unsigned long EA;
	int pos = 0;

	/* Early out if we are an invalid form of lswx */
	if ((instword & PPC_INST_STRING_MASK) == PPC_INST_LSWX)
		if ((rT == rA) || (rT == NB_RB))
			return -EINVAL;

	EA = (rA == 0) ? 0 : regs->gpr[rA];

	switch (instword & PPC_INST_STRING_MASK) {
		case PPC_INST_LSWX:
		case PPC_INST_STSWX:
			EA += NB_RB;
			num_bytes = regs->xer & 0x7f;
			break;
		case PPC_INST_LSWI:
		case PPC_INST_STSWI:
			num_bytes = (NB_RB == 0) ? 32 : NB_RB;
			break;
		default:
			return -EINVAL;
	}

	while (num_bytes != 0)
	{
		u8 val;
		u32 shift = 8 * (3 - (pos & 0x3));

		/* if process is 32-bit, clear upper 32 bits of EA */
		if ((regs->msr & MSR_64BIT) == 0)
			EA &= 0xFFFFFFFF;

		switch ((instword & PPC_INST_STRING_MASK)) {
			case PPC_INST_LSWX:
			case PPC_INST_LSWI:
				if (get_user(val, (u8 __user *)EA))
					return -EFAULT;
				/* first time updating this reg,
				 * zero it out */
				if (pos == 0)
					regs->gpr[rT] = 0;
				regs->gpr[rT] |= val << shift;
				break;
			case PPC_INST_STSWI:
			case PPC_INST_STSWX:
				val = regs->gpr[rT] >> shift;
				if (put_user(val, (u8 __user *)EA))
					return -EFAULT;
				break;
		}
		/* move EA to next address */
		EA += 1;
		num_bytes--;

		/* manage our position within the register */
		if (++pos == 4) {
			pos = 0;
			if (++rT == 32)
				rT = 0;
		}
	}

	return 0;
}

static int emulate_popcntb_inst(struct pt_regs *regs, u32 instword)
{
	u32 ra,rs;
	unsigned long tmp;

	ra = (instword >> 16) & 0x1f;
	rs = (instword >> 21) & 0x1f;

	tmp = regs->gpr[rs];
	tmp = tmp - ((tmp >> 1) & 0x5555555555555555ULL);
	tmp = (tmp & 0x3333333333333333ULL) + ((tmp >> 2) & 0x3333333333333333ULL);
	tmp = (tmp + (tmp >> 4)) & 0x0f0f0f0f0f0f0f0fULL;
	regs->gpr[ra] = tmp;

	return 0;
}

static int emulate_isel(struct pt_regs *regs, u32 instword)
{
	u8 rT = (instword >> 21) & 0x1f;
	u8 rA = (instword >> 16) & 0x1f;
	u8 rB = (instword >> 11) & 0x1f;
	u8 BC = (instword >> 6) & 0x1f;
	u8 bit;
	unsigned long tmp;

	tmp = (rA == 0) ? 0 : regs->gpr[rA];
	bit = (regs->ccr >> (31 - BC)) & 0x1;

	regs->gpr[rT] = bit ? tmp : regs->gpr[rB];

	return 0;
}

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
static inline bool tm_abort_check(struct pt_regs *regs, int cause)
{
        /* If we're emulating a load/store in an active transaction, we cannot
         * emulate it as the kernel operates in transaction suspended context.
         * We need to abort the transaction.  This creates a persistent TM
         * abort so tell the user what caused it with a new code.
	 */
	if (MSR_TM_TRANSACTIONAL(regs->msr)) {
		tm_enable();
		tm_abort(cause);
		return true;
	}
	return false;
}
#else
static inline bool tm_abort_check(struct pt_regs *regs, int reason)
{
	return false;
}
#endif

static int emulate_instruction(struct pt_regs *regs)
{
	u32 instword;
	u32 rd;

	if (!user_mode(regs))
		return -EINVAL;

	if (get_user(instword, (u32 __user *)(regs->nip)))
		return -EFAULT;

	/* Emulate the mfspr rD, PVR. */
	if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
		PPC_WARN_EMULATED(mfpvr, regs);
		rd = (instword >> 21) & 0x1f;
		regs->gpr[rd] = mfspr(SPRN_PVR);
		return 0;
	}

	/* Emulating the dcba insn is just a no-op.  */
	if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) {
		PPC_WARN_EMULATED(dcba, regs);
		return 0;
	}

	/* Emulate the mcrxr insn.  */
	if ((instword & PPC_INST_MCRXR_MASK) == PPC_INST_MCRXR) {
		int shift = (instword >> 21) & 0x1c;
		unsigned long msk = 0xf0000000UL >> shift;

		PPC_WARN_EMULATED(mcrxr, regs);
		regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk);
		regs->xer &= ~0xf0000000UL;
		return 0;
	}

	/* Emulate load/store string insn. */
	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
		if (tm_abort_check(regs,
				   TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
			return -EINVAL;
		PPC_WARN_EMULATED(string, regs);
		return emulate_string_inst(regs, instword);
	}

	/* Emulate the popcntb (Population Count Bytes) instruction. */
	if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) {
		PPC_WARN_EMULATED(popcntb, regs);
		return emulate_popcntb_inst(regs, instword);
	}

	/* Emulate isel (Integer Select) instruction */
	if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) {
		PPC_WARN_EMULATED(isel, regs);
		return emulate_isel(regs, instword);
	}

	/* Emulate sync instruction variants */
	if ((instword & PPC_INST_SYNC_MASK) == PPC_INST_SYNC) {
		PPC_WARN_EMULATED(sync, regs);
		asm volatile("sync");
		return 0;
	}

#ifdef CONFIG_PPC64
	/* Emulate the mfspr rD, DSCR. */
	if ((((instword & PPC_INST_MFSPR_DSCR_USER_MASK) ==
		PPC_INST_MFSPR_DSCR_USER) ||
	     ((instword & PPC_INST_MFSPR_DSCR_MASK) ==
		PPC_INST_MFSPR_DSCR)) &&
			cpu_has_feature(CPU_FTR_DSCR)) {
		PPC_WARN_EMULATED(mfdscr, regs);
		rd = (instword >> 21) & 0x1f;
		regs->gpr[rd] = mfspr(SPRN_DSCR);
		return 0;
	}
	/* Emulate the mtspr DSCR, rD. */
	if ((((instword & PPC_INST_MTSPR_DSCR_USER_MASK) ==
		PPC_INST_MTSPR_DSCR_USER) ||
	     ((instword & PPC_INST_MTSPR_DSCR_MASK) ==
		PPC_INST_MTSPR_DSCR)) &&
			cpu_has_feature(CPU_FTR_DSCR)) {
		PPC_WARN_EMULATED(mtdscr, regs);
		rd = (instword >> 21) & 0x1f;
		current->thread.dscr = regs->gpr[rd];
		current->thread.dscr_inherit = 1;
		mtspr(SPRN_DSCR, current->thread.dscr);
		return 0;
	}
#endif

	return -EINVAL;
}

#ifdef CONFIG_GENERIC_BUG
int is_valid_bugaddr(unsigned long addr)
{
	return is_kernel_addr(addr);
}
#endif

#ifdef CONFIG_MATH_EMULATION
static int emulate_math(struct pt_regs *regs)
{
	int ret;

	ret = do_mathemu(regs);
	if (ret >= 0)
		PPC_WARN_EMULATED(math, regs);

	switch (ret) {
	case 0:
		emulate_single_step(regs);
		return 0;
	case 1: {
			int code = 0;
			code = __parse_fpscr(current->thread.fp_state.fpscr);
			_exception(SIGFPE, regs, code, regs->nip);
			return 0;
		}
	case -EFAULT:
		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
		return 0;
	}

	return -1;
}
#else
static inline int emulate_math(struct pt_regs *regs) { return -1; }
#endif

static void do_program_check(struct pt_regs *regs)
{
	unsigned int reason = get_reason(regs);

	/* We can now get here via a FP Unavailable exception if the core
	 * has no FPU, in that case the reason flags will be 0 */

	if (reason & REASON_FP) {
		/* IEEE FP exception */
		parse_fpe(regs);
		return;
	}
	if (reason & REASON_TRAP) {
		unsigned long bugaddr;
		/* Debugger is first in line to stop recursive faults in
		 * rcu_lock, notify_die, or atomic_notifier_call_chain */
		if (debugger_bpt(regs))
			return;

		if (kprobe_handler(regs))
			return;

		/* trap exception */
		if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
				== NOTIFY_STOP)
			return;

		bugaddr = regs->nip;
		/*
		 * Fixup bugaddr for BUG_ON() in real mode
		 */
		if (!is_kernel_addr(bugaddr) && !(regs->msr & MSR_IR))
			bugaddr += PAGE_OFFSET;

		if (!user_mode(regs) &&
		    report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
			regs_add_return_ip(regs, 4);
			return;
		}

		/* User mode considers other cases after enabling IRQs */
		if (!user_mode(regs)) {
			_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
			return;
		}
	}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	if (reason & REASON_TM) {
		/* This is a TM "Bad Thing Exception" program check.
		 * This occurs when:
		 * -  An rfid/hrfid/mtmsrd attempts to cause an illegal
		 *    transition in TM states.
		 * -  A trechkpt is attempted when transactional.
		 * -  A treclaim is attempted when non transactional.
		 * -  A tend is illegally attempted.
		 * -  writing a TM SPR when transactional.
		 *
		 * If usermode caused this, it's done something illegal and
		 * gets a SIGILL slap on the wrist.  We call it an illegal
		 * operand to distinguish from the instruction just being bad
		 * (e.g. executing a 'tend' on a CPU without TM!); it's an
		 * illegal /placement/ of a valid instruction.
		 */
		if (user_mode(regs)) {
			_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
			return;
		} else {
			printk(KERN_EMERG "Unexpected TM Bad Thing exception "
			       "at %lx (msr 0x%lx) tm_scratch=%llx\n",
			       regs->nip, regs->msr, get_paca()->tm_scratch);
			die("Unrecoverable exception", regs, SIGABRT);
		}
	}
#endif

	/*
	 * If we took the program check in the kernel skip down to sending a
	 * SIGILL. The subsequent cases all relate to user space, such as
	 * emulating instructions which we should only do for user space. We
	 * also do not want to enable interrupts for kernel faults because that
	 * might lead to further faults, and loose the context of the original
	 * exception.
	 */
	if (!user_mode(regs))
		goto sigill;

	interrupt_cond_local_irq_enable(regs);

	/*
	 * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
	 * except get_user_instr() can sleep so we cannot reliably inspect the
	 * current instruction in that context. Now that we know we are
	 * handling a user space trap and can sleep, we can check if the trap
	 * was a hashchk failure.
	 */
	if (reason & REASON_TRAP) {
		if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
			ppc_inst_t insn;

			if (get_user_instr(insn, (void __user *)regs->nip)) {
				_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
				return;
			}

			if (ppc_inst_primary_opcode(insn) == 31 &&
			    get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
				_exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
				return;
			}
		}

		_exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
		return;
	}

	/* (reason & REASON_ILLEGAL) would be the obvious thing here,
	 * but there seems to be a hardware bug on the 405GP (RevD)
	 * that means ESR is sometimes set incorrectly - either to
	 * ESR_DST (!?) or 0.  In the process of chasing this with the
	 * hardware people - not sure if it can happen on any illegal
	 * instruction or only on FP instructions, whether there is a
	 * pattern to occurrences etc. -dgibson 31/Mar/2003
	 */
	if (!emulate_math(regs))
		return;

	/* Try to emulate it if we should. */
	if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
		switch (emulate_instruction(regs)) {
		case 0:
			regs_add_return_ip(regs, 4);
			emulate_single_step(regs);
			return;
		case -EFAULT:
			_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
			return;
		}
	}

sigill:
	if (reason & REASON_PRIVILEGED)
		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
	else
		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);

}

DEFINE_INTERRUPT_HANDLER(program_check_exception)
{
	do_program_check(regs);
}

/*
 * This occurs when running in hypervisor mode on POWER6 or later
 * and an illegal instruction is encountered.
 */
DEFINE_INTERRUPT_HANDLER(emulation_assist_interrupt)
{
	regs_set_return_msr(regs, regs->msr | REASON_ILLEGAL);
	do_program_check(regs);
}

DEFINE_INTERRUPT_HANDLER(alignment_exception)
{
	int sig, code, fixed = 0;
	unsigned long  reason;

	interrupt_cond_local_irq_enable(regs);

	reason = get_reason(regs);
	if (reason & REASON_BOUNDARY) {
		sig = SIGBUS;
		code = BUS_ADRALN;
		goto bad;
	}

	if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
		return;

	/* we don't implement logging of alignment exceptions */
	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
		fixed = fix_alignment(regs);

	if (fixed == 1) {
		/* skip over emulated instruction */
		regs_add_return_ip(regs, inst_length(reason));
		emulate_single_step(regs);
		return;
	}

	/* Operand address was bad */
	if (fixed == -EFAULT) {
		sig = SIGSEGV;
		code = SEGV_ACCERR;
	} else {
		sig = SIGBUS;
		code = BUS_ADRALN;
	}
bad:
	if (user_mode(regs))
		_exception(sig, regs, code, regs->dar);
	else
		bad_page_fault(regs, sig);
}

DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
{
	die("Kernel stack overflow", regs, SIGSEGV);
}

DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
{
	printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
			  "%lx at %lx\n", regs->trap, regs->nip);
	die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
}

DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
{
	if (user_mode(regs)) {
		/* A user program has executed an altivec instruction,
		   but this kernel doesn't support altivec. */
		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
		return;
	}

	printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
			"%lx at %lx\n", regs->trap, regs->nip);
	die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
}

DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
{
	if (user_mode(regs)) {
		/* A user program has executed an vsx instruction,
		   but this kernel doesn't support vsx. */
		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
		return;
	}

	printk(KERN_EMERG "Unrecoverable VSX Unavailable Exception "
			"%lx at %lx\n", regs->trap, regs->nip);
	die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
}

#ifdef CONFIG_PPC_BOOK3S_64
static void tm_unavailable(struct pt_regs *regs)
{
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
	if (user_mode(regs)) {
		current->thread.load_tm++;
		regs_set_return_msr(regs, regs->msr | MSR_TM);
		tm_enable();
		tm_restore_sprs(&current->thread);
		return;
	}
#endif
	pr_emerg("Unrecoverable TM Unavailable Exception "
			"%lx at %lx\n", regs->trap, regs->nip);
	die("Unrecoverable TM Unavailable Exception", regs, SIGABRT);
}

DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
{
	static char *facility_strings[] = {
		[FSCR_FP_LG] = "FPU",
		[FSCR_VECVSX_LG] = "VMX/VSX",
		[FSCR_DSCR_LG] = "DSCR",
		[FSCR_PM_LG] = "PMU SPRs",
		[FSCR_BHRB_LG] = "BHRB",
		[FSCR_TM_LG] = "TM",
		[FSCR_EBB_LG] = "EBB",
		[FSCR_TAR_LG] = "TAR",
		[FSCR_MSGP_LG] = "MSGP",
		[FSCR_SCV_LG] = "SCV",
		[FSCR_PREFIX_LG] = "PREFIX",
	};
	char *facility = "unknown";
	u64 value;
	u32 instword, rd;
	u8 status;
	bool hv;

	hv = (TRAP(regs) == INTERRUPT_H_FAC_UNAVAIL);
	if (hv)
		value = mfspr(SPRN_HFSCR);
	else
		value = mfspr(SPRN_FSCR);

	status = value >> 56;
	if ((hv || status >= 2) &&
	    (status < ARRAY_SIZE(facility_strings)) &&
	    facility_strings[status])
		facility = facility_strings[status];

	/* We should not have taken this interrupt in kernel */
	if (!user_mode(regs)) {
		pr_emerg("Facility '%s' unavailable (%d) exception in kernel mode at %lx\n",
			 facility, status, regs->nip);
		die("Unexpected facility unavailable exception", regs, SIGABRT);
	}

	interrupt_cond_local_irq_enable(regs);

	if (status == FSCR_DSCR_LG) {
		/*
		 * User is accessing the DSCR register using the problem
		 * state only SPR number (0x03) either through a mfspr or
		 * a mtspr instruction. If it is a write attempt through
		 * a mtspr, then we set the inherit bit. This also allows
		 * the user to write or read the register directly in the
		 * future by setting via the FSCR DSCR bit. But in case it
		 * is a read DSCR attempt through a mfspr instruction, we
		 * just emulate the instruction instead. This code path will
		 * always emulate all the mfspr instructions till the user
		 * has attempted at least one mtspr instruction. This way it
		 * preserves the same behaviour when the user is accessing
		 * the DSCR through privilege level only SPR number (0x11)
		 * which is emulated through illegal instruction exception.
		 * We always leave HFSCR DSCR set.
		 */
		if (get_user(instword, (u32 __user *)(regs->nip))) {
			pr_err("Failed to fetch the user instruction\n");
			return;
		}

		/* Write into DSCR (mtspr 0x03, RS) */
		if ((instword & PPC_INST_MTSPR_DSCR_USER_MASK)
				== PPC_INST_MTSPR_DSCR_USER) {
			rd = (instword >> 21) & 0x1f;
			current->thread.dscr = regs->gpr[rd];
			current->thread.dscr_inherit = 1;
			current->thread.fscr |= FSCR_DSCR;
			mtspr(SPRN_FSCR, current->thread.fscr);
		}

		/* Read from DSCR (mfspr RT, 0x03) */
		if ((instword & PPC_INST_MFSPR_DSCR_USER_MASK)
				== PPC_INST_MFSPR_DSCR_USER) {
			if (emulate_instruction(regs)) {
				pr_err("DSCR based mfspr emulation failed\n");
				return;
			}
			regs_add_return_ip(regs, 4);
			emulate_single_step(regs);
		}
		return;
	}

	if (status == FSCR_TM_LG) {
		/*
		 * If we're here then the hardware is TM aware because it
		 * generated an exception with FSRM_TM set.
		 *
		 * If cpu_has_feature(CPU_FTR_TM) is false, then either firmware
		 * told us not to do TM, or the kernel is not built with TM
		 * support.
		 *
		 * If both of those things are true, then userspace can spam the
		 * console by triggering the printk() below just by continually
		 * doing tbegin (or any TM instruction). So in that case just
		 * send the process a SIGILL immediately.
		 */
		if (!cpu_has_feature(CPU_FTR_TM))
			goto out;

		tm_unavailable(regs);
		return;
	}

	pr_err_ratelimited("%sFacility '%s' unavailable (%d), exception at 0x%lx, MSR=%lx\n",
		hv ? "Hypervisor " : "", facility, status, regs->nip, regs->msr);

out:
	_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
}
#endif

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM

DEFINE_INTERRUPT_HANDLER(fp_unavailable_tm)
{
	/* Note:  This does not handle any kind of FP laziness. */

	TM_DEBUG("FP Unavailable trap whilst transactional at 0x%lx, MSR=%lx\n",
		 regs->nip, regs->msr);

        /* We can only have got here if the task started using FP after
         * beginning the transaction.  So, the transactional regs are just a
         * copy of the checkpointed ones.  But, we still need to recheckpoint
         * as we're enabling FP for the process; it will return, abort the
         * transaction, and probably retry but now with FP enabled.  So the
         * checkpointed FP registers need to be loaded.
	 */
	tm_reclaim_current(TM_CAUSE_FAC_UNAV);

	/*
	 * Reclaim initially saved out bogus (lazy) FPRs to ckfp_state, and
	 * then it was overwrite by the thr->fp_state by tm_reclaim_thread().
	 *
	 * At this point, ck{fp,vr}_state contains the exact values we want to
	 * recheckpoint.
	 */

	/* Enable FP for the task: */
	current->thread.load_fp = 1;

	/*
	 * Recheckpoint all the checkpointed ckpt, ck{fp, vr}_state registers.
	 */
	tm_recheckpoint(&current->thread);
}

DEFINE_INTERRUPT_HANDLER(altivec_unavailable_tm)
{
	/* See the comments in fp_unavailable_tm().  This function operates
	 * the same way.
	 */

	TM_DEBUG("Vector Unavailable trap whilst transactional at 0x%lx,"
		 "MSR=%lx\n",
		 regs->nip, regs->msr);
	tm_reclaim_current(TM_CAUSE_FAC_UNAV);
	current->thread.load_vec = 1;
	tm_recheckpoint(&current->thread);
	current->thread.used_vr = 1;
}

DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
{
	/* See the comments in fp_unavailable_tm().  This works similarly,
	 * though we're loading both FP and VEC registers in here.
	 *
	 * If FP isn't in use, load FP regs.  If VEC isn't in use, load VEC
	 * regs.  Either way, set MSR_VSX.
	 */

	TM_DEBUG("VSX Unavailable trap whilst transactional at 0x%lx,"
		 "MSR=%lx\n",
		 regs->nip, regs->msr);

	current->thread.used_vsr = 1;

	/* This reclaims FP and/or VR regs if they're already enabled */
	tm_reclaim_current(TM_CAUSE_FAC_UNAV);

	current->thread.load_vec = 1;
	current->thread.load_fp = 1;

	tm_recheckpoint(&current->thread);
}
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */

#ifdef CONFIG_PPC64
DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
{
	__this_cpu_inc(irq_stat.pmu_irqs);

	perf_irq(regs);

	return 0;
}
#endif

DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
{
	__this_cpu_inc(irq_stat.pmu_irqs);

	perf_irq(regs);
}

DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
{
	/*
	 * On 64-bit, if perf interrupts hit in a local_irq_disable
	 * (soft-masked) region, we consider them as NMIs. This is required to
	 * prevent hash faults on user addresses when reading callchains (and
	 * looks better from an irq tracing perspective).
	 */
	if (IS_ENABLED(CONFIG_PPC64) && unlikely(arch_irq_disabled_regs(regs)))
		performance_monitor_exception_nmi(regs);
	else
		performance_monitor_exception_async(regs);

	return 0;
}

#ifdef CONFIG_PPC_ADV_DEBUG_REGS
static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
{
	int changed = 0;
	/*
	 * Determine the cause of the debug event, clear the
	 * event flags and send a trap to the handler. Torez
	 */
	if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) {
		dbcr_dac(current) &= ~(DBCR_DAC1R | DBCR_DAC1W);
#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
		current->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
#endif
		do_send_trap(regs, mfspr(SPRN_DAC1), debug_status,
			     5);
		changed |= 0x01;
	}  else if (debug_status & (DBSR_DAC2R | DBSR_DAC2W)) {
		dbcr_dac(current) &= ~(DBCR_DAC2R | DBCR_DAC2W);
		do_send_trap(regs, mfspr(SPRN_DAC2), debug_status,
			     6);
		changed |= 0x01;
	}  else if (debug_status & DBSR_IAC1) {
		current->thread.debug.dbcr0 &= ~DBCR0_IAC1;
		dbcr_iac_range(current) &= ~DBCR_IAC12MODE;
		do_send_trap(regs, mfspr(SPRN_IAC1), debug_status,
			     1);
		changed |= 0x01;
	}  else if (debug_status & DBSR_IAC2) {
		current->thread.debug.dbcr0 &= ~DBCR0_IAC2;
		do_send_trap(regs, mfspr(SPRN_IAC2), debug_status,
			     2);
		changed |= 0x01;
	}  else if (debug_status & DBSR_IAC3) {
		current->thread.debug.dbcr0 &= ~DBCR0_IAC3;
		dbcr_iac_range(current) &= ~DBCR_IAC34MODE;
		do_send_trap(regs, mfspr(SPRN_IAC3), debug_status,
			     3);
		changed |= 0x01;
	}  else if (debug_status & DBSR_IAC4) {
		current->thread.debug.dbcr0 &= ~DBCR0_IAC4;
		do_send_trap(regs, mfspr(SPRN_IAC4), debug_status,
			     4);
		changed |= 0x01;
	}
	/*
	 * At the point this routine was called, the MSR(DE) was turned off.
	 * Check all other debug flags and see if that bit needs to be turned
	 * back on or not.
	 */
	if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0,
			       current->thread.debug.dbcr1))
		regs_set_return_msr(regs, regs->msr | MSR_DE);
	else
		/* Make sure the IDM flag is off */
		current->thread.debug.dbcr0 &= ~DBCR0_IDM;

	if (changed & 0x01)
		mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
}

DEFINE_INTERRUPT_HANDLER(DebugException)
{
	unsigned long debug_status = regs->dsisr;

	current->thread.debug.dbsr = debug_status;

	/* Hack alert: On BookE, Branch Taken stops on the branch itself, while
	 * on server, it stops on the target of the branch. In order to simulate
	 * the server behaviour, we thus restart right away with a single step
	 * instead of stopping here when hitting a BT
	 */
	if (debug_status & DBSR_BT) {
		regs_set_return_msr(regs, regs->msr & ~MSR_DE);

		/* Disable BT */
		mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_BT);
		/* Clear the BT event */
		mtspr(SPRN_DBSR, DBSR_BT);

		/* Do the single step trick only when coming from userspace */
		if (user_mode(regs)) {
			current->thread.debug.dbcr0 &= ~DBCR0_BT;
			current->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
			regs_set_return_msr(regs, regs->msr | MSR_DE);
			return;
		}

		if (kprobe_post_handler(regs))
			return;

		if (notify_die(DIE_SSTEP, "block_step", regs, 5,
			       5, SIGTRAP) == NOTIFY_STOP) {
			return;
		}
		if (debugger_sstep(regs))
			return;
	} else if (debug_status & DBSR_IC) { 	/* Instruction complete */
		regs_set_return_msr(regs, regs->msr & ~MSR_DE);

		/* Disable instruction completion */
		mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_IC);
		/* Clear the instruction completion event */
		mtspr(SPRN_DBSR, DBSR_IC);

		if (kprobe_post_handler(regs))
			return;

		if (notify_die(DIE_SSTEP, "single_step", regs, 5,
			       5, SIGTRAP) == NOTIFY_STOP) {
			return;
		}

		if (debugger_sstep(regs))
			return;

		if (user_mode(regs)) {
			current->thread.debug.dbcr0 &= ~DBCR0_IC;
			if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0,
					       current->thread.debug.dbcr1))
				regs_set_return_msr(regs, regs->msr | MSR_DE);
			else
				/* Make sure the IDM bit is off */
				current->thread.debug.dbcr0 &= ~DBCR0_IDM;
		}

		_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
	} else
		handle_debug(regs, debug_status);
}
#endif /* CONFIG_PPC_ADV_DEBUG_REGS */

#ifdef CONFIG_ALTIVEC
DEFINE_INTERRUPT_HANDLER(altivec_assist_exception)
{
	int err;

	if (!user_mode(regs)) {
		printk(KERN_EMERG "VMX/Altivec assist exception in kernel mode"
		       " at %lx\n", regs->nip);
		die("Kernel VMX/Altivec assist exception", regs, SIGILL);
	}

	flush_altivec_to_thread(current);

	PPC_WARN_EMULATED(altivec, regs);
	err = emulate_altivec(regs);
	if (err == 0) {
		regs_add_return_ip(regs, 4); /* skip emulated instruction */
		emulate_single_step(regs);
		return;
	}

	if (err == -EFAULT) {
		/* got an error reading the instruction */
		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
	} else {
		/* didn't recognize the instruction */
		/* XXX quick hack for now: set the non-Java bit in the VSCR */
		printk_ratelimited(KERN_ERR "Unrecognized altivec instruction "
				   "in %s at %lx\n", current->comm, regs->nip);
		current->thread.vr_state.vscr.u[3] |= 0x10000;
	}
}
#endif /* CONFIG_ALTIVEC */

#ifdef CONFIG_PPC_85xx
DEFINE_INTERRUPT_HANDLER(CacheLockingException)
{
	unsigned long error_code = regs->dsisr;

	/* We treat cache locking instructions from the user
	 * as priv ops, in the future we could try to do
	 * something smarter
	 */
	if (error_code & (ESR_DLK|ESR_ILK))
		_exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
	return;
}
#endif /* CONFIG_PPC_85xx */

#ifdef CONFIG_SPE
DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
{
	unsigned long spefscr;
	int fpexc_mode;
	int code = FPE_FLTUNK;
	int err;

	interrupt_cond_local_irq_enable(regs);

	flush_spe_to_thread(current);

	spefscr = current->thread.spefscr;
	fpexc_mode = current->thread.fpexc_mode;

	if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) {
		code = FPE_FLTOVF;
	}
	else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) {
		code = FPE_FLTUND;
	}
	else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV))
		code = FPE_FLTDIV;
	else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) {
		code = FPE_FLTINV;
	}
	else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES))
		code = FPE_FLTRES;

	err = do_spe_mathemu(regs);
	if (err == 0) {
		regs_add_return_ip(regs, 4); /* skip emulated instruction */
		emulate_single_step(regs);
		return;
	}

	if (err == -EFAULT) {
		/* got an error reading the instruction */
		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
	} else if (err == -EINVAL) {
		/* didn't recognize the instruction */
		printk(KERN_ERR "unrecognized spe instruction "
		       "in %s at %lx\n", current->comm, regs->nip);
	} else {
		_exception(SIGFPE, regs, code, regs->nip);
	}

	return;
}

DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
{
	int err;

	interrupt_cond_local_irq_enable(regs);

	preempt_disable();
	if (regs->msr & MSR_SPE)
		giveup_spe(current);
	preempt_enable();

	regs_add_return_ip(regs, -4);
	err = speround_handler(regs);
	if (err == 0) {
		regs_add_return_ip(regs, 4); /* skip emulated instruction */
		emulate_single_step(regs);
		return;
	}

	if (err == -EFAULT) {
		/* got an error reading the instruction */
		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
	} else if (err == -EINVAL) {
		/* didn't recognize the instruction */
		printk(KERN_ERR "unrecognized spe instruction "
		       "in %s at %lx\n", current->comm, regs->nip);
	} else {
		_exception(SIGFPE, regs, FPE_FLTUNK, regs->nip);
		return;
	}
}
#endif

/*
 * We enter here if we get an unrecoverable exception, that is, one
 * that happened at a point where the RI (recoverable interrupt) bit
 * in the MSR is 0.  This indicates that SRR0/1 are live, and that
 * we therefore lost state by taking this exception.
 */
void __noreturn unrecoverable_exception(struct pt_regs *regs)
{
	pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
		 regs->trap, regs->nip, regs->msr);
	die("Unrecoverable exception", regs, SIGABRT);
	/* die() should not return */
	for (;;)
		;
}

#if defined(CONFIG_BOOKE_WDT) || defined(CONFIG_40x)
DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException)
{
	printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
	mtspr(SPRN_TCR, mfspr(SPRN_TCR) & ~TCR_WIE);
	return 0;
}
#endif

/*
 * We enter here if we discover during exception entry that we are
 * running in supervisor mode with a userspace value in the stack pointer.
 */
DEFINE_INTERRUPT_HANDLER(kernel_bad_stack)
{
	printk(KERN_EMERG "Bad kernel stack pointer %lx at %lx\n",
	       regs->gpr[1], regs->nip);
	die("Bad kernel stack pointer", regs, SIGABRT);
}

#ifdef CONFIG_PPC_EMULATED_STATS

#define WARN_EMULATED_SETUP(type)	.type = { .name = #type }

struct ppc_emulated ppc_emulated = {
#ifdef CONFIG_ALTIVEC
	WARN_EMULATED_SETUP(altivec),
#endif
	WARN_EMULATED_SETUP(dcba),
	WARN_EMULATED_SETUP(dcbz),
	WARN_EMULATED_SETUP(fp_pair),
	WARN_EMULATED_SETUP(isel),
	WARN_EMULATED_SETUP(mcrxr),
	WARN_EMULATED_SETUP(mfpvr),
	WARN_EMULATED_SETUP(multiple),
	WARN_EMULATED_SETUP(popcntb),
	WARN_EMULATED_SETUP(spe),
	WARN_EMULATED_SETUP(string),
	WARN_EMULATED_SETUP(sync),
	WARN_EMULATED_SETUP(unaligned),
#ifdef CONFIG_MATH_EMULATION
	WARN_EMULATED_SETUP(math),
#endif
#ifdef CONFIG_VSX
	WARN_EMULATED_SETUP(vsx),
#endif
#ifdef CONFIG_PPC64
	WARN_EMULATED_SETUP(mfdscr),
	WARN_EMULATED_SETUP(mtdscr),
	WARN_EMULATED_SETUP(lq_stq),
	WARN_EMULATED_SETUP(lxvw4x),
	WARN_EMULATED_SETUP(lxvh8x),
	WARN_EMULATED_SETUP(lxvd2x),
	WARN_EMULATED_SETUP(lxvb16x),
#endif
};

u32 ppc_warn_emulated;

void ppc_warn_emulated_print(const char *type)
{
	pr_warn_ratelimited("%s used emulated %s instruction\n", current->comm,
			    type);
}

static int __init ppc_warn_emulated_init(void)
{
	struct dentry *dir;
	unsigned int i;
	struct ppc_emulated_entry *entries = (void *)&ppc_emulated;

	dir = debugfs_create_dir("emulated_instructions",
				 arch_debugfs_dir);

	debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);

	for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++)
		debugfs_create_u32(entries[i].name, 0644, dir,
				   (u32 *)&entries[i].val.counter);

	return 0;
}

device_initcall(ppc_warn_emulated_init);

#endif /* CONFIG_PPC_EMULATED_STATS */