aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mcheck/mce.c
blob: 01213048f62f9a1a7e8a58926337c25c67b2711f (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
/*
 * Machine check handler.
 *
 * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs.
 * Rest from unknown author(s).
 * 2004 Andi Kleen. Rewrote most of it.
 * Copyright 2008 Intel Corporation
 * Author: Andi Kleen
 */
#include <linux/thread_info.h>
#include <linux/capability.h>
#include <linux/miscdevice.h>
#include <linux/interrupt.h>
#include <linux/ratelimit.h>
#include <linux/kallsyms.h>
#include <linux/rcupdate.h>
#include <linux/kobject.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/string.h>
#include <linux/sysdev.h>
#include <linux/delay.h>
#include <linux/ctype.h>
#include <linux/sched.h>
#include <linux/sysfs.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/mm.h>

#include <asm/processor.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/idle.h>
#include <asm/ipi.h>
#include <asm/mce.h>
#include <asm/msr.h>

#include "mce-internal.h"

/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
	printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n",
	       smp_processor_id());
}

/* Call the installed machine check handler for this CPU setup. */
void (*machine_check_vector)(struct pt_regs *, long error_code) =
						unexpected_machine_check;

int mce_disabled __read_mostly;

#ifdef CONFIG_X86_NEW_MCE

#define MISC_MCELOG_MINOR	227

#define SPINUNIT 100	/* 100ns */

atomic_t mce_entry;

DEFINE_PER_CPU(unsigned, mce_exception_count);

/*
 * Tolerant levels:
 *   0: always panic on uncorrected errors, log corrected errors
 *   1: panic or SIGBUS on uncorrected errors, log corrected errors
 *   2: SIGBUS or log uncorrected errors (if possible), log corrected errors
 *   3: never panic or SIGBUS, log all errors (for testing only)
 */
static int			tolerant		__read_mostly = 1;
static int			banks			__read_mostly;
static u64			*bank			__read_mostly;
static int			rip_msr			__read_mostly;
static int			mce_bootlog		__read_mostly = -1;
static int			monarch_timeout		__read_mostly = -1;
static int			mce_panic_timeout	__read_mostly;
static int			mce_dont_log_ce		__read_mostly;
int				mce_cmci_disabled	__read_mostly;
int				mce_ignore_ce		__read_mostly;
int				mce_ser			__read_mostly;

/* User mode helper program triggered by machine check event */
static unsigned long		mce_need_notify;
static char			mce_helper[128];
static char			*mce_helper_argv[2] = { mce_helper, NULL };

static unsigned long		dont_init_banks;

static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
static DEFINE_PER_CPU(struct mce, mces_seen);
static int			cpu_missing;


/* MCA banks polled by the period polling timer for corrected events */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
};

static inline int skip_bank_init(int i)
{
	return i < BITS_PER_LONG && test_bit(i, &dont_init_banks);
}

static DEFINE_PER_CPU(struct work_struct, mce_work);

/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
{
	memset(m, 0, sizeof(struct mce));
	m->cpu = m->extcpu = smp_processor_id();
	rdtscll(m->tsc);
	/* We hope get_seconds stays lockless */
	m->time = get_seconds();
	m->cpuvendor = boot_cpu_data.x86_vendor;
	m->cpuid = cpuid_eax(1);
#ifdef CONFIG_SMP
	m->socketid = cpu_data(m->extcpu).phys_proc_id;
#endif
	m->apicid = cpu_data(m->extcpu).initial_apicid;
	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
}

DEFINE_PER_CPU(struct mce, injectm);
EXPORT_PER_CPU_SYMBOL_GPL(injectm);

/*
 * Lockless MCE logging infrastructure.
 * This avoids deadlocks on printk locks without having to break locks. Also
 * separate MCEs from kernel messages to avoid bogus bug reports.
 */

static struct mce_log mcelog = {
	.signature	= MCE_LOG_SIGNATURE,
	.len		= MCE_LOG_LEN,
	.recordlen	= sizeof(struct mce),
};

void mce_log(struct mce *mce)
{
	unsigned next, entry;

	mce->finished = 0;
	wmb();
	for (;;) {
		entry = rcu_dereference(mcelog.next);
		for (;;) {
			/*
			 * When the buffer fills up discard new entries.
			 * Assume that the earlier errors are the more
			 * interesting ones:
			 */
			if (entry >= MCE_LOG_LEN) {
				set_bit(MCE_OVERFLOW,
					(unsigned long *)&mcelog.flags);
				return;
			}
			/* Old left over entry. Skip: */
			if (mcelog.entry[entry].finished) {
				entry++;
				continue;
			}
			break;
		}
		smp_rmb();
		next = entry + 1;
		if (cmpxchg(&mcelog.next, entry, next) == entry)
			break;
	}
	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
	wmb();
	mcelog.entry[entry].finished = 1;
	wmb();

	mce->finished = 1;
	set_bit(0, &mce_need_notify);
}

static void print_mce(struct mce *m)
{
	printk(KERN_EMERG
	       "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
	       m->extcpu, m->mcgstatus, m->bank, m->status);
	if (m->ip) {
		printk(KERN_EMERG "RIP%s %02x:<%016Lx> ",
		       !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
		       m->cs, m->ip);
		if (m->cs == __KERNEL_CS)
			print_symbol("{%s}", m->ip);
		printk(KERN_CONT "\n");
	}
	printk(KERN_EMERG "TSC %llx ", m->tsc);
	if (m->addr)
		printk(KERN_CONT "ADDR %llx ", m->addr);
	if (m->misc)
		printk(KERN_CONT "MISC %llx ", m->misc);
	printk(KERN_CONT "\n");
	printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
			m->cpuvendor, m->cpuid, m->time, m->socketid,
			m->apicid);
}

static void print_mce_head(void)
{
	printk(KERN_EMERG "\nHARDWARE ERROR\n");
}

static void print_mce_tail(void)
{
	printk(KERN_EMERG "This is not a software problem!\n"
	       "Run through mcelog --ascii to decode and contact your hardware vendor\n");
}

#define PANIC_TIMEOUT 5 /* 5 seconds */

static atomic_t mce_paniced;

/* Panic in progress. Enable interrupts and wait for final IPI */
static void wait_for_panic(void)
{
	long timeout = PANIC_TIMEOUT*USEC_PER_SEC;
	preempt_disable();
	local_irq_enable();
	while (timeout-- > 0)
		udelay(1);
	if (panic_timeout == 0)
		panic_timeout = mce_panic_timeout;
	panic("Panicing machine check CPU died");
}

static void mce_panic(char *msg, struct mce *final, char *exp)
{
	int i;

	/*
	 * Make sure only one CPU runs in machine check panic
	 */
	if (atomic_add_return(1, &mce_paniced) > 1)
		wait_for_panic();
	barrier();

	bust_spinlocks(1);
	console_verbose();
	print_mce_head();
	/* First print corrected ones that are still unlogged */
	for (i = 0; i < MCE_LOG_LEN; i++) {
		struct mce *m = &mcelog.entry[i];
		if (!(m->status & MCI_STATUS_VAL))
			continue;
		if (!(m->status & MCI_STATUS_UC))
			print_mce(m);
	}
	/* Now print uncorrected but with the final one last */
	for (i = 0; i < MCE_LOG_LEN; i++) {
		struct mce *m = &mcelog.entry[i];
		if (!(m->status & MCI_STATUS_VAL))
			continue;
		if (!(m->status & MCI_STATUS_UC))
			continue;
		if (!final || memcmp(m, final, sizeof(struct mce)))
			print_mce(m);
	}
	if (final)
		print_mce(final);
	if (cpu_missing)
		printk(KERN_EMERG "Some CPUs didn't answer in synchronization\n");
	print_mce_tail();
	if (exp)
		printk(KERN_EMERG "Machine check: %s\n", exp);
	if (panic_timeout == 0)
		panic_timeout = mce_panic_timeout;
	panic(msg);
}

/* Support code for software error injection */

static int msr_to_offset(u32 msr)
{
	unsigned bank = __get_cpu_var(injectm.bank);
	if (msr == rip_msr)
		return offsetof(struct mce, ip);
	if (msr == MSR_IA32_MC0_STATUS + bank*4)
		return offsetof(struct mce, status);
	if (msr == MSR_IA32_MC0_ADDR + bank*4)
		return offsetof(struct mce, addr);
	if (msr == MSR_IA32_MC0_MISC + bank*4)
		return offsetof(struct mce, misc);
	if (msr == MSR_IA32_MCG_STATUS)
		return offsetof(struct mce, mcgstatus);
	return -1;
}

/* MSR access wrappers used for error injection */
static u64 mce_rdmsrl(u32 msr)
{
	u64 v;
	if (__get_cpu_var(injectm).finished) {
		int offset = msr_to_offset(msr);
		if (offset < 0)
			return 0;
		return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
	}
	rdmsrl(msr, v);
	return v;
}

static void mce_wrmsrl(u32 msr, u64 v)
{
	if (__get_cpu_var(injectm).finished) {
		int offset = msr_to_offset(msr);
		if (offset >= 0)
			*(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
		return;
	}
	wrmsrl(msr, v);
}

/*
 * Simple lockless ring to communicate PFNs from the exception handler with the
 * process context work function. This is vastly simplified because there's
 * only a single reader and a single writer.
 */
#define MCE_RING_SIZE 16	/* we use one entry less */

struct mce_ring {
	unsigned short start;
	unsigned short end;
	unsigned long ring[MCE_RING_SIZE];
};
static DEFINE_PER_CPU(struct mce_ring, mce_ring);

/* Runs with CPU affinity in workqueue */
static int mce_ring_empty(void)
{
	struct mce_ring *r = &__get_cpu_var(mce_ring);

	return r->start == r->end;
}

static int mce_ring_get(unsigned long *pfn)
{
	struct mce_ring *r;
	int ret = 0;

	*pfn = 0;
	get_cpu();
	r = &__get_cpu_var(mce_ring);
	if (r->start == r->end)
		goto out;
	*pfn = r->ring[r->start];
	r->start = (r->start + 1) % MCE_RING_SIZE;
	ret = 1;
out:
	put_cpu();
	return ret;
}

/* Always runs in MCE context with preempt off */
static int mce_ring_add(unsigned long pfn)
{
	struct mce_ring *r = &__get_cpu_var(mce_ring);
	unsigned next;

	next = (r->end + 1) % MCE_RING_SIZE;
	if (next == r->start)
		return -1;
	r->ring[r->end] = pfn;
	wmb();
	r->end = next;
	return 0;
}

int mce_available(struct cpuinfo_x86 *c)
{
	if (mce_disabled)
		return 0;
	return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA);
}

static void mce_schedule_work(void)
{
	if (!mce_ring_empty()) {
		struct work_struct *work = &__get_cpu_var(mce_work);
		if (!work_pending(work))
			schedule_work(work);
	}
}

/*
 * Get the address of the instruction at the time of the machine check
 * error.
 */
static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
{

	if (regs && (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV))) {
		m->ip = regs->ip;
		m->cs = regs->cs;
	} else {
		m->ip = 0;
		m->cs = 0;
	}
	if (rip_msr)
		m->ip = mce_rdmsrl(rip_msr);
}

#ifdef CONFIG_X86_LOCAL_APIC 
/*
 * Called after interrupts have been reenabled again
 * when a MCE happened during an interrupts off region
 * in the kernel.
 */
asmlinkage void smp_mce_self_interrupt(struct pt_regs *regs)
{
	ack_APIC_irq();
	exit_idle();
	irq_enter();
	mce_notify_irq();
	mce_schedule_work();
	irq_exit();
}
#endif

static void mce_report_event(struct pt_regs *regs)
{
	if (regs->flags & (X86_VM_MASK|X86_EFLAGS_IF)) {
		mce_notify_irq();
		/*
		 * Triggering the work queue here is just an insurance
		 * policy in case the syscall exit notify handler
		 * doesn't run soon enough or ends up running on the
		 * wrong CPU (can happen when audit sleeps)
		 */
		mce_schedule_work();
		return;
	}

#ifdef CONFIG_X86_LOCAL_APIC
	/*
	 * Without APIC do not notify. The event will be picked
	 * up eventually.
	 */
	if (!cpu_has_apic)
		return;

	/*
	 * When interrupts are disabled we cannot use
	 * kernel services safely. Trigger an self interrupt
	 * through the APIC to instead do the notification
	 * after interrupts are reenabled again.
	 */
	apic->send_IPI_self(MCE_SELF_VECTOR);

	/*
	 * Wait for idle afterwards again so that we don't leave the
	 * APIC in a non idle state because the normal APIC writes
	 * cannot exclude us.
	 */
	apic_wait_icr_idle();
#endif
}

DEFINE_PER_CPU(unsigned, mce_poll_count);

/*
 * Poll for corrected events or events that happened before reset.
 * Those are just logged through /dev/mcelog.
 *
 * This is executed in standard interrupt context.
 *
 * Note: spec recommends to panic for fatal unsignalled
 * errors here. However this would be quite problematic --
 * we would need to reimplement the Monarch handling and
 * it would mess up the exclusion between exception handler
 * and poll hander -- * so we skip this for now.
 * These cases should not happen anyways, or only when the CPU
 * is already totally * confused. In this case it's likely it will
 * not fully execute the machine check handler either.
 */
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
	struct mce m;
	int i;

	__get_cpu_var(mce_poll_count)++;

	mce_setup(&m);

	m.mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
	for (i = 0; i < banks; i++) {
		if (!bank[i] || !test_bit(i, *b))
			continue;

		m.misc = 0;
		m.addr = 0;
		m.bank = i;
		m.tsc = 0;

		barrier();
		m.status = mce_rdmsrl(MSR_IA32_MC0_STATUS + i*4);
		if (!(m.status & MCI_STATUS_VAL))
			continue;

		/*
		 * Uncorrected or signalled events are handled by the exception
		 * handler when it is enabled, so don't process those here.
		 *
		 * TBD do the same check for MCI_STATUS_EN here?
		 */
		if (!(flags & MCP_UC) &&
		    (m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)))
			continue;

		if (m.status & MCI_STATUS_MISCV)
			m.misc = mce_rdmsrl(MSR_IA32_MC0_MISC + i*4);
		if (m.status & MCI_STATUS_ADDRV)
			m.addr = mce_rdmsrl(MSR_IA32_MC0_ADDR + i*4);

		if (!(flags & MCP_TIMESTAMP))
			m.tsc = 0;
		/*
		 * Don't get the IP here because it's unlikely to
		 * have anything to do with the actual error location.
		 */
		if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
			mce_log(&m);
			add_taint(TAINT_MACHINE_CHECK);
		}

		/*
		 * Clear state for this bank.
		 */
		mce_wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
	}

	/*
	 * Don't clear MCG_STATUS here because it's only defined for
	 * exceptions.
	 */

	sync_core();
}
EXPORT_SYMBOL_GPL(machine_check_poll);

/*
 * Do a quick check if any of the events requires a panic.
 * This decides if we keep the events around or clear them.
 */
static int mce_no_way_out(struct mce *m, char **msg)
{
	int i;

	for (i = 0; i < banks; i++) {
		m->status = mce_rdmsrl(MSR_IA32_MC0_STATUS + i*4);
		if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY)
			return 1;
	}
	return 0;
}

/*
 * Variable to establish order between CPUs while scanning.
 * Each CPU spins initially until executing is equal its number.
 */
static atomic_t mce_executing;

/*
 * Defines order of CPUs on entry. First CPU becomes Monarch.
 */
static atomic_t mce_callin;

/*
 * Check if a timeout waiting for other CPUs happened.
 */
static int mce_timed_out(u64 *t)
{
	/*
	 * The others already did panic for some reason.
	 * Bail out like in a timeout.
	 * rmb() to tell the compiler that system_state
	 * might have been modified by someone else.
	 */
	rmb();
	if (atomic_read(&mce_paniced))
		wait_for_panic();
	if (!monarch_timeout)
		goto out;
	if ((s64)*t < SPINUNIT) {
		/* CHECKME: Make panic default for 1 too? */
		if (tolerant < 1)
			mce_panic("Timeout synchronizing machine check over CPUs",
				  NULL, NULL);
		cpu_missing = 1;
		return 1;
	}
	*t -= SPINUNIT;
out:
	touch_nmi_watchdog();
	return 0;
}

/*
 * The Monarch's reign.  The Monarch is the CPU who entered
 * the machine check handler first. It waits for the others to
 * raise the exception too and then grades them. When any
 * error is fatal panic. Only then let the others continue.
 *
 * The other CPUs entering the MCE handler will be controlled by the
 * Monarch. They are called Subjects.
 *
 * This way we prevent any potential data corruption in a unrecoverable case
 * and also makes sure always all CPU's errors are examined.
 *
 * Also this detects the case of an machine check event coming from outer
 * space (not detected by any CPUs) In this case some external agent wants
 * us to shut down, so panic too.
 *
 * The other CPUs might still decide to panic if the handler happens
 * in a unrecoverable place, but in this case the system is in a semi-stable
 * state and won't corrupt anything by itself. It's ok to let the others
 * continue for a bit first.
 *
 * All the spin loops have timeouts; when a timeout happens a CPU
 * typically elects itself to be Monarch.
 */
static void mce_reign(void)
{
	int cpu;
	struct mce *m = NULL;
	int global_worst = 0;
	char *msg = NULL;
	char *nmsg = NULL;

	/*
	 * This CPU is the Monarch and the other CPUs have run
	 * through their handlers.
	 * Grade the severity of the errors of all the CPUs.
	 */
	for_each_possible_cpu(cpu) {
		int severity = mce_severity(&per_cpu(mces_seen, cpu), tolerant,
					    &nmsg);
		if (severity > global_worst) {
			msg = nmsg;
			global_worst = severity;
			m = &per_cpu(mces_seen, cpu);
		}
	}

	/*
	 * Cannot recover? Panic here then.
	 * This dumps all the mces in the log buffer and stops the
	 * other CPUs.
	 */
	if (m && global_worst >= MCE_PANIC_SEVERITY && tolerant < 3)
		mce_panic("Fatal Machine check", m, msg);

	/*
	 * For UC somewhere we let the CPU who detects it handle it.
	 * Also must let continue the others, otherwise the handling
	 * CPU could deadlock on a lock.
	 */

	/*
	 * No machine check event found. Must be some external
	 * source or one CPU is hung. Panic.
	 */
	if (!m && tolerant < 3)
		mce_panic("Machine check from unknown source", NULL, NULL);

	/*
	 * Now clear all the mces_seen so that they don't reappear on
	 * the next mce.
	 */
	for_each_possible_cpu(cpu)
		memset(&per_cpu(mces_seen, cpu), 0, sizeof(struct mce));
}

static atomic_t global_nwo;

/*
 * Start of Monarch synchronization. This waits until all CPUs have
 * entered the exception handler and then determines if any of them
 * saw a fatal event that requires panic. Then it executes them
 * in the entry order.
 * TBD double check parallel CPU hotunplug
 */
static int mce_start(int *no_way_out)
{
	int order;
	int cpus = num_online_cpus();
	u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC;

	if (!timeout)
		return -1;

	atomic_add(*no_way_out, &global_nwo);
	/*
	 * global_nwo should be updated before mce_callin
	 */
	smp_wmb();
	order = atomic_add_return(1, &mce_callin);

	/*
	 * Wait for everyone.
	 */
	while (atomic_read(&mce_callin) != cpus) {
		if (mce_timed_out(&timeout)) {
			atomic_set(&global_nwo, 0);
			return -1;
		}
		ndelay(SPINUNIT);
	}

	/*
	 * mce_callin should be read before global_nwo
	 */
	smp_rmb();

	if (order == 1) {
		/*
		 * Monarch: Starts executing now, the others wait.
		 */
		atomic_set(&mce_executing, 1);
	} else {
		/*
		 * Subject: Now start the scanning loop one by one in
		 * the original callin order.
		 * This way when there are any shared banks it will be
		 * only seen by one CPU before cleared, avoiding duplicates.
		 */
		while (atomic_read(&mce_executing) < order) {
			if (mce_timed_out(&timeout)) {
				atomic_set(&global_nwo, 0);
				return -1;
			}
			ndelay(SPINUNIT);
		}
	}

	/*
	 * Cache the global no_way_out state.
	 */
	*no_way_out = atomic_read(&global_nwo);

	return order;
}

/*
 * Synchronize between CPUs after main scanning loop.
 * This invokes the bulk of the Monarch processing.
 */
static int mce_end(int order)
{
	int ret = -1;
	u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC;

	if (!timeout)
		goto reset;
	if (order < 0)
		goto reset;

	/*
	 * Allow others to run.
	 */
	atomic_inc(&mce_executing);

	if (order == 1) {
		/* CHECKME: Can this race with a parallel hotplug? */
		int cpus = num_online_cpus();

		/*
		 * Monarch: Wait for everyone to go through their scanning
		 * loops.
		 */
		while (atomic_read(&mce_executing) <= cpus) {
			if (mce_timed_out(&timeout))
				goto reset;
			ndelay(SPINUNIT);
		}

		mce_reign();
		barrier();
		ret = 0;
	} else {
		/*
		 * Subject: Wait for Monarch to finish.
		 */
		while (atomic_read(&mce_executing) != 0) {
			if (mce_timed_out(&timeout))
				goto reset;
			ndelay(SPINUNIT);
		}

		/*
		 * Don't reset anything. That's done by the Monarch.
		 */
		return 0;
	}

	/*
	 * Reset all global state.
	 */
reset:
	atomic_set(&global_nwo, 0);
	atomic_set(&mce_callin, 0);
	barrier();

	/*
	 * Let others run again.
	 */
	atomic_set(&mce_executing, 0);
	return ret;
}

/*
 * Check if the address reported by the CPU is in a format we can parse.
 * It would be possible to add code for most other cases, but all would
 * be somewhat complicated (e.g. segment offset would require an instruction
 * parser). So only support physical addresses upto page granuality for now.
 */
static int mce_usable_address(struct mce *m)
{
	if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
		return 0;
	if ((m->misc & 0x3f) > PAGE_SHIFT)
		return 0;
	if (((m->misc >> 6) & 7) != MCM_ADDR_PHYS)
		return 0;
	return 1;
}

static void mce_clear_state(unsigned long *toclear)
{
	int i;

	for (i = 0; i < banks; i++) {
		if (test_bit(i, toclear))
			mce_wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
	}
}

/*
 * The actual machine check handler. This only handles real
 * exceptions when something got corrupted coming in through int 18.
 *
 * This is executed in NMI context not subject to normal locking rules. This
 * implies that most kernel services cannot be safely used. Don't even
 * think about putting a printk in there!
 *
 * On Intel systems this is entered on all CPUs in parallel through
 * MCE broadcast. However some CPUs might be broken beyond repair,
 * so be always careful when synchronizing with others.
 */
void do_machine_check(struct pt_regs *regs, long error_code)
{
	struct mce m, *final;
	int i;
	int worst = 0;
	int severity;
	/*
	 * Establish sequential order between the CPUs entering the machine
	 * check handler.
	 */
	int order;
	/*
	 * If no_way_out gets set, there is no safe way to recover from this
	 * MCE.  If tolerant is cranked up, we'll try anyway.
	 */
	int no_way_out = 0;
	/*
	 * If kill_it gets set, there might be a way to recover from this
	 * error.
	 */
	int kill_it = 0;
	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
	char *msg = "Unknown";

	atomic_inc(&mce_entry);

	__get_cpu_var(mce_exception_count)++;

	if (notify_die(DIE_NMI, "machine check", regs, error_code,
			   18, SIGKILL) == NOTIFY_STOP)
		goto out;
	if (!banks)
		goto out;

	mce_setup(&m);

	m.mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
	no_way_out = mce_no_way_out(&m, &msg);

	final = &__get_cpu_var(mces_seen);
	*final = m;

	barrier();

	/*
	 * When no restart IP must always kill or panic.
	 */
	if (!(m.mcgstatus & MCG_STATUS_RIPV))
		kill_it = 1;

	/*
	 * Go through all the banks in exclusion of the other CPUs.
	 * This way we don't report duplicated events on shared banks
	 * because the first one to see it will clear it.
	 */
	order = mce_start(&no_way_out);
	for (i = 0; i < banks; i++) {
		__clear_bit(i, toclear);
		if (!bank[i])
			continue;

		m.misc = 0;
		m.addr = 0;
		m.bank = i;

		m.status = mce_rdmsrl(MSR_IA32_MC0_STATUS + i*4);
		if ((m.status & MCI_STATUS_VAL) == 0)
			continue;

		/*
		 * Non uncorrected or non signaled errors are handled by
		 * machine_check_poll. Leave them alone, unless this panics.
		 */
		if (!(m.status & (mce_ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
			!no_way_out)
			continue;

		/*
		 * Set taint even when machine check was not enabled.
		 */
		add_taint(TAINT_MACHINE_CHECK);

		severity = mce_severity(&m, tolerant, NULL);

		/*
		 * When machine check was for corrected handler don't touch,
		 * unless we're panicing.
		 */
		if (severity == MCE_KEEP_SEVERITY && !no_way_out)
			continue;
		__set_bit(i, toclear);
		if (severity == MCE_NO_SEVERITY) {
			/*
			 * Machine check event was not enabled. Clear, but
			 * ignore.
			 */
			continue;
		}

		/*
		 * Kill on action required.
		 */
		if (severity == MCE_AR_SEVERITY)
			kill_it = 1;

		if (m.status & MCI_STATUS_MISCV)
			m.misc = mce_rdmsrl(MSR_IA32_MC0_MISC + i*4);
		if (m.status & MCI_STATUS_ADDRV)
			m.addr = mce_rdmsrl(MSR_IA32_MC0_ADDR + i*4);

		/*
		 * Action optional error. Queue address for later processing.
		 * When the ring overflows we just ignore the AO error.
		 * RED-PEN add some logging mechanism when
		 * usable_address or mce_add_ring fails.
		 * RED-PEN don't ignore overflow for tolerant == 0
		 */
		if (severity == MCE_AO_SEVERITY && mce_usable_address(&m))
			mce_ring_add(m.addr >> PAGE_SHIFT);

		mce_get_rip(&m, regs);
		mce_log(&m);

		if (severity > worst) {
			*final = m;
			worst = severity;
		}
	}

	if (!no_way_out)
		mce_clear_state(toclear);

	/*
	 * Do most of the synchronization with other CPUs.
	 * When there's any problem use only local no_way_out state.
	 */
	if (mce_end(order) < 0)
		no_way_out = worst >= MCE_PANIC_SEVERITY;

	/*
	 * If we have decided that we just CAN'T continue, and the user
	 * has not set tolerant to an insane level, give up and die.
	 *
	 * This is mainly used in the case when the system doesn't
	 * support MCE broadcasting or it has been disabled.
	 */
	if (no_way_out && tolerant < 3)
		mce_panic("Fatal machine check on current CPU", final, msg);

	/*
	 * If the error seems to be unrecoverable, something should be
	 * done.  Try to kill as little as possible.  If we can kill just
	 * one task, do that.  If the user has set the tolerance very
	 * high, don't try to do anything at all.
	 */

	if (kill_it && tolerant < 3)
		force_sig(SIGBUS, current);

	/* notify userspace ASAP */
	set_thread_flag(TIF_MCE_NOTIFY);

	if (worst > 0)
		mce_report_event(regs);
	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
out:
	atomic_dec(&mce_entry);
	sync_core();
}
EXPORT_SYMBOL_GPL(do_machine_check);

/* dummy to break dependency. actual code is in mm/memory-failure.c */
void __attribute__((weak)) memory_failure(unsigned long pfn, int vector)
{
	printk(KERN_ERR "Action optional memory failure at %lx ignored\n", pfn);
}

/*
 * Called after mce notification in process context. This code
 * is allowed to sleep. Call the high level VM handler to process
 * any corrupted pages.
 * Assume that the work queue code only calls this one at a time
 * per CPU.
 * Note we don't disable preemption, so this code might run on the wrong
 * CPU. In this case the event is picked up by the scheduled work queue.
 * This is merely a fast path to expedite processing in some common
 * cases.
 */
void mce_notify_process(void)
{
	unsigned long pfn;
	mce_notify_irq();
	while (mce_ring_get(&pfn))
		memory_failure(pfn, MCE_VECTOR);
}

static void mce_process_work(struct work_struct *dummy)
{
	mce_notify_process();
}

#ifdef CONFIG_X86_MCE_INTEL
/***
 * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog
 * @cpu: The CPU on which the event occurred.
 * @status: Event status information
 *
 * This function should be called by the thermal interrupt after the
 * event has been processed and the decision was made to log the event
 * further.
 *
 * The status parameter will be saved to the 'status' field of 'struct mce'
 * and historically has been the register value of the
 * MSR_IA32_THERMAL_STATUS (Intel) msr.
 */
void mce_log_therm_throt_event(__u64 status)
{
	struct mce m;

	mce_setup(&m);
	m.bank = MCE_THERMAL_BANK;
	m.status = status;
	mce_log(&m);
}
#endif /* CONFIG_X86_MCE_INTEL */

/*
 * Periodic polling timer for "silent" machine check errors.  If the
 * poller finds an MCE, poll 2x faster.  When the poller finds no more
 * errors, poll 2x slower (up to check_interval seconds).
 */
static int check_interval = 5 * 60; /* 5 minutes */

static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);

static void mcheck_timer(unsigned long data)
{
	struct timer_list *t = &per_cpu(mce_timer, data);
	int *n;

	WARN_ON(smp_processor_id() != data);

	if (mce_available(&current_cpu_data)) {
		machine_check_poll(MCP_TIMESTAMP,
				&__get_cpu_var(mce_poll_banks));
	}

	/*
	 * Alert userspace if needed.  If we logged an MCE, reduce the
	 * polling interval, otherwise increase the polling interval.
	 */
	n = &__get_cpu_var(next_interval);
	if (mce_notify_irq())
		*n = max(*n/2, HZ/100);
	else
		*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));

	t->expires = jiffies + *n;
	add_timer_on(t, smp_processor_id());
}

static void mce_do_trigger(struct work_struct *work)
{
	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
}

static DECLARE_WORK(mce_trigger_work, mce_do_trigger);

/*
 * Notify the user(s) about new machine check events.
 * Can be called from interrupt context, but not from machine check/NMI
 * context.
 */
int mce_notify_irq(void)
{
	/* Not more than two messages every minute */
	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);

	clear_thread_flag(TIF_MCE_NOTIFY);

	if (test_and_clear_bit(0, &mce_need_notify)) {
		wake_up_interruptible(&mce_wait);

		/*
		 * There is no risk of missing notifications because
		 * work_pending is always cleared before the function is
		 * executed.
		 */
		if (mce_helper[0] && !work_pending(&mce_trigger_work))
			schedule_work(&mce_trigger_work);

		if (__ratelimit(&ratelimit))
			printk(KERN_INFO "Machine check events logged\n");

		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(mce_notify_irq);

/*
 * Initialize Machine Checks for a CPU.
 */
static int mce_cap_init(void)
{
	unsigned b;
	u64 cap;

	rdmsrl(MSR_IA32_MCG_CAP, cap);

	b = cap & MCG_BANKCNT_MASK;
	printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);

	if (b > MAX_NR_BANKS) {
		printk(KERN_WARNING
		       "MCE: Using only %u machine check banks out of %u\n",
			MAX_NR_BANKS, b);
		b = MAX_NR_BANKS;
	}

	/* Don't support asymmetric configurations today */
	WARN_ON(banks != 0 && b != banks);
	banks = b;
	if (!bank) {
		bank = kmalloc(banks * sizeof(u64), GFP_KERNEL);
		if (!bank)
			return -ENOMEM;
		memset(bank, 0xff, banks * sizeof(u64));
	}

	/* Use accurate RIP reporting if available. */
	if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9)
		rip_msr = MSR_IA32_MCG_EIP;

	if (cap & MCG_SER_P)
		mce_ser = 1;

	return 0;
}

static void mce_init(void)
{
	mce_banks_t all_banks;
	u64 cap;
	int i;

	/*
	 * Log the machine checks left over from the previous reset.
	 */
	bitmap_fill(all_banks, MAX_NR_BANKS);
	machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks);

	set_in_cr4(X86_CR4_MCE);

	rdmsrl(MSR_IA32_MCG_CAP, cap);
	if (cap & MCG_CTL_P)
		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);

	for (i = 0; i < banks; i++) {
		if (skip_bank_init(i))
			continue;
		wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
		wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
	}
}

/* Add per CPU specific workarounds here */
static int mce_cpu_quirks(struct cpuinfo_x86 *c)
{
	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
		pr_info("MCE: unknown CPU type - not enabling MCE support.\n");
		return -EOPNOTSUPP;
	}

	/* This should be disabled by the BIOS, but isn't always */
	if (c->x86_vendor == X86_VENDOR_AMD) {
		if (c->x86 == 15 && banks > 4) {
			/*
			 * disable GART TBL walk error reporting, which
			 * trips off incorrectly with the IOMMU & 3ware
			 * & Cerberus:
			 */
			clear_bit(10, (unsigned long *)&bank[4]);
		}
		if (c->x86 <= 17 && mce_bootlog < 0) {
			/*
			 * Lots of broken BIOS around that don't clear them
			 * by default and leave crap in there. Don't log:
			 */
			mce_bootlog = 0;
		}
		/*
		 * Various K7s with broken bank 0 around. Always disable
		 * by default.
		 */
		 if (c->x86 == 6 && banks > 0)
			bank[0] = 0;
	}

	if (c->x86_vendor == X86_VENDOR_INTEL) {
		/*
		 * SDM documents that on family 6 bank 0 should not be written
		 * because it aliases to another special BIOS controlled
		 * register.
		 * But it's not aliased anymore on model 0x1a+
		 * Don't ignore bank 0 completely because there could be a
		 * valid event later, merely don't write CTL0.
		 */

		if (c->x86 == 6 && c->x86_model < 0x1A)
			__set_bit(0, &dont_init_banks);

		/*
		 * All newer Intel systems support MCE broadcasting. Enable
		 * synchronization with a one second timeout.
		 */
		if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
			monarch_timeout < 0)
			monarch_timeout = USEC_PER_SEC;

		/*
		 * There are also broken BIOSes on some Pentium M and
		 * earlier systems:
		 */
		if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
			mce_bootlog = 0;
	}
	if (monarch_timeout < 0)
		monarch_timeout = 0;
	if (mce_bootlog != 0)
		mce_panic_timeout = 30;

	return 0;
}

static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
{
	if (c->x86 != 5)
		return;
	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		intel_p5_mcheck_init(c);
		break;
	case X86_VENDOR_CENTAUR:
		winchip_mcheck_init(c);
		break;
	}
}

static void mce_cpu_features(struct cpuinfo_x86 *c)
{
	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		mce_intel_feature_init(c);
		break;
	case X86_VENDOR_AMD:
		mce_amd_feature_init(c);
		break;
	default:
		break;
	}
}

static void mce_init_timer(void)
{
	struct timer_list *t = &__get_cpu_var(mce_timer);
	int *n = &__get_cpu_var(next_interval);

	if (mce_ignore_ce)
		return;

	*n = check_interval * HZ;
	if (!*n)
		return;
	setup_timer(t, mcheck_timer, smp_processor_id());
	t->expires = round_jiffies(jiffies + *n);
	add_timer_on(t, smp_processor_id());
}

/*
 * Called for each booted CPU to set up machine checks.
 * Must be called with preempt off:
 */
void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
{
	if (mce_disabled)
		return;

	mce_ancient_init(c);

	if (!mce_available(c))
		return;

	if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) {
		mce_disabled = 1;
		return;
	}

	machine_check_vector = do_machine_check;

	mce_init();
	mce_cpu_features(c);
	mce_init_timer();
	INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
}

/*
 * Character device to read and clear the MCE log.
 */

static DEFINE_SPINLOCK(mce_state_lock);
static int		open_count;		/* #times opened */
static int		open_exclu;		/* already open exclusive? */

static int mce_open(struct inode *inode, struct file *file)
{
	spin_lock(&mce_state_lock);

	if (open_exclu || (open_count && (file->f_flags & O_EXCL))) {
		spin_unlock(&mce_state_lock);

		return -EBUSY;
	}

	if (file->f_flags & O_EXCL)
		open_exclu = 1;
	open_count++;

	spin_unlock(&mce_state_lock);

	return nonseekable_open(inode, file);
}

static int mce_release(struct inode *inode, struct file *file)
{
	spin_lock(&mce_state_lock);

	open_count--;
	open_exclu = 0;

	spin_unlock(&mce_state_lock);

	return 0;
}

static void collect_tscs(void *data)
{
	unsigned long *cpu_tsc = (unsigned long *)data;

	rdtscll(cpu_tsc[smp_processor_id()]);
}

static DEFINE_MUTEX(mce_read_mutex);

static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
			loff_t *off)
{
	char __user *buf = ubuf;
	unsigned long *cpu_tsc;
	unsigned prev, next;
	int i, err;

	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
	if (!cpu_tsc)
		return -ENOMEM;

	mutex_lock(&mce_read_mutex);
	next = rcu_dereference(mcelog.next);

	/* Only supports full reads right now */
	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
		mutex_unlock(&mce_read_mutex);
		kfree(cpu_tsc);

		return -EINVAL;
	}

	err = 0;
	prev = 0;
	do {
		for (i = prev; i < next; i++) {
			unsigned long start = jiffies;

			while (!mcelog.entry[i].finished) {
				if (time_after_eq(jiffies, start + 2)) {
					memset(mcelog.entry + i, 0,
					       sizeof(struct mce));
					goto timeout;
				}
				cpu_relax();
			}
			smp_rmb();
			err |= copy_to_user(buf, mcelog.entry + i,
					    sizeof(struct mce));
			buf += sizeof(struct mce);
timeout:
			;
		}

		memset(mcelog.entry + prev, 0,
		       (next - prev) * sizeof(struct mce));
		prev = next;
		next = cmpxchg(&mcelog.next, prev, 0);
	} while (next != prev);

	synchronize_sched();

	/*
	 * Collect entries that were still getting written before the
	 * synchronize.
	 */
	on_each_cpu(collect_tscs, cpu_tsc, 1);

	for (i = next; i < MCE_LOG_LEN; i++) {
		if (mcelog.entry[i].finished &&
		    mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) {
			err |= copy_to_user(buf, mcelog.entry+i,
					    sizeof(struct mce));
			smp_rmb();
			buf += sizeof(struct mce);
			memset(&mcelog.entry[i], 0, sizeof(struct mce));
		}
	}
	mutex_unlock(&mce_read_mutex);
	kfree(cpu_tsc);

	return err ? -EFAULT : buf - ubuf;
}

static unsigned int mce_poll(struct file *file, poll_table *wait)
{
	poll_wait(file, &mce_wait, wait);
	if (rcu_dereference(mcelog.next))
		return POLLIN | POLLRDNORM;
	return 0;
}

static long mce_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
	int __user *p = (int __user *)arg;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	switch (cmd) {
	case MCE_GET_RECORD_LEN:
		return put_user(sizeof(struct mce), p);
	case MCE_GET_LOG_LEN:
		return put_user(MCE_LOG_LEN, p);
	case MCE_GETCLEAR_FLAGS: {
		unsigned flags;

		do {
			flags = mcelog.flags;
		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);

		return put_user(flags, p);
	}
	default:
		return -ENOTTY;
	}
}

/* Modified in mce-inject.c, so not static or const */
struct file_operations mce_chrdev_ops = {
	.open			= mce_open,
	.release		= mce_release,
	.read			= mce_read,
	.poll			= mce_poll,
	.unlocked_ioctl		= mce_ioctl,
};
EXPORT_SYMBOL_GPL(mce_chrdev_ops);

static struct miscdevice mce_log_device = {
	MISC_MCELOG_MINOR,
	"mcelog",
	&mce_chrdev_ops,
};

/*
 * mce=off Disables machine check
 * mce=no_cmci Disables CMCI
 * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
 * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
 * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
 *	monarchtimeout is how long to wait for other CPUs on machine
 *	check, or 0 to not wait
 * mce=bootlog Log MCEs from before booting. Disabled by default on AMD.
 * mce=nobootlog Don't log MCEs from before booting.
 */
static int __init mcheck_enable(char *str)
{
	if (*str == 0)
		enable_p5_mce();
	if (*str == '=')
		str++;
	if (!strcmp(str, "off"))
		mce_disabled = 1;
	else if (!strcmp(str, "no_cmci"))
		mce_cmci_disabled = 1;
	else if (!strcmp(str, "dont_log_ce"))
		mce_dont_log_ce = 1;
	else if (!strcmp(str, "ignore_ce"))
		mce_ignore_ce = 1;
	else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
		mce_bootlog = (str[0] == 'b');
	else if (isdigit(str[0])) {
		get_option(&str, &tolerant);
		if (*str == ',') {
			++str;
			get_option(&str, &monarch_timeout);
		}
	} else {
		printk(KERN_INFO "mce argument %s ignored. Please use /sys\n",
		       str);
		return 0;
	}
	return 1;
}
__setup("mce", mcheck_enable);

/*
 * Sysfs support
 */

/*
 * Disable machine checks on suspend and shutdown. We can't really handle
 * them later.
 */
static int mce_disable(void)
{
	int i;

	for (i = 0; i < banks; i++) {
		if (!skip_bank_init(i))
			wrmsrl(MSR_IA32_MC0_CTL + i*4, 0);
	}
	return 0;
}

static int mce_suspend(struct sys_device *dev, pm_message_t state)
{
	return mce_disable();
}

static int mce_shutdown(struct sys_device *dev)
{
	return mce_disable();
}

/*
 * On resume clear all MCE state. Don't want to see leftovers from the BIOS.
 * Only one CPU is active at this time, the others get re-added later using
 * CPU hotplug:
 */
static int mce_resume(struct sys_device *dev)
{
	mce_init();
	mce_cpu_features(&current_cpu_data);

	return 0;
}

static void mce_cpu_restart(void *data)
{
	del_timer_sync(&__get_cpu_var(mce_timer));
	if (!mce_available(&current_cpu_data))
		return;
	mce_init();
	mce_init_timer();
}

/* Reinit MCEs after user configuration changes */
static void mce_restart(void)
{
	on_each_cpu(mce_cpu_restart, NULL, 1);
}

/* Toggle features for corrected errors */
static void mce_disable_ce(void *all)
{
	if (!mce_available(&current_cpu_data))
		return;
	if (all)
		del_timer_sync(&__get_cpu_var(mce_timer));
	cmci_clear();
}

static void mce_enable_ce(void *all)
{
	if (!mce_available(&current_cpu_data))
		return;
	cmci_reenable();
	cmci_recheck();
	if (all)
		mce_init_timer();
}

static struct sysdev_class mce_sysclass = {
	.suspend	= mce_suspend,
	.shutdown	= mce_shutdown,
	.resume		= mce_resume,
	.name		= "machinecheck",
};

DEFINE_PER_CPU(struct sys_device, mce_dev);

__cpuinitdata
void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);

static struct sysdev_attribute *bank_attrs;

static ssize_t show_bank(struct sys_device *s, struct sysdev_attribute *attr,
			 char *buf)
{
	u64 b = bank[attr - bank_attrs];

	return sprintf(buf, "%llx\n", b);
}

static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr,
			const char *buf, size_t size)
{
	u64 new;

	if (strict_strtoull(buf, 0, &new) < 0)
		return -EINVAL;

	bank[attr - bank_attrs] = new;
	mce_restart();

	return size;
}

static ssize_t
show_trigger(struct sys_device *s, struct sysdev_attribute *attr, char *buf)
{
	strcpy(buf, mce_helper);
	strcat(buf, "\n");
	return strlen(mce_helper) + 1;
}

static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
				const char *buf, size_t siz)
{
	char *p;

	strncpy(mce_helper, buf, sizeof(mce_helper));
	mce_helper[sizeof(mce_helper)-1] = 0;
	p = strchr(mce_helper, '\n');

	if (p)
		*p = 0;

	return strlen(mce_helper) + !!p;
}

static ssize_t set_ignore_ce(struct sys_device *s,
			     struct sysdev_attribute *attr,
			     const char *buf, size_t size)
{
	u64 new;

	if (strict_strtoull(buf, 0, &new) < 0)
		return -EINVAL;

	if (mce_ignore_ce ^ !!new) {
		if (new) {
			/* disable ce features */
			on_each_cpu(mce_disable_ce, (void *)1, 1);
			mce_ignore_ce = 1;
		} else {
			/* enable ce features */
			mce_ignore_ce = 0;
			on_each_cpu(mce_enable_ce, (void *)1, 1);
		}
	}
	return size;
}

static ssize_t set_cmci_disabled(struct sys_device *s,
				 struct sysdev_attribute *attr,
				 const char *buf, size_t size)
{
	u64 new;

	if (strict_strtoull(buf, 0, &new) < 0)
		return -EINVAL;

	if (mce_cmci_disabled ^ !!new) {
		if (new) {
			/* disable cmci */
			on_each_cpu(mce_disable_ce, NULL, 1);
			mce_cmci_disabled = 1;
		} else {
			/* enable cmci */
			mce_cmci_disabled = 0;
			on_each_cpu(mce_enable_ce, NULL, 1);
		}
	}
	return size;
}

static ssize_t store_int_with_restart(struct sys_device *s,
				      struct sysdev_attribute *attr,
				      const char *buf, size_t size)
{
	ssize_t ret = sysdev_store_int(s, attr, buf, size);
	mce_restart();
	return ret;
}

static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
static SYSDEV_INT_ATTR(tolerant, 0644, tolerant);
static SYSDEV_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
static SYSDEV_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);

static struct sysdev_ext_attribute attr_check_interval = {
	_SYSDEV_ATTR(check_interval, 0644, sysdev_show_int,
		     store_int_with_restart),
	&check_interval
};

static struct sysdev_ext_attribute attr_ignore_ce = {
	_SYSDEV_ATTR(ignore_ce, 0644, sysdev_show_int, set_ignore_ce),
	&mce_ignore_ce
};

static struct sysdev_ext_attribute attr_cmci_disabled = {
	_SYSDEV_ATTR(cmci_disabled, 0644, sysdev_show_int, set_cmci_disabled),
	&mce_cmci_disabled
};

static struct sysdev_attribute *mce_attrs[] = {
	&attr_tolerant.attr,
	&attr_check_interval.attr,
	&attr_trigger,
	&attr_monarch_timeout.attr,
	&attr_dont_log_ce.attr,
	&attr_ignore_ce.attr,
	&attr_cmci_disabled.attr,
	NULL
};

static cpumask_var_t mce_dev_initialized;

/* Per cpu sysdev init. All of the cpus still share the same ctrl bank: */
static __cpuinit int mce_create_device(unsigned int cpu)
{
	int err;
	int i, j;

	if (!mce_available(&boot_cpu_data))
		return -EIO;

	memset(&per_cpu(mce_dev, cpu).kobj, 0, sizeof(struct kobject));
	per_cpu(mce_dev, cpu).id	= cpu;
	per_cpu(mce_dev, cpu).cls	= &mce_sysclass;

	err = sysdev_register(&per_cpu(mce_dev, cpu));
	if (err)
		return err;

	for (i = 0; mce_attrs[i]; i++) {
		err = sysdev_create_file(&per_cpu(mce_dev, cpu), mce_attrs[i]);
		if (err)
			goto error;
	}
	for (j = 0; j < banks; j++) {
		err = sysdev_create_file(&per_cpu(mce_dev, cpu),
					&bank_attrs[j]);
		if (err)
			goto error2;
	}
	cpumask_set_cpu(cpu, mce_dev_initialized);

	return 0;
error2:
	while (--j >= 0)
		sysdev_remove_file(&per_cpu(mce_dev, cpu), &bank_attrs[j]);
error:
	while (--i >= 0)
		sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]);

	sysdev_unregister(&per_cpu(mce_dev, cpu));

	return err;
}

static __cpuinit void mce_remove_device(unsigned int cpu)
{
	int i;

	if (!cpumask_test_cpu(cpu, mce_dev_initialized))
		return;

	for (i = 0; mce_attrs[i]; i++)
		sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]);

	for (i = 0; i < banks; i++)
		sysdev_remove_file(&per_cpu(mce_dev, cpu), &bank_attrs[i]);

	sysdev_unregister(&per_cpu(mce_dev, cpu));
	cpumask_clear_cpu(cpu, mce_dev_initialized);
}

/* Make sure there are no machine checks on offlined CPUs. */
static void mce_disable_cpu(void *h)
{
	unsigned long action = *(unsigned long *)h;
	int i;

	if (!mce_available(&current_cpu_data))
		return;
	if (!(action & CPU_TASKS_FROZEN))
		cmci_clear();
	for (i = 0; i < banks; i++) {
		if (!skip_bank_init(i))
			wrmsrl(MSR_IA32_MC0_CTL + i*4, 0);
	}
}

static void mce_reenable_cpu(void *h)
{
	unsigned long action = *(unsigned long *)h;
	int i;

	if (!mce_available(&current_cpu_data))
		return;

	if (!(action & CPU_TASKS_FROZEN))
		cmci_reenable();
	for (i = 0; i < banks; i++) {
		if (!skip_bank_init(i))
			wrmsrl(MSR_IA32_MC0_CTL + i*4, bank[i]);
	}
}

/* Get notified when a cpu comes on/off. Be hotplug friendly. */
static int __cpuinit
mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;
	struct timer_list *t = &per_cpu(mce_timer, cpu);

	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		mce_create_device(cpu);
		if (threshold_cpu_callback)
			threshold_cpu_callback(action, cpu);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		if (threshold_cpu_callback)
			threshold_cpu_callback(action, cpu);
		mce_remove_device(cpu);
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		del_timer_sync(t);
		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
		break;
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		t->expires = round_jiffies(jiffies +
						__get_cpu_var(next_interval));
		add_timer_on(t, cpu);
		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
		break;
	case CPU_POST_DEAD:
		/* intentionally ignoring frozen here */
		cmci_rediscover(cpu);
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block mce_cpu_notifier __cpuinitdata = {
	.notifier_call = mce_cpu_callback,
};

static __init int mce_init_banks(void)
{
	int i;

	bank_attrs = kzalloc(sizeof(struct sysdev_attribute) * banks,
				GFP_KERNEL);
	if (!bank_attrs)
		return -ENOMEM;

	for (i = 0; i < banks; i++) {
		struct sysdev_attribute *a = &bank_attrs[i];

		a->attr.name	= kasprintf(GFP_KERNEL, "bank%d", i);
		if (!a->attr.name)
			goto nomem;

		a->attr.mode	= 0644;
		a->show		= show_bank;
		a->store	= set_bank;
	}
	return 0;

nomem:
	while (--i >= 0)
		kfree(bank_attrs[i].attr.name);
	kfree(bank_attrs);
	bank_attrs = NULL;

	return -ENOMEM;
}

static __init int mce_init_device(void)
{
	int err;
	int i = 0;

	if (!mce_available(&boot_cpu_data))
		return -EIO;

	zalloc_cpumask_var(&mce_dev_initialized, GFP_KERNEL);

	err = mce_init_banks();
	if (err)
		return err;

	err = sysdev_class_register(&mce_sysclass);
	if (err)
		return err;

	for_each_online_cpu(i) {
		err = mce_create_device(i);
		if (err)
			return err;
	}

	register_hotcpu_notifier(&mce_cpu_notifier);
	misc_register(&mce_log_device);

	return err;
}

device_initcall(mce_init_device);

#else /* CONFIG_X86_OLD_MCE: */

int nr_mce_banks;
EXPORT_SYMBOL_GPL(nr_mce_banks);	/* non-fatal.o */

/* This has to be run for each processor */
void mcheck_init(struct cpuinfo_x86 *c)
{
	if (mce_disabled)
		return;

	switch (c->x86_vendor) {
	case X86_VENDOR_AMD:
		amd_mcheck_init(c);
		break;

	case X86_VENDOR_INTEL:
		if (c->x86 == 5)
			intel_p5_mcheck_init(c);
		if (c->x86 == 6)
			intel_p6_mcheck_init(c);
		if (c->x86 == 15)
			intel_p4_mcheck_init(c);
		break;

	case X86_VENDOR_CENTAUR:
		if (c->x86 == 5)
			winchip_mcheck_init(c);
		break;

	default:
		break;
	}
	printk(KERN_INFO "mce: CPU supports %d MCE banks\n", nr_mce_banks);
}

static int __init mcheck_enable(char *str)
{
	mce_p5_enabled = 1;
	return 1;
}
__setup("mce", mcheck_enable);

#endif /* CONFIG_X86_OLD_MCE */

/*
 * Old style boot options parsing. Only for compatibility.
 */
static int __init mcheck_disable(char *str)
{
	mce_disabled = 1;
	return 1;
}
__setup("nomce", mcheck_disable);