summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mcheck/mce.c
blob: 0fef5406f0eb9bec5dbad3c419c5d58cd14c8800 (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
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
/*
 * 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
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/thread_info.h>
#include <linux/capability.h>
#include <linux/miscdevice.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/device.h>
#include <linux/syscore_ops.h>
#include <linux/delay.h>
#include <linux/ctype.h>
#include <linux/sched.h>
#include <linux/sysfs.h>
#include <linux/types.h>
#include <linux/slab.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 <linux/debugfs.h>
#include <linux/irq_work.h>
#include <linux/export.h>
#include <linux/jump_label.h>

#include <asm/intel-family.h>
#include <asm/processor.h>
#include <asm/traps.h>
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/msr.h>

#include "mce-internal.h"

static DEFINE_MUTEX(mce_chrdev_read_mutex);

#define mce_log_get_idx_check(p) \
({ \
	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
			 !lockdep_is_held(&mce_chrdev_read_mutex), \
			 "suspicious mce_log_get_idx_check() usage"); \
	smp_load_acquire(&(p)); \
})

#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>

#define SPINUNIT		100	/* 100ns */

DEFINE_PER_CPU(unsigned, mce_exception_count);

struct mce_bank *mce_banks __read_mostly;
struct mce_vendor_flags mce_flags __read_mostly;

struct mca_config mca_cfg __read_mostly = {
	.bootlog  = -1,
	/*
	 * 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 corr. errors
	 * 3: never panic or SIGBUS, log all errors (for testing only)
	 */
	.tolerant = 1,
	.monarch_timeout = -1
};

/* 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 DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);

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

/*
 * MCA banks polled by the period polling timer for corrected events.
 * With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
 */
DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
};

/*
 * MCA banks controlled through firmware first for corrected errors.
 * This is a global list of banks for which we won't enable CMCI and we
 * won't poll. Firmware controls these banks and is responsible for
 * reporting corrected errors through GHES. Uncorrected/recoverable
 * errors are still notified through a machine check.
 */
mce_banks_t mce_banks_ce_disabled;

static struct work_struct mce_work;
static struct irq_work mce_irq_work;

static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);

/*
 * CPU/chipset specific EDAC code can register a notifier call here to print
 * MCE errors in a human-readable form.
 */
ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);

/* 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();
	/* We hope get_seconds stays lockless */
	m->time = get_seconds();
	m->cpuvendor = boot_cpu_data.x86_vendor;
	m->cpuid = cpuid_eax(1);
	m->socketid = cpu_data(m->extcpu).phys_proc_id;
	m->apicid = cpu_data(m->extcpu).initial_apicid;
	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);

	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
		rdmsrl(MSR_PPIN, m->ppin);
}

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;

	/* Emit the trace record: */
	trace_mce_record(mce);

	if (!mce_gen_pool_add(mce))
		irq_work_queue(&mce_irq_work);

	wmb();
	for (;;) {
		entry = mce_log_get_idx_check(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();

	set_bit(0, &mce_need_notify);
}

void mce_inject_log(struct mce *m)
{
	mutex_lock(&mce_chrdev_read_mutex);
	mce_log(m);
	mutex_unlock(&mce_chrdev_read_mutex);
}
EXPORT_SYMBOL_GPL(mce_inject_log);

static struct notifier_block mce_srao_nb;

static atomic_t num_notifiers;

void mce_register_decode_chain(struct notifier_block *nb)
{
	atomic_inc(&num_notifiers);

	/* Ensure SRAO notifier has the highest priority in the decode chain. */
	if (nb != &mce_srao_nb && nb->priority == INT_MAX)
		nb->priority -= 1;

	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_register_decode_chain);

void mce_unregister_decode_chain(struct notifier_block *nb)
{
	atomic_dec(&num_notifiers);

	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);

static inline u32 ctl_reg(int bank)
{
	return MSR_IA32_MCx_CTL(bank);
}

static inline u32 status_reg(int bank)
{
	return MSR_IA32_MCx_STATUS(bank);
}

static inline u32 addr_reg(int bank)
{
	return MSR_IA32_MCx_ADDR(bank);
}

static inline u32 misc_reg(int bank)
{
	return MSR_IA32_MCx_MISC(bank);
}

static inline u32 smca_ctl_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_CTL(bank);
}

static inline u32 smca_status_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_STATUS(bank);
}

static inline u32 smca_addr_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_ADDR(bank);
}

static inline u32 smca_misc_reg(int bank)
{
	return MSR_AMD64_SMCA_MCx_MISC(bank);
}

struct mca_msr_regs msr_ops = {
	.ctl	= ctl_reg,
	.status	= status_reg,
	.addr	= addr_reg,
	.misc	= misc_reg
};

static void __print_mce(struct mce *m)
{
	pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n",
		 m->extcpu,
		 (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""),
		 m->mcgstatus, m->bank, m->status);

	if (m->ip) {
		pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ",
			!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
			m->cs, m->ip);

		if (m->cs == __KERNEL_CS)
			print_symbol("{%s}", m->ip);
		pr_cont("\n");
	}

	pr_emerg(HW_ERR "TSC %llx ", m->tsc);
	if (m->addr)
		pr_cont("ADDR %llx ", m->addr);
	if (m->misc)
		pr_cont("MISC %llx ", m->misc);

	if (mce_flags.smca) {
		if (m->synd)
			pr_cont("SYND %llx ", m->synd);
		if (m->ipid)
			pr_cont("IPID %llx ", m->ipid);
	}

	pr_cont("\n");
	/*
	 * Note this output is parsed by external tools and old fields
	 * should not be changed.
	 */
	pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
		cpu_data(m->extcpu).microcode);
}

static void print_mce(struct mce *m)
{
	int ret = 0;

	__print_mce(m);

	/*
	 * Print out human-readable details about the MCE error,
	 * (if the CPU has an implementation for that)
	 */
	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
	if (ret == NOTIFY_STOP)
		return;

	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}

#define PANIC_TIMEOUT 5 /* 5 seconds */

static atomic_t mce_panicked;

static int fake_panic;
static atomic_t mce_fake_panicked;

/* 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 = mca_cfg.panic_timeout;
	panic("Panicing machine check CPU died");
}

static void mce_panic(const char *msg, struct mce *final, char *exp)
{
	int apei_err = 0;
	struct llist_node *pending;
	struct mce_evt_llist *l;

	if (!fake_panic) {
		/*
		 * Make sure only one CPU runs in machine check panic
		 */
		if (atomic_inc_return(&mce_panicked) > 1)
			wait_for_panic();
		barrier();

		bust_spinlocks(1);
		console_verbose();
	} else {
		/* Don't log too much for fake panic */
		if (atomic_inc_return(&mce_fake_panicked) > 1)
			return;
	}
	pending = mce_gen_pool_prepare_records();
	/* First print corrected ones that are still unlogged */
	llist_for_each_entry(l, pending, llnode) {
		struct mce *m = &l->mce;
		if (!(m->status & MCI_STATUS_UC)) {
			print_mce(m);
			if (!apei_err)
				apei_err = apei_write_mce(m);
		}
	}
	/* Now print uncorrected but with the final one last */
	llist_for_each_entry(l, pending, llnode) {
		struct mce *m = &l->mce;
		if (!(m->status & MCI_STATUS_UC))
			continue;
		if (!final || mce_cmp(m, final)) {
			print_mce(m);
			if (!apei_err)
				apei_err = apei_write_mce(m);
		}
	}
	if (final) {
		print_mce(final);
		if (!apei_err)
			apei_err = apei_write_mce(final);
	}
	if (cpu_missing)
		pr_emerg(HW_ERR "Some CPUs didn't answer in synchronization\n");
	if (exp)
		pr_emerg(HW_ERR "Machine check: %s\n", exp);
	if (!fake_panic) {
		if (panic_timeout == 0)
			panic_timeout = mca_cfg.panic_timeout;
		panic(msg);
	} else
		pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
}

/* Support code for software error injection */

static int msr_to_offset(u32 msr)
{
	unsigned bank = __this_cpu_read(injectm.bank);

	if (msr == mca_cfg.rip_msr)
		return offsetof(struct mce, ip);
	if (msr == msr_ops.status(bank))
		return offsetof(struct mce, status);
	if (msr == msr_ops.addr(bank))
		return offsetof(struct mce, addr);
	if (msr == msr_ops.misc(bank))
		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 (__this_cpu_read(injectm.finished)) {
		int offset = msr_to_offset(msr);

		if (offset < 0)
			return 0;
		return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
	}

	if (rdmsrl_safe(msr, &v)) {
		WARN_ONCE(1, "mce: Unable to read MSR 0x%x!\n", msr);
		/*
		 * Return zero in case the access faulted. This should
		 * not happen normally but can happen if the CPU does
		 * something weird, or if the code is buggy.
		 */
		v = 0;
	}

	return v;
}

static void mce_wrmsrl(u32 msr, u64 v)
{
	if (__this_cpu_read(injectm.finished)) {
		int offset = msr_to_offset(msr);

		if (offset >= 0)
			*(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
		return;
	}
	wrmsrl(msr, v);
}

/*
 * Collect all global (w.r.t. this processor) status about this machine
 * check into our "mce" struct so that we can use it later to assess
 * the severity of the problem as we read per-bank specific details.
 */
static inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
{
	mce_setup(m);

	m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
	if (regs) {
		/*
		 * Get the address of the instruction at the time of
		 * the machine check error.
		 */
		if (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) {
			m->ip = regs->ip;
			m->cs = regs->cs;

			/*
			 * When in VM86 mode make the cs look like ring 3
			 * always. This is a lie, but it's better than passing
			 * the additional vm86 bit around everywhere.
			 */
			if (v8086_mode(regs))
				m->cs |= 3;
		}
		/* Use accurate RIP reporting if available. */
		if (mca_cfg.rip_msr)
			m->ip = mce_rdmsrl(mca_cfg.rip_msr);
	}
}

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

static void mce_schedule_work(void)
{
	if (!mce_gen_pool_empty())
		schedule_work(&mce_work);
}

static void mce_irq_work_cb(struct irq_work *entry)
{
	mce_notify_irq();
	mce_schedule_work();
}

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;
	}

	irq_work_queue(&mce_irq_work);
}

/*
 * 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 up to 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;

	/* Checks after this one are Intel-specific: */
	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
		return 1;

	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
		return 0;
	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
		return 0;
	return 1;
}

static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
				void *data)
{
	struct mce *mce = (struct mce *)data;
	unsigned long pfn;

	if (!mce)
		return NOTIFY_DONE;

	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
		pfn = mce->addr >> PAGE_SHIFT;
		memory_failure(pfn, MCE_VECTOR, 0);
	}

	return NOTIFY_OK;
}
static struct notifier_block mce_srao_nb = {
	.notifier_call	= srao_decode_notifier,
	.priority = INT_MAX,
};

static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
				void *data)
{
	struct mce *m = (struct mce *)data;

	if (!m)
		return NOTIFY_DONE;

	/*
	 * Run the default notifier if we have only the SRAO
	 * notifier and us registered.
	 */
	if (atomic_read(&num_notifiers) > 2)
		return NOTIFY_DONE;

	__print_mce(m);

	return NOTIFY_DONE;
}

static struct notifier_block mce_default_nb = {
	.notifier_call	= mce_default_notifier,
	/* lowest prio, we want it to run last. */
	.priority	= 0,
};

/*
 * Read ADDR and MISC registers.
 */
static void mce_read_aux(struct mce *m, int i)
{
	if (m->status & MCI_STATUS_MISCV)
		m->misc = mce_rdmsrl(msr_ops.misc(i));

	if (m->status & MCI_STATUS_ADDRV) {
		m->addr = mce_rdmsrl(msr_ops.addr(i));

		/*
		 * Mask the reported address by the reported granularity.
		 */
		if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) {
			u8 shift = MCI_MISC_ADDR_LSB(m->misc);
			m->addr >>= shift;
			m->addr <<= shift;
		}

		/*
		 * Extract [55:<lsb>] where lsb is the least significant
		 * *valid* bit of the address bits.
		 */
		if (mce_flags.smca) {
			u8 lsb = (m->addr >> 56) & 0x3f;

			m->addr &= GENMASK_ULL(55, lsb);
		}
	}

	if (mce_flags.smca) {
		m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));

		if (m->status & MCI_STATUS_SYNDV)
			m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
	}
}

static bool memory_error(struct mce *m)
{
	struct cpuinfo_x86 *c = &boot_cpu_data;

	if (c->x86_vendor == X86_VENDOR_AMD) {
		/* ErrCodeExt[20:16] */
		u8 xec = (m->status >> 16) & 0x1f;

		return (xec == 0x0 || xec == 0x8);
	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
		/*
		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
		 *
		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
		 * indicating a memory error. Bit 8 is used for indicating a
		 * cache hierarchy error. The combination of bit 2 and bit 3
		 * is used for indicating a `generic' cache hierarchy error
		 * But we can't just blindly check the above bits, because if
		 * bit 11 is set, then it is a bus/interconnect error - and
		 * either way the above bits just gives more detail on what
		 * bus/interconnect error happened. Note that bit 12 can be
		 * ignored, as it's the "filter" bit.
		 */
		return (m->status & 0xef80) == BIT(7) ||
		       (m->status & 0xef00) == BIT(8) ||
		       (m->status & 0xeffc) == 0xc;
	}

	return false;
}

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.
 */
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
	bool error_seen = false;
	struct mce m;
	int severity;
	int i;

	this_cpu_inc(mce_poll_count);

	mce_gather_info(&m, NULL);

	if (flags & MCP_TIMESTAMP)
		m.tsc = rdtsc();

	for (i = 0; i < mca_cfg.banks; i++) {
		if (!mce_banks[i].ctl || !test_bit(i, *b))
			continue;

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

		barrier();
		m.status = mce_rdmsrl(msr_ops.status(i));
		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 & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
			continue;

		error_seen = true;

		mce_read_aux(&m, i);

		severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);

		if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
			if (m.status & MCI_STATUS_ADDRV)
				m.severity = severity;

		/*
		 * Don't get the IP here because it's unlikely to
		 * have anything to do with the actual error location.
		 */
		if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce)
			mce_log(&m);
		else if (mce_usable_address(&m)) {
			/*
			 * Although we skipped logging this, we still want
			 * to take action. Add to the pool so the registered
			 * notifiers will see it.
			 */
			if (!mce_gen_pool_add(&m))
				mce_schedule_work();
		}

		/*
		 * Clear state for this bank.
		 */
		mce_wrmsrl(msr_ops.status(i), 0);
	}

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

	sync_core();

	return error_seen;
}
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, unsigned long *validp,
			  struct pt_regs *regs)
{
	int i, ret = 0;
	char *tmp;

	for (i = 0; i < mca_cfg.banks; i++) {
		m->status = mce_rdmsrl(msr_ops.status(i));
		if (m->status & MCI_STATUS_VAL) {
			__set_bit(i, validp);
			if (quirk_no_way_out)
				quirk_no_way_out(i, m, regs);
		}

		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
			*msg = tmp;
			ret = 1;
		}
	}
	return ret;
}

/*
 * 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, const char *msg)
{
	/*
	 * 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_panicked))
		wait_for_panic();
	if (!mca_cfg.monarch_timeout)
		goto out;
	if ((s64)*t < SPINUNIT) {
		if (mca_cfg.tolerant <= 1)
			mce_panic(msg, 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 a 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),
					    mca_cfg.tolerant,
					    &nmsg, true);
		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 && mca_cfg.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 (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3)
		mce_panic("Fatal 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)mca_cfg.monarch_timeout * NSEC_PER_USEC;

	if (!timeout)
		return -1;

	atomic_add(*no_way_out, &global_nwo);
	/*
	 * Rely on the implied barrier below, such that global_nwo
	 * is updated before mce_callin.
	 */
	order = atomic_inc_return(&mce_callin);

	/*
	 * Wait for everyone.
	 */
	while (atomic_read(&mce_callin) != cpus) {
		if (mce_timed_out(&timeout,
				  "Timeout: Not all CPUs entered broadcast exception handler")) {
			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,
					  "Timeout: Subject CPUs unable to finish machine check processing")) {
				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)mca_cfg.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,
					  "Timeout: Monarch CPU unable to finish machine check processing"))
				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,
					  "Timeout: Monarch CPU did not finish machine check processing"))
				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;
}

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

	for (i = 0; i < mca_cfg.banks; i++) {
		if (test_bit(i, toclear))
			mce_wrmsrl(msr_ops.status(i), 0);
	}
}

static int do_memory_failure(struct mce *m)
{
	int flags = MF_ACTION_REQUIRED;
	int ret;

	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
	if (!(m->mcgstatus & MCG_STATUS_RIPV))
		flags |= MF_MUST_KILL;
	ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
	if (ret)
		pr_err("Memory error not recovered");
	return ret;
}

/*
 * 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 mca_config *cfg = &mca_cfg;
	struct mce m, *final;
	int i;
	int worst = 0;
	int severity;

	/*
	 * Establish sequential order between the CPUs entering the machine
	 * check handler.
	 */
	int order = -1;
	/*
	 * If no_way_out gets set, there is no safe way to recover from this
	 * MCE.  If mca_cfg.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);
	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
	char *msg = "Unknown";

	/*
	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
	 * on Intel.
	 */
	int lmce = 1;

	/* If this CPU is offline, just bail out. */
	if (cpu_is_offline(smp_processor_id())) {
		u64 mcgstatus;

		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
		if (mcgstatus & MCG_STATUS_RIPV) {
			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
			return;
		}
	}

	ist_enter(regs);

	this_cpu_inc(mce_exception_count);

	if (!cfg->banks)
		goto out;

	mce_gather_info(&m, regs);
	m.tsc = rdtsc();

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

	memset(valid_banks, 0, sizeof(valid_banks));
	no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs);

	barrier();

	/*
	 * When no restart IP might need to kill or panic.
	 * Assume the worst for now, but if we find the
	 * severity is MCE_AR_SEVERITY we have other options.
	 */
	if (!(m.mcgstatus & MCG_STATUS_RIPV))
		kill_it = 1;

	/*
	 * Check if this MCE is signaled to only this logical processor,
	 * on Intel only.
	 */
	if (m.cpuvendor == X86_VENDOR_INTEL)
		lmce = m.mcgstatus & MCG_STATUS_LMCES;

	/*
	 * Go through all 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. If this is a Local MCE, then no need to
	 * perform rendezvous.
	 */
	if (!lmce)
		order = mce_start(&no_way_out);

	for (i = 0; i < cfg->banks; i++) {
		__clear_bit(i, toclear);
		if (!test_bit(i, valid_banks))
			continue;
		if (!mce_banks[i].ctl)
			continue;

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

		m.status = mce_rdmsrl(msr_ops.status(i));
		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 & (cfg->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, LOCKDEP_NOW_UNRELIABLE);

		severity = mce_severity(&m, cfg->tolerant, NULL, true);

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

		mce_read_aux(&m, i);

		/* assuming valid severity level != 0 */
		m.severity = severity;

		mce_log(&m);

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

	/* mce_clear_state will clear *final, save locally for use later */
	m = *final;

	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 (!lmce) {
		if (mce_end(order) < 0)
			no_way_out = worst >= MCE_PANIC_SEVERITY;
	} else {
		/*
		 * Local MCE skipped calling mce_reign()
		 * If we found a fatal error, we need to panic here.
		 */
		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
			mce_panic("Machine check from unknown source",
				NULL, NULL);
	}

	/*
	 * If tolerant is at an insane level we drop requests to kill
	 * processes and continue even when there is no way out.
	 */
	if (cfg->tolerant == 3)
		kill_it = 0;
	else if (no_way_out)
		mce_panic("Fatal machine check on current CPU", &m, msg);

	if (worst > 0)
		mce_report_event(regs);
	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
out:
	sync_core();

	if (worst != MCE_AR_SEVERITY && !kill_it)
		goto out_ist;

	/* Fault was in user mode and we need to take some action */
	if ((m.cs & 3) == 3) {
		ist_begin_non_atomic(regs);
		local_irq_enable();

		if (kill_it || do_memory_failure(&m))
			force_sig(SIGBUS, current);
		local_irq_disable();
		ist_end_non_atomic();
	} else {
		if (!fixup_exception(regs, X86_TRAP_MC))
			mce_panic("Failed kernel mode recovery", &m, NULL);
	}

out_ist:
	ist_exit(regs);
}
EXPORT_SYMBOL_GPL(do_machine_check);

#ifndef CONFIG_MEMORY_FAILURE
int memory_failure(unsigned long pfn, int vector, int flags)
{
	/* mce_severity() should not hand us an ACTION_REQUIRED error */
	BUG_ON(flags & MF_ACTION_REQUIRED);
	pr_err("Uncorrected memory error in page 0x%lx ignored\n"
	       "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n",
	       pfn);

	return 0;
}
#endif

/*
 * 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 unsigned long check_interval = INITIAL_CHECK_INTERVAL;

static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);

static unsigned long mce_adjust_timer_default(unsigned long interval)
{
	return interval;
}

static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;

static void __restart_timer(struct timer_list *t, unsigned long interval)
{
	unsigned long when = jiffies + interval;
	unsigned long flags;

	local_irq_save(flags);

	if (timer_pending(t)) {
		if (time_before(when, t->expires))
			mod_timer(t, when);
	} else {
		t->expires = round_jiffies(when);
		add_timer_on(t, smp_processor_id());
	}

	local_irq_restore(flags);
}

static void mce_timer_fn(unsigned long data)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);
	int cpu = smp_processor_id();
	unsigned long iv;

	WARN_ON(cpu != data);

	iv = __this_cpu_read(mce_next_interval);

	if (mce_available(this_cpu_ptr(&cpu_info))) {
		machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));

		if (mce_intel_cmci_poll()) {
			iv = mce_adjust_timer(iv);
			goto done;
		}
	}

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

done:
	__this_cpu_write(mce_next_interval, iv);
	__restart_timer(t, iv);
}

/*
 * Ensure that the timer is firing in @interval from now.
 */
void mce_timer_kick(unsigned long interval)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);
	unsigned long iv = __this_cpu_read(mce_next_interval);

	__restart_timer(t, interval);

	if (interval < iv)
		__this_cpu_write(mce_next_interval, interval);
}

/* Must not be called in IRQ context where del_timer_sync() can deadlock */
static void mce_timer_delete_all(void)
{
	int cpu;

	for_each_online_cpu(cpu)
		del_timer_sync(&per_cpu(mce_timer, cpu));
}

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);

	if (test_and_clear_bit(0, &mce_need_notify)) {
		/* wake processes polling /dev/mcelog */
		wake_up_interruptible(&mce_chrdev_wait);

		if (mce_helper[0])
			schedule_work(&mce_trigger_work);

		if (__ratelimit(&ratelimit))
			pr_info(HW_ERR "Machine check events logged\n");

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

static int __mcheck_cpu_mce_banks_init(void)
{
	int i;
	u8 num_banks = mca_cfg.banks;

	mce_banks = kzalloc(num_banks * sizeof(struct mce_bank), GFP_KERNEL);
	if (!mce_banks)
		return -ENOMEM;

	for (i = 0; i < num_banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		b->ctl = -1ULL;
		b->init = 1;
	}
	return 0;
}

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

	rdmsrl(MSR_IA32_MCG_CAP, cap);

	b = cap & MCG_BANKCNT_MASK;
	if (!mca_cfg.banks)
		pr_info("CPU supports %d MCE banks\n", b);

	if (b > MAX_NR_BANKS) {
		pr_warn("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(mca_cfg.banks != 0 && b != mca_cfg.banks);
	mca_cfg.banks = b;

	if (!mce_banks) {
		int err = __mcheck_cpu_mce_banks_init();

		if (err)
			return err;
	}

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

	if (cap & MCG_SER_P)
		mca_cfg.ser = true;

	return 0;
}

static void __mcheck_cpu_init_generic(void)
{
	enum mcp_flags m_fl = 0;
	mce_banks_t all_banks;
	u64 cap;

	if (!mca_cfg.bootlog)
		m_fl = MCP_DONTLOG;

	/*
	 * Log the machine checks left over from the previous reset.
	 */
	bitmap_fill(all_banks, MAX_NR_BANKS);
	machine_check_poll(MCP_UC | m_fl, &all_banks);

	cr4_set_bits(X86_CR4_MCE);

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

static void __mcheck_cpu_init_clear_banks(void)
{
	int i;

	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		if (!b->init)
			continue;
		wrmsrl(msr_ops.ctl(i), b->ctl);
		wrmsrl(msr_ops.status(i), 0);
	}
}

/*
 * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
 * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
 * Vol 3B Table 15-20). But this confuses both the code that determines
 * whether the machine check occurred in kernel or user mode, and also
 * the severity assessment code. Pretend that EIPV was set, and take the
 * ip/cs values from the pt_regs that mce_gather_info() ignored earlier.
 */
static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
{
	if (bank != 0)
		return;
	if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0)
		return;
	if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC|
		          MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV|
			  MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR|
			  MCACOD)) !=
			 (MCI_STATUS_UC|MCI_STATUS_EN|
			  MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S|
			  MCI_STATUS_AR|MCACOD_INSTR))
		return;

	m->mcgstatus |= MCG_STATUS_EIPV;
	m->ip = regs->ip;
	m->cs = regs->cs;
}

/* Add per CPU specific workarounds here */
static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
{
	struct mca_config *cfg = &mca_cfg;

	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
		pr_info("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 && cfg->banks > 4) {
			/*
			 * disable GART TBL walk error reporting, which
			 * trips off incorrectly with the IOMMU & 3ware
			 * & Cerberus:
			 */
			clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
		}
		if (c->x86 < 17 && cfg->bootlog < 0) {
			/*
			 * Lots of broken BIOS around that don't clear them
			 * by default and leave crap in there. Don't log:
			 */
			cfg->bootlog = 0;
		}
		/*
		 * Various K7s with broken bank 0 around. Always disable
		 * by default.
		 */
		if (c->x86 == 6 && cfg->banks > 0)
			mce_banks[0].ctl = 0;

		/*
		 * overflow_recov is supported for F15h Models 00h-0fh
		 * even though we don't have a CPUID bit for it.
		 */
		if (c->x86 == 0x15 && c->x86_model <= 0xf)
			mce_flags.overflow_recov = 1;

		/*
		 * Turn off MC4_MISC thresholding banks on those models since
		 * they're not supported there.
		 */
		if (c->x86 == 0x15 &&
		    (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) {
			int i;
			u64 hwcr;
			bool need_toggle;
			u32 msrs[] = {
				0x00000413, /* MC4_MISC0 */
				0xc0000408, /* MC4_MISC1 */
			};

			rdmsrl(MSR_K7_HWCR, hwcr);

			/* McStatusWrEn has to be set */
			need_toggle = !(hwcr & BIT(18));

			if (need_toggle)
				wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));

			/* Clear CntP bit safely */
			for (i = 0; i < ARRAY_SIZE(msrs); i++)
				msr_clear_bit(msrs[i], 62);

			/* restore old settings */
			if (need_toggle)
				wrmsrl(MSR_K7_HWCR, hwcr);
		}
	}

	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 && cfg->banks > 0)
			mce_banks[0].init = 0;

		/*
		 * 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)) &&
			cfg->monarch_timeout < 0)
			cfg->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 && cfg->bootlog < 0)
			cfg->bootlog = 0;

		if (c->x86 == 6 && c->x86_model == 45)
			quirk_no_way_out = quirk_sandybridge_ifu;
	}
	if (cfg->monarch_timeout < 0)
		cfg->monarch_timeout = 0;
	if (cfg->bootlog != 0)
		cfg->panic_timeout = 30;

	return 0;
}

static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
{
	if (c->x86 != 5)
		return 0;

	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		intel_p5_mcheck_init(c);
		return 1;
		break;
	case X86_VENDOR_CENTAUR:
		winchip_mcheck_init(c);
		return 1;
		break;
	default:
		return 0;
	}

	return 0;
}

static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
{
	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		mce_intel_feature_init(c);
		mce_adjust_timer = cmci_intel_adjust_timer;
		break;

	case X86_VENDOR_AMD: {
		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);

		/*
		 * Install proper ops for Scalable MCA enabled processors
		 */
		if (mce_flags.smca) {
			msr_ops.ctl	= smca_ctl_reg;
			msr_ops.status	= smca_status_reg;
			msr_ops.addr	= smca_addr_reg;
			msr_ops.misc	= smca_misc_reg;
		}
		mce_amd_feature_init(c);

		break;
		}

	default:
		break;
	}
}

static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
{
	switch (c->x86_vendor) {
	case X86_VENDOR_INTEL:
		mce_intel_feature_clear(c);
		break;
	default:
		break;
	}
}

static void mce_start_timer(unsigned int cpu, struct timer_list *t)
{
	unsigned long iv = check_interval * HZ;

	if (mca_cfg.ignore_ce || !iv)
		return;

	per_cpu(mce_next_interval, cpu) = iv;

	t->expires = round_jiffies(jiffies + iv);
	add_timer_on(t, cpu);
}

static void __mcheck_cpu_setup_timer(void)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);
	unsigned int cpu = smp_processor_id();

	setup_pinned_timer(t, mce_timer_fn, cpu);
}

static void __mcheck_cpu_init_timer(void)
{
	struct timer_list *t = this_cpu_ptr(&mce_timer);
	unsigned int cpu = smp_processor_id();

	setup_pinned_timer(t, mce_timer_fn, cpu);
	mce_start_timer(cpu, t);
}

/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
	pr_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;

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

	if (__mcheck_cpu_ancient_init(c))
		return;

	if (!mce_available(c))
		return;

	if (__mcheck_cpu_cap_init() < 0 || __mcheck_cpu_apply_quirks(c) < 0) {
		mca_cfg.disabled = true;
		return;
	}

	if (mce_gen_pool_init()) {
		mca_cfg.disabled = true;
		pr_emerg("Couldn't allocate MCE records pool!\n");
		return;
	}

	machine_check_vector = do_machine_check;

	__mcheck_cpu_init_generic();
	__mcheck_cpu_init_vendor(c);
	__mcheck_cpu_init_clear_banks();
	__mcheck_cpu_setup_timer();
}

/*
 * Called for each booted CPU to clear some machine checks opt-ins
 */
void mcheck_cpu_clear(struct cpuinfo_x86 *c)
{
	if (mca_cfg.disabled)
		return;

	if (!mce_available(c))
		return;

	/*
	 * Possibly to clear general settings generic to x86
	 * __mcheck_cpu_clear_generic(c);
	 */
	__mcheck_cpu_clear_vendor(c);

}

/*
 * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
 */

static DEFINE_SPINLOCK(mce_chrdev_state_lock);
static int mce_chrdev_open_count;	/* #times opened */
static int mce_chrdev_open_exclu;	/* already open exclusive? */

static int mce_chrdev_open(struct inode *inode, struct file *file)
{
	spin_lock(&mce_chrdev_state_lock);

	if (mce_chrdev_open_exclu ||
	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
		spin_unlock(&mce_chrdev_state_lock);

		return -EBUSY;
	}

	if (file->f_flags & O_EXCL)
		mce_chrdev_open_exclu = 1;
	mce_chrdev_open_count++;

	spin_unlock(&mce_chrdev_state_lock);

	return nonseekable_open(inode, file);
}

static int mce_chrdev_release(struct inode *inode, struct file *file)
{
	spin_lock(&mce_chrdev_state_lock);

	mce_chrdev_open_count--;
	mce_chrdev_open_exclu = 0;

	spin_unlock(&mce_chrdev_state_lock);

	return 0;
}

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

	cpu_tsc[smp_processor_id()] = rdtsc();
}

static int mce_apei_read_done;

/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
static int __mce_read_apei(char __user **ubuf, size_t usize)
{
	int rc;
	u64 record_id;
	struct mce m;

	if (usize < sizeof(struct mce))
		return -EINVAL;

	rc = apei_read_mce(&m, &record_id);
	/* Error or no more MCE record */
	if (rc <= 0) {
		mce_apei_read_done = 1;
		/*
		 * When ERST is disabled, mce_chrdev_read() should return
		 * "no record" instead of "no device."
		 */
		if (rc == -ENODEV)
			return 0;
		return rc;
	}
	rc = -EFAULT;
	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
		return rc;
	/*
	 * In fact, we should have cleared the record after that has
	 * been flushed to the disk or sent to network in
	 * /sbin/mcelog, but we have no interface to support that now,
	 * so just clear it to avoid duplication.
	 */
	rc = apei_clear_mce(record_id);
	if (rc) {
		mce_apei_read_done = 1;
		return rc;
	}
	*ubuf += sizeof(struct mce);

	return 0;
}

static ssize_t mce_chrdev_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_chrdev_read_mutex);

	if (!mce_apei_read_done) {
		err = __mce_read_apei(&buf, usize);
		if (err || buf != ubuf)
			goto out;
	}

	next = mce_log_get_idx_check(mcelog.next);

	/* Only supports full reads right now */
	err = -EINVAL;
	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
		goto out;

	err = 0;
	prev = 0;
	do {
		for (i = prev; i < next; i++) {
			unsigned long start = jiffies;
			struct mce *m = &mcelog.entry[i];

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

		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
			err |= copy_to_user(buf, m, sizeof(*m));
			smp_rmb();
			buf += sizeof(*m);
			memset(m, 0, sizeof(*m));
		}
	}

	if (err)
		err = -EFAULT;

out:
	mutex_unlock(&mce_chrdev_read_mutex);
	kfree(cpu_tsc);

	return err ? err : buf - ubuf;
}

static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
{
	poll_wait(file, &mce_chrdev_wait, wait);
	if (READ_ONCE(mcelog.next))
		return POLLIN | POLLRDNORM;
	if (!mce_apei_read_done && apei_check_mce())
		return POLLIN | POLLRDNORM;
	return 0;
}

static long mce_chrdev_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;
	}
}

static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
			    size_t usize, loff_t *off);

void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
			     const char __user *ubuf,
			     size_t usize, loff_t *off))
{
	mce_write = fn;
}
EXPORT_SYMBOL_GPL(register_mce_write_callback);

static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
				size_t usize, loff_t *off)
{
	if (mce_write)
		return mce_write(filp, ubuf, usize, off);
	else
		return -EINVAL;
}

static const struct file_operations mce_chrdev_ops = {
	.open			= mce_chrdev_open,
	.release		= mce_chrdev_release,
	.read			= mce_chrdev_read,
	.write			= mce_chrdev_write,
	.poll			= mce_chrdev_poll,
	.unlocked_ioctl		= mce_chrdev_ioctl,
	.llseek			= no_llseek,
};

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

static void __mce_disable_bank(void *arg)
{
	int bank = *((int *)arg);
	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
	cmci_disable_bank(bank);
}

void mce_disable_bank(int bank)
{
	if (bank >= mca_cfg.banks) {
		pr_warn(FW_BUG
			"Ignoring request to disable invalid MCA bank %d.\n",
			bank);
		return;
	}
	set_bit(bank, mce_banks_ce_disabled);
	on_each_cpu(__mce_disable_bank, &bank, 1);
}

/*
 * mce=off Disables machine check
 * mce=no_cmci Disables CMCI
 * mce=no_lmce Disables LMCE
 * 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.
 * mce=bios_cmci_threshold Don't program the CMCI threshold
 * mce=recovery force enable memcpy_mcsafe()
 */
static int __init mcheck_enable(char *str)
{
	struct mca_config *cfg = &mca_cfg;

	if (*str == 0) {
		enable_p5_mce();
		return 1;
	}
	if (*str == '=')
		str++;
	if (!strcmp(str, "off"))
		cfg->disabled = true;
	else if (!strcmp(str, "no_cmci"))
		cfg->cmci_disabled = true;
	else if (!strcmp(str, "no_lmce"))
		cfg->lmce_disabled = true;
	else if (!strcmp(str, "dont_log_ce"))
		cfg->dont_log_ce = true;
	else if (!strcmp(str, "ignore_ce"))
		cfg->ignore_ce = true;
	else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
		cfg->bootlog = (str[0] == 'b');
	else if (!strcmp(str, "bios_cmci_threshold"))
		cfg->bios_cmci_threshold = true;
	else if (!strcmp(str, "recovery"))
		cfg->recovery = true;
	else if (isdigit(str[0])) {
		if (get_option(&str, &cfg->tolerant) == 2)
			get_option(&str, &(cfg->monarch_timeout));
	} else {
		pr_info("mce argument %s ignored. Please use /sys\n", str);
		return 0;
	}
	return 1;
}
__setup("mce", mcheck_enable);

int __init mcheck_init(void)
{
	mcheck_intel_therm_init();
	mce_register_decode_chain(&mce_srao_nb);
	mce_register_decode_chain(&mce_default_nb);
	mcheck_vendor_init_severity();

	INIT_WORK(&mce_work, mce_gen_pool_process);
	init_irq_work(&mce_irq_work, mce_irq_work_cb);

	return 0;
}

/*
 * mce_syscore: PM support
 */

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

	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		if (b->init)
			wrmsrl(msr_ops.ctl(i), 0);
	}
	return;
}

static void vendor_disable_error_reporting(void)
{
	/*
	 * Don't clear on Intel CPUs. Some of these MSRs are socket-wide.
	 * Disabling them for just a single offlined CPU is bad, since it will
	 * inhibit reporting for all shared resources on the socket like the
	 * last level cache (LLC), the integrated memory controller (iMC), etc.
	 */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
		return;

	mce_disable_error_reporting();
}

static int mce_syscore_suspend(void)
{
	vendor_disable_error_reporting();
	return 0;
}

static void mce_syscore_shutdown(void)
{
	vendor_disable_error_reporting();
}

/*
 * 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 void mce_syscore_resume(void)
{
	__mcheck_cpu_init_generic();
	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
	__mcheck_cpu_init_clear_banks();
}

static struct syscore_ops mce_syscore_ops = {
	.suspend	= mce_syscore_suspend,
	.shutdown	= mce_syscore_shutdown,
	.resume		= mce_syscore_resume,
};

/*
 * mce_device: Sysfs support
 */

static void mce_cpu_restart(void *data)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;
	__mcheck_cpu_init_generic();
	__mcheck_cpu_init_clear_banks();
	__mcheck_cpu_init_timer();
}

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

/* Toggle features for corrected errors */
static void mce_disable_cmci(void *data)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;
	cmci_clear();
}

static void mce_enable_ce(void *all)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;
	cmci_reenable();
	cmci_recheck();
	if (all)
		__mcheck_cpu_init_timer();
}

static struct bus_type mce_subsys = {
	.name		= "machinecheck",
	.dev_name	= "machinecheck",
};

DEFINE_PER_CPU(struct device *, mce_device);

static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
{
	return container_of(attr, struct mce_bank, attr);
}

static ssize_t show_bank(struct device *s, struct device_attribute *attr,
			 char *buf)
{
	return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
}

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

	if (kstrtou64(buf, 0, &new) < 0)
		return -EINVAL;

	attr_to_bank(attr)->ctl = new;
	mce_restart();

	return size;
}

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

static ssize_t set_trigger(struct device *s, struct device_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 device *s,
			     struct device_attribute *attr,
			     const char *buf, size_t size)
{
	u64 new;

	if (kstrtou64(buf, 0, &new) < 0)
		return -EINVAL;

	if (mca_cfg.ignore_ce ^ !!new) {
		if (new) {
			/* disable ce features */
			mce_timer_delete_all();
			on_each_cpu(mce_disable_cmci, NULL, 1);
			mca_cfg.ignore_ce = true;
		} else {
			/* enable ce features */
			mca_cfg.ignore_ce = false;
			on_each_cpu(mce_enable_ce, (void *)1, 1);
		}
	}
	return size;
}

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

	if (kstrtou64(buf, 0, &new) < 0)
		return -EINVAL;

	if (mca_cfg.cmci_disabled ^ !!new) {
		if (new) {
			/* disable cmci */
			on_each_cpu(mce_disable_cmci, NULL, 1);
			mca_cfg.cmci_disabled = true;
		} else {
			/* enable cmci */
			mca_cfg.cmci_disabled = false;
			on_each_cpu(mce_enable_ce, NULL, 1);
		}
	}
	return size;
}

static ssize_t store_int_with_restart(struct device *s,
				      struct device_attribute *attr,
				      const char *buf, size_t size)
{
	ssize_t ret = device_store_int(s, attr, buf, size);
	mce_restart();
	return ret;
}

static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);

static struct dev_ext_attribute dev_attr_check_interval = {
	__ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
	&check_interval
};

static struct dev_ext_attribute dev_attr_ignore_ce = {
	__ATTR(ignore_ce, 0644, device_show_bool, set_ignore_ce),
	&mca_cfg.ignore_ce
};

static struct dev_ext_attribute dev_attr_cmci_disabled = {
	__ATTR(cmci_disabled, 0644, device_show_bool, set_cmci_disabled),
	&mca_cfg.cmci_disabled
};

static struct device_attribute *mce_device_attrs[] = {
	&dev_attr_tolerant.attr,
	&dev_attr_check_interval.attr,
	&dev_attr_trigger,
	&dev_attr_monarch_timeout.attr,
	&dev_attr_dont_log_ce.attr,
	&dev_attr_ignore_ce.attr,
	&dev_attr_cmci_disabled.attr,
	NULL
};

static cpumask_var_t mce_device_initialized;

static void mce_device_release(struct device *dev)
{
	kfree(dev);
}

/* Per cpu device init. All of the cpus still share the same ctrl bank: */
static int mce_device_create(unsigned int cpu)
{
	struct device *dev;
	int err;
	int i, j;

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

	dev = per_cpu(mce_device, cpu);
	if (dev)
		return 0;

	dev = kzalloc(sizeof *dev, GFP_KERNEL);
	if (!dev)
		return -ENOMEM;
	dev->id  = cpu;
	dev->bus = &mce_subsys;
	dev->release = &mce_device_release;

	err = device_register(dev);
	if (err) {
		put_device(dev);
		return err;
	}

	for (i = 0; mce_device_attrs[i]; i++) {
		err = device_create_file(dev, mce_device_attrs[i]);
		if (err)
			goto error;
	}
	for (j = 0; j < mca_cfg.banks; j++) {
		err = device_create_file(dev, &mce_banks[j].attr);
		if (err)
			goto error2;
	}
	cpumask_set_cpu(cpu, mce_device_initialized);
	per_cpu(mce_device, cpu) = dev;

	return 0;
error2:
	while (--j >= 0)
		device_remove_file(dev, &mce_banks[j].attr);
error:
	while (--i >= 0)
		device_remove_file(dev, mce_device_attrs[i]);

	device_unregister(dev);

	return err;
}

static void mce_device_remove(unsigned int cpu)
{
	struct device *dev = per_cpu(mce_device, cpu);
	int i;

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

	for (i = 0; mce_device_attrs[i]; i++)
		device_remove_file(dev, mce_device_attrs[i]);

	for (i = 0; i < mca_cfg.banks; i++)
		device_remove_file(dev, &mce_banks[i].attr);

	device_unregister(dev);
	cpumask_clear_cpu(cpu, mce_device_initialized);
	per_cpu(mce_device, cpu) = NULL;
}

/* Make sure there are no machine checks on offlined CPUs. */
static void mce_disable_cpu(void)
{
	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;

	if (!cpuhp_tasks_frozen)
		cmci_clear();

	vendor_disable_error_reporting();
}

static void mce_reenable_cpu(void)
{
	int i;

	if (!mce_available(raw_cpu_ptr(&cpu_info)))
		return;

	if (!cpuhp_tasks_frozen)
		cmci_reenable();
	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];

		if (b->init)
			wrmsrl(msr_ops.ctl(i), b->ctl);
	}
}

static int mce_cpu_dead(unsigned int cpu)
{
	mce_intel_hcpu_update(cpu);

	/* intentionally ignoring frozen here */
	if (!cpuhp_tasks_frozen)
		cmci_rediscover();
	return 0;
}

static int mce_cpu_online(unsigned int cpu)
{
	struct timer_list *t = &per_cpu(mce_timer, cpu);
	int ret;

	mce_device_create(cpu);

	ret = mce_threshold_create_device(cpu);
	if (ret) {
		mce_device_remove(cpu);
		return ret;
	}
	mce_reenable_cpu();
	mce_start_timer(cpu, t);
	return 0;
}

static int mce_cpu_pre_down(unsigned int cpu)
{
	struct timer_list *t = &per_cpu(mce_timer, cpu);

	mce_disable_cpu();
	del_timer_sync(t);
	mce_threshold_remove_device(cpu);
	mce_device_remove(cpu);
	return 0;
}

static __init void mce_init_banks(void)
{
	int i;

	for (i = 0; i < mca_cfg.banks; i++) {
		struct mce_bank *b = &mce_banks[i];
		struct device_attribute *a = &b->attr;

		sysfs_attr_init(&a->attr);
		a->attr.name	= b->attrname;
		snprintf(b->attrname, ATTR_LEN, "bank%d", i);

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

static __init int mcheck_init_device(void)
{
	enum cpuhp_state hp_online;
	int err;

	if (!mce_available(&boot_cpu_data)) {
		err = -EIO;
		goto err_out;
	}

	if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) {
		err = -ENOMEM;
		goto err_out;
	}

	mce_init_banks();

	err = subsys_system_register(&mce_subsys, NULL);
	if (err)
		goto err_out_mem;

	err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL,
				mce_cpu_dead);
	if (err)
		goto err_out_mem;

	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
				mce_cpu_online, mce_cpu_pre_down);
	if (err < 0)
		goto err_out_online;
	hp_online = err;

	register_syscore_ops(&mce_syscore_ops);

	/* register character device /dev/mcelog */
	err = misc_register(&mce_chrdev_device);
	if (err)
		goto err_register;

	return 0;

err_register:
	unregister_syscore_ops(&mce_syscore_ops);
	cpuhp_remove_state(hp_online);

err_out_online:
	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);

err_out_mem:
	free_cpumask_var(mce_device_initialized);

err_out:
	pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);

	return err;
}
device_initcall_sync(mcheck_init_device);

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

#ifdef CONFIG_DEBUG_FS
struct dentry *mce_get_debugfs_dir(void)
{
	static struct dentry *dmce;

	if (!dmce)
		dmce = debugfs_create_dir("mce", NULL);

	return dmce;
}

static void mce_reset(void)
{
	cpu_missing = 0;
	atomic_set(&mce_fake_panicked, 0);
	atomic_set(&mce_executing, 0);
	atomic_set(&mce_callin, 0);
	atomic_set(&global_nwo, 0);
}

static int fake_panic_get(void *data, u64 *val)
{
	*val = fake_panic;
	return 0;
}

static int fake_panic_set(void *data, u64 val)
{
	mce_reset();
	fake_panic = val;
	return 0;
}

DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get,
			fake_panic_set, "%llu\n");

static int __init mcheck_debugfs_init(void)
{
	struct dentry *dmce, *ffake_panic;

	dmce = mce_get_debugfs_dir();
	if (!dmce)
		return -ENOMEM;
	ffake_panic = debugfs_create_file("fake_panic", 0444, dmce, NULL,
					  &fake_panic_fops);
	if (!ffake_panic)
		return -ENOMEM;

	return 0;
}
#else
static int __init mcheck_debugfs_init(void) { return -EINVAL; }
#endif

DEFINE_STATIC_KEY_FALSE(mcsafe_key);
EXPORT_SYMBOL_GPL(mcsafe_key);

static int __init mcheck_late_init(void)
{
	if (mca_cfg.recovery)
		static_branch_inc(&mcsafe_key);

	mcheck_debugfs_init();

	/*
	 * Flush out everything that has been logged during early boot, now that
	 * everything has been initialized (workqueues, decoders, ...).
	 */
	mce_schedule_work();

	return 0;
}
late_initcall(mcheck_late_init);