summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mce/amd.c
blob: b3a50d962851cec722df10623dbc90e6a3f16985 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  (c) 2005-2016 Advanced Micro Devices, Inc.
 *
 *  Written by Jacob Shin - AMD, Inc.
 *  Maintained by: Borislav Petkov <bp@alien8.de>
 *
 *  All MC4_MISCi registers are shared between cores on a node.
 */
#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <linux/kobject.h>
#include <linux/percpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/string.h>

#include <asm/amd_nb.h>
#include <asm/traps.h>
#include <asm/apic.h>
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/trace/irq_vectors.h>

#include "internal.h"

#define NR_BLOCKS         5
#define THRESHOLD_MAX     0xFFF
#define INT_TYPE_APIC     0x00020000
#define MASK_VALID_HI     0x80000000
#define MASK_CNTP_HI      0x40000000
#define MASK_LOCKED_HI    0x20000000
#define MASK_LVTOFF_HI    0x00F00000
#define MASK_COUNT_EN_HI  0x00080000
#define MASK_INT_TYPE_HI  0x00060000
#define MASK_OVERFLOW_HI  0x00010000
#define MASK_ERR_COUNT_HI 0x00000FFF
#define MASK_BLKPTR_LO    0xFF000000
#define MCG_XBLK_ADDR     0xC0000400

/* Deferred error settings */
#define MSR_CU_DEF_ERR		0xC0000410
#define MASK_DEF_LVTOFF		0x000000F0
#define MASK_DEF_INT_TYPE	0x00000006
#define DEF_LVT_OFF		0x2
#define DEF_INT_TYPE_APIC	0x2

/* Scalable MCA: */

/* Threshold LVT offset is at MSR0xC0000410[15:12] */
#define SMCA_THR_LVT_OFF	0xF000

static bool thresholding_irq_en;

static const char * const th_names[] = {
	"load_store",
	"insn_fetch",
	"combined_unit",
	"decode_unit",
	"northbridge",
	"execution_unit",
};

static const char * const smca_umc_block_names[] = {
	"dram_ecc",
	"misc_umc"
};

struct smca_bank_name {
	const char *name;	/* Short name for sysfs */
	const char *long_name;	/* Long name for pretty-printing */
};

static struct smca_bank_name smca_names[] = {
	[SMCA_LS]	= { "load_store",	"Load Store Unit" },
	[SMCA_LS_V2]	= { "load_store",	"Load Store Unit" },
	[SMCA_IF]	= { "insn_fetch",	"Instruction Fetch Unit" },
	[SMCA_L2_CACHE]	= { "l2_cache",		"L2 Cache" },
	[SMCA_DE]	= { "decode_unit",	"Decode Unit" },
	[SMCA_RESERVED]	= { "reserved",		"Reserved" },
	[SMCA_EX]	= { "execution_unit",	"Execution Unit" },
	[SMCA_FP]	= { "floating_point",	"Floating Point Unit" },
	[SMCA_L3_CACHE]	= { "l3_cache",		"L3 Cache" },
	[SMCA_CS]	= { "coherent_slave",	"Coherent Slave" },
	[SMCA_CS_V2]	= { "coherent_slave",	"Coherent Slave" },
	[SMCA_PIE]	= { "pie",		"Power, Interrupts, etc." },
	[SMCA_UMC]	= { "umc",		"Unified Memory Controller" },
	[SMCA_PB]	= { "param_block",	"Parameter Block" },
	[SMCA_PSP]	= { "psp",		"Platform Security Processor" },
	[SMCA_PSP_V2]	= { "psp",		"Platform Security Processor" },
	[SMCA_SMU]	= { "smu",		"System Management Unit" },
	[SMCA_SMU_V2]	= { "smu",		"System Management Unit" },
	[SMCA_MP5]	= { "mp5",		"Microprocessor 5 Unit" },
	[SMCA_NBIO]	= { "nbio",		"Northbridge IO Unit" },
	[SMCA_PCIE]	= { "pcie",		"PCI Express Unit" },
};

static const char *smca_get_name(enum smca_bank_types t)
{
	if (t >= N_SMCA_BANK_TYPES)
		return NULL;

	return smca_names[t].name;
}

const char *smca_get_long_name(enum smca_bank_types t)
{
	if (t >= N_SMCA_BANK_TYPES)
		return NULL;

	return smca_names[t].long_name;
}
EXPORT_SYMBOL_GPL(smca_get_long_name);

static enum smca_bank_types smca_get_bank_type(unsigned int bank)
{
	struct smca_bank *b;

	if (bank >= MAX_NR_BANKS)
		return N_SMCA_BANK_TYPES;

	b = &smca_banks[bank];
	if (!b->hwid)
		return N_SMCA_BANK_TYPES;

	return b->hwid->bank_type;
}

static struct smca_hwid smca_hwid_mcatypes[] = {
	/* { bank_type, hwid_mcatype, xec_bitmap } */

	/* Reserved type */
	{ SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 },

	/* ZN Core (HWID=0xB0) MCA types */
	{ SMCA_LS,	 HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF },
	{ SMCA_LS_V2,	 HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF },
	{ SMCA_IF,	 HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
	{ SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF },
	{ SMCA_DE,	 HWID_MCATYPE(0xB0, 0x3), 0x1FF },
	/* HWID 0xB0 MCATYPE 0x4 is Reserved */
	{ SMCA_EX,	 HWID_MCATYPE(0xB0, 0x5), 0xFFF },
	{ SMCA_FP,	 HWID_MCATYPE(0xB0, 0x6), 0x7F },
	{ SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7), 0xFF },

	/* Data Fabric MCA types */
	{ SMCA_CS,	 HWID_MCATYPE(0x2E, 0x0), 0x1FF },
	{ SMCA_PIE,	 HWID_MCATYPE(0x2E, 0x1), 0x1F },
	{ SMCA_CS_V2,	 HWID_MCATYPE(0x2E, 0x2), 0x3FFF },

	/* Unified Memory Controller MCA type */
	{ SMCA_UMC,	 HWID_MCATYPE(0x96, 0x0), 0xFF },

	/* Parameter Block MCA type */
	{ SMCA_PB,	 HWID_MCATYPE(0x05, 0x0), 0x1 },

	/* Platform Security Processor MCA type */
	{ SMCA_PSP,	 HWID_MCATYPE(0xFF, 0x0), 0x1 },
	{ SMCA_PSP_V2,	 HWID_MCATYPE(0xFF, 0x1), 0x3FFFF },

	/* System Management Unit MCA type */
	{ SMCA_SMU,	 HWID_MCATYPE(0x01, 0x0), 0x1 },
	{ SMCA_SMU_V2,	 HWID_MCATYPE(0x01, 0x1), 0x7FF },

	/* Microprocessor 5 Unit MCA type */
	{ SMCA_MP5,	 HWID_MCATYPE(0x01, 0x2), 0x3FF },

	/* Northbridge IO Unit MCA type */
	{ SMCA_NBIO,	 HWID_MCATYPE(0x18, 0x0), 0x1F },

	/* PCI Express Unit MCA type */
	{ SMCA_PCIE,	 HWID_MCATYPE(0x46, 0x0), 0x1F },
};

struct smca_bank smca_banks[MAX_NR_BANKS];
EXPORT_SYMBOL_GPL(smca_banks);

/*
 * In SMCA enabled processors, we can have multiple banks for a given IP type.
 * So to define a unique name for each bank, we use a temp c-string to append
 * the MCA_IPID[InstanceId] to type's name in get_name().
 *
 * InstanceId is 32 bits which is 8 characters. Make sure MAX_MCATYPE_NAME_LEN
 * is greater than 8 plus 1 (for underscore) plus length of longest type name.
 */
#define MAX_MCATYPE_NAME_LEN	30
static char buf_mcatype[MAX_MCATYPE_NAME_LEN];

static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
static DEFINE_PER_CPU(unsigned int, bank_map);	/* see which banks are on */

/* Map of banks that have more than MCA_MISC0 available. */
static DEFINE_PER_CPU(u32, smca_misc_banks_map);

static void amd_threshold_interrupt(void);
static void amd_deferred_error_interrupt(void);

static void default_deferred_error_interrupt(void)
{
	pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
}
void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;

static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu)
{
	u32 low, high;

	/*
	 * For SMCA enabled processors, BLKPTR field of the first MISC register
	 * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4).
	 */
	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
		return;

	if (!(low & MCI_CONFIG_MCAX))
		return;

	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high))
		return;

	if (low & MASK_BLKPTR_LO)
		per_cpu(smca_misc_banks_map, cpu) |= BIT(bank);

}

static void smca_configure(unsigned int bank, unsigned int cpu)
{
	unsigned int i, hwid_mcatype;
	struct smca_hwid *s_hwid;
	u32 high, low;
	u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank);

	/* Set appropriate bits in MCA_CONFIG */
	if (!rdmsr_safe(smca_config, &low, &high)) {
		/*
		 * OS is required to set the MCAX bit to acknowledge that it is
		 * now using the new MSR ranges and new registers under each
		 * bank. It also means that the OS will configure deferred
		 * errors in the new MCx_CONFIG register. If the bit is not set,
		 * uncorrectable errors will cause a system panic.
		 *
		 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.)
		 */
		high |= BIT(0);

		/*
		 * SMCA sets the Deferred Error Interrupt type per bank.
		 *
		 * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us
		 * if the DeferredIntType bit field is available.
		 *
		 * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the
		 * high portion of the MSR). OS should set this to 0x1 to enable
		 * APIC based interrupt. First, check that no interrupt has been
		 * set.
		 */
		if ((low & BIT(5)) && !((high >> 5) & 0x3))
			high |= BIT(5);

		wrmsr(smca_config, low, high);
	}

	smca_set_misc_banks_map(bank, cpu);

	/* Return early if this bank was already initialized. */
	if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0)
		return;

	if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) {
		pr_warn("Failed to read MCA_IPID for bank %d\n", bank);
		return;
	}

	hwid_mcatype = HWID_MCATYPE(high & MCI_IPID_HWID,
				    (high & MCI_IPID_MCATYPE) >> 16);

	for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) {
		s_hwid = &smca_hwid_mcatypes[i];
		if (hwid_mcatype == s_hwid->hwid_mcatype) {
			smca_banks[bank].hwid = s_hwid;
			smca_banks[bank].id = low;
			smca_banks[bank].sysfs_id = s_hwid->count++;
			break;
		}
	}
}

struct thresh_restart {
	struct threshold_block	*b;
	int			reset;
	int			set_lvt_off;
	int			lvt_off;
	u16			old_limit;
};

static inline bool is_shared_bank(int bank)
{
	/*
	 * Scalable MCA provides for only one core to have access to the MSRs of
	 * a shared bank.
	 */
	if (mce_flags.smca)
		return false;

	/* Bank 4 is for northbridge reporting and is thus shared */
	return (bank == 4);
}

static const char *bank4_names(const struct threshold_block *b)
{
	switch (b->address) {
	/* MSR4_MISC0 */
	case 0x00000413:
		return "dram";

	case 0xc0000408:
		return "ht_links";

	case 0xc0000409:
		return "l3_cache";

	default:
		WARN(1, "Funny MSR: 0x%08x\n", b->address);
		return "";
	}
};


static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits)
{
	/*
	 * bank 4 supports APIC LVT interrupts implicitly since forever.
	 */
	if (bank == 4)
		return true;

	/*
	 * IntP: interrupt present; if this bit is set, the thresholding
	 * bank can generate APIC LVT interrupts
	 */
	return msr_high_bits & BIT(28);
}

static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
{
	int msr = (hi & MASK_LVTOFF_HI) >> 20;

	if (apic < 0) {
		pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
		       b->bank, b->block, b->address, hi, lo);
		return 0;
	}

	if (apic != msr) {
		/*
		 * On SMCA CPUs, LVT offset is programmed at a different MSR, and
		 * the BIOS provides the value. The original field where LVT offset
		 * was set is reserved. Return early here:
		 */
		if (mce_flags.smca)
			return 0;

		pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
		       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
		return 0;
	}

	return 1;
};

/* Reprogram MCx_MISC MSR behind this threshold bank. */
static void threshold_restart_bank(void *_tr)
{
	struct thresh_restart *tr = _tr;
	u32 hi, lo;

	rdmsr(tr->b->address, lo, hi);

	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
		tr->reset = 1;	/* limit cannot be lower than err count */

	if (tr->reset) {		/* reset err count and overflow bit */
		hi =
		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
		    (THRESHOLD_MAX - tr->b->threshold_limit);
	} else if (tr->old_limit) {	/* change limit w/o reset */
		int new_count = (hi & THRESHOLD_MAX) +
		    (tr->old_limit - tr->b->threshold_limit);

		hi = (hi & ~MASK_ERR_COUNT_HI) |
		    (new_count & THRESHOLD_MAX);
	}

	/* clear IntType */
	hi &= ~MASK_INT_TYPE_HI;

	if (!tr->b->interrupt_capable)
		goto done;

	if (tr->set_lvt_off) {
		if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
			/* set new lvt offset */
			hi &= ~MASK_LVTOFF_HI;
			hi |= tr->lvt_off << 20;
		}
	}

	if (tr->b->interrupt_enable)
		hi |= INT_TYPE_APIC;

 done:

	hi |= MASK_COUNT_EN_HI;
	wrmsr(tr->b->address, lo, hi);
}

static void mce_threshold_block_init(struct threshold_block *b, int offset)
{
	struct thresh_restart tr = {
		.b			= b,
		.set_lvt_off		= 1,
		.lvt_off		= offset,
	};

	b->threshold_limit		= THRESHOLD_MAX;
	threshold_restart_bank(&tr);
};

static int setup_APIC_mce_threshold(int reserved, int new)
{
	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
					      APIC_EILVT_MSG_FIX, 0))
		return new;

	return reserved;
}

static int setup_APIC_deferred_error(int reserved, int new)
{
	if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
					      APIC_EILVT_MSG_FIX, 0))
		return new;

	return reserved;
}

static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
{
	u32 low = 0, high = 0;
	int def_offset = -1, def_new;

	if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
		return;

	def_new = (low & MASK_DEF_LVTOFF) >> 4;
	if (!(low & MASK_DEF_LVTOFF)) {
		pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
		def_new = DEF_LVT_OFF;
		low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
	}

	def_offset = setup_APIC_deferred_error(def_offset, def_new);
	if ((def_offset == def_new) &&
	    (deferred_error_int_vector != amd_deferred_error_interrupt))
		deferred_error_int_vector = amd_deferred_error_interrupt;

	if (!mce_flags.smca)
		low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;

	wrmsr(MSR_CU_DEF_ERR, low, high);
}

static u32 smca_get_block_address(unsigned int bank, unsigned int block,
				  unsigned int cpu)
{
	if (!block)
		return MSR_AMD64_SMCA_MCx_MISC(bank);

	if (!(per_cpu(smca_misc_banks_map, cpu) & BIT(bank)))
		return 0;

	return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
}

static u32 get_block_address(u32 current_addr, u32 low, u32 high,
			     unsigned int bank, unsigned int block,
			     unsigned int cpu)
{
	u32 addr = 0, offset = 0;

	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
		return addr;

	if (mce_flags.smca)
		return smca_get_block_address(bank, block, cpu);

	/* Fall back to method we used for older processors: */
	switch (block) {
	case 0:
		addr = msr_ops.misc(bank);
		break;
	case 1:
		offset = ((low & MASK_BLKPTR_LO) >> 21);
		if (offset)
			addr = MCG_XBLK_ADDR + offset;
		break;
	default:
		addr = ++current_addr;
	}
	return addr;
}

static int
prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
			int offset, u32 misc_high)
{
	unsigned int cpu = smp_processor_id();
	u32 smca_low, smca_high;
	struct threshold_block b;
	int new;

	if (!block)
		per_cpu(bank_map, cpu) |= (1 << bank);

	memset(&b, 0, sizeof(b));
	b.cpu			= cpu;
	b.bank			= bank;
	b.block			= block;
	b.address		= addr;
	b.interrupt_capable	= lvt_interrupt_supported(bank, misc_high);

	if (!b.interrupt_capable)
		goto done;

	b.interrupt_enable = 1;

	if (!mce_flags.smca) {
		new = (misc_high & MASK_LVTOFF_HI) >> 20;
		goto set_offset;
	}

	/* Gather LVT offset for thresholding: */
	if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
		goto out;

	new = (smca_low & SMCA_THR_LVT_OFF) >> 12;

set_offset:
	offset = setup_APIC_mce_threshold(offset, new);
	if (offset == new)
		thresholding_irq_en = true;

done:
	mce_threshold_block_init(&b, offset);

out:
	return offset;
}

bool amd_filter_mce(struct mce *m)
{
	enum smca_bank_types bank_type = smca_get_bank_type(m->bank);
	struct cpuinfo_x86 *c = &boot_cpu_data;
	u8 xec = (m->status >> 16) & 0x3F;

	/* See Family 17h Models 10h-2Fh Erratum #1114. */
	if (c->x86 == 0x17 &&
	    c->x86_model >= 0x10 && c->x86_model <= 0x2F &&
	    bank_type == SMCA_IF && xec == 10)
		return true;

	return false;
}

/*
 * Turn off thresholding banks for the following conditions:
 * - MC4_MISC thresholding is not supported on Family 0x15.
 * - Prevent possible spurious interrupts from the IF bank on Family 0x17
 *   Models 0x10-0x2F due to Erratum #1114.
 */
static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
{
	int i, num_msrs;
	u64 hwcr;
	bool need_toggle;
	u32 msrs[NR_BLOCKS];

	if (c->x86 == 0x15 && bank == 4) {
		msrs[0] = 0x00000413; /* MC4_MISC0 */
		msrs[1] = 0xc0000408; /* MC4_MISC1 */
		num_msrs = 2;
	} else if (c->x86 == 0x17 &&
		   (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) {

		if (smca_get_bank_type(bank) != SMCA_IF)
			return;

		msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank);
		num_msrs = 1;
	} else {
		return;
	}

	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 < num_msrs; i++)
		msr_clear_bit(msrs[i], 62);

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

/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
	unsigned int bank, block, cpu = smp_processor_id();
	u32 low = 0, high = 0, address = 0;
	int offset = -1;


	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
		if (mce_flags.smca)
			smca_configure(bank, cpu);

		disable_err_thresholding(c, bank);

		for (block = 0; block < NR_BLOCKS; ++block) {
			address = get_block_address(address, low, high, bank, block, cpu);
			if (!address)
				break;

			if (rdmsr_safe(address, &low, &high))
				break;

			if (!(high & MASK_VALID_HI))
				continue;

			if (!(high & MASK_CNTP_HI)  ||
			     (high & MASK_LOCKED_HI))
				continue;

			offset = prepare_threshold_block(bank, block, address, offset, high);
		}
	}

	if (mce_flags.succor)
		deferred_error_interrupt_enable(c);
}

int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
{
	u64 dram_base_addr, dram_limit_addr, dram_hole_base;
	/* We start from the normalized address */
	u64 ret_addr = norm_addr;

	u32 tmp;

	u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
	u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
	u8 intlv_addr_sel, intlv_addr_bit;
	u8 num_intlv_bits, hashed_bit;
	u8 lgcy_mmio_hole_en, base = 0;
	u8 cs_mask, cs_id = 0;
	bool hash_enabled = false;

	/* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
	if (amd_df_indirect_read(nid, 0, 0x1B4, umc, &tmp))
		goto out_err;

	/* Remove HiAddrOffset from normalized address, if enabled: */
	if (tmp & BIT(0)) {
		u64 hi_addr_offset = (tmp & GENMASK_ULL(31, 20)) << 8;

		if (norm_addr >= hi_addr_offset) {
			ret_addr -= hi_addr_offset;
			base = 1;
		}
	}

	/* Read D18F0x110 (DramBaseAddress). */
	if (amd_df_indirect_read(nid, 0, 0x110 + (8 * base), umc, &tmp))
		goto out_err;

	/* Check if address range is valid. */
	if (!(tmp & BIT(0))) {
		pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
			__func__, tmp);
		goto out_err;
	}

	lgcy_mmio_hole_en = tmp & BIT(1);
	intlv_num_chan	  = (tmp >> 4) & 0xF;
	intlv_addr_sel	  = (tmp >> 8) & 0x7;
	dram_base_addr	  = (tmp & GENMASK_ULL(31, 12)) << 16;

	/* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
	if (intlv_addr_sel > 3) {
		pr_err("%s: Invalid interleave address select %d.\n",
			__func__, intlv_addr_sel);
		goto out_err;
	}

	/* Read D18F0x114 (DramLimitAddress). */
	if (amd_df_indirect_read(nid, 0, 0x114 + (8 * base), umc, &tmp))
		goto out_err;

	intlv_num_sockets = (tmp >> 8) & 0x1;
	intlv_num_dies	  = (tmp >> 10) & 0x3;
	dram_limit_addr	  = ((tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);

	intlv_addr_bit = intlv_addr_sel + 8;

	/* Re-use intlv_num_chan by setting it equal to log2(#channels) */
	switch (intlv_num_chan) {
	case 0:	intlv_num_chan = 0; break;
	case 1: intlv_num_chan = 1; break;
	case 3: intlv_num_chan = 2; break;
	case 5:	intlv_num_chan = 3; break;
	case 7:	intlv_num_chan = 4; break;

	case 8: intlv_num_chan = 1;
		hash_enabled = true;
		break;
	default:
		pr_err("%s: Invalid number of interleaved channels %d.\n",
			__func__, intlv_num_chan);
		goto out_err;
	}

	num_intlv_bits = intlv_num_chan;

	if (intlv_num_dies > 2) {
		pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
			__func__, intlv_num_dies);
		goto out_err;
	}

	num_intlv_bits += intlv_num_dies;

	/* Add a bit if sockets are interleaved. */
	num_intlv_bits += intlv_num_sockets;

	/* Assert num_intlv_bits <= 4 */
	if (num_intlv_bits > 4) {
		pr_err("%s: Invalid interleave bits %d.\n",
			__func__, num_intlv_bits);
		goto out_err;
	}

	if (num_intlv_bits > 0) {
		u64 temp_addr_x, temp_addr_i, temp_addr_y;
		u8 die_id_bit, sock_id_bit, cs_fabric_id;

		/*
		 * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
		 * This is the fabric id for this coherent slave. Use
		 * umc/channel# as instance id of the coherent slave
		 * for FICAA.
		 */
		if (amd_df_indirect_read(nid, 0, 0x50, umc, &tmp))
			goto out_err;

		cs_fabric_id = (tmp >> 8) & 0xFF;
		die_id_bit   = 0;

		/* If interleaved over more than 1 channel: */
		if (intlv_num_chan) {
			die_id_bit = intlv_num_chan;
			cs_mask	   = (1 << die_id_bit) - 1;
			cs_id	   = cs_fabric_id & cs_mask;
		}

		sock_id_bit = die_id_bit;

		/* Read D18F1x208 (SystemFabricIdMask). */
		if (intlv_num_dies || intlv_num_sockets)
			if (amd_df_indirect_read(nid, 1, 0x208, umc, &tmp))
				goto out_err;

		/* If interleaved over more than 1 die. */
		if (intlv_num_dies) {
			sock_id_bit  = die_id_bit + intlv_num_dies;
			die_id_shift = (tmp >> 24) & 0xF;
			die_id_mask  = (tmp >> 8) & 0xFF;

			cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
		}

		/* If interleaved over more than 1 socket. */
		if (intlv_num_sockets) {
			socket_id_shift	= (tmp >> 28) & 0xF;
			socket_id_mask	= (tmp >> 16) & 0xFF;

			cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
		}

		/*
		 * The pre-interleaved address consists of XXXXXXIIIYYYYY
		 * where III is the ID for this CS, and XXXXXXYYYYY are the
		 * address bits from the post-interleaved address.
		 * "num_intlv_bits" has been calculated to tell us how many "I"
		 * bits there are. "intlv_addr_bit" tells us how many "Y" bits
		 * there are (where "I" starts).
		 */
		temp_addr_y = ret_addr & GENMASK_ULL(intlv_addr_bit-1, 0);
		temp_addr_i = (cs_id << intlv_addr_bit);
		temp_addr_x = (ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
		ret_addr    = temp_addr_x | temp_addr_i | temp_addr_y;
	}

	/* Add dram base address */
	ret_addr += dram_base_addr;

	/* If legacy MMIO hole enabled */
	if (lgcy_mmio_hole_en) {
		if (amd_df_indirect_read(nid, 0, 0x104, umc, &tmp))
			goto out_err;

		dram_hole_base = tmp & GENMASK(31, 24);
		if (ret_addr >= dram_hole_base)
			ret_addr += (BIT_ULL(32) - dram_hole_base);
	}

	if (hash_enabled) {
		/* Save some parentheses and grab ls-bit at the end. */
		hashed_bit =	(ret_addr >> 12) ^
				(ret_addr >> 18) ^
				(ret_addr >> 21) ^
				(ret_addr >> 30) ^
				cs_id;

		hashed_bit &= BIT(0);

		if (hashed_bit != ((ret_addr >> intlv_addr_bit) & BIT(0)))
			ret_addr ^= BIT(intlv_addr_bit);
	}

	/* Is calculated system address is above DRAM limit address? */
	if (ret_addr > dram_limit_addr)
		goto out_err;

	*sys_addr = ret_addr;
	return 0;

out_err:
	return -EINVAL;
}
EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);

bool amd_mce_is_memory_error(struct mce *m)
{
	/* ErrCodeExt[20:16] */
	u8 xec = (m->status >> 16) & 0x1f;

	if (mce_flags.smca)
		return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0;

	return m->bank == 4 && xec == 0x8;
}

static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
{
	struct mce m;

	mce_setup(&m);

	m.status = status;
	m.misc   = misc;
	m.bank   = bank;
	m.tsc	 = rdtsc();

	if (m.status & MCI_STATUS_ADDRV) {
		m.addr = addr;

		/*
		 * 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) {
		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid);

		if (m.status & MCI_STATUS_SYNDV)
			rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd);
	}

	mce_log(&m);
}

asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(struct pt_regs *regs)
{
	entering_irq();
	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
	inc_irq_stat(irq_deferred_error_count);
	deferred_error_int_vector();
	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
	exiting_ack_irq();
}

/*
 * Returns true if the logged error is deferred. False, otherwise.
 */
static inline bool
_log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc)
{
	u64 status, addr = 0;

	rdmsrl(msr_stat, status);
	if (!(status & MCI_STATUS_VAL))
		return false;

	if (status & MCI_STATUS_ADDRV)
		rdmsrl(msr_addr, addr);

	__log_error(bank, status, addr, misc);

	wrmsrl(msr_stat, 0);

	return status & MCI_STATUS_DEFERRED;
}

/*
 * We have three scenarios for checking for Deferred errors:
 *
 * 1) Non-SMCA systems check MCA_STATUS and log error if found.
 * 2) SMCA systems check MCA_STATUS. If error is found then log it and also
 *    clear MCA_DESTAT.
 * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and
 *    log it.
 */
static void log_error_deferred(unsigned int bank)
{
	bool defrd;

	defrd = _log_error_bank(bank, msr_ops.status(bank),
					msr_ops.addr(bank), 0);

	if (!mce_flags.smca)
		return;

	/* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */
	if (defrd) {
		wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
		return;
	}

	/*
	 * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check
	 * for a valid error.
	 */
	_log_error_bank(bank, MSR_AMD64_SMCA_MCx_DESTAT(bank),
			      MSR_AMD64_SMCA_MCx_DEADDR(bank), 0);
}

/* APIC interrupt handler for deferred errors */
static void amd_deferred_error_interrupt(void)
{
	unsigned int bank;

	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank)
		log_error_deferred(bank);
}

static void log_error_thresholding(unsigned int bank, u64 misc)
{
	_log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc);
}

static void log_and_reset_block(struct threshold_block *block)
{
	struct thresh_restart tr;
	u32 low = 0, high = 0;

	if (!block)
		return;

	if (rdmsr_safe(block->address, &low, &high))
		return;

	if (!(high & MASK_OVERFLOW_HI))
		return;

	/* Log the MCE which caused the threshold event. */
	log_error_thresholding(block->bank, ((u64)high << 32) | low);

	/* Reset threshold block after logging error. */
	memset(&tr, 0, sizeof(tr));
	tr.b = block;
	threshold_restart_bank(&tr);
}

/*
 * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt
 * goes off when error_count reaches threshold_limit.
 */
static void amd_threshold_interrupt(void)
{
	struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL;
	unsigned int bank, cpu = smp_processor_id();

	for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
			continue;

		first_block = per_cpu(threshold_banks, cpu)[bank]->blocks;
		if (!first_block)
			continue;

		/*
		 * The first block is also the head of the list. Check it first
		 * before iterating over the rest.
		 */
		log_and_reset_block(first_block);
		list_for_each_entry_safe(block, tmp, &first_block->miscj, miscj)
			log_and_reset_block(block);
	}
}

/*
 * Sysfs Interface
 */

struct threshold_attr {
	struct attribute attr;
	ssize_t (*show) (struct threshold_block *, char *);
	ssize_t (*store) (struct threshold_block *, const char *, size_t count);
};

#define SHOW_FIELDS(name)						\
static ssize_t show_ ## name(struct threshold_block *b, char *buf)	\
{									\
	return sprintf(buf, "%lu\n", (unsigned long) b->name);		\
}
SHOW_FIELDS(interrupt_enable)
SHOW_FIELDS(threshold_limit)

static ssize_t
store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
{
	struct thresh_restart tr;
	unsigned long new;

	if (!b->interrupt_capable)
		return -EINVAL;

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

	b->interrupt_enable = !!new;

	memset(&tr, 0, sizeof(tr));
	tr.b		= b;

	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);

	return size;
}

static ssize_t
store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
{
	struct thresh_restart tr;
	unsigned long new;

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

	if (new > THRESHOLD_MAX)
		new = THRESHOLD_MAX;
	if (new < 1)
		new = 1;

	memset(&tr, 0, sizeof(tr));
	tr.old_limit = b->threshold_limit;
	b->threshold_limit = new;
	tr.b = b;

	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);

	return size;
}

static ssize_t show_error_count(struct threshold_block *b, char *buf)
{
	u32 lo, hi;

	rdmsr_on_cpu(b->cpu, b->address, &lo, &hi);

	return sprintf(buf, "%u\n", ((hi & THRESHOLD_MAX) -
				     (THRESHOLD_MAX - b->threshold_limit)));
}

static struct threshold_attr error_count = {
	.attr = {.name = __stringify(error_count), .mode = 0444 },
	.show = show_error_count,
};

#define RW_ATTR(val)							\
static struct threshold_attr val = {					\
	.attr	= {.name = __stringify(val), .mode = 0644 },		\
	.show	= show_## val,						\
	.store	= store_## val,						\
};

RW_ATTR(interrupt_enable);
RW_ATTR(threshold_limit);

static struct attribute *default_attrs[] = {
	&threshold_limit.attr,
	&error_count.attr,
	NULL,	/* possibly interrupt_enable if supported, see below */
	NULL,
};

#define to_block(k)	container_of(k, struct threshold_block, kobj)
#define to_attr(a)	container_of(a, struct threshold_attr, attr)

static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
{
	struct threshold_block *b = to_block(kobj);
	struct threshold_attr *a = to_attr(attr);
	ssize_t ret;

	ret = a->show ? a->show(b, buf) : -EIO;

	return ret;
}

static ssize_t store(struct kobject *kobj, struct attribute *attr,
		     const char *buf, size_t count)
{
	struct threshold_block *b = to_block(kobj);
	struct threshold_attr *a = to_attr(attr);
	ssize_t ret;

	ret = a->store ? a->store(b, buf, count) : -EIO;

	return ret;
}

static const struct sysfs_ops threshold_ops = {
	.show			= show,
	.store			= store,
};

static struct kobj_type threshold_ktype = {
	.sysfs_ops		= &threshold_ops,
	.default_attrs		= default_attrs,
};

static const char *get_name(unsigned int bank, struct threshold_block *b)
{
	enum smca_bank_types bank_type;

	if (!mce_flags.smca) {
		if (b && bank == 4)
			return bank4_names(b);

		return th_names[bank];
	}

	bank_type = smca_get_bank_type(bank);
	if (bank_type >= N_SMCA_BANK_TYPES)
		return NULL;

	if (b && bank_type == SMCA_UMC) {
		if (b->block < ARRAY_SIZE(smca_umc_block_names))
			return smca_umc_block_names[b->block];
		return NULL;
	}

	if (smca_banks[bank].hwid->count == 1)
		return smca_get_name(bank_type);

	snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
		 "%s_%x", smca_get_name(bank_type),
			  smca_banks[bank].sysfs_id);
	return buf_mcatype;
}

static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
				     unsigned int block, u32 address)
{
	struct threshold_block *b = NULL;
	u32 low, high;
	int err;

	if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS))
		return 0;

	if (rdmsr_safe_on_cpu(cpu, address, &low, &high))
		return 0;

	if (!(high & MASK_VALID_HI)) {
		if (block)
			goto recurse;
		else
			return 0;
	}

	if (!(high & MASK_CNTP_HI)  ||
	     (high & MASK_LOCKED_HI))
		goto recurse;

	b = kzalloc(sizeof(struct threshold_block), GFP_KERNEL);
	if (!b)
		return -ENOMEM;

	b->block		= block;
	b->bank			= bank;
	b->cpu			= cpu;
	b->address		= address;
	b->interrupt_enable	= 0;
	b->interrupt_capable	= lvt_interrupt_supported(bank, high);
	b->threshold_limit	= THRESHOLD_MAX;

	if (b->interrupt_capable) {
		threshold_ktype.default_attrs[2] = &interrupt_enable.attr;
		b->interrupt_enable = 1;
	} else {
		threshold_ktype.default_attrs[2] = NULL;
	}

	INIT_LIST_HEAD(&b->miscj);

	if (per_cpu(threshold_banks, cpu)[bank]->blocks) {
		list_add(&b->miscj,
			 &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj);
	} else {
		per_cpu(threshold_banks, cpu)[bank]->blocks = b;
	}

	err = kobject_init_and_add(&b->kobj, &threshold_ktype,
				   per_cpu(threshold_banks, cpu)[bank]->kobj,
				   get_name(bank, b));
	if (err)
		goto out_free;
recurse:
	address = get_block_address(address, low, high, bank, ++block, cpu);
	if (!address)
		return 0;

	err = allocate_threshold_blocks(cpu, bank, block, address);
	if (err)
		goto out_free;

	if (b)
		kobject_uevent(&b->kobj, KOBJ_ADD);

	return err;

out_free:
	if (b) {
		kobject_put(&b->kobj);
		list_del(&b->miscj);
		kfree(b);
	}
	return err;
}

static int __threshold_add_blocks(struct threshold_bank *b)
{
	struct list_head *head = &b->blocks->miscj;
	struct threshold_block *pos = NULL;
	struct threshold_block *tmp = NULL;
	int err = 0;

	err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name);
	if (err)
		return err;

	list_for_each_entry_safe(pos, tmp, head, miscj) {

		err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name);
		if (err) {
			list_for_each_entry_safe_reverse(pos, tmp, head, miscj)
				kobject_del(&pos->kobj);

			return err;
		}
	}
	return err;
}

static int threshold_create_bank(unsigned int cpu, unsigned int bank)
{
	struct device *dev = per_cpu(mce_device, cpu);
	struct amd_northbridge *nb = NULL;
	struct threshold_bank *b = NULL;
	const char *name = get_name(bank, NULL);
	int err = 0;

	if (!dev)
		return -ENODEV;

	if (is_shared_bank(bank)) {
		nb = node_to_amd_nb(amd_get_nb_id(cpu));

		/* threshold descriptor already initialized on this node? */
		if (nb && nb->bank4) {
			/* yes, use it */
			b = nb->bank4;
			err = kobject_add(b->kobj, &dev->kobj, name);
			if (err)
				goto out;

			per_cpu(threshold_banks, cpu)[bank] = b;
			refcount_inc(&b->cpus);

			err = __threshold_add_blocks(b);

			goto out;
		}
	}

	b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
	if (!b) {
		err = -ENOMEM;
		goto out;
	}

	b->kobj = kobject_create_and_add(name, &dev->kobj);
	if (!b->kobj) {
		err = -EINVAL;
		goto out_free;
	}

	per_cpu(threshold_banks, cpu)[bank] = b;

	if (is_shared_bank(bank)) {
		refcount_set(&b->cpus, 1);

		/* nb is already initialized, see above */
		if (nb) {
			WARN_ON(nb->bank4);
			nb->bank4 = b;
		}
	}

	err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
	if (!err)
		goto out;

 out_free:
	kfree(b);

 out:
	return err;
}

static void deallocate_threshold_block(unsigned int cpu,
						 unsigned int bank)
{
	struct threshold_block *pos = NULL;
	struct threshold_block *tmp = NULL;
	struct threshold_bank *head = per_cpu(threshold_banks, cpu)[bank];

	if (!head)
		return;

	list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
		kobject_put(&pos->kobj);
		list_del(&pos->miscj);
		kfree(pos);
	}

	kfree(per_cpu(threshold_banks, cpu)[bank]->blocks);
	per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
}

static void __threshold_remove_blocks(struct threshold_bank *b)
{
	struct threshold_block *pos = NULL;
	struct threshold_block *tmp = NULL;

	kobject_del(b->kobj);

	list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj)
		kobject_del(&pos->kobj);
}

static void threshold_remove_bank(unsigned int cpu, int bank)
{
	struct amd_northbridge *nb;
	struct threshold_bank *b;

	b = per_cpu(threshold_banks, cpu)[bank];
	if (!b)
		return;

	if (!b->blocks)
		goto free_out;

	if (is_shared_bank(bank)) {
		if (!refcount_dec_and_test(&b->cpus)) {
			__threshold_remove_blocks(b);
			per_cpu(threshold_banks, cpu)[bank] = NULL;
			return;
		} else {
			/*
			 * the last CPU on this node using the shared bank is
			 * going away, remove that bank now.
			 */
			nb = node_to_amd_nb(amd_get_nb_id(cpu));
			nb->bank4 = NULL;
		}
	}

	deallocate_threshold_block(cpu, bank);

free_out:
	kobject_del(b->kobj);
	kobject_put(b->kobj);
	kfree(b);
	per_cpu(threshold_banks, cpu)[bank] = NULL;
}

int mce_threshold_remove_device(unsigned int cpu)
{
	unsigned int bank;

	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
			continue;
		threshold_remove_bank(cpu, bank);
	}
	kfree(per_cpu(threshold_banks, cpu));
	per_cpu(threshold_banks, cpu) = NULL;
	return 0;
}

/* create dir/files for all valid threshold banks */
int mce_threshold_create_device(unsigned int cpu)
{
	unsigned int bank;
	struct threshold_bank **bp;
	int err = 0;

	bp = per_cpu(threshold_banks, cpu);
	if (bp)
		return 0;

	bp = kcalloc(per_cpu(mce_num_banks, cpu), sizeof(struct threshold_bank *),
		     GFP_KERNEL);
	if (!bp)
		return -ENOMEM;

	per_cpu(threshold_banks, cpu) = bp;

	for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
			continue;
		err = threshold_create_bank(cpu, bank);
		if (err)
			goto err;
	}
	return err;
err:
	mce_threshold_remove_device(cpu);
	return err;
}

static __init int threshold_init_device(void)
{
	unsigned lcpu = 0;

	/* to hit CPUs online before the notifier is up */
	for_each_online_cpu(lcpu) {
		int err = mce_threshold_create_device(lcpu);

		if (err)
			return err;
	}

	if (thresholding_irq_en)
		mce_threshold_vector = amd_threshold_interrupt;

	return 0;
}
/*
 * there are 3 funcs which need to be _initcalled in a logic sequence:
 * 1. xen_late_init_mcelog
 * 2. mcheck_init_device
 * 3. threshold_init_device
 *
 * xen_late_init_mcelog must register xen_mce_chrdev_device before
 * native mce_chrdev_device registration if running under xen platform;
 *
 * mcheck_init_device should be inited before threshold_init_device to
 * initialize mce_device, otherwise a NULL ptr dereference will cause panic.
 *
 * so we use following _initcalls
 * 1. device_initcall(xen_late_init_mcelog);
 * 2. device_initcall_sync(mcheck_init_device);
 * 3. late_initcall(threshold_init_device);
 *
 * when running under xen, the initcall order is 1,2,3;
 * on baremetal, we skip 1 and we do only 2 and 3.
 */
late_initcall(threshold_init_device);