summaryrefslogtreecommitdiff
path: root/drivers/acpi/apei/ghes.c
blob: 94c4872ae55ffc11f779baec5c6d786c90b655b2 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * APEI Generic Hardware Error Source support
 *
 * Generic Hardware Error Source provides a way to report platform
 * hardware errors (such as that from chipset). It works in so called
 * "Firmware First" mode, that is, hardware errors are reported to
 * firmware firstly, then reported to Linux by firmware. This way,
 * some non-standard hardware error registers or non-standard hardware
 * link can be checked by firmware to produce more hardware error
 * information for Linux.
 *
 * For more information about Generic Hardware Error Source, please
 * refer to ACPI Specification version 4.0, section 17.3.2.6
 *
 * Copyright 2010,2011 Intel Corp.
 *   Author: Huang Ying <ying.huang@intel.com>
 */

#include <linux/arm_sdei.h>
#include <linux/kernel.h>
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/interrupt.h>
#include <linux/timer.h>
#include <linux/cper.h>
#include <linux/platform_device.h>
#include <linux/mutex.h>
#include <linux/ratelimit.h>
#include <linux/vmalloc.h>
#include <linux/irq_work.h>
#include <linux/llist.h>
#include <linux/genalloc.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/aer.h>
#include <linux/nmi.h>
#include <linux/sched/clock.h>
#include <linux/uuid.h>
#include <linux/ras.h>
#include <linux/task_work.h>

#include <acpi/actbl1.h>
#include <acpi/ghes.h>
#include <acpi/apei.h>
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
#include <ras/ras_event.h>

#include "apei-internal.h"

#define GHES_PFX	"GHES: "

#define GHES_ESTATUS_MAX_SIZE		65536
#define GHES_ESOURCE_PREALLOC_MAX_SIZE	65536

#define GHES_ESTATUS_POOL_MIN_ALLOC_ORDER 3

/* This is just an estimation for memory pool allocation */
#define GHES_ESTATUS_CACHE_AVG_SIZE	512

#define GHES_ESTATUS_CACHES_SIZE	4

#define GHES_ESTATUS_IN_CACHE_MAX_NSEC	10000000000ULL
/* Prevent too many caches are allocated because of RCU */
#define GHES_ESTATUS_CACHE_ALLOCED_MAX	(GHES_ESTATUS_CACHES_SIZE * 3 / 2)

#define GHES_ESTATUS_CACHE_LEN(estatus_len)			\
	(sizeof(struct ghes_estatus_cache) + (estatus_len))
#define GHES_ESTATUS_FROM_CACHE(estatus_cache)			\
	((struct acpi_hest_generic_status *)				\
	 ((struct ghes_estatus_cache *)(estatus_cache) + 1))

#define GHES_ESTATUS_NODE_LEN(estatus_len)			\
	(sizeof(struct ghes_estatus_node) + (estatus_len))
#define GHES_ESTATUS_FROM_NODE(estatus_node)			\
	((struct acpi_hest_generic_status *)				\
	 ((struct ghes_estatus_node *)(estatus_node) + 1))

#define GHES_VENDOR_ENTRY_LEN(gdata_len)                               \
	(sizeof(struct ghes_vendor_record_entry) + (gdata_len))
#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry)                     \
	((struct acpi_hest_generic_data *)                              \
	((struct ghes_vendor_record_entry *)(vendor_entry) + 1))

/*
 *  NMI-like notifications vary by architecture, before the compiler can prune
 *  unused static functions it needs a value for these enums.
 */
#ifndef CONFIG_ARM_SDE_INTERFACE
#define FIX_APEI_GHES_SDEI_NORMAL	__end_of_fixed_addresses
#define FIX_APEI_GHES_SDEI_CRITICAL	__end_of_fixed_addresses
#endif

static inline bool is_hest_type_generic_v2(struct ghes *ghes)
{
	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
}

/*
 * This driver isn't really modular, however for the time being,
 * continuing to use module_param is the easiest way to remain
 * compatible with existing boot arg use cases.
 */
bool ghes_disable;
module_param_named(disable, ghes_disable, bool, 0);

/*
 * All error sources notified with HED (Hardware Error Device) share a
 * single notifier callback, so they need to be linked and checked one
 * by one. This holds true for NMI too.
 *
 * RCU is used for these lists, so ghes_list_mutex is only used for
 * list changing, not for traversing.
 */
static LIST_HEAD(ghes_hed);
static DEFINE_MUTEX(ghes_list_mutex);

/*
 * Because the memory area used to transfer hardware error information
 * from BIOS to Linux can be determined only in NMI, IRQ or timer
 * handler, but general ioremap can not be used in atomic context, so
 * the fixmap is used instead.
 *
 * This spinlock is used to prevent the fixmap entry from being used
 * simultaneously.
 */
static DEFINE_SPINLOCK(ghes_notify_lock_irq);

struct ghes_vendor_record_entry {
	struct work_struct work;
	int error_severity;
	char vendor_record[];
};

static struct gen_pool *ghes_estatus_pool;
static unsigned long ghes_estatus_pool_size_request;

static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
static atomic_t ghes_estatus_cache_alloced;

static int ghes_panic_timeout __read_mostly = 30;

static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx)
{
	phys_addr_t paddr;
	pgprot_t prot;

	paddr = PFN_PHYS(pfn);
	prot = arch_apei_get_mem_attribute(paddr);
	__set_fixmap(fixmap_idx, paddr, prot);

	return (void __iomem *) __fix_to_virt(fixmap_idx);
}

static void ghes_unmap(void __iomem *vaddr, enum fixed_addresses fixmap_idx)
{
	int _idx = virt_to_fix((unsigned long)vaddr);

	WARN_ON_ONCE(fixmap_idx != _idx);
	clear_fixmap(fixmap_idx);
}

int ghes_estatus_pool_init(unsigned int num_ghes)
{
	unsigned long addr, len;
	int rc;

	ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1);
	if (!ghes_estatus_pool)
		return -ENOMEM;

	len = GHES_ESTATUS_CACHE_AVG_SIZE * GHES_ESTATUS_CACHE_ALLOCED_MAX;
	len += (num_ghes * GHES_ESOURCE_PREALLOC_MAX_SIZE);

	ghes_estatus_pool_size_request = PAGE_ALIGN(len);
	addr = (unsigned long)vmalloc(PAGE_ALIGN(len));
	if (!addr)
		goto err_pool_alloc;

	rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1);
	if (rc)
		goto err_pool_add;

	return 0;

err_pool_add:
	vfree((void *)addr);

err_pool_alloc:
	gen_pool_destroy(ghes_estatus_pool);

	return -ENOMEM;
}

static int map_gen_v2(struct ghes *ghes)
{
	return apei_map_generic_address(&ghes->generic_v2->read_ack_register);
}

static void unmap_gen_v2(struct ghes *ghes)
{
	apei_unmap_generic_address(&ghes->generic_v2->read_ack_register);
}

static void ghes_ack_error(struct acpi_hest_generic_v2 *gv2)
{
	int rc;
	u64 val = 0;

	rc = apei_read(&val, &gv2->read_ack_register);
	if (rc)
		return;

	val &= gv2->read_ack_preserve << gv2->read_ack_register.bit_offset;
	val |= gv2->read_ack_write    << gv2->read_ack_register.bit_offset;

	apei_write(val, &gv2->read_ack_register);
}

static struct ghes *ghes_new(struct acpi_hest_generic *generic)
{
	struct ghes *ghes;
	unsigned int error_block_length;
	int rc;

	ghes = kzalloc(sizeof(*ghes), GFP_KERNEL);
	if (!ghes)
		return ERR_PTR(-ENOMEM);

	ghes->generic = generic;
	if (is_hest_type_generic_v2(ghes)) {
		rc = map_gen_v2(ghes);
		if (rc)
			goto err_free;
	}

	rc = apei_map_generic_address(&generic->error_status_address);
	if (rc)
		goto err_unmap_read_ack_addr;
	error_block_length = generic->error_block_length;
	if (error_block_length > GHES_ESTATUS_MAX_SIZE) {
		pr_warn(FW_WARN GHES_PFX
			"Error status block length is too long: %u for "
			"generic hardware error source: %d.\n",
			error_block_length, generic->header.source_id);
		error_block_length = GHES_ESTATUS_MAX_SIZE;
	}
	ghes->estatus = kmalloc(error_block_length, GFP_KERNEL);
	if (!ghes->estatus) {
		rc = -ENOMEM;
		goto err_unmap_status_addr;
	}

	return ghes;

err_unmap_status_addr:
	apei_unmap_generic_address(&generic->error_status_address);
err_unmap_read_ack_addr:
	if (is_hest_type_generic_v2(ghes))
		unmap_gen_v2(ghes);
err_free:
	kfree(ghes);
	return ERR_PTR(rc);
}

static void ghes_fini(struct ghes *ghes)
{
	kfree(ghes->estatus);
	apei_unmap_generic_address(&ghes->generic->error_status_address);
	if (is_hest_type_generic_v2(ghes))
		unmap_gen_v2(ghes);
}

static inline int ghes_severity(int severity)
{
	switch (severity) {
	case CPER_SEV_INFORMATIONAL:
		return GHES_SEV_NO;
	case CPER_SEV_CORRECTED:
		return GHES_SEV_CORRECTED;
	case CPER_SEV_RECOVERABLE:
		return GHES_SEV_RECOVERABLE;
	case CPER_SEV_FATAL:
		return GHES_SEV_PANIC;
	default:
		/* Unknown, go panic */
		return GHES_SEV_PANIC;
	}
}

static void ghes_copy_tofrom_phys(void *buffer, u64 paddr, u32 len,
				  int from_phys,
				  enum fixed_addresses fixmap_idx)
{
	void __iomem *vaddr;
	u64 offset;
	u32 trunk;

	while (len > 0) {
		offset = paddr - (paddr & PAGE_MASK);
		vaddr = ghes_map(PHYS_PFN(paddr), fixmap_idx);
		trunk = PAGE_SIZE - offset;
		trunk = min(trunk, len);
		if (from_phys)
			memcpy_fromio(buffer, vaddr + offset, trunk);
		else
			memcpy_toio(vaddr + offset, buffer, trunk);
		len -= trunk;
		paddr += trunk;
		buffer += trunk;
		ghes_unmap(vaddr, fixmap_idx);
	}
}

/* Check the top-level record header has an appropriate size. */
static int __ghes_check_estatus(struct ghes *ghes,
				struct acpi_hest_generic_status *estatus)
{
	u32 len = cper_estatus_len(estatus);

	if (len < sizeof(*estatus)) {
		pr_warn_ratelimited(FW_WARN GHES_PFX "Truncated error status block!\n");
		return -EIO;
	}

	if (len > ghes->generic->error_block_length) {
		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid error status block length!\n");
		return -EIO;
	}

	if (cper_estatus_check_header(estatus)) {
		pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid CPER header!\n");
		return -EIO;
	}

	return 0;
}

/* Read the CPER block, returning its address, and header in estatus. */
static int __ghes_peek_estatus(struct ghes *ghes,
			       struct acpi_hest_generic_status *estatus,
			       u64 *buf_paddr, enum fixed_addresses fixmap_idx)
{
	struct acpi_hest_generic *g = ghes->generic;
	int rc;

	rc = apei_read(buf_paddr, &g->error_status_address);
	if (rc) {
		*buf_paddr = 0;
		pr_warn_ratelimited(FW_WARN GHES_PFX
"Failed to read error status block address for hardware error source: %d.\n",
				   g->header.source_id);
		return -EIO;
	}
	if (!*buf_paddr)
		return -ENOENT;

	ghes_copy_tofrom_phys(estatus, *buf_paddr, sizeof(*estatus), 1,
			      fixmap_idx);
	if (!estatus->block_status) {
		*buf_paddr = 0;
		return -ENOENT;
	}

	return 0;
}

static int __ghes_read_estatus(struct acpi_hest_generic_status *estatus,
			       u64 buf_paddr, enum fixed_addresses fixmap_idx,
			       size_t buf_len)
{
	ghes_copy_tofrom_phys(estatus, buf_paddr, buf_len, 1, fixmap_idx);
	if (cper_estatus_check(estatus)) {
		pr_warn_ratelimited(FW_WARN GHES_PFX
				    "Failed to read error status block!\n");
		return -EIO;
	}

	return 0;
}

static int ghes_read_estatus(struct ghes *ghes,
			     struct acpi_hest_generic_status *estatus,
			     u64 *buf_paddr, enum fixed_addresses fixmap_idx)
{
	int rc;

	rc = __ghes_peek_estatus(ghes, estatus, buf_paddr, fixmap_idx);
	if (rc)
		return rc;

	rc = __ghes_check_estatus(ghes, estatus);
	if (rc)
		return rc;

	return __ghes_read_estatus(estatus, *buf_paddr, fixmap_idx,
				   cper_estatus_len(estatus));
}

static void ghes_clear_estatus(struct ghes *ghes,
			       struct acpi_hest_generic_status *estatus,
			       u64 buf_paddr, enum fixed_addresses fixmap_idx)
{
	estatus->block_status = 0;

	if (!buf_paddr)
		return;

	ghes_copy_tofrom_phys(estatus, buf_paddr,
			      sizeof(estatus->block_status), 0,
			      fixmap_idx);

	/*
	 * GHESv2 type HEST entries introduce support for error acknowledgment,
	 * so only acknowledge the error if this support is present.
	 */
	if (is_hest_type_generic_v2(ghes))
		ghes_ack_error(ghes->generic_v2);
}

/*
 * Called as task_work before returning to user-space.
 * Ensure any queued work has been done before we return to the context that
 * triggered the notification.
 */
static void ghes_kick_task_work(struct callback_head *head)
{
	struct acpi_hest_generic_status *estatus;
	struct ghes_estatus_node *estatus_node;
	u32 node_len;

	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
		memory_failure_queue_kick(estatus_node->task_work_cpu);

	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
}

static bool ghes_do_memory_failure(u64 physical_addr, int flags)
{
	unsigned long pfn;

	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
		return false;

	pfn = PHYS_PFN(physical_addr);
	if (!pfn_valid(pfn) && !arch_is_platform_page(physical_addr)) {
		pr_warn_ratelimited(FW_WARN GHES_PFX
		"Invalid address in generic error data: %#llx\n",
		physical_addr);
		return false;
	}

	memory_failure_queue(pfn, flags);
	return true;
}

static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
				       int sev)
{
	int flags = -1;
	int sec_sev = ghes_severity(gdata->error_severity);
	struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);

	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
		return false;

	/* iff following two events can be handled properly by now */
	if (sec_sev == GHES_SEV_CORRECTED &&
	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
		flags = MF_SOFT_OFFLINE;
	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
		flags = 0;

	if (flags != -1)
		return ghes_do_memory_failure(mem_err->physical_addr, flags);

	return false;
}

static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
{
	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
	bool queued = false;
	int sec_sev, i;
	char *p;

	log_arm_hw_error(err);

	sec_sev = ghes_severity(gdata->error_severity);
	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
		return false;

	p = (char *)(err + 1);
	for (i = 0; i < err->err_info_num; i++) {
		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
		bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
		const char *error_type = "unknown error";

		/*
		 * The field (err_info->error_info & BIT(26)) is fixed to set to
		 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
		 * firmware won't mix corrected errors in an uncorrected section,
		 * and don't filter out 'corrected' error here.
		 */
		if (is_cache && has_pa) {
			queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
			p += err_info->length;
			continue;
		}

		if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
			error_type = cper_proc_error_type_strs[err_info->type];

		pr_warn_ratelimited(FW_WARN GHES_PFX
				    "Unhandled processor error type: %s\n",
				    error_type);
		p += err_info->length;
	}

	return queued;
}

/*
 * PCIe AER errors need to be sent to the AER driver for reporting and
 * recovery. The GHES severities map to the following AER severities and
 * require the following handling:
 *
 * GHES_SEV_CORRECTABLE -> AER_CORRECTABLE
 *     These need to be reported by the AER driver but no recovery is
 *     necessary.
 * GHES_SEV_RECOVERABLE -> AER_NONFATAL
 * GHES_SEV_RECOVERABLE && CPER_SEC_RESET -> AER_FATAL
 *     These both need to be reported and recovered from by the AER driver.
 * GHES_SEV_PANIC does not make it to this handling since the kernel must
 *     panic.
 */
static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
{
#ifdef CONFIG_ACPI_APEI_PCIEAER
	struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);

	if (pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
	    pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) {
		unsigned int devfn;
		int aer_severity;

		devfn = PCI_DEVFN(pcie_err->device_id.device,
				  pcie_err->device_id.function);
		aer_severity = cper_severity_to_aer(gdata->error_severity);

		/*
		 * If firmware reset the component to contain
		 * the error, we must reinitialize it before
		 * use, so treat it as a fatal AER error.
		 */
		if (gdata->flags & CPER_SEC_RESET)
			aer_severity = AER_FATAL;

		aer_recover_queue(pcie_err->device_id.segment,
				  pcie_err->device_id.bus,
				  devfn, aer_severity,
				  (struct aer_capability_regs *)
				  pcie_err->aer_info);
	}
#endif
}

static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);

int ghes_register_vendor_record_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&vendor_record_notify_list, nb);
}
EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier);

void ghes_unregister_vendor_record_notifier(struct notifier_block *nb)
{
	blocking_notifier_chain_unregister(&vendor_record_notify_list, nb);
}
EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier);

static void ghes_vendor_record_work_func(struct work_struct *work)
{
	struct ghes_vendor_record_entry *entry;
	struct acpi_hest_generic_data *gdata;
	u32 len;

	entry = container_of(work, struct ghes_vendor_record_entry, work);
	gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);

	blocking_notifier_call_chain(&vendor_record_notify_list,
				     entry->error_severity, gdata);

	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
	gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len);
}

static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
					  int sev)
{
	struct acpi_hest_generic_data *copied_gdata;
	struct ghes_vendor_record_entry *entry;
	u32 len;

	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
	entry = (void *)gen_pool_alloc(ghes_estatus_pool, len);
	if (!entry)
		return;

	copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
	memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata));
	entry->error_severity = sev;

	INIT_WORK(&entry->work, ghes_vendor_record_work_func);
	schedule_work(&entry->work);
}

static bool ghes_do_proc(struct ghes *ghes,
			 const struct acpi_hest_generic_status *estatus)
{
	int sev, sec_sev;
	struct acpi_hest_generic_data *gdata;
	guid_t *sec_type;
	const guid_t *fru_id = &guid_null;
	char *fru_text = "";
	bool queued = false;

	sev = ghes_severity(estatus->error_severity);
	apei_estatus_for_each_section(estatus, gdata) {
		sec_type = (guid_t *)gdata->section_type;
		sec_sev = ghes_severity(gdata->error_severity);
		if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
			fru_id = (guid_t *)gdata->fru_id;

		if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
			fru_text = gdata->fru_text;

		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
			struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);

			ghes_edac_report_mem_error(sev, mem_err);

			arch_apei_report_mem_error(sev, mem_err);
			queued = ghes_handle_memory_failure(gdata, sev);
		}
		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
			ghes_handle_aer(gdata);
		}
		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
			queued = ghes_handle_arm_hw_error(gdata, sev);
		} else {
			void *err = acpi_hest_get_payload(gdata);

			ghes_defer_non_standard_event(gdata, sev);
			log_non_standard_event(sec_type, fru_id, fru_text,
					       sec_sev, err,
					       gdata->error_data_length);
		}
	}

	return queued;
}

static void __ghes_print_estatus(const char *pfx,
				 const struct acpi_hest_generic *generic,
				 const struct acpi_hest_generic_status *estatus)
{
	static atomic_t seqno;
	unsigned int curr_seqno;
	char pfx_seq[64];

	if (pfx == NULL) {
		if (ghes_severity(estatus->error_severity) <=
		    GHES_SEV_CORRECTED)
			pfx = KERN_WARNING;
		else
			pfx = KERN_ERR;
	}
	curr_seqno = atomic_inc_return(&seqno);
	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}" HW_ERR, pfx, curr_seqno);
	printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n",
	       pfx_seq, generic->header.source_id);
	cper_estatus_print(pfx_seq, estatus);
}

static int ghes_print_estatus(const char *pfx,
			      const struct acpi_hest_generic *generic,
			      const struct acpi_hest_generic_status *estatus)
{
	/* Not more than 2 messages every 5 seconds */
	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
	static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2);
	struct ratelimit_state *ratelimit;

	if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED)
		ratelimit = &ratelimit_corrected;
	else
		ratelimit = &ratelimit_uncorrected;
	if (__ratelimit(ratelimit)) {
		__ghes_print_estatus(pfx, generic, estatus);
		return 1;
	}
	return 0;
}

/*
 * GHES error status reporting throttle, to report more kinds of
 * errors, instead of just most frequently occurred errors.
 */
static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus)
{
	u32 len;
	int i, cached = 0;
	unsigned long long now;
	struct ghes_estatus_cache *cache;
	struct acpi_hest_generic_status *cache_estatus;

	len = cper_estatus_len(estatus);
	rcu_read_lock();
	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
		cache = rcu_dereference(ghes_estatus_caches[i]);
		if (cache == NULL)
			continue;
		if (len != cache->estatus_len)
			continue;
		cache_estatus = GHES_ESTATUS_FROM_CACHE(cache);
		if (memcmp(estatus, cache_estatus, len))
			continue;
		atomic_inc(&cache->count);
		now = sched_clock();
		if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC)
			cached = 1;
		break;
	}
	rcu_read_unlock();
	return cached;
}

static struct ghes_estatus_cache *ghes_estatus_cache_alloc(
	struct acpi_hest_generic *generic,
	struct acpi_hest_generic_status *estatus)
{
	int alloced;
	u32 len, cache_len;
	struct ghes_estatus_cache *cache;
	struct acpi_hest_generic_status *cache_estatus;

	alloced = atomic_add_return(1, &ghes_estatus_cache_alloced);
	if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) {
		atomic_dec(&ghes_estatus_cache_alloced);
		return NULL;
	}
	len = cper_estatus_len(estatus);
	cache_len = GHES_ESTATUS_CACHE_LEN(len);
	cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len);
	if (!cache) {
		atomic_dec(&ghes_estatus_cache_alloced);
		return NULL;
	}
	cache_estatus = GHES_ESTATUS_FROM_CACHE(cache);
	memcpy(cache_estatus, estatus, len);
	cache->estatus_len = len;
	atomic_set(&cache->count, 0);
	cache->generic = generic;
	cache->time_in = sched_clock();
	return cache;
}

static void ghes_estatus_cache_rcu_free(struct rcu_head *head)
{
	struct ghes_estatus_cache *cache;
	u32 len;

	cache = container_of(head, struct ghes_estatus_cache, rcu);
	len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache));
	len = GHES_ESTATUS_CACHE_LEN(len);
	gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len);
	atomic_dec(&ghes_estatus_cache_alloced);
}

static void
ghes_estatus_cache_add(struct acpi_hest_generic *generic,
		       struct acpi_hest_generic_status *estatus)
{
	unsigned long long now, duration, period, max_period = 0;
	struct ghes_estatus_cache *cache, *new_cache;
	struct ghes_estatus_cache __rcu *victim;
	int i, slot = -1, count;

	new_cache = ghes_estatus_cache_alloc(generic, estatus);
	if (!new_cache)
		return;

	rcu_read_lock();
	now = sched_clock();
	for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) {
		cache = rcu_dereference(ghes_estatus_caches[i]);
		if (cache == NULL) {
			slot = i;
			break;
		}
		duration = now - cache->time_in;
		if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) {
			slot = i;
			break;
		}
		count = atomic_read(&cache->count);
		period = duration;
		do_div(period, (count + 1));
		if (period > max_period) {
			max_period = period;
			slot = i;
		}
	}
	rcu_read_unlock();

	if (slot != -1) {
		/*
		 * Use release semantics to ensure that ghes_estatus_cached()
		 * running on another CPU will see the updated cache fields if
		 * it can see the new value of the pointer.
		 */
		victim = xchg_release(&ghes_estatus_caches[slot],
				      RCU_INITIALIZER(new_cache));

		/*
		 * At this point, victim may point to a cached item different
		 * from the one based on which we selected the slot. Instead of
		 * going to the loop again to pick another slot, let's just
		 * drop the other item anyway: this may cause a false cache
		 * miss later on, but that won't cause any problems.
		 */
		if (victim)
			call_rcu(&unrcu_pointer(victim)->rcu,
				 ghes_estatus_cache_rcu_free);
	}
}

static void __ghes_panic(struct ghes *ghes,
			 struct acpi_hest_generic_status *estatus,
			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
{
	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);

	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);

	/* reboot to log the error! */
	if (!panic_timeout)
		panic_timeout = ghes_panic_timeout;
	panic("Fatal hardware error!");
}

static int ghes_proc(struct ghes *ghes)
{
	struct acpi_hest_generic_status *estatus = ghes->estatus;
	u64 buf_paddr;
	int rc;

	rc = ghes_read_estatus(ghes, estatus, &buf_paddr, FIX_APEI_GHES_IRQ);
	if (rc)
		goto out;

	if (ghes_severity(estatus->error_severity) >= GHES_SEV_PANIC)
		__ghes_panic(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);

	if (!ghes_estatus_cached(estatus)) {
		if (ghes_print_estatus(NULL, ghes->generic, estatus))
			ghes_estatus_cache_add(ghes->generic, estatus);
	}
	ghes_do_proc(ghes, estatus);

out:
	ghes_clear_estatus(ghes, estatus, buf_paddr, FIX_APEI_GHES_IRQ);

	return rc;
}

static void ghes_add_timer(struct ghes *ghes)
{
	struct acpi_hest_generic *g = ghes->generic;
	unsigned long expire;

	if (!g->notify.poll_interval) {
		pr_warn(FW_WARN GHES_PFX "Poll interval is 0 for generic hardware error source: %d, disabled.\n",
			g->header.source_id);
		return;
	}
	expire = jiffies + msecs_to_jiffies(g->notify.poll_interval);
	ghes->timer.expires = round_jiffies_relative(expire);
	add_timer(&ghes->timer);
}

static void ghes_poll_func(struct timer_list *t)
{
	struct ghes *ghes = from_timer(ghes, t, timer);
	unsigned long flags;

	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
	ghes_proc(ghes);
	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
	if (!(ghes->flags & GHES_EXITING))
		ghes_add_timer(ghes);
}

static irqreturn_t ghes_irq_func(int irq, void *data)
{
	struct ghes *ghes = data;
	unsigned long flags;
	int rc;

	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
	rc = ghes_proc(ghes);
	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);
	if (rc)
		return IRQ_NONE;

	return IRQ_HANDLED;
}

static int ghes_notify_hed(struct notifier_block *this, unsigned long event,
			   void *data)
{
	struct ghes *ghes;
	unsigned long flags;
	int ret = NOTIFY_DONE;

	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
	rcu_read_lock();
	list_for_each_entry_rcu(ghes, &ghes_hed, list) {
		if (!ghes_proc(ghes))
			ret = NOTIFY_OK;
	}
	rcu_read_unlock();
	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);

	return ret;
}

static struct notifier_block ghes_notifier_hed = {
	.notifier_call = ghes_notify_hed,
};

/*
 * Handlers for CPER records may not be NMI safe. For example,
 * memory_failure_queue() takes spinlocks and calls schedule_work_on().
 * In any NMI-like handler, memory from ghes_estatus_pool is used to save
 * estatus, and added to the ghes_estatus_llist. irq_work_queue() causes
 * ghes_proc_in_irq() to run in IRQ context where each estatus in
 * ghes_estatus_llist is processed.
 *
 * Memory from the ghes_estatus_pool is also used with the ghes_estatus_cache
 * to suppress frequent messages.
 */
static struct llist_head ghes_estatus_llist;
static struct irq_work ghes_proc_irq_work;

static void ghes_proc_in_irq(struct irq_work *irq_work)
{
	struct llist_node *llnode, *next;
	struct ghes_estatus_node *estatus_node;
	struct acpi_hest_generic *generic;
	struct acpi_hest_generic_status *estatus;
	bool task_work_pending;
	u32 len, node_len;
	int ret;

	llnode = llist_del_all(&ghes_estatus_llist);
	/*
	 * Because the time order of estatus in list is reversed,
	 * revert it back to proper order.
	 */
	llnode = llist_reverse_order(llnode);
	while (llnode) {
		next = llnode->next;
		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
					   llnode);
		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
		len = cper_estatus_len(estatus);
		node_len = GHES_ESTATUS_NODE_LEN(len);
		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
		if (!ghes_estatus_cached(estatus)) {
			generic = estatus_node->generic;
			if (ghes_print_estatus(NULL, generic, estatus))
				ghes_estatus_cache_add(generic, estatus);
		}

		if (task_work_pending && current->mm) {
			estatus_node->task_work.func = ghes_kick_task_work;
			estatus_node->task_work_cpu = smp_processor_id();
			ret = task_work_add(current, &estatus_node->task_work,
					    TWA_RESUME);
			if (ret)
				estatus_node->task_work.func = NULL;
		}

		if (!estatus_node->task_work.func)
			gen_pool_free(ghes_estatus_pool,
				      (unsigned long)estatus_node, node_len);

		llnode = next;
	}
}

static void ghes_print_queued_estatus(void)
{
	struct llist_node *llnode;
	struct ghes_estatus_node *estatus_node;
	struct acpi_hest_generic *generic;
	struct acpi_hest_generic_status *estatus;

	llnode = llist_del_all(&ghes_estatus_llist);
	/*
	 * Because the time order of estatus in list is reversed,
	 * revert it back to proper order.
	 */
	llnode = llist_reverse_order(llnode);
	while (llnode) {
		estatus_node = llist_entry(llnode, struct ghes_estatus_node,
					   llnode);
		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
		generic = estatus_node->generic;
		ghes_print_estatus(NULL, generic, estatus);
		llnode = llnode->next;
	}
}

static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
				       enum fixed_addresses fixmap_idx)
{
	struct acpi_hest_generic_status *estatus, tmp_header;
	struct ghes_estatus_node *estatus_node;
	u32 len, node_len;
	u64 buf_paddr;
	int sev, rc;

	if (!IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG))
		return -EOPNOTSUPP;

	rc = __ghes_peek_estatus(ghes, &tmp_header, &buf_paddr, fixmap_idx);
	if (rc) {
		ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
		return rc;
	}

	rc = __ghes_check_estatus(ghes, &tmp_header);
	if (rc) {
		ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);
		return rc;
	}

	len = cper_estatus_len(&tmp_header);
	node_len = GHES_ESTATUS_NODE_LEN(len);
	estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, node_len);
	if (!estatus_node)
		return -ENOMEM;

	estatus_node->ghes = ghes;
	estatus_node->generic = ghes->generic;
	estatus_node->task_work.func = NULL;
	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);

	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
		ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
		rc = -ENOENT;
		goto no_work;
	}

	sev = ghes_severity(estatus->error_severity);
	if (sev >= GHES_SEV_PANIC) {
		ghes_print_queued_estatus();
		__ghes_panic(ghes, estatus, buf_paddr, fixmap_idx);
	}

	ghes_clear_estatus(ghes, &tmp_header, buf_paddr, fixmap_idx);

	/* This error has been reported before, don't process it again. */
	if (ghes_estatus_cached(estatus))
		goto no_work;

	llist_add(&estatus_node->llnode, &ghes_estatus_llist);

	return rc;

no_work:
	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
		      node_len);

	return rc;
}

static int ghes_in_nmi_spool_from_list(struct list_head *rcu_list,
				       enum fixed_addresses fixmap_idx)
{
	int ret = -ENOENT;
	struct ghes *ghes;

	rcu_read_lock();
	list_for_each_entry_rcu(ghes, rcu_list, list) {
		if (!ghes_in_nmi_queue_one_entry(ghes, fixmap_idx))
			ret = 0;
	}
	rcu_read_unlock();

	if (IS_ENABLED(CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG) && !ret)
		irq_work_queue(&ghes_proc_irq_work);

	return ret;
}

#ifdef CONFIG_ACPI_APEI_SEA
static LIST_HEAD(ghes_sea);

/*
 * Return 0 only if one of the SEA error sources successfully reported an error
 * record sent from the firmware.
 */
int ghes_notify_sea(void)
{
	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sea);
	int rv;

	raw_spin_lock(&ghes_notify_lock_sea);
	rv = ghes_in_nmi_spool_from_list(&ghes_sea, FIX_APEI_GHES_SEA);
	raw_spin_unlock(&ghes_notify_lock_sea);

	return rv;
}

static void ghes_sea_add(struct ghes *ghes)
{
	mutex_lock(&ghes_list_mutex);
	list_add_rcu(&ghes->list, &ghes_sea);
	mutex_unlock(&ghes_list_mutex);
}

static void ghes_sea_remove(struct ghes *ghes)
{
	mutex_lock(&ghes_list_mutex);
	list_del_rcu(&ghes->list);
	mutex_unlock(&ghes_list_mutex);
	synchronize_rcu();
}
#else /* CONFIG_ACPI_APEI_SEA */
static inline void ghes_sea_add(struct ghes *ghes) { }
static inline void ghes_sea_remove(struct ghes *ghes) { }
#endif /* CONFIG_ACPI_APEI_SEA */

#ifdef CONFIG_HAVE_ACPI_APEI_NMI
/*
 * NMI may be triggered on any CPU, so ghes_in_nmi is used for
 * having only one concurrent reader.
 */
static atomic_t ghes_in_nmi = ATOMIC_INIT(0);

static LIST_HEAD(ghes_nmi);

static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
{
	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_nmi);
	int ret = NMI_DONE;

	if (!atomic_add_unless(&ghes_in_nmi, 1, 1))
		return ret;

	raw_spin_lock(&ghes_notify_lock_nmi);
	if (!ghes_in_nmi_spool_from_list(&ghes_nmi, FIX_APEI_GHES_NMI))
		ret = NMI_HANDLED;
	raw_spin_unlock(&ghes_notify_lock_nmi);

	atomic_dec(&ghes_in_nmi);
	return ret;
}

static void ghes_nmi_add(struct ghes *ghes)
{
	mutex_lock(&ghes_list_mutex);
	if (list_empty(&ghes_nmi))
		register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, "ghes");
	list_add_rcu(&ghes->list, &ghes_nmi);
	mutex_unlock(&ghes_list_mutex);
}

static void ghes_nmi_remove(struct ghes *ghes)
{
	mutex_lock(&ghes_list_mutex);
	list_del_rcu(&ghes->list);
	if (list_empty(&ghes_nmi))
		unregister_nmi_handler(NMI_LOCAL, "ghes");
	mutex_unlock(&ghes_list_mutex);
	/*
	 * To synchronize with NMI handler, ghes can only be
	 * freed after NMI handler finishes.
	 */
	synchronize_rcu();
}
#else /* CONFIG_HAVE_ACPI_APEI_NMI */
static inline void ghes_nmi_add(struct ghes *ghes) { }
static inline void ghes_nmi_remove(struct ghes *ghes) { }
#endif /* CONFIG_HAVE_ACPI_APEI_NMI */

static void ghes_nmi_init_cxt(void)
{
	init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq);
}

static int __ghes_sdei_callback(struct ghes *ghes,
				enum fixed_addresses fixmap_idx)
{
	if (!ghes_in_nmi_queue_one_entry(ghes, fixmap_idx)) {
		irq_work_queue(&ghes_proc_irq_work);

		return 0;
	}

	return -ENOENT;
}

static int ghes_sdei_normal_callback(u32 event_num, struct pt_regs *regs,
				      void *arg)
{
	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sdei_normal);
	struct ghes *ghes = arg;
	int err;

	raw_spin_lock(&ghes_notify_lock_sdei_normal);
	err = __ghes_sdei_callback(ghes, FIX_APEI_GHES_SDEI_NORMAL);
	raw_spin_unlock(&ghes_notify_lock_sdei_normal);

	return err;
}

static int ghes_sdei_critical_callback(u32 event_num, struct pt_regs *regs,
				       void *arg)
{
	static DEFINE_RAW_SPINLOCK(ghes_notify_lock_sdei_critical);
	struct ghes *ghes = arg;
	int err;

	raw_spin_lock(&ghes_notify_lock_sdei_critical);
	err = __ghes_sdei_callback(ghes, FIX_APEI_GHES_SDEI_CRITICAL);
	raw_spin_unlock(&ghes_notify_lock_sdei_critical);

	return err;
}

static int apei_sdei_register_ghes(struct ghes *ghes)
{
	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
		return -EOPNOTSUPP;

	return sdei_register_ghes(ghes, ghes_sdei_normal_callback,
				 ghes_sdei_critical_callback);
}

static int apei_sdei_unregister_ghes(struct ghes *ghes)
{
	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
		return -EOPNOTSUPP;

	return sdei_unregister_ghes(ghes);
}

static int ghes_probe(struct platform_device *ghes_dev)
{
	struct acpi_hest_generic *generic;
	struct ghes *ghes = NULL;
	unsigned long flags;

	int rc = -EINVAL;

	generic = *(struct acpi_hest_generic **)ghes_dev->dev.platform_data;
	if (!generic->enabled)
		return -ENODEV;

	switch (generic->notify.type) {
	case ACPI_HEST_NOTIFY_POLLED:
	case ACPI_HEST_NOTIFY_EXTERNAL:
	case ACPI_HEST_NOTIFY_SCI:
	case ACPI_HEST_NOTIFY_GSIV:
	case ACPI_HEST_NOTIFY_GPIO:
		break;

	case ACPI_HEST_NOTIFY_SEA:
		if (!IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
			pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEA is not supported\n",
				generic->header.source_id);
			rc = -ENOTSUPP;
			goto err;
		}
		break;
	case ACPI_HEST_NOTIFY_NMI:
		if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
			pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
				generic->header.source_id);
			goto err;
		}
		break;
	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
		if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE)) {
			pr_warn(GHES_PFX "Generic hardware error source: %d notified via SDE Interface is not supported!\n",
				generic->header.source_id);
			goto err;
		}
		break;
	case ACPI_HEST_NOTIFY_LOCAL:
		pr_warn(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
			generic->header.source_id);
		goto err;
	default:
		pr_warn(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n",
			generic->notify.type, generic->header.source_id);
		goto err;
	}

	rc = -EIO;
	if (generic->error_block_length <
	    sizeof(struct acpi_hest_generic_status)) {
		pr_warn(FW_BUG GHES_PFX "Invalid error block length: %u for generic hardware error source: %d\n",
			generic->error_block_length, generic->header.source_id);
		goto err;
	}
	ghes = ghes_new(generic);
	if (IS_ERR(ghes)) {
		rc = PTR_ERR(ghes);
		ghes = NULL;
		goto err;
	}

	switch (generic->notify.type) {
	case ACPI_HEST_NOTIFY_POLLED:
		timer_setup(&ghes->timer, ghes_poll_func, 0);
		ghes_add_timer(ghes);
		break;
	case ACPI_HEST_NOTIFY_EXTERNAL:
		/* External interrupt vector is GSI */
		rc = acpi_gsi_to_irq(generic->notify.vector, &ghes->irq);
		if (rc) {
			pr_err(GHES_PFX "Failed to map GSI to IRQ for generic hardware error source: %d\n",
			       generic->header.source_id);
			goto err;
		}
		rc = request_irq(ghes->irq, ghes_irq_func, IRQF_SHARED,
				 "GHES IRQ", ghes);
		if (rc) {
			pr_err(GHES_PFX "Failed to register IRQ for generic hardware error source: %d\n",
			       generic->header.source_id);
			goto err;
		}
		break;

	case ACPI_HEST_NOTIFY_SCI:
	case ACPI_HEST_NOTIFY_GSIV:
	case ACPI_HEST_NOTIFY_GPIO:
		mutex_lock(&ghes_list_mutex);
		if (list_empty(&ghes_hed))
			register_acpi_hed_notifier(&ghes_notifier_hed);
		list_add_rcu(&ghes->list, &ghes_hed);
		mutex_unlock(&ghes_list_mutex);
		break;

	case ACPI_HEST_NOTIFY_SEA:
		ghes_sea_add(ghes);
		break;
	case ACPI_HEST_NOTIFY_NMI:
		ghes_nmi_add(ghes);
		break;
	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
		rc = apei_sdei_register_ghes(ghes);
		if (rc)
			goto err;
		break;
	default:
		BUG();
	}

	platform_set_drvdata(ghes_dev, ghes);

	ghes_edac_register(ghes, &ghes_dev->dev);

	/* Handle any pending errors right away */
	spin_lock_irqsave(&ghes_notify_lock_irq, flags);
	ghes_proc(ghes);
	spin_unlock_irqrestore(&ghes_notify_lock_irq, flags);

	return 0;

err:
	if (ghes) {
		ghes_fini(ghes);
		kfree(ghes);
	}
	return rc;
}

static int ghes_remove(struct platform_device *ghes_dev)
{
	int rc;
	struct ghes *ghes;
	struct acpi_hest_generic *generic;

	ghes = platform_get_drvdata(ghes_dev);
	generic = ghes->generic;

	ghes->flags |= GHES_EXITING;
	switch (generic->notify.type) {
	case ACPI_HEST_NOTIFY_POLLED:
		del_timer_sync(&ghes->timer);
		break;
	case ACPI_HEST_NOTIFY_EXTERNAL:
		free_irq(ghes->irq, ghes);
		break;

	case ACPI_HEST_NOTIFY_SCI:
	case ACPI_HEST_NOTIFY_GSIV:
	case ACPI_HEST_NOTIFY_GPIO:
		mutex_lock(&ghes_list_mutex);
		list_del_rcu(&ghes->list);
		if (list_empty(&ghes_hed))
			unregister_acpi_hed_notifier(&ghes_notifier_hed);
		mutex_unlock(&ghes_list_mutex);
		synchronize_rcu();
		break;

	case ACPI_HEST_NOTIFY_SEA:
		ghes_sea_remove(ghes);
		break;
	case ACPI_HEST_NOTIFY_NMI:
		ghes_nmi_remove(ghes);
		break;
	case ACPI_HEST_NOTIFY_SOFTWARE_DELEGATED:
		rc = apei_sdei_unregister_ghes(ghes);
		if (rc)
			return rc;
		break;
	default:
		BUG();
		break;
	}

	ghes_fini(ghes);

	ghes_edac_unregister(ghes);

	kfree(ghes);

	return 0;
}

static struct platform_driver ghes_platform_driver = {
	.driver		= {
		.name	= "GHES",
	},
	.probe		= ghes_probe,
	.remove		= ghes_remove,
};

void __init acpi_ghes_init(void)
{
	int rc;

	sdei_init();

	if (acpi_disabled)
		return;

	switch (hest_disable) {
	case HEST_NOT_FOUND:
		return;
	case HEST_DISABLED:
		pr_info(GHES_PFX "HEST is not enabled!\n");
		return;
	default:
		break;
	}

	if (ghes_disable) {
		pr_info(GHES_PFX "GHES is not enabled!\n");
		return;
	}

	ghes_nmi_init_cxt();

	rc = platform_driver_register(&ghes_platform_driver);
	if (rc)
		return;

	rc = apei_osc_setup();
	if (rc == 0 && osc_sb_apei_support_acked)
		pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit and WHEA _OSC.\n");
	else if (rc == 0 && !osc_sb_apei_support_acked)
		pr_info(GHES_PFX "APEI firmware first mode is enabled by WHEA _OSC.\n");
	else if (rc && osc_sb_apei_support_acked)
		pr_info(GHES_PFX "APEI firmware first mode is enabled by APEI bit.\n");
	else
		pr_info(GHES_PFX "Failed to enable APEI firmware first mode.\n");
}