aboutsummaryrefslogtreecommitdiff
path: root/drivers/acpi/apei/erst.c
blob: eb9fab5b96e4d3dca071e11e8dbdec2405b23508 (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
/*
 * APEI Error Record Serialization Table support
 *
 * ERST is a way provided by APEI to save and retrieve hardware error
 * information to and from a persistent store.
 *
 * For more information about ERST, please refer to ACPI Specification
 * version 4.0, section 17.4.
 *
 * Copyright 2010 Intel Corp.
 *   Author: Huang Ying <ying.huang@intel.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version
 * 2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/io.h>
#include <linux/acpi.h>
#include <linux/uaccess.h>
#include <linux/cper.h>
#include <linux/nmi.h>
#include <linux/hardirq.h>
#include <linux/pstore.h>
#include <acpi/apei.h>

#include "apei-internal.h"

#define ERST_PFX "ERST: "

/* ERST command status */
#define ERST_STATUS_SUCCESS			0x0
#define ERST_STATUS_NOT_ENOUGH_SPACE		0x1
#define ERST_STATUS_HARDWARE_NOT_AVAILABLE	0x2
#define ERST_STATUS_FAILED			0x3
#define ERST_STATUS_RECORD_STORE_EMPTY		0x4
#define ERST_STATUS_RECORD_NOT_FOUND		0x5

#define ERST_TAB_ENTRY(tab)						\
	((struct acpi_whea_header *)((char *)(tab) +			\
				     sizeof(struct acpi_table_erst)))

#define SPIN_UNIT		100			/* 100ns */
/* Firmware should respond within 1 milliseconds */
#define FIRMWARE_TIMEOUT	(1 * NSEC_PER_MSEC)
#define FIRMWARE_MAX_STALL	50			/* 50us */

int erst_disable;
EXPORT_SYMBOL_GPL(erst_disable);

static struct acpi_table_erst *erst_tab;

/* ERST Error Log Address Range atrributes */
#define ERST_RANGE_RESERVED	0x0001
#define ERST_RANGE_NVRAM	0x0002
#define ERST_RANGE_SLOW		0x0004

/*
 * ERST Error Log Address Range, used as buffer for reading/writing
 * error records.
 */
static struct erst_erange {
	u64 base;
	u64 size;
	void __iomem *vaddr;
	u32 attr;
} erst_erange;

/*
 * Prevent ERST interpreter to run simultaneously, because the
 * corresponding firmware implementation may not work properly when
 * invoked simultaneously.
 *
 * It is used to provide exclusive accessing for ERST Error Log
 * Address Range too.
 */
static DEFINE_RAW_SPINLOCK(erst_lock);

static inline int erst_errno(int command_status)
{
	switch (command_status) {
	case ERST_STATUS_SUCCESS:
		return 0;
	case ERST_STATUS_HARDWARE_NOT_AVAILABLE:
		return -ENODEV;
	case ERST_STATUS_NOT_ENOUGH_SPACE:
		return -ENOSPC;
	case ERST_STATUS_RECORD_STORE_EMPTY:
	case ERST_STATUS_RECORD_NOT_FOUND:
		return -ENOENT;
	default:
		return -EINVAL;
	}
}

static int erst_timedout(u64 *t, u64 spin_unit)
{
	if ((s64)*t < spin_unit) {
		pr_warning(FW_WARN ERST_PFX
			   "Firmware does not respond in time\n");
		return 1;
	}
	*t -= spin_unit;
	ndelay(spin_unit);
	touch_nmi_watchdog();
	return 0;
}

static int erst_exec_load_var1(struct apei_exec_context *ctx,
			       struct acpi_whea_header *entry)
{
	return __apei_exec_read_register(entry, &ctx->var1);
}

static int erst_exec_load_var2(struct apei_exec_context *ctx,
			       struct acpi_whea_header *entry)
{
	return __apei_exec_read_register(entry, &ctx->var2);
}

static int erst_exec_store_var1(struct apei_exec_context *ctx,
				struct acpi_whea_header *entry)
{
	return __apei_exec_write_register(entry, ctx->var1);
}

static int erst_exec_add(struct apei_exec_context *ctx,
			 struct acpi_whea_header *entry)
{
	ctx->var1 += ctx->var2;
	return 0;
}

static int erst_exec_subtract(struct apei_exec_context *ctx,
			      struct acpi_whea_header *entry)
{
	ctx->var1 -= ctx->var2;
	return 0;
}

static int erst_exec_add_value(struct apei_exec_context *ctx,
			       struct acpi_whea_header *entry)
{
	int rc;
	u64 val;

	rc = __apei_exec_read_register(entry, &val);
	if (rc)
		return rc;
	val += ctx->value;
	rc = __apei_exec_write_register(entry, val);
	return rc;
}

static int erst_exec_subtract_value(struct apei_exec_context *ctx,
				    struct acpi_whea_header *entry)
{
	int rc;
	u64 val;

	rc = __apei_exec_read_register(entry, &val);
	if (rc)
		return rc;
	val -= ctx->value;
	rc = __apei_exec_write_register(entry, val);
	return rc;
}

static int erst_exec_stall(struct apei_exec_context *ctx,
			   struct acpi_whea_header *entry)
{
	u64 stall_time;

	if (ctx->value > FIRMWARE_MAX_STALL) {
		if (!in_nmi())
			pr_warning(FW_WARN ERST_PFX
			"Too long stall time for stall instruction: %llx.\n",
				   ctx->value);
		stall_time = FIRMWARE_MAX_STALL;
	} else
		stall_time = ctx->value;
	udelay(stall_time);
	return 0;
}

static int erst_exec_stall_while_true(struct apei_exec_context *ctx,
				      struct acpi_whea_header *entry)
{
	int rc;
	u64 val;
	u64 timeout = FIRMWARE_TIMEOUT;
	u64 stall_time;

	if (ctx->var1 > FIRMWARE_MAX_STALL) {
		if (!in_nmi())
			pr_warning(FW_WARN ERST_PFX
		"Too long stall time for stall while true instruction: %llx.\n",
				   ctx->var1);
		stall_time = FIRMWARE_MAX_STALL;
	} else
		stall_time = ctx->var1;

	for (;;) {
		rc = __apei_exec_read_register(entry, &val);
		if (rc)
			return rc;
		if (val != ctx->value)
			break;
		if (erst_timedout(&timeout, stall_time * NSEC_PER_USEC))
			return -EIO;
	}
	return 0;
}

static int erst_exec_skip_next_instruction_if_true(
	struct apei_exec_context *ctx,
	struct acpi_whea_header *entry)
{
	int rc;
	u64 val;

	rc = __apei_exec_read_register(entry, &val);
	if (rc)
		return rc;
	if (val == ctx->value) {
		ctx->ip += 2;
		return APEI_EXEC_SET_IP;
	}

	return 0;
}

static int erst_exec_goto(struct apei_exec_context *ctx,
			  struct acpi_whea_header *entry)
{
	ctx->ip = ctx->value;
	return APEI_EXEC_SET_IP;
}

static int erst_exec_set_src_address_base(struct apei_exec_context *ctx,
					  struct acpi_whea_header *entry)
{
	return __apei_exec_read_register(entry, &ctx->src_base);
}

static int erst_exec_set_dst_address_base(struct apei_exec_context *ctx,
					  struct acpi_whea_header *entry)
{
	return __apei_exec_read_register(entry, &ctx->dst_base);
}

static int erst_exec_move_data(struct apei_exec_context *ctx,
			       struct acpi_whea_header *entry)
{
	int rc;
	u64 offset;
	void *src, *dst;

	/* ioremap does not work in interrupt context */
	if (in_interrupt()) {
		pr_warning(ERST_PFX
			   "MOVE_DATA can not be used in interrupt context");
		return -EBUSY;
	}

	rc = __apei_exec_read_register(entry, &offset);
	if (rc)
		return rc;

	src = ioremap(ctx->src_base + offset, ctx->var2);
	if (!src)
		return -ENOMEM;
	dst = ioremap(ctx->dst_base + offset, ctx->var2);
	if (!dst)
		return -ENOMEM;

	memmove(dst, src, ctx->var2);

	iounmap(src);
	iounmap(dst);

	return 0;
}

static struct apei_exec_ins_type erst_ins_type[] = {
	[ACPI_ERST_READ_REGISTER] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = apei_exec_read_register,
	},
	[ACPI_ERST_READ_REGISTER_VALUE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = apei_exec_read_register_value,
	},
	[ACPI_ERST_WRITE_REGISTER] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = apei_exec_write_register,
	},
	[ACPI_ERST_WRITE_REGISTER_VALUE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = apei_exec_write_register_value,
	},
	[ACPI_ERST_NOOP] = {
		.flags = 0,
		.run = apei_exec_noop,
	},
	[ACPI_ERST_LOAD_VAR1] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_load_var1,
	},
	[ACPI_ERST_LOAD_VAR2] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_load_var2,
	},
	[ACPI_ERST_STORE_VAR1] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_store_var1,
	},
	[ACPI_ERST_ADD] = {
		.flags = 0,
		.run = erst_exec_add,
	},
	[ACPI_ERST_SUBTRACT] = {
		.flags = 0,
		.run = erst_exec_subtract,
	},
	[ACPI_ERST_ADD_VALUE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_add_value,
	},
	[ACPI_ERST_SUBTRACT_VALUE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_subtract_value,
	},
	[ACPI_ERST_STALL] = {
		.flags = 0,
		.run = erst_exec_stall,
	},
	[ACPI_ERST_STALL_WHILE_TRUE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_stall_while_true,
	},
	[ACPI_ERST_SKIP_NEXT_IF_TRUE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_skip_next_instruction_if_true,
	},
	[ACPI_ERST_GOTO] = {
		.flags = 0,
		.run = erst_exec_goto,
	},
	[ACPI_ERST_SET_SRC_ADDRESS_BASE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_set_src_address_base,
	},
	[ACPI_ERST_SET_DST_ADDRESS_BASE] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_set_dst_address_base,
	},
	[ACPI_ERST_MOVE_DATA] = {
		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
		.run = erst_exec_move_data,
	},
};

static inline void erst_exec_ctx_init(struct apei_exec_context *ctx)
{
	apei_exec_ctx_init(ctx, erst_ins_type, ARRAY_SIZE(erst_ins_type),
			   ERST_TAB_ENTRY(erst_tab), erst_tab->entries);
}

static int erst_get_erange(struct erst_erange *range)
{
	struct apei_exec_context ctx;
	int rc;

	erst_exec_ctx_init(&ctx);
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_ERROR_RANGE);
	if (rc)
		return rc;
	range->base = apei_exec_ctx_get_output(&ctx);
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_ERROR_LENGTH);
	if (rc)
		return rc;
	range->size = apei_exec_ctx_get_output(&ctx);
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_ERROR_ATTRIBUTES);
	if (rc)
		return rc;
	range->attr = apei_exec_ctx_get_output(&ctx);

	return 0;
}

static ssize_t __erst_get_record_count(void)
{
	struct apei_exec_context ctx;
	int rc;

	erst_exec_ctx_init(&ctx);
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_RECORD_COUNT);
	if (rc)
		return rc;
	return apei_exec_ctx_get_output(&ctx);
}

ssize_t erst_get_record_count(void)
{
	ssize_t count;
	unsigned long flags;

	if (erst_disable)
		return -ENODEV;

	raw_spin_lock_irqsave(&erst_lock, flags);
	count = __erst_get_record_count();
	raw_spin_unlock_irqrestore(&erst_lock, flags);

	return count;
}
EXPORT_SYMBOL_GPL(erst_get_record_count);

#define ERST_RECORD_ID_CACHE_SIZE_MIN	16
#define ERST_RECORD_ID_CACHE_SIZE_MAX	1024

struct erst_record_id_cache {
	struct mutex lock;
	u64 *entries;
	int len;
	int size;
	int refcount;
};

static struct erst_record_id_cache erst_record_id_cache = {
	.lock = __MUTEX_INITIALIZER(erst_record_id_cache.lock),
	.refcount = 0,
};

static int __erst_get_next_record_id(u64 *record_id)
{
	struct apei_exec_context ctx;
	int rc;

	erst_exec_ctx_init(&ctx);
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_RECORD_ID);
	if (rc)
		return rc;
	*record_id = apei_exec_ctx_get_output(&ctx);

	return 0;
}

int erst_get_record_id_begin(int *pos)
{
	int rc;

	if (erst_disable)
		return -ENODEV;

	rc = mutex_lock_interruptible(&erst_record_id_cache.lock);
	if (rc)
		return rc;
	erst_record_id_cache.refcount++;
	mutex_unlock(&erst_record_id_cache.lock);

	*pos = 0;

	return 0;
}
EXPORT_SYMBOL_GPL(erst_get_record_id_begin);

/* erst_record_id_cache.lock must be held by caller */
static int __erst_record_id_cache_add_one(void)
{
	u64 id, prev_id, first_id;
	int i, rc;
	u64 *entries;
	unsigned long flags;

	id = prev_id = first_id = APEI_ERST_INVALID_RECORD_ID;
retry:
	raw_spin_lock_irqsave(&erst_lock, flags);
	rc = __erst_get_next_record_id(&id);
	raw_spin_unlock_irqrestore(&erst_lock, flags);
	if (rc == -ENOENT)
		return 0;
	if (rc)
		return rc;
	if (id == APEI_ERST_INVALID_RECORD_ID)
		return 0;
	/* can not skip current ID, or loop back to first ID */
	if (id == prev_id || id == first_id)
		return 0;
	if (first_id == APEI_ERST_INVALID_RECORD_ID)
		first_id = id;
	prev_id = id;

	entries = erst_record_id_cache.entries;
	for (i = 0; i < erst_record_id_cache.len; i++) {
		if (entries[i] == id)
			break;
	}
	/* record id already in cache, try next */
	if (i < erst_record_id_cache.len)
		goto retry;
	if (erst_record_id_cache.len >= erst_record_id_cache.size) {
		int new_size, alloc_size;
		u64 *new_entries;

		new_size = erst_record_id_cache.size * 2;
		new_size = clamp_val(new_size, ERST_RECORD_ID_CACHE_SIZE_MIN,
				     ERST_RECORD_ID_CACHE_SIZE_MAX);
		if (new_size <= erst_record_id_cache.size) {
			if (printk_ratelimit())
				pr_warning(FW_WARN ERST_PFX
					   "too many record ID!\n");
			return 0;
		}
		alloc_size = new_size * sizeof(entries[0]);
		if (alloc_size < PAGE_SIZE)
			new_entries = kmalloc(alloc_size, GFP_KERNEL);
		else
			new_entries = vmalloc(alloc_size);
		if (!new_entries)
			return -ENOMEM;
		memcpy(new_entries, entries,
		       erst_record_id_cache.len * sizeof(entries[0]));
		if (erst_record_id_cache.size < PAGE_SIZE)
			kfree(entries);
		else
			vfree(entries);
		erst_record_id_cache.entries = entries = new_entries;
		erst_record_id_cache.size = new_size;
	}
	entries[i] = id;
	erst_record_id_cache.len++;

	return 1;
}

/*
 * Get the record ID of an existing error record on the persistent
 * storage. If there is no error record on the persistent storage, the
 * returned record_id is APEI_ERST_INVALID_RECORD_ID.
 */
int erst_get_record_id_next(int *pos, u64 *record_id)
{
	int rc = 0;
	u64 *entries;

	if (erst_disable)
		return -ENODEV;

	/* must be enclosed by erst_get_record_id_begin/end */
	BUG_ON(!erst_record_id_cache.refcount);
	BUG_ON(*pos < 0 || *pos > erst_record_id_cache.len);

	mutex_lock(&erst_record_id_cache.lock);
	entries = erst_record_id_cache.entries;
	for (; *pos < erst_record_id_cache.len; (*pos)++)
		if (entries[*pos] != APEI_ERST_INVALID_RECORD_ID)
			break;
	/* found next record id in cache */
	if (*pos < erst_record_id_cache.len) {
		*record_id = entries[*pos];
		(*pos)++;
		goto out_unlock;
	}

	/* Try to add one more record ID to cache */
	rc = __erst_record_id_cache_add_one();
	if (rc < 0)
		goto out_unlock;
	/* successfully add one new ID */
	if (rc == 1) {
		*record_id = erst_record_id_cache.entries[*pos];
		(*pos)++;
		rc = 0;
	} else {
		*pos = -1;
		*record_id = APEI_ERST_INVALID_RECORD_ID;
	}
out_unlock:
	mutex_unlock(&erst_record_id_cache.lock);

	return rc;
}
EXPORT_SYMBOL_GPL(erst_get_record_id_next);

/* erst_record_id_cache.lock must be held by caller */
static void __erst_record_id_cache_compact(void)
{
	int i, wpos = 0;
	u64 *entries;

	if (erst_record_id_cache.refcount)
		return;

	entries = erst_record_id_cache.entries;
	for (i = 0; i < erst_record_id_cache.len; i++) {
		if (entries[i] == APEI_ERST_INVALID_RECORD_ID)
			continue;
		if (wpos != i)
			memcpy(&entries[wpos], &entries[i], sizeof(entries[i]));
		wpos++;
	}
	erst_record_id_cache.len = wpos;
}

void erst_get_record_id_end(void)
{
	/*
	 * erst_disable != 0 should be detected by invoker via the
	 * return value of erst_get_record_id_begin/next, so this
	 * function should not be called for erst_disable != 0.
	 */
	BUG_ON(erst_disable);

	mutex_lock(&erst_record_id_cache.lock);
	erst_record_id_cache.refcount--;
	BUG_ON(erst_record_id_cache.refcount < 0);
	__erst_record_id_cache_compact();
	mutex_unlock(&erst_record_id_cache.lock);
}
EXPORT_SYMBOL_GPL(erst_get_record_id_end);

static int __erst_write_to_storage(u64 offset)
{
	struct apei_exec_context ctx;
	u64 timeout = FIRMWARE_TIMEOUT;
	u64 val;
	int rc;

	erst_exec_ctx_init(&ctx);
	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_WRITE);
	if (rc)
		return rc;
	apei_exec_ctx_set_input(&ctx, offset);
	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_OFFSET);
	if (rc)
		return rc;
	rc = apei_exec_run(&ctx, ACPI_ERST_EXECUTE_OPERATION);
	if (rc)
		return rc;
	for (;;) {
		rc = apei_exec_run(&ctx, ACPI_ERST_CHECK_BUSY_STATUS);
		if (rc)
			return rc;
		val = apei_exec_ctx_get_output(&ctx);
		if (!val)
			break;
		if (erst_timedout(&timeout, SPIN_UNIT))
			return -EIO;
	}
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS);
	if (rc)
		return rc;
	val = apei_exec_ctx_get_output(&ctx);
	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
	if (rc)
		return rc;

	return erst_errno(val);
}

static int __erst_read_from_storage(u64 record_id, u64 offset)
{
	struct apei_exec_context ctx;
	u64 timeout = FIRMWARE_TIMEOUT;
	u64 val;
	int rc;

	erst_exec_ctx_init(&ctx);
	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_READ);
	if (rc)
		return rc;
	apei_exec_ctx_set_input(&ctx, offset);
	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_OFFSET);
	if (rc)
		return rc;
	apei_exec_ctx_set_input(&ctx, record_id);
	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_ID);
	if (rc)
		return rc;
	rc = apei_exec_run(&ctx, ACPI_ERST_EXECUTE_OPERATION);
	if (rc)
		return rc;
	for (;;) {
		rc = apei_exec_run(&ctx, ACPI_ERST_CHECK_BUSY_STATUS);
		if (rc)
			return rc;
		val = apei_exec_ctx_get_output(&ctx);
		if (!val)
			break;
		if (erst_timedout(&timeout, SPIN_UNIT))
			return -EIO;
	};
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS);
	if (rc)
		return rc;
	val = apei_exec_ctx_get_output(&ctx);
	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
	if (rc)
		return rc;

	return erst_errno(val);
}

static int __erst_clear_from_storage(u64 record_id)
{
	struct apei_exec_context ctx;
	u64 timeout = FIRMWARE_TIMEOUT;
	u64 val;
	int rc;

	erst_exec_ctx_init(&ctx);
	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_CLEAR);
	if (rc)
		return rc;
	apei_exec_ctx_set_input(&ctx, record_id);
	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_ID);
	if (rc)
		return rc;
	rc = apei_exec_run(&ctx, ACPI_ERST_EXECUTE_OPERATION);
	if (rc)
		return rc;
	for (;;) {
		rc = apei_exec_run(&ctx, ACPI_ERST_CHECK_BUSY_STATUS);
		if (rc)
			return rc;
		val = apei_exec_ctx_get_output(&ctx);
		if (!val)
			break;
		if (erst_timedout(&timeout, SPIN_UNIT))
			return -EIO;
	}
	rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS);
	if (rc)
		return rc;
	val = apei_exec_ctx_get_output(&ctx);
	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
	if (rc)
		return rc;

	return erst_errno(val);
}

/* NVRAM ERST Error Log Address Range is not supported yet */
static void pr_unimpl_nvram(void)
{
	if (printk_ratelimit())
		pr_warning(ERST_PFX
		"NVRAM ERST Log Address Range is not implemented yet\n");
}

static int __erst_write_to_nvram(const struct cper_record_header *record)
{
	/* do not print message, because printk is not safe for NMI */
	return -ENOSYS;
}

static int __erst_read_to_erange_from_nvram(u64 record_id, u64 *offset)
{
	pr_unimpl_nvram();
	return -ENOSYS;
}

static int __erst_clear_from_nvram(u64 record_id)
{
	pr_unimpl_nvram();
	return -ENOSYS;
}

int erst_write(const struct cper_record_header *record)
{
	int rc;
	unsigned long flags;
	struct cper_record_header *rcd_erange;

	if (erst_disable)
		return -ENODEV;

	if (memcmp(record->signature, CPER_SIG_RECORD, CPER_SIG_SIZE))
		return -EINVAL;

	if (erst_erange.attr & ERST_RANGE_NVRAM) {
		if (!raw_spin_trylock_irqsave(&erst_lock, flags))
			return -EBUSY;
		rc = __erst_write_to_nvram(record);
		raw_spin_unlock_irqrestore(&erst_lock, flags);
		return rc;
	}

	if (record->record_length > erst_erange.size)
		return -EINVAL;

	if (!raw_spin_trylock_irqsave(&erst_lock, flags))
		return -EBUSY;
	memcpy(erst_erange.vaddr, record, record->record_length);
	rcd_erange = erst_erange.vaddr;
	/* signature for serialization system */
	memcpy(&rcd_erange->persistence_information, "ER", 2);

	rc = __erst_write_to_storage(0);
	raw_spin_unlock_irqrestore(&erst_lock, flags);

	return rc;
}
EXPORT_SYMBOL_GPL(erst_write);

static int __erst_read_to_erange(u64 record_id, u64 *offset)
{
	int rc;

	if (erst_erange.attr & ERST_RANGE_NVRAM)
		return __erst_read_to_erange_from_nvram(
			record_id, offset);

	rc = __erst_read_from_storage(record_id, 0);
	if (rc)
		return rc;
	*offset = 0;

	return 0;
}

static ssize_t __erst_read(u64 record_id, struct cper_record_header *record,
			   size_t buflen)
{
	int rc;
	u64 offset, len = 0;
	struct cper_record_header *rcd_tmp;

	rc = __erst_read_to_erange(record_id, &offset);
	if (rc)
		return rc;
	rcd_tmp = erst_erange.vaddr + offset;
	len = rcd_tmp->record_length;
	if (len <= buflen)
		memcpy(record, rcd_tmp, len);

	return len;
}

/*
 * If return value > buflen, the buffer size is not big enough,
 * else if return value < 0, something goes wrong,
 * else everything is OK, and return value is record length
 */
ssize_t erst_read(u64 record_id, struct cper_record_header *record,
		  size_t buflen)
{
	ssize_t len;
	unsigned long flags;

	if (erst_disable)
		return -ENODEV;

	raw_spin_lock_irqsave(&erst_lock, flags);
	len = __erst_read(record_id, record, buflen);
	raw_spin_unlock_irqrestore(&erst_lock, flags);
	return len;
}
EXPORT_SYMBOL_GPL(erst_read);

int erst_clear(u64 record_id)
{
	int rc, i;
	unsigned long flags;
	u64 *entries;

	if (erst_disable)
		return -ENODEV;

	rc = mutex_lock_interruptible(&erst_record_id_cache.lock);
	if (rc)
		return rc;
	raw_spin_lock_irqsave(&erst_lock, flags);
	if (erst_erange.attr & ERST_RANGE_NVRAM)
		rc = __erst_clear_from_nvram(record_id);
	else
		rc = __erst_clear_from_storage(record_id);
	raw_spin_unlock_irqrestore(&erst_lock, flags);
	if (rc)
		goto out;
	entries = erst_record_id_cache.entries;
	for (i = 0; i < erst_record_id_cache.len; i++) {
		if (entries[i] == record_id)
			entries[i] = APEI_ERST_INVALID_RECORD_ID;
	}
	__erst_record_id_cache_compact();
out:
	mutex_unlock(&erst_record_id_cache.lock);
	return rc;
}
EXPORT_SYMBOL_GPL(erst_clear);

static int __init setup_erst_disable(char *str)
{
	erst_disable = 1;
	return 0;
}

__setup("erst_disable", setup_erst_disable);

static int erst_check_table(struct acpi_table_erst *erst_tab)
{
	if ((erst_tab->header_length !=
	     (sizeof(struct acpi_table_erst) - sizeof(erst_tab->header)))
	    && (erst_tab->header_length != sizeof(struct acpi_table_einj)))
		return -EINVAL;
	if (erst_tab->header.length < sizeof(struct acpi_table_erst))
		return -EINVAL;
	if (erst_tab->entries !=
	    (erst_tab->header.length - sizeof(struct acpi_table_erst)) /
	    sizeof(struct acpi_erst_entry))
		return -EINVAL;

	return 0;
}

static int erst_open_pstore(struct pstore_info *psi);
static int erst_close_pstore(struct pstore_info *psi);
static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
			   struct timespec *time, char **buf,
			   struct pstore_info *psi);
static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
		       u64 *id, unsigned int part,
		       size_t size, struct pstore_info *psi);
static int erst_clearer(enum pstore_type_id type, u64 id,
			struct pstore_info *psi);

static struct pstore_info erst_info = {
	.owner		= THIS_MODULE,
	.name		= "erst",
	.open		= erst_open_pstore,
	.close		= erst_close_pstore,
	.read		= erst_reader,
	.write		= erst_writer,
	.erase		= erst_clearer
};

#define CPER_CREATOR_PSTORE						\
	UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,	\
		0x64, 0x90, 0xb8, 0x9d)
#define CPER_SECTION_TYPE_DMESG						\
	UUID_LE(0xc197e04e, 0xd545, 0x4a70, 0x9c, 0x17, 0xa5, 0x54,	\
		0x94, 0x19, 0xeb, 0x12)
#define CPER_SECTION_TYPE_MCE						\
	UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
		0x04, 0x4a, 0x38, 0xfc)

struct cper_pstore_record {
	struct cper_record_header hdr;
	struct cper_section_descriptor sec_hdr;
	char data[];
} __packed;

static int reader_pos;

static int erst_open_pstore(struct pstore_info *psi)
{
	int rc;

	if (erst_disable)
		return -ENODEV;

	rc = erst_get_record_id_begin(&reader_pos);

	return rc;
}

static int erst_close_pstore(struct pstore_info *psi)
{
	erst_get_record_id_end();

	return 0;
}

static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
			   struct timespec *time, char **buf,
			   struct pstore_info *psi)
{
	int rc;
	ssize_t len = 0;
	u64 record_id;
	struct cper_pstore_record *rcd;
	size_t rcd_len = sizeof(*rcd) + erst_info.bufsize;

	if (erst_disable)
		return -ENODEV;

	rcd = kmalloc(rcd_len, GFP_KERNEL);
	if (!rcd) {
		rc = -ENOMEM;
		goto out;
	}
skip:
	rc = erst_get_record_id_next(&reader_pos, &record_id);
	if (rc)
		goto out;

	/* no more record */
	if (record_id == APEI_ERST_INVALID_RECORD_ID) {
		rc = -EINVAL;
		goto out;
	}

	len = erst_read(record_id, &rcd->hdr, rcd_len);
	/* The record may be cleared by others, try read next record */
	if (len == -ENOENT)
		goto skip;
	else if (len < sizeof(*rcd)) {
		rc = -EIO;
		goto out;
	}
	if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0)
		goto skip;

	*buf = kmalloc(len, GFP_KERNEL);
	if (*buf == NULL) {
		rc = -ENOMEM;
		goto out;
	}
	memcpy(*buf, rcd->data, len - sizeof(*rcd));
	*id = record_id;
	if (uuid_le_cmp(rcd->sec_hdr.section_type,
			CPER_SECTION_TYPE_DMESG) == 0)
		*type = PSTORE_TYPE_DMESG;
	else if (uuid_le_cmp(rcd->sec_hdr.section_type,
			     CPER_SECTION_TYPE_MCE) == 0)
		*type = PSTORE_TYPE_MCE;
	else
		*type = PSTORE_TYPE_UNKNOWN;

	if (rcd->hdr.validation_bits & CPER_VALID_TIMESTAMP)
		time->tv_sec = rcd->hdr.timestamp;
	else
		time->tv_sec = 0;
	time->tv_nsec = 0;

out:
	kfree(rcd);
	return (rc < 0) ? rc : (len - sizeof(*rcd));
}

static int erst_writer(enum pstore_type_id type, enum kmsg_dump_reason reason,
		       u64 *id, unsigned int part,
		       size_t size, struct pstore_info *psi)
{
	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
					(erst_info.buf - sizeof(*rcd));
	int ret;

	memset(rcd, 0, sizeof(*rcd));
	memcpy(rcd->hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
	rcd->hdr.revision = CPER_RECORD_REV;
	rcd->hdr.signature_end = CPER_SIG_END;
	rcd->hdr.section_count = 1;
	rcd->hdr.error_severity = CPER_SEV_FATAL;
	/* timestamp valid. platform_id, partition_id are invalid */
	rcd->hdr.validation_bits = CPER_VALID_TIMESTAMP;
	rcd->hdr.timestamp = get_seconds();
	rcd->hdr.record_length = sizeof(*rcd) + size;
	rcd->hdr.creator_id = CPER_CREATOR_PSTORE;
	rcd->hdr.notification_type = CPER_NOTIFY_MCE;
	rcd->hdr.record_id = cper_next_record_id();
	rcd->hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR;

	rcd->sec_hdr.section_offset = sizeof(*rcd);
	rcd->sec_hdr.section_length = size;
	rcd->sec_hdr.revision = CPER_SEC_REV;
	/* fru_id and fru_text is invalid */
	rcd->sec_hdr.validation_bits = 0;
	rcd->sec_hdr.flags = CPER_SEC_PRIMARY;
	switch (type) {
	case PSTORE_TYPE_DMESG:
		rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG;
		break;
	case PSTORE_TYPE_MCE:
		rcd->sec_hdr.section_type = CPER_SECTION_TYPE_MCE;
		break;
	default:
		return -EINVAL;
	}
	rcd->sec_hdr.section_severity = CPER_SEV_FATAL;

	ret = erst_write(&rcd->hdr);
	*id = rcd->hdr.record_id;

	return ret;
}

static int erst_clearer(enum pstore_type_id type, u64 id,
			struct pstore_info *psi)
{
	return erst_clear(id);
}

static int __init erst_init(void)
{
	int rc = 0;
	acpi_status status;
	struct apei_exec_context ctx;
	struct apei_resources erst_resources;
	struct resource *r;
	char *buf;

	if (acpi_disabled)
		goto err;

	if (erst_disable) {
		pr_info(ERST_PFX
	"Error Record Serialization Table (ERST) support is disabled.\n");
		goto err;
	}

	status = acpi_get_table(ACPI_SIG_ERST, 0,
				(struct acpi_table_header **)&erst_tab);
	if (status == AE_NOT_FOUND)
		goto err;
	else if (ACPI_FAILURE(status)) {
		const char *msg = acpi_format_exception(status);
		pr_err(ERST_PFX "Failed to get table, %s\n", msg);
		rc = -EINVAL;
		goto err;
	}

	rc = erst_check_table(erst_tab);
	if (rc) {
		pr_err(FW_BUG ERST_PFX "ERST table is invalid\n");
		goto err;
	}

	apei_resources_init(&erst_resources);
	erst_exec_ctx_init(&ctx);
	rc = apei_exec_collect_resources(&ctx, &erst_resources);
	if (rc)
		goto err_fini;
	rc = apei_resources_request(&erst_resources, "APEI ERST");
	if (rc)
		goto err_fini;
	rc = apei_exec_pre_map_gars(&ctx);
	if (rc)
		goto err_release;
	rc = erst_get_erange(&erst_erange);
	if (rc) {
		if (rc == -ENODEV)
			pr_info(ERST_PFX
	"The corresponding hardware device or firmware implementation "
	"is not available.\n");
		else
			pr_err(ERST_PFX
			       "Failed to get Error Log Address Range.\n");
		goto err_unmap_reg;
	}

	r = request_mem_region(erst_erange.base, erst_erange.size, "APEI ERST");
	if (!r) {
		pr_err(ERST_PFX
		"Can not request iomem region <0x%16llx-0x%16llx> for ERST.\n",
		(unsigned long long)erst_erange.base,
		(unsigned long long)erst_erange.base + erst_erange.size);
		rc = -EIO;
		goto err_unmap_reg;
	}
	rc = -ENOMEM;
	erst_erange.vaddr = ioremap_cache(erst_erange.base,
					  erst_erange.size);
	if (!erst_erange.vaddr)
		goto err_release_erange;

	buf = kmalloc(erst_erange.size, GFP_KERNEL);
	spin_lock_init(&erst_info.buf_lock);
	if (buf) {
		erst_info.buf = buf + sizeof(struct cper_pstore_record);
		erst_info.bufsize = erst_erange.size -
				    sizeof(struct cper_pstore_record);
		if (pstore_register(&erst_info)) {
			pr_info(ERST_PFX "Could not register with persistent store\n");
			kfree(buf);
		}
	}

	pr_info(ERST_PFX
	"Error Record Serialization Table (ERST) support is initialized.\n");

	return 0;

err_release_erange:
	release_mem_region(erst_erange.base, erst_erange.size);
err_unmap_reg:
	apei_exec_post_unmap_gars(&ctx);
err_release:
	apei_resources_release(&erst_resources);
err_fini:
	apei_resources_fini(&erst_resources);
err:
	erst_disable = 1;
	return rc;
}

device_initcall(erst_init);