summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/fadump.c
blob: 4eab97292cc2ca8cca57d9d1a056094810ae2ee6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
 * dump with assistance from firmware. This approach does not use kexec,
 * instead firmware assists in booting the kdump kernel while preserving
 * memory contents. The most of the code implementation has been adapted
 * from phyp assisted dump implementation written by Linas Vepstas and
 * Manish Ahuja
 *
 * Copyright 2011 IBM Corporation
 * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
 */

#undef DEBUG
#define pr_fmt(fmt) "fadump: " fmt

#include <linux/string.h>
#include <linux/memblock.h>
#include <linux/delay.h>
#include <linux/seq_file.h>
#include <linux/crash_dump.h>
#include <linux/kobject.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/cma.h>
#include <linux/hugetlb.h>

#include <asm/debugfs.h>
#include <asm/page.h>
#include <asm/prom.h>
#include <asm/rtas.h>
#include <asm/fadump.h>
#include <asm/setup.h>

static struct fw_dump fw_dump;
static struct fadump_mem_struct fdm;
static const struct fadump_mem_struct *fdm_active;
#ifdef CONFIG_CMA
static struct cma *fadump_cma;
#endif

static DEFINE_MUTEX(fadump_mutex);
struct fad_crash_memory_ranges *crash_memory_ranges;
int crash_memory_ranges_size;
int crash_mem_ranges;
int max_crash_mem_ranges;

#ifdef CONFIG_CMA
/*
 * fadump_cma_init() - Initialize CMA area from a fadump reserved memory
 *
 * This function initializes CMA area from fadump reserved memory.
 * The total size of fadump reserved memory covers for boot memory size
 * + cpu data size + hpte size and metadata.
 * Initialize only the area equivalent to boot memory size for CMA use.
 * The reamining portion of fadump reserved memory will be not given
 * to CMA and pages for thoes will stay reserved. boot memory size is
 * aligned per CMA requirement to satisy cma_init_reserved_mem() call.
 * But for some reason even if it fails we still have the memory reservation
 * with us and we can still continue doing fadump.
 */
int __init fadump_cma_init(void)
{
	unsigned long long base, size;
	int rc;

	if (!fw_dump.fadump_enabled)
		return 0;

	/*
	 * Do not use CMA if user has provided fadump=nocma kernel parameter.
	 * Return 1 to continue with fadump old behaviour.
	 */
	if (fw_dump.nocma)
		return 1;

	base = fw_dump.reserve_dump_area_start;
	size = fw_dump.boot_memory_size;

	if (!size)
		return 0;

	rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma);
	if (rc) {
		pr_err("Failed to init cma area for firmware-assisted dump,%d\n", rc);
		/*
		 * Though the CMA init has failed we still have memory
		 * reservation with us. The reserved memory will be
		 * blocked from production system usage.  Hence return 1,
		 * so that we can continue with fadump.
		 */
		return 1;
	}

	/*
	 * So we now have successfully initialized cma area for fadump.
	 */
	pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
		"bytes of memory reserved for firmware-assisted dump\n",
		cma_get_size(fadump_cma),
		(unsigned long)cma_get_base(fadump_cma) >> 20,
		fw_dump.reserve_dump_area_size);
	return 1;
}
#else
static int __init fadump_cma_init(void) { return 1; }
#endif /* CONFIG_CMA */

/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node,
			const char *uname, int depth, void *data)
{
	const __be32 *sections;
	int i, num_sections;
	int size;
	const __be32 *token;

	if (depth != 1 || strcmp(uname, "rtas") != 0)
		return 0;

	/*
	 * Check if Firmware Assisted dump is supported. if yes, check
	 * if dump has been initiated on last reboot.
	 */
	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
	if (!token)
		return 1;

	fw_dump.fadump_supported = 1;
	fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);

	/*
	 * The 'ibm,kernel-dump' rtas node is present only if there is
	 * dump data waiting for us.
	 */
	fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
	if (fdm_active)
		fw_dump.dump_active = 1;

	/* Get the sizes required to store dump data for the firmware provided
	 * dump sections.
	 * For each dump section type supported, a 32bit cell which defines
	 * the ID of a supported section followed by two 32 bit cells which
	 * gives teh size of the section in bytes.
	 */
	sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
					&size);

	if (!sections)
		return 1;

	num_sections = size / (3 * sizeof(u32));

	for (i = 0; i < num_sections; i++, sections += 3) {
		u32 type = (u32)of_read_number(sections, 1);

		switch (type) {
		case FADUMP_CPU_STATE_DATA:
			fw_dump.cpu_state_data_size =
					of_read_ulong(&sections[1], 2);
			break;
		case FADUMP_HPTE_REGION:
			fw_dump.hpte_region_size =
					of_read_ulong(&sections[1], 2);
			break;
		}
	}

	return 1;
}

/*
 * If fadump is registered, check if the memory provided
 * falls within boot memory area and reserved memory area.
 */
int is_fadump_memory_area(u64 addr, ulong size)
{
	u64 d_start = fw_dump.reserve_dump_area_start;
	u64 d_end = d_start + fw_dump.reserve_dump_area_size;

	if (!fw_dump.dump_registered)
		return 0;

	if (((addr + size) > d_start) && (addr <= d_end))
		return 1;

	return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size;
}

int should_fadump_crash(void)
{
	if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr)
		return 0;
	return 1;
}

int is_fadump_active(void)
{
	return fw_dump.dump_active;
}

/*
 * Returns 1, if there are no holes in boot memory area,
 * 0 otherwise.
 */
static int is_boot_memory_area_contiguous(void)
{
	struct memblock_region *reg;
	unsigned long tstart, tend;
	unsigned long start_pfn = PHYS_PFN(RMA_START);
	unsigned long end_pfn = PHYS_PFN(RMA_START + fw_dump.boot_memory_size);
	unsigned int ret = 0;

	for_each_memblock(memory, reg) {
		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
		if (tstart < tend) {
			/* Memory hole from start_pfn to tstart */
			if (tstart > start_pfn)
				break;

			if (tend == end_pfn) {
				ret = 1;
				break;
			}

			start_pfn = tend + 1;
		}
	}

	return ret;
}

/*
 * Returns true, if there are no holes in reserved memory area,
 * false otherwise.
 */
static bool is_reserved_memory_area_contiguous(void)
{
	struct memblock_region *reg;
	unsigned long start, end;
	unsigned long d_start = fw_dump.reserve_dump_area_start;
	unsigned long d_end = d_start + fw_dump.reserve_dump_area_size;

	for_each_memblock(memory, reg) {
		start = max(d_start, (unsigned long)reg->base);
		end = min(d_end, (unsigned long)(reg->base + reg->size));
		if (d_start < end) {
			/* Memory hole from d_start to start */
			if (start > d_start)
				break;

			if (end == d_end)
				return true;

			d_start = end + 1;
		}
	}

	return false;
}

/* Print firmware assisted dump configurations for debugging purpose. */
static void fadump_show_config(void)
{
	pr_debug("Support for firmware-assisted dump (fadump): %s\n",
			(fw_dump.fadump_supported ? "present" : "no support"));

	if (!fw_dump.fadump_supported)
		return;

	pr_debug("Fadump enabled    : %s\n",
				(fw_dump.fadump_enabled ? "yes" : "no"));
	pr_debug("Dump Active       : %s\n",
				(fw_dump.dump_active ? "yes" : "no"));
	pr_debug("Dump section sizes:\n");
	pr_debug("    CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
	pr_debug("    HPTE region size   : %lx\n", fw_dump.hpte_region_size);
	pr_debug("Boot memory size  : %lx\n", fw_dump.boot_memory_size);
}

static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
				unsigned long addr)
{
	if (!fdm)
		return 0;

	memset(fdm, 0, sizeof(struct fadump_mem_struct));
	addr = addr & PAGE_MASK;

	fdm->header.dump_format_version = cpu_to_be32(0x00000001);
	fdm->header.dump_num_sections = cpu_to_be16(3);
	fdm->header.dump_status_flag = 0;
	fdm->header.offset_first_dump_section =
		cpu_to_be32((u32)offsetof(struct fadump_mem_struct, cpu_state_data));

	/*
	 * Fields for disk dump option.
	 * We are not using disk dump option, hence set these fields to 0.
	 */
	fdm->header.dd_block_size = 0;
	fdm->header.dd_block_offset = 0;
	fdm->header.dd_num_blocks = 0;
	fdm->header.dd_offset_disk_path = 0;

	/* set 0 to disable an automatic dump-reboot. */
	fdm->header.max_time_auto = 0;

	/* Kernel dump sections */
	/* cpu state data section. */
	fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
	fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA);
	fdm->cpu_state_data.source_address = 0;
	fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size);
	fdm->cpu_state_data.destination_address = cpu_to_be64(addr);
	addr += fw_dump.cpu_state_data_size;

	/* hpte region section */
	fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
	fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION);
	fdm->hpte_region.source_address = 0;
	fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size);
	fdm->hpte_region.destination_address = cpu_to_be64(addr);
	addr += fw_dump.hpte_region_size;

	/* RMA region section */
	fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
	fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION);
	fdm->rmr_region.source_address = cpu_to_be64(RMA_START);
	fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size);
	fdm->rmr_region.destination_address = cpu_to_be64(addr);
	addr += fw_dump.boot_memory_size;

	return addr;
}

/**
 * fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
 *
 * Function to find the largest memory size we need to reserve during early
 * boot process. This will be the size of the memory that is required for a
 * kernel to boot successfully.
 *
 * This function has been taken from phyp-assisted dump feature implementation.
 *
 * returns larger of 256MB or 5% rounded down to multiples of 256MB.
 *
 * TODO: Come up with better approach to find out more accurate memory size
 * that is required for a kernel to boot successfully.
 *
 */
static inline unsigned long fadump_calculate_reserve_size(void)
{
	int ret;
	unsigned long long base, size;

	if (fw_dump.reserve_bootvar)
		pr_warn("'fadump_reserve_mem=' parameter is deprecated in favor of 'crashkernel=' parameter.\n");

	/*
	 * Check if the size is specified through crashkernel= cmdline
	 * option. If yes, then use that but ignore base as fadump reserves
	 * memory at a predefined offset.
	 */
	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
				&size, &base);
	if (ret == 0 && size > 0) {
		unsigned long max_size;

		if (fw_dump.reserve_bootvar)
			pr_info("Using 'crashkernel=' parameter for memory reservation.\n");

		fw_dump.reserve_bootvar = (unsigned long)size;

		/*
		 * Adjust if the boot memory size specified is above
		 * the upper limit.
		 */
		max_size = memblock_phys_mem_size() / MAX_BOOT_MEM_RATIO;
		if (fw_dump.reserve_bootvar > max_size) {
			fw_dump.reserve_bootvar = max_size;
			pr_info("Adjusted boot memory size to %luMB\n",
				(fw_dump.reserve_bootvar >> 20));
		}

		return fw_dump.reserve_bootvar;
	} else if (fw_dump.reserve_bootvar) {
		/*
		 * 'fadump_reserve_mem=' is being used to reserve memory
		 * for firmware-assisted dump.
		 */
		return fw_dump.reserve_bootvar;
	}

	/* divide by 20 to get 5% of value */
	size = memblock_phys_mem_size() / 20;

	/* round it down in multiples of 256 */
	size = size & ~0x0FFFFFFFUL;

	/* Truncate to memory_limit. We don't want to over reserve the memory.*/
	if (memory_limit && size > memory_limit)
		size = memory_limit;

	return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
}

/*
 * Calculate the total memory size required to be reserved for
 * firmware-assisted dump registration.
 */
static unsigned long get_fadump_area_size(void)
{
	unsigned long size = 0;

	size += fw_dump.cpu_state_data_size;
	size += fw_dump.hpte_region_size;
	size += fw_dump.boot_memory_size;
	size += sizeof(struct fadump_crash_info_header);
	size += sizeof(struct elfhdr); /* ELF core header.*/
	size += sizeof(struct elf_phdr); /* place holder for cpu notes */
	/* Program headers for crash memory regions. */
	size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);

	size = PAGE_ALIGN(size);
	return size;
}

static void __init fadump_reserve_crash_area(unsigned long base,
					     unsigned long size)
{
	struct memblock_region *reg;
	unsigned long mstart, mend, msize;

	for_each_memblock(memory, reg) {
		mstart = max_t(unsigned long, base, reg->base);
		mend = reg->base + reg->size;
		mend = min(base + size, mend);

		if (mstart < mend) {
			msize = mend - mstart;
			memblock_reserve(mstart, msize);
			pr_info("Reserved %ldMB of memory at %#016lx for saving crash dump\n",
				(msize >> 20), mstart);
		}
	}
}

int __init fadump_reserve_mem(void)
{
	unsigned long base, size, memory_boundary;

	if (!fw_dump.fadump_enabled)
		return 0;

	if (!fw_dump.fadump_supported) {
		printk(KERN_INFO "Firmware-assisted dump is not supported on"
				" this hardware\n");
		fw_dump.fadump_enabled = 0;
		return 0;
	}
	/*
	 * Initialize boot memory size
	 * If dump is active then we have already calculated the size during
	 * first kernel.
	 */
	if (fdm_active)
		fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len);
	else {
		fw_dump.boot_memory_size = fadump_calculate_reserve_size();
#ifdef CONFIG_CMA
		if (!fw_dump.nocma)
			fw_dump.boot_memory_size =
				ALIGN(fw_dump.boot_memory_size,
							FADUMP_CMA_ALIGNMENT);
#endif
	}

	/*
	 * Calculate the memory boundary.
	 * If memory_limit is less than actual memory boundary then reserve
	 * the memory for fadump beyond the memory_limit and adjust the
	 * memory_limit accordingly, so that the running kernel can run with
	 * specified memory_limit.
	 */
	if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
		size = get_fadump_area_size();
		if ((memory_limit + size) < memblock_end_of_DRAM())
			memory_limit += size;
		else
			memory_limit = memblock_end_of_DRAM();
		printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
				" dump, now %#016llx\n", memory_limit);
	}
	if (memory_limit)
		memory_boundary = memory_limit;
	else
		memory_boundary = memblock_end_of_DRAM();

	if (fw_dump.dump_active) {
		pr_info("Firmware-assisted dump is active.\n");

#ifdef CONFIG_HUGETLB_PAGE
		/*
		 * FADump capture kernel doesn't care much about hugepages.
		 * In fact, handling hugepages in capture kernel is asking for
		 * trouble. So, disable HugeTLB support when fadump is active.
		 */
		hugetlb_disabled = true;
#endif
		/*
		 * If last boot has crashed then reserve all the memory
		 * above boot_memory_size so that we don't touch it until
		 * dump is written to disk by userspace tool. This memory
		 * will be released for general use once the dump is saved.
		 */
		base = fw_dump.boot_memory_size;
		size = memory_boundary - base;
		fadump_reserve_crash_area(base, size);

		fw_dump.fadumphdr_addr =
				be64_to_cpu(fdm_active->rmr_region.destination_address) +
				be64_to_cpu(fdm_active->rmr_region.source_len);
		pr_debug("fadumphdr_addr = %pa\n", &fw_dump.fadumphdr_addr);
		fw_dump.reserve_dump_area_start = base;
		fw_dump.reserve_dump_area_size = size;
	} else {
		size = get_fadump_area_size();

		/*
		 * Reserve memory at an offset closer to bottom of the RAM to
		 * minimize the impact of memory hot-remove operation. We can't
		 * use memblock_find_in_range() here since it doesn't allocate
		 * from bottom to top.
		 */
		for (base = fw_dump.boot_memory_size;
		     base <= (memory_boundary - size);
		     base += size) {
			if (memblock_is_region_memory(base, size) &&
			    !memblock_is_region_reserved(base, size))
				break;
		}
		if ((base > (memory_boundary - size)) ||
		    memblock_reserve(base, size)) {
			pr_err("Failed to reserve memory\n");
			return 0;
		}

		pr_info("Reserved %ldMB of memory at %ldMB for firmware-"
			"assisted dump (System RAM: %ldMB)\n",
			(unsigned long)(size >> 20),
			(unsigned long)(base >> 20),
			(unsigned long)(memblock_phys_mem_size() >> 20));

		fw_dump.reserve_dump_area_start = base;
		fw_dump.reserve_dump_area_size = size;
		return fadump_cma_init();
	}
	return 1;
}

unsigned long __init arch_reserved_kernel_pages(void)
{
	return memblock_reserved_size() / PAGE_SIZE;
}

/* Look for fadump= cmdline option. */
static int __init early_fadump_param(char *p)
{
	if (!p)
		return 1;

	if (strncmp(p, "on", 2) == 0)
		fw_dump.fadump_enabled = 1;
	else if (strncmp(p, "off", 3) == 0)
		fw_dump.fadump_enabled = 0;
	else if (strncmp(p, "nocma", 5) == 0) {
		fw_dump.fadump_enabled = 1;
		fw_dump.nocma = 1;
	}

	return 0;
}
early_param("fadump", early_fadump_param);

/*
 * Look for fadump_reserve_mem= cmdline option
 * TODO: Remove references to 'fadump_reserve_mem=' parameter,
 *       the sooner 'crashkernel=' parameter is accustomed to.
 */
static int __init early_fadump_reserve_mem(char *p)
{
	if (p)
		fw_dump.reserve_bootvar = memparse(p, &p);
	return 0;
}
early_param("fadump_reserve_mem", early_fadump_reserve_mem);

static int register_fw_dump(struct fadump_mem_struct *fdm)
{
	int rc, err;
	unsigned int wait_time;

	pr_debug("Registering for firmware-assisted kernel dump...\n");

	/* TODO: Add upper time limit for the delay */
	do {
		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
			FADUMP_REGISTER, fdm,
			sizeof(struct fadump_mem_struct));

		wait_time = rtas_busy_delay_time(rc);
		if (wait_time)
			mdelay(wait_time);

	} while (wait_time);

	err = -EIO;
	switch (rc) {
	default:
		pr_err("Failed to register. Unknown Error(%d).\n", rc);
		break;
	case -1:
		printk(KERN_ERR "Failed to register firmware-assisted kernel"
			" dump. Hardware Error(%d).\n", rc);
		break;
	case -3:
		if (!is_boot_memory_area_contiguous())
			pr_err("Can't have holes in boot memory area while registering fadump\n");
		else if (!is_reserved_memory_area_contiguous())
			pr_err("Can't have holes in reserved memory area while"
			       " registering fadump\n");

		printk(KERN_ERR "Failed to register firmware-assisted kernel"
			" dump. Parameter Error(%d).\n", rc);
		err = -EINVAL;
		break;
	case -9:
		printk(KERN_ERR "firmware-assisted kernel dump is already "
			" registered.");
		fw_dump.dump_registered = 1;
		err = -EEXIST;
		break;
	case 0:
		printk(KERN_INFO "firmware-assisted kernel dump registration"
			" is successful\n");
		fw_dump.dump_registered = 1;
		err = 0;
		break;
	}
	return err;
}

void crash_fadump(struct pt_regs *regs, const char *str)
{
	struct fadump_crash_info_header *fdh = NULL;
	int old_cpu, this_cpu;

	if (!should_fadump_crash())
		return;

	/*
	 * old_cpu == -1 means this is the first CPU which has come here,
	 * go ahead and trigger fadump.
	 *
	 * old_cpu != -1 means some other CPU has already on it's way
	 * to trigger fadump, just keep looping here.
	 */
	this_cpu = smp_processor_id();
	old_cpu = cmpxchg(&crashing_cpu, -1, this_cpu);

	if (old_cpu != -1) {
		/*
		 * We can't loop here indefinitely. Wait as long as fadump
		 * is in force. If we race with fadump un-registration this
		 * loop will break and then we go down to normal panic path
		 * and reboot. If fadump is in force the first crashing
		 * cpu will definitely trigger fadump.
		 */
		while (fw_dump.dump_registered)
			cpu_relax();
		return;
	}

	fdh = __va(fw_dump.fadumphdr_addr);
	fdh->crashing_cpu = crashing_cpu;
	crash_save_vmcoreinfo();

	if (regs)
		fdh->regs = *regs;
	else
		ppc_save_regs(&fdh->regs);

	fdh->online_mask = *cpu_online_mask;

	/* Call ibm,os-term rtas call to trigger firmware assisted dump */
	rtas_os_term((char *)str);
}

#define GPR_MASK	0xffffff0000000000
static inline int fadump_gpr_index(u64 id)
{
	int i = -1;
	char str[3];

	if ((id & GPR_MASK) == REG_ID("GPR")) {
		/* get the digits at the end */
		id &= ~GPR_MASK;
		id >>= 24;
		str[2] = '\0';
		str[1] = id & 0xff;
		str[0] = (id >> 8) & 0xff;
		sscanf(str, "%d", &i);
		if (i > 31)
			i = -1;
	}
	return i;
}

static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
								u64 reg_val)
{
	int i;

	i = fadump_gpr_index(reg_id);
	if (i >= 0)
		regs->gpr[i] = (unsigned long)reg_val;
	else if (reg_id == REG_ID("NIA"))
		regs->nip = (unsigned long)reg_val;
	else if (reg_id == REG_ID("MSR"))
		regs->msr = (unsigned long)reg_val;
	else if (reg_id == REG_ID("CTR"))
		regs->ctr = (unsigned long)reg_val;
	else if (reg_id == REG_ID("LR"))
		regs->link = (unsigned long)reg_val;
	else if (reg_id == REG_ID("XER"))
		regs->xer = (unsigned long)reg_val;
	else if (reg_id == REG_ID("CR"))
		regs->ccr = (unsigned long)reg_val;
	else if (reg_id == REG_ID("DAR"))
		regs->dar = (unsigned long)reg_val;
	else if (reg_id == REG_ID("DSISR"))
		regs->dsisr = (unsigned long)reg_val;
}

static struct fadump_reg_entry*
fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
{
	memset(regs, 0, sizeof(struct pt_regs));

	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) {
		fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
					be64_to_cpu(reg_entry->reg_value));
		reg_entry++;
	}
	reg_entry++;
	return reg_entry;
}

static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
{
	struct elf_prstatus prstatus;

	memset(&prstatus, 0, sizeof(prstatus));
	/*
	 * FIXME: How do i get PID? Do I really need it?
	 * prstatus.pr_pid = ????
	 */
	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
			      &prstatus, sizeof(prstatus));
	return buf;
}

static void fadump_update_elfcore_header(char *bufp)
{
	struct elfhdr *elf;
	struct elf_phdr *phdr;

	elf = (struct elfhdr *)bufp;
	bufp += sizeof(struct elfhdr);

	/* First note is a place holder for cpu notes info. */
	phdr = (struct elf_phdr *)bufp;

	if (phdr->p_type == PT_NOTE) {
		phdr->p_paddr = fw_dump.cpu_notes_buf;
		phdr->p_offset	= phdr->p_paddr;
		phdr->p_filesz	= fw_dump.cpu_notes_buf_size;
		phdr->p_memsz = fw_dump.cpu_notes_buf_size;
	}
	return;
}

static void *fadump_cpu_notes_buf_alloc(unsigned long size)
{
	void *vaddr;
	struct page *page;
	unsigned long order, count, i;

	order = get_order(size);
	vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
	if (!vaddr)
		return NULL;

	count = 1 << order;
	page = virt_to_page(vaddr);
	for (i = 0; i < count; i++)
		SetPageReserved(page + i);
	return vaddr;
}

static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
{
	struct page *page;
	unsigned long order, count, i;

	order = get_order(size);
	count = 1 << order;
	page = virt_to_page(vaddr);
	for (i = 0; i < count; i++)
		ClearPageReserved(page + i);
	__free_pages(page, order);
}

/*
 * Read CPU state dump data and convert it into ELF notes.
 * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
 * used to access the data to allow for additional fields to be added without
 * affecting compatibility. Each list of registers for a CPU starts with
 * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
 * 8 Byte ASCII identifier and 8 Byte register value. The register entry
 * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
 * of register value. For more details refer to PAPR document.
 *
 * Only for the crashing cpu we ignore the CPU dump data and get exact
 * state from fadump crash info structure populated by first kernel at the
 * time of crash.
 */
static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
{
	struct fadump_reg_save_area_header *reg_header;
	struct fadump_reg_entry *reg_entry;
	struct fadump_crash_info_header *fdh = NULL;
	void *vaddr;
	unsigned long addr;
	u32 num_cpus, *note_buf;
	struct pt_regs regs;
	int i, rc = 0, cpu = 0;

	if (!fdm->cpu_state_data.bytes_dumped)
		return -EINVAL;

	addr = be64_to_cpu(fdm->cpu_state_data.destination_address);
	vaddr = __va(addr);

	reg_header = vaddr;
	if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) {
		printk(KERN_ERR "Unable to read register save area.\n");
		return -ENOENT;
	}
	pr_debug("--------CPU State Data------------\n");
	pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number));
	pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset));

	vaddr += be32_to_cpu(reg_header->num_cpu_offset);
	num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
	pr_debug("NumCpus     : %u\n", num_cpus);
	vaddr += sizeof(u32);
	reg_entry = (struct fadump_reg_entry *)vaddr;

	/* Allocate buffer to hold cpu crash notes. */
	fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
	fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
	note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
	if (!note_buf) {
		printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
			"cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
		return -ENOMEM;
	}
	fw_dump.cpu_notes_buf = __pa(note_buf);

	pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
			(num_cpus * sizeof(note_buf_t)), note_buf);

	if (fw_dump.fadumphdr_addr)
		fdh = __va(fw_dump.fadumphdr_addr);

	for (i = 0; i < num_cpus; i++) {
		if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) {
			printk(KERN_ERR "Unable to read CPU state data\n");
			rc = -ENOENT;
			goto error_out;
		}
		/* Lower 4 bytes of reg_value contains logical cpu id */
		cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK;
		if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
			SKIP_TO_NEXT_CPU(reg_entry);
			continue;
		}
		pr_debug("Reading register data for cpu %d...\n", cpu);
		if (fdh && fdh->crashing_cpu == cpu) {
			regs = fdh->regs;
			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
			SKIP_TO_NEXT_CPU(reg_entry);
		} else {
			reg_entry++;
			reg_entry = fadump_read_registers(reg_entry, &regs);
			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
		}
	}
	final_note(note_buf);

	if (fdh) {
		pr_debug("Updating elfcore header (%llx) with cpu notes\n",
							fdh->elfcorehdr_addr);
		fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
	}
	return 0;

error_out:
	fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
					fw_dump.cpu_notes_buf_size);
	fw_dump.cpu_notes_buf = 0;
	fw_dump.cpu_notes_buf_size = 0;
	return rc;

}

/*
 * Validate and process the dump data stored by firmware before exporting
 * it through '/proc/vmcore'.
 */
static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
{
	struct fadump_crash_info_header *fdh;
	int rc = 0;

	if (!fdm_active || !fw_dump.fadumphdr_addr)
		return -EINVAL;

	/* Check if the dump data is valid. */
	if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) ||
			(fdm_active->cpu_state_data.error_flags != 0) ||
			(fdm_active->rmr_region.error_flags != 0)) {
		printk(KERN_ERR "Dump taken by platform is not valid\n");
		return -EINVAL;
	}
	if ((fdm_active->rmr_region.bytes_dumped !=
			fdm_active->rmr_region.source_len) ||
			!fdm_active->cpu_state_data.bytes_dumped) {
		printk(KERN_ERR "Dump taken by platform is incomplete\n");
		return -EINVAL;
	}

	/* Validate the fadump crash info header */
	fdh = __va(fw_dump.fadumphdr_addr);
	if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
		printk(KERN_ERR "Crash info header is not valid.\n");
		return -EINVAL;
	}

	rc = fadump_build_cpu_notes(fdm_active);
	if (rc)
		return rc;

	/*
	 * We are done validating dump info and elfcore header is now ready
	 * to be exported. set elfcorehdr_addr so that vmcore module will
	 * export the elfcore header through '/proc/vmcore'.
	 */
	elfcorehdr_addr = fdh->elfcorehdr_addr;

	return 0;
}

static void free_crash_memory_ranges(void)
{
	kfree(crash_memory_ranges);
	crash_memory_ranges = NULL;
	crash_memory_ranges_size = 0;
	max_crash_mem_ranges = 0;
}

/*
 * Allocate or reallocate crash memory ranges array in incremental units
 * of PAGE_SIZE.
 */
static int allocate_crash_memory_ranges(void)
{
	struct fad_crash_memory_ranges *new_array;
	u64 new_size;

	new_size = crash_memory_ranges_size + PAGE_SIZE;
	pr_debug("Allocating %llu bytes of memory for crash memory ranges\n",
		 new_size);

	new_array = krealloc(crash_memory_ranges, new_size, GFP_KERNEL);
	if (new_array == NULL) {
		pr_err("Insufficient memory for setting up crash memory ranges\n");
		free_crash_memory_ranges();
		return -ENOMEM;
	}

	crash_memory_ranges = new_array;
	crash_memory_ranges_size = new_size;
	max_crash_mem_ranges = (new_size /
				sizeof(struct fad_crash_memory_ranges));
	return 0;
}

static inline int fadump_add_crash_memory(unsigned long long base,
					  unsigned long long end)
{
	u64  start, size;
	bool is_adjacent = false;

	if (base == end)
		return 0;

	/*
	 * Fold adjacent memory ranges to bring down the memory ranges/
	 * PT_LOAD segments count.
	 */
	if (crash_mem_ranges) {
		start = crash_memory_ranges[crash_mem_ranges - 1].base;
		size = crash_memory_ranges[crash_mem_ranges - 1].size;

		if ((start + size) == base)
			is_adjacent = true;
	}
	if (!is_adjacent) {
		/* resize the array on reaching the limit */
		if (crash_mem_ranges == max_crash_mem_ranges) {
			int ret;

			ret = allocate_crash_memory_ranges();
			if (ret)
				return ret;
		}

		start = base;
		crash_memory_ranges[crash_mem_ranges].base = start;
		crash_mem_ranges++;
	}

	crash_memory_ranges[crash_mem_ranges - 1].size = (end - start);
	pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
		(crash_mem_ranges - 1), start, end - 1, (end - start));
	return 0;
}

static int fadump_exclude_reserved_area(unsigned long long start,
					unsigned long long end)
{
	unsigned long long ra_start, ra_end;
	int ret = 0;

	ra_start = fw_dump.reserve_dump_area_start;
	ra_end = ra_start + fw_dump.reserve_dump_area_size;

	if ((ra_start < end) && (ra_end > start)) {
		if ((start < ra_start) && (end > ra_end)) {
			ret = fadump_add_crash_memory(start, ra_start);
			if (ret)
				return ret;

			ret = fadump_add_crash_memory(ra_end, end);
		} else if (start < ra_start) {
			ret = fadump_add_crash_memory(start, ra_start);
		} else if (ra_end < end) {
			ret = fadump_add_crash_memory(ra_end, end);
		}
	} else
		ret = fadump_add_crash_memory(start, end);

	return ret;
}

static int fadump_init_elfcore_header(char *bufp)
{
	struct elfhdr *elf;

	elf = (struct elfhdr *) bufp;
	bufp += sizeof(struct elfhdr);
	memcpy(elf->e_ident, ELFMAG, SELFMAG);
	elf->e_ident[EI_CLASS] = ELF_CLASS;
	elf->e_ident[EI_DATA] = ELF_DATA;
	elf->e_ident[EI_VERSION] = EV_CURRENT;
	elf->e_ident[EI_OSABI] = ELF_OSABI;
	memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
	elf->e_type = ET_CORE;
	elf->e_machine = ELF_ARCH;
	elf->e_version = EV_CURRENT;
	elf->e_entry = 0;
	elf->e_phoff = sizeof(struct elfhdr);
	elf->e_shoff = 0;
#if defined(_CALL_ELF)
	elf->e_flags = _CALL_ELF;
#else
	elf->e_flags = 0;
#endif
	elf->e_ehsize = sizeof(struct elfhdr);
	elf->e_phentsize = sizeof(struct elf_phdr);
	elf->e_phnum = 0;
	elf->e_shentsize = 0;
	elf->e_shnum = 0;
	elf->e_shstrndx = 0;

	return 0;
}

/*
 * Traverse through memblock structure and setup crash memory ranges. These
 * ranges will be used create PT_LOAD program headers in elfcore header.
 */
static int fadump_setup_crash_memory_ranges(void)
{
	struct memblock_region *reg;
	unsigned long long start, end;
	int ret;

	pr_debug("Setup crash memory ranges.\n");
	crash_mem_ranges = 0;

	/*
	 * add the first memory chunk (RMA_START through boot_memory_size) as
	 * a separate memory chunk. The reason is, at the time crash firmware
	 * will move the content of this memory chunk to different location
	 * specified during fadump registration. We need to create a separate
	 * program header for this chunk with the correct offset.
	 */
	ret = fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
	if (ret)
		return ret;

	for_each_memblock(memory, reg) {
		start = (unsigned long long)reg->base;
		end = start + (unsigned long long)reg->size;

		/*
		 * skip the first memory chunk that is already added (RMA_START
		 * through boot_memory_size). This logic needs a relook if and
		 * when RMA_START changes to a non-zero value.
		 */
		BUILD_BUG_ON(RMA_START != 0);
		if (start < fw_dump.boot_memory_size) {
			if (end > fw_dump.boot_memory_size)
				start = fw_dump.boot_memory_size;
			else
				continue;
		}

		/* add this range excluding the reserved dump area. */
		ret = fadump_exclude_reserved_area(start, end);
		if (ret)
			return ret;
	}

	return 0;
}

/*
 * If the given physical address falls within the boot memory region then
 * return the relocated address that points to the dump region reserved
 * for saving initial boot memory contents.
 */
static inline unsigned long fadump_relocate(unsigned long paddr)
{
	if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
		return be64_to_cpu(fdm.rmr_region.destination_address) + paddr;
	else
		return paddr;
}

static int fadump_create_elfcore_headers(char *bufp)
{
	struct elfhdr *elf;
	struct elf_phdr *phdr;
	int i;

	fadump_init_elfcore_header(bufp);
	elf = (struct elfhdr *)bufp;
	bufp += sizeof(struct elfhdr);

	/*
	 * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
	 * will be populated during second kernel boot after crash. Hence
	 * this PT_NOTE will always be the first elf note.
	 *
	 * NOTE: Any new ELF note addition should be placed after this note.
	 */
	phdr = (struct elf_phdr *)bufp;
	bufp += sizeof(struct elf_phdr);
	phdr->p_type = PT_NOTE;
	phdr->p_flags = 0;
	phdr->p_vaddr = 0;
	phdr->p_align = 0;

	phdr->p_offset = 0;
	phdr->p_paddr = 0;
	phdr->p_filesz = 0;
	phdr->p_memsz = 0;

	(elf->e_phnum)++;

	/* setup ELF PT_NOTE for vmcoreinfo */
	phdr = (struct elf_phdr *)bufp;
	bufp += sizeof(struct elf_phdr);
	phdr->p_type	= PT_NOTE;
	phdr->p_flags	= 0;
	phdr->p_vaddr	= 0;
	phdr->p_align	= 0;

	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
	phdr->p_offset	= phdr->p_paddr;
	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;

	/* Increment number of program headers. */
	(elf->e_phnum)++;

	/* setup PT_LOAD sections. */

	for (i = 0; i < crash_mem_ranges; i++) {
		unsigned long long mbase, msize;
		mbase = crash_memory_ranges[i].base;
		msize = crash_memory_ranges[i].size;

		if (!msize)
			continue;

		phdr = (struct elf_phdr *)bufp;
		bufp += sizeof(struct elf_phdr);
		phdr->p_type	= PT_LOAD;
		phdr->p_flags	= PF_R|PF_W|PF_X;
		phdr->p_offset	= mbase;

		if (mbase == RMA_START) {
			/*
			 * The entire RMA region will be moved by firmware
			 * to the specified destination_address. Hence set
			 * the correct offset.
			 */
			phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address);
		}

		phdr->p_paddr = mbase;
		phdr->p_vaddr = (unsigned long)__va(mbase);
		phdr->p_filesz = msize;
		phdr->p_memsz = msize;
		phdr->p_align = 0;

		/* Increment number of program headers. */
		(elf->e_phnum)++;
	}
	return 0;
}

static unsigned long init_fadump_header(unsigned long addr)
{
	struct fadump_crash_info_header *fdh;

	if (!addr)
		return 0;

	fw_dump.fadumphdr_addr = addr;
	fdh = __va(addr);
	addr += sizeof(struct fadump_crash_info_header);

	memset(fdh, 0, sizeof(struct fadump_crash_info_header));
	fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
	fdh->elfcorehdr_addr = addr;
	/* We will set the crashing cpu id in crash_fadump() during crash. */
	fdh->crashing_cpu = CPU_UNKNOWN;

	return addr;
}

static int register_fadump(void)
{
	unsigned long addr;
	void *vaddr;
	int ret;

	/*
	 * If no memory is reserved then we can not register for firmware-
	 * assisted dump.
	 */
	if (!fw_dump.reserve_dump_area_size)
		return -ENODEV;

	ret = fadump_setup_crash_memory_ranges();
	if (ret)
		return ret;

	addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len);
	/* Initialize fadump crash info header. */
	addr = init_fadump_header(addr);
	vaddr = __va(addr);

	pr_debug("Creating ELF core headers at %#016lx\n", addr);
	fadump_create_elfcore_headers(vaddr);

	/* register the future kernel dump with firmware. */
	return register_fw_dump(&fdm);
}

static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
{
	int rc = 0;
	unsigned int wait_time;

	pr_debug("Un-register firmware-assisted dump\n");

	/* TODO: Add upper time limit for the delay */
	do {
		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
			FADUMP_UNREGISTER, fdm,
			sizeof(struct fadump_mem_struct));

		wait_time = rtas_busy_delay_time(rc);
		if (wait_time)
			mdelay(wait_time);
	} while (wait_time);

	if (rc) {
		printk(KERN_ERR "Failed to un-register firmware-assisted dump."
			" unexpected error(%d).\n", rc);
		return rc;
	}
	fw_dump.dump_registered = 0;
	return 0;
}

static int fadump_invalidate_dump(const struct fadump_mem_struct *fdm)
{
	int rc = 0;
	unsigned int wait_time;

	pr_debug("Invalidating firmware-assisted dump registration\n");

	/* TODO: Add upper time limit for the delay */
	do {
		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
			FADUMP_INVALIDATE, fdm,
			sizeof(struct fadump_mem_struct));

		wait_time = rtas_busy_delay_time(rc);
		if (wait_time)
			mdelay(wait_time);
	} while (wait_time);

	if (rc) {
		pr_err("Failed to invalidate firmware-assisted dump registration. Unexpected error (%d).\n", rc);
		return rc;
	}
	fw_dump.dump_active = 0;
	fdm_active = NULL;
	return 0;
}

void fadump_cleanup(void)
{
	/* Invalidate the registration only if dump is active. */
	if (fw_dump.dump_active) {
		/* pass the same memory dump structure provided by platform */
		fadump_invalidate_dump(fdm_active);
	} else if (fw_dump.dump_registered) {
		/* Un-register Firmware-assisted dump if it was registered. */
		fadump_unregister_dump(&fdm);
		free_crash_memory_ranges();
	}
}

static void fadump_free_reserved_memory(unsigned long start_pfn,
					unsigned long end_pfn)
{
	unsigned long pfn;
	unsigned long time_limit = jiffies + HZ;

	pr_info("freeing reserved memory (0x%llx - 0x%llx)\n",
		PFN_PHYS(start_pfn), PFN_PHYS(end_pfn));

	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
		free_reserved_page(pfn_to_page(pfn));

		if (time_after(jiffies, time_limit)) {
			cond_resched();
			time_limit = jiffies + HZ;
		}
	}
}

/*
 * Skip memory holes and free memory that was actually reserved.
 */
static void fadump_release_reserved_area(unsigned long start, unsigned long end)
{
	struct memblock_region *reg;
	unsigned long tstart, tend;
	unsigned long start_pfn = PHYS_PFN(start);
	unsigned long end_pfn = PHYS_PFN(end);

	for_each_memblock(memory, reg) {
		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
		if (tstart < tend) {
			fadump_free_reserved_memory(tstart, tend);

			if (tend == end_pfn)
				break;

			start_pfn = tend + 1;
		}
	}
}

/*
 * Release the memory that was reserved in early boot to preserve the memory
 * contents. The released memory will be available for general use.
 */
static void fadump_release_memory(unsigned long begin, unsigned long end)
{
	unsigned long ra_start, ra_end;

	ra_start = fw_dump.reserve_dump_area_start;
	ra_end = ra_start + fw_dump.reserve_dump_area_size;

	/*
	 * exclude the dump reserve area. Will reuse it for next
	 * fadump registration.
	 */
	if (begin < ra_end && end > ra_start) {
		if (begin < ra_start)
			fadump_release_reserved_area(begin, ra_start);
		if (end > ra_end)
			fadump_release_reserved_area(ra_end, end);
	} else
		fadump_release_reserved_area(begin, end);
}

static void fadump_invalidate_release_mem(void)
{
	unsigned long reserved_area_start, reserved_area_end;
	unsigned long destination_address;

	mutex_lock(&fadump_mutex);
	if (!fw_dump.dump_active) {
		mutex_unlock(&fadump_mutex);
		return;
	}

	destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address);
	fadump_cleanup();
	mutex_unlock(&fadump_mutex);

	/*
	 * Save the current reserved memory bounds we will require them
	 * later for releasing the memory for general use.
	 */
	reserved_area_start = fw_dump.reserve_dump_area_start;
	reserved_area_end = reserved_area_start +
			fw_dump.reserve_dump_area_size;
	/*
	 * Setup reserve_dump_area_start and its size so that we can
	 * reuse this reserved memory for Re-registration.
	 */
	fw_dump.reserve_dump_area_start = destination_address;
	fw_dump.reserve_dump_area_size = get_fadump_area_size();

	fadump_release_memory(reserved_area_start, reserved_area_end);
	if (fw_dump.cpu_notes_buf) {
		fadump_cpu_notes_buf_free(
				(unsigned long)__va(fw_dump.cpu_notes_buf),
				fw_dump.cpu_notes_buf_size);
		fw_dump.cpu_notes_buf = 0;
		fw_dump.cpu_notes_buf_size = 0;
	}
	/* Initialize the kernel dump memory structure for FAD registration. */
	init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
}

static ssize_t fadump_release_memory_store(struct kobject *kobj,
					struct kobj_attribute *attr,
					const char *buf, size_t count)
{
	int input = -1;

	if (!fw_dump.dump_active)
		return -EPERM;

	if (kstrtoint(buf, 0, &input))
		return -EINVAL;

	if (input == 1) {
		/*
		 * Take away the '/proc/vmcore'. We are releasing the dump
		 * memory, hence it will not be valid anymore.
		 */
#ifdef CONFIG_PROC_VMCORE
		vmcore_cleanup();
#endif
		fadump_invalidate_release_mem();

	} else
		return -EINVAL;
	return count;
}

static ssize_t fadump_enabled_show(struct kobject *kobj,
					struct kobj_attribute *attr,
					char *buf)
{
	return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
}

static ssize_t fadump_register_show(struct kobject *kobj,
					struct kobj_attribute *attr,
					char *buf)
{
	return sprintf(buf, "%d\n", fw_dump.dump_registered);
}

static ssize_t fadump_register_store(struct kobject *kobj,
					struct kobj_attribute *attr,
					const char *buf, size_t count)
{
	int ret = 0;
	int input = -1;

	if (!fw_dump.fadump_enabled || fdm_active)
		return -EPERM;

	if (kstrtoint(buf, 0, &input))
		return -EINVAL;

	mutex_lock(&fadump_mutex);

	switch (input) {
	case 0:
		if (fw_dump.dump_registered == 0) {
			goto unlock_out;
		}
		/* Un-register Firmware-assisted dump */
		fadump_unregister_dump(&fdm);
		break;
	case 1:
		if (fw_dump.dump_registered == 1) {
			/* Un-register Firmware-assisted dump */
			fadump_unregister_dump(&fdm);
		}
		/* Register Firmware-assisted dump */
		ret = register_fadump();
		break;
	default:
		ret = -EINVAL;
		break;
	}

unlock_out:
	mutex_unlock(&fadump_mutex);
	return ret < 0 ? ret : count;
}

static int fadump_region_show(struct seq_file *m, void *private)
{
	const struct fadump_mem_struct *fdm_ptr;

	if (!fw_dump.fadump_enabled)
		return 0;

	mutex_lock(&fadump_mutex);
	if (fdm_active)
		fdm_ptr = fdm_active;
	else {
		mutex_unlock(&fadump_mutex);
		fdm_ptr = &fdm;
	}

	seq_printf(m,
			"CPU : [%#016llx-%#016llx] %#llx bytes, "
			"Dumped: %#llx\n",
			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address),
			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) +
			be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1,
			be64_to_cpu(fdm_ptr->cpu_state_data.source_len),
			be64_to_cpu(fdm_ptr->cpu_state_data.bytes_dumped));
	seq_printf(m,
			"HPTE: [%#016llx-%#016llx] %#llx bytes, "
			"Dumped: %#llx\n",
			be64_to_cpu(fdm_ptr->hpte_region.destination_address),
			be64_to_cpu(fdm_ptr->hpte_region.destination_address) +
			be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1,
			be64_to_cpu(fdm_ptr->hpte_region.source_len),
			be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped));
	seq_printf(m,
			"DUMP: [%#016llx-%#016llx] %#llx bytes, "
			"Dumped: %#llx\n",
			be64_to_cpu(fdm_ptr->rmr_region.destination_address),
			be64_to_cpu(fdm_ptr->rmr_region.destination_address) +
			be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1,
			be64_to_cpu(fdm_ptr->rmr_region.source_len),
			be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped));

	if (!fdm_active ||
		(fw_dump.reserve_dump_area_start ==
		be64_to_cpu(fdm_ptr->cpu_state_data.destination_address)))
		goto out;

	/* Dump is active. Show reserved memory region. */
	seq_printf(m,
			"    : [%#016llx-%#016llx] %#llx bytes, "
			"Dumped: %#llx\n",
			(unsigned long long)fw_dump.reserve_dump_area_start,
			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1,
			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
			fw_dump.reserve_dump_area_start,
			be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) -
			fw_dump.reserve_dump_area_start);
out:
	if (fdm_active)
		mutex_unlock(&fadump_mutex);
	return 0;
}

static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
						0200, NULL,
						fadump_release_memory_store);
static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
						0444, fadump_enabled_show,
						NULL);
static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
						0644, fadump_register_show,
						fadump_register_store);

DEFINE_SHOW_ATTRIBUTE(fadump_region);

static void fadump_init_files(void)
{
	struct dentry *debugfs_file;
	int rc = 0;

	rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
	if (rc)
		printk(KERN_ERR "fadump: unable to create sysfs file"
			" fadump_enabled (%d)\n", rc);

	rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
	if (rc)
		printk(KERN_ERR "fadump: unable to create sysfs file"
			" fadump_registered (%d)\n", rc);

	debugfs_file = debugfs_create_file("fadump_region", 0444,
					powerpc_debugfs_root, NULL,
					&fadump_region_fops);
	if (!debugfs_file)
		printk(KERN_ERR "fadump: unable to create debugfs file"
				" fadump_region\n");

	if (fw_dump.dump_active) {
		rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
		if (rc)
			printk(KERN_ERR "fadump: unable to create sysfs file"
				" fadump_release_mem (%d)\n", rc);
	}
	return;
}

/*
 * Prepare for firmware-assisted dump.
 */
int __init setup_fadump(void)
{
	if (!fw_dump.fadump_enabled)
		return 0;

	if (!fw_dump.fadump_supported) {
		printk(KERN_ERR "Firmware-assisted dump is not supported on"
			" this hardware\n");
		return 0;
	}

	fadump_show_config();
	/*
	 * If dump data is available then see if it is valid and prepare for
	 * saving it to the disk.
	 */
	if (fw_dump.dump_active) {
		/*
		 * if dump process fails then invalidate the registration
		 * and release memory before proceeding for re-registration.
		 */
		if (process_fadump(fdm_active) < 0)
			fadump_invalidate_release_mem();
	}
	/* Initialize the kernel dump memory structure for FAD registration. */
	else if (fw_dump.reserve_dump_area_size)
		init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
	fadump_init_files();

	return 1;
}
subsys_initcall(setup_fadump);