summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kexec/file_load_64.c
blob: 5b4c5cb233548509f3db2c3953ba7877debde09d (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * ppc64 code to implement the kexec_file_load syscall
 *
 * Copyright (C) 2004  Adam Litke (agl@us.ibm.com)
 * Copyright (C) 2004  IBM Corp.
 * Copyright (C) 2004,2005  Milton D Miller II, IBM Corporation
 * Copyright (C) 2005  R Sharada (sharada@in.ibm.com)
 * Copyright (C) 2006  Mohan Kumar M (mohan@in.ibm.com)
 * Copyright (C) 2020  IBM Corporation
 *
 * Based on kexec-tools' kexec-ppc64.c, kexec-elf-rel-ppc64.c, fs2dt.c.
 * Heavily modified for the kernel by
 * Hari Bathini, IBM Corporation.
 */

#include <linux/kexec.h>
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <linux/of.h>
#include <linux/memblock.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <asm/setup.h>
#include <asm/drmem.h>
#include <asm/firmware.h>
#include <asm/kexec_ranges.h>
#include <asm/crashdump-ppc64.h>
#include <asm/mmzone.h>
#include <asm/iommu.h>
#include <asm/prom.h>
#include <asm/plpks.h>

struct umem_info {
	__be64 *buf;		/* data buffer for usable-memory property */
	u32 size;		/* size allocated for the data buffer */
	u32 max_entries;	/* maximum no. of entries */
	u32 idx;		/* index of current entry */

	/* usable memory ranges to look up */
	unsigned int nr_ranges;
	const struct range *ranges;
};

const struct kexec_file_ops * const kexec_file_loaders[] = {
	&kexec_elf64_ops,
	NULL
};

/**
 * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
 *                             regions like opal/rtas, tce-table, initrd,
 *                             kernel, htab which should be avoided while
 *                             setting up kexec load segments.
 * @mem_ranges:                Range list to add the memory ranges to.
 *
 * Returns 0 on success, negative errno on error.
 */
static int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
{
	int ret;

	ret = add_tce_mem_ranges(mem_ranges);
	if (ret)
		goto out;

	ret = add_initrd_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_htab_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_kernel_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_rtas_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_opal_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_reserved_mem_ranges(mem_ranges);
	if (ret)
		goto out;

	/* exclude memory ranges should be sorted for easy lookup */
	sort_memory_ranges(*mem_ranges, true);
out:
	if (ret)
		pr_err("Failed to setup exclude memory ranges\n");
	return ret;
}

/**
 * get_usable_memory_ranges - Get usable memory ranges. This list includes
 *                            regions like crashkernel, opal/rtas & tce-table,
 *                            that kdump kernel could use.
 * @mem_ranges:               Range list to add the memory ranges to.
 *
 * Returns 0 on success, negative errno on error.
 */
static int get_usable_memory_ranges(struct crash_mem **mem_ranges)
{
	int ret;

	/*
	 * Early boot failure observed on guests when low memory (first memory
	 * block?) is not added to usable memory. So, add [0, crashk_res.end]
	 * instead of [crashk_res.start, crashk_res.end] to workaround it.
	 * Also, crashed kernel's memory must be added to reserve map to
	 * avoid kdump kernel from using it.
	 */
	ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1);
	if (ret)
		goto out;

	ret = add_rtas_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_opal_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_tce_mem_ranges(mem_ranges);
out:
	if (ret)
		pr_err("Failed to setup usable memory ranges\n");
	return ret;
}

/**
 * get_crash_memory_ranges - Get crash memory ranges. This list includes
 *                           first/crashing kernel's memory regions that
 *                           would be exported via an elfcore.
 * @mem_ranges:              Range list to add the memory ranges to.
 *
 * Returns 0 on success, negative errno on error.
 */
static int get_crash_memory_ranges(struct crash_mem **mem_ranges)
{
	phys_addr_t base, end;
	struct crash_mem *tmem;
	u64 i;
	int ret;

	for_each_mem_range(i, &base, &end) {
		u64 size = end - base;

		/* Skip backup memory region, which needs a separate entry */
		if (base == BACKUP_SRC_START) {
			if (size > BACKUP_SRC_SIZE) {
				base = BACKUP_SRC_END + 1;
				size -= BACKUP_SRC_SIZE;
			} else
				continue;
		}

		ret = add_mem_range(mem_ranges, base, size);
		if (ret)
			goto out;

		/* Try merging adjacent ranges before reallocation attempt */
		if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges)
			sort_memory_ranges(*mem_ranges, true);
	}

	/* Reallocate memory ranges if there is no space to split ranges */
	tmem = *mem_ranges;
	if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) {
		tmem = realloc_mem_ranges(mem_ranges);
		if (!tmem)
			goto out;
	}

	/* Exclude crashkernel region */
	ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end);
	if (ret)
		goto out;

	/*
	 * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL
	 *        regions are exported to save their context at the time of
	 *        crash, they should actually be backed up just like the
	 *        first 64K bytes of memory.
	 */
	ret = add_rtas_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_opal_mem_range(mem_ranges);
	if (ret)
		goto out;

	/* create a separate program header for the backup region */
	ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE);
	if (ret)
		goto out;

	sort_memory_ranges(*mem_ranges, false);
out:
	if (ret)
		pr_err("Failed to setup crash memory ranges\n");
	return ret;
}

/**
 * get_reserved_memory_ranges - Get reserve memory ranges. This list includes
 *                              memory regions that should be added to the
 *                              memory reserve map to ensure the region is
 *                              protected from any mischief.
 * @mem_ranges:                 Range list to add the memory ranges to.
 *
 * Returns 0 on success, negative errno on error.
 */
static int get_reserved_memory_ranges(struct crash_mem **mem_ranges)
{
	int ret;

	ret = add_rtas_mem_range(mem_ranges);
	if (ret)
		goto out;

	ret = add_tce_mem_ranges(mem_ranges);
	if (ret)
		goto out;

	ret = add_reserved_mem_ranges(mem_ranges);
out:
	if (ret)
		pr_err("Failed to setup reserved memory ranges\n");
	return ret;
}

/**
 * __locate_mem_hole_top_down - Looks top down for a large enough memory hole
 *                              in the memory regions between buf_min & buf_max
 *                              for the buffer. If found, sets kbuf->mem.
 * @kbuf:                       Buffer contents and memory parameters.
 * @buf_min:                    Minimum address for the buffer.
 * @buf_max:                    Maximum address for the buffer.
 *
 * Returns 0 on success, negative errno on error.
 */
static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
				      u64 buf_min, u64 buf_max)
{
	int ret = -EADDRNOTAVAIL;
	phys_addr_t start, end;
	u64 i;

	for_each_mem_range_rev(i, &start, &end) {
		/*
		 * memblock uses [start, end) convention while it is
		 * [start, end] here. Fix the off-by-one to have the
		 * same convention.
		 */
		end -= 1;

		if (start > buf_max)
			continue;

		/* Memory hole not found */
		if (end < buf_min)
			break;

		/* Adjust memory region based on the given range */
		if (start < buf_min)
			start = buf_min;
		if (end > buf_max)
			end = buf_max;

		start = ALIGN(start, kbuf->buf_align);
		if (start < end && (end - start + 1) >= kbuf->memsz) {
			/* Suitable memory range found. Set kbuf->mem */
			kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1,
					       kbuf->buf_align);
			ret = 0;
			break;
		}
	}

	return ret;
}

/**
 * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a
 *                                  suitable buffer with top down approach.
 * @kbuf:                           Buffer contents and memory parameters.
 * @buf_min:                        Minimum address for the buffer.
 * @buf_max:                        Maximum address for the buffer.
 * @emem:                           Exclude memory ranges.
 *
 * Returns 0 on success, negative errno on error.
 */
static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf,
					  u64 buf_min, u64 buf_max,
					  const struct crash_mem *emem)
{
	int i, ret = 0, err = -EADDRNOTAVAIL;
	u64 start, end, tmin, tmax;

	tmax = buf_max;
	for (i = (emem->nr_ranges - 1); i >= 0; i--) {
		start = emem->ranges[i].start;
		end = emem->ranges[i].end;

		if (start > tmax)
			continue;

		if (end < tmax) {
			tmin = (end < buf_min ? buf_min : end + 1);
			ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
			if (!ret)
				return 0;
		}

		tmax = start - 1;

		if (tmax < buf_min) {
			ret = err;
			break;
		}
		ret = 0;
	}

	if (!ret) {
		tmin = buf_min;
		ret = __locate_mem_hole_top_down(kbuf, tmin, tmax);
	}
	return ret;
}

/**
 * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole
 *                               in the memory regions between buf_min & buf_max
 *                               for the buffer. If found, sets kbuf->mem.
 * @kbuf:                        Buffer contents and memory parameters.
 * @buf_min:                     Minimum address for the buffer.
 * @buf_max:                     Maximum address for the buffer.
 *
 * Returns 0 on success, negative errno on error.
 */
static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
				       u64 buf_min, u64 buf_max)
{
	int ret = -EADDRNOTAVAIL;
	phys_addr_t start, end;
	u64 i;

	for_each_mem_range(i, &start, &end) {
		/*
		 * memblock uses [start, end) convention while it is
		 * [start, end] here. Fix the off-by-one to have the
		 * same convention.
		 */
		end -= 1;

		if (end < buf_min)
			continue;

		/* Memory hole not found */
		if (start > buf_max)
			break;

		/* Adjust memory region based on the given range */
		if (start < buf_min)
			start = buf_min;
		if (end > buf_max)
			end = buf_max;

		start = ALIGN(start, kbuf->buf_align);
		if (start < end && (end - start + 1) >= kbuf->memsz) {
			/* Suitable memory range found. Set kbuf->mem */
			kbuf->mem = start;
			ret = 0;
			break;
		}
	}

	return ret;
}

/**
 * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a
 *                                   suitable buffer with bottom up approach.
 * @kbuf:                            Buffer contents and memory parameters.
 * @buf_min:                         Minimum address for the buffer.
 * @buf_max:                         Maximum address for the buffer.
 * @emem:                            Exclude memory ranges.
 *
 * Returns 0 on success, negative errno on error.
 */
static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
					   u64 buf_min, u64 buf_max,
					   const struct crash_mem *emem)
{
	int i, ret = 0, err = -EADDRNOTAVAIL;
	u64 start, end, tmin, tmax;

	tmin = buf_min;
	for (i = 0; i < emem->nr_ranges; i++) {
		start = emem->ranges[i].start;
		end = emem->ranges[i].end;

		if (end < tmin)
			continue;

		if (start > tmin) {
			tmax = (start > buf_max ? buf_max : start - 1);
			ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
			if (!ret)
				return 0;
		}

		tmin = end + 1;

		if (tmin > buf_max) {
			ret = err;
			break;
		}
		ret = 0;
	}

	if (!ret) {
		tmax = buf_max;
		ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax);
	}
	return ret;
}

/**
 * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries
 * @um_info:                  Usable memory buffer and ranges info.
 * @cnt:                      No. of entries to accommodate.
 *
 * Frees up the old buffer if memory reallocation fails.
 *
 * Returns buffer on success, NULL on error.
 */
static __be64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt)
{
	u32 new_size;
	__be64 *tbuf;

	if ((um_info->idx + cnt) <= um_info->max_entries)
		return um_info->buf;

	new_size = um_info->size + MEM_RANGE_CHUNK_SZ;
	tbuf = krealloc(um_info->buf, new_size, GFP_KERNEL);
	if (tbuf) {
		um_info->buf = tbuf;
		um_info->size = new_size;
		um_info->max_entries = (um_info->size / sizeof(u64));
	}

	return tbuf;
}

/**
 * add_usable_mem - Add the usable memory ranges within the given memory range
 *                  to the buffer
 * @um_info:        Usable memory buffer and ranges info.
 * @base:           Base address of memory range to look for.
 * @end:            End address of memory range to look for.
 *
 * Returns 0 on success, negative errno on error.
 */
static int add_usable_mem(struct umem_info *um_info, u64 base, u64 end)
{
	u64 loc_base, loc_end;
	bool add;
	int i;

	for (i = 0; i < um_info->nr_ranges; i++) {
		add = false;
		loc_base = um_info->ranges[i].start;
		loc_end = um_info->ranges[i].end;
		if (loc_base >= base && loc_end <= end)
			add = true;
		else if (base < loc_end && end > loc_base) {
			if (loc_base < base)
				loc_base = base;
			if (loc_end > end)
				loc_end = end;
			add = true;
		}

		if (add) {
			if (!check_realloc_usable_mem(um_info, 2))
				return -ENOMEM;

			um_info->buf[um_info->idx++] = cpu_to_be64(loc_base);
			um_info->buf[um_info->idx++] =
					cpu_to_be64(loc_end - loc_base + 1);
		}
	}

	return 0;
}

/**
 * kdump_setup_usable_lmb - This is a callback function that gets called by
 *                          walk_drmem_lmbs for every LMB to set its
 *                          usable memory ranges.
 * @lmb:                    LMB info.
 * @usm:                    linux,drconf-usable-memory property value.
 * @data:                   Pointer to usable memory buffer and ranges info.
 *
 * Returns 0 on success, negative errno on error.
 */
static int kdump_setup_usable_lmb(struct drmem_lmb *lmb, const __be32 **usm,
				  void *data)
{
	struct umem_info *um_info;
	int tmp_idx, ret;
	u64 base, end;

	/*
	 * kdump load isn't supported on kernels already booted with
	 * linux,drconf-usable-memory property.
	 */
	if (*usm) {
		pr_err("linux,drconf-usable-memory property already exists!");
		return -EINVAL;
	}

	um_info = data;
	tmp_idx = um_info->idx;
	if (!check_realloc_usable_mem(um_info, 1))
		return -ENOMEM;

	um_info->idx++;
	base = lmb->base_addr;
	end = base + drmem_lmb_size() - 1;
	ret = add_usable_mem(um_info, base, end);
	if (!ret) {
		/*
		 * Update the no. of ranges added. Two entries (base & size)
		 * for every range added.
		 */
		um_info->buf[tmp_idx] =
				cpu_to_be64((um_info->idx - tmp_idx - 1) / 2);
	}

	return ret;
}

#define NODE_PATH_LEN		256
/**
 * add_usable_mem_property - Add usable memory property for the given
 *                           memory node.
 * @fdt:                     Flattened device tree for the kdump kernel.
 * @dn:                      Memory node.
 * @um_info:                 Usable memory buffer and ranges info.
 *
 * Returns 0 on success, negative errno on error.
 */
static int add_usable_mem_property(void *fdt, struct device_node *dn,
				   struct umem_info *um_info)
{
	int n_mem_addr_cells, n_mem_size_cells, node;
	char path[NODE_PATH_LEN];
	int i, len, ranges, ret;
	const __be32 *prop;
	u64 base, end;

	of_node_get(dn);

	if (snprintf(path, NODE_PATH_LEN, "%pOF", dn) > (NODE_PATH_LEN - 1)) {
		pr_err("Buffer (%d) too small for memory node: %pOF\n",
		       NODE_PATH_LEN, dn);
		return -EOVERFLOW;
	}
	kexec_dprintk("Memory node path: %s\n", path);

	/* Now that we know the path, find its offset in kdump kernel's fdt */
	node = fdt_path_offset(fdt, path);
	if (node < 0) {
		pr_err("Malformed device tree: error reading %s\n", path);
		ret = -EINVAL;
		goto out;
	}

	/* Get the address & size cells */
	n_mem_addr_cells = of_n_addr_cells(dn);
	n_mem_size_cells = of_n_size_cells(dn);
	kexec_dprintk("address cells: %d, size cells: %d\n", n_mem_addr_cells,
		      n_mem_size_cells);

	um_info->idx  = 0;
	if (!check_realloc_usable_mem(um_info, 2)) {
		ret = -ENOMEM;
		goto out;
	}

	prop = of_get_property(dn, "reg", &len);
	if (!prop || len <= 0) {
		ret = 0;
		goto out;
	}

	/*
	 * "reg" property represents sequence of (addr,size) tuples
	 * each representing a memory range.
	 */
	ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);

	for (i = 0; i < ranges; i++) {
		base = of_read_number(prop, n_mem_addr_cells);
		prop += n_mem_addr_cells;
		end = base + of_read_number(prop, n_mem_size_cells) - 1;
		prop += n_mem_size_cells;

		ret = add_usable_mem(um_info, base, end);
		if (ret)
			goto out;
	}

	/*
	 * No kdump kernel usable memory found in this memory node.
	 * Write (0,0) tuple in linux,usable-memory property for
	 * this region to be ignored.
	 */
	if (um_info->idx == 0) {
		um_info->buf[0] = 0;
		um_info->buf[1] = 0;
		um_info->idx = 2;
	}

	ret = fdt_setprop(fdt, node, "linux,usable-memory", um_info->buf,
			  (um_info->idx * sizeof(u64)));

out:
	of_node_put(dn);
	return ret;
}


/**
 * update_usable_mem_fdt - Updates kdump kernel's fdt with linux,usable-memory
 *                         and linux,drconf-usable-memory DT properties as
 *                         appropriate to restrict its memory usage.
 * @fdt:                   Flattened device tree for the kdump kernel.
 * @usable_mem:            Usable memory ranges for kdump kernel.
 *
 * Returns 0 on success, negative errno on error.
 */
static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem)
{
	struct umem_info um_info;
	struct device_node *dn;
	int node, ret = 0;

	if (!usable_mem) {
		pr_err("Usable memory ranges for kdump kernel not found\n");
		return -ENOENT;
	}

	node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory");
	if (node == -FDT_ERR_NOTFOUND)
		kexec_dprintk("No dynamic reconfiguration memory found\n");
	else if (node < 0) {
		pr_err("Malformed device tree: error reading /ibm,dynamic-reconfiguration-memory.\n");
		return -EINVAL;
	}

	um_info.buf  = NULL;
	um_info.size = 0;
	um_info.max_entries = 0;
	um_info.idx  = 0;
	/* Memory ranges to look up */
	um_info.ranges = &(usable_mem->ranges[0]);
	um_info.nr_ranges = usable_mem->nr_ranges;

	dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
	if (dn) {
		ret = walk_drmem_lmbs(dn, &um_info, kdump_setup_usable_lmb);
		of_node_put(dn);

		if (ret) {
			pr_err("Could not setup linux,drconf-usable-memory property for kdump\n");
			goto out;
		}

		ret = fdt_setprop(fdt, node, "linux,drconf-usable-memory",
				  um_info.buf, (um_info.idx * sizeof(u64)));
		if (ret) {
			pr_err("Failed to update fdt with linux,drconf-usable-memory property: %s",
			       fdt_strerror(ret));
			goto out;
		}
	}

	/*
	 * Walk through each memory node and set linux,usable-memory property
	 * for the corresponding node in kdump kernel's fdt.
	 */
	for_each_node_by_type(dn, "memory") {
		ret = add_usable_mem_property(fdt, dn, &um_info);
		if (ret) {
			pr_err("Failed to set linux,usable-memory property for %s node",
			       dn->full_name);
			of_node_put(dn);
			goto out;
		}
	}

out:
	kfree(um_info.buf);
	return ret;
}

/**
 * load_backup_segment - Locate a memory hole to place the backup region.
 * @image:               Kexec image.
 * @kbuf:                Buffer contents and memory parameters.
 *
 * Returns 0 on success, negative errno on error.
 */
static int load_backup_segment(struct kimage *image, struct kexec_buf *kbuf)
{
	void *buf;
	int ret;

	/*
	 * Setup a source buffer for backup segment.
	 *
	 * A source buffer has no meaning for backup region as data will
	 * be copied from backup source, after crash, in the purgatory.
	 * But as load segment code doesn't recognize such segments,
	 * setup a dummy source buffer to keep it happy for now.
	 */
	buf = vzalloc(BACKUP_SRC_SIZE);
	if (!buf)
		return -ENOMEM;

	kbuf->buffer = buf;
	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
	kbuf->bufsz = kbuf->memsz = BACKUP_SRC_SIZE;
	kbuf->top_down = false;

	ret = kexec_add_buffer(kbuf);
	if (ret) {
		vfree(buf);
		return ret;
	}

	image->arch.backup_buf = buf;
	image->arch.backup_start = kbuf->mem;
	return 0;
}

/**
 * update_backup_region_phdr - Update backup region's offset for the core to
 *                             export the region appropriately.
 * @image:                     Kexec image.
 * @ehdr:                      ELF core header.
 *
 * Assumes an exclusive program header is setup for the backup region
 * in the ELF headers
 *
 * Returns nothing.
 */
static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr)
{
	Elf64_Phdr *phdr;
	unsigned int i;

	phdr = (Elf64_Phdr *)(ehdr + 1);
	for (i = 0; i < ehdr->e_phnum; i++) {
		if (phdr->p_paddr == BACKUP_SRC_START) {
			phdr->p_offset = image->arch.backup_start;
			kexec_dprintk("Backup region offset updated to 0x%lx\n",
				      image->arch.backup_start);
			return;
		}
	}
}

/**
 * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr
 *                           segment needed to load kdump kernel.
 * @image:                   Kexec image.
 * @kbuf:                    Buffer contents and memory parameters.
 *
 * Returns 0 on success, negative errno on error.
 */
static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
{
	struct crash_mem *cmem = NULL;
	unsigned long headers_sz;
	void *headers = NULL;
	int ret;

	ret = get_crash_memory_ranges(&cmem);
	if (ret)
		goto out;

	/* Setup elfcorehdr segment */
	ret = crash_prepare_elf64_headers(cmem, false, &headers, &headers_sz);
	if (ret) {
		pr_err("Failed to prepare elf headers for the core\n");
		goto out;
	}

	/* Fix the offset for backup region in the ELF header */
	update_backup_region_phdr(image, headers);

	kbuf->buffer = headers;
	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
	kbuf->bufsz = kbuf->memsz = headers_sz;
	kbuf->top_down = false;

	ret = kexec_add_buffer(kbuf);
	if (ret) {
		vfree(headers);
		goto out;
	}

	image->elf_load_addr = kbuf->mem;
	image->elf_headers_sz = headers_sz;
	image->elf_headers = headers;
out:
	kfree(cmem);
	return ret;
}

/**
 * load_crashdump_segments_ppc64 - Initialize the additional segements needed
 *                                 to load kdump kernel.
 * @image:                         Kexec image.
 * @kbuf:                          Buffer contents and memory parameters.
 *
 * Returns 0 on success, negative errno on error.
 */
int load_crashdump_segments_ppc64(struct kimage *image,
				  struct kexec_buf *kbuf)
{
	int ret;

	/* Load backup segment - first 64K bytes of the crashing kernel */
	ret = load_backup_segment(image, kbuf);
	if (ret) {
		pr_err("Failed to load backup segment\n");
		return ret;
	}
	kexec_dprintk("Loaded the backup region at 0x%lx\n", kbuf->mem);

	/* Load elfcorehdr segment - to export crashing kernel's vmcore */
	ret = load_elfcorehdr_segment(image, kbuf);
	if (ret) {
		pr_err("Failed to load elfcorehdr segment\n");
		return ret;
	}
	kexec_dprintk("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n",
		      image->elf_load_addr, kbuf->bufsz, kbuf->memsz);

	return 0;
}

/**
 * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global
 *                         variables and call setup_purgatory() to initialize
 *                         common global variable.
 * @image:                 kexec image.
 * @slave_code:            Slave code for the purgatory.
 * @fdt:                   Flattened device tree for the next kernel.
 * @kernel_load_addr:      Address where the kernel is loaded.
 * @fdt_load_addr:         Address where the flattened device tree is loaded.
 *
 * Returns 0 on success, negative errno on error.
 */
int setup_purgatory_ppc64(struct kimage *image, const void *slave_code,
			  const void *fdt, unsigned long kernel_load_addr,
			  unsigned long fdt_load_addr)
{
	struct device_node *dn = NULL;
	int ret;

	ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr,
			      fdt_load_addr);
	if (ret)
		goto out;

	if (image->type == KEXEC_TYPE_CRASH) {
		u32 my_run_at_load = 1;

		/*
		 * Tell relocatable kernel to run at load address
		 * via the word meant for that at 0x5c.
		 */
		ret = kexec_purgatory_get_set_symbol(image, "run_at_load",
						     &my_run_at_load,
						     sizeof(my_run_at_load),
						     false);
		if (ret)
			goto out;
	}

	/* Tell purgatory where to look for backup region */
	ret = kexec_purgatory_get_set_symbol(image, "backup_start",
					     &image->arch.backup_start,
					     sizeof(image->arch.backup_start),
					     false);
	if (ret)
		goto out;

	/* Setup OPAL base & entry values */
	dn = of_find_node_by_path("/ibm,opal");
	if (dn) {
		u64 val;

		of_property_read_u64(dn, "opal-base-address", &val);
		ret = kexec_purgatory_get_set_symbol(image, "opal_base", &val,
						     sizeof(val), false);
		if (ret)
			goto out;

		of_property_read_u64(dn, "opal-entry-address", &val);
		ret = kexec_purgatory_get_set_symbol(image, "opal_entry", &val,
						     sizeof(val), false);
	}
out:
	if (ret)
		pr_err("Failed to setup purgatory symbols");
	of_node_put(dn);
	return ret;
}

/**
 * cpu_node_size - Compute the size of a CPU node in the FDT.
 *                 This should be done only once and the value is stored in
 *                 a static variable.
 * Returns the max size of a CPU node in the FDT.
 */
static unsigned int cpu_node_size(void)
{
	static unsigned int size;
	struct device_node *dn;
	struct property *pp;

	/*
	 * Don't compute it twice, we are assuming that the per CPU node size
	 * doesn't change during the system's life.
	 */
	if (size)
		return size;

	dn = of_find_node_by_type(NULL, "cpu");
	if (WARN_ON_ONCE(!dn)) {
		// Unlikely to happen
		return 0;
	}

	/*
	 * We compute the sub node size for a CPU node, assuming it
	 * will be the same for all.
	 */
	size += strlen(dn->name) + 5;
	for_each_property_of_node(dn, pp) {
		size += strlen(pp->name);
		size += pp->length;
	}

	of_node_put(dn);
	return size;
}

/**
 * kexec_extra_fdt_size_ppc64 - Return the estimated additional size needed to
 *                              setup FDT for kexec/kdump kernel.
 * @image:                      kexec image being loaded.
 *
 * Returns the estimated extra size needed for kexec/kdump kernel FDT.
 */
unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
{
	unsigned int cpu_nodes, extra_size = 0;
	struct device_node *dn;
	u64 usm_entries;

	// Budget some space for the password blob. There's already extra space
	// for the key name
	if (plpks_is_available())
		extra_size += (unsigned int)plpks_get_passwordlen();

	if (image->type != KEXEC_TYPE_CRASH)
		return extra_size;

	/*
	 * For kdump kernel, account for linux,usable-memory and
	 * linux,drconf-usable-memory properties. Get an approximate on the
	 * number of usable memory entries and use for FDT size estimation.
	 */
	if (drmem_lmb_size()) {
		usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) +
			       (2 * (resource_size(&crashk_res) / drmem_lmb_size())));
		extra_size += (unsigned int)(usm_entries * sizeof(u64));
	}

	/*
	 * Get the number of CPU nodes in the current DT. This allows to
	 * reserve places for CPU nodes added since the boot time.
	 */
	cpu_nodes = 0;
	for_each_node_by_type(dn, "cpu") {
		cpu_nodes++;
	}

	if (cpu_nodes > boot_cpu_node_count)
		extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size();

	return extra_size;
}

/**
 * add_node_props - Reads node properties from device node structure and add
 *                  them to fdt.
 * @fdt:            Flattened device tree of the kernel
 * @node_offset:    offset of the node to add a property at
 * @dn:             device node pointer
 *
 * Returns 0 on success, negative errno on error.
 */
static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
{
	int ret = 0;
	struct property *pp;

	if (!dn)
		return -EINVAL;

	for_each_property_of_node(dn, pp) {
		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
		if (ret < 0) {
			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
			return ret;
		}
	}
	return ret;
}

/**
 * update_cpus_node - Update cpus node of flattened device tree using of_root
 *                    device node.
 * @fdt:              Flattened device tree of the kernel.
 *
 * Returns 0 on success, negative errno on error.
 */
static int update_cpus_node(void *fdt)
{
	struct device_node *cpus_node, *dn;
	int cpus_offset, cpus_subnode_offset, ret = 0;

	cpus_offset = fdt_path_offset(fdt, "/cpus");
	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
		pr_err("Malformed device tree: error reading /cpus node: %s\n",
		       fdt_strerror(cpus_offset));
		return cpus_offset;
	}

	if (cpus_offset > 0) {
		ret = fdt_del_node(fdt, cpus_offset);
		if (ret < 0) {
			pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
			return -EINVAL;
		}
	}

	/* Add cpus node to fdt */
	cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
	if (cpus_offset < 0) {
		pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
		return -EINVAL;
	}

	/* Add cpus node properties */
	cpus_node = of_find_node_by_path("/cpus");
	ret = add_node_props(fdt, cpus_offset, cpus_node);
	of_node_put(cpus_node);
	if (ret < 0)
		return ret;

	/* Loop through all subnodes of cpus and add them to fdt */
	for_each_node_by_type(dn, "cpu") {
		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
		if (cpus_subnode_offset < 0) {
			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
			       fdt_strerror(cpus_subnode_offset));
			ret = cpus_subnode_offset;
			goto out;
		}

		ret = add_node_props(fdt, cpus_subnode_offset, dn);
		if (ret < 0)
			goto out;
	}
out:
	of_node_put(dn);
	return ret;
}

static int copy_property(void *fdt, int node_offset, const struct device_node *dn,
			 const char *propname)
{
	const void *prop, *fdtprop;
	int len = 0, fdtlen = 0;

	prop = of_get_property(dn, propname, &len);
	fdtprop = fdt_getprop(fdt, node_offset, propname, &fdtlen);

	if (fdtprop && !prop)
		return fdt_delprop(fdt, node_offset, propname);
	else if (prop)
		return fdt_setprop(fdt, node_offset, propname, prop, len);
	else
		return -FDT_ERR_NOTFOUND;
}

static int update_pci_dma_nodes(void *fdt, const char *dmapropname)
{
	struct device_node *dn;
	int pci_offset, root_offset, ret = 0;

	if (!firmware_has_feature(FW_FEATURE_LPAR))
		return 0;

	root_offset = fdt_path_offset(fdt, "/");
	for_each_node_with_property(dn, dmapropname) {
		pci_offset = fdt_subnode_offset(fdt, root_offset, of_node_full_name(dn));
		if (pci_offset < 0)
			continue;

		ret = copy_property(fdt, pci_offset, dn, "ibm,dma-window");
		if (ret < 0) {
			of_node_put(dn);
			break;
		}
		ret = copy_property(fdt, pci_offset, dn, dmapropname);
		if (ret < 0) {
			of_node_put(dn);
			break;
		}
	}

	return ret;
}

/**
 * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel
 *                       being loaded.
 * @image:               kexec image being loaded.
 * @fdt:                 Flattened device tree for the next kernel.
 * @initrd_load_addr:    Address where the next initrd will be loaded.
 * @initrd_len:          Size of the next initrd, or 0 if there will be none.
 * @cmdline:             Command line for the next kernel, or NULL if there will
 *                       be none.
 *
 * Returns 0 on success, negative errno on error.
 */
int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
			unsigned long initrd_load_addr,
			unsigned long initrd_len, const char *cmdline)
{
	struct crash_mem *umem = NULL, *rmem = NULL;
	int i, nr_ranges, ret;

	/*
	 * Restrict memory usage for kdump kernel by setting up
	 * usable memory ranges and memory reserve map.
	 */
	if (image->type == KEXEC_TYPE_CRASH) {
		ret = get_usable_memory_ranges(&umem);
		if (ret)
			goto out;

		ret = update_usable_mem_fdt(fdt, umem);
		if (ret) {
			pr_err("Error setting up usable-memory property for kdump kernel\n");
			goto out;
		}

		/*
		 * Ensure we don't touch crashed kernel's memory except the
		 * first 64K of RAM, which will be backed up.
		 */
		ret = fdt_add_mem_rsv(fdt, BACKUP_SRC_END + 1,
				      crashk_res.start - BACKUP_SRC_SIZE);
		if (ret) {
			pr_err("Error reserving crash memory: %s\n",
			       fdt_strerror(ret));
			goto out;
		}

		/* Ensure backup region is not used by kdump/capture kernel */
		ret = fdt_add_mem_rsv(fdt, image->arch.backup_start,
				      BACKUP_SRC_SIZE);
		if (ret) {
			pr_err("Error reserving memory for backup: %s\n",
			       fdt_strerror(ret));
			goto out;
		}
	}

	/* Update cpus nodes information to account hotplug CPUs. */
	ret =  update_cpus_node(fdt);
	if (ret < 0)
		goto out;

	ret = update_pci_dma_nodes(fdt, DIRECT64_PROPNAME);
	if (ret < 0)
		goto out;

	ret = update_pci_dma_nodes(fdt, DMA64_PROPNAME);
	if (ret < 0)
		goto out;

	/* Update memory reserve map */
	ret = get_reserved_memory_ranges(&rmem);
	if (ret)
		goto out;

	nr_ranges = rmem ? rmem->nr_ranges : 0;
	for (i = 0; i < nr_ranges; i++) {
		u64 base, size;

		base = rmem->ranges[i].start;
		size = rmem->ranges[i].end - base + 1;
		ret = fdt_add_mem_rsv(fdt, base, size);
		if (ret) {
			pr_err("Error updating memory reserve map: %s\n",
			       fdt_strerror(ret));
			goto out;
		}
	}

	// If we have PLPKS active, we need to provide the password to the new kernel
	if (plpks_is_available())
		ret = plpks_populate_fdt(fdt);

out:
	kfree(rmem);
	kfree(umem);
	return ret;
}

/**
 * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal,
 *                              tce-table, reserved-ranges & such (exclude
 *                              memory ranges) as they can't be used for kexec
 *                              segment buffer. Sets kbuf->mem when a suitable
 *                              memory hole is found.
 * @kbuf:                       Buffer contents and memory parameters.
 *
 * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align.
 *
 * Returns 0 on success, negative errno on error.
 */
int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
{
	struct crash_mem **emem;
	u64 buf_min, buf_max;
	int ret;

	/* Look up the exclude ranges list while locating the memory hole */
	emem = &(kbuf->image->arch.exclude_ranges);
	if (!(*emem) || ((*emem)->nr_ranges == 0)) {
		pr_warn("No exclude range list. Using the default locate mem hole method\n");
		return kexec_locate_mem_hole(kbuf);
	}

	buf_min = kbuf->buf_min;
	buf_max = kbuf->buf_max;
	/* Segments for kdump kernel should be within crashkernel region */
	if (kbuf->image->type == KEXEC_TYPE_CRASH) {
		buf_min = (buf_min < crashk_res.start ?
			   crashk_res.start : buf_min);
		buf_max = (buf_max > crashk_res.end ?
			   crashk_res.end : buf_max);
	}

	if (buf_min > buf_max) {
		pr_err("Invalid buffer min and/or max values\n");
		return -EINVAL;
	}

	if (kbuf->top_down)
		ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max,
						     *emem);
	else
		ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max,
						      *emem);

	/* Add the buffer allocated to the exclude list for the next lookup */
	if (!ret) {
		add_mem_range(emem, kbuf->mem, kbuf->memsz);
		sort_memory_ranges(*emem, true);
	} else {
		pr_err("Failed to locate memory buffer of size %lu\n",
		       kbuf->memsz);
	}
	return ret;
}

/**
 * arch_kexec_kernel_image_probe - Does additional handling needed to setup
 *                                 kexec segments.
 * @image:                         kexec image being loaded.
 * @buf:                           Buffer pointing to elf data.
 * @buf_len:                       Length of the buffer.
 *
 * Returns 0 on success, negative errno on error.
 */
int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
				  unsigned long buf_len)
{
	int ret;

	/* Get exclude memory ranges needed for setting up kexec segments */
	ret = get_exclude_memory_ranges(&(image->arch.exclude_ranges));
	if (ret) {
		pr_err("Failed to setup exclude memory ranges for buffer lookup\n");
		return ret;
	}

	return kexec_image_probe_default(image, buf, buf_len);
}

/**
 * arch_kimage_file_post_load_cleanup - Frees up all the allocations done
 *                                      while loading the image.
 * @image:                              kexec image being loaded.
 *
 * Returns 0 on success, negative errno on error.
 */
int arch_kimage_file_post_load_cleanup(struct kimage *image)
{
	kfree(image->arch.exclude_ranges);
	image->arch.exclude_ranges = NULL;

	vfree(image->arch.backup_buf);
	image->arch.backup_buf = NULL;

	vfree(image->elf_headers);
	image->elf_headers = NULL;
	image->elf_headers_sz = 0;

	kvfree(image->arch.fdt);
	image->arch.fdt = NULL;

	return kexec_image_post_load_cleanup_default(image);
}