summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/e820.c
blob: 8f32e705a980b63a0f8a6a2d420196d754735e91 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Low level x86 E820 memory map handling functions.
 *
 * The firmware and bootloader passes us the "E820 table", which is the primary
 * physical memory layout description available about x86 systems.
 *
 * The kernel takes the E820 memory layout and optionally modifies it with
 * quirks and other tweaks, and feeds that into the generic Linux memory
 * allocation code routines via a platform independent interface (memblock, etc.).
 */
#include <linux/crash_dump.h>
#include <linux/memblock.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <linux/firmware-map.h>
#include <linux/sort.h>
#include <linux/memory_hotplug.h>

#include <asm/e820/api.h>
#include <asm/setup.h>

/*
 * We organize the E820 table into three main data structures:
 *
 * - 'e820_table_firmware': the original firmware version passed to us by the
 *   bootloader - not modified by the kernel. It is composed of two parts:
 *   the first 128 E820 memory entries in boot_params.e820_table and the remaining
 *   (if any) entries of the SETUP_E820_EXT nodes. We use this to:
 *
 *       - inform the user about the firmware's notion of memory layout
 *         via /sys/firmware/memmap
 *
 *       - the hibernation code uses it to generate a kernel-independent MD5
 *         fingerprint of the physical memory layout of a system.
 *
 * - 'e820_table_kexec': a slightly modified (by the kernel) firmware version
 *   passed to us by the bootloader - the major difference between
 *   e820_table_firmware[] and this one is that, the latter marks the setup_data
 *   list created by the EFI boot stub as reserved, so that kexec can reuse the
 *   setup_data information in the second kernel. Besides, e820_table_kexec[]
 *   might also be modified by the kexec itself to fake a mptable.
 *   We use this to:
 *
 *       - kexec, which is a bootloader in disguise, uses the original E820
 *         layout to pass to the kexec-ed kernel. This way the original kernel
 *         can have a restricted E820 map while the kexec()-ed kexec-kernel
 *         can have access to full memory - etc.
 *
 * - 'e820_table': this is the main E820 table that is massaged by the
 *   low level x86 platform code, or modified by boot parameters, before
 *   passed on to higher level MM layers.
 *
 * Once the E820 map has been converted to the standard Linux memory layout
 * information its role stops - modifying it has no effect and does not get
 * re-propagated. So itsmain role is a temporary bootstrap storage of firmware
 * specific memory layout data during early bootup.
 */
static struct e820_table e820_table_init		__initdata;
static struct e820_table e820_table_kexec_init		__initdata;
static struct e820_table e820_table_firmware_init	__initdata;

struct e820_table *e820_table __refdata			= &e820_table_init;
struct e820_table *e820_table_kexec __refdata		= &e820_table_kexec_init;
struct e820_table *e820_table_firmware __refdata	= &e820_table_firmware_init;

/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0xaeedbabe;
#ifdef CONFIG_PCI
EXPORT_SYMBOL(pci_mem_start);
#endif

/*
 * This function checks if any part of the range <start,end> is mapped
 * with type.
 */
static bool _e820__mapped_any(struct e820_table *table,
			      u64 start, u64 end, enum e820_type type)
{
	int i;

	for (i = 0; i < table->nr_entries; i++) {
		struct e820_entry *entry = &table->entries[i];

		if (type && entry->type != type)
			continue;
		if (entry->addr >= end || entry->addr + entry->size <= start)
			continue;
		return 1;
	}
	return 0;
}

bool e820__mapped_raw_any(u64 start, u64 end, enum e820_type type)
{
	return _e820__mapped_any(e820_table_firmware, start, end, type);
}
EXPORT_SYMBOL_GPL(e820__mapped_raw_any);

bool e820__mapped_any(u64 start, u64 end, enum e820_type type)
{
	return _e820__mapped_any(e820_table, start, end, type);
}
EXPORT_SYMBOL_GPL(e820__mapped_any);

/*
 * This function checks if the entire <start,end> range is mapped with 'type'.
 *
 * Note: this function only works correctly once the E820 table is sorted and
 * not-overlapping (at least for the range specified), which is the case normally.
 */
static struct e820_entry *__e820__mapped_all(u64 start, u64 end,
					     enum e820_type type)
{
	int i;

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];

		if (type && entry->type != type)
			continue;

		/* Is the region (part) in overlap with the current region? */
		if (entry->addr >= end || entry->addr + entry->size <= start)
			continue;

		/*
		 * If the region is at the beginning of <start,end> we move
		 * 'start' to the end of the region since it's ok until there
		 */
		if (entry->addr <= start)
			start = entry->addr + entry->size;

		/*
		 * If 'start' is now at or beyond 'end', we're done, full
		 * coverage of the desired range exists:
		 */
		if (start >= end)
			return entry;
	}

	return NULL;
}

/*
 * This function checks if the entire range <start,end> is mapped with type.
 */
bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type)
{
	return __e820__mapped_all(start, end, type);
}

/*
 * This function returns the type associated with the range <start,end>.
 */
int e820__get_entry_type(u64 start, u64 end)
{
	struct e820_entry *entry = __e820__mapped_all(start, end, 0);

	return entry ? entry->type : -EINVAL;
}

/*
 * Add a memory region to the kernel E820 map.
 */
static void __init __e820__range_add(struct e820_table *table, u64 start, u64 size, enum e820_type type)
{
	int x = table->nr_entries;

	if (x >= ARRAY_SIZE(table->entries)) {
		pr_err("too many entries; ignoring [mem %#010llx-%#010llx]\n",
		       start, start + size - 1);
		return;
	}

	table->entries[x].addr = start;
	table->entries[x].size = size;
	table->entries[x].type = type;
	table->nr_entries++;
}

void __init e820__range_add(u64 start, u64 size, enum e820_type type)
{
	__e820__range_add(e820_table, start, size, type);
}

static void __init e820_print_type(enum e820_type type)
{
	switch (type) {
	case E820_TYPE_RAM:		/* Fall through: */
	case E820_TYPE_RESERVED_KERN:	pr_cont("usable");			break;
	case E820_TYPE_RESERVED:	pr_cont("reserved");			break;
	case E820_TYPE_ACPI:		pr_cont("ACPI data");			break;
	case E820_TYPE_NVS:		pr_cont("ACPI NVS");			break;
	case E820_TYPE_UNUSABLE:	pr_cont("unusable");			break;
	case E820_TYPE_PMEM:		/* Fall through: */
	case E820_TYPE_PRAM:		pr_cont("persistent (type %u)", type);	break;
	default:			pr_cont("type %u", type);		break;
	}
}

void __init e820__print_table(char *who)
{
	int i;

	for (i = 0; i < e820_table->nr_entries; i++) {
		pr_info("%s: [mem %#018Lx-%#018Lx] ",
			who,
			e820_table->entries[i].addr,
			e820_table->entries[i].addr + e820_table->entries[i].size - 1);

		e820_print_type(e820_table->entries[i].type);
		pr_cont("\n");
	}
}

/*
 * Sanitize an E820 map.
 *
 * Some E820 layouts include overlapping entries. The following
 * replaces the original E820 map with a new one, removing overlaps,
 * and resolving conflicting memory types in favor of highest
 * numbered type.
 *
 * The input parameter 'entries' points to an array of 'struct
 * e820_entry' which on entry has elements in the range [0, *nr_entries)
 * valid, and which has space for up to max_nr_entries entries.
 * On return, the resulting sanitized E820 map entries will be in
 * overwritten in the same location, starting at 'entries'.
 *
 * The integer pointed to by nr_entries must be valid on entry (the
 * current number of valid entries located at 'entries'). If the
 * sanitizing succeeds the *nr_entries will be updated with the new
 * number of valid entries (something no more than max_nr_entries).
 *
 * The return value from e820__update_table() is zero if it
 * successfully 'sanitized' the map entries passed in, and is -1
 * if it did nothing, which can happen if either of (1) it was
 * only passed one map entry, or (2) any of the input map entries
 * were invalid (start + size < start, meaning that the size was
 * so big the described memory range wrapped around through zero.)
 *
 *	Visually we're performing the following
 *	(1,2,3,4 = memory types)...
 *
 *	Sample memory map (w/overlaps):
 *	   ____22__________________
 *	   ______________________4_
 *	   ____1111________________
 *	   _44_____________________
 *	   11111111________________
 *	   ____________________33__
 *	   ___________44___________
 *	   __________33333_________
 *	   ______________22________
 *	   ___________________2222_
 *	   _________111111111______
 *	   _____________________11_
 *	   _________________4______
 *
 *	Sanitized equivalent (no overlap):
 *	   1_______________________
 *	   _44_____________________
 *	   ___1____________________
 *	   ____22__________________
 *	   ______11________________
 *	   _________1______________
 *	   __________3_____________
 *	   ___________44___________
 *	   _____________33_________
 *	   _______________2________
 *	   ________________1_______
 *	   _________________4______
 *	   ___________________2____
 *	   ____________________33__
 *	   ______________________4_
 */
struct change_member {
	/* Pointer to the original entry: */
	struct e820_entry	*entry;
	/* Address for this change point: */
	unsigned long long	addr;
};

static struct change_member	change_point_list[2*E820_MAX_ENTRIES]	__initdata;
static struct change_member	*change_point[2*E820_MAX_ENTRIES]	__initdata;
static struct e820_entry	*overlap_list[E820_MAX_ENTRIES]		__initdata;
static struct e820_entry	new_entries[E820_MAX_ENTRIES]		__initdata;

static int __init cpcompare(const void *a, const void *b)
{
	struct change_member * const *app = a, * const *bpp = b;
	const struct change_member *ap = *app, *bp = *bpp;

	/*
	 * Inputs are pointers to two elements of change_point[].  If their
	 * addresses are not equal, their difference dominates.  If the addresses
	 * are equal, then consider one that represents the end of its region
	 * to be greater than one that does not.
	 */
	if (ap->addr != bp->addr)
		return ap->addr > bp->addr ? 1 : -1;

	return (ap->addr != ap->entry->addr) - (bp->addr != bp->entry->addr);
}

int __init e820__update_table(struct e820_table *table)
{
	struct e820_entry *entries = table->entries;
	u32 max_nr_entries = ARRAY_SIZE(table->entries);
	enum e820_type current_type, last_type;
	unsigned long long last_addr;
	u32 new_nr_entries, overlap_entries;
	u32 i, chg_idx, chg_nr;

	/* If there's only one memory region, don't bother: */
	if (table->nr_entries < 2)
		return -1;

	BUG_ON(table->nr_entries > max_nr_entries);

	/* Bail out if we find any unreasonable addresses in the map: */
	for (i = 0; i < table->nr_entries; i++) {
		if (entries[i].addr + entries[i].size < entries[i].addr)
			return -1;
	}

	/* Create pointers for initial change-point information (for sorting): */
	for (i = 0; i < 2 * table->nr_entries; i++)
		change_point[i] = &change_point_list[i];

	/*
	 * Record all known change-points (starting and ending addresses),
	 * omitting empty memory regions:
	 */
	chg_idx = 0;
	for (i = 0; i < table->nr_entries; i++)	{
		if (entries[i].size != 0) {
			change_point[chg_idx]->addr	= entries[i].addr;
			change_point[chg_idx++]->entry	= &entries[i];
			change_point[chg_idx]->addr	= entries[i].addr + entries[i].size;
			change_point[chg_idx++]->entry	= &entries[i];
		}
	}
	chg_nr = chg_idx;

	/* Sort change-point list by memory addresses (low -> high): */
	sort(change_point, chg_nr, sizeof(*change_point), cpcompare, NULL);

	/* Create a new memory map, removing overlaps: */
	overlap_entries = 0;	 /* Number of entries in the overlap table */
	new_nr_entries = 0;	 /* Index for creating new map entries */
	last_type = 0;		 /* Start with undefined memory type */
	last_addr = 0;		 /* Start with 0 as last starting address */

	/* Loop through change-points, determining effect on the new map: */
	for (chg_idx = 0; chg_idx < chg_nr; chg_idx++) {
		/* Keep track of all overlapping entries */
		if (change_point[chg_idx]->addr == change_point[chg_idx]->entry->addr) {
			/* Add map entry to overlap list (> 1 entry implies an overlap) */
			overlap_list[overlap_entries++] = change_point[chg_idx]->entry;
		} else {
			/* Remove entry from list (order independent, so swap with last): */
			for (i = 0; i < overlap_entries; i++) {
				if (overlap_list[i] == change_point[chg_idx]->entry)
					overlap_list[i] = overlap_list[overlap_entries-1];
			}
			overlap_entries--;
		}
		/*
		 * If there are overlapping entries, decide which
		 * "type" to use (larger value takes precedence --
		 * 1=usable, 2,3,4,4+=unusable)
		 */
		current_type = 0;
		for (i = 0; i < overlap_entries; i++) {
			if (overlap_list[i]->type > current_type)
				current_type = overlap_list[i]->type;
		}

		/* Continue building up new map based on this information: */
		if (current_type != last_type || current_type == E820_TYPE_PRAM) {
			if (last_type != 0)	 {
				new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr;
				/* Move forward only if the new size was non-zero: */
				if (new_entries[new_nr_entries].size != 0)
					/* No more space left for new entries? */
					if (++new_nr_entries >= max_nr_entries)
						break;
			}
			if (current_type != 0)	{
				new_entries[new_nr_entries].addr = change_point[chg_idx]->addr;
				new_entries[new_nr_entries].type = current_type;
				last_addr = change_point[chg_idx]->addr;
			}
			last_type = current_type;
		}
	}

	/* Copy the new entries into the original location: */
	memcpy(entries, new_entries, new_nr_entries*sizeof(*entries));
	table->nr_entries = new_nr_entries;

	return 0;
}

static int __init __append_e820_table(struct boot_e820_entry *entries, u32 nr_entries)
{
	struct boot_e820_entry *entry = entries;

	while (nr_entries) {
		u64 start = entry->addr;
		u64 size = entry->size;
		u64 end = start + size - 1;
		u32 type = entry->type;

		/* Ignore the entry on 64-bit overflow: */
		if (start > end && likely(size))
			return -1;

		e820__range_add(start, size, type);

		entry++;
		nr_entries--;
	}
	return 0;
}

/*
 * Copy the BIOS E820 map into a safe place.
 *
 * Sanity-check it while we're at it..
 *
 * If we're lucky and live on a modern system, the setup code
 * will have given us a memory map that we can use to properly
 * set up memory.  If we aren't, we'll fake a memory map.
 */
static int __init append_e820_table(struct boot_e820_entry *entries, u32 nr_entries)
{
	/* Only one memory region (or negative)? Ignore it */
	if (nr_entries < 2)
		return -1;

	return __append_e820_table(entries, nr_entries);
}

static u64 __init
__e820__range_update(struct e820_table *table, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
{
	u64 end;
	unsigned int i;
	u64 real_updated_size = 0;

	BUG_ON(old_type == new_type);

	if (size > (ULLONG_MAX - start))
		size = ULLONG_MAX - start;

	end = start + size;
	printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", start, end - 1);
	e820_print_type(old_type);
	pr_cont(" ==> ");
	e820_print_type(new_type);
	pr_cont("\n");

	for (i = 0; i < table->nr_entries; i++) {
		struct e820_entry *entry = &table->entries[i];
		u64 final_start, final_end;
		u64 entry_end;

		if (entry->type != old_type)
			continue;

		entry_end = entry->addr + entry->size;

		/* Completely covered by new range? */
		if (entry->addr >= start && entry_end <= end) {
			entry->type = new_type;
			real_updated_size += entry->size;
			continue;
		}

		/* New range is completely covered? */
		if (entry->addr < start && entry_end > end) {
			__e820__range_add(table, start, size, new_type);
			__e820__range_add(table, end, entry_end - end, entry->type);
			entry->size = start - entry->addr;
			real_updated_size += size;
			continue;
		}

		/* Partially covered: */
		final_start = max(start, entry->addr);
		final_end = min(end, entry_end);
		if (final_start >= final_end)
			continue;

		__e820__range_add(table, final_start, final_end - final_start, new_type);

		real_updated_size += final_end - final_start;

		/*
		 * Left range could be head or tail, so need to update
		 * its size first:
		 */
		entry->size -= final_end - final_start;
		if (entry->addr < final_start)
			continue;

		entry->addr = final_end;
	}
	return real_updated_size;
}

u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
{
	return __e820__range_update(e820_table, start, size, old_type, new_type);
}

static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type  new_type)
{
	return __e820__range_update(e820_table_kexec, start, size, old_type, new_type);
}

/* Remove a range of memory from the E820 table: */
u64 __init e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type)
{
	int i;
	u64 end;
	u64 real_removed_size = 0;

	if (size > (ULLONG_MAX - start))
		size = ULLONG_MAX - start;

	end = start + size;
	printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", start, end - 1);
	if (check_type)
		e820_print_type(old_type);
	pr_cont("\n");

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];
		u64 final_start, final_end;
		u64 entry_end;

		if (check_type && entry->type != old_type)
			continue;

		entry_end = entry->addr + entry->size;

		/* Completely covered? */
		if (entry->addr >= start && entry_end <= end) {
			real_removed_size += entry->size;
			memset(entry, 0, sizeof(*entry));
			continue;
		}

		/* Is the new range completely covered? */
		if (entry->addr < start && entry_end > end) {
			e820__range_add(end, entry_end - end, entry->type);
			entry->size = start - entry->addr;
			real_removed_size += size;
			continue;
		}

		/* Partially covered: */
		final_start = max(start, entry->addr);
		final_end = min(end, entry_end);
		if (final_start >= final_end)
			continue;

		real_removed_size += final_end - final_start;

		/*
		 * Left range could be head or tail, so need to update
		 * the size first:
		 */
		entry->size -= final_end - final_start;
		if (entry->addr < final_start)
			continue;

		entry->addr = final_end;
	}
	return real_removed_size;
}

void __init e820__update_table_print(void)
{
	if (e820__update_table(e820_table))
		return;

	pr_info("modified physical RAM map:\n");
	e820__print_table("modified");
}

static void __init e820__update_table_kexec(void)
{
	e820__update_table(e820_table_kexec);
}

#define MAX_GAP_END 0x100000000ull

/*
 * Search for a gap in the E820 memory space from 0 to MAX_GAP_END (4GB).
 */
static int __init e820_search_gap(unsigned long *gapstart, unsigned long *gapsize)
{
	unsigned long long last = MAX_GAP_END;
	int i = e820_table->nr_entries;
	int found = 0;

	while (--i >= 0) {
		unsigned long long start = e820_table->entries[i].addr;
		unsigned long long end = start + e820_table->entries[i].size;

		/*
		 * Since "last" is at most 4GB, we know we'll
		 * fit in 32 bits if this condition is true:
		 */
		if (last > end) {
			unsigned long gap = last - end;

			if (gap >= *gapsize) {
				*gapsize = gap;
				*gapstart = end;
				found = 1;
			}
		}
		if (start < last)
			last = start;
	}
	return found;
}

/*
 * Search for the biggest gap in the low 32 bits of the E820
 * memory space. We pass this space to the PCI subsystem, so
 * that it can assign MMIO resources for hotplug or
 * unconfigured devices in.
 *
 * Hopefully the BIOS let enough space left.
 */
__init void e820__setup_pci_gap(void)
{
	unsigned long gapstart, gapsize;
	int found;

	gapsize = 0x400000;
	found  = e820_search_gap(&gapstart, &gapsize);

	if (!found) {
#ifdef CONFIG_X86_64
		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
		pr_err("Cannot find an available gap in the 32-bit address range\n");
		pr_err("PCI devices with unassigned 32-bit BARs may not work!\n");
#else
		gapstart = 0x10000000;
#endif
	}

	/*
	 * e820__reserve_resources_late() protects stolen RAM already:
	 */
	pci_mem_start = gapstart;

	pr_info("[mem %#010lx-%#010lx] available for PCI devices\n",
		gapstart, gapstart + gapsize - 1);
}

/*
 * Called late during init, in free_initmem().
 *
 * Initial e820_table and e820_table_kexec are largish __initdata arrays.
 *
 * Copy them to a (usually much smaller) dynamically allocated area that is
 * sized precisely after the number of e820 entries.
 *
 * This is done after we've performed all the fixes and tweaks to the tables.
 * All functions which modify them are __init functions, which won't exist
 * after free_initmem().
 */
__init void e820__reallocate_tables(void)
{
	struct e820_table *n;
	int size;

	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries;
	n = kmemdup(e820_table, size, GFP_KERNEL);
	BUG_ON(!n);
	e820_table = n;

	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_kexec->nr_entries;
	n = kmemdup(e820_table_kexec, size, GFP_KERNEL);
	BUG_ON(!n);
	e820_table_kexec = n;

	size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries;
	n = kmemdup(e820_table_firmware, size, GFP_KERNEL);
	BUG_ON(!n);
	e820_table_firmware = n;
}

/*
 * Because of the small fixed size of struct boot_params, only the first
 * 128 E820 memory entries are passed to the kernel via boot_params.e820_table,
 * the remaining (if any) entries are passed via the SETUP_E820_EXT node of
 * struct setup_data, which is parsed here.
 */
void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
{
	int entries;
	struct boot_e820_entry *extmap;
	struct setup_data *sdata;

	sdata = early_memremap(phys_addr, data_len);
	entries = sdata->len / sizeof(*extmap);
	extmap = (struct boot_e820_entry *)(sdata->data);

	__append_e820_table(extmap, entries);
	e820__update_table(e820_table);

	memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec));
	memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));

	early_memunmap(sdata, data_len);
	pr_info("extended physical RAM map:\n");
	e820__print_table("extended");
}

/*
 * Find the ranges of physical addresses that do not correspond to
 * E820 RAM areas and register the corresponding pages as 'nosave' for
 * hibernation (32-bit) or software suspend and suspend to RAM (64-bit).
 *
 * This function requires the E820 map to be sorted and without any
 * overlapping entries.
 */
void __init e820__register_nosave_regions(unsigned long limit_pfn)
{
	int i;
	unsigned long pfn = 0;

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];

		if (pfn < PFN_UP(entry->addr))
			register_nosave_region(pfn, PFN_UP(entry->addr));

		pfn = PFN_DOWN(entry->addr + entry->size);

		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
			register_nosave_region(PFN_UP(entry->addr), pfn);

		if (pfn >= limit_pfn)
			break;
	}
}

#ifdef CONFIG_ACPI
/*
 * Register ACPI NVS memory regions, so that we can save/restore them during
 * hibernation and the subsequent resume:
 */
static int __init e820__register_nvs_regions(void)
{
	int i;

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];

		if (entry->type == E820_TYPE_NVS)
			acpi_nvs_register(entry->addr, entry->size);
	}

	return 0;
}
core_initcall(e820__register_nvs_regions);
#endif

/*
 * Allocate the requested number of bytes with the requsted alignment
 * and return (the physical address) to the caller. Also register this
 * range in the 'kexec' E820 table as a reserved range.
 *
 * This allows kexec to fake a new mptable, as if it came from the real
 * system.
 */
u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
{
	u64 addr;

	addr = memblock_phys_alloc(size, align);
	if (addr) {
		e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
		pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n");
		e820__update_table_kexec();
	}

	return addr;
}

#ifdef CONFIG_X86_32
# ifdef CONFIG_X86_PAE
#  define MAX_ARCH_PFN		(1ULL<<(36-PAGE_SHIFT))
# else
#  define MAX_ARCH_PFN		(1ULL<<(32-PAGE_SHIFT))
# endif
#else /* CONFIG_X86_32 */
# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT
#endif

/*
 * Find the highest page frame number we have available
 */
static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type)
{
	int i;
	unsigned long last_pfn = 0;
	unsigned long max_arch_pfn = MAX_ARCH_PFN;

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];
		unsigned long start_pfn;
		unsigned long end_pfn;

		if (entry->type != type)
			continue;

		start_pfn = entry->addr >> PAGE_SHIFT;
		end_pfn = (entry->addr + entry->size) >> PAGE_SHIFT;

		if (start_pfn >= limit_pfn)
			continue;
		if (end_pfn > limit_pfn) {
			last_pfn = limit_pfn;
			break;
		}
		if (end_pfn > last_pfn)
			last_pfn = end_pfn;
	}

	if (last_pfn > max_arch_pfn)
		last_pfn = max_arch_pfn;

	pr_info("last_pfn = %#lx max_arch_pfn = %#lx\n",
		last_pfn, max_arch_pfn);
	return last_pfn;
}

unsigned long __init e820__end_of_ram_pfn(void)
{
	return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM);
}

unsigned long __init e820__end_of_low_ram_pfn(void)
{
	return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM);
}

static void __init early_panic(char *msg)
{
	early_printk(msg);
	panic(msg);
}

static int userdef __initdata;

/* The "mem=nopentium" boot option disables 4MB page tables on 32-bit kernels: */
static int __init parse_memopt(char *p)
{
	u64 mem_size;

	if (!p)
		return -EINVAL;

	if (!strcmp(p, "nopentium")) {
#ifdef CONFIG_X86_32
		setup_clear_cpu_cap(X86_FEATURE_PSE);
		return 0;
#else
		pr_warn("mem=nopentium ignored! (only supported on x86_32)\n");
		return -EINVAL;
#endif
	}

	userdef = 1;
	mem_size = memparse(p, &p);

	/* Don't remove all memory when getting "mem={invalid}" parameter: */
	if (mem_size == 0)
		return -EINVAL;

	e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);

#ifdef CONFIG_MEMORY_HOTPLUG
	max_mem_size = mem_size;
#endif

	return 0;
}
early_param("mem", parse_memopt);

static int __init parse_memmap_one(char *p)
{
	char *oldp;
	u64 start_at, mem_size;

	if (!p)
		return -EINVAL;

	if (!strncmp(p, "exactmap", 8)) {
#ifdef CONFIG_CRASH_DUMP
		/*
		 * If we are doing a crash dump, we still need to know
		 * the real memory size before the original memory map is
		 * reset.
		 */
		saved_max_pfn = e820__end_of_ram_pfn();
#endif
		e820_table->nr_entries = 0;
		userdef = 1;
		return 0;
	}

	oldp = p;
	mem_size = memparse(p, &p);
	if (p == oldp)
		return -EINVAL;

	userdef = 1;
	if (*p == '@') {
		start_at = memparse(p+1, &p);
		e820__range_add(start_at, mem_size, E820_TYPE_RAM);
	} else if (*p == '#') {
		start_at = memparse(p+1, &p);
		e820__range_add(start_at, mem_size, E820_TYPE_ACPI);
	} else if (*p == '$') {
		start_at = memparse(p+1, &p);
		e820__range_add(start_at, mem_size, E820_TYPE_RESERVED);
	} else if (*p == '!') {
		start_at = memparse(p+1, &p);
		e820__range_add(start_at, mem_size, E820_TYPE_PRAM);
	} else if (*p == '%') {
		enum e820_type from = 0, to = 0;

		start_at = memparse(p + 1, &p);
		if (*p == '-')
			from = simple_strtoull(p + 1, &p, 0);
		if (*p == '+')
			to = simple_strtoull(p + 1, &p, 0);
		if (*p != '\0')
			return -EINVAL;
		if (from && to)
			e820__range_update(start_at, mem_size, from, to);
		else if (to)
			e820__range_add(start_at, mem_size, to);
		else if (from)
			e820__range_remove(start_at, mem_size, from, 1);
		else
			e820__range_remove(start_at, mem_size, 0, 0);
	} else {
		e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
	}

	return *p == '\0' ? 0 : -EINVAL;
}

static int __init parse_memmap_opt(char *str)
{
	while (str) {
		char *k = strchr(str, ',');

		if (k)
			*k++ = 0;

		parse_memmap_one(str);
		str = k;
	}

	return 0;
}
early_param("memmap", parse_memmap_opt);

/*
 * Reserve all entries from the bootloader's extensible data nodes list,
 * because if present we are going to use it later on to fetch e820
 * entries from it:
 */
void __init e820__reserve_setup_data(void)
{
	struct setup_data *data;
	u64 pa_data;

	pa_data = boot_params.hdr.setup_data;
	if (!pa_data)
		return;

	while (pa_data) {
		data = early_memremap(pa_data, sizeof(*data));
		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
		e820__range_update_kexec(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
		pa_data = data->next;
		early_memunmap(data, sizeof(*data));
	}

	e820__update_table(e820_table);
	e820__update_table(e820_table_kexec);

	pr_info("extended physical RAM map:\n");
	e820__print_table("reserve setup_data");
}

/*
 * Called after parse_early_param(), after early parameters (such as mem=)
 * have been processed, in which case we already have an E820 table filled in
 * via the parameter callback function(s), but it's not sorted and printed yet:
 */
void __init e820__finish_early_params(void)
{
	if (userdef) {
		if (e820__update_table(e820_table) < 0)
			early_panic("Invalid user supplied memory map");

		pr_info("user-defined physical RAM map:\n");
		e820__print_table("user");
	}
}

static const char *__init e820_type_to_string(struct e820_entry *entry)
{
	switch (entry->type) {
	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
	case E820_TYPE_RAM:		return "System RAM";
	case E820_TYPE_ACPI:		return "ACPI Tables";
	case E820_TYPE_NVS:		return "ACPI Non-volatile Storage";
	case E820_TYPE_UNUSABLE:	return "Unusable memory";
	case E820_TYPE_PRAM:		return "Persistent Memory (legacy)";
	case E820_TYPE_PMEM:		return "Persistent Memory";
	case E820_TYPE_RESERVED:	return "Reserved";
	default:			return "Unknown E820 type";
	}
}

static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
{
	switch (entry->type) {
	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
	case E820_TYPE_RAM:		return IORESOURCE_SYSTEM_RAM;
	case E820_TYPE_ACPI:		/* Fall-through: */
	case E820_TYPE_NVS:		/* Fall-through: */
	case E820_TYPE_UNUSABLE:	/* Fall-through: */
	case E820_TYPE_PRAM:		/* Fall-through: */
	case E820_TYPE_PMEM:		/* Fall-through: */
	case E820_TYPE_RESERVED:	/* Fall-through: */
	default:			return IORESOURCE_MEM;
	}
}

static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
{
	switch (entry->type) {
	case E820_TYPE_ACPI:		return IORES_DESC_ACPI_TABLES;
	case E820_TYPE_NVS:		return IORES_DESC_ACPI_NV_STORAGE;
	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
	case E820_TYPE_RAM:		/* Fall-through: */
	case E820_TYPE_UNUSABLE:	/* Fall-through: */
	case E820_TYPE_RESERVED:	/* Fall-through: */
	default:			return IORES_DESC_NONE;
	}
}

static bool __init do_mark_busy(enum e820_type type, struct resource *res)
{
	/* this is the legacy bios/dos rom-shadow + mmio region */
	if (res->start < (1ULL<<20))
		return true;

	/*
	 * Treat persistent memory like device memory, i.e. reserve it
	 * for exclusive use of a driver
	 */
	switch (type) {
	case E820_TYPE_RESERVED:
	case E820_TYPE_PRAM:
	case E820_TYPE_PMEM:
		return false;
	case E820_TYPE_RESERVED_KERN:
	case E820_TYPE_RAM:
	case E820_TYPE_ACPI:
	case E820_TYPE_NVS:
	case E820_TYPE_UNUSABLE:
	default:
		return true;
	}
}

/*
 * Mark E820 reserved areas as busy for the resource manager:
 */

static struct resource __initdata *e820_res;

void __init e820__reserve_resources(void)
{
	int i;
	struct resource *res;
	u64 end;

	res = memblock_alloc(sizeof(*res) * e820_table->nr_entries,
			     SMP_CACHE_BYTES);
	if (!res)
		panic("%s: Failed to allocate %zu bytes\n", __func__,
		      sizeof(*res) * e820_table->nr_entries);
	e820_res = res;

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = e820_table->entries + i;

		end = entry->addr + entry->size - 1;
		if (end != (resource_size_t)end) {
			res++;
			continue;
		}
		res->start = entry->addr;
		res->end   = end;
		res->name  = e820_type_to_string(entry);
		res->flags = e820_type_to_iomem_type(entry);
		res->desc  = e820_type_to_iores_desc(entry);

		/*
		 * Don't register the region that could be conflicted with
		 * PCI device BAR resources and insert them later in
		 * pcibios_resource_survey():
		 */
		if (do_mark_busy(entry->type, res)) {
			res->flags |= IORESOURCE_BUSY;
			insert_resource(&iomem_resource, res);
		}
		res++;
	}

	/* Expose the bootloader-provided memory layout to the sysfs. */
	for (i = 0; i < e820_table_firmware->nr_entries; i++) {
		struct e820_entry *entry = e820_table_firmware->entries + i;

		firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry));
	}
}

/*
 * How much should we pad the end of RAM, depending on where it is?
 */
static unsigned long __init ram_alignment(resource_size_t pos)
{
	unsigned long mb = pos >> 20;

	/* To 64kB in the first megabyte */
	if (!mb)
		return 64*1024;

	/* To 1MB in the first 16MB */
	if (mb < 16)
		return 1024*1024;

	/* To 64MB for anything above that */
	return 64*1024*1024;
}

#define MAX_RESOURCE_SIZE ((resource_size_t)-1)

void __init e820__reserve_resources_late(void)
{
	int i;
	struct resource *res;

	res = e820_res;
	for (i = 0; i < e820_table->nr_entries; i++) {
		if (!res->parent && res->end)
			insert_resource_expand_to_fit(&iomem_resource, res);
		res++;
	}

	/*
	 * Try to bump up RAM regions to reasonable boundaries, to
	 * avoid stolen RAM:
	 */
	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];
		u64 start, end;

		if (entry->type != E820_TYPE_RAM)
			continue;

		start = entry->addr + entry->size;
		end = round_up(start, ram_alignment(start)) - 1;
		if (end > MAX_RESOURCE_SIZE)
			end = MAX_RESOURCE_SIZE;
		if (start >= end)
			continue;

		printk(KERN_DEBUG "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", start, end);
		reserve_region_with_split(&iomem_resource, start, end, "RAM buffer");
	}
}

/*
 * Pass the firmware (bootloader) E820 map to the kernel and process it:
 */
char *__init e820__memory_setup_default(void)
{
	char *who = "BIOS-e820";

	/*
	 * Try to copy the BIOS-supplied E820-map.
	 *
	 * Otherwise fake a memory map; one section from 0k->640k,
	 * the next section from 1mb->appropriate_mem_k
	 */
	if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) {
		u64 mem_size;

		/* Compare results from other methods and take the one that gives more RAM: */
		if (boot_params.alt_mem_k < boot_params.screen_info.ext_mem_k) {
			mem_size = boot_params.screen_info.ext_mem_k;
			who = "BIOS-88";
		} else {
			mem_size = boot_params.alt_mem_k;
			who = "BIOS-e801";
		}

		e820_table->nr_entries = 0;
		e820__range_add(0, LOWMEMSIZE(), E820_TYPE_RAM);
		e820__range_add(HIGH_MEMORY, mem_size << 10, E820_TYPE_RAM);
	}

	/* We just appended a lot of ranges, sanitize the table: */
	e820__update_table(e820_table);

	return who;
}

/*
 * Calls e820__memory_setup_default() in essence to pick up the firmware/bootloader
 * E820 map - with an optional platform quirk available for virtual platforms
 * to override this method of boot environment processing:
 */
void __init e820__memory_setup(void)
{
	char *who;

	/* This is a firmware interface ABI - make sure we don't break it: */
	BUILD_BUG_ON(sizeof(struct boot_e820_entry) != 20);

	who = x86_init.resources.memory_setup();

	memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec));
	memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));

	pr_info("BIOS-provided physical RAM map:\n");
	e820__print_table(who);
}

void __init e820__memblock_setup(void)
{
	int i;
	u64 end;

	/*
	 * The bootstrap memblock region count maximum is 128 entries
	 * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries
	 * than that - so allow memblock resizing.
	 *
	 * This is safe, because this call happens pretty late during x86 setup,
	 * so we know about reserved memory regions already. (This is important
	 * so that memblock resizing does no stomp over reserved areas.)
	 */
	memblock_allow_resize();

	for (i = 0; i < e820_table->nr_entries; i++) {
		struct e820_entry *entry = &e820_table->entries[i];

		end = entry->addr + entry->size;
		if (end != (resource_size_t)end)
			continue;

		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
			continue;

		memblock_add(entry->addr, entry->size);
	}

	/* Throw away partial pages: */
	memblock_trim_memory(PAGE_SIZE);

	memblock_dump_all();
}