Bootlin logo

Elixir Cross Referencer

   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
/*
 * Handle the memory map.
 * The functions here do the job until bootmem takes over.
 *
 *  Getting sanitize_e820_map() in sync with i386 version by applying change:
 *  -  Provisions for empty E820 memory regions (reported by certain BIOSes).
 *     Alex Achenbach <xela@slit.de>, December 2002.
 *  Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
 *
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
#include <linux/export.h>
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <linux/firmware-map.h>
#include <linux/memblock.h>
#include <linux/sort.h>

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

/*
 * The e820 map is the map that gets modified e.g. with command line parameters
 * and that is also registered with modifications in the kernel resource tree
 * with the iomem_resource as parent.
 *
 * The e820_saved is directly saved after the BIOS-provided memory map is
 * copied. It doesn't get modified afterwards. It's registered for the
 * /sys/firmware/memmap interface.
 *
 * That memory map is not modified and is used as base for kexec. The kexec'd
 * kernel should get the same memory map as the firmware provides. Then the
 * user can e.g. boot the original kernel with mem=1G while still booting the
 * next kernel with full memory.
 */
struct e820map e820;
struct e820map e820_saved;

/* 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.
 */
int
e820_any_mapped(u64 start, u64 end, unsigned type)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];

		if (type && ei->type != type)
			continue;
		if (ei->addr >= end || ei->addr + ei->size <= start)
			continue;
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(e820_any_mapped);

/*
 * This function checks if the entire range <start,end> is mapped with type.
 *
 * Note: this function only works correct if the e820 table is sorted and
 * not-overlapping, which is the case
 */
int __init e820_all_mapped(u64 start, u64 end, unsigned type)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];

		if (type && ei->type != type)
			continue;
		/* is the region (part) in overlap with the current region ?*/
		if (ei->addr >= end || ei->addr + ei->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 (ei->addr <= start)
			start = ei->addr + ei->size;
		/*
		 * if start is now at or beyond end, we're done, full
		 * coverage
		 */
		if (start >= end)
			return 1;
	}
	return 0;
}

/*
 * Add a memory region to the kernel e820 map.
 */
static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
					 int type)
{
	int x = e820x->nr_map;

	if (x >= ARRAY_SIZE(e820x->map)) {
		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
		return;
	}

	e820x->map[x].addr = start;
	e820x->map[x].size = size;
	e820x->map[x].type = type;
	e820x->nr_map++;
}

void __init e820_add_region(u64 start, u64 size, int type)
{
	__e820_add_region(&e820, start, size, type);
}

static void __init e820_print_type(u32 type)
{
	switch (type) {
	case E820_RAM:
	case E820_RESERVED_KERN:
		printk(KERN_CONT "(usable)");
		break;
	case E820_RESERVED:
		printk(KERN_CONT "(reserved)");
		break;
	case E820_ACPI:
		printk(KERN_CONT "(ACPI data)");
		break;
	case E820_NVS:
		printk(KERN_CONT "(ACPI NVS)");
		break;
	case E820_UNUSABLE:
		printk(KERN_CONT "(unusable)");
		break;
	default:
		printk(KERN_CONT "type %u", type);
		break;
	}
}

void __init e820_print_map(char *who)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
		       (unsigned long long) e820.map[i].addr,
		       (unsigned long long)
		       (e820.map[i].addr + e820.map[i].size));
		e820_print_type(e820.map[i].type);
		printk(KERN_CONT "\n");
	}
}

/*
 * Sanitize the BIOS e820 map.
 *
 * Some e820 responses 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 biosmap points to an array of 'struct
 * e820entry' which on entry has elements in the range [0, *pnr_map)
 * valid, and which has space for up to max_nr_map entries.
 * On return, the resulting sanitized e820 map entries will be in
 * overwritten in the same location, starting at biosmap.
 *
 * The integer pointed to by pnr_map must be valid on entry (the
 * current number of valid entries located at biosmap) and will
 * be updated on return, with the new number of valid entries
 * (something no more than max_nr_map.)
 *
 * The return value from sanitize_e820_map() 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 {
	struct e820entry *pbios; /* pointer to original bios entry */
	unsigned long long addr; /* address for this change point */
};

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 unequal, 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->pbios->addr) - (bp->addr != bp->pbios->addr);
}

int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
			     u32 *pnr_map)
{
	static struct change_member change_point_list[2*E820_X_MAX] __initdata;
	static struct change_member *change_point[2*E820_X_MAX] __initdata;
	static struct e820entry *overlap_list[E820_X_MAX] __initdata;
	static struct e820entry new_bios[E820_X_MAX] __initdata;
	unsigned long current_type, last_type;
	unsigned long long last_addr;
	int chgidx;
	int overlap_entries;
	int new_bios_entry;
	int old_nr, new_nr, chg_nr;
	int i;

	/* if there's only one memory region, don't bother */
	if (*pnr_map < 2)
		return -1;

	old_nr = *pnr_map;
	BUG_ON(old_nr > max_nr_map);

	/* bail out if we find any unreasonable addresses in bios map */
	for (i = 0; i < old_nr; i++)
		if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
			return -1;

	/* create pointers for initial change-point information (for sorting) */
	for (i = 0; i < 2 * old_nr; i++)
		change_point[i] = &change_point_list[i];

	/* record all known change-points (starting and ending addresses),
	   omitting those that are for empty memory regions */
	chgidx = 0;
	for (i = 0; i < old_nr; i++)	{
		if (biosmap[i].size != 0) {
			change_point[chgidx]->addr = biosmap[i].addr;
			change_point[chgidx++]->pbios = &biosmap[i];
			change_point[chgidx]->addr = biosmap[i].addr +
				biosmap[i].size;
			change_point[chgidx++]->pbios = &biosmap[i];
		}
	}
	chg_nr = chgidx;

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

	/* create a new bios memory map, removing overlaps */
	overlap_entries = 0;	 /* number of entries in the overlap table */
	new_bios_entry = 0;	 /* index for creating new bios 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 affect on the new bios map */
	for (chgidx = 0; chgidx < chg_nr; chgidx++) {
		/* keep track of all overlapping bios entries */
		if (change_point[chgidx]->addr ==
		    change_point[chgidx]->pbios->addr) {
			/*
			 * add map entry to overlap list (> 1 entry
			 * implies an overlap)
			 */
			overlap_list[overlap_entries++] =
				change_point[chgidx]->pbios;
		} else {
			/*
			 * remove entry from list (order independent,
			 * so swap with last)
			 */
			for (i = 0; i < overlap_entries; i++) {
				if (overlap_list[i] ==
				    change_point[chgidx]->pbios)
					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 bios map based on this
		 * information
		 */
		if (current_type != last_type)	{
			if (last_type != 0)	 {
				new_bios[new_bios_entry].size =
					change_point[chgidx]->addr - last_addr;
				/*
				 * move forward only if the new size
				 * was non-zero
				 */
				if (new_bios[new_bios_entry].size != 0)
					/*
					 * no more space left for new
					 * bios entries ?
					 */
					if (++new_bios_entry >= max_nr_map)
						break;
			}
			if (current_type != 0)	{
				new_bios[new_bios_entry].addr =
					change_point[chgidx]->addr;
				new_bios[new_bios_entry].type = current_type;
				last_addr = change_point[chgidx]->addr;
			}
			last_type = current_type;
		}
	}
	/* retain count for new bios entries */
	new_nr = new_bios_entry;

	/* copy new bios mapping into original location */
	memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry));
	*pnr_map = new_nr;

	return 0;
}

static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
{
	while (nr_map) {
		u64 start = biosmap->addr;
		u64 size = biosmap->size;
		u64 end = start + size;
		u32 type = biosmap->type;

		/* Overflow in 64 bits? Ignore the memory map. */
		if (start > end)
			return -1;

		e820_add_region(start, size, type);

		biosmap++;
		nr_map--;
	}
	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_map(struct e820entry *biosmap, int nr_map)
{
	/* Only one memory region (or negative)? Ignore it */
	if (nr_map < 2)
		return -1;

	return __append_e820_map(biosmap, nr_map);
}

static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
					u64 size, unsigned old_type,
					unsigned 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 range: %016Lx - %016Lx ",
		       (unsigned long long) start,
		       (unsigned long long) end);
	e820_print_type(old_type);
	printk(KERN_CONT " ==> ");
	e820_print_type(new_type);
	printk(KERN_CONT "\n");

	for (i = 0; i < e820x->nr_map; i++) {
		struct e820entry *ei = &e820x->map[i];
		u64 final_start, final_end;
		u64 ei_end;

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

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

		/* new range is totally covered? */
		if (ei->addr < start && ei_end > end) {
			__e820_add_region(e820x, start, size, new_type);
			__e820_add_region(e820x, end, ei_end - end, ei->type);
			ei->size = start - ei->addr;
			real_updated_size += size;
			continue;
		}

		/* partially covered */
		final_start = max(start, ei->addr);
		final_end = min(end, ei_end);
		if (final_start >= final_end)
			continue;

		__e820_add_region(e820x, 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
		 * size at first.
		 */
		ei->size -= final_end - final_start;
		if (ei->addr < final_start)
			continue;
		ei->addr = final_end;
	}
	return real_updated_size;
}

u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
			     unsigned new_type)
{
	return __e820_update_range(&e820, start, size, old_type, new_type);
}

static u64 __init e820_update_range_saved(u64 start, u64 size,
					  unsigned old_type, unsigned new_type)
{
	return __e820_update_range(&e820_saved, start, size, old_type,
				     new_type);
}

/* make e820 not cover the range */
u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
			     int checktype)
{
	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 range: %016Lx - %016Lx ",
		       (unsigned long long) start,
		       (unsigned long long) end);
	if (checktype)
		e820_print_type(old_type);
	printk(KERN_CONT "\n");

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 final_start, final_end;
		u64 ei_end;

		if (checktype && ei->type != old_type)
			continue;

		ei_end = ei->addr + ei->size;
		/* totally covered? */
		if (ei->addr >= start && ei_end <= end) {
			real_removed_size += ei->size;
			memset(ei, 0, sizeof(struct e820entry));
			continue;
		}

		/* new range is totally covered? */
		if (ei->addr < start && ei_end > end) {
			e820_add_region(end, ei_end - end, ei->type);
			ei->size = start - ei->addr;
			real_removed_size += size;
			continue;
		}

		/* partially covered */
		final_start = max(start, ei->addr);
		final_end = min(end, ei_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
		 * size at first.
		 */
		ei->size -= final_end - final_start;
		if (ei->addr < final_start)
			continue;
		ei->addr = final_end;
	}
	return real_removed_size;
}

void __init update_e820(void)
{
	u32 nr_map;

	nr_map = e820.nr_map;
	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
		return;
	e820.nr_map = nr_map;
	printk(KERN_INFO "modified physical RAM map:\n");
	e820_print_map("modified");
}
static void __init update_e820_saved(void)
{
	u32 nr_map;

	nr_map = e820_saved.nr_map;
	if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map))
		return;
	e820_saved.nr_map = nr_map;
}
#define MAX_GAP_END 0x100000000ull
/*
 * Search for a gap in the e820 memory space from start_addr to end_addr.
 */
__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
		unsigned long start_addr, unsigned long long end_addr)
{
	unsigned long long last;
	int i = e820.nr_map;
	int found = 0;

	last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;

	while (--i >= 0) {
		unsigned long long start = e820.map[i].addr;
		unsigned long long end = start + e820.map[i].size;

		if (end < start_addr)
			continue;

		/*
		 * 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 PCI to assign MMIO resources
 * for hotplug or unconfigured devices in.
 * Hopefully the BIOS let enough space left.
 */
__init void e820_setup_gap(void)
{
	unsigned long gapstart, gapsize;
	int found;

	gapstart = 0x10000000;
	gapsize = 0x400000;
	found  = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);

#ifdef CONFIG_X86_64
	if (!found) {
		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
		printk(KERN_ERR
	"PCI: Warning: Cannot find a gap in the 32bit address range\n"
	"PCI: Unassigned devices with 32bit resource registers may break!\n");
	}
#endif

	/*
	 * e820_reserve_resources_late protect stolen RAM already
	 */
	pci_mem_start = gapstart;

	printk(KERN_INFO
	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
	       pci_mem_start, gapstart, gapsize);
}

/**
 * Because of the size limitation of struct boot_params, only first
 * 128 E820 memory entries are passed to kernel via
 * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
 * linked list of struct setup_data, which is parsed here.
 */
void __init parse_e820_ext(struct setup_data *sdata)
{
	int entries;
	struct e820entry *extmap;

	entries = sdata->len / sizeof(struct e820entry);
	extmap = (struct e820entry *)(sdata->data);
	__append_e820_map(extmap, entries);
	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
	printk(KERN_INFO "extended physical RAM map:\n");
	e820_print_map("extended");
}

#if defined(CONFIG_X86_64) || \
	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
/**
 * Find the ranges of physical addresses that do not correspond to
 * e820 RAM areas and mark 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 and assumes the first e820 area to be RAM.
 */
void __init e820_mark_nosave_regions(unsigned long limit_pfn)
{
	int i;
	unsigned long pfn;

	pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
	for (i = 1; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];

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

		pfn = PFN_DOWN(ei->addr + ei->size);
		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
			register_nosave_region(PFN_UP(ei->addr), pfn);

		if (pfn >= limit_pfn)
			break;
	}
}
#endif

#ifdef CONFIG_ACPI
/**
 * Mark ACPI NVS memory region, so that we can save/restore it during
 * hibernation and the subsequent resume.
 */
static int __init e820_mark_nvs_memory(void)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];

		if (ei->type == E820_NVS)
			acpi_nvs_register(ei->addr, ei->size);
	}

	return 0;
}
core_initcall(e820_mark_nvs_memory);
#endif

/*
 * pre allocated 4k and reserved it in memblock and e820_saved
 */
u64 __init early_reserve_e820(u64 size, u64 align)
{
	u64 addr;

	addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
	if (addr) {
		e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
		printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
		update_e820_saved();
	}

	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, unsigned type)
{
	int i;
	unsigned long last_pfn = 0;
	unsigned long max_arch_pfn = MAX_ARCH_PFN;

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		unsigned long start_pfn;
		unsigned long end_pfn;

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

		start_pfn = ei->addr >> PAGE_SHIFT;
		end_pfn = (ei->addr + ei->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;

	printk(KERN_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_RAM);
}

unsigned long __init e820_end_of_low_ram_pfn(void)
{
	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
}

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

static int userdef __initdata;

/* "mem=nopentium" disables the 4MB page tables. */
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
		printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
		return -EINVAL;
#endif
	}

	userdef = 1;
	mem_size = memparse(p, &p);
	/* don't remove all of memory when handling "mem={invalid}" param */
	if (mem_size == 0)
		return -EINVAL;
	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);

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

static int __init parse_memmap_opt(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 mem size before original memory map is
		 * reset.
		 */
		saved_max_pfn = e820_end_of_ram_pfn();
#endif
		e820.nr_map = 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_add_region(start_at, mem_size, E820_RAM);
	} else if (*p == '#') {
		start_at = memparse(p+1, &p);
		e820_add_region(start_at, mem_size, E820_ACPI);
	} else if (*p == '$') {
		start_at = memparse(p+1, &p);
		e820_add_region(start_at, mem_size, E820_RESERVED);
	} else
		e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);

	return *p == '\0' ? 0 : -EINVAL;
}
early_param("memmap", parse_memmap_opt);

void __init finish_e820_parsing(void)
{
	if (userdef) {
		u32 nr = e820.nr_map;

		if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0)
			early_panic("Invalid user supplied memory map");
		e820.nr_map = nr;

		printk(KERN_INFO "user-defined physical RAM map:\n");
		e820_print_map("user");
	}
}

static inline const char *e820_type_to_string(int e820_type)
{
	switch (e820_type) {
	case E820_RESERVED_KERN:
	case E820_RAM:	return "System RAM";
	case E820_ACPI:	return "ACPI Tables";
	case E820_NVS:	return "ACPI Non-volatile Storage";
	case E820_UNUSABLE:	return "Unusable memory";
	default:	return "reserved";
	}
}

/*
 * 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 = alloc_bootmem(sizeof(struct resource) * e820.nr_map);
	e820_res = res;
	for (i = 0; i < e820.nr_map; i++) {
		end = e820.map[i].addr + e820.map[i].size - 1;
		if (end != (resource_size_t)end) {
			res++;
			continue;
		}
		res->name = e820_type_to_string(e820.map[i].type);
		res->start = e820.map[i].addr;
		res->end = end;

		res->flags = IORESOURCE_MEM;

		/*
		 * don't register the region that could be conflicted with
		 * pci device BAR resource and insert them later in
		 * pcibios_resource_survey()
		 */
		if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
			res->flags |= IORESOURCE_BUSY;
			insert_resource(&iomem_resource, res);
		}
		res++;
	}

	for (i = 0; i < e820_saved.nr_map; i++) {
		struct e820entry *entry = &e820_saved.map[i];
		firmware_map_add_early(entry->addr,
			entry->addr + entry->size - 1,
			e820_type_to_string(entry->type));
	}
}

/* How much should we pad RAM ending depending on where it is? */
static unsigned long 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.nr_map; 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.nr_map; i++) {
		struct e820entry *entry = &e820.map[i];
		u64 start, end;

		if (entry->type != E820_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 "reserve RAM buffer: %016llx - %016llx ",
			       start, end);
		reserve_region_with_split(&iomem_resource, start, end,
					  "RAM buffer");
	}
}

char *__init default_machine_specific_memory_setup(void)
{
	char *who = "BIOS-e820";
	u32 new_nr;
	/*
	 * 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
	 */
	new_nr = boot_params.e820_entries;
	sanitize_e820_map(boot_params.e820_map,
			ARRAY_SIZE(boot_params.e820_map),
			&new_nr);
	boot_params.e820_entries = new_nr;
	if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
	  < 0) {
		u64 mem_size;

		/* compare results from other methods and take the greater */
		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.nr_map = 0;
		e820_add_region(0, LOWMEMSIZE(), E820_RAM);
		e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
	}

	/* In case someone cares... */
	return who;
}

void __init setup_memory_map(void)
{
	char *who;

	who = x86_init.resources.memory_setup();
	memcpy(&e820_saved, &e820, sizeof(struct e820map));
	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
	e820_print_map(who);
}

void __init memblock_x86_fill(void)
{
	int i;
	u64 end;

	/*
	 * EFI may have more than 128 entries
	 * We are safe to enable resizing, beause memblock_x86_fill()
	 * is rather later for x86
	 */
	memblock_allow_resize();

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];

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

		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
			continue;

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

	memblock_dump_all();
}

void __init memblock_find_dma_reserve(void)
{
#ifdef CONFIG_X86_64
	u64 nr_pages = 0, nr_free_pages = 0;
	unsigned long start_pfn, end_pfn;
	phys_addr_t start, end;
	int i;
	u64 u;

	/*
	 * need to find out used area below MAX_DMA_PFN
	 * need to use memblock to get free size in [0, MAX_DMA_PFN]
	 * at first, and assume boot_mem will not take below MAX_DMA_PFN
	 */
	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
		start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN);
		end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN);
		nr_pages += end_pfn - start_pfn;
	}

	for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) {
		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
		if (start_pfn < end_pfn)
			nr_free_pages += end_pfn - start_pfn;
	}

	set_dma_reserve(nr_pages - nr_free_pages);
#endif
}