e820.c 27.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 * 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>
14
#include <linux/crash_dump.h>
15
#include <linux/export.h>
16 17
#include <linux/bootmem.h>
#include <linux/pfn.h>
18
#include <linux/suspend.h>
19
#include <linux/acpi.h>
20
#include <linux/firmware-map.h>
21
#include <linux/memblock.h>
22 23

#include <asm/e820.h>
24
#include <asm/proto.h>
25 26
#include <asm/setup.h>

27 28 29 30 31 32 33 34 35 36 37 38 39 40
/*
 * 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.
 */
41
struct e820map e820;
42
struct e820map e820_saved;
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

/* 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.
 */
Y
Yinghai Lu 已提交
109 110
static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
					 int type)
111
{
Y
Yinghai Lu 已提交
112
	int x = e820x->nr_map;
113

114
	if (x >= ARRAY_SIZE(e820x->map)) {
115 116 117 118
		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
		return;
	}

Y
Yinghai Lu 已提交
119 120 121 122 123 124 125 126 127
	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);
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
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;
	}
}

155 156 157 158 159 160 161 162 163
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));
164 165
		e820_print_type(e820.map[i].type);
		printk(KERN_CONT "\n");
166 167 168 169 170 171 172
	}
}

/*
 * Sanitize the BIOS e820 map.
 *
 * Some e820 responses include overlapping entries. The following
173 174 175
 * replaces the original e820 map with a new one, removing overlaps,
 * and resolving conflicting memory types in favor of highest
 * numbered type.
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
 * 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_
229
 */
230

231
int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
232
			     u32 *pnr_map)
233 234 235 236 237
{
	struct change_member {
		struct e820entry *pbios; /* pointer to original bios entry */
		unsigned long long addr; /* address for this change point */
	};
238 239 240 241
	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;
242 243 244 245 246 247 248 249 250 251 252 253 254 255
	struct change_member *change_tmp;
	unsigned long current_type, last_type;
	unsigned long long last_addr;
	int chgidx, still_changing;
	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;
256
	BUG_ON(old_nr > max_nr_map);
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

	/* 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) */
	still_changing = 1;
	while (still_changing)	{
		still_changing = 0;
		for (i = 1; i < chg_nr; i++)  {
			unsigned long long curaddr, lastaddr;
			unsigned long long curpbaddr, lastpbaddr;

			curaddr = change_point[i]->addr;
			lastaddr = change_point[i - 1]->addr;
			curpbaddr = change_point[i]->pbios->addr;
			lastpbaddr = change_point[i - 1]->pbios->addr;

			/*
			 * swap entries, when:
			 *
			 * curaddr > lastaddr or
			 * curaddr == lastaddr and curaddr == curpbaddr and
			 * lastaddr != lastpbaddr
			 */
			if (curaddr < lastaddr ||
			    (curaddr == lastaddr && curaddr == curpbaddr &&
			     lastaddr != lastpbaddr)) {
				change_tmp = change_point[i];
				change_point[i] = change_point[i-1];
				change_point[i-1] = change_tmp;
				still_changing = 1;
			}
		}
	}

	/* 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 ?
					 */
368
					if (++new_bios_entry >= max_nr_map)
369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
						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;
}

390
static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
{
	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;
}

410 411 412 413 414 415 416 417 418
/*
 * 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.
 */
419
static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
420 421 422 423 424
{
	/* Only one memory region (or negative)? Ignore it */
	if (nr_map < 2)
		return -1;

425
	return __append_e820_map(biosmap, nr_map);
426 427
}

Y
Yinghai Lu 已提交
428
static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
429 430
					u64 size, unsigned old_type,
					unsigned new_type)
431
{
432
	u64 end;
Y
Yinghai Lu 已提交
433
	unsigned int i;
434 435 436 437
	u64 real_updated_size = 0;

	BUG_ON(old_type == new_type);

438 439 440
	if (size > (ULLONG_MAX - start))
		size = ULLONG_MAX - start;

441
	end = start + size;
442 443 444 445 446 447 448 449
	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");

450
	for (i = 0; i < e820x->nr_map; i++) {
451
		struct e820entry *ei = &e820x->map[i];
452
		u64 final_start, final_end;
453 454
		u64 ei_end;

455 456
		if (ei->type != old_type)
			continue;
457 458 459 460

		ei_end = ei->addr + ei->size;
		/* totally covered by new range? */
		if (ei->addr >= start && ei_end <= end) {
461 462 463 464
			ei->type = new_type;
			real_updated_size += ei->size;
			continue;
		}
465 466 467 468 469 470 471 472 473 474

		/* 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;
		}

475 476
		/* partially covered */
		final_start = max(start, ei->addr);
477
		final_end = min(end, ei_end);
478 479
		if (final_start >= final_end)
			continue;
480

Y
Yinghai Lu 已提交
481 482
		__e820_add_region(e820x, final_start, final_end - final_start,
				  new_type);
483

484
		real_updated_size += final_end - final_start;
485

Y
Yinghai Lu 已提交
486 487 488 489 490
		/*
		 * left range could be head or tail, so need to update
		 * size at first.
		 */
		ei->size -= final_end - final_start;
491 492 493
		if (ei->addr < final_start)
			continue;
		ei->addr = final_end;
494 495 496 497
	}
	return real_updated_size;
}

498 499 500
u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
			     unsigned new_type)
{
Y
Yinghai Lu 已提交
501
	return __e820_update_range(&e820, start, size, old_type, new_type);
502 503 504 505 506
}

static u64 __init e820_update_range_saved(u64 start, u64 size,
					  unsigned old_type, unsigned new_type)
{
Y
Yinghai Lu 已提交
507
	return __e820_update_range(&e820_saved, start, size, old_type,
508 509 510
				     new_type);
}

Y
Yinghai Lu 已提交
511 512 513 514 515
/* make e820 not cover the range */
u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
			     int checktype)
{
	int i;
516
	u64 end;
Y
Yinghai Lu 已提交
517 518
	u64 real_removed_size = 0;

519 520 521
	if (size > (ULLONG_MAX - start))
		size = ULLONG_MAX - start;

522 523 524 525
	end = start + size;
	printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
		       (unsigned long long) start,
		       (unsigned long long) end);
526 527
	if (checktype)
		e820_print_type(old_type);
528 529
	printk(KERN_CONT "\n");

Y
Yinghai Lu 已提交
530 531 532
	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 final_start, final_end;
533
		u64 ei_end;
Y
Yinghai Lu 已提交
534 535 536

		if (checktype && ei->type != old_type)
			continue;
537 538

		ei_end = ei->addr + ei->size;
Y
Yinghai Lu 已提交
539
		/* totally covered? */
540
		if (ei->addr >= start && ei_end <= end) {
Y
Yinghai Lu 已提交
541 542 543 544
			real_removed_size += ei->size;
			memset(ei, 0, sizeof(struct e820entry));
			continue;
		}
545 546 547 548 549 550 551 552 553

		/* 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;
		}

Y
Yinghai Lu 已提交
554 555
		/* partially covered */
		final_start = max(start, ei->addr);
556
		final_end = min(end, ei_end);
Y
Yinghai Lu 已提交
557 558 559 560
		if (final_start >= final_end)
			continue;
		real_removed_size += final_end - final_start;

561 562 563 564
		/*
		 * left range could be head or tail, so need to update
		 * size at first.
		 */
Y
Yinghai Lu 已提交
565 566 567 568 569 570 571 572
		ei->size -= final_end - final_start;
		if (ei->addr < final_start)
			continue;
		ei->addr = final_end;
	}
	return real_removed_size;
}

573 574
void __init update_e820(void)
{
575
	u32 nr_map;
576 577

	nr_map = e820.nr_map;
578
	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
579 580 581 582 583
		return;
	e820.nr_map = nr_map;
	printk(KERN_INFO "modified physical RAM map:\n");
	e820_print_map("modified");
}
584 585
static void __init update_e820_saved(void)
{
586
	u32 nr_map;
587 588 589 590 591 592

	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;
}
A
Alok Kataria 已提交
593
#define MAX_GAP_END 0x100000000ull
594
/*
A
Alok Kataria 已提交
595
 * Search for a gap in the e820 memory space from start_addr to end_addr.
596
 */
597
__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
A
Alok Kataria 已提交
598
		unsigned long start_addr, unsigned long long end_addr)
599
{
A
Alok Kataria 已提交
600
	unsigned long long last;
601
	int i = e820.nr_map;
602 603
	int found = 0;

A
Alok Kataria 已提交
604 605
	last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;

606 607 608 609
	while (--i >= 0) {
		unsigned long long start = e820.map[i].addr;
		unsigned long long end = start + e820.map[i].size;

610 611 612
		if (end < start_addr)
			continue;

613 614 615 616 617 618 619
		/*
		 * 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;

620 621 622
			if (gap >= *gapsize) {
				*gapsize = gap;
				*gapstart = end;
623 624 625 626 627 628
				found = 1;
			}
		}
		if (start < last)
			last = start;
	}
629 630 631 632 633 634 635 636 637 638 639
	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)
{
640
	unsigned long gapstart, gapsize;
641 642 643 644
	int found;

	gapstart = 0x10000000;
	gapsize = 0x400000;
A
Alok Kataria 已提交
645
	found  = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);
646 647 648

#ifdef CONFIG_X86_64
	if (!found) {
Y
Yinghai Lu 已提交
649
		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
650 651 652
		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");
653 654 655 656
	}
#endif

	/*
657
	 * e820_reserve_resources_late protect stolen RAM already
658
	 */
659
	pci_mem_start = gapstart;
660 661 662 663 664 665

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

666 667 668 669 670 671
/**
 * 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.
 */
672
void __init parse_e820_ext(struct setup_data *sdata)
673 674 675 676 677 678
{
	int entries;
	struct e820entry *extmap;

	entries = sdata->len / sizeof(struct e820entry);
	extmap = (struct e820entry *)(sdata->data);
679
	__append_e820_map(extmap, entries);
680 681 682 683 684
	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
	printk(KERN_INFO "extended physical RAM map:\n");
	e820_print_map("extended");
}

685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
#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);
708
		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
709 710 711 712 713 714 715
			register_nosave_region(PFN_UP(ei->addr), pfn);

		if (pfn >= limit_pfn)
			break;
	}
}
#endif
716

717 718 719 720 721 722 723 724 725 726 727 728 729
#ifdef CONFIG_HIBERNATION
/**
 * 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)
730
			suspend_nvs_register(ei->addr, ei->size);
731 732 733 734 735 736 737
	}

	return 0;
}
core_initcall(e820_mark_nvs_memory);
#endif

Y
Yinghai Lu 已提交
738
/*
739
 * pre allocated 4k and reserved it in memblock and e820_saved
Y
Yinghai Lu 已提交
740
 */
741
u64 __init early_reserve_e820(u64 size, u64 align)
Y
Yinghai Lu 已提交
742 743 744
{
	u64 addr;

745 746 747 748 749
	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();
750
	}
Y
Yinghai Lu 已提交
751 752 753 754

	return addr;
}

755 756 757 758 759 760 761
#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 */
762
# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT
763 764 765 766 767
#endif

/*
 * Find the highest page frame number we have available
 */
768
static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
769
{
770 771
	int i;
	unsigned long last_pfn = 0;
772 773
	unsigned long max_arch_pfn = MAX_ARCH_PFN;

774 775
	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
776
		unsigned long start_pfn;
777 778
		unsigned long end_pfn;

779
		if (ei->type != type)
780 781
			continue;

782
		start_pfn = ei->addr >> PAGE_SHIFT;
783
		end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
784 785 786 787 788 789 790

		if (start_pfn >= limit_pfn)
			continue;
		if (end_pfn > limit_pfn) {
			last_pfn = limit_pfn;
			break;
		}
791 792 793
		if (end_pfn > last_pfn)
			last_pfn = end_pfn;
	}
794 795 796 797

	if (last_pfn > max_arch_pfn)
		last_pfn = max_arch_pfn;

798
	printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
799 800 801
			 last_pfn, max_arch_pfn);
	return last_pfn;
}
802 803 804 805
unsigned long __init e820_end_of_ram_pfn(void)
{
	return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
}
806

807 808 809 810
unsigned long __init e820_end_of_low_ram_pfn(void)
{
	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
}
811

812 813 814 815 816 817
static void early_panic(char *msg)
{
	early_printk(msg);
	panic(msg);
}

818 819
static int userdef __initdata;

820 821 822 823 824 825 826 827 828
/* "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")) {
829
#ifdef CONFIG_X86_32
830 831
		setup_clear_cpu_cap(X86_FEATURE_PSE);
		return 0;
832 833 834
#else
		printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
		return -EINVAL;
835
#endif
836
	}
837

838
	userdef = 1;
839
	mem_size = memparse(p, &p);
840 841 842
	/* don't remove all of memory when handling "mem={invalid}" param */
	if (mem_size == 0)
		return -EINVAL;
843
	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
844

845 846 847 848 849 850 851 852 853
	return 0;
}
early_param("mem", parse_memopt);

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

854 855 856
	if (!p)
		return -EINVAL;

857
	if (!strncmp(p, "exactmap", 8)) {
858 859 860 861 862 863
#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.
		 */
864
		saved_max_pfn = e820_end_of_ram_pfn();
865 866 867 868 869 870 871 872 873 874 875 876 877 878
#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);
879
		e820_add_region(start_at, mem_size, E820_RAM);
880 881
	} else if (*p == '#') {
		start_at = memparse(p+1, &p);
882
		e820_add_region(start_at, mem_size, E820_ACPI);
883 884
	} else if (*p == '$') {
		start_at = memparse(p+1, &p);
885
		e820_add_region(start_at, mem_size, E820_RESERVED);
Y
Yinghai Lu 已提交
886
	} else
887
		e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
Y
Yinghai Lu 已提交
888

889 890 891 892 893 894 895
	return *p == '\0' ? 0 : -EINVAL;
}
early_param("memmap", parse_memmap_opt);

void __init finish_e820_parsing(void)
{
	if (userdef) {
896
		u32 nr = e820.nr_map;
897 898 899 900 901 902 903 904 905

		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");
	}
}
906

907 908 909 910 911 912 913
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";
914
	case E820_UNUSABLE:	return "Unusable memory";
915 916 917 918
	default:	return "reserved";
	}
}

919 920 921
/*
 * Mark e820 reserved areas as busy for the resource manager.
 */
922
static struct resource __initdata *e820_res;
923 924 925
void __init e820_reserve_resources(void)
{
	int i;
926
	struct resource *res;
927
	u64 end;
928

929
	res = alloc_bootmem(sizeof(struct resource) * e820.nr_map);
930
	e820_res = res;
931
	for (i = 0; i < e820.nr_map; i++) {
932
		end = e820.map[i].addr + e820.map[i].size - 1;
933
		if (end != (resource_size_t)end) {
934 935 936
			res++;
			continue;
		}
937
		res->name = e820_type_to_string(e820.map[i].type);
938 939 940
		res->start = e820.map[i].addr;
		res->end = end;

941
		res->flags = IORESOURCE_MEM;
942 943 944 945 946 947

		/*
		 * don't register the region that could be conflicted with
		 * pci device BAR resource and insert them later in
		 * pcibios_resource_survey()
		 */
948 949
		if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
			res->flags |= IORESOURCE_BUSY;
950
			insert_resource(&iomem_resource, res);
951
		}
952 953
		res++;
	}
954 955 956 957 958 959 960

	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));
	}
961 962
}

963 964 965 966 967 968 969 970 971 972 973 974 975
/* 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;

976 977
	/* To 64MB for anything above that */
	return 64*1024*1024;
978 979
}

980 981
#define MAX_RESOURCE_SIZE ((resource_size_t)-1)

982 983 984 985 986 987 988
void __init e820_reserve_resources_late(void)
{
	int i;
	struct resource *res;

	res = e820_res;
	for (i = 0; i < e820.nr_map; i++) {
989
		if (!res->parent && res->end)
990
			insert_resource_expand_to_fit(&iomem_resource, res);
991 992
		res++;
	}
993 994 995 996 997 998

	/*
	 * Try to bump up RAM regions to reasonable boundaries to
	 * avoid stolen RAM:
	 */
	for (i = 0; i < e820.nr_map; i++) {
999 1000
		struct e820entry *entry = &e820.map[i];
		u64 start, end;
1001 1002 1003 1004

		if (entry->type != E820_RAM)
			continue;
		start = entry->addr + entry->size;
1005 1006 1007 1008
		end = round_up(start, ram_alignment(start)) - 1;
		if (end > MAX_RESOURCE_SIZE)
			end = MAX_RESOURCE_SIZE;
		if (start >= end)
1009
			continue;
1010 1011
		printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ",
			       start, end);
1012 1013
		reserve_region_with_split(&iomem_resource, start, end,
					  "RAM buffer");
1014
	}
1015 1016
}

1017
char *__init default_machine_specific_memory_setup(void)
1018 1019
{
	char *who = "BIOS-e820";
1020
	u32 new_nr;
1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
	/*
	 * 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;
1032 1033
	if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
	  < 0) {
1034
		u64 mem_size;
1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056

		/* 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)
{
1057 1058
	char *who;

1059
	who = x86_init.resources.memory_setup();
1060
	memcpy(&e820_saved, &e820, sizeof(struct e820map));
1061
	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
1062
	e820_print_map(who);
1063
}
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074

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
	 */
1075
	memblock_allow_resize();
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091

	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();
}
1092 1093 1094 1095

void __init memblock_find_dma_reserve(void)
{
#ifdef CONFIG_X86_64
1096 1097 1098 1099 1100 1101
	u64 nr_pages = 0, nr_free_pages = 0;
	unsigned long start_pfn, end_pfn;
	phys_addr_t start, end;
	int i;
	u64 u;

1102 1103 1104 1105 1106
	/*
	 * 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
	 */
1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120
	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);
1121 1122
#endif
}