e820.c 33.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
/*
 * 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/bootmem.h>
#include <linux/ioport.h>
#include <linux/string.h>
#include <linux/kexec.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/pfn.h>
21
#include <linux/suspend.h>
22
#include <linux/firmware-map.h>
23 24 25 26

#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/e820.h>
27
#include <asm/proto.h>
28
#include <asm/setup.h>
29
#include <asm/trampoline.h>
30

31 32 33 34 35 36 37 38 39 40 41 42 43 44
/*
 * 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.
 */
45
struct e820map e820;
46
struct e820map e820_saved;
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

/* 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.
 */
113
void __init e820_add_region(u64 start, u64 size, int type)
114 115 116
{
	int x = e820.nr_map;

117
	if (x == ARRAY_SIZE(e820.map)) {
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
		return;
	}

	e820.map[x].addr = start;
	e820.map[x].size = size;
	e820.map[x].type = type;
	e820.nr_map++;
}

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));
		switch (e820.map[i].type) {
		case E820_RAM:
139
		case E820_RESERVED_KERN:
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
			printk(KERN_CONT "(usable)\n");
			break;
		case E820_RESERVED:
			printk(KERN_CONT "(reserved)\n");
			break;
		case E820_ACPI:
			printk(KERN_CONT "(ACPI data)\n");
			break;
		case E820_NVS:
			printk(KERN_CONT "(ACPI NVS)\n");
			break;
		default:
			printk(KERN_CONT "type %u\n", e820.map[i].type);
			break;
		}
	}
}

/*
 * Sanitize the BIOS e820 map.
 *
 * Some e820 responses include overlapping entries. The following
162 163 164
 * replaces the original e820 map with a new one, removing overlaps,
 * and resolving conflicting memory types in favor of highest
 * numbered type.
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
 * 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_
218
 */
219

220
int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
221
				int *pnr_map)
222 223 224 225 226
{
	struct change_member {
		struct e820entry *pbios; /* pointer to original bios entry */
		unsigned long long addr; /* address for this change point */
	};
227 228 229 230
	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;
231 232 233 234 235 236 237 238 239 240 241 242 243 244
	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;
245
	BUG_ON(old_nr > max_nr_map);
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

	/* 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 ?
					 */
357
					if (++new_bios_entry >= max_nr_map)
358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
						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;
}

379
static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
{
	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;
}

399 400 401 402 403 404 405 406 407
/*
 * 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.
 */
408
static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
409 410 411 412 413
{
	/* Only one memory region (or negative)? Ignore it */
	if (nr_map < 2)
		return -1;

414
	return __append_e820_map(biosmap, nr_map);
415 416
}

417
u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
418 419 420 421 422 423 424
				unsigned new_type)
{
	int i;
	u64 real_updated_size = 0;

	BUG_ON(old_type == new_type);

425 426 427
	if (size > (ULLONG_MAX - start))
		size = ULLONG_MAX - start;

428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444
	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 final_start, final_end;
		if (ei->type != old_type)
			continue;
		/* totally covered? */
		if (ei->addr >= start &&
		    (ei->addr + ei->size) <= (start + size)) {
			ei->type = new_type;
			real_updated_size += ei->size;
			continue;
		}
		/* partially covered */
		final_start = max(start, ei->addr);
		final_end = min(start + size, ei->addr + ei->size);
		if (final_start >= final_end)
			continue;
445
		e820_add_region(final_start, final_end - final_start,
446 447
					 new_type);
		real_updated_size += final_end - final_start;
448 449 450 451 452

		ei->size -= final_end - final_start;
		if (ei->addr < final_start)
			continue;
		ei->addr = final_end;
453 454 455 456
	}
	return real_updated_size;
}

Y
Yinghai Lu 已提交
457 458 459 460 461 462 463
/* make e820 not cover the range */
u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
			     int checktype)
{
	int i;
	u64 real_removed_size = 0;

464 465 466
	if (size > (ULLONG_MAX - start))
		size = ULLONG_MAX - start;

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

		if (checktype && ei->type != old_type)
			continue;
		/* totally covered? */
		if (ei->addr >= start &&
		    (ei->addr + ei->size) <= (start + size)) {
			real_removed_size += ei->size;
			memset(ei, 0, sizeof(struct e820entry));
			continue;
		}
		/* partially covered */
		final_start = max(start, ei->addr);
		final_end = min(start + size, ei->addr + ei->size);
		if (final_start >= final_end)
			continue;
		real_removed_size += final_end - final_start;

		ei->size -= final_end - final_start;
		if (ei->addr < final_start)
			continue;
		ei->addr = final_end;
	}
	return real_removed_size;
}

495 496
void __init update_e820(void)
{
497
	int nr_map;
498 499

	nr_map = e820.nr_map;
500
	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
501 502 503 504 505
		return;
	e820.nr_map = nr_map;
	printk(KERN_INFO "modified physical RAM map:\n");
	e820_print_map("modified");
}
A
Alok Kataria 已提交
506
#define MAX_GAP_END 0x100000000ull
507
/*
A
Alok Kataria 已提交
508
 * Search for a gap in the e820 memory space from start_addr to end_addr.
509
 */
510
__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
A
Alok Kataria 已提交
511
		unsigned long start_addr, unsigned long long end_addr)
512
{
A
Alok Kataria 已提交
513
	unsigned long long last;
514
	int i = e820.nr_map;
515 516
	int found = 0;

A
Alok Kataria 已提交
517 518
	last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;

519 520 521 522
	while (--i >= 0) {
		unsigned long long start = e820.map[i].addr;
		unsigned long long end = start + e820.map[i].size;

523 524 525
		if (end < start_addr)
			continue;

526 527 528 529 530 531 532
		/*
		 * 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;

533 534 535
			if (gap >= *gapsize) {
				*gapsize = gap;
				*gapstart = end;
536 537 538 539 540 541
				found = 1;
			}
		}
		if (start < last)
			last = start;
	}
542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557
	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, round;
	int found;

	gapstart = 0x10000000;
	gapsize = 0x400000;
A
Alok Kataria 已提交
558
	found  = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);
559 560 561

#ifdef CONFIG_X86_64
	if (!found) {
Y
Yinghai Lu 已提交
562
		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584
		printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit "
		       "address range\n"
		       KERN_ERR "PCI: Unassigned devices with 32bit resource "
		       "registers may break!\n");
	}
#endif

	/*
	 * See how much we want to round up: start off with
	 * rounding to the next 1MB area.
	 */
	round = 0x100000;
	while ((gapsize >> 4) > round)
		round += round;
	/* Fun with two's complement */
	pci_mem_start = (gapstart + round) & -round;

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

585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601
/**
 * 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, unsigned long pa_data)
{
	u32 map_len;
	int entries;
	struct e820entry *extmap;

	entries = sdata->len / sizeof(struct e820entry);
	map_len = sdata->len + sizeof(struct setup_data);
	if (map_len > PAGE_SIZE)
		sdata = early_ioremap(pa_data, map_len);
	extmap = (struct e820entry *)(sdata->data);
602
	__append_e820_map(extmap, entries);
603 604 605 606 607 608 609
	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
	if (map_len > PAGE_SIZE)
		early_iounmap(sdata, map_len);
	printk(KERN_INFO "extended physical RAM map:\n");
	e820_print_map("extended");
}

610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632
#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);
633
		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
634 635 636 637 638 639 640
			register_nosave_region(PFN_UP(ei->addr), pfn);

		if (pfn >= limit_pfn)
			break;
	}
}
#endif
641 642 643 644 645 646 647 648 649

/*
 * Early reserved memory areas.
 */
#define MAX_EARLY_RES 20

struct early_res {
	u64 start, end;
	char name[16];
650
	char overlap_ok;
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
};
static struct early_res early_res[MAX_EARLY_RES] __initdata = {
	{ 0, PAGE_SIZE, "BIOS data page" },	/* BIOS data page */
#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE)
	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
#endif
#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
	/*
	 * But first pinch a few for the stack/trampoline stuff
	 * FIXME: Don't need the extra page at 4K, but need to fix
	 * trampoline before removing it. (see the GDT stuff)
	 */
	{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" },
	/*
	 * Has to be in very low memory so we can execute
	 * real-mode AP code.
	 */
	{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" },
#endif
	{}
};

673
static int __init find_overlapped_early(u64 start, u64 end)
674 675 676
{
	int i;
	struct early_res *r;
677

678 679 680
	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		r = &early_res[i];
		if (end > r->start && start < r->end)
681
			break;
682
	}
683 684 685 686

	return i;
}

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
/*
 * Drop the i-th range from the early reservation map,
 * by copying any higher ranges down one over it, and
 * clearing what had been the last slot.
 */
static void __init drop_range(int i)
{
	int j;

	for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
		;

	memmove(&early_res[i], &early_res[i + 1],
	       (j - 1 - i) * sizeof(struct early_res));

	early_res[j - 1].end = 0;
}

/*
 * Split any existing ranges that:
 *  1) are marked 'overlap_ok', and
 *  2) overlap with the stated range [start, end)
 * into whatever portion (if any) of the existing range is entirely
 * below or entirely above the stated range.  Drop the portion
 * of the existing range that overlaps with the stated range,
 * which will allow the caller of this routine to then add that
 * stated range without conflicting with any existing range.
 */
static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
{
	int i;
	struct early_res *r;
	u64 lower_start, lower_end;
	u64 upper_start, upper_end;
	char name[16];

	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		r = &early_res[i];

		/* Continue past non-overlapping ranges */
		if (end <= r->start || start >= r->end)
			continue;

		/*
		 * Leave non-ok overlaps as is; let caller
		 * panic "Overlapping early reservations"
		 * when it hits this overlap.
		 */
		if (!r->overlap_ok)
			return;

		/*
		 * We have an ok overlap.  We will drop it from the early
		 * reservation map, and add back in any non-overlapping
		 * portions (lower or upper) as separate, overlap_ok,
		 * non-overlapping ranges.
		 */

		/* 1. Note any non-overlapping (lower or upper) ranges. */
		strncpy(name, r->name, sizeof(name) - 1);

		lower_start = lower_end = 0;
		upper_start = upper_end = 0;
		if (r->start < start) {
		 	lower_start = r->start;
			lower_end = start;
		}
		if (r->end > end) {
			upper_start = end;
			upper_end = r->end;
		}

		/* 2. Drop the original ok overlapping range */
		drop_range(i);

		i--;		/* resume for-loop on copied down entry */

		/* 3. Add back in any non-overlapping ranges. */
		if (lower_end)
			reserve_early_overlap_ok(lower_start, lower_end, name);
		if (upper_end)
			reserve_early_overlap_ok(upper_start, upper_end, name);
	}
}

static void __init __reserve_early(u64 start, u64 end, char *name,
						int overlap_ok)
774 775 776 777 778
{
	int i;
	struct early_res *r;

	i = find_overlapped_early(start, end);
779 780 781
	if (i >= MAX_EARLY_RES)
		panic("Too many early reservations");
	r = &early_res[i];
782 783 784 785 786
	if (r->end)
		panic("Overlapping early reservations "
		      "%llx-%llx %s to %llx-%llx %s\n",
		      start, end - 1, name?name:"", r->start,
		      r->end - 1, r->name);
787 788
	r->start = start;
	r->end = end;
789
	r->overlap_ok = overlap_ok;
790 791 792 793
	if (name)
		strncpy(r->name, name, sizeof(r->name) - 1);
}

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
/*
 * A few early reservtations come here.
 *
 * The 'overlap_ok' in the name of this routine does -not- mean it
 * is ok for these reservations to overlap an earlier reservation.
 * Rather it means that it is ok for subsequent reservations to
 * overlap this one.
 *
 * Use this entry point to reserve early ranges when you are doing
 * so out of "Paranoia", reserving perhaps more memory than you need,
 * just in case, and don't mind a subsequent overlapping reservation
 * that is known to be needed.
 *
 * The drop_overlaps_that_are_ok() call here isn't really needed.
 * It would be needed if we had two colliding 'overlap_ok'
 * reservations, so that the second such would not panic on the
 * overlap with the first.  We don't have any such as of this
 * writing, but might as well tolerate such if it happens in
 * the future.
 */
void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
{
	drop_overlaps_that_are_ok(start, end);
	__reserve_early(start, end, name, 1);
}

/*
 * Most early reservations come here.
 *
 * We first have drop_overlaps_that_are_ok() drop any pre-existing
 * 'overlap_ok' ranges, so that we can then reserve this memory
 * range without risk of panic'ing on an overlapping overlap_ok
 * early reservation.
 */
void __init reserve_early(u64 start, u64 end, char *name)
{
	drop_overlaps_that_are_ok(start, end);
	__reserve_early(start, end, name, 0);
}

834 835 836
void __init free_early(u64 start, u64 end)
{
	struct early_res *r;
837
	int i;
838

839 840 841
	i = find_overlapped_early(start, end);
	r = &early_res[i];
	if (i >= MAX_EARLY_RES || r->end != end || r->start != start)
842
		panic("free_early on not reserved area: %llx-%llx!",
843
			 start, end - 1);
844

845
	drop_range(i);
846 847 848 849
}

void __init early_res_to_bootmem(u64 start, u64 end)
{
850
	int i, count;
851
	u64 final_start, final_end;
852 853 854 855 856 857 858

	count  = 0;
	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++)
		count++;

	printk(KERN_INFO "(%d early reservations) ==> bootmem\n", count);
	for (i = 0; i < count; i++) {
859
		struct early_res *r = &early_res[i];
860
		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
861
			r->start, r->end, r->name);
862 863
		final_start = max(start, r->start);
		final_end = min(end, r->end);
864 865
		if (final_start >= final_end) {
			printk(KERN_CONT "\n");
866
			continue;
867
		}
868
		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
869
			final_start, final_end);
870
		reserve_bootmem_generic(final_start, final_end - final_start,
871 872 873 874 875 876 877 878
				BOOTMEM_DEFAULT);
	}
}

/* Check for already reserved areas */
static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
{
	int i;
879
	u64 addr = *addrp;
880
	int changed = 0;
881
	struct early_res *r;
882
again:
883 884 885 886 887 888
	i = find_overlapped_early(addr, addr + size);
	r = &early_res[i];
	if (i < MAX_EARLY_RES && r->end) {
		*addrp = addr = round_up(r->end, align);
		changed = 1;
		goto again;
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
	}
	return changed;
}

/* Check for already reserved areas */
static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
{
	int i;
	u64 addr = *addrp, last;
	u64 size = *sizep;
	int changed = 0;
again:
	last = addr + size;
	for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		if (last > r->start && addr < r->start) {
			size = r->start - addr;
			changed = 1;
			goto again;
		}
		if (last > r->end && addr < r->end) {
			addr = round_up(r->end, align);
			size = last - addr;
			changed = 1;
			goto again;
		}
		if (last <= r->end && addr >= r->start) {
			(*sizep)++;
			return 0;
		}
	}
	if (changed) {
		*addrp = addr;
		*sizep = size;
	}
	return changed;
}

/*
 * Find a free area with specified alignment in a specific range.
 */
u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 addr, last;
		u64 ei_last;

		if (ei->type != E820_RAM)
			continue;
		addr = round_up(ei->addr, align);
		ei_last = ei->addr + ei->size;
		if (addr < start)
			addr = round_up(start, align);
		if (addr >= ei_last)
			continue;
		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
			;
		last = addr + size;
		if (last > ei_last)
			continue;
		if (last > end)
			continue;
		return addr;
	}
	return -1ULL;
}

/*
 * Find next free range after *start
 */
u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
{
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 addr, last;
		u64 ei_last;

		if (ei->type != E820_RAM)
			continue;
		addr = round_up(ei->addr, align);
		ei_last = ei->addr + ei->size;
		if (addr < start)
			addr = round_up(start, align);
		if (addr >= ei_last)
			continue;
		*sizep = ei_last - addr;
		while (bad_addr_size(&addr, sizep, align) &&
			addr + *sizep <= ei_last)
			;
		last = addr + *sizep;
		if (last > ei_last)
			continue;
		return addr;
	}
	return -1UL;

}
Y
Yinghai Lu 已提交
991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008

/*
 * pre allocated 4k and reserved it in e820
 */
u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
{
	u64 size = 0;
	u64 addr;
	u64 start;

	start = startt;
	while (size < sizet)
		start = find_e820_area_size(start, &size, align);

	if (size < sizet)
		return 0;

	addr = round_down(start + size - sizet, align);
1009
	e820_update_range(addr, sizet, E820_RAM, E820_RESERVED);
Y
Yinghai Lu 已提交
1010 1011 1012 1013 1014 1015
	printk(KERN_INFO "update e820 for early_reserve_e820\n");
	update_e820();

	return addr;
}

1016 1017 1018 1019 1020 1021 1022
#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 */
1023
# define MAX_ARCH_PFN MAXMEM>>PAGE_SHIFT
1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045
#endif

/*
 * Last pfn which the user wants to use.
 */
unsigned long __initdata end_user_pfn = MAX_ARCH_PFN;

/*
 * Find the highest page frame number we have available
 */
unsigned long __init e820_end_of_ram(void)
{
	unsigned long last_pfn;
	unsigned long max_arch_pfn = MAX_ARCH_PFN;

	last_pfn = find_max_pfn_with_active_regions();

	if (last_pfn > max_arch_pfn)
		last_pfn = max_arch_pfn;
	if (last_pfn > end_user_pfn)
		last_pfn = end_user_pfn;

1046
	printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
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
			 last_pfn, max_arch_pfn);
	return last_pfn;
}

/*
 * Finds an active region in the address range from start_pfn to last_pfn and
 * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
 */
int __init e820_find_active_region(const struct e820entry *ei,
				  unsigned long start_pfn,
				  unsigned long last_pfn,
				  unsigned long *ei_startpfn,
				  unsigned long *ei_endpfn)
{
	u64 align = PAGE_SIZE;

	*ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT;
	*ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT;

	/* Skip map entries smaller than a page */
	if (*ei_startpfn >= *ei_endpfn)
		return 0;

	/* Skip if map is outside the node */
	if (ei->type != E820_RAM || *ei_endpfn <= start_pfn ||
				    *ei_startpfn >= last_pfn)
		return 0;

	/* Check for overlaps */
	if (*ei_startpfn < start_pfn)
		*ei_startpfn = start_pfn;
	if (*ei_endpfn > last_pfn)
		*ei_endpfn = last_pfn;

	/* Obey end_user_pfn to save on memmap */
	if (*ei_startpfn >= end_user_pfn)
		return 0;
	if (*ei_endpfn > end_user_pfn)
		*ei_endpfn = end_user_pfn;

	return 1;
}

/* Walk the e820 map and register active regions within a node */
void __init e820_register_active_regions(int nid, unsigned long start_pfn,
					 unsigned long last_pfn)
{
	unsigned long ei_startpfn;
	unsigned long ei_endpfn;
	int i;

	for (i = 0; i < e820.nr_map; i++)
		if (e820_find_active_region(&e820.map[i],
					    start_pfn, last_pfn,
					    &ei_startpfn, &ei_endpfn))
			add_active_range(nid, ei_startpfn, ei_endpfn);
}

/*
 * Find the hole size (in bytes) in the memory range.
 * @start: starting address of the memory range to scan
 * @end: ending address of the memory range to scan
 */
u64 __init e820_hole_size(u64 start, u64 end)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long last_pfn = end >> PAGE_SHIFT;
	unsigned long ei_startpfn, ei_endpfn, ram = 0;
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		if (e820_find_active_region(&e820.map[i],
					    start_pfn, last_pfn,
					    &ei_startpfn, &ei_endpfn))
			ram += ei_endpfn - ei_startpfn;
	}
	return end - start - ((u64)ram << PAGE_SHIFT);
}
1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148

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

/* "mem=nopentium" disables the 4MB page tables. */
static int __init parse_memopt(char *p)
{
	u64 mem_size;

	if (!p)
		return -EINVAL;

#ifdef CONFIG_X86_32
	if (!strcmp(p, "nopentium")) {
		setup_clear_cpu_cap(X86_FEATURE_PSE);
		return 0;
	}
#endif

	mem_size = memparse(p, &p);
	end_user_pfn = mem_size>>PAGE_SHIFT;
1149 1150 1151
	e820_update_range(mem_size, ULLONG_MAX - mem_size,
		E820_RAM, E820_RESERVED);

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

static int userdef __initdata;

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

	if (!strcmp(p, "exactmap")) {
#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.
		 */
		e820_register_active_regions(0, 0, -1UL);
		saved_max_pfn = e820_end_of_ram();
		remove_all_active_ranges();
#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);
1187
		e820_add_region(start_at, mem_size, E820_RAM);
1188 1189
	} else if (*p == '#') {
		start_at = memparse(p+1, &p);
1190
		e820_add_region(start_at, mem_size, E820_ACPI);
1191 1192
	} else if (*p == '$') {
		start_at = memparse(p+1, &p);
1193
		e820_add_region(start_at, mem_size, E820_RESERVED);
1194 1195
	} else {
		end_user_pfn = (mem_size >> PAGE_SHIFT);
1196 1197
		e820_update_range(mem_size, ULLONG_MAX - mem_size,
			E820_RAM, E820_RESERVED);
1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215
	}
	return *p == '\0' ? 0 : -EINVAL;
}
early_param("memmap", parse_memmap_opt);

void __init finish_e820_parsing(void)
{
	if (userdef) {
		int 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");
	}
}
1216

1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227
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";
	default:	return "reserved";
	}
}

1228 1229 1230 1231 1232 1233 1234
/*
 * Mark e820 reserved areas as busy for the resource manager.
 */
void __init e820_reserve_resources(void)
{
	int i;
	struct resource *res;
1235
	u64 end;
1236 1237 1238

	res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map);
	for (i = 0; i < e820.nr_map; i++) {
1239
		end = e820.map[i].addr + e820.map[i].size - 1;
1240
#ifndef CONFIG_RESOURCES_64BIT
1241
		if (end > 0x100000000ULL) {
1242 1243 1244 1245
			res++;
			continue;
		}
#endif
1246
		res->name = e820_type_to_string(e820.map[i].type);
1247 1248 1249
		res->start = e820.map[i].addr;
		res->end = end;

1250 1251 1252 1253
		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
		insert_resource(&iomem_resource, res);
		res++;
	}
1254 1255 1256 1257 1258 1259 1260

	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));
	}
1261 1262
}

1263
char *__init default_machine_specific_memory_setup(void)
1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
{
	char *who = "BIOS-e820";
	int 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;
1278 1279
	if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
	  < 0) {
1280
		u64 mem_size;
1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300

		/* 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;
}

1301 1302 1303 1304 1305
char *__init __attribute__((weak)) machine_specific_memory_setup(void)
{
	return default_machine_specific_memory_setup();
}

1306 1307 1308 1309 1310 1311 1312 1313
/* Overridden in paravirt.c if CONFIG_PARAVIRT */
char * __init __attribute__((weak)) memory_setup(void)
{
	return machine_specific_memory_setup();
}

void __init setup_memory_map(void)
{
1314 1315 1316 1317
	char *who;

	who = memory_setup();
	memcpy(&e820_saved, &e820, sizeof(struct e820map));
1318
	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
1319
	e820_print_map(who);
1320 1321 1322 1323 1324 1325
}

#ifdef CONFIG_X86_64
int __init arch_get_ram_range(int slot, u64 *addr, u64 *size)
{
	int i;
1326

1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
	if (slot < 0 || slot >= e820.nr_map)
		return -1;
	for (i = slot; i < e820.nr_map; i++) {
		if (e820.map[i].type != E820_RAM)
			continue;
		break;
	}
	if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT))
		return -1;
	*addr = e820.map[i].addr;
	*size = min_t(u64, e820.map[i].size + e820.map[i].addr,
		max_pfn << PAGE_SHIFT) - *addr;
	return i + 1;
}
#endif