e820_32.c 23.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10
#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/efi.h>
11
#include <linux/pfn.h>
12
#include <linux/uaccess.h>
13
#include <linux/suspend.h>
14 15 16 17

#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/e820.h>
18
#include <asm/setup.h>
19 20 21 22 23 24 25

#ifdef CONFIG_EFI
int efi_enabled = 0;
EXPORT_SYMBOL(efi_enabled);
#endif

struct e820map e820;
26 27 28 29 30 31 32 33
struct change_member {
	struct e820entry *pbios; /* pointer to original bios entry */
	unsigned long long addr; /* address for this change point */
};
static struct change_member change_point_list[2*E820MAX] __initdata;
static struct change_member *change_point[2*E820MAX] __initdata;
static struct e820entry *overlap_list[E820MAX] __initdata;
static struct e820entry new_bios[E820MAX] __initdata;
34 35 36 37 38
/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0x10000000;
#ifdef CONFIG_PCI
EXPORT_SYMBOL(pci_mem_start);
#endif
39
extern int user_defined_memmap;
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
struct resource data_resource = {
	.name	= "Kernel data",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

struct resource code_resource = {
	.name	= "Kernel code",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource system_rom_resource = {
	.name	= "System ROM",
	.start	= 0xf0000,
	.end	= 0xfffff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
};

static struct resource extension_rom_resource = {
	.name	= "Extension ROM",
	.start	= 0xe0000,
	.end	= 0xeffff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
};

static struct resource adapter_rom_resources[] = { {
	.name 	= "Adapter ROM",
	.start	= 0xc8000,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
}, {
	.name 	= "Adapter ROM",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
}, {
	.name 	= "Adapter ROM",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
}, {
	.name 	= "Adapter ROM",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
}, {
	.name 	= "Adapter ROM",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
}, {
	.name 	= "Adapter ROM",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
} };

static struct resource video_rom_resource = {
	.name 	= "Video ROM",
	.start	= 0xc0000,
	.end	= 0xc7fff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM
};

static struct resource video_ram_resource = {
	.name	= "Video RAM area",
	.start	= 0xa0000,
	.end	= 0xbffff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource standard_io_resources[] = { {
	.name	= "dma1",
	.start	= 0x0000,
	.end	= 0x001f,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "pic1",
	.start	= 0x0020,
	.end	= 0x0021,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name   = "timer0",
	.start	= 0x0040,
	.end    = 0x0043,
	.flags  = IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name   = "timer1",
	.start  = 0x0050,
	.end    = 0x0053,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "keyboard",
	.start	= 0x0060,
	.end	= 0x006f,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "dma page reg",
	.start	= 0x0080,
	.end	= 0x008f,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "pic2",
	.start	= 0x00a0,
	.end	= 0x00a1,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "dma2",
	.start	= 0x00c0,
	.end	= 0x00df,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
}, {
	.name	= "fpu",
	.start	= 0x00f0,
	.end	= 0x00ff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
} };

161 162 163
#define ROMSIGNATURE 0xaa55

static int __init romsignature(const unsigned char *rom)
164
{
R
Rene Herman 已提交
165
	const unsigned short * const ptr = (const unsigned short *)rom;
166
	unsigned short sig;
167

R
Rene Herman 已提交
168
	return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
169
}
170

R
Rene Herman 已提交
171
static int __init romchecksum(const unsigned char *rom, unsigned long length)
172
{
R
Rene Herman 已提交
173
	unsigned char sum, c;
174

R
Rene Herman 已提交
175 176 177
	for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--)
		sum += c;
	return !length && !sum;
178 179 180 181
}

static void __init probe_roms(void)
{
R
Rene Herman 已提交
182
	const unsigned char *rom;
183
	unsigned long start, length, upper;
R
Rene Herman 已提交
184 185
	unsigned char c;
	int i;
186 187 188 189 190 191 192 193 194 195

	/* video rom */
	upper = adapter_rom_resources[0].start;
	for (start = video_rom_resource.start; start < upper; start += 2048) {
		rom = isa_bus_to_virt(start);
		if (!romsignature(rom))
			continue;

		video_rom_resource.start = start;

R
Rene Herman 已提交
196 197 198
		if (probe_kernel_address(rom + 2, c) != 0)
			continue;

199
		/* 0 < length <= 0x7f * 512, historically */
R
Rene Herman 已提交
200
		length = c * 512;
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

		/* if checksum okay, trust length byte */
		if (length && romchecksum(rom, length))
			video_rom_resource.end = start + length - 1;

		request_resource(&iomem_resource, &video_rom_resource);
		break;
	}

	start = (video_rom_resource.end + 1 + 2047) & ~2047UL;
	if (start < upper)
		start = upper;

	/* system rom */
	request_resource(&iomem_resource, &system_rom_resource);
	upper = system_rom_resource.start;

	/* check for extension rom (ignore length byte!) */
	rom = isa_bus_to_virt(extension_rom_resource.start);
	if (romsignature(rom)) {
		length = extension_rom_resource.end - extension_rom_resource.start + 1;
		if (romchecksum(rom, length)) {
			request_resource(&iomem_resource, &extension_rom_resource);
			upper = extension_rom_resource.start;
		}
	}

	/* check for adapter roms on 2k boundaries */
	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources) && start < upper; start += 2048) {
		rom = isa_bus_to_virt(start);
		if (!romsignature(rom))
			continue;

R
Rene Herman 已提交
234 235 236
		if (probe_kernel_address(rom + 2, c) != 0)
			continue;

237
		/* 0 < length <= 0x7f * 512, historically */
R
Rene Herman 已提交
238
		length = c * 512;
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

		/* but accept any length that fits if checksum okay */
		if (!length || start + length > upper || !romchecksum(rom, length))
			continue;

		adapter_rom_resources[i].start = start;
		adapter_rom_resources[i].end = start + length - 1;
		request_resource(&iomem_resource, &adapter_rom_resources[i]);

		start = adapter_rom_resources[i++].end & ~2047UL;
	}
}

/*
 * Request address space for all standard RAM and ROM resources
 * and also for regions reported as reserved by the e820.
 */
static void __init
legacy_init_iomem_resources(struct resource *code_resource, struct resource *data_resource)
{
	int i;

	probe_roms();
	for (i = 0; i < e820.nr_map; i++) {
		struct resource *res;
#ifndef CONFIG_RESOURCES_64BIT
		if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)
			continue;
#endif
		res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
		switch (e820.map[i].type) {
		case E820_RAM:	res->name = "System RAM"; break;
		case E820_ACPI:	res->name = "ACPI Tables"; break;
		case E820_NVS:	res->name = "ACPI Non-volatile Storage"; break;
		default:	res->name = "reserved";
		}
		res->start = e820.map[i].addr;
		res->end = res->start + e820.map[i].size - 1;
		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
		if (request_resource(&iomem_resource, res)) {
			kfree(res);
			continue;
		}
		if (e820.map[i].type == E820_RAM) {
			/*
			 *  We don't know which RAM region contains kernel data,
			 *  so we try it repeatedly and let the resource manager
			 *  test it.
			 */
			request_resource(res, code_resource);
			request_resource(res, data_resource);
#ifdef CONFIG_KEXEC
			request_resource(res, &crashk_res);
#endif
		}
	}
}

/*
 * Request address space for all standard resources
 *
 * This is called just before pcibios_init(), which is also a
 * subsys_initcall, but is linked in later (in arch/i386/pci/common.c).
 */
static int __init request_standard_resources(void)
{
	int i;

	printk("Setting up standard PCI resources\n");
	if (efi_enabled)
		efi_initialize_iomem_resources(&code_resource, &data_resource);
	else
		legacy_init_iomem_resources(&code_resource, &data_resource);

	/* EFI systems may still have VGA */
	request_resource(&iomem_resource, &video_ram_resource);

	/* request I/O space for devices used on all i[345]86 PCs */
	for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++)
		request_resource(&ioport_resource, &standard_io_resources[i]);
	return 0;
}

subsys_initcall(request_standard_resources);
323

324
#if defined(CONFIG_PM) && defined(CONFIG_HIBERNATION)
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
/**
 * e820_mark_nosave_regions - Find the ranges of physical addresses that do not
 * correspond to e820 RAM areas and mark the corresponding pages as nosave for
 * hibernation.
 *
 * 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(void)
{
	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)
			register_nosave_region(PFN_UP(ei->addr), pfn);

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

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
void __init add_memory_region(unsigned long long start,
			      unsigned long long size, int type)
{
	int x;

	if (!efi_enabled) {
       		x = e820.nr_map;

		if (x == E820MAX) {
		    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++;
	}
} /* add_memory_region */

/*
 * Sanitize the BIOS e820 map.
 *
 * Some e820 responses include overlapping entries.  The following
 * replaces the original e820 map with a new one, removing overlaps.
 *
 */
int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map)
{
	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;

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

	old_nr = *pnr_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;    	/* true number of change-points */

	/* 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++)  {
			/* if <current_addr> > <last_addr>, swap */
			/* or, if current=<start_addr> & last=<end_addr>, swap */
			if ((change_point[i]->addr < change_point[i-1]->addr) ||
				((change_point[i]->addr == change_point[i-1]->addr) &&
				 (change_point[i]->addr == change_point[i]->pbios->addr) &&
				 (change_point[i-1]->addr != change_point[i-1]->pbios->addr))
			   )
			{
				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)
					if (++new_bios_entry >= E820MAX)
						break; 	/* no more space left for new bios entries */
			}
			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;
		}
	}
	new_nr = new_bios_entry;   /* retain count for new bios entries */

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

	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.
 *
 * We check to see that the memory map contains at least 2 elements
 * before we'll use it, because the detection code in setup.S may
 * not be perfect and most every PC known to man has two memory
 * regions: one from 0 to 640k, and one from 1mb up.  (The IBM
 * thinkpad 560x, for example, does not cooperate with the memory
 * detection code.)
 */
int __init copy_e820_map(struct e820entry * biosmap, int nr_map)
{
	/* Only one memory region (or negative)? Ignore it */
	if (nr_map < 2)
		return -1;

	do {
		unsigned long long start = biosmap->addr;
		unsigned long long size = biosmap->size;
		unsigned long long end = start + size;
		unsigned long type = biosmap->type;

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

		/*
		 * Some BIOSes claim RAM in the 640k - 1M region.
		 * Not right. Fix it up.
		 */
		if (type == E820_RAM) {
			if (start < 0x100000ULL && end > 0xA0000ULL) {
574
				if (start < 0xA0000ULL)
575
					add_memory_region(start, 0xA0000ULL-start, type);
576
				if (end <= 0x100000ULL)
577 578 579 580 581 582 583 584 585 586
					continue;
				start = 0x100000ULL;
				size = end - start;
			}
		}
		add_memory_region(start, size, type);
	} while (biosmap++,--nr_map);
	return 0;
}

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
/*
 * Callback for efi_memory_walk.
 */
static int __init
efi_find_max_pfn(unsigned long start, unsigned long end, void *arg)
{
	unsigned long *max_pfn = arg, pfn;

	if (start < end) {
		pfn = PFN_UP(end -1);
		if (pfn > *max_pfn)
			*max_pfn = pfn;
	}
	return 0;
}

static int __init
efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
{
	memory_present(0, PFN_UP(start), PFN_DOWN(end));
	return 0;
}

/*
 * Find the highest page frame number we have available
 */
void __init find_max_pfn(void)
{
	int i;

	max_pfn = 0;
	if (efi_enabled) {
		efi_memmap_walk(efi_find_max_pfn, &max_pfn);
		efi_memmap_walk(efi_memory_present_wrapper, NULL);
		return;
	}

	for (i = 0; i < e820.nr_map; i++) {
		unsigned long start, end;
		/* RAM? */
		if (e820.map[i].type != E820_RAM)
			continue;
		start = PFN_UP(e820.map[i].addr);
		end = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
		if (start >= end)
			continue;
		if (end > max_pfn)
			max_pfn = end;
		memory_present(0, start, end);
	}
}
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

/*
 * Free all available memory for boot time allocation.  Used
 * as a callback function by efi_memory_walk()
 */

static int __init
free_available_memory(unsigned long start, unsigned long end, void *arg)
{
	/* check max_low_pfn */
	if (start >= (max_low_pfn << PAGE_SHIFT))
		return 0;
	if (end >= (max_low_pfn << PAGE_SHIFT))
		end = max_low_pfn << PAGE_SHIFT;
	if (start < end)
		free_bootmem(start, end - start);

	return 0;
}
/*
 * Register fully available low RAM pages with the bootmem allocator.
 */
void __init register_bootmem_low_pages(unsigned long max_low_pfn)
{
	int i;

	if (efi_enabled) {
		efi_memmap_walk(free_available_memory, NULL);
		return;
	}
	for (i = 0; i < e820.nr_map; i++) {
		unsigned long curr_pfn, last_pfn, size;
		/*
		 * Reserve usable low memory
		 */
		if (e820.map[i].type != E820_RAM)
			continue;
		/*
		 * We are rounding up the start address of usable memory:
		 */
		curr_pfn = PFN_UP(e820.map[i].addr);
		if (curr_pfn >= max_low_pfn)
			continue;
		/*
		 * ... and at the end of the usable range downwards:
		 */
		last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size);

		if (last_pfn > max_low_pfn)
			last_pfn = max_low_pfn;

		/*
		 * .. finally, did all the rounding and playing
		 * around just make the area go away?
		 */
		if (last_pfn <= curr_pfn)
			continue;

		size = last_pfn - curr_pfn;
		free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size));
	}
}

701
void __init e820_register_memory(void)
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
{
	unsigned long gapstart, gapsize, round;
	unsigned long long last;
	int i;

	/*
	 * Search for the bigest gap in the low 32 bits of the e820
	 * memory space.
	 */
	last = 0x100000000ull;
	gapstart = 0x10000000;
	gapsize = 0x400000;
	i = e820.nr_map;
	while (--i >= 0) {
		unsigned long long start = e820.map[i].addr;
		unsigned long long end = start + e820.map[i].size;

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

			if (gap > gapsize) {
				gapsize = gap;
				gapstart = end;
			}
		}
		if (start < last)
			last = start;
	}

	/*
	 * 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("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n",
		pci_mem_start, gapstart, gapsize);
}
748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768

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

	for (i = 0; i < e820.nr_map; i++) {
		printk(" %s: %016Lx - %016Lx ", who,
			e820.map[i].addr,
			e820.map[i].addr + e820.map[i].size);
		switch (e820.map[i].type) {
		case E820_RAM:	printk("(usable)\n");
				break;
		case E820_RESERVED:
				printk("(reserved)\n");
				break;
		case E820_ACPI:
				printk("(ACPI data)\n");
				break;
		case E820_NVS:
				printk("(ACPI NVS)\n");
				break;
769
		default:	printk("type %u\n", e820.map[i].type);
770 771 772 773 774
				break;
		}
	}
}

775
static __init __always_inline void efi_limit_regions(unsigned long long size)
776 777
{
	unsigned long long current_addr = 0;
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
	efi_memory_desc_t *md, *next_md;
	void *p, *p1;
	int i, j;

	j = 0;
	p1 = memmap.map;
	for (p = p1, i = 0; p < memmap.map_end; p += memmap.desc_size, i++) {
		md = p;
		next_md = p1;
		current_addr = md->phys_addr +
			PFN_PHYS(md->num_pages);
		if (is_available_memory(md)) {
			if (md->phys_addr >= size) continue;
			memcpy(next_md, md, memmap.desc_size);
			if (current_addr >= size) {
				next_md->num_pages -=
					PFN_UP(current_addr-size);
			}
			p1 += memmap.desc_size;
			next_md = p1;
			j++;
		} else if ((md->attribute & EFI_MEMORY_RUNTIME) ==
			   EFI_MEMORY_RUNTIME) {
			/* In order to make runtime services
			 * available we have to include runtime
			 * memory regions in memory map */
			memcpy(next_md, md, memmap.desc_size);
			p1 += memmap.desc_size;
			next_md = p1;
			j++;
		}
	}
	memmap.nr_map = j;
	memmap.map_end = memmap.map +
		(memmap.nr_map * memmap.desc_size);
}

void __init limit_regions(unsigned long long size)
{
	unsigned long long current_addr;
818 819 820 821
	int i;

	print_memory_map("limit_regions start");
	if (efi_enabled) {
822 823
		efi_limit_regions(size);
		return;
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
	}
	for (i = 0; i < e820.nr_map; i++) {
		current_addr = e820.map[i].addr + e820.map[i].size;
		if (current_addr < size)
			continue;

		if (e820.map[i].type != E820_RAM)
			continue;

		if (e820.map[i].addr >= size) {
			/*
			 * This region starts past the end of the
			 * requested size, skip it completely.
			 */
			e820.nr_map = i;
		} else {
			e820.nr_map = i + 1;
			e820.map[i].size -= current_addr - size;
		}
		print_memory_map("limit_regions endfor");
		return;
	}
	print_memory_map("limit_regions endfunc");
}

849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868
/*
 * 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++) {
		const 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);

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
 /*
  * 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(unsigned long s, unsigned long e, unsigned type)
{
	u64 start = s;
	u64 end = e;
	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; /* we're done */
	}
	return 0;
}

static int __init parse_memmap(char *arg)
{
	if (!arg)
		return -EINVAL;

	if (strcmp(arg, "exactmap") == 0) {
#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.
		 */
		find_max_pfn();
		saved_max_pfn = max_pfn;
#endif
		e820.nr_map = 0;
		user_defined_memmap = 1;
	} else {
		/* If the user specifies memory size, we
		 * limit the BIOS-provided memory map to
		 * that size. exactmap can be used to specify
		 * the exact map. mem=number can be used to
		 * trim the existing memory map.
		 */
		unsigned long long start_at, mem_size;

		mem_size = memparse(arg, &arg);
		if (*arg == '@') {
			start_at = memparse(arg+1, &arg);
			add_memory_region(start_at, mem_size, E820_RAM);
		} else if (*arg == '#') {
			start_at = memparse(arg+1, &arg);
			add_memory_region(start_at, mem_size, E820_ACPI);
		} else if (*arg == '$') {
			start_at = memparse(arg+1, &arg);
			add_memory_region(start_at, mem_size, E820_RESERVED);
		} else {
			limit_regions(mem_size);
			user_defined_memmap = 1;
		}
	}
	return 0;
}
early_param("memmap", parse_memmap);