e820_32.c

linux 内核源代码

				 (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) {
				if (start < 0xA0000ULL)
					add_memory_region(start, 0xA0000ULL-start, type);
				if (end <= 0x100000ULL)
					continue;
				start = 0x100000ULL;
				size = end - start;
			}
		}
		add_memory_region(start, size, type);
	} while (biosmap++,--nr_map);
	return 0;
}

/*
 * 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);
	}
}

/*
 * 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));
	}
}

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

	/*
	 * Search for the biggest 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);
}

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;
		default:	printk("type %u\n", e820.map[i].type);
				break;
		}
	}
}

static __init __always_inline void efi_limit_regions(unsigned long long size)
{
	unsigned long long current_addr = 0;
	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;
	int i;

	print_memory_map("limit_regions start");
	if (efi_enabled) {
		efi_limit_regions(size);
		return;
	}
	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");
}

/*
 * 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);

 /*
  * 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);