e820_64.c

linux 内核源代码

/* 
 * 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 <[e-mail]>, December 2002.
 *  Venkatesh Pallipadi <[e-mail]>
 *
 */
#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/suspend.h>
#include <linux/pfn.h>

#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/setup.h>
#include <asm/sections.h>

struct e820map e820;

/* 
 * PFN of last memory page.
 */
unsigned long end_pfn; 
EXPORT_SYMBOL(end_pfn);

/* 
 * end_pfn only includes RAM, while end_pfn_map includes all e820 entries.
 * The direct mapping extends to end_pfn_map, so that we can directly access
 * apertures, ACPI and other tables without having to play with fixmaps.
 */ 
unsigned long end_pfn_map; 

/* 
 * Last pfn which the user wants to use.
 */
static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT;

extern struct resource code_resource, data_resource, bss_resource;

/* Check for some hardcoded bad areas that early boot is not allowed to touch */ 
static inline int bad_addr(unsigned long *addrp, unsigned long size)
{ 
	unsigned long addr = *addrp, last = addr + size; 

	/* various gunk below that needed for SMP startup */
	if (addr < 0x8000) { 
		*addrp = PAGE_ALIGN(0x8000);
		return 1; 
	}

	/* direct mapping tables of the kernel */
	if (last >= table_start<<PAGE_SHIFT && addr < table_end<<PAGE_SHIFT) { 
		*addrp = PAGE_ALIGN(table_end << PAGE_SHIFT);
		return 1;
	} 

	/* initrd */ 
#ifdef CONFIG_BLK_DEV_INITRD
	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
		unsigned long ramdisk_end   = ramdisk_image+ramdisk_size;

		if (last >= ramdisk_image && addr < ramdisk_end) {
			*addrp = PAGE_ALIGN(ramdisk_end);
			return 1;
		}
	} 
#endif
	/* kernel code */
	if (last >= __pa_symbol(&_text) && addr < __pa_symbol(&_end)) {
		*addrp = PAGE_ALIGN(__pa_symbol(&_end));
		return 1;
	}

	if (last >= ebda_addr && addr < ebda_addr + ebda_size) {
		*addrp = PAGE_ALIGN(ebda_addr + ebda_size);
		return 1;
	}

#ifdef CONFIG_NUMA
	/* NUMA memory to node map */
	if (last >= nodemap_addr && addr < nodemap_addr + nodemap_size) {
		*addrp = nodemap_addr + nodemap_size;
		return 1;
	}
#endif
	/* XXX ramdisk image here? */ 
	return 0;
} 

/*
 * This function checks if any part of the range <start,end> is mapped
 * with type.
 */
int
e820_any_mapped(unsigned long start, unsigned long 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(unsigned long start, unsigned long 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; /* we're done */
	}
	return 0;
}

/* 
 * Find a free area in a specific range. 
 */ 
unsigned long __init find_e820_area(unsigned long start, unsigned long end, unsigned size) 
{ 
	int i; 
	for (i = 0; i < e820.nr_map; i++) { 
		struct e820entry *ei = &e820.map[i]; 
		unsigned long addr = ei->addr, last; 
		if (ei->type != E820_RAM) 
			continue; 
		if (addr < start) 
			addr = start;
		if (addr > ei->addr + ei->size) 
			continue; 
		while (bad_addr(&addr, size) && addr+size <= ei->addr+ei->size)
			;
		last = PAGE_ALIGN(addr) + size;
		if (last > ei->addr + ei->size)
			continue;
		if (last > end) 
			continue;
		return addr; 
	} 
	return -1UL;		
} 

/*
 * Find the highest page frame number we have available
 */
unsigned long __init e820_end_of_ram(void)
{
	unsigned long end_pfn = 0;
	end_pfn = find_max_pfn_with_active_regions();
	
	if (end_pfn > end_pfn_map) 
		end_pfn_map = end_pfn;
	if (end_pfn_map > MAXMEM>>PAGE_SHIFT)
		end_pfn_map = MAXMEM>>PAGE_SHIFT;
	if (end_pfn > end_user_pfn)
		end_pfn = end_user_pfn;
	if (end_pfn > end_pfn_map) 
		end_pfn = end_pfn_map; 

	printk("end_pfn_map = %lu\n", end_pfn_map);
	return end_pfn;	
}

/*
 * Mark e820 reserved areas as busy for the resource manager.
 */
void __init e820_reserve_resources(void)
{
	int i;
	for (i = 0; i < e820.nr_map; i++) {
		struct resource *res;
		res = alloc_bootmem_low(sizeof(struct resource));
		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;
		request_resource(&iomem_resource, res);
		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);
			request_resource(res, &bss_resource);
#ifdef CONFIG_KEXEC
			if (crashk_res.start != crashk_res.end)
				request_resource(res, &crashk_res);
#endif
		}
	}
}

/*
 * Find the ranges of physical addresses that do not correspond to
 * e820 RAM areas and mark the corresponding pages as nosave for software
 * suspend and suspend to RAM.
 *
 * 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 paddr;

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

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

		paddr = round_down(ei->addr + ei->size, PAGE_SIZE);
		if (ei->type != E820_RAM)
			register_nosave_region(PFN_UP(ei->addr),
						PFN_DOWN(paddr));

		if (paddr >= (end_pfn << PAGE_SHIFT))
			break;
	}
}

/*
 * Finds an active region in the address range from start_pfn to end_pfn and
 * returns its range in ei_startpfn and ei_endpfn for the e820 entry.
 */
static int __init e820_find_active_region(const struct e820entry *ei,
					  unsigned long start_pfn,
					  unsigned long end_pfn,
					  unsigned long *ei_startpfn,
					  unsigned long *ei_endpfn)
{
	*ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
	*ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE) >> PAGE_SHIFT;

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

	/* Check if end_pfn_map should be updated */
	if (ei->type != E820_RAM && *ei_endpfn > end_pfn_map)
		end_pfn_map = *ei_endpfn;

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

	/* Check for overlaps */
	if (*ei_startpfn < start_pfn)
		*ei_startpfn = start_pfn;
	if (*ei_endpfn > end_pfn)
		*ei_endpfn = end_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 end_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, end_pfn,
					    &ei_startpfn, &ei_endpfn))
			add_active_range(nid, ei_startpfn, ei_endpfn);
}

/* 
 * Add a memory region to the kernel e820 map.
 */ 
void __init add_memory_region(unsigned long start, unsigned long size, int type)
{
	int 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++;
}

/*
 * 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
 */
unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long end_pfn = end >> PAGE_SHIFT;
	unsigned long ei_startpfn;
	unsigned long ei_endpfn;
	unsigned long ram = 0;
	int i;

	for (i = 0; i < e820.nr_map; i++) {
		if (e820_find_active_region(&e820.map[i],
					    start_pfn, end_pfn,
					    &ei_startpfn, &ei_endpfn))
			ram += ei_endpfn - ei_startpfn;
	}
	return end - start - (ram << PAGE_SHIFT);
}

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:	printk("(usable)\n");
				break;