arch/x86/kernel/e820.c

/*
 * 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>

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

struct e820map e820;

/* 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.
 */
void __init add_memory_region(u64 start, u64 size, int type)
{
	int x = e820.nr_map;

	if (x == ARRAY_SIZE(e820.map)) {
		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:
			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
 * replaces the original e820 map with a new one, removing overlaps,
 * and resolving conflicting memory types in favor of highest
 * numbered type.
 *
 * 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_
 */

int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
				int *pnr_map)
{
	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*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;
	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;
	BUG_ON(old_nr > max_nr_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;

	/* 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 ?
					 */
					if (++new_bios_entry >= max_nr_map)
						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;
}

/*
 * 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.
 */
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 {
		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;

		add_memory_region(start, size, type);
	} while (biosmap++, --nr_map);
	return 0;
}

u64 __init update_memory_range(u64 start, u64 size, unsigned old_type,
				unsigned new_type)
{
	int i;
	u64 real_updated_size = 0;

	BUG_ON(old_type == new_type);

	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;
		add_memory_region(final_start, final_end - final_start,
					 new_type);
		real_updated_size += final_end - final_start;
	}
	return real_updated_size;
}

void __init update_e820(void)
{
	int nr_map;

	nr_map = e820.nr_map;
	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
		return;
	e820.nr_map = nr_map;
	printk(KERN_INFO "modified physical RAM map:\n");
	e820_print_map("modified");
}

/*
 * 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;
	unsigned long long last;
	int i;
	int found = 0;

	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;
				found = 1;
			}
		}
		if (start < last)
			last = start;
	}

#ifdef CONFIG_X86_64
	if (!found) {
		gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024;
		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);
}