linux/arch/i386/kernel/e820.c

#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>
#include <linux/pfn.h>

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

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

struct e820map e820;
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;
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
} };

#define romsignature(x) (*(unsigned short *)(x) == 0xaa55)

static int __init romchecksum(unsigned char *rom, unsigned long length)
{
	unsigned char *p, sum = 0;

	for (p = rom; p < rom + length; p++)
		sum += *p;
	return sum == 0;
}

static void __init probe_roms(void)
{
	unsigned long start, length, upper;
	unsigned char *rom;
	int	      i;

	/* 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;

		/* 0 < length <= 0x7f * 512, historically */
		length = rom[2] * 512;

		/* 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;

		/* 0 < length <= 0x7f * 512, historically */
		length = rom[2] * 512;

		/* 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);

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_
	*/
	printk("sanitize start\n");
	/* if there's only one memory region, don't bother */
	if (*pnr_map < 2) {
		printk("sanitize bail 0\n");
		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) {
			printk("sanitize bail 1\n");
			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;

	printk("sanitize end\n");
	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;
		printk("copy_e820_map() start: %016Lx size: %016Lx end: %016Lx type: %ld\n", start, size, end, 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) {
			printk("copy_e820_map() type is E820_RAM\n");
			if (start < 0x100000ULL && end > 0xA0000ULL) {
				printk("copy_e820_map() lies in range...\n");
				if (start < 0xA0000ULL) {
					printk("copy_e820_map() start < 0xA0000ULL\n");
					add_memory_region(start, 0xA0000ULL-start, type);
				}
				if (end <= 0x100000ULL) {
					printk("copy_e820_map() end <= 0x100000ULL\n");
					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);
	}
}