setup.c

linux-2.6.15.6

		}
	}
	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.)
 */
static 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;
}

#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
struct edd edd;
#ifdef CONFIG_EDD_MODULE
EXPORT_SYMBOL(edd);
#endif
/**
 * copy_edd() - Copy the BIOS EDD information
 *              from boot_params into a safe place.
 *
 */
static inline void copy_edd(void)
{
     memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature));
     memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info));
     edd.mbr_signature_nr = EDD_MBR_SIG_NR;
     edd.edd_info_nr = EDD_NR;
}
#else
static inline void copy_edd(void)
{
}
#endif

/*
 * Do NOT EVER look at the BIOS memory size location.
 * It does not work on many machines.
 */
#define LOWMEMSIZE()	(0x9f000)

static void __init parse_cmdline_early (char ** cmdline_p)
{
	char c = ' ', *to = command_line, *from = saved_command_line;
	int len = 0;
	int userdef = 0;

	/* Save unparsed command line copy for /proc/cmdline */
	saved_command_line[COMMAND_LINE_SIZE-1] = '\0';

	for (;;) {
		if (c != ' ')
			goto next_char;
		/*
		 * "mem=nopentium" disables the 4MB page tables.
		 * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM
		 * to <mem>, overriding the bios size.
		 * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from
		 * <start> to <start>+<mem>, overriding the bios size.
		 *
		 * HPA tells me bootloaders need to parse mem=, so no new
		 * option should be mem=  [also see Documentation/i386/boot.txt]
		 */
		if (!memcmp(from, "mem=", 4)) {
			if (to != command_line)
				to--;
			if (!memcmp(from+4, "nopentium", 9)) {
				from += 9+4;
				clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
				disable_pse = 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 mem_size;
 
				mem_size = memparse(from+4, &from);
				limit_regions(mem_size);
				userdef=1;
			}
		}

		else if (!memcmp(from, "memmap=", 7)) {
			if (to != command_line)
				to--;
			if (!memcmp(from+7, "exactmap", 8)) {
#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
				from += 8+7;
				e820.nr_map = 0;
				userdef = 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(from+7, &from);
				if (*from == '@') {
					start_at = memparse(from+1, &from);
					add_memory_region(start_at, mem_size, E820_RAM);
				} else if (*from == '#') {
					start_at = memparse(from+1, &from);
					add_memory_region(start_at, mem_size, E820_ACPI);
				} else if (*from == '$') {
					start_at = memparse(from+1, &from);
					add_memory_region(start_at, mem_size, E820_RESERVED);
				} else {
					limit_regions(mem_size);
					userdef=1;
				}
			}
		}

		else if (!memcmp(from, "noexec=", 7))
			noexec_setup(from + 7);


#ifdef  CONFIG_X86_SMP
		/*
		 * If the BIOS enumerates physical processors before logical,
		 * maxcpus=N at enumeration-time can be used to disable HT.
		 */
		else if (!memcmp(from, "maxcpus=", 8)) {
			extern unsigned int maxcpus;

			maxcpus = simple_strtoul(from + 8, NULL, 0);
		}
#endif

#ifdef CONFIG_ACPI
		/* "acpi=off" disables both ACPI table parsing and interpreter */
		else if (!memcmp(from, "acpi=off", 8)) {
			disable_acpi();
		}

		/* acpi=force to over-ride black-list */
		else if (!memcmp(from, "acpi=force", 10)) {
			acpi_force = 1;
			acpi_ht = 1;
			acpi_disabled = 0;
		}

		/* acpi=strict disables out-of-spec workarounds */
		else if (!memcmp(from, "acpi=strict", 11)) {
			acpi_strict = 1;
		}

		/* Limit ACPI just to boot-time to enable HT */
		else if (!memcmp(from, "acpi=ht", 7)) {
			if (!acpi_force)
				disable_acpi();
			acpi_ht = 1;
		}
		
		/* "pci=noacpi" disable ACPI IRQ routing and PCI scan */
		else if (!memcmp(from, "pci=noacpi", 10)) {
			acpi_disable_pci();
		}
		/* "acpi=noirq" disables ACPI interrupt routing */
		else if (!memcmp(from, "acpi=noirq", 10)) {
			acpi_noirq_set();
		}

		else if (!memcmp(from, "acpi_sci=edge", 13))
			acpi_sci_flags.trigger =  1;

		else if (!memcmp(from, "acpi_sci=level", 14))
			acpi_sci_flags.trigger = 3;

		else if (!memcmp(from, "acpi_sci=high", 13))
			acpi_sci_flags.polarity = 1;

		else if (!memcmp(from, "acpi_sci=low", 12))
			acpi_sci_flags.polarity = 3;

#ifdef CONFIG_X86_IO_APIC
		else if (!memcmp(from, "acpi_skip_timer_override", 24))
			acpi_skip_timer_override = 1;

		if (!memcmp(from, "disable_timer_pin_1", 19))
			disable_timer_pin_1 = 1;
		if (!memcmp(from, "enable_timer_pin_1", 18))
			disable_timer_pin_1 = -1;

		/* disable IO-APIC */
		else if (!memcmp(from, "noapic", 6))
			disable_ioapic_setup();
#endif /* CONFIG_X86_IO_APIC */
#endif /* CONFIG_ACPI */

#ifdef CONFIG_X86_LOCAL_APIC
		/* enable local APIC */
		else if (!memcmp(from, "lapic", 5))
			lapic_enable();

		/* disable local APIC */
		else if (!memcmp(from, "nolapic", 6))
			lapic_disable();
#endif /* CONFIG_X86_LOCAL_APIC */

#ifdef CONFIG_KEXEC
		/* crashkernel=size@addr specifies the location to reserve for
		 * a crash kernel.  By reserving this memory we guarantee
		 * that linux never set's it up as a DMA target.
		 * Useful for holding code to do something appropriate
		 * after a kernel panic.
		 */
		else if (!memcmp(from, "crashkernel=", 12)) {
			unsigned long size, base;
			size = memparse(from+12, &from);
			if (*from == '@') {
				base = memparse(from+1, &from);
				/* FIXME: Do I want a sanity check
				 * to validate the memory range?
				 */
				crashk_res.start = base;
				crashk_res.end   = base + size - 1;
			}
		}
#endif
#ifdef CONFIG_CRASH_DUMP
		/* elfcorehdr= specifies the location of elf core header
		 * stored by the crashed kernel.
		 */
		else if (!memcmp(from, "elfcorehdr=", 11))
			elfcorehdr_addr = memparse(from+11, &from);
#endif

		/*
		 * highmem=size forces highmem to be exactly 'size' bytes.
		 * This works even on boxes that have no highmem otherwise.
		 * This also works to reduce highmem size on bigger boxes.
		 */
		else if (!memcmp(from, "highmem=", 8))
			highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT;
	
		/*
		 * vmalloc=size forces the vmalloc area to be exactly 'size'
		 * bytes. This can be used to increase (or decrease) the
		 * vmalloc area - the default is 128m.
		 */
		else if (!memcmp(from, "vmalloc=", 8))
			__VMALLOC_RESERVE = memparse(from+8, &from);

	next_char:
		c = *(from++);
		if (!c)
			break;
		if (COMMAND_LINE_SIZE <= ++len)
			break;
		*(to++) = c;
	}
	*to = '\0';
	*cmdline_p = command_line;
	if (userdef) {
		printk(KERN_INFO "user-defined physical RAM map:\n");
		print_memory_map("user");
	}
}

/*
 * 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;
}


/*
 * 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);
		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;
	}
}

/*
 * Determine low and high memory ranges:
 */
unsigned long __init find_max_low_pfn(void)
{
	unsigned long max_low_pfn;

	max_low_pfn = max_pfn;
	if (max_low_pfn > MAXMEM_PFN) {
		if (highmem_pages == -1)
			highmem_pages = max_pfn - MAXMEM_PFN;
		if (highmem_pages + MAXMEM_PFN < max_pfn)
			max_pfn = MAXMEM_PFN + highmem_pages;
		if (highmem_pages + MAXMEM_PFN > max_pfn) {
			printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages));
			highmem_pages = 0;
		}
		max_low_pfn = MAXMEM_PFN;
#ifndef CONFIG_HIGHMEM
		/* Maximum memory usable is what is directly addressable */
		printk(KERN_WARNING "Warning only %ldMB will be used.\n",
					MAXMEM>>20);
		if (max_pfn > MAX_NONPAE_PFN)
			printk(KERN_WARNING "Use a PAE enabled kernel.\n");
		else
			printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
		max_pfn = MAXMEM_PFN;
#else /* !CONFIG_HIGHMEM */
#ifndef CONFIG_X86_PAE
		if (max_pfn > MAX_NONPAE_PFN) {
			max_pfn = MAX_NONPAE_PFN;
			printk(KERN_WARNING "Warning only 4GB will be used.\n");
			printk(KERN_WARNING "Use a PAE enabled kernel.\n");
		}
#endif /* !CONFIG_X86_PAE */
#endif /* !CONFIG_HIGHMEM */
	} else {
		if (highmem_pages == -1)
			highmem_pages = 0;
#ifdef CONFIG_HIGHMEM
		if (highmem_pages >= max_pfn) {
			printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
			highmem_pages = 0;
		}
		if (highmem_pages) {
			if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){
				printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages));
				highmem_pages = 0;
			}
			max_low_pfn -= highmem_pages;
		}
#else
		if (highmem_pages)
			printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
#endif
	}
	return max_low_pfn;
}

/*
 * 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 + 1) << PAGE_SHIFT))
		return 0;
	if (end >= ((max_low_pfn + 1) << PAGE_SHIFT))
		end = (max_low_pfn + 1) << PAGE_SHIFT;
	if (start < end)
		free_bootmem(start, end - start);

	return 0;
}
/*
 * Register fully available low RAM pages with the bootmem allocator.
 */
static 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);