linux/arch/x86/kernel/setup.c

/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *
 *  Memory region support
 *	David Parsons <orc@pell.chi.il.us>, July-August 1999
 *
 *  Added E820 sanitization routine (removes overlapping memory regions);
 *  Brian Moyle <bmoyle@mvista.com>, February 2001
 *
 * Moved CPU detection code to cpu/${cpu}.c
 *    Patrick Mochel <mochel@osdl.org>, March 2002
 *
 *  Provisions for empty E820 memory regions (reported by certain BIOSes).
 *  Alex Achenbach <xela@slit.de>, December 2002.
 *
 */

/*
 * This file handles the architecture-dependent parts of initialization
 */

#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/acpi.h>
#include <linux/apm_bios.h>
#include <linux/initrd.h>
#include <linux/bootmem.h>
#include <linux/seq_file.h>
#include <linux/console.h>
#include <linux/mca.h>
#include <linux/root_dev.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/edd.h>
#include <linux/iscsi_ibft.h>
#include <linux/nodemask.h>
#include <linux/kexec.h>
#include <linux/dmi.h>
#include <linux/pfn.h>
#include <linux/pci.h>
#include <asm/pci-direct.h>
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/delay.h>
#include <linux/highmem.h>

#include <linux/kallsyms.h>
#include <linux/edd.h>
#include <linux/iscsi_ibft.h>
#include <linux/kexec.h>
#include <linux/cpufreq.h>
#include <linux/dma-mapping.h>
#include <linux/ctype.h>
#include <linux/uaccess.h>

#include <linux/percpu.h>
#include <linux/crash_dump.h>

#include <video/edid.h>

#include <asm/mtrr.h>
#include <asm/apic.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/arch_hooks.h>
#include <asm/efi.h>
#include <asm/sections.h>
#include <asm/dmi.h>
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/vmi.h>
#include <setup_arch.h>
#include <asm/bios_ebda.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/bugs.h>

#include <asm/system.h>
#include <asm/vsyscall.h>
#include <asm/smp.h>
#include <asm/desc.h>
#include <asm/dma.h>
#include <asm/gart.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>

#include <mach_apic.h>
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define ARCH_SETUP
#endif

#include <asm/percpu.h>
#include <asm/sections.h>
#include <asm/topology.h>
#include <asm/apicdef.h>
#ifdef CONFIG_X86_64
#include <asm/numa_64.h>
#endif
#ifdef CONFIG_X86_32
#include <asm/highmem.h>
#endif

#ifndef CONFIG_DEBUG_BOOT_PARAMS
struct boot_params __initdata boot_params;
#else
struct boot_params boot_params;
#endif

/* This value is set up by the early boot code to point to the value
   immediately after the boot time page tables.  It contains a *physical*
   address, and must not be in the .bss segment! */
unsigned long init_pg_tables_start __initdata = ~0UL;
unsigned long init_pg_tables_end __initdata = ~0UL;

/*
 * Machine setup..
 */
static struct resource data_resource = {
	.name	= "Kernel data",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource code_resource = {
	.name	= "Kernel code",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

static struct resource bss_resource = {
	.name	= "Kernel bss",
	.start	= 0,
	.end	= 0,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};


#ifdef CONFIG_X86_32
static struct resource video_ram_resource = {
	.name	= "Video RAM area",
	.start	= 0xa0000,
	.end	= 0xbffff,
	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
};

/* cpu data as detected by the assembly code in head.S */
struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
/* common cpu data for all cpus */
struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1};
EXPORT_SYMBOL(boot_cpu_data);
static void set_mca_bus(int x)
{
#ifdef CONFIG_MCA
	MCA_bus = x;
#endif
}

unsigned int def_to_bigsmp;

/* for MCA, but anyone else can use it if they want */
unsigned int machine_id;
unsigned int machine_submodel_id;
unsigned int BIOS_revision;

struct apm_info apm_info;
EXPORT_SYMBOL(apm_info);

#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
	defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
struct ist_info ist_info;
EXPORT_SYMBOL(ist_info);
#else
struct ist_info ist_info;
#endif

#else
struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);
#endif


#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
unsigned long mmu_cr4_features;
#else
unsigned long mmu_cr4_features = X86_CR4_PAE;
#endif

/* Boot loader ID as an integer, for the benefit of proc_dointvec */
int bootloader_type;

/*
 * Early DMI memory
 */
int dmi_alloc_index;
char dmi_alloc_data[DMI_MAX_DATA];

/*
 * Setup options
 */
struct screen_info screen_info;
EXPORT_SYMBOL(screen_info);
struct edid_info edid_info;
EXPORT_SYMBOL_GPL(edid_info);

extern int root_mountflags;

unsigned long saved_video_mode;

#define RAMDISK_IMAGE_START_MASK	0x07FF
#define RAMDISK_PROMPT_FLAG		0x8000
#define RAMDISK_LOAD_FLAG		0x4000

static char __initdata command_line[COMMAND_LINE_SIZE];

#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, boot_params.edd_mbr_sig_buffer,
	    sizeof(edd.mbr_signature));
     memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info));
     edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries;
     edd.edd_info_nr = boot_params.eddbuf_entries;
}
#else
static inline void copy_edd(void)
{
}
#endif

#ifdef CONFIG_BLK_DEV_INITRD

#ifdef CONFIG_X86_32

#define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
static void __init relocate_initrd(void)
{

	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
	u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT;
	u64 ramdisk_here;
	unsigned long slop, clen, mapaddr;
	char *p, *q;

	/* We need to move the initrd down into lowmem */
	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
					 PAGE_SIZE);

	if (ramdisk_here == -1ULL)
		panic("Cannot find place for new RAMDISK of size %lld\n",
			 ramdisk_size);

	/* Note: this includes all the lowmem currently occupied by
	   the initrd, we rely on that fact to keep the data intact. */
	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
			 "NEW RAMDISK");
	initrd_start = ramdisk_here + PAGE_OFFSET;
	initrd_end   = initrd_start + ramdisk_size;
	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
			 ramdisk_here, ramdisk_here + ramdisk_size);

	q = (char *)initrd_start;

	/* Copy any lowmem portion of the initrd */
	if (ramdisk_image < end_of_lowmem) {
		clen = end_of_lowmem - ramdisk_image;
		p = (char *)__va(ramdisk_image);
		memcpy(q, p, clen);
		q += clen;
		ramdisk_image += clen;
		ramdisk_size  -= clen;
	}

	/* Copy the highmem portion of the initrd */
	while (ramdisk_size) {
		slop = ramdisk_image & ~PAGE_MASK;
		clen = ramdisk_size;
		if (clen > MAX_MAP_CHUNK-slop)
			clen = MAX_MAP_CHUNK-slop;
		mapaddr = ramdisk_image & PAGE_MASK;
		p = early_ioremap(mapaddr, clen+slop);
		memcpy(q, p+slop, clen);
		early_iounmap(p, clen+slop);
		q += clen;
		ramdisk_image += clen;
		ramdisk_size  -= clen;
	}
	/* high pages is not converted by early_res_to_bootmem */
	ramdisk_image = boot_params.hdr.ramdisk_image;
	ramdisk_size  = boot_params.hdr.ramdisk_size;
	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
		" %08llx - %08llx\n",
		ramdisk_image, ramdisk_image + ramdisk_size - 1,
		ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
#endif

static void __init reserve_initrd(void)
{
	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
	u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT;

	if (!boot_params.hdr.type_of_loader ||
	    !ramdisk_image || !ramdisk_size)
		return;		/* No initrd provided by bootloader */

	initrd_start = 0;

	if (ramdisk_size >= (end_of_lowmem>>1)) {
		free_early(ramdisk_image, ramdisk_end);
		printk(KERN_ERR "initrd too large to handle, "
		       "disabling initrd\n");
		return;
	}

	printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image,
			ramdisk_end);


	if (ramdisk_end <= end_of_lowmem) {
		/* All in lowmem, easy case */
		/*
		 * don't need to reserve again, already reserved early
		 * in i386_start_kernel
		 */
		initrd_start = ramdisk_image + PAGE_OFFSET;
		initrd_end = initrd_start + ramdisk_size;
		return;
	}

#ifdef CONFIG_X86_32
	relocate_initrd();
#else
	printk(KERN_ERR "initrd extends beyond end of memory "
	       "(0x%08llx > 0x%08llx)\ndisabling initrd\n",
	       ramdisk_end, end_of_lowmem);
	initrd_start = 0;
#endif
	free_early(ramdisk_image, ramdisk_end);
}
#else
static void __init reserve_initrd(void)
{
}
#endif /* CONFIG_BLK_DEV_INITRD */

void __init parse_setup_data(void)
{
	struct setup_data *data;
	u64 pa_data;

	if (boot_params.hdr.version < 0x0209)
		return;
	pa_data = boot_params.hdr.setup_data;
	while (pa_data) {
		data = early_ioremap(pa_data, PAGE_SIZE);
		switch (data->type) {
		case SETUP_E820_EXT:
			parse_e820_ext(data, pa_data);
			break;
		default:
			break;
		}
#ifndef CONFIG_DEBUG_BOOT_PARAMS
		free_early(pa_data, pa_data+sizeof(*data)+data->len);
#endif
		pa_data = data->next;
		early_iounmap(data, PAGE_SIZE);
	}
}

/*
 * Determine if we were loaded by an EFI loader.  If so, then we have also been
 * passed the efi memmap, systab, etc., so we should use these data structures
 * for initialization.  Note, the efi init code path is determined by the
 * global efi_enabled. This allows the same kernel image to be used on existing
 * systems (with a traditional BIOS) as well as on EFI systems.
 */
/*
 * setup_arch - architecture-specific boot-time initializations
 *
 * Note: On x86_64, fixmaps are ready for use even before this is called.
 */

void __init setup_arch(char **cmdline_p)
{
#ifdef CONFIG_X86_32
	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
	pre_setup_arch_hook();
	early_cpu_init();
	early_ioremap_init();
	reserve_setup_data();
#else
	printk(KERN_INFO "Command line: %s\n", boot_command_line);
#endif

	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
	screen_info = boot_params.screen_info;
	edid_info = boot_params.edid_info;
#ifdef CONFIG_X86_32
	apm_info.bios = boot_params.apm_bios_info;
	ist_info = boot_params.ist_info;
	if (boot_params.sys_desc_table.length != 0) {
		set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2);
		machine_id = boot_params.sys_desc_table.table[0];
		machine_submodel_id = boot_params.sys_desc_table.table[1];
		BIOS_revision = boot_params.sys_desc_table.table[2];
	}
#endif
	saved_video_mode = boot_params.hdr.vid_mode;
	bootloader_type = boot_params.hdr.type_of_loader;

#ifdef CONFIG_BLK_DEV_RAM
	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
#endif
#ifdef CONFIG_EFI
	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
#ifdef CONFIG_X86_32
		     "EL32",
#else
		     "EL64",
#endif
	 4)) {
		efi_enabled = 1;
		efi_reserve_early();
	}
#endif

	ARCH_SETUP

	setup_memory_map();
	copy_edd();

	if (!boot_params.hdr.root_flags)
		root_mountflags &= ~MS_RDONLY;
	init_mm.start_code = (unsigned long) _text;
	init_mm.end_code = (unsigned long) _etext;
	init_mm.end_data = (unsigned long) _edata;
#ifdef CONFIG_X86_32
	init_mm.brk = init_pg_tables_end + PAGE_OFFSET;
#else
	init_mm.brk = (unsigned long) &_end;
#endif

	code_resource.start = virt_to_phys(_text);
	code_resource.end = virt_to_phys(_etext)-1;
	data_resource.start = virt_to_phys(_etext);
	data_resource.end = virt_to_phys(_edata)-1;
	bss_resource.start = virt_to_phys(&__bss_start);
	bss_resource.end = virt_to_phys(&__bss_stop)-1;

#ifdef CONFIG_X86_64
	early_cpu_init();
#endif
	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
	*cmdline_p = command_line;

	parse_setup_data();

	parse_early_param();

	if (acpi_mps_check()) {
#ifdef CONFIG_X86_LOCAL_APIC
#ifdef CONFIG_X86_32
		enable_local_apic = -1;
#else
		disable_apic = 1;
#endif
#endif
		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
	}

	finish_e820_parsing();

#ifdef CONFIG_X86_32
	probe_roms();
#else
# ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
	if (init_ohci1394_dma_early)
		init_ohci1394_dma_on_all_controllers();
# endif
#endif

	/* after parse_early_param, so could debug it */
	insert_resource(&iomem_resource, &code_resource);
	insert_resource(&iomem_resource, &data_resource);
	insert_resource(&iomem_resource, &bss_resource);

	if (efi_enabled)
		efi_init();

#ifdef CONFIG_X86_32
	if (ppro_with_ram_bug()) {
		e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
				  E820_RESERVED);
		sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
		printk(KERN_INFO "fixed physical RAM map:\n");
		e820_print_map("bad_ppro");
	}
#else
	early_gart_iommu_check();
#endif

	e820_register_active_regions(0, 0, -1UL);
	/*
	 * partially used pages are not usable - thus
	 * we are rounding upwards:
	 */
	max_pfn = e820_end_of_ram();

	/* preallocate 4k for mptable mpc */
	early_reserve_e820_mpc_new();
	/* update e820 for memory not covered by WB MTRRs */
	mtrr_bp_init();
	if (mtrr_trim_uncached_memory(max_pfn)) {
		remove_all_active_ranges();
		e820_register_active_regions(0, 0, -1UL);
		max_pfn = e820_end_of_ram();
	}

#ifdef CONFIG_X86_32
	/* max_low_pfn get updated here */
	find_low_pfn_range();
#else
	num_physpages = max_pfn;

	check_efer();

	/* How many end-of-memory variables you have, grandma! */
	/* need this before calling reserve_initrd */
	max_low_pfn = max_pfn;
	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
#endif

	/* max_pfn_mapped is updated here */
	max_pfn_mapped = init_memory_mapping(0, (max_low_pfn << PAGE_SHIFT));

	reserve_initrd();

#ifdef CONFIG_X86_64
	vsmp_init();
#endif

	dmi_scan_machine();

	io_delay_init();

	/*
	 * Parse the ACPI tables for possible boot-time SMP configuration.
	 */
	acpi_boot_table_init();

#ifdef CONFIG_X86_64
	/* Remove active ranges so rediscovery with NUMA-awareness happens */
	remove_all_active_ranges();
#endif

#ifdef CONFIG_ACPI_NUMA
	/*
	 * Parse SRAT to discover nodes.
	 */
	acpi_numa_init();
#endif

	initmem_init(0, max_pfn);

#ifdef CONFIG_X86_64
	dma32_reserve_bootmem();
#endif

#ifdef CONFIG_ACPI_SLEEP
	/*
	 * Reserve low memory region for sleep support.
	 */
	acpi_reserve_bootmem();
#endif
#if defined(CONFIG_X86_FIND_SMP_CONFIG) && defined(CONFIG_X86_32) || \
    defined(CONFIG_X86_MPPARSE) && defined(CONFIG_X86_64)
	/*
	 * Find and reserve possible boot-time SMP configuration:
	 */
	find_smp_config();
#endif
	reserve_crashkernel();

	reserve_ibft_region();

#ifdef CONFIG_KVM_CLOCK
	kvmclock_init();
#endif

#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
	/*
	 * Must be after max_low_pfn is determined, and before kernel
	 * pagetables are setup.
	 */
	vmi_init();
#endif

	paging_init();

#ifdef CONFIG_X86_64
	map_vsyscall();
#endif

	/*
	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
	 */

#if defined(CONFIG_PROVIDE_OHCI1394_DMA_INIT) && defined(CONFIG_X86_32)
	if (init_ohci1394_dma_early)
		init_ohci1394_dma_on_all_controllers();
#endif

#ifdef CONFIG_X86_GENERICARCH
	generic_apic_probe();
#endif

	early_quirks();

	/*
	 * Read APIC and some other early information from ACPI tables.
	 */
	acpi_boot_init();

#ifdef CONFIG_X86_64
	init_cpu_to_node();
#endif

#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS)
	/*
	 * get boot-time SMP configuration:
	 */
	if (smp_found_config)
		get_smp_config();
#endif

#ifdef CONFIG_X86_64
	init_apic_mappings();
	ioapic_init_mappings();
#else
# if defined(CONFIG_SMP) && defined(CONFIG_X86_PC)
	if (def_to_bigsmp)
		printk(KERN_WARNING "More than 8 CPUs detected and "
			"CONFIG_X86_PC cannot handle it.\nUse "
			"CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
# endif
#endif
	kvm_guest_init();

	e820_reserve_resources();
	e820_mark_nosave_regions(max_low_pfn);

#ifdef CONFIG_X86_32
	request_resource(&iomem_resource, &video_ram_resource);
#endif
	reserve_standard_io_resources();

	e820_setup_gap();

#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
		conswitchp = &vga_con;
#elif defined(CONFIG_DUMMY_CONSOLE)
	conswitchp = &dummy_con;
#endif
#endif
}