OpenCloudOS-Kernel/arch/i386/kernel/setup.c

1508 lines
38 KiB
C

/*
* linux/arch/i386/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/platform_device.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/nodemask.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <linux/dmi.h>
#include <linux/pfn.h>
#include <video/edid.h>
#include <asm/apic.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/mmzone.h>
#include <asm/setup.h>
#include <asm/arch_hooks.h>
#include <asm/sections.h>
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/io.h>
#include <setup_arch.h>
#include <bios_ebda.h>
/* Forward Declaration. */
void __init find_max_pfn(void);
/* 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_end __initdata = ~0UL;
int disable_pse __devinitdata = 0;
/*
* Machine setup..
*/
#ifdef CONFIG_EFI
int efi_enabled = 0;
EXPORT_SYMBOL(efi_enabled);
#endif
/* cpu data as detected by the assembly code in head.S */
struct cpuinfo_x86 new_cpu_data __initdata = { 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);
unsigned long mmu_cr4_features;
/* for MCA, but anyone else can use it if they want */
unsigned int machine_id;
#ifdef CONFIG_MCA
EXPORT_SYMBOL(machine_id);
#endif
unsigned int machine_submodel_id;
unsigned int BIOS_revision;
unsigned int mca_pentium_flag;
/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0x10000000;
#ifdef CONFIG_PCI
EXPORT_SYMBOL(pci_mem_start);
#endif
/* Boot loader ID as an integer, for the benefit of proc_dointvec */
int bootloader_type;
/* user-defined highmem size */
static unsigned int highmem_pages = -1;
/*
* Setup options
*/
struct drive_info_struct { char dummy[32]; } drive_info;
#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || \
defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE)
EXPORT_SYMBOL(drive_info);
#endif
struct screen_info screen_info;
EXPORT_SYMBOL(screen_info);
struct apm_info apm_info;
EXPORT_SYMBOL(apm_info);
struct sys_desc_table_struct {
unsigned short length;
unsigned char table[0];
};
struct edid_info edid_info;
EXPORT_SYMBOL_GPL(edid_info);
struct ist_info ist_info;
#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
EXPORT_SYMBOL(ist_info);
#endif
struct e820map e820;
extern void early_cpu_init(void);
extern int root_mountflags;
unsigned long saved_videomode;
#define RAMDISK_IMAGE_START_MASK 0x07FF
#define RAMDISK_PROMPT_FLAG 0x8000
#define RAMDISK_LOAD_FLAG 0x4000
static char command_line[COMMAND_LINE_SIZE];
unsigned char __initdata boot_params[PARAM_SIZE];
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 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;
}
}
static void __init limit_regions(unsigned long long size)
{
unsigned long long current_addr = 0;
int i;
if (efi_enabled) {
efi_memory_desc_t *md;
void *p;
for (p = memmap.map, i = 0; p < memmap.map_end;
p += memmap.desc_size, i++) {
md = p;
current_addr = md->phys_addr + (md->num_pages << 12);
if (md->type == EFI_CONVENTIONAL_MEMORY) {
if (current_addr >= size) {
md->num_pages -=
(((current_addr-size) + PAGE_SIZE-1) >> PAGE_SHIFT);
memmap.nr_map = i + 1;
return;
}
}
}
}
for (i = 0; i < e820.nr_map; i++) {
current_addr = e820.map[i].addr + e820.map[i].size;
if (current_addr < size)
continue;
if (e820.map[i].type != E820_RAM)
continue;
if (e820.map[i].addr >= size) {
/*
* This region starts past the end of the
* requested size, skip it completely.
*/
e820.nr_map = i;
} else {
e820.nr_map = i + 1;
e820.map[i].size -= current_addr - size;
}
return;
}
}
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 */
#define E820_DEBUG 1
static void __init print_memory_map(char *who)
{
int i;
for (i = 0; i < e820.nr_map; i++) {
printk(" %s: %016Lx - %016Lx ", who,
e820.map[i].addr,
e820.map[i].addr + e820.map[i].size);
switch (e820.map[i].type) {
case E820_RAM: printk("(usable)\n");
break;
case E820_RESERVED:
printk("(reserved)\n");
break;
case E820_ACPI:
printk("(ACPI data)\n");
break;
case E820_NVS:
printk("(ACPI NVS)\n");
break;
default: printk("type %lu\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.
*
*/
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;
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_
*/
/* if there's only one memory region, don't bother */
if (*pnr_map < 2)
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)
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;
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;
/* 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
static int __initdata user_defined_memmap = 0;
/*
* "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]
*/
static int __init parse_mem(char *arg)
{
if (!arg)
return -EINVAL;
if (strcmp(arg, "nopentium") == 0) {
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(arg, &arg);
limit_regions(mem_size);
user_defined_memmap = 1;
}
return 0;
}
early_param("mem", parse_mem);
static int __init parse_memmap(char *arg)
{
if (!arg)
return -EINVAL;
if (strcmp(arg, "exactmap") == 0) {
#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
e820.nr_map = 0;
user_defined_memmap = 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(arg, &arg);
if (*arg == '@') {
start_at = memparse(arg+1, &arg);
add_memory_region(start_at, mem_size, E820_RAM);
} else if (*arg == '#') {
start_at = memparse(arg+1, &arg);
add_memory_region(start_at, mem_size, E820_ACPI);
} else if (*arg == '$') {
start_at = memparse(arg+1, &arg);
add_memory_region(start_at, mem_size, E820_RESERVED);
} else {
limit_regions(mem_size);
user_defined_memmap = 1;
}
}
return 0;
}
early_param("memmap", parse_memmap);
#ifdef CONFIG_PROC_VMCORE
/* elfcorehdr= specifies the location of elf core header
* stored by the crashed kernel.
*/
static int __init parse_elfcorehdr(char *arg)
{
if (!arg)
return -EINVAL;
elfcorehdr_addr = memparse(arg, &arg);
return 0;
}
early_param("elfcorehdr", parse_elfcorehdr);
#endif /* CONFIG_PROC_VMCORE */
/*
* 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.
*/
static int __init parse_highmem(char *arg)
{
if (!arg)
return -EINVAL;
highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT;
return 0;
}
early_param("highmem", parse_highmem);
/*
* 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.
*/
static int __init parse_vmalloc(char *arg)
{
if (!arg)
return -EINVAL;
__VMALLOC_RESERVE = memparse(arg, &arg);
return 0;
}
early_param("vmalloc", parse_vmalloc);
/*
* reservetop=size reserves a hole at the top of the kernel address space which
* a hypervisor can load into later. Needed for dynamically loaded hypervisors,
* so relocating the fixmap can be done before paging initialization.
*/
static int __init parse_reservetop(char *arg)
{
unsigned long address;
if (!arg)
return -EINVAL;
address = memparse(arg, &arg);
reserve_top_address(address);
return 0;
}
early_param("reservetop", parse_reservetop);
/*
* 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;
}
/*
* 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 s, unsigned long e, unsigned type)
{
u64 start = s;
u64 end = e;
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 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);
}
}
/*
* 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 << PAGE_SHIFT))
return 0;
if (end >= (max_low_pfn << PAGE_SHIFT))
end = max_low_pfn << 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);
if (last_pfn > max_low_pfn)
last_pfn = max_low_pfn;
/*
* .. finally, did all the rounding and playing
* around just make the area go away?
*/
if (last_pfn <= curr_pfn)
continue;
size = last_pfn - curr_pfn;
free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size));
}
}
/*
* workaround for Dell systems that neglect to reserve EBDA
*/
static void __init reserve_ebda_region(void)
{
unsigned int addr;
addr = get_bios_ebda();
if (addr)
reserve_bootmem(addr, PAGE_SIZE);
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init setup_bootmem_allocator(void);
static unsigned long __init setup_memory(void)
{
/*
* partially used pages are not usable - thus
* we are rounding upwards:
*/
min_low_pfn = PFN_UP(init_pg_tables_end);
find_max_pfn();
max_low_pfn = find_max_low_pfn();
#ifdef CONFIG_HIGHMEM
highstart_pfn = highend_pfn = max_pfn;
if (max_pfn > max_low_pfn) {
highstart_pfn = max_low_pfn;
}
printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
pages_to_mb(highend_pfn - highstart_pfn));
num_physpages = highend_pfn;
high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
#ifdef CONFIG_FLATMEM
max_mapnr = num_physpages;
#endif
printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
pages_to_mb(max_low_pfn));
setup_bootmem_allocator();
return max_low_pfn;
}
void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] =
virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
add_active_range(0, 0, highend_pfn);
#else
add_active_range(0, 0, max_low_pfn);
#endif
free_area_init_nodes(max_zone_pfns);
}
#else
extern unsigned long __init setup_memory(void);
extern void zone_sizes_init(void);
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
void __init setup_bootmem_allocator(void)
{
unsigned long bootmap_size;
/*
* Initialize the boot-time allocator (with low memory only):
*/
bootmap_size = init_bootmem(min_low_pfn, max_low_pfn);
register_bootmem_low_pages(max_low_pfn);
/*
* Reserve the bootmem bitmap itself as well. We do this in two
* steps (first step was init_bootmem()) because this catches
* the (very unlikely) case of us accidentally initializing the
* bootmem allocator with an invalid RAM area.
*/
reserve_bootmem(__PHYSICAL_START, (PFN_PHYS(min_low_pfn) +
bootmap_size + PAGE_SIZE-1) - (__PHYSICAL_START));
/*
* reserve physical page 0 - it's a special BIOS page on many boxes,
* enabling clean reboots, SMP operation, laptop functions.
*/
reserve_bootmem(0, PAGE_SIZE);
/* reserve EBDA region, it's a 4K region */
reserve_ebda_region();
/* could be an AMD 768MPX chipset. Reserve a page before VGA to prevent
PCI prefetch into it (errata #56). Usually the page is reserved anyways,
unless you have no PS/2 mouse plugged in. */
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 == 6)
reserve_bootmem(0xa0000 - 4096, 4096);
#ifdef CONFIG_SMP
/*
* But first pinch a few for the stack/trampoline stuff
* FIXME: Don't need the extra page at 4K, but need to fix
* trampoline before removing it. (see the GDT stuff)
*/
reserve_bootmem(PAGE_SIZE, PAGE_SIZE);
#endif
#ifdef CONFIG_ACPI_SLEEP
/*
* Reserve low memory region for sleep support.
*/
acpi_reserve_bootmem();
#endif
#ifdef CONFIG_X86_FIND_SMP_CONFIG
/*
* Find and reserve possible boot-time SMP configuration:
*/
find_smp_config();
#endif
numa_kva_reserve();
#ifdef CONFIG_BLK_DEV_INITRD
if (LOADER_TYPE && INITRD_START) {
if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
reserve_bootmem(INITRD_START, INITRD_SIZE);
initrd_start =
INITRD_START ? INITRD_START + PAGE_OFFSET : 0;
initrd_end = initrd_start+INITRD_SIZE;
}
else {
printk(KERN_ERR "initrd extends beyond end of memory "
"(0x%08lx > 0x%08lx)\ndisabling initrd\n",
INITRD_START + INITRD_SIZE,
max_low_pfn << PAGE_SHIFT);
initrd_start = 0;
}
}
#endif
#ifdef CONFIG_KEXEC
if (crashk_res.start != crashk_res.end)
reserve_bootmem(crashk_res.start,
crashk_res.end - crashk_res.start + 1);
#endif
}
/*
* The node 0 pgdat is initialized before all of these because
* it's needed for bootmem. node>0 pgdats have their virtual
* space allocated before the pagetables are in place to access
* them, so they can't be cleared then.
*
* This should all compile down to nothing when NUMA is off.
*/
void __init remapped_pgdat_init(void)
{
int nid;
for_each_online_node(nid) {
if (nid != 0)
memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
}
}
/*
* 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);
static void __init register_memory(void)
{
unsigned long gapstart, gapsize, round;
unsigned long long last;
int i;
/*
* Search for the bigest gap in the low 32 bits of the e820
* memory space.
*/
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;
}
}
if (start < last)
last = start;
}
/*
* 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("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n",
pci_mem_start, gapstart, gapsize);
}
#ifdef CONFIG_MCA
static void set_mca_bus(int x)
{
MCA_bus = x;
}
#else
static void set_mca_bus(int x) { }
#endif
/*
* 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.
*/
void __init setup_arch(char **cmdline_p)
{
unsigned long max_low_pfn;
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
pre_setup_arch_hook();
early_cpu_init();
/*
* FIXME: This isn't an official loader_type right
* now but does currently work with elilo.
* If we were configured as an EFI kernel, check to make
* sure that we were loaded correctly from elilo and that
* the system table is valid. If not, then initialize normally.
*/
#ifdef CONFIG_EFI
if ((LOADER_TYPE == 0x50) && EFI_SYSTAB)
efi_enabled = 1;
#endif
ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV);
drive_info = DRIVE_INFO;
screen_info = SCREEN_INFO;
edid_info = EDID_INFO;
apm_info.bios = APM_BIOS_INFO;
ist_info = IST_INFO;
saved_videomode = VIDEO_MODE;
if( SYS_DESC_TABLE.length != 0 ) {
set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2);
machine_id = SYS_DESC_TABLE.table[0];
machine_submodel_id = SYS_DESC_TABLE.table[1];
BIOS_revision = SYS_DESC_TABLE.table[2];
}
bootloader_type = LOADER_TYPE;
#ifdef CONFIG_BLK_DEV_RAM
rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK;
rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0);
rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0);
#endif
ARCH_SETUP
if (efi_enabled)
efi_init();
else {
printk(KERN_INFO "BIOS-provided physical RAM map:\n");
print_memory_map(machine_specific_memory_setup());
}
copy_edd();
if (!MOUNT_ROOT_RDONLY)
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;
init_mm.brk = init_pg_tables_end + PAGE_OFFSET;
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;
parse_early_param();
if (user_defined_memmap) {
printk(KERN_INFO "user-defined physical RAM map:\n");
print_memory_map("user");
}
strlcpy(command_line, saved_command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
max_low_pfn = setup_memory();
/*
* NOTE: before this point _nobody_ is allowed to allocate
* any memory using the bootmem allocator. Although the
* alloctor is now initialised only the first 8Mb of the kernel
* virtual address space has been mapped. All allocations before
* paging_init() has completed must use the alloc_bootmem_low_pages()
* variant (which allocates DMA'able memory) and care must be taken
* not to exceed the 8Mb limit.
*/
#ifdef CONFIG_SMP
smp_alloc_memory(); /* AP processor realmode stacks in low memory*/
#endif
paging_init();
remapped_pgdat_init();
sparse_init();
zone_sizes_init();
/*
* NOTE: at this point the bootmem allocator is fully available.
*/
dmi_scan_machine();
#ifdef CONFIG_X86_GENERICARCH
generic_apic_probe();
#endif
if (efi_enabled)
efi_map_memmap();
#ifdef CONFIG_ACPI
/*
* Parse the ACPI tables for possible boot-time SMP configuration.
*/
acpi_boot_table_init();
#endif
#ifdef CONFIG_PCI
#ifdef CONFIG_X86_IO_APIC
check_acpi_pci(); /* Checks more than just ACPI actually */
#endif
#endif
#ifdef CONFIG_ACPI
acpi_boot_init();
#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
#ifdef CONFIG_X86_LOCAL_APIC
if (smp_found_config)
get_smp_config();
#endif
register_memory();
#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
tsc_init();
}
static __init int add_pcspkr(void)
{
struct platform_device *pd;
int ret;
pd = platform_device_alloc("pcspkr", -1);
if (!pd)
return -ENOMEM;
ret = platform_device_add(pd);
if (ret)
platform_device_put(pd);
return ret;
}
device_initcall(add_pcspkr);
/*
* Local Variables:
* mode:c
* c-file-style:"k&r"
* c-basic-offset:8
* End:
*/