linux_dsm_epyc7002/arch/i386/kernel/setup.c
Vivek Goyal 10dbe196a8 [PATCH] i386: export: memory more than 4G through /proc/iomem
Currently /proc/iomem exports physical memory also apart from io device
memory.  But on i386, it truncates any memory more than 4GB.  This leads to
problems for kexec/kdump.

Kexec reads /proc/iomem to determine the system memory layout and prepares a
memory map based on that and passes it to the kernel being kexeced.  Given the
fact that memory more than 4GB has been truncated, new kernel never gets to
see and use that memory.

Kdump also reads /proc/iomem to determine the physical memory layout of the
system and encodes this informaiton in ELF headers.  After a crash new kernel
parses these ELF headers being used by previous kernel and vmcore is prepared
accordingly.  As memory more than 4GB has been truncated, kdump never sees
that memory and never prepares ELF headers for it.  Hence vmcore is truncated
and limited to 4GB even if there is more physical memory in the system.

This patch exports memory more than 4GB through /proc/iomem on i386.

Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-26 08:56:54 -08:00

1557 lines
40 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/config.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/tty.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/nodemask.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <linux/dmi.h>
#include <video/edid.h>
#include <asm/apic.h>
#include <asm/e820.h>
#include <asm/mpspec.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_pre.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;
#ifdef CONFIG_ACPI
int acpi_disabled = 0;
#else
int acpi_disabled = 1;
#endif
EXPORT_SYMBOL(acpi_disabled);
#ifdef CONFIG_ACPI
int __initdata acpi_force = 0;
extern acpi_interrupt_flags acpi_sci_flags;
#endif
/* 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 void generic_apic_probe(char *);
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
} };
#define ADAPTER_ROM_RESOURCES \
(sizeof adapter_rom_resources / sizeof adapter_rom_resources[0])
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 STANDARD_IO_RESOURCES \
(sizeof standard_io_resources / sizeof standard_io_resources[0])
#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 < 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;
}
}
static 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;
static 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.)
*/
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_PROC_VMCORE
/* 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;
}
static int __init
efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
{
memory_present(0, start, 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);
}
}
/*
* 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);
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));
#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 zones_size[MAX_NR_ZONES] = {0, 0, 0};
unsigned int max_dma, low;
max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
low = max_low_pfn;
if (low < max_dma)
zones_size[ZONE_DMA] = low;
else {
zones_size[ZONE_DMA] = max_dma;
zones_size[ZONE_NORMAL] = low - max_dma;
#ifdef CONFIG_HIGHMEM
zones_size[ZONE_HIGHMEM] = highend_pfn - low;
#endif
}
free_area_init(zones_size);
}
#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
#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;
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;
request_resource(&iomem_resource, res);
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_assign_resources(), which is also
* an fs_initcall, but is linked in later (in arch/i386/pci/i386.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 < STANDARD_IO_RESOURCES; i++)
request_resource(&ioport_resource, &standard_io_resources[i]);
return 0;
}
fs_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);
}
static char * __init machine_specific_memory_setup(void);
#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_cmdline_early(cmdline_p);
#ifdef CONFIG_EARLY_PRINTK
{
char *s = strstr(*cmdline_p, "earlyprintk=");
if (s) {
setup_early_printk(strchr(s, '=') + 1);
printk("early console enabled\n");
}
}
#endif
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(*cmdline_p);
#endif
if (efi_enabled)
efi_map_memmap();
#ifdef CONFIG_X86_IO_APIC
check_acpi_pci(); /* Checks more than just ACPI actually */
#endif
#ifdef CONFIG_ACPI
/*
* Parse the ACPI tables for possible boot-time SMP configuration.
*/
acpi_boot_table_init();
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
}
#include "setup_arch_post.h"
/*
* Local Variables:
* mode:c
* c-file-style:"k&r"
* c-basic-offset:8
* End:
*/