* 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/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/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/setup.h>
#include <asm/io_apic.h>
#include <asm/ist.h>
#include <asm/io.h>
-#include <asm/crash_dump.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 __initdata = 0;
-unsigned int dump_enabled;
+int disable_pse __devinitdata = 0;
/*
* Machine setup..
/* 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 = { 0, 0, 0, 0, -1, 1, 0, 0, -1 };
+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_INTERPRETER
+#ifdef CONFIG_ACPI
int acpi_disabled = 0;
#else
int acpi_disabled = 1;
#endif
EXPORT_SYMBOL(acpi_disabled);
-#ifdef CONFIG_ACPI_BOOT
+#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;
* 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 dmi_scan_machine(void);
extern void generic_apic_probe(char *);
extern int root_mountflags;
int i;
if (efi_enabled) {
- for (i = 0; i < memmap.nr_map; i++) {
- current_addr = memmap.map[i].phys_addr +
- (memmap.map[i].num_pages << 12);
- if (memmap.map[i].type == EFI_CONVENTIONAL_MEMORY) {
+ 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) {
- memmap.map[i].num_pages -=
+ 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++) {
- if (e820.map[i].type == E820_RAM) {
- current_addr = e820.map[i].addr + e820.map[i].size;
- if (current_addr >= size) {
- e820.map[i].size -= current_addr-size;
- e820.nr_map = i + 1;
- return;
- }
+ 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;
}
}
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.
+ * size before original memory map is
+ * reset.
*/
- set_saved_max_pfn();
+ find_max_pfn();
+ saved_max_pfn = max_pfn;
+#endif
from += 8+7;
e820.nr_map = 0;
userdef = 1;
}
#endif
-#ifdef CONFIG_ACPI_BOOT
+#ifdef CONFIG_ACPI
/* "acpi=off" disables both ACPI table parsing and interpreter */
else if (!memcmp(from, "acpi=off", 8)) {
disable_acpi();
#ifdef CONFIG_X86_IO_APIC
else if (!memcmp(from, "acpi_skip_timer_override", 24))
acpi_skip_timer_override = 1;
-#endif
-#ifdef CONFIG_X86_LOCAL_APIC
+ 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 */
-#endif /* CONFIG_ACPI_BOOT */
+
+#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.
*/
else if (!memcmp(from, "highmem=", 8))
highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT;
-
- if (!memcmp(from, "dump", 4))
- dump_enabled = 1;
/*
* vmalloc=size forces the vmalloc area to be exactly 'size'
return 0;
}
+static int __init
+efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
+{
+ memory_present(0, start, 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
max_pfn = 0;
if (efi_enabled) {
efi_memmap_walk(efi_find_max_pfn, &max_pfn);
+ efi_memmap_walk(efi_memory_present_wrapper, NULL);
return;
}
continue;
if (end > max_pfn)
max_pfn = end;
+ memory_present(0, start, end);
}
}
free_available_memory(unsigned long start, unsigned long end, void *arg)
{
/* check max_low_pfn */
- if (start >= ((max_low_pfn + 1) << PAGE_SHIFT))
+ if (start >= (max_low_pfn << PAGE_SHIFT))
return 0;
- if (end >= ((max_low_pfn + 1) << PAGE_SHIFT))
- end = (max_low_pfn + 1) << PAGE_SHIFT;
+ if (end >= (max_low_pfn << PAGE_SHIFT))
+ end = max_low_pfn << PAGE_SHIFT;
if (start < end)
free_bootmem(start, end - start);
reserve_bootmem(addr, PAGE_SIZE);
}
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init setup_bootmem_allocator(void);
static unsigned long __init setup_memory(void)
{
free_area_init(zones_size);
}
#else
-extern unsigned long setup_memory(void);
+extern unsigned long __init setup_memory(void);
extern void zone_sizes_init(void);
-#endif /* !CONFIG_DISCONTIGMEM */
+#endif /* !CONFIG_NEED_MULTIPLE_NODES */
void __init setup_bootmem_allocator(void)
{
* the (very unlikely) case of us accidentally initializing the
* bootmem allocator with an invalid RAM area.
*/
- reserve_bootmem(HIGH_MEMORY, (PFN_PHYS(min_low_pfn) +
- bootmap_size + PAGE_SIZE-1) - (HIGH_MEMORY));
+ 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,
}
}
#endif
+#ifdef CONFIG_KEXEC
+ if (crashk_res.start != crashk_res.end)
+ reserve_bootmem(crashk_res.start,
+ crashk_res.end - crashk_res.start + 1);
+#endif
}
/*
struct resource *res;
if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)
continue;
- res = alloc_bootmem_low(sizeof(struct resource));
+ 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;
*/
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 void __init register_memory(void)
+static int __init request_standard_resources(void)
{
- unsigned long gapstart, gapsize;
- unsigned long long last;
- int i;
+ int i;
+ printk("Setting up standard PCI resources\n");
if (efi_enabled)
efi_initialize_iomem_resources(&code_resource, &data_resource);
else
/* 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;
+}
+
+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
}
/*
- * Start allocating dynamic PCI memory a bit into the gap,
- * aligned up to the nearest megabyte.
- *
- * Question: should we try to pad it up a bit (do something
- * like " + (gapsize >> 3)" in there too?). We now have the
- * technology.
+ * See how much we want to round up: start off with
+ * rounding to the next 1MB area.
*/
- pci_mem_start = (gapstart + 0xfffff) & ~0xfffff;
+ 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);
}
-/* Use inline assembly to define this because the nops are defined
- as inline assembly strings in the include files and we cannot
- get them easily into strings. */
-asm("\t.data\nintelnops: "
- GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
- GENERIC_NOP7 GENERIC_NOP8);
-asm("\t.data\nk8nops: "
- K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
- K8_NOP7 K8_NOP8);
-asm("\t.data\nk7nops: "
- K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
- K7_NOP7 K7_NOP8);
-
-extern unsigned char intelnops[], k8nops[], k7nops[];
-static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
- NULL,
- intelnops,
- intelnops + 1,
- intelnops + 1 + 2,
- intelnops + 1 + 2 + 3,
- intelnops + 1 + 2 + 3 + 4,
- intelnops + 1 + 2 + 3 + 4 + 5,
- intelnops + 1 + 2 + 3 + 4 + 5 + 6,
- intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-};
-static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
- NULL,
- k8nops,
- k8nops + 1,
- k8nops + 1 + 2,
- k8nops + 1 + 2 + 3,
- k8nops + 1 + 2 + 3 + 4,
- k8nops + 1 + 2 + 3 + 4 + 5,
- k8nops + 1 + 2 + 3 + 4 + 5 + 6,
- k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-};
-static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
- NULL,
- k7nops,
- k7nops + 1,
- k7nops + 1 + 2,
- k7nops + 1 + 2 + 3,
- k7nops + 1 + 2 + 3 + 4,
- k7nops + 1 + 2 + 3 + 4 + 5,
- k7nops + 1 + 2 + 3 + 4 + 5 + 6,
- k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-};
-static struct nop {
- int cpuid;
- unsigned char **noptable;
-} noptypes[] = {
- { X86_FEATURE_K8, k8_nops },
- { X86_FEATURE_K7, k7_nops },
- { -1, NULL }
-};
-
-/* Replace instructions with better alternatives for this CPU type.
-
- This runs before SMP is initialized to avoid SMP problems with
- self modifying code. This implies that assymetric systems where
- APs have less capabilities than the boot processor are not handled.
- In this case boot with "noreplacement". */
-void apply_alternatives(void *start, void *end)
-{
- struct alt_instr *a;
- int diff, i, k;
- unsigned char **noptable = intel_nops;
- for (i = 0; noptypes[i].cpuid >= 0; i++) {
- if (boot_cpu_has(noptypes[i].cpuid)) {
- noptable = noptypes[i].noptable;
- break;
- }
- }
- for (a = start; (void *)a < end; a++) {
- if (!boot_cpu_has(a->cpuid))
- continue;
- BUG_ON(a->replacementlen > a->instrlen);
- memcpy(a->instr, a->replacement, a->replacementlen);
- diff = a->instrlen - a->replacementlen;
- /* Pad the rest with nops */
- for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
- k = diff;
- if (k > ASM_NOP_MAX)
- k = ASM_NOP_MAX;
- memcpy(a->instr + i, noptable[k], k);
- }
- }
-}
-
-static int no_replacement __initdata = 0;
-
-void __init alternative_instructions(void)
-{
- extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
- if (no_replacement)
- return;
- apply_alternatives(__alt_instructions, __alt_instructions_end);
-}
-
-static int __init noreplacement_setup(char *s)
-{
- no_replacement = 1;
- return 0;
-}
-
-__setup("noreplacement", noreplacement_setup);
-
static char * __init machine_specific_memory_setup(void);
#ifdef CONFIG_MCA
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();
/*
#endif
paging_init();
remapped_pgdat_init();
+ sparse_init();
zone_sizes_init();
/*
* NOTE: at this point the bootmem allocator is fully available.
*/
-#ifdef CONFIG_EARLY_PRINTK
- {
- char *s = strstr(*cmdline_p, "earlyprintk=");
- if (s) {
- extern void setup_early_printk(char *);
-
- setup_early_printk(s);
- printk("early console enabled\n");
- }
- }
-#endif
-
-
dmi_scan_machine();
#ifdef CONFIG_X86_GENERICARCH
if (efi_enabled)
efi_map_memmap();
-#ifdef CONFIG_ACPI_BOOT
+#ifdef CONFIG_ACPI
/*
* Parse the ACPI tables for possible boot-time SMP configuration.
*/
acpi_boot_table_init();
- acpi_boot_init();
#endif
+#ifdef CONFIG_X86_IO_APIC
+ check_acpi_pci(); /* Checks more than just ACPI actually */
+#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
}
+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);
+
#include "setup_arch_post.h"
/*
* Local Variables: