linux/arch/x86/kernel/setup.c
Huang, Ying 8c5beb50d3 x86 boot: pass E820 memory map entries more than 128 via linked list of setup data
Because of the size limits of struct boot_params (zero page), the
maximum number of E820 memory map entries can be passed to kernel is
128. As pointed by Paul Jackson, there is some machine produced by SGI
with so many nodes that the number of E820 memory map entries is more
than 128. To enabling Linux kernel on these system, a new setup data
type named SETUP_E820_EXT is defined to pass additional memory map
entries to Linux kernel.

This patch is based on x86/auto-latest branch of git-x86 tree and has
been tested on x86_64 and i386 platform.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-08 10:37:39 +02:00

165 lines
4 KiB
C

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/percpu.h>
#include <asm/smp.h>
#include <asm/percpu.h>
#include <asm/sections.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/topology.h>
#include <asm/mpspec.h>
#include <asm/apicdef.h>
#ifdef CONFIG_X86_LOCAL_APIC
unsigned int num_processors;
unsigned disabled_cpus __cpuinitdata;
/* Processor that is doing the boot up */
unsigned int boot_cpu_physical_apicid = -1U;
unsigned int max_physical_apicid;
EXPORT_SYMBOL(boot_cpu_physical_apicid);
DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID;
EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid);
/* Bitmask of physically existing CPUs */
physid_mask_t phys_cpu_present_map;
#endif
#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
/*
* Copy data used in early init routines from the initial arrays to the
* per cpu data areas. These arrays then become expendable and the
* *_early_ptr's are zeroed indicating that the static arrays are gone.
*/
static void __init setup_per_cpu_maps(void)
{
int cpu;
for_each_possible_cpu(cpu) {
per_cpu(x86_cpu_to_apicid, cpu) = x86_cpu_to_apicid_init[cpu];
per_cpu(x86_bios_cpu_apicid, cpu) =
x86_bios_cpu_apicid_init[cpu];
#ifdef CONFIG_NUMA
per_cpu(x86_cpu_to_node_map, cpu) =
x86_cpu_to_node_map_init[cpu];
#endif
}
/* indicate the early static arrays will soon be gone */
x86_cpu_to_apicid_early_ptr = NULL;
x86_bios_cpu_apicid_early_ptr = NULL;
#ifdef CONFIG_NUMA
x86_cpu_to_node_map_early_ptr = NULL;
#endif
}
#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP
cpumask_t *cpumask_of_cpu_map __read_mostly;
EXPORT_SYMBOL(cpumask_of_cpu_map);
/* requires nr_cpu_ids to be initialized */
static void __init setup_cpumask_of_cpu(void)
{
int i;
/* alloc_bootmem zeroes memory */
cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids);
for (i = 0; i < nr_cpu_ids; i++)
cpu_set(i, cpumask_of_cpu_map[i]);
}
#else
static inline void setup_cpumask_of_cpu(void) { }
#endif
#ifdef CONFIG_X86_32
/*
* Great future not-so-futuristic plan: make i386 and x86_64 do it
* the same way
*/
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
#endif
/*
* Great future plan:
* Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
* Always point %gs to its beginning
*/
void __init setup_per_cpu_areas(void)
{
int i, highest_cpu = 0;
unsigned long size;
#ifdef CONFIG_HOTPLUG_CPU
prefill_possible_map();
#endif
/* Copy section for each CPU (we discard the original) */
size = PERCPU_ENOUGH_ROOM;
printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n",
size);
for_each_possible_cpu(i) {
char *ptr;
#ifndef CONFIG_NEED_MULTIPLE_NODES
ptr = alloc_bootmem_pages(size);
#else
int node = early_cpu_to_node(i);
if (!node_online(node) || !NODE_DATA(node)) {
ptr = alloc_bootmem_pages(size);
printk(KERN_INFO
"cpu %d has no node or node-local memory\n", i);
}
else
ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
#endif
if (!ptr)
panic("Cannot allocate cpu data for CPU %d\n", i);
#ifdef CONFIG_X86_64
cpu_pda(i)->data_offset = ptr - __per_cpu_start;
#else
__per_cpu_offset[i] = ptr - __per_cpu_start;
#endif
memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
highest_cpu = i;
}
nr_cpu_ids = highest_cpu + 1;
printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d\n", NR_CPUS, nr_cpu_ids);
/* Setup percpu data maps */
setup_per_cpu_maps();
/* Setup cpumask_of_cpu map */
setup_cpumask_of_cpu();
}
#endif
void __init parse_setup_data(void)
{
struct setup_data *data;
u64 pa_data;
if (boot_params.hdr.version < 0x0209)
return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_ioremap(pa_data, PAGE_SIZE);
switch (data->type) {
case SETUP_E820_EXT:
parse_e820_ext(data, pa_data);
break;
default:
break;
}
#ifndef CONFIG_DEBUG_BOOT_PARAMS
free_early(pa_data, pa_data+sizeof(*data)+data->len);
#endif
pa_data = data->next;
early_iounmap(data, PAGE_SIZE);
}
}