284 lines
6.6 KiB
C
284 lines
6.6 KiB
C
/*
|
|
* handle transition of Linux booting another kernel
|
|
* Copyright (C) 2002-2005 Eric Biederman <ebiederm@xmission.com>
|
|
*
|
|
* This source code is licensed under the GNU General Public License,
|
|
* Version 2. See the file COPYING for more details.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/kexec.h>
|
|
#include <linux/string.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/reboot.h>
|
|
#include <linux/numa.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/io.h>
|
|
#include <linux/suspend.h>
|
|
|
|
#include <asm/init.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/debugreg.h>
|
|
|
|
static void free_transition_pgtable(struct kimage *image)
|
|
{
|
|
free_page((unsigned long)image->arch.pud);
|
|
free_page((unsigned long)image->arch.pmd);
|
|
free_page((unsigned long)image->arch.pte);
|
|
}
|
|
|
|
static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
|
|
{
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
unsigned long vaddr, paddr;
|
|
int result = -ENOMEM;
|
|
|
|
vaddr = (unsigned long)relocate_kernel;
|
|
paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
|
|
pgd += pgd_index(vaddr);
|
|
if (!pgd_present(*pgd)) {
|
|
pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
|
|
if (!pud)
|
|
goto err;
|
|
image->arch.pud = pud;
|
|
set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
|
|
}
|
|
pud = pud_offset(pgd, vaddr);
|
|
if (!pud_present(*pud)) {
|
|
pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
|
|
if (!pmd)
|
|
goto err;
|
|
image->arch.pmd = pmd;
|
|
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
|
|
}
|
|
pmd = pmd_offset(pud, vaddr);
|
|
if (!pmd_present(*pmd)) {
|
|
pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
|
|
if (!pte)
|
|
goto err;
|
|
image->arch.pte = pte;
|
|
set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
|
|
}
|
|
pte = pte_offset_kernel(pmd, vaddr);
|
|
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
|
|
return 0;
|
|
err:
|
|
free_transition_pgtable(image);
|
|
return result;
|
|
}
|
|
|
|
static void *alloc_pgt_page(void *data)
|
|
{
|
|
struct kimage *image = (struct kimage *)data;
|
|
struct page *page;
|
|
void *p = NULL;
|
|
|
|
page = kimage_alloc_control_pages(image, 0);
|
|
if (page) {
|
|
p = page_address(page);
|
|
clear_page(p);
|
|
}
|
|
|
|
return p;
|
|
}
|
|
|
|
static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
|
|
{
|
|
struct x86_mapping_info info = {
|
|
.alloc_pgt_page = alloc_pgt_page,
|
|
.context = image,
|
|
.pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
|
|
};
|
|
unsigned long mstart, mend;
|
|
pgd_t *level4p;
|
|
int result;
|
|
int i;
|
|
|
|
level4p = (pgd_t *)__va(start_pgtable);
|
|
clear_page(level4p);
|
|
for (i = 0; i < nr_pfn_mapped; i++) {
|
|
mstart = pfn_mapped[i].start << PAGE_SHIFT;
|
|
mend = pfn_mapped[i].end << PAGE_SHIFT;
|
|
|
|
result = kernel_ident_mapping_init(&info,
|
|
level4p, mstart, mend);
|
|
if (result)
|
|
return result;
|
|
}
|
|
|
|
/*
|
|
* segments's mem ranges could be outside 0 ~ max_pfn,
|
|
* for example when jump back to original kernel from kexeced kernel.
|
|
* or first kernel is booted with user mem map, and second kernel
|
|
* could be loaded out of that range.
|
|
*/
|
|
for (i = 0; i < image->nr_segments; i++) {
|
|
mstart = image->segment[i].mem;
|
|
mend = mstart + image->segment[i].memsz;
|
|
|
|
result = kernel_ident_mapping_init(&info,
|
|
level4p, mstart, mend);
|
|
|
|
if (result)
|
|
return result;
|
|
}
|
|
|
|
return init_transition_pgtable(image, level4p);
|
|
}
|
|
|
|
static void set_idt(void *newidt, u16 limit)
|
|
{
|
|
struct desc_ptr curidt;
|
|
|
|
/* x86-64 supports unaliged loads & stores */
|
|
curidt.size = limit;
|
|
curidt.address = (unsigned long)newidt;
|
|
|
|
__asm__ __volatile__ (
|
|
"lidtq %0\n"
|
|
: : "m" (curidt)
|
|
);
|
|
};
|
|
|
|
|
|
static void set_gdt(void *newgdt, u16 limit)
|
|
{
|
|
struct desc_ptr curgdt;
|
|
|
|
/* x86-64 supports unaligned loads & stores */
|
|
curgdt.size = limit;
|
|
curgdt.address = (unsigned long)newgdt;
|
|
|
|
__asm__ __volatile__ (
|
|
"lgdtq %0\n"
|
|
: : "m" (curgdt)
|
|
);
|
|
};
|
|
|
|
static void load_segments(void)
|
|
{
|
|
__asm__ __volatile__ (
|
|
"\tmovl %0,%%ds\n"
|
|
"\tmovl %0,%%es\n"
|
|
"\tmovl %0,%%ss\n"
|
|
"\tmovl %0,%%fs\n"
|
|
"\tmovl %0,%%gs\n"
|
|
: : "a" (__KERNEL_DS) : "memory"
|
|
);
|
|
}
|
|
|
|
int machine_kexec_prepare(struct kimage *image)
|
|
{
|
|
unsigned long start_pgtable;
|
|
int result;
|
|
|
|
/* Calculate the offsets */
|
|
start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
|
|
|
|
/* Setup the identity mapped 64bit page table */
|
|
result = init_pgtable(image, start_pgtable);
|
|
if (result)
|
|
return result;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void machine_kexec_cleanup(struct kimage *image)
|
|
{
|
|
free_transition_pgtable(image);
|
|
}
|
|
|
|
/*
|
|
* Do not allocate memory (or fail in any way) in machine_kexec().
|
|
* We are past the point of no return, committed to rebooting now.
|
|
*/
|
|
void machine_kexec(struct kimage *image)
|
|
{
|
|
unsigned long page_list[PAGES_NR];
|
|
void *control_page;
|
|
int save_ftrace_enabled;
|
|
|
|
#ifdef CONFIG_KEXEC_JUMP
|
|
if (image->preserve_context)
|
|
save_processor_state();
|
|
#endif
|
|
|
|
save_ftrace_enabled = __ftrace_enabled_save();
|
|
|
|
/* Interrupts aren't acceptable while we reboot */
|
|
local_irq_disable();
|
|
hw_breakpoint_disable();
|
|
|
|
if (image->preserve_context) {
|
|
#ifdef CONFIG_X86_IO_APIC
|
|
/*
|
|
* We need to put APICs in legacy mode so that we can
|
|
* get timer interrupts in second kernel. kexec/kdump
|
|
* paths already have calls to disable_IO_APIC() in
|
|
* one form or other. kexec jump path also need
|
|
* one.
|
|
*/
|
|
disable_IO_APIC();
|
|
#endif
|
|
}
|
|
|
|
control_page = page_address(image->control_code_page) + PAGE_SIZE;
|
|
memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
|
|
|
|
page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
|
|
page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
|
|
page_list[PA_TABLE_PAGE] =
|
|
(unsigned long)__pa(page_address(image->control_code_page));
|
|
|
|
if (image->type == KEXEC_TYPE_DEFAULT)
|
|
page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
|
|
<< PAGE_SHIFT);
|
|
|
|
/*
|
|
* The segment registers are funny things, they have both a
|
|
* visible and an invisible part. Whenever the visible part is
|
|
* set to a specific selector, the invisible part is loaded
|
|
* with from a table in memory. At no other time is the
|
|
* descriptor table in memory accessed.
|
|
*
|
|
* I take advantage of this here by force loading the
|
|
* segments, before I zap the gdt with an invalid value.
|
|
*/
|
|
load_segments();
|
|
/*
|
|
* The gdt & idt are now invalid.
|
|
* If you want to load them you must set up your own idt & gdt.
|
|
*/
|
|
set_gdt(phys_to_virt(0), 0);
|
|
set_idt(phys_to_virt(0), 0);
|
|
|
|
/* now call it */
|
|
image->start = relocate_kernel((unsigned long)image->head,
|
|
(unsigned long)page_list,
|
|
image->start,
|
|
image->preserve_context);
|
|
|
|
#ifdef CONFIG_KEXEC_JUMP
|
|
if (image->preserve_context)
|
|
restore_processor_state();
|
|
#endif
|
|
|
|
__ftrace_enabled_restore(save_ftrace_enabled);
|
|
}
|
|
|
|
void arch_crash_save_vmcoreinfo(void)
|
|
{
|
|
VMCOREINFO_SYMBOL(phys_base);
|
|
VMCOREINFO_SYMBOL(init_level4_pgt);
|
|
|
|
#ifdef CONFIG_NUMA
|
|
VMCOREINFO_SYMBOL(node_data);
|
|
VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
|
|
#endif
|
|
}
|
|
|