linux/arch/x86/kernel/machine_kexec_64.c
Huang Ying f5deb79679 x86: kexec: Use one page table in x86_64 machine_kexec
Impact: reduce kernel BSS size by 7 pages, improve code readability

Two page tables are used in current x86_64 kexec implementation. One
is used to jump from kernel virtual address to identity map address,
the other is used to map all physical memory. In fact, on x86_64,
there is no conflict between kernel virtual address space and physical
memory space, so just one page table is sufficient. The page table
pages used to map control page are dynamically allocated to save
memory if kexec image is not loaded. ASM code used to map control page
is replaced by C code too.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-02-03 18:29:18 -08:00

277 lines
6.3 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/reboot.h>
#include <linux/numa.h>
#include <linux/ftrace.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/io.h>
static void init_level2_page(pmd_t *level2p, unsigned long addr)
{
unsigned long end_addr;
addr &= PAGE_MASK;
end_addr = addr + PUD_SIZE;
while (addr < end_addr) {
set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
addr += PMD_SIZE;
}
}
static int init_level3_page(struct kimage *image, pud_t *level3p,
unsigned long addr, unsigned long last_addr)
{
unsigned long end_addr;
int result;
result = 0;
addr &= PAGE_MASK;
end_addr = addr + PGDIR_SIZE;
while ((addr < last_addr) && (addr < end_addr)) {
struct page *page;
pmd_t *level2p;
page = kimage_alloc_control_pages(image, 0);
if (!page) {
result = -ENOMEM;
goto out;
}
level2p = (pmd_t *)page_address(page);
init_level2_page(level2p, addr);
set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE));
addr += PUD_SIZE;
}
/* clear the unused entries */
while (addr < end_addr) {
pud_clear(level3p++);
addr += PUD_SIZE;
}
out:
return result;
}
static int init_level4_page(struct kimage *image, pgd_t *level4p,
unsigned long addr, unsigned long last_addr)
{
unsigned long end_addr;
int result;
result = 0;
addr &= PAGE_MASK;
end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE);
while ((addr < last_addr) && (addr < end_addr)) {
struct page *page;
pud_t *level3p;
page = kimage_alloc_control_pages(image, 0);
if (!page) {
result = -ENOMEM;
goto out;
}
level3p = (pud_t *)page_address(page);
result = init_level3_page(image, level3p, addr, last_addr);
if (result) {
goto out;
}
set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
addr += PGDIR_SIZE;
}
/* clear the unused entries */
while (addr < end_addr) {
pgd_clear(level4p++);
addr += PGDIR_SIZE;
}
out:
return result;
}
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 int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
pgd_t *level4p;
int result;
level4p = (pgd_t *)__va(start_pgtable);
result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
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;
tracer_disable();
/* Interrupts aren't acceptable while we reboot */
local_irq_disable();
control_page = page_address(image->control_code_page) + PAGE_SIZE;
memcpy(control_page, relocate_kernel, PAGE_SIZE);
page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
page_list[PA_TABLE_PAGE] =
(unsigned long)__pa(page_address(image->control_code_page));
/* 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 */
relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
image->start);
}
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
}