linux_dsm_epyc7002/arch/x86/kernel/machine_kexec_64.c
Huang Ying 3ab8352137 kexec jump
This patch provides an enhancement to kexec/kdump.  It implements the
following features:

- Backup/restore memory used by the original kernel before/after
  kexec.

- Save/restore CPU state before/after kexec.

The features of this patch can be used as a general method to call program in
physical mode (paging turning off).  This can be used to call BIOS code under
Linux.

kexec-tools needs to be patched to support kexec jump. The patches and
the precompiled kexec can be download from the following URL:

       source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2
       patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2
       binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10

Usage example of calling some physical mode code and return:

1. Compile and install patched kernel with following options selected:

CONFIG_X86_32=y
CONFIG_KEXEC=y
CONFIG_PM=y
CONFIG_KEXEC_JUMP=y

2. Build patched kexec-tool or download the pre-built one.

3. Build some physical mode executable named such as "phy_mode"

4. Boot kernel compiled in step 1.

5. Load physical mode executable with /sbin/kexec. The shell command
   line can be as follow:

   /sbin/kexec --load-preserve-context --args-none phy_mode

6. Call physical mode executable with following shell command line:

   /sbin/kexec -e

Implementation point:

To support jumping without reserving memory.  One shadow backup page (source
page) is allocated for each page used by kexeced code image (destination
page).  When do kexec_load, the image of kexeced code is loaded into source
pages, and before executing, the destination pages and the source pages are
swapped, so the contents of destination pages are backupped.  Before jumping
to the kexeced code image and after jumping back to the original kernel, the
destination pages and the source pages are swapped too.

C ABI (calling convention) is used as communication protocol between
kernel and called code.

A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to
indicate that the loaded kernel image is used for jumping back.

Now, only the i386 architecture is supported.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Nigel Cunningham <nigel@nigel.suspend2.net>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 12:00:04 -07:00

249 lines
6.0 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>
#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
static u64 kexec_pgd[512] PAGE_ALIGNED;
static u64 kexec_pud0[512] PAGE_ALIGNED;
static u64 kexec_pmd0[512] PAGE_ALIGNED;
static u64 kexec_pte0[512] PAGE_ALIGNED;
static u64 kexec_pud1[512] PAGE_ALIGNED;
static u64 kexec_pmd1[512] PAGE_ALIGNED;
static u64 kexec_pte1[512] PAGE_ALIGNED;
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 int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
pgd_t *level4p;
level4p = (pgd_t *)__va(start_pgtable);
return init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
}
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)
{
return;
}
/*
* 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[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
page_list[PA_PGD] = virt_to_phys(&kexec_pgd);
page_list[VA_PGD] = (unsigned long)kexec_pgd;
page_list[PA_PUD_0] = virt_to_phys(&kexec_pud0);
page_list[VA_PUD_0] = (unsigned long)kexec_pud0;
page_list[PA_PMD_0] = virt_to_phys(&kexec_pmd0);
page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
page_list[PA_PTE_0] = virt_to_phys(&kexec_pte0);
page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
page_list[PA_PUD_1] = virt_to_phys(&kexec_pud1);
page_list[VA_PUD_1] = (unsigned long)kexec_pud1;
page_list[PA_PMD_1] = virt_to_phys(&kexec_pmd1);
page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
page_list[PA_PTE_1] = virt_to_phys(&kexec_pte1);
page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
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
}