linux-sg2042/arch/x86/kernel/machine_kexec_64.c

357 lines
8.3 KiB
C
Raw Normal View History

/*
* 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 cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#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/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/debugreg.h>
static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
unsigned long addr)
{
pud_t *pud;
pmd_t *pmd;
struct page *page;
int result = -ENOMEM;
addr &= PMD_MASK;
pgd += pgd_index(addr);
if (!pgd_present(*pgd)) {
page = kimage_alloc_control_pages(image, 0);
if (!page)
goto out;
pud = (pud_t *)page_address(page);
clear_page(pud);
set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
}
pud = pud_offset(pgd, addr);
if (!pud_present(*pud)) {
page = kimage_alloc_control_pages(image, 0);
if (!page)
goto out;
pmd = (pmd_t *)page_address(page);
clear_page(pmd);
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
}
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd))
set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
result = 0;
out:
return result;
}
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;
/*
* image->start may be outside 0 ~ max_pfn, for example when
* jump back to original kernel from kexeced kernel
*/
result = init_one_level2_page(image, level4p, image->start);
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.
*/
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 10:45:07 +08:00
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
}