Commit 3ab83521 authored by Huang Ying's avatar Huang Ying Committed by Linus Torvalds
Browse files

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: default avatarHuang Ying <ying.huang@intel.com>
Acked-by: default avatarVivek 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 7fccf032

arch/powerpc/kernel/machine_kexec.c

+1 −1
Original line number Original line Diff line number Diff line
@@ -48,7 +48,7 @@ void machine_kexec_cleanup(struct kimage *image) 
 * Do not allocate memory (or fail in any way) in machine_kexec().

 * Do not allocate memory (or fail in any way) in machine_kexec().

 * We are past the point of no return, committed to rebooting now.

 * We are past the point of no return, committed to rebooting now.

 */

 */

NORET_TYPE void machine_kexec(struct kimage *image)

void machine_kexec(struct kimage *image)

{

{

	if (ppc_md.machine_kexec)

	if (ppc_md.machine_kexec)

		ppc_md.machine_kexec(image);

		ppc_md.machine_kexec(image);

arch/sh/kernel/machine_kexec.c

+1 −1
Original line number Original line Diff line number Diff line
@@ -70,7 +70,7 @@ static void kexec_info(struct kimage *image) 
 * Do not allocate memory (or fail in any way) in machine_kexec().

 * Do not allocate memory (or fail in any way) in machine_kexec().

 * We are past the point of no return, committed to rebooting now.

 * We are past the point of no return, committed to rebooting now.

 */

 */

NORET_TYPE void machine_kexec(struct kimage *image)

void machine_kexec(struct kimage *image)

{

{





	unsigned long page_list;

	unsigned long page_list;

arch/x86/Kconfig

+7 −0
Original line number Original line Diff line number Diff line
@@ -1279,6 +1279,13 @@ config CRASH_DUMP 
	  (CONFIG_RELOCATABLE=y).

	  (CONFIG_RELOCATABLE=y).

	  For more details see Documentation/kdump/kdump.txt

	  For more details see Documentation/kdump/kdump.txt





config KEXEC_JUMP

	bool "kexec jump (EXPERIMENTAL)"

	depends on EXPERIMENTAL

	depends on KEXEC && PM_SLEEP && X86_32

	help

	  Invoke code in physical address mode via KEXEC



config PHYSICAL_START

config PHYSICAL_START

	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)

	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)

	default "0x1000000" if X86_NUMAQ

	default "0x1000000" if X86_NUMAQ

arch/x86/kernel/machine_kexec_32.c

+21 −6
Original line number Original line Diff line number Diff line
@@ -22,6 +22,7 @@ 
#include <asm/cpufeature.h>

#include <asm/cpufeature.h>

#include <asm/desc.h>

#include <asm/desc.h>

#include <asm/system.h>

#include <asm/system.h>

#include <asm/cacheflush.h>





#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))

#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))

static u32 kexec_pgd[1024] PAGE_ALIGNED;

static u32 kexec_pgd[1024] PAGE_ALIGNED;
@@ -85,10 +86,12 @@ static void load_segments(void) 
 * reboot code buffer to allow us to avoid allocations

 * reboot code buffer to allow us to avoid allocations

 * later.

 * later.

 *

 *

 * Currently nothing.

 * Make control page executable.

 */

 */

int machine_kexec_prepare(struct kimage *image)

int machine_kexec_prepare(struct kimage *image)

{

{

	if (nx_enabled)

		set_pages_x(image->control_code_page, 1);

	return 0;

	return 0;

}

}
@@ -98,16 +101,24 @@ int machine_kexec_prepare(struct kimage *image) 
 */

 */

void machine_kexec_cleanup(struct kimage *image)

void machine_kexec_cleanup(struct kimage *image)

{

{

	if (nx_enabled)

		set_pages_nx(image->control_code_page, 1);

}

}





/*

/*

 * Do not allocate memory (or fail in any way) in machine_kexec().

 * Do not allocate memory (or fail in any way) in machine_kexec().

 * We are past the point of no return, committed to rebooting now.

 * We are past the point of no return, committed to rebooting now.

 */

 */

NORET_TYPE void machine_kexec(struct kimage *image)

void machine_kexec(struct kimage *image)

{

{

	unsigned long page_list[PAGES_NR];

	unsigned long page_list[PAGES_NR];

	void *control_page;

	void *control_page;

	asmlinkage unsigned long

		(*relocate_kernel_ptr)(unsigned long indirection_page,

				       unsigned long control_page,

				       unsigned long start_address,

				       unsigned int has_pae,

				       unsigned int preserve_context);





	tracer_disable();

	tracer_disable();
@@ -115,10 +126,11 @@ NORET_TYPE void machine_kexec(struct kimage *image) 
	local_irq_disable();

	local_irq_disable();





	control_page = page_address(image->control_code_page);

	control_page = page_address(image->control_code_page);

	memcpy(control_page, relocate_kernel, PAGE_SIZE);

	memcpy(control_page, relocate_kernel, PAGE_SIZE/2);





	relocate_kernel_ptr = control_page;

	page_list[PA_CONTROL_PAGE] = __pa(control_page);

	page_list[PA_CONTROL_PAGE] = __pa(control_page);

	page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;

	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;

	page_list[PA_PGD] = __pa(kexec_pgd);

	page_list[PA_PGD] = __pa(kexec_pgd);

	page_list[VA_PGD] = (unsigned long)kexec_pgd;

	page_list[VA_PGD] = (unsigned long)kexec_pgd;

#ifdef CONFIG_X86_PAE

#ifdef CONFIG_X86_PAE
@@ -131,6 +143,7 @@ NORET_TYPE void machine_kexec(struct kimage *image) 
	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;

	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;

	page_list[PA_PTE_1] = __pa(kexec_pte1);

	page_list[PA_PTE_1] = __pa(kexec_pte1);

	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;

	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;

	page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT);





	/* The segment registers are funny things, they have both a

	/* The segment registers are funny things, they have both a

	 * visible and an invisible part.  Whenever the visible part is

	 * visible and an invisible part.  Whenever the visible part is
@@ -149,8 +162,10 @@ NORET_TYPE void machine_kexec(struct kimage *image) 
	set_idt(phys_to_virt(0),0);

	set_idt(phys_to_virt(0),0);





	/* now call it */

	/* now call it */

	relocate_kernel((unsigned long)image->head, (unsigned long)page_list,

	image->start = relocate_kernel_ptr((unsigned long)image->head,

			image->start, cpu_has_pae);

					   (unsigned long)page_list,

					   image->start, cpu_has_pae,

					   image->preserve_context);

}

}





void arch_crash_save_vmcoreinfo(void)

void arch_crash_save_vmcoreinfo(void)

arch/x86/kernel/machine_kexec_64.c

+1 −1
Original line number Original line Diff line number Diff line
@@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage *image) 
 * Do not allocate memory (or fail in any way) in machine_kexec().

 * Do not allocate memory (or fail in any way) in machine_kexec().

 * We are past the point of no return, committed to rebooting now.

 * We are past the point of no return, committed to rebooting now.

 */

 */

NORET_TYPE void machine_kexec(struct kimage *image)

void machine_kexec(struct kimage *image)

{

{

	unsigned long page_list[PAGES_NR];

	unsigned long page_list[PAGES_NR];

	void *control_page;

	void *control_page;

CRA Git | Maintained and supported by SUSTech CRA and CCSE