mirror of
https://github.com/torvalds/linux.git
synced 2024-12-21 18:42:44 +00:00
89081d17f7
This patch implements devices state save/restore before after kexec. This patch together with features in kexec_jump patch can be used for following: - A simple hibernation implementation without ACPI support. You can kexec a hibernating kernel, save the memory image of original system and shutdown the system. When resuming, you restore the memory image of original system via ordinary kexec load then jump back. - Kernel/system debug through making system snapshot. You can make system snapshot, jump back, do some thing and make another system snapshot. - Cooperative multi-kernel/system. With kexec jump, you can switch between several kernels/systems quickly without boot process except the first time. This appears like swap a whole kernel/system out/in. - A general method to call program in physical mode (paging turning off). This can be used to invoke BIOS code under Linux. The following user-space tools can be used with kexec jump: - 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 - makedumpfile with patches are used as memory image saving tool, it can exclude free pages from original kernel memory image file. The patches and the precompiled makedumpfile can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-src_cvs_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-patches_cvs_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile_cvs_kh10 - An initramfs image can be used as the root file system of kexeced kernel. An initramfs image built with "BuildRoot" can be downloaded from the following URL: initramfs image: http://khibernation.sourceforge.net/download/release_v10/initramfs/rootfs_cvs_kh10.gz All user space tools above are included in the initramfs image. Usage example of simple hibernation: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_RELOCATABLE=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_PM=y CONFIG_HIBERNATION=y CONFIG_KEXEC_JUMP=y 2. Build an initramfs image contains kexec-tool and makedumpfile, or download the pre-built initramfs image, called rootfs.gz in following text. 3. Prepare a partition to save memory image of original kernel, called hibernating partition in following text. 4. Boot kernel compiled in step 1 (kernel A). 5. In the kernel A, load kernel compiled in step 1 (kernel B) with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context /boot/bzImage --mem-min=0x100000 --mem-max=0xffffff --initrd=rootfs.gz 6. Boot the kernel B with following shell command line: /sbin/kexec -e 7. The kernel B will boot as normal kexec. In kernel B the memory image of kernel A can be saved into hibernating partition as follow: jump_back_entry=`cat /proc/cmdline | tr ' ' '\n' | grep kexec_jump_back_entry | cut -d '='` echo $jump_back_entry > kexec_jump_back_entry cp /proc/vmcore dump.elf Then you can shutdown the machine as normal. 8. Boot kernel compiled in step 1 (kernel C). Use the rootfs.gz as root file system. 9. In kernel C, load the memory image of kernel A as follow: /sbin/kexec -l --args-none --entry=`cat kexec_jump_back_entry` dump.elf 10. Jump back to the kernel A as follow: /sbin/kexec -e Then, kernel A is resumed. Implementation point: To support jumping between two kernels, before jumping to (executing) the new kernel and jumping back to the original kernel, the devices are put into quiescent state, and the state of devices and CPU is saved. After jumping back from kexeced kernel and jumping to the new kernel, the state of devices and CPU are restored accordingly. The devices/CPU state save/restore code of software suspend is called to implement corresponding function. Known issues: - Because the segment number supported by sys_kexec_load is limited, hibernation image with many segments may not be load. This is planned to be eliminated by adding a new flag to sys_kexec_load to make a image can be loaded with multiple sys_kexec_load invoking. 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>
226 lines
6.4 KiB
C
226 lines
6.4 KiB
C
#include <linux/suspend.h>
|
|
#include <linux/suspend_ioctls.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/freezer.h>
|
|
|
|
struct swsusp_info {
|
|
struct new_utsname uts;
|
|
u32 version_code;
|
|
unsigned long num_physpages;
|
|
int cpus;
|
|
unsigned long image_pages;
|
|
unsigned long pages;
|
|
unsigned long size;
|
|
} __attribute__((aligned(PAGE_SIZE)));
|
|
|
|
#ifdef CONFIG_HIBERNATION
|
|
#ifdef CONFIG_ARCH_HIBERNATION_HEADER
|
|
/* Maximum size of architecture specific data in a hibernation header */
|
|
#define MAX_ARCH_HEADER_SIZE (sizeof(struct new_utsname) + 4)
|
|
|
|
extern int arch_hibernation_header_save(void *addr, unsigned int max_size);
|
|
extern int arch_hibernation_header_restore(void *addr);
|
|
|
|
static inline int init_header_complete(struct swsusp_info *info)
|
|
{
|
|
return arch_hibernation_header_save(info, MAX_ARCH_HEADER_SIZE);
|
|
}
|
|
|
|
static inline char *check_image_kernel(struct swsusp_info *info)
|
|
{
|
|
return arch_hibernation_header_restore(info) ?
|
|
"architecture specific data" : NULL;
|
|
}
|
|
#endif /* CONFIG_ARCH_HIBERNATION_HEADER */
|
|
|
|
/*
|
|
* Keep some memory free so that I/O operations can succeed without paging
|
|
* [Might this be more than 4 MB?]
|
|
*/
|
|
#define PAGES_FOR_IO ((4096 * 1024) >> PAGE_SHIFT)
|
|
|
|
/*
|
|
* Keep 1 MB of memory free so that device drivers can allocate some pages in
|
|
* their .suspend() routines without breaking the suspend to disk.
|
|
*/
|
|
#define SPARE_PAGES ((1024 * 1024) >> PAGE_SHIFT)
|
|
|
|
/* kernel/power/disk.c */
|
|
extern int hibernation_snapshot(int platform_mode);
|
|
extern int hibernation_restore(int platform_mode);
|
|
extern int hibernation_platform_enter(void);
|
|
#endif
|
|
|
|
extern int pfn_is_nosave(unsigned long);
|
|
|
|
#define power_attr(_name) \
|
|
static struct kobj_attribute _name##_attr = { \
|
|
.attr = { \
|
|
.name = __stringify(_name), \
|
|
.mode = 0644, \
|
|
}, \
|
|
.show = _name##_show, \
|
|
.store = _name##_store, \
|
|
}
|
|
|
|
/* Preferred image size in bytes (default 500 MB) */
|
|
extern unsigned long image_size;
|
|
extern int in_suspend;
|
|
extern dev_t swsusp_resume_device;
|
|
extern sector_t swsusp_resume_block;
|
|
|
|
extern asmlinkage int swsusp_arch_suspend(void);
|
|
extern asmlinkage int swsusp_arch_resume(void);
|
|
|
|
extern int create_basic_memory_bitmaps(void);
|
|
extern void free_basic_memory_bitmaps(void);
|
|
extern unsigned int count_data_pages(void);
|
|
|
|
/**
|
|
* Auxiliary structure used for reading the snapshot image data and
|
|
* metadata from and writing them to the list of page backup entries
|
|
* (PBEs) which is the main data structure of swsusp.
|
|
*
|
|
* Using struct snapshot_handle we can transfer the image, including its
|
|
* metadata, as a continuous sequence of bytes with the help of
|
|
* snapshot_read_next() and snapshot_write_next().
|
|
*
|
|
* The code that writes the image to a storage or transfers it to
|
|
* the user land is required to use snapshot_read_next() for this
|
|
* purpose and it should not make any assumptions regarding the internal
|
|
* structure of the image. Similarly, the code that reads the image from
|
|
* a storage or transfers it from the user land is required to use
|
|
* snapshot_write_next().
|
|
*
|
|
* This may allow us to change the internal structure of the image
|
|
* in the future with considerably less effort.
|
|
*/
|
|
|
|
struct snapshot_handle {
|
|
loff_t offset; /* number of the last byte ready for reading
|
|
* or writing in the sequence
|
|
*/
|
|
unsigned int cur; /* number of the block of PAGE_SIZE bytes the
|
|
* next operation will refer to (ie. current)
|
|
*/
|
|
unsigned int cur_offset; /* offset with respect to the current
|
|
* block (for the next operation)
|
|
*/
|
|
unsigned int prev; /* number of the block of PAGE_SIZE bytes that
|
|
* was the current one previously
|
|
*/
|
|
void *buffer; /* address of the block to read from
|
|
* or write to
|
|
*/
|
|
unsigned int buf_offset; /* location to read from or write to,
|
|
* given as a displacement from 'buffer'
|
|
*/
|
|
int sync_read; /* Set to one to notify the caller of
|
|
* snapshot_write_next() that it may
|
|
* need to call wait_on_bio_chain()
|
|
*/
|
|
};
|
|
|
|
/* This macro returns the address from/to which the caller of
|
|
* snapshot_read_next()/snapshot_write_next() is allowed to
|
|
* read/write data after the function returns
|
|
*/
|
|
#define data_of(handle) ((handle).buffer + (handle).buf_offset)
|
|
|
|
extern unsigned int snapshot_additional_pages(struct zone *zone);
|
|
extern unsigned long snapshot_get_image_size(void);
|
|
extern int snapshot_read_next(struct snapshot_handle *handle, size_t count);
|
|
extern int snapshot_write_next(struct snapshot_handle *handle, size_t count);
|
|
extern void snapshot_write_finalize(struct snapshot_handle *handle);
|
|
extern int snapshot_image_loaded(struct snapshot_handle *handle);
|
|
|
|
/* If unset, the snapshot device cannot be open. */
|
|
extern atomic_t snapshot_device_available;
|
|
|
|
extern sector_t alloc_swapdev_block(int swap);
|
|
extern void free_all_swap_pages(int swap);
|
|
extern int swsusp_swap_in_use(void);
|
|
|
|
/*
|
|
* Flags that can be passed from the hibernatig hernel to the "boot" kernel in
|
|
* the image header.
|
|
*/
|
|
#define SF_PLATFORM_MODE 1
|
|
|
|
/* kernel/power/disk.c */
|
|
extern int swsusp_check(void);
|
|
extern int swsusp_shrink_memory(void);
|
|
extern void swsusp_free(void);
|
|
extern int swsusp_read(unsigned int *flags_p);
|
|
extern int swsusp_write(unsigned int flags);
|
|
extern void swsusp_close(void);
|
|
|
|
struct timeval;
|
|
/* kernel/power/swsusp.c */
|
|
extern void swsusp_show_speed(struct timeval *, struct timeval *,
|
|
unsigned int, char *);
|
|
|
|
#ifdef CONFIG_SUSPEND
|
|
/* kernel/power/main.c */
|
|
extern int suspend_devices_and_enter(suspend_state_t state);
|
|
#else /* !CONFIG_SUSPEND */
|
|
static inline int suspend_devices_and_enter(suspend_state_t state)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
#endif /* !CONFIG_SUSPEND */
|
|
|
|
#ifdef CONFIG_PM_SLEEP
|
|
/* kernel/power/main.c */
|
|
extern int pm_notifier_call_chain(unsigned long val);
|
|
#endif
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
unsigned int count_highmem_pages(void);
|
|
int restore_highmem(void);
|
|
#else
|
|
static inline unsigned int count_highmem_pages(void) { return 0; }
|
|
static inline int restore_highmem(void) { return 0; }
|
|
#endif
|
|
|
|
/*
|
|
* Suspend test levels
|
|
*/
|
|
enum {
|
|
/* keep first */
|
|
TEST_NONE,
|
|
TEST_CORE,
|
|
TEST_CPUS,
|
|
TEST_PLATFORM,
|
|
TEST_DEVICES,
|
|
TEST_FREEZER,
|
|
/* keep last */
|
|
__TEST_AFTER_LAST
|
|
};
|
|
|
|
#define TEST_FIRST TEST_NONE
|
|
#define TEST_MAX (__TEST_AFTER_LAST - 1)
|
|
|
|
extern int pm_test_level;
|
|
|
|
#ifdef CONFIG_SUSPEND_FREEZER
|
|
static inline int suspend_freeze_processes(void)
|
|
{
|
|
return freeze_processes();
|
|
}
|
|
|
|
static inline void suspend_thaw_processes(void)
|
|
{
|
|
thaw_processes();
|
|
}
|
|
#else
|
|
static inline int suspend_freeze_processes(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void suspend_thaw_processes(void)
|
|
{
|
|
}
|
|
#endif
|