3dd083255d
The following patch makes swsusp avoid the possible temporary corruption of page translation tables during resume on x86-64. This is achieved by creating a copy of the relevant page tables that will not be modified by swsusp and can be safely used by it on resume. The problem is that during resume on x86-64 swsusp may temporarily corrupt the page tables used for the direct mapping of RAM. If that happens, a page fault occurs and cannot be handled properly, which leads to the solid hang of the affected system. This leads to the loss of the system's state from before suspend and may result in the loss of data or the corruption of filesystems, so it is a serious issue. Also, it appears to happen quite often (for me, as often as 50% of the time). The problem is related to the fact that (at least) one of the PMD entries used in the direct memory mapping (starting at PAGE_OFFSET) points to a page table the physical address of which is much greater than the physical address of the PMD entry itself. Moreover, unfortunately, the physical address of the page table before suspend (i.e. the one stored in the suspend image) happens to be different to the physical address of the corresponding page table used during resume (i.e. the one that is valid right before swsusp_arch_resume() in arch/x86_64/kernel/suspend_asm.S is executed). Thus while the image is restored, the "offending" PMD entry gets overwritten, so it does not point to the right physical address any more (i.e. there's no page table at the address pointed to by it, because it points to the address the page table has been at during suspend). Consequently, if the PMD entry is used later on, and it _is_ used in the process of copying the image pages, a page fault occurs, but it cannot be handled in the normal way and the system hangs. In principle we can call create_resume_mapping() from swsusp_arch_resume() (ie. from suspend_asm.S), but then the memory allocations in create_resume_mapping(), resume_pud_mapping(), and resume_pmd_mapping() must be made carefully so that we use _only_ NosaveFree pages in them (the other pages are overwritten by the loop in swsusp_arch_resume()). Additionally, we are in atomic context at that time, so we cannot use GFP_KERNEL. Moreover, if one of the allocations fails, we should free all of the allocated pages, so we need to trace them somehow. All of this is done in the appended patch, except that the functions populating the page tables are located in arch/x86_64/kernel/suspend.c rather than in init.c. It may be done in a more elegan way in the future, with the help of some swsusp patches that are in the works now. [AK: move some externs into headers, renamed a function] Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
78 lines
1.9 KiB
C
78 lines
1.9 KiB
C
#ifndef _LINUX_SWSUSP_H
|
|
#define _LINUX_SWSUSP_H
|
|
|
|
#if defined(CONFIG_X86) || defined(CONFIG_FRV) || defined(CONFIG_PPC32)
|
|
#include <asm/suspend.h>
|
|
#endif
|
|
#include <linux/swap.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/config.h>
|
|
#include <linux/init.h>
|
|
#include <linux/pm.h>
|
|
|
|
/* page backup entry */
|
|
typedef struct pbe {
|
|
unsigned long address; /* address of the copy */
|
|
unsigned long orig_address; /* original address of page */
|
|
swp_entry_t swap_address;
|
|
|
|
struct pbe *next; /* also used as scratch space at
|
|
* end of page (see link, diskpage)
|
|
*/
|
|
} suspend_pagedir_t;
|
|
|
|
#define for_each_pbe(pbe, pblist) \
|
|
for (pbe = pblist ; pbe ; pbe = pbe->next)
|
|
|
|
#define PBES_PER_PAGE (PAGE_SIZE/sizeof(struct pbe))
|
|
#define PB_PAGE_SKIP (PBES_PER_PAGE-1)
|
|
|
|
#define for_each_pb_page(pbe, pblist) \
|
|
for (pbe = pblist ; pbe ; pbe = (pbe+PB_PAGE_SKIP)->next)
|
|
|
|
|
|
#define SWAP_FILENAME_MAXLENGTH 32
|
|
|
|
|
|
extern dev_t swsusp_resume_device;
|
|
|
|
/* mm/vmscan.c */
|
|
extern int shrink_mem(void);
|
|
|
|
/* mm/page_alloc.c */
|
|
extern void drain_local_pages(void);
|
|
extern void mark_free_pages(struct zone *zone);
|
|
|
|
#ifdef CONFIG_PM
|
|
/* kernel/power/swsusp.c */
|
|
extern int software_suspend(void);
|
|
|
|
extern int pm_prepare_console(void);
|
|
extern void pm_restore_console(void);
|
|
|
|
#else
|
|
static inline int software_suspend(void)
|
|
{
|
|
printk("Warning: fake suspend called\n");
|
|
return -EPERM;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SUSPEND_SMP
|
|
extern void disable_nonboot_cpus(void);
|
|
extern void enable_nonboot_cpus(void);
|
|
#else
|
|
static inline void disable_nonboot_cpus(void) {}
|
|
static inline void enable_nonboot_cpus(void) {}
|
|
#endif
|
|
|
|
void save_processor_state(void);
|
|
void restore_processor_state(void);
|
|
struct saved_context;
|
|
void __save_processor_state(struct saved_context *ctxt);
|
|
void __restore_processor_state(struct saved_context *ctxt);
|
|
extern unsigned long get_usable_page(unsigned gfp_mask);
|
|
extern void free_eaten_memory(void);
|
|
|
|
#endif /* _LINUX_SWSUSP_H */
|