/*
* linux/kernel/power/swsusp.c
*
- * This file is to realize architecture-independent
- * machine suspend feature using pretty near only high-level routines
+ * This file provides code to write suspend image to swap and read it back.
*
* Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
- * Copyright (C) 1998,2001-2004 Pavel Machek <pavel@suse.cz>
+ * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
*
* This file is released under the GPLv2.
*
* I'd like to thank the following people for their work:
- *
+ *
* Pavel Machek <pavel@ucw.cz>:
* Modifications, defectiveness pointing, being with me at the very beginning,
* suspend to swap space, stop all tasks. Port to 2.4.18-ac and 2.5.17.
*
- * Steve Doddi <dirk@loth.demon.co.uk>:
+ * Steve Doddi <dirk@loth.demon.co.uk>:
* Support the possibility of hardware state restoring.
*
* Raph <grey.havens@earthling.net>:
* Alex Badea <vampire@go.ro>:
* Fixed runaway init
*
+ * Rafael J. Wysocki <rjw@sisk.pl>
+ * Added the swap map data structure and reworked the handling of swap
+ *
* More state savers are welcome. Especially for the scsi layer...
*
* For TODOs,FIXMEs also look in Documentation/power/swsusp.txt
#include <linux/utsname.h>
#include <linux/version.h>
#include <linux/delay.h>
-#include <linux/reboot.h>
#include <linux/bitops.h>
-#include <linux/vt_kern.h>
-#include <linux/kbd_kern.h>
-#include <linux/keyboard.h>
#include <linux/spinlock.h>
#include <linux/genhd.h>
#include <linux/kernel.h>
#include <linux/swapops.h>
#include <linux/bootmem.h>
#include <linux/syscalls.h>
-#include <linux/console.h>
#include <linux/highmem.h>
#include <linux/bio.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
#include <asm/io.h>
#include "power.h"
-/* References to section boundaries */
-extern char __nosave_begin, __nosave_end;
-
-extern int is_head_of_free_region(struct page *);
+/*
+ * Preferred image size in bytes (tunable via /sys/power/image_size).
+ * When it is set to N, swsusp will do its best to ensure the image
+ * size will not exceed N bytes, but if that is impossible, it will
+ * try to create the smallest image possible.
+ */
+unsigned long image_size = 500 * 1024 * 1024;
-/* Variables to be preserved over suspend */
-int pagedir_order_check;
-int nr_copy_pages_check;
+#ifdef CONFIG_HIGHMEM
+unsigned int count_highmem_pages(void);
+int save_highmem(void);
+int restore_highmem(void);
+#else
+static int save_highmem(void) { return 0; }
+static int restore_highmem(void) { return 0; }
+static unsigned int count_highmem_pages(void) { return 0; }
+#endif
extern char resume_file[];
-static dev_t resume_device;
-/* Local variables that should not be affected by save */
-unsigned int nr_copy_pages __nosavedata = 0;
-
-/* Suspend pagedir is allocated before final copy, therefore it
- must be freed after resume
-
- Warning: this is evil. There are actually two pagedirs at time of
- resume. One is "pagedir_save", which is empty frame allocated at
- time of suspend, that must be freed. Second is "pagedir_nosave",
- allocated at time of resume, that travels through memory not to
- collide with anything.
-
- Warning: this is even more evil than it seems. Pagedirs this file
- talks about are completely different from page directories used by
- MMU hardware.
- */
-suspend_pagedir_t *pagedir_nosave __nosavedata = NULL;
-static suspend_pagedir_t *pagedir_save;
-static int pagedir_order __nosavedata = 0;
#define SWSUSP_SIG "S1SUSPEND"
-struct swsusp_header {
+static struct swsusp_header {
char reserved[PAGE_SIZE - 20 - sizeof(swp_entry_t)];
- swp_entry_t swsusp_info;
+ swp_entry_t image;
char orig_sig[10];
char sig[10];
} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
-struct swsusp_info swsusp_info;
-
-/*
- * XXX: We try to keep some more pages free so that I/O operations succeed
- * without paging. Might this be more?
- */
-#define PAGES_FOR_IO 512
+static struct swsusp_info swsusp_info;
/*
* Saving part...
*/
-/* We memorize in swapfile_used what swap devices are used for suspension */
-#define SWAPFILE_UNUSED 0
-#define SWAPFILE_SUSPEND 1 /* This is the suspending device */
-#define SWAPFILE_IGNORED 2 /* Those are other swap devices ignored for suspension */
-
-static unsigned short swapfile_used[MAX_SWAPFILES];
-static unsigned short root_swap;
+static unsigned short root_swap = 0xffff;
-static int mark_swapfiles(swp_entry_t prev)
+static int mark_swapfiles(swp_entry_t start)
{
int error;
- rw_swap_page_sync(READ,
+ rw_swap_page_sync(READ,
swp_entry(root_swap, 0),
virt_to_page((unsigned long)&swsusp_header));
if (!memcmp("SWAP-SPACE",swsusp_header.sig, 10) ||
!memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
- swsusp_header.swsusp_info = prev;
- error = rw_swap_page_sync(WRITE,
+ swsusp_header.image = start;
+ error = rw_swap_page_sync(WRITE,
swp_entry(root_swap, 0),
virt_to_page((unsigned long)
&swsusp_header));
* devfs, since the resume code can only recognize the form /dev/hda4,
* but the suspend code would see the long name.)
*/
-static int is_resume_device(const struct swap_info_struct *swap_info)
+static inline int is_resume_device(const struct swap_info_struct *swap_info)
{
struct file *file = swap_info->swap_file;
struct inode *inode = file->f_dentry->d_inode;
return S_ISBLK(inode->i_mode) &&
- resume_device == MKDEV(imajor(inode), iminor(inode));
+ swsusp_resume_device == MKDEV(imajor(inode), iminor(inode));
}
-int swsusp_swap_check(void) /* This is called before saving image */
-{
- int i, len;
-
- len=strlen(resume_file);
- root_swap = 0xFFFF;
-
- swap_list_lock();
- for(i=0; i<MAX_SWAPFILES; i++) {
- if (swap_info[i].flags == 0) {
- swapfile_used[i]=SWAPFILE_UNUSED;
- } else {
- if(!len) {
- printk(KERN_WARNING "resume= option should be used to set suspend device" );
- if(root_swap == 0xFFFF) {
- swapfile_used[i] = SWAPFILE_SUSPEND;
- root_swap = i;
- } else
- swapfile_used[i] = SWAPFILE_IGNORED;
- } else {
- /* we ignore all swap devices that are not the resume_file */
- if (is_resume_device(&swap_info[i])) {
- swapfile_used[i] = SWAPFILE_SUSPEND;
- root_swap = i;
- } else {
- swapfile_used[i] = SWAPFILE_IGNORED;
- }
- }
- }
- }
- swap_list_unlock();
- return (root_swap != 0xffff) ? 0 : -ENODEV;
-}
-
-/**
- * This is called after saving image so modification
- * will be lost after resume... and that's what we want.
- * we make the device unusable. A new call to
- * lock_swapdevices can unlock the devices.
- */
-static void lock_swapdevices(void)
+static int swsusp_swap_check(void) /* This is called before saving image */
{
int i;
- swap_list_lock();
- for(i = 0; i< MAX_SWAPFILES; i++)
- if(swapfile_used[i] == SWAPFILE_IGNORED) {
- swap_info[i].flags ^= 0xFF;
+ spin_lock(&swap_lock);
+ for (i = 0; i < MAX_SWAPFILES; i++) {
+ if (!(swap_info[i].flags & SWP_WRITEOK))
+ continue;
+ if (!swsusp_resume_device || is_resume_device(swap_info + i)) {
+ spin_unlock(&swap_lock);
+ root_swap = i;
+ return 0;
}
- swap_list_unlock();
+ }
+ spin_unlock(&swap_lock);
+ return -ENODEV;
}
-
-
/**
- * write_swap_page - Write one page to a fresh swap location.
+ * write_page - Write one page to a fresh swap location.
* @addr: Address we're writing.
* @loc: Place to store the entry we used.
*
* Allocate a new swap entry and 'sync' it. Note we discard -EIO
- * errors. That is an artifact left over from swsusp. It did not
+ * errors. That is an artifact left over from swsusp. It did not
* check the return of rw_swap_page_sync() at all, since most pages
* written back to swap would return -EIO.
* This is a partial improvement, since we will at least return other
* errors, though we need to eventually fix the damn code.
*/
-
-static int write_page(unsigned long addr, swp_entry_t * loc)
+static int write_page(unsigned long addr, swp_entry_t *loc)
{
swp_entry_t entry;
- int error = 0;
+ int error = -ENOSPC;
- entry = get_swap_page();
- if (swp_offset(entry) &&
- swapfile_used[swp_type(entry)] == SWAPFILE_SUSPEND) {
- error = rw_swap_page_sync(WRITE, entry,
- virt_to_page(addr));
- if (error == -EIO)
- error = 0;
- if (!error)
+ entry = get_swap_page_of_type(root_swap);
+ if (swp_offset(entry)) {
+ error = rw_swap_page_sync(WRITE, entry, virt_to_page(addr));
+ if (!error || error == -EIO)
*loc = entry;
- } else
- error = -ENOSPC;
+ }
return error;
}
-
/**
- * data_free - Free the swap entries used by the saved image.
+ * Swap map-handling functions
*
- * Walk the list of used swap entries and free each one.
- * This is only used for cleanup when suspend fails.
- */
-
-static void data_free(void)
-{
- swp_entry_t entry;
- int i;
-
- for (i = 0; i < nr_copy_pages; i++) {
- entry = (pagedir_nosave + i)->swap_address;
- if (entry.val)
- swap_free(entry);
- else
- break;
- (pagedir_nosave + i)->swap_address = (swp_entry_t){0};
- }
-}
-
-
-/**
- * data_write - Write saved image to swap.
+ * The swap map is a data structure used for keeping track of each page
+ * written to the swap. It consists of many swap_map_page structures
+ * that contain each an array of MAP_PAGE_SIZE swap entries.
+ * These structures are linked together with the help of either the
+ * .next (in memory) or the .next_swap (in swap) member.
+ *
+ * The swap map is created during suspend. At that time we need to keep
+ * it in memory, because we have to free all of the allocated swap
+ * entries if an error occurs. The memory needed is preallocated
+ * so that we know in advance if there's enough of it.
+ *
+ * The first swap_map_page structure is filled with the swap entries that
+ * correspond to the first MAP_PAGE_SIZE data pages written to swap and
+ * so on. After the all of the data pages have been written, the order
+ * of the swap_map_page structures in the map is reversed so that they
+ * can be read from swap in the original order. This causes the data
+ * pages to be loaded in exactly the same order in which they have been
+ * saved.
*
- * Walk the list of pages in the image and sync each one to swap.
+ * During resume we only need to use one swap_map_page structure
+ * at a time, which means that we only need to use two memory pages for
+ * reading the image - one for reading the swap_map_page structures
+ * and the second for reading the data pages from swap.
*/
-static int data_write(void)
-{
- int error = 0;
- int i;
+#define MAP_PAGE_SIZE ((PAGE_SIZE - sizeof(swp_entry_t) - sizeof(void *)) \
+ / sizeof(swp_entry_t))
- printk( "Writing data to swap (%d pages): ", nr_copy_pages );
- for (i = 0; i < nr_copy_pages && !error; i++) {
- if (!(i%100))
- printk( "." );
- error = write_page((pagedir_nosave+i)->address,
- &((pagedir_nosave+i)->swap_address));
- }
- printk(" %d Pages done.\n",i);
- return error;
-}
-
-static void dump_info(void)
-{
- pr_debug(" swsusp: Version: %u\n",swsusp_info.version_code);
- pr_debug(" swsusp: Num Pages: %ld\n",swsusp_info.num_physpages);
- pr_debug(" swsusp: UTS Sys: %s\n",swsusp_info.uts.sysname);
- pr_debug(" swsusp: UTS Node: %s\n",swsusp_info.uts.nodename);
- pr_debug(" swsusp: UTS Release: %s\n",swsusp_info.uts.release);
- pr_debug(" swsusp: UTS Version: %s\n",swsusp_info.uts.version);
- pr_debug(" swsusp: UTS Machine: %s\n",swsusp_info.uts.machine);
- pr_debug(" swsusp: UTS Domain: %s\n",swsusp_info.uts.domainname);
- pr_debug(" swsusp: CPUs: %d\n",swsusp_info.cpus);
- pr_debug(" swsusp: Image: %ld Pages\n",swsusp_info.image_pages);
- pr_debug(" swsusp: Pagedir: %ld Pages\n",swsusp_info.pagedir_pages);
-}
+struct swap_map_page {
+ swp_entry_t entries[MAP_PAGE_SIZE];
+ swp_entry_t next_swap;
+ struct swap_map_page *next;
+};
-static void init_header(void)
+static inline void free_swap_map(struct swap_map_page *swap_map)
{
- memset(&swsusp_info,0,sizeof(swsusp_info));
- swsusp_info.version_code = LINUX_VERSION_CODE;
- swsusp_info.num_physpages = num_physpages;
- memcpy(&swsusp_info.uts,&system_utsname,sizeof(system_utsname));
+ struct swap_map_page *swp;
- swsusp_info.suspend_pagedir = pagedir_nosave;
- swsusp_info.cpus = num_online_cpus();
- swsusp_info.image_pages = nr_copy_pages;
- dump_info();
+ while (swap_map) {
+ swp = swap_map->next;
+ free_page((unsigned long)swap_map);
+ swap_map = swp;
+ }
}
-static int close_swap(void)
+static struct swap_map_page *alloc_swap_map(unsigned int nr_pages)
{
- swp_entry_t entry;
- int error;
-
- error = write_page((unsigned long)&swsusp_info,&entry);
- if (!error) {
- printk( "S" );
- error = mark_swapfiles(entry);
- printk( "|\n" );
+ struct swap_map_page *swap_map, *swp;
+ unsigned n = 0;
+
+ if (!nr_pages)
+ return NULL;
+
+ pr_debug("alloc_swap_map(): nr_pages = %d\n", nr_pages);
+ swap_map = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+ swp = swap_map;
+ for (n = MAP_PAGE_SIZE; n < nr_pages; n += MAP_PAGE_SIZE) {
+ swp->next = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+ swp = swp->next;
+ if (!swp) {
+ free_swap_map(swap_map);
+ return NULL;
+ }
}
- return error;
+ return swap_map;
}
/**
- * free_pagedir_entries - Free pages used by the page directory.
- *
- * This is used during suspend for error recovery.
+ * reverse_swap_map - reverse the order of pages in the swap map
+ * @swap_map
*/
-static void free_pagedir_entries(void)
+static inline struct swap_map_page *reverse_swap_map(struct swap_map_page *swap_map)
{
- int i;
-
- for (i = 0; i < swsusp_info.pagedir_pages; i++)
- swap_free(swsusp_info.pagedir[i]);
+ struct swap_map_page *prev, *next;
+
+ prev = NULL;
+ while (swap_map) {
+ next = swap_map->next;
+ swap_map->next = prev;
+ prev = swap_map;
+ swap_map = next;
+ }
+ return prev;
}
-
/**
- * write_pagedir - Write the array of pages holding the page directory.
- * @last: Last swap entry we write (needed for header).
+ * free_swap_map_entries - free the swap entries allocated to store
+ * the swap map @swap_map (this is only called in case of an error)
*/
-
-static int write_pagedir(void)
+static inline void free_swap_map_entries(struct swap_map_page *swap_map)
{
- unsigned long addr = (unsigned long)pagedir_nosave;
- int error = 0;
- int n = SUSPEND_PD_PAGES(nr_copy_pages);
- int i;
-
- swsusp_info.pagedir_pages = n;
- printk( "Writing pagedir (%d pages)\n", n);
- for (i = 0; i < n && !error; i++, addr += PAGE_SIZE)
- error = write_page(addr, &swsusp_info.pagedir[i]);
- return error;
+ while (swap_map) {
+ if (swap_map->next_swap.val)
+ swap_free(swap_map->next_swap);
+ swap_map = swap_map->next;
+ }
}
/**
- * write_suspend_image - Write entire image and metadata.
- *
+ * save_swap_map - save the swap map used for tracing the data pages
+ * stored in the swap
*/
-static int write_suspend_image(void)
+static int save_swap_map(struct swap_map_page *swap_map, swp_entry_t *start)
{
+ swp_entry_t entry = (swp_entry_t){0};
int error;
- init_header();
- if ((error = data_write()))
- goto FreeData;
-
- if ((error = write_pagedir()))
- goto FreePagedir;
-
- if ((error = close_swap()))
- goto FreePagedir;
- Done:
- return error;
- FreePagedir:
- free_pagedir_entries();
- FreeData:
- data_free();
- goto Done;
-}
-
-
-#ifdef CONFIG_HIGHMEM
-struct highmem_page {
- char *data;
- struct page *page;
- struct highmem_page *next;
-};
-
-struct highmem_page *highmem_copy = NULL;
-
-static int save_highmem_zone(struct zone *zone)
-{
- unsigned long zone_pfn;
- for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
- struct page *page;
- struct highmem_page *save;
- void *kaddr;
- unsigned long pfn = zone_pfn + zone->zone_start_pfn;
- int chunk_size;
-
- if (!(pfn%1000))
- printk(".");
- if (!pfn_valid(pfn))
- continue;
- page = pfn_to_page(pfn);
- /*
- * This condition results from rvmalloc() sans vmalloc_32()
- * and architectural memory reservations. This should be
- * corrected eventually when the cases giving rise to this
- * are better understood.
- */
- if (PageReserved(page)) {
- printk("highmem reserved page?!\n");
- continue;
- }
- if ((chunk_size = is_head_of_free_region(page))) {
- pfn += chunk_size - 1;
- zone_pfn += chunk_size - 1;
- continue;
- }
- save = kmalloc(sizeof(struct highmem_page), GFP_ATOMIC);
- if (!save)
- return -ENOMEM;
- save->next = highmem_copy;
- save->page = page;
- save->data = (void *) get_zeroed_page(GFP_ATOMIC);
- if (!save->data) {
- kfree(save);
- return -ENOMEM;
- }
- kaddr = kmap_atomic(page, KM_USER0);
- memcpy(save->data, kaddr, PAGE_SIZE);
- kunmap_atomic(kaddr, KM_USER0);
- highmem_copy = save;
+ while (swap_map) {
+ swap_map->next_swap = entry;
+ if ((error = write_page((unsigned long)swap_map, &entry)))
+ return error;
+ swap_map = swap_map->next;
}
+ *start = entry;
return 0;
}
-#endif /* CONFIG_HIGHMEM */
+/**
+ * free_image_entries - free the swap entries allocated to store
+ * the image data pages (this is only called in case of an error)
+ */
-static int save_highmem(void)
+static inline void free_image_entries(struct swap_map_page *swp)
{
-#ifdef CONFIG_HIGHMEM
- struct zone *zone;
- int res = 0;
-
- pr_debug("swsusp: Saving Highmem\n");
- for_each_zone(zone) {
- if (is_highmem(zone))
- res = save_highmem_zone(zone);
- if (res)
- return res;
- }
-#endif
- return 0;
-}
+ unsigned k;
-static int restore_highmem(void)
-{
-#ifdef CONFIG_HIGHMEM
- printk("swsusp: Restoring Highmem\n");
- while (highmem_copy) {
- struct highmem_page *save = highmem_copy;
- void *kaddr;
- highmem_copy = save->next;
-
- kaddr = kmap_atomic(save->page, KM_USER0);
- memcpy(kaddr, save->data, PAGE_SIZE);
- kunmap_atomic(kaddr, KM_USER0);
- free_page((long) save->data);
- kfree(save);
+ while (swp) {
+ for (k = 0; k < MAP_PAGE_SIZE; k++)
+ if (swp->entries[k].val)
+ swap_free(swp->entries[k]);
+ swp = swp->next;
}
-#endif
- return 0;
-}
-
-
-static int pfn_is_nosave(unsigned long pfn)
-{
- unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
- unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
- return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
}
/**
- * saveable - Determine whether a page should be cloned or not.
- * @pfn: The page
- *
- * We save a page if it's Reserved, and not in the range of pages
- * statically defined as 'unsaveable', or if it isn't reserved, and
- * isn't part of a free chunk of pages.
- * If it is part of a free chunk, we update @pfn to point to the last
- * page of the chunk.
+ * The swap_map_handle structure is used for handling the swap map in
+ * a file-alike way
*/
-static int saveable(struct zone * zone, unsigned long * zone_pfn)
-{
- unsigned long pfn = *zone_pfn + zone->zone_start_pfn;
- unsigned long chunk_size;
- struct page * page;
-
- if (!pfn_valid(pfn))
- return 0;
-
- if (!(pfn%1000))
- printk(".");
- page = pfn_to_page(pfn);
- BUG_ON(PageReserved(page) && PageNosave(page));
- if (PageNosave(page))
- return 0;
- if (PageReserved(page) && pfn_is_nosave(pfn)) {
- pr_debug("[nosave pfn 0x%lx]", pfn);
- return 0;
- }
- if ((chunk_size = is_head_of_free_region(page))) {
- *zone_pfn += chunk_size - 1;
- return 0;
- }
+struct swap_map_handle {
+ struct swap_map_page *cur;
+ unsigned int k;
+};
- return 1;
+static inline void init_swap_map_handle(struct swap_map_handle *handle,
+ struct swap_map_page *map)
+{
+ handle->cur = map;
+ handle->k = 0;
}
-static void count_data_pages(void)
+static inline int swap_map_write_page(struct swap_map_handle *handle,
+ unsigned long addr)
{
- struct zone *zone;
- unsigned long zone_pfn;
-
- nr_copy_pages = 0;
+ int error;
- for_each_zone(zone) {
- if (!is_highmem(zone)) {
- for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
- nr_copy_pages += saveable(zone, &zone_pfn);
- }
+ error = write_page(addr, handle->cur->entries + handle->k);
+ if (error)
+ return error;
+ if (++handle->k >= MAP_PAGE_SIZE) {
+ handle->cur = handle->cur->next;
+ handle->k = 0;
}
+ return 0;
}
+/**
+ * save_image_data - save the data pages pointed to by the PBEs
+ * from the list @pblist using the swap map handle @handle
+ * (assume there are @nr_pages data pages to save)
+ */
-static void copy_data_pages(void)
+static int save_image_data(struct pbe *pblist,
+ struct swap_map_handle *handle,
+ unsigned int nr_pages)
{
- struct zone *zone;
- unsigned long zone_pfn;
- struct pbe * pbe = pagedir_nosave;
-
- for_each_zone(zone) {
- if (!is_highmem(zone))
- for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
- if (saveable(zone, &zone_pfn)) {
- struct page * page;
- page = pfn_to_page(zone_pfn + zone->zone_start_pfn);
- pbe->orig_address = (long) page_address(page);
- /* copy_page is no usable for copying task structs. */
- memcpy((void *)pbe->address, (void *)pbe->orig_address, PAGE_SIZE);
- pbe++;
- }
- }
- }
-}
-
+ unsigned int m;
+ struct pbe *p;
+ int error = 0;
-static void free_suspend_pagedir_zone(struct zone *zone, unsigned long pagedir)
-{
- unsigned long zone_pfn, pagedir_end, pagedir_pfn, pagedir_end_pfn;
- pagedir_end = pagedir + (PAGE_SIZE << pagedir_order);
- pagedir_pfn = __pa(pagedir) >> PAGE_SHIFT;
- pagedir_end_pfn = __pa(pagedir_end) >> PAGE_SHIFT;
- for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) {
- struct page *page;
- unsigned long pfn = zone_pfn + zone->zone_start_pfn;
- if (!pfn_valid(pfn))
- continue;
- page = pfn_to_page(pfn);
- if (!TestClearPageNosave(page))
- continue;
- else if (pfn >= pagedir_pfn && pfn < pagedir_end_pfn)
- continue;
- __free_page(page);
+ printk("Saving image data pages (%u pages) ... ", nr_pages);
+ m = nr_pages / 100;
+ if (!m)
+ m = 1;
+ nr_pages = 0;
+ for_each_pbe (p, pblist) {
+ error = swap_map_write_page(handle, p->address);
+ if (error)
+ break;
+ if (!(nr_pages % m))
+ printk("\b\b\b\b%3d%%", nr_pages / m);
+ nr_pages++;
}
+ if (!error)
+ printk("\b\b\b\bdone\n");
+ return error;
}
-void swsusp_free(void)
+static void dump_info(void)
{
- unsigned long p = (unsigned long)pagedir_save;
- struct zone *zone;
- for_each_zone(zone) {
- if (!is_highmem(zone))
- free_suspend_pagedir_zone(zone, p);
- }
- free_pages(p, pagedir_order);
+ pr_debug(" swsusp: Version: %u\n",swsusp_info.version_code);
+ pr_debug(" swsusp: Num Pages: %ld\n",swsusp_info.num_physpages);
+ pr_debug(" swsusp: UTS Sys: %s\n",swsusp_info.uts.sysname);
+ pr_debug(" swsusp: UTS Node: %s\n",swsusp_info.uts.nodename);
+ pr_debug(" swsusp: UTS Release: %s\n",swsusp_info.uts.release);
+ pr_debug(" swsusp: UTS Version: %s\n",swsusp_info.uts.version);
+ pr_debug(" swsusp: UTS Machine: %s\n",swsusp_info.uts.machine);
+ pr_debug(" swsusp: UTS Domain: %s\n",swsusp_info.uts.domainname);
+ pr_debug(" swsusp: CPUs: %d\n",swsusp_info.cpus);
+ pr_debug(" swsusp: Image: %ld Pages\n",swsusp_info.image_pages);
+ pr_debug(" swsusp: Total: %ld Pages\n", swsusp_info.pages);
}
-
-/**
- * calc_order - Determine the order of allocation needed for pagedir_save.
- *
- * This looks tricky, but is just subtle. Please fix it some time.
- * Since there are %nr_copy_pages worth of pages in the snapshot, we need
- * to allocate enough contiguous space to hold
- * (%nr_copy_pages * sizeof(struct pbe)),
- * which has the saved/orig locations of the page..
- *
- * SUSPEND_PD_PAGES() tells us how many pages we need to hold those
- * structures, then we call get_bitmask_order(), which will tell us the
- * last bit set in the number, starting with 1. (If we need 30 pages, that
- * is 0x0000001e in hex. The last bit is the 5th, which is the order we
- * would use to allocate 32 contiguous pages).
- *
- * Since we also need to save those pages, we add the number of pages that
- * we need to nr_copy_pages, and in case of an overflow, do the
- * calculation again to update the number of pages needed.
- *
- * With this model, we will tend to waste a lot of memory if we just cross
- * an order boundary. Plus, the higher the order of allocation that we try
- * to do, the more likely we are to fail in a low-memory situtation
- * (though we're unlikely to get this far in such a case, since swsusp
- * requires half of memory to be free anyway).
- */
-
-
-static void calc_order(void)
+static void init_header(unsigned int nr_pages)
{
- int diff = 0;
- int order = 0;
+ memset(&swsusp_info, 0, sizeof(swsusp_info));
+ swsusp_info.version_code = LINUX_VERSION_CODE;
+ swsusp_info.num_physpages = num_physpages;
+ memcpy(&swsusp_info.uts, &system_utsname, sizeof(system_utsname));
- do {
- diff = get_bitmask_order(SUSPEND_PD_PAGES(nr_copy_pages)) - order;
- if (diff) {
- order += diff;
- nr_copy_pages += 1 << diff;
- }
- } while(diff);
- pagedir_order = order;
+ swsusp_info.cpus = num_online_cpus();
+ swsusp_info.image_pages = nr_pages;
+ swsusp_info.pages = nr_pages +
+ ((nr_pages * sizeof(long) + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
}
-
/**
- * alloc_pagedir - Allocate the page directory.
- *
- * First, determine exactly how many contiguous pages we need and
- * allocate them.
+ * pack_orig_addresses - the .orig_address fields of the PBEs from the
+ * list starting at @pbe are stored in the array @buf[] (1 page)
*/
-static int alloc_pagedir(void)
+static inline struct pbe *pack_orig_addresses(unsigned long *buf,
+ struct pbe *pbe)
{
- calc_order();
- pagedir_save = (suspend_pagedir_t *)__get_free_pages(GFP_ATOMIC | __GFP_COLD,
- pagedir_order);
- if (!pagedir_save)
- return -ENOMEM;
- memset(pagedir_save, 0, (1 << pagedir_order) * PAGE_SIZE);
- pagedir_nosave = pagedir_save;
- return 0;
-}
+ int j;
+ for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) {
+ buf[j] = pbe->orig_address;
+ pbe = pbe->next;
+ }
+ if (!pbe)
+ for (; j < PAGE_SIZE / sizeof(long); j++)
+ buf[j] = 0;
+ return pbe;
+}
/**
- * alloc_image_pages - Allocate pages for the snapshot.
- *
+ * save_image_metadata - save the .orig_address fields of the PBEs
+ * from the list @pblist using the swap map handle @handle
*/
-static int alloc_image_pages(void)
+static int save_image_metadata(struct pbe *pblist,
+ struct swap_map_handle *handle)
{
- struct pbe * p;
- int i;
+ unsigned long *buf;
+ unsigned int n = 0;
+ struct pbe *p;
+ int error = 0;
- for (i = 0, p = pagedir_save; i < nr_copy_pages; i++, p++) {
- p->address = get_zeroed_page(GFP_ATOMIC | __GFP_COLD);
- if(!p->address)
- goto Error;
- SetPageNosave(virt_to_page(p->address));
+ printk("Saving image metadata ... ");
+ buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
+ if (!buf)
+ return -ENOMEM;
+ p = pblist;
+ while (p) {
+ p = pack_orig_addresses(buf, p);
+ error = swap_map_write_page(handle, (unsigned long)buf);
+ if (error)
+ break;
+ n++;
}
- return 0;
- Error:
- do {
- if (p->address)
- free_page(p->address);
- p->address = 0;
- } while (p-- > pagedir_save);
- return -ENOMEM;
+ free_page((unsigned long)buf);
+ if (!error)
+ printk("done (%u pages saved)\n", n);
+ return error;
}
-
/**
- * enough_free_mem - Make sure we enough free memory to snapshot.
+ * enough_swap - Make sure we have enough swap to save the image.
*
- * Returns TRUE or FALSE after checking the number of available
- * free pages.
+ * Returns TRUE or FALSE after checking the total amount of swap
+ * space avaiable from the resume partition.
*/
-static int enough_free_mem(void)
+static int enough_swap(unsigned int nr_pages)
{
- if (nr_free_pages() < (nr_copy_pages + PAGES_FOR_IO)) {
- pr_debug("swsusp: Not enough free pages: Have %d\n",
- nr_free_pages());
- return 0;
- }
- return 1;
-}
+ unsigned int free_swap = swap_info[root_swap].pages -
+ swap_info[root_swap].inuse_pages;
+ pr_debug("swsusp: free swap pages: %u\n", free_swap);
+ return free_swap > (nr_pages + PAGES_FOR_IO +
+ (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE);
+}
/**
- * enough_swap - Make sure we have enough swap to save the image.
+ * swsusp_write - Write entire image and metadata.
*
- * Returns TRUE or FALSE after checking the total amount of swap
- * space avaiable.
- *
- * FIXME: si_swapinfo(&i) returns all swap devices information.
- * We should only consider resume_device.
+ * It is important _NOT_ to umount filesystems at this point. We want
+ * them synced (in case something goes wrong) but we DO not want to mark
+ * filesystem clean: it is not. (And it does not matter, if we resume
+ * correctly, we'll mark system clean, anyway.)
*/
-static int enough_swap(void)
-{
- struct sysinfo i;
-
- si_swapinfo(&i);
- if (i.freeswap < (nr_copy_pages + PAGES_FOR_IO)) {
- pr_debug("swsusp: Not enough swap. Need %ld\n",i.freeswap);
- return 0;
- }
- return 1;
-}
-
-static int swsusp_alloc(void)
+int swsusp_write(struct pbe *pblist, unsigned int nr_pages)
{
+ struct swap_map_page *swap_map;
+ struct swap_map_handle handle;
+ swp_entry_t start;
int error;
- pr_debug("suspend: (pages needed: %d + %d free: %d)\n",
- nr_copy_pages, PAGES_FOR_IO, nr_free_pages());
-
- pagedir_nosave = NULL;
- if (!enough_free_mem())
- return -ENOMEM;
-
- if (!enough_swap())
- return -ENOSPC;
-
- if ((error = alloc_pagedir())) {
- pr_debug("suspend: Allocating pagedir failed.\n");
+ if ((error = swsusp_swap_check())) {
+ printk(KERN_ERR "swsusp: Cannot find swap device, try swapon -a.\n");
return error;
}
- if ((error = alloc_image_pages())) {
- pr_debug("suspend: Allocating image pages failed.\n");
- swsusp_free();
- return error;
+ if (!enough_swap(nr_pages)) {
+ printk(KERN_ERR "swsusp: Not enough free swap\n");
+ return -ENOSPC;
}
- nr_copy_pages_check = nr_copy_pages;
- pagedir_order_check = pagedir_order;
- return 0;
-}
-
-int suspend_prepare_image(void)
-{
- unsigned int nr_needed_pages = 0;
- int error;
-
- pr_debug("swsusp: critical section: \n");
- if (save_highmem()) {
- printk(KERN_CRIT "Suspend machine: Not enough free pages for highmem\n");
+ init_header(nr_pages);
+ swap_map = alloc_swap_map(swsusp_info.pages);
+ if (!swap_map)
return -ENOMEM;
- }
+ init_swap_map_handle(&handle, swap_map);
- drain_local_pages();
- count_data_pages();
- printk("swsusp: Need to copy %u pages\n",nr_copy_pages);
- nr_needed_pages = nr_copy_pages + PAGES_FOR_IO;
-
- error = swsusp_alloc();
+ error = swap_map_write_page(&handle, (unsigned long)&swsusp_info);
+ if (!error)
+ error = save_image_metadata(pblist, &handle);
+ if (!error)
+ error = save_image_data(pblist, &handle, nr_pages);
if (error)
- return error;
-
- /* During allocating of suspend pagedir, new cold pages may appear.
- * Kill them.
- */
- drain_local_pages();
- copy_data_pages();
-
- /*
- * End of critical section. From now on, we can write to memory,
- * but we should not touch disk. This specially means we must _not_
- * touch swap space! Except we must write out our image of course.
- */
+ goto Free_image_entries;
- printk("swsusp: critical section/: done (%d pages copied)\n", nr_copy_pages );
- return 0;
-}
+ swap_map = reverse_swap_map(swap_map);
+ error = save_swap_map(swap_map, &start);
+ if (error)
+ goto Free_map_entries;
+ dump_info();
+ printk( "S" );
+ error = mark_swapfiles(start);
+ printk( "|\n" );
+ if (error)
+ goto Free_map_entries;
-/* It is important _NOT_ to umount filesystems at this point. We want
- * them synced (in case something goes wrong) but we DO not want to mark
- * filesystem clean: it is not. (And it does not matter, if we resume
- * correctly, we'll mark system clean, anyway.)
- */
-int swsusp_write(void)
-{
- int error;
- device_resume();
- lock_swapdevices();
- error = write_suspend_image();
- /* This will unlock ignored swap devices since writing is finished */
- lock_swapdevices();
+Free_swap_map:
+ free_swap_map(swap_map);
return error;
+Free_map_entries:
+ free_swap_map_entries(swap_map);
+Free_image_entries:
+ free_image_entries(swap_map);
+ goto Free_swap_map;
}
+/**
+ * swsusp_shrink_memory - Try to free as much memory as needed
+ *
+ * ... but do not OOM-kill anyone
+ *
+ * Notice: all userland should be stopped before it is called, or
+ * livelock is possible.
+ */
-extern asmlinkage int swsusp_arch_suspend(void);
-extern asmlinkage int swsusp_arch_resume(void);
-
+#define SHRINK_BITE 10000
-asmlinkage int swsusp_save(void)
+int swsusp_shrink_memory(void)
{
- int error = 0;
+ long size, tmp;
+ struct zone *zone;
+ unsigned long pages = 0;
+ unsigned int i = 0;
+ char *p = "-\\|/";
- if ((error = swsusp_swap_check()))
- return error;
- return suspend_prepare_image();
+ printk("Shrinking memory... ");
+ do {
+ size = 2 * count_highmem_pages();
+ size += size / 50 + count_data_pages();
+ size += (size + PBES_PER_PAGE - 1) / PBES_PER_PAGE +
+ PAGES_FOR_IO;
+ tmp = size;
+ for_each_zone (zone)
+ if (!is_highmem(zone))
+ tmp -= zone->free_pages;
+ if (tmp > 0) {
+ tmp = shrink_all_memory(SHRINK_BITE);
+ if (!tmp)
+ return -ENOMEM;
+ pages += tmp;
+ } else if (size > image_size / PAGE_SIZE) {
+ tmp = shrink_all_memory(SHRINK_BITE);
+ pages += tmp;
+ }
+ printk("\b%c", p[i++%4]);
+ } while (tmp > 0);
+ printk("\bdone (%lu pages freed)\n", pages);
+
+ return 0;
}
int swsusp_suspend(void)
{
int error;
+
if ((error = arch_prepare_suspend()))
return error;
local_irq_disable();
+ /* At this point, device_suspend() has been called, but *not*
+ * device_power_down(). We *must* device_power_down() now.
+ * Otherwise, drivers for some devices (e.g. interrupt controllers)
+ * become desynchronized with the actual state of the hardware
+ * at resume time, and evil weirdness ensues.
+ */
+ if ((error = device_power_down(PMSG_FREEZE))) {
+ printk(KERN_ERR "Some devices failed to power down, aborting suspend\n");
+ goto Enable_irqs;
+ }
+
+ if ((error = save_highmem())) {
+ printk(KERN_ERR "swsusp: Not enough free pages for highmem\n");
+ goto Restore_highmem;
+ }
+
save_processor_state();
- error = swsusp_arch_suspend();
+ if ((error = swsusp_arch_suspend()))
+ printk(KERN_ERR "Error %d suspending\n", error);
/* Restore control flow magically appears here */
restore_processor_state();
+Restore_highmem:
restore_highmem();
+ device_power_up();
+Enable_irqs:
local_irq_enable();
return error;
}
-
-asmlinkage int swsusp_restore(void)
-{
- BUG_ON (nr_copy_pages_check != nr_copy_pages);
- BUG_ON (pagedir_order_check != pagedir_order);
-
- /* Even mappings of "global" things (vmalloc) need to be fixed */
- __flush_tlb_global();
- return 0;
-}
-
int swsusp_resume(void)
{
int error;
local_irq_disable();
+ if (device_power_down(PMSG_FREEZE))
+ printk(KERN_ERR "Some devices failed to power down, very bad\n");
/* We'll ignore saved state, but this gets preempt count (etc) right */
save_processor_state();
error = swsusp_arch_resume();
* execution continues at place where swsusp_arch_suspend was called
*/
BUG_ON(!error);
+ /* The only reason why swsusp_arch_resume() can fail is memory being
+ * very tight, so we have to free it as soon as we can to avoid
+ * subsequent failures
+ */
+ swsusp_free();
restore_processor_state();
restore_highmem();
+ touch_softlockup_watchdog();
+ device_power_up();
local_irq_enable();
return error;
}
-
-
-/* More restore stuff */
-
-#define does_collide(addr) does_collide_order(pagedir_nosave, addr, 0)
-
-/*
- * Returns true if given address/order collides with any orig_address
- */
-static int __init does_collide_order(suspend_pagedir_t *pagedir, unsigned long addr,
- int order)
-{
- int i;
- unsigned long addre = addr + (PAGE_SIZE<<order);
-
- for (i=0; i < nr_copy_pages; i++)
- if ((pagedir+i)->orig_address >= addr &&
- (pagedir+i)->orig_address < addre)
- return 1;
-
- return 0;
-}
-
-/*
- * We check here that pagedir & pages it points to won't collide with pages
- * where we're going to restore from the loaded pages later
+/**
+ * mark_unsafe_pages - mark the pages that cannot be used for storing
+ * the image during resume, because they conflict with the pages that
+ * had been used before suspend
*/
-static int __init check_pagedir(void)
-{
- int i;
-
- for(i=0; i < nr_copy_pages; i++) {
- unsigned long addr;
-
- do {
- addr = get_zeroed_page(GFP_ATOMIC);
- if(!addr)
- return -ENOMEM;
- } while (does_collide(addr));
-
- (pagedir_nosave+i)->address = addr;
- }
- return 0;
-}
-static int __init swsusp_pagedir_relocate(void)
+static void mark_unsafe_pages(struct pbe *pblist)
{
- /*
- * We have to avoid recursion (not to overflow kernel stack),
- * and that's why code looks pretty cryptic
- */
- suspend_pagedir_t *old_pagedir = pagedir_nosave;
- void **eaten_memory = NULL;
- void **c = eaten_memory, *m, *f;
- int ret = 0;
+ struct zone *zone;
+ unsigned long zone_pfn;
+ struct pbe *p;
- printk("Relocating pagedir ");
+ if (!pblist) /* a sanity check */
+ return;
- if (!does_collide_order(old_pagedir, (unsigned long)old_pagedir, pagedir_order)) {
- printk("not necessary\n");
- return check_pagedir();
+ /* Clear page flags */
+ for_each_zone (zone) {
+ for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+ if (pfn_valid(zone_pfn + zone->zone_start_pfn))
+ ClearPageNosaveFree(pfn_to_page(zone_pfn +
+ zone->zone_start_pfn));
}
- while ((m = (void *) __get_free_pages(GFP_ATOMIC, pagedir_order)) != NULL) {
- if (!does_collide_order(old_pagedir, (unsigned long)m, pagedir_order))
- break;
- eaten_memory = m;
- printk( "." );
- *eaten_memory = c;
- c = eaten_memory;
- }
+ /* Mark orig addresses */
+ for_each_pbe (p, pblist)
+ SetPageNosaveFree(virt_to_page(p->orig_address));
- if (!m) {
- printk("out of memory\n");
- ret = -ENOMEM;
- } else {
- pagedir_nosave =
- memcpy(m, old_pagedir, PAGE_SIZE << pagedir_order);
- }
+}
- c = eaten_memory;
- while (c) {
- printk(":");
- f = c;
- c = *c;
- free_pages((unsigned long)f, pagedir_order);
+static void copy_page_backup_list(struct pbe *dst, struct pbe *src)
+{
+ /* We assume both lists contain the same number of elements */
+ while (src) {
+ dst->orig_address = src->orig_address;
+ dst = dst->next;
+ src = src->next;
}
- printk("|\n");
- return check_pagedir();
}
-/**
+/*
* Using bio to read from swap.
* This code requires a bit more work than just using buffer heads
* but, it is the recommended way for 2.5/2.6.
static atomic_t io_done = ATOMIC_INIT(0);
-static void start_io(void)
-{
- atomic_set(&io_done,1);
-}
-
-static int end_io(struct bio * bio, unsigned int num, int err)
+static int end_io(struct bio *bio, unsigned int num, int err)
{
- atomic_set(&io_done,0);
+ if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ panic("I/O error reading memory image");
+ atomic_set(&io_done, 0);
return 0;
}
-static void wait_io(void)
-{
- while(atomic_read(&io_done))
- io_schedule();
-}
-
-
-static struct block_device * resume_bdev;
+static struct block_device *resume_bdev;
/**
* submit - submit BIO request.
* Then submit it and wait.
*/
-static int submit(int rw, pgoff_t page_off, void * page)
+static int submit(int rw, pgoff_t page_off, void *page)
{
int error = 0;
- struct bio * bio;
+ struct bio *bio;
bio = bio_alloc(GFP_ATOMIC, 1);
if (!bio)
return -ENOMEM;
bio->bi_sector = page_off * (PAGE_SIZE >> 9);
- bio_get(bio);
bio->bi_bdev = resume_bdev;
bio->bi_end_io = end_io;
goto Done;
}
- if (rw == WRITE)
- bio_set_pages_dirty(bio);
- start_io();
+
+ atomic_set(&io_done, 1);
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
- wait_io();
+ while (atomic_read(&io_done))
+ yield();
+ if (rw == READ)
+ bio_set_pages_dirty(bio);
Done:
bio_put(bio);
return error;
}
-int bio_read_page(pgoff_t page_off, void * page)
+static int bio_read_page(pgoff_t page_off, void *page)
{
return submit(READ, page_off, page);
}
-int bio_write_page(pgoff_t page_off, void * page)
+static int bio_write_page(pgoff_t page_off, void *page)
{
return submit(WRITE, page_off, page);
}
-/*
- * Sanity check if this image makes sense with this kernel/swap context
- * I really don't think that it's foolproof but more than nothing..
+/**
+ * The following functions allow us to read data using a swap map
+ * in a file-alike way
*/
-static const char * __init sanity_check(void)
+static inline void release_swap_map_reader(struct swap_map_handle *handle)
{
- dump_info();
- if(swsusp_info.version_code != LINUX_VERSION_CODE)
- return "kernel version";
- if(swsusp_info.num_physpages != num_physpages)
- return "memory size";
- if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname))
- return "system type";
- if (strcmp(swsusp_info.uts.release,system_utsname.release))
- return "kernel release";
- if (strcmp(swsusp_info.uts.version,system_utsname.version))
- return "version";
- if (strcmp(swsusp_info.uts.machine,system_utsname.machine))
- return "machine";
- if(swsusp_info.cpus != num_online_cpus())
- return "number of cpus";
- return NULL;
+ if (handle->cur)
+ free_page((unsigned long)handle->cur);
+ handle->cur = NULL;
}
+static inline int get_swap_map_reader(struct swap_map_handle *handle,
+ swp_entry_t start)
+{
+ int error;
+
+ if (!swp_offset(start))
+ return -EINVAL;
+ handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_ATOMIC);
+ if (!handle->cur)
+ return -ENOMEM;
+ error = bio_read_page(swp_offset(start), handle->cur);
+ if (error) {
+ release_swap_map_reader(handle);
+ return error;
+ }
+ handle->k = 0;
+ return 0;
+}
-static int __init check_header(void)
+static inline int swap_map_read_page(struct swap_map_handle *handle, void *buf)
{
- const char * reason = NULL;
+ unsigned long offset;
int error;
- if ((error = bio_read_page(swp_offset(swsusp_header.swsusp_info), &swsusp_info)))
+ if (!handle->cur)
+ return -EINVAL;
+ offset = swp_offset(handle->cur->entries[handle->k]);
+ if (!offset)
+ return -EINVAL;
+ error = bio_read_page(offset, buf);
+ if (error)
return error;
+ if (++handle->k >= MAP_PAGE_SIZE) {
+ handle->k = 0;
+ offset = swp_offset(handle->cur->next_swap);
+ if (!offset)
+ release_swap_map_reader(handle);
+ else
+ error = bio_read_page(offset, handle->cur);
+ }
+ return error;
+}
- /* Is this same machine? */
- if ((reason = sanity_check())) {
- printk(KERN_ERR "swsusp: Resume mismatch: %s\n",reason);
+static int check_header(void)
+{
+ char *reason = NULL;
+
+ dump_info();
+ if (swsusp_info.version_code != LINUX_VERSION_CODE)
+ reason = "kernel version";
+ if (swsusp_info.num_physpages != num_physpages)
+ reason = "memory size";
+ if (strcmp(swsusp_info.uts.sysname,system_utsname.sysname))
+ reason = "system type";
+ if (strcmp(swsusp_info.uts.release,system_utsname.release))
+ reason = "kernel release";
+ if (strcmp(swsusp_info.uts.version,system_utsname.version))
+ reason = "version";
+ if (strcmp(swsusp_info.uts.machine,system_utsname.machine))
+ reason = "machine";
+ if (reason) {
+ printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason);
return -EPERM;
}
- nr_copy_pages = swsusp_info.image_pages;
- return error;
+ return 0;
}
-static int __init check_sig(void)
+/**
+ * load_image_data - load the image data using the swap map handle
+ * @handle and store them using the page backup list @pblist
+ * (assume there are @nr_pages pages to load)
+ */
+
+static int load_image_data(struct pbe *pblist,
+ struct swap_map_handle *handle,
+ unsigned int nr_pages)
{
int error;
+ unsigned int m;
+ struct pbe *p;
- memset(&swsusp_header, 0, sizeof(swsusp_header));
- if ((error = bio_read_page(0, &swsusp_header)))
- return error;
- if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
- memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
-
- /*
- * Reset swap signature now.
- */
- error = bio_write_page(0, &swsusp_header);
- } else {
- pr_debug(KERN_ERR "swsusp: Invalid partition type.\n");
+ if (!pblist)
return -EINVAL;
+ printk("Loading image data pages (%u pages) ... ", nr_pages);
+ m = nr_pages / 100;
+ if (!m)
+ m = 1;
+ nr_pages = 0;
+ p = pblist;
+ while (p) {
+ error = swap_map_read_page(handle, (void *)p->address);
+ if (error)
+ break;
+ p = p->next;
+ if (!(nr_pages % m))
+ printk("\b\b\b\b%3d%%", nr_pages / m);
+ nr_pages++;
}
if (!error)
- pr_debug("swsusp: Signature found, resuming\n");
+ printk("\b\b\b\bdone\n");
return error;
}
/**
- * swsusp_read_data - Read image pages from swap.
- *
- * You do not need to check for overlaps, check_pagedir()
- * already did that.
+ * unpack_orig_addresses - copy the elements of @buf[] (1 page) to
+ * the PBEs in the list starting at @pbe
*/
-static int __init data_read(void)
+static inline struct pbe *unpack_orig_addresses(unsigned long *buf,
+ struct pbe *pbe)
{
- struct pbe * p;
- int error;
- int i;
-
- if ((error = swsusp_pagedir_relocate()))
- return error;
+ int j;
- printk( "Reading image data (%d pages): ", nr_copy_pages );
- for(i = 0, p = pagedir_nosave; i < nr_copy_pages && !error; i++, p++) {
- if (!(i%100))
- printk( "." );
- error = bio_read_page(swp_offset(p->swap_address),
- (void *)p->address);
+ for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) {
+ pbe->orig_address = buf[j];
+ pbe = pbe->next;
}
- printk(" %d done.\n",i);
- return error;
-
+ return pbe;
}
-extern dev_t __init name_to_dev_t(const char *line);
+/**
+ * load_image_metadata - load the image metadata using the swap map
+ * handle @handle and put them into the PBEs in the list @pblist
+ */
-static int __init read_pagedir(void)
+static int load_image_metadata(struct pbe *pblist, struct swap_map_handle *handle)
{
- unsigned long addr;
- int i, n = swsusp_info.pagedir_pages;
+ struct pbe *p;
+ unsigned long *buf;
+ unsigned int n = 0;
int error = 0;
- pagedir_order = get_bitmask_order(n);
-
- addr =__get_free_pages(GFP_ATOMIC, pagedir_order);
- if (!addr)
+ printk("Loading image metadata ... ");
+ buf = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
+ if (!buf)
return -ENOMEM;
- pagedir_nosave = (struct pbe *)addr;
-
- pr_debug("pmdisk: Reading pagedir (%d Pages)\n",n);
-
- for (i = 0; i < n && !error; i++, addr += PAGE_SIZE) {
- unsigned long offset = swp_offset(swsusp_info.pagedir[i]);
- if (offset)
- error = bio_read_page(offset, (void *)addr);
- else
- error = -EFAULT;
+ p = pblist;
+ while (p) {
+ error = swap_map_read_page(handle, buf);
+ if (error)
+ break;
+ p = unpack_orig_addresses(buf, p);
+ n++;
}
- if (error)
- free_pages((unsigned long)pagedir_nosave, pagedir_order);
+ free_page((unsigned long)buf);
+ if (!error)
+ printk("done (%u pages loaded)\n", n);
return error;
}
-static int __init read_suspend_image(void)
+int swsusp_read(struct pbe **pblist_ptr)
{
- int error = 0;
+ int error;
+ struct pbe *p, *pblist;
+ struct swap_map_handle handle;
+ unsigned int nr_pages;
- if ((error = check_sig()))
- return error;
- if ((error = check_header()))
- return error;
- if ((error = read_pagedir()))
+ if (IS_ERR(resume_bdev)) {
+ pr_debug("swsusp: block device not initialised\n");
+ return PTR_ERR(resume_bdev);
+ }
+
+ error = get_swap_map_reader(&handle, swsusp_header.image);
+ if (!error)
+ error = swap_map_read_page(&handle, &swsusp_info);
+ if (!error)
+ error = check_header();
+ if (error)
return error;
- if ((error = data_read()))
- free_pages((unsigned long)pagedir_nosave, pagedir_order);
+ nr_pages = swsusp_info.image_pages;
+ p = alloc_pagedir(nr_pages, GFP_ATOMIC, 0);
+ if (!p)
+ return -ENOMEM;
+ error = load_image_metadata(p, &handle);
+ if (!error) {
+ mark_unsafe_pages(p);
+ pblist = alloc_pagedir(nr_pages, GFP_ATOMIC, 1);
+ if (pblist)
+ copy_page_backup_list(pblist, p);
+ free_pagedir(p);
+ if (!pblist)
+ error = -ENOMEM;
+
+ /* Allocate memory for the image and read the data from swap */
+ if (!error)
+ error = alloc_data_pages(pblist, GFP_ATOMIC, 1);
+ if (!error) {
+ release_eaten_pages();
+ error = load_image_data(pblist, &handle, nr_pages);
+ }
+ if (!error)
+ *pblist_ptr = pblist;
+ }
+ release_swap_map_reader(&handle);
+
+ blkdev_put(resume_bdev);
+
+ if (!error)
+ pr_debug("swsusp: Reading resume file was successful\n");
+ else
+ pr_debug("swsusp: Error %d resuming\n", error);
return error;
}
/**
- * pmdisk_read - Read saved image from swap.
+ * swsusp_check - Check for swsusp signature in the resume device
*/
-int __init swsusp_read(void)
+int swsusp_check(void)
{
int error;
- if (!strlen(resume_file))
- return -ENOENT;
-
- resume_device = name_to_dev_t(resume_file);
- pr_debug("swsusp: Resume From Partition: %s\n", resume_file);
-
- resume_bdev = open_by_devnum(resume_device, FMODE_READ);
+ resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
if (!IS_ERR(resume_bdev)) {
set_blocksize(resume_bdev, PAGE_SIZE);
- error = read_suspend_image();
- blkdev_put(resume_bdev);
- } else
+ memset(&swsusp_header, 0, sizeof(swsusp_header));
+ if ((error = bio_read_page(0, &swsusp_header)))
+ return error;
+ if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
+ memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
+ /* Reset swap signature now */
+ error = bio_write_page(0, &swsusp_header);
+ } else {
+ return -EINVAL;
+ }
+ if (error)
+ blkdev_put(resume_bdev);
+ else
+ pr_debug("swsusp: Signature found, resuming\n");
+ } else {
error = PTR_ERR(resume_bdev);
+ }
+
+ if (error)
+ pr_debug("swsusp: Error %d check for resume file\n", error);
- if (!error)
- pr_debug("Reading resume file was successful\n");
- else
- pr_debug("pmdisk: Error %d resuming\n", error);
return error;
}
+
+/**
+ * swsusp_close - close swap device.
+ */
+
+void swsusp_close(void)
+{
+ if (IS_ERR(resume_bdev)) {
+ pr_debug("swsusp: block device not initialised\n");
+ return;
+ }
+
+ blkdev_put(resume_bdev);
+}