X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fpower%2Fswsusp.c;h=5da304c8f1f66473233d68d713a66e2a17c59d54;hb=89862e3be1ba387c738fc2c3a5875cfd7e51c5a8;hp=ae8425b69b44a9be863e0c45d29231cf5514bcb8;hpb=96bc7aec20b50761822f96130127b8e31e168af1;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index ae8425b..5da304c 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -30,554 +30,253 @@ * Alex Badea : * Fixed runaway init * - * Andreas Steinmetz : - * Added encrypted suspend option + * Rafael J. Wysocki + * Reworked the freeing of memory and 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 #include #include -#include -#include -#include -#include -#include -#include #include -#include #include #include #include #include -#include -#include #include #include #include #include -#include - -#include -#include -#include -#include -#include - -#include -#include -#include +#include +#include #include "power.h" -#define CIPHER "aes" -#define MAXKEY 32 -#define MAXIV 32 - -extern char resume_file[]; - -/* 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; -suspend_pagedir_t *pagedir_save; - -#define SWSUSP_SIG "S1SUSPEND" - -static struct swsusp_header { - char reserved[PAGE_SIZE - 20 - MAXKEY - MAXIV - sizeof(swp_entry_t)]; - u8 key_iv[MAXKEY+MAXIV]; - swp_entry_t swsusp_info; - char orig_sig[10]; - char sig[10]; -} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header; - -static struct swsusp_info swsusp_info; - /* - * Saving part... + * 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; -/* 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 int write_page(unsigned long addr, swp_entry_t * loc); -static int bio_read_page(pgoff_t page_off, void * page); - -static u8 key_iv[MAXKEY+MAXIV]; - -#ifdef CONFIG_SWSUSP_ENCRYPT - -static int crypto_init(int mode, void **mem) -{ - int error = 0; - int len; - char *modemsg; - struct crypto_tfm *tfm; - - modemsg = mode ? "suspend not possible" : "resume not possible"; - - tfm = crypto_alloc_tfm(CIPHER, CRYPTO_TFM_MODE_CBC); - if(!tfm) { - printk(KERN_ERR "swsusp: no tfm, %s\n", modemsg); - error = -EINVAL; - goto out; - } - - if(MAXKEY < crypto_tfm_alg_min_keysize(tfm)) { - printk(KERN_ERR "swsusp: key buffer too small, %s\n", modemsg); - error = -ENOKEY; - goto fail; - } - - if (mode) - get_random_bytes(key_iv, MAXKEY+MAXIV); - - len = crypto_tfm_alg_max_keysize(tfm); - if (len > MAXKEY) - len = MAXKEY; - - if (crypto_cipher_setkey(tfm, key_iv, len)) { - printk(KERN_ERR "swsusp: key setup failure, %s\n", modemsg); - error = -EKEYREJECTED; - goto fail; - } - - len = crypto_tfm_alg_ivsize(tfm); - - if (MAXIV < len) { - printk(KERN_ERR "swsusp: iv buffer too small, %s\n", modemsg); - error = -EOVERFLOW; - goto fail; - } - - crypto_cipher_set_iv(tfm, key_iv+MAXKEY, len); - - *mem=(void *)tfm; - - goto out; - -fail: crypto_free_tfm(tfm); -out: return error; -} - -static __inline__ void crypto_exit(void *mem) -{ - crypto_free_tfm((struct crypto_tfm *)mem); -} - -static __inline__ int crypto_write(struct pbe *p, void *mem) -{ - int error = 0; - struct scatterlist src, dst; - - src.page = virt_to_page(p->address); - src.offset = 0; - src.length = PAGE_SIZE; - dst.page = virt_to_page((void *)&swsusp_header); - dst.offset = 0; - dst.length = PAGE_SIZE; - - error = crypto_cipher_encrypt((struct crypto_tfm *)mem, &dst, &src, - PAGE_SIZE); - - if (!error) - error = write_page((unsigned long)&swsusp_header, - &(p->swap_address)); - return error; -} - -static __inline__ int crypto_read(struct pbe *p, void *mem) -{ - int error = 0; - struct scatterlist src, dst; - - error = bio_read_page(swp_offset(p->swap_address), (void *)p->address); - if (!error) { - src.offset = 0; - src.length = PAGE_SIZE; - dst.offset = 0; - dst.length = PAGE_SIZE; - src.page = dst.page = virt_to_page((void *)p->address); +int in_suspend __nosavedata = 0; - error = crypto_cipher_decrypt((struct crypto_tfm *)mem, &dst, - &src, PAGE_SIZE); - } - return error; -} +#ifdef CONFIG_HIGHMEM +unsigned int count_highmem_pages(void); +int restore_highmem(void); #else -static __inline__ int crypto_init(int mode, void *mem) -{ - return 0; -} - -static __inline__ void crypto_exit(void *mem) -{ -} - -static __inline__ int crypto_write(struct pbe *p, void *mem) -{ - return write_page(p->address, &(p->swap_address)); -} - -static __inline__ int crypto_read(struct pbe *p, void *mem) -{ - return bio_read_page(swp_offset(p->swap_address), (void *)p->address); -} +static inline int restore_highmem(void) { return 0; } +static inline unsigned int count_highmem_pages(void) { return 0; } #endif -static int mark_swapfiles(swp_entry_t prev) -{ - int error; - - 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); - memcpy(swsusp_header.key_iv, key_iv, MAXKEY+MAXIV); - swsusp_header.swsusp_info = prev; - error = rw_swap_page_sync(WRITE, - swp_entry(root_swap, 0), - virt_to_page((unsigned long) - &swsusp_header)); - } else { - pr_debug("swsusp: Partition is not swap space.\n"); - error = -ENODEV; - } - return error; -} - -/* - * Check whether the swap device is the specified resume - * device, irrespective of whether they are specified by - * identical names. - * - * (Thus, device inode aliasing is allowed. You can say /dev/hda4 - * instead of /dev/ide/host0/bus0/target0/lun0/part4 [if using devfs] - * and they'll be considered the same device. This is *necessary* for - * devfs, since the resume code can only recognize the form /dev/hda4, - * but the suspend code would see the long name.) +/** + * The following functions are used for tracing the allocated + * swap pages, so that they can be freed in case of an error. */ -static 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) && - swsusp_resume_device == MKDEV(imajor(inode), iminor(inode)); -} - -static int swsusp_swap_check(void) /* This is called before saving image */ -{ - int i, len; - len=strlen(resume_file); - root_swap = 0xFFFF; - - spin_lock(&swap_lock); - for (i=0; istart) { + /* Try to merge */ + if (swap_offset == ext->start - 1) { + ext->start--; + return 0; + } + new = &((*new)->rb_left); + } else if (swap_offset > ext->end) { + /* Try to merge */ + if (swap_offset == ext->end + 1) { + ext->end++; + return 0; } + new = &((*new)->rb_right); + } else { + /* It already is in the tree */ + return -EINVAL; } } - spin_unlock(&swap_lock); - 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) -{ - int i; + /* Add the new node and rebalance the tree. */ + ext = kzalloc(sizeof(struct swsusp_extent), GFP_KERNEL); + if (!ext) + return -ENOMEM; - spin_lock(&swap_lock); - for (i = 0; i< MAX_SWAPFILES; i++) - if (swapfile_used[i] == SWAPFILE_IGNORED) { - swap_info[i].flags ^= SWP_WRITEOK; - } - spin_unlock(&swap_lock); + ext->start = swap_offset; + ext->end = swap_offset; + rb_link_node(&ext->node, parent, new); + rb_insert_color(&ext->node, &swsusp_extents); + return 0; } /** - * 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 - * 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. + * alloc_swapdev_block - allocate a swap page and register that it has + * been allocated, so that it can be freed in case of an error. */ -static int write_page(unsigned long addr, swp_entry_t * loc) -{ - swp_entry_t entry; - int error = 0; - - 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) - *loc = entry; - } else - error = -ENOSPC; - return error; -} -/** - * data_free - Free the swap entries used by the saved image. - * - * 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) +sector_t alloc_swapdev_block(int swap) { - swp_entry_t entry; - struct pbe * p; + unsigned long offset; - for_each_pbe(p, pagedir_nosave) { - entry = p->swap_address; - if (entry.val) - swap_free(entry); + offset = swp_offset(get_swap_page_of_type(swap)); + if (offset) { + if (swsusp_extents_insert(offset)) + swap_free(swp_entry(swap, offset)); else - break; + return swapdev_block(swap, offset); } + return 0; } /** - * data_write - Write saved image to swap. - * - * Walk the list of pages in the image and sync each one to swap. + * free_all_swap_pages - free swap pages allocated for saving image data. + * It also frees the extents used to register which swap entres had been + * allocated. */ -static int data_write(void) -{ - int error = 0, i = 0; - unsigned int mod = nr_copy_pages / 100; - struct pbe *p; - void *tfm; - - if ((error = crypto_init(1, &tfm))) - return error; - - if (!mod) - mod = 1; - printk( "Writing data to swap (%d pages)... ", nr_copy_pages ); - for_each_pbe (p, pagedir_nosave) { - if (!(i%mod)) - printk( "\b\b\b\b%3d%%", i / mod ); - if ((error = crypto_write(p, tfm))) { - crypto_exit(tfm); - return error; - } - i++; - } - printk("\b\b\b\bdone\n"); - crypto_exit(tfm); - return error; -} - -static void dump_info(void) +void free_all_swap_pages(int swap) { - 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 rb_node *node; -static void init_header(void) -{ - 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)); - - swsusp_info.suspend_pagedir = pagedir_nosave; - swsusp_info.cpus = num_online_cpus(); - swsusp_info.image_pages = nr_copy_pages; -} + while ((node = swsusp_extents.rb_node)) { + struct swsusp_extent *ext; + unsigned long offset; -static int close_swap(void) -{ - swp_entry_t entry; - int error; + ext = container_of(node, struct swsusp_extent, node); + rb_erase(node, &swsusp_extents); + for (offset = ext->start; offset <= ext->end; offset++) + swap_free(swp_entry(swap, offset)); - dump_info(); - error = write_page((unsigned long)&swsusp_info, &entry); - if (!error) { - printk( "S" ); - error = mark_swapfiles(entry); - printk( "|\n" ); + kfree(ext); } - return error; } -/** - * free_pagedir_entries - Free pages used by the page directory. - * - * This is used during suspend for error recovery. - */ - -static void free_pagedir_entries(void) +int swsusp_swap_in_use(void) { - int i; - - for (i = 0; i < swsusp_info.pagedir_pages; i++) - swap_free(swsusp_info.pagedir[i]); + return (swsusp_extents.rb_node != NULL); } - /** - * write_pagedir - Write the array of pages holding the page directory. - * @last: Last swap entry we write (needed for header). - */ - -static int write_pagedir(void) -{ - int error = 0; - unsigned n = 0; - struct pbe * pbe; - - printk( "Writing pagedir..."); - for_each_pb_page (pbe, pagedir_nosave) { - if ((error = write_page((unsigned long)pbe, &swsusp_info.pagedir[n++]))) - return error; - } - - swsusp_info.pagedir_pages = n; - printk("done (%u pages)\n", n); - return error; -} - -/** - * write_suspend_image - Write entire image and metadata. + * swsusp_show_speed - print the time elapsed between two events represented by + * @start and @stop * + * @nr_pages - number of pages processed between @start and @stop + * @msg - introductory message to print */ -static int write_suspend_image(void) -{ - int error; - init_header(); - if ((error = data_write())) - goto FreeData; - - if ((error = write_pagedir())) - goto FreePagedir; +void swsusp_show_speed(struct timeval *start, struct timeval *stop, + unsigned nr_pages, char *msg) +{ + s64 elapsed_centisecs64; + int centisecs; + int k; + int kps; - if ((error = close_swap())) - goto FreePagedir; - Done: - memset(key_iv, 0, MAXKEY+MAXIV); - return error; - FreePagedir: - free_pagedir_entries(); - FreeData: - data_free(); - goto Done; + elapsed_centisecs64 = timeval_to_ns(stop) - timeval_to_ns(start); + do_div(elapsed_centisecs64, NSEC_PER_SEC / 100); + centisecs = elapsed_centisecs64; + if (centisecs == 0) + centisecs = 1; /* avoid div-by-zero */ + k = nr_pages * (PAGE_SIZE / 1024); + kps = (k * 100) / centisecs; + printk("%s %d kbytes in %d.%02d seconds (%d.%02d MB/s)\n", msg, k, + centisecs / 100, centisecs % 100, + kps / 1000, (kps % 1000) / 10); } /** - * enough_swap - Make sure we have enough swap to save the image. + * swsusp_shrink_memory - Try to free as much memory as needed * - * Returns TRUE or FALSE after checking the total amount of swap - * space avaiable. + * ... but do not OOM-kill anyone * - * FIXME: si_swapinfo(&i) returns all swap devices information. - * We should only consider resume_device. + * Notice: all userland should be stopped before it is called, or + * livelock is possible. */ -int enough_swap(unsigned nr_pages) +#define SHRINK_BITE 10000 +static inline unsigned long __shrink_memory(long tmp) { - struct sysinfo i; - - si_swapinfo(&i); - pr_debug("swsusp: available swap: %lu pages\n", i.freeswap); - return i.freeswap > (nr_pages + PAGES_FOR_IO + - (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE); + if (tmp > SHRINK_BITE) + tmp = SHRINK_BITE; + return shrink_all_memory(tmp); } - -/* 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 swsusp_shrink_memory(void) { - int error; - device_resume(); - lock_swapdevices(); - error = write_suspend_image(); - /* This will unlock ignored swap devices since writing is finished */ - lock_swapdevices(); - return error; + long tmp; + struct zone *zone; + unsigned long pages = 0; + unsigned int i = 0; + char *p = "-\\|/"; + struct timeval start, stop; -} + printk("Shrinking memory... "); + do_gettimeofday(&start); + do { + long size, highmem_size; + + highmem_size = count_highmem_pages(); + size = count_data_pages() + PAGES_FOR_IO + SPARE_PAGES; + tmp = size; + size += highmem_size; + for_each_zone (zone) + if (populated_zone(zone)) { + tmp += snapshot_additional_pages(zone); + if (is_highmem(zone)) { + highmem_size -= + zone_page_state(zone, NR_FREE_PAGES); + } else { + tmp -= zone_page_state(zone, NR_FREE_PAGES); + tmp += zone->lowmem_reserve[ZONE_NORMAL]; + } + } + if (highmem_size < 0) + highmem_size = 0; + + tmp += highmem_size; + if (tmp > 0) { + tmp = __shrink_memory(tmp); + if (!tmp) + return -ENOMEM; + pages += tmp; + } else if (size > image_size / PAGE_SIZE) { + tmp = __shrink_memory(size - (image_size / PAGE_SIZE)); + pages += tmp; + } + printk("\b%c", p[i++%4]); + } while (tmp > 0); + do_gettimeofday(&stop); + printk("\bdone (%lu pages freed)\n", pages); + swsusp_show_speed(&start, &stop, pages, "Freed"); + 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. @@ -587,15 +286,7 @@ int swsusp_suspend(void) */ if ((error = device_power_down(PMSG_FREEZE))) { printk(KERN_ERR "Some devices failed to power down, aborting suspend\n"); - local_irq_enable(); - return error; - } - - if ((error = swsusp_swap_check())) { - printk(KERN_ERR "swsusp: cannot find swap device, try swapon -a.\n"); - device_power_up(); - local_irq_enable(); - return error; + goto Enable_irqs; } save_processor_state(); @@ -603,8 +294,11 @@ int swsusp_suspend(void) printk(KERN_ERR "Error %d suspending\n", error); /* Restore control flow magically appears here */ restore_processor_state(); - restore_highmem(); + /* NOTE: device_power_up() is just a resume() for devices + * that suspended with irqs off ... no overall powerup. + */ device_power_up(); + Enable_irqs: local_irq_enable(); return error; } @@ -612,470 +306,34 @@ int swsusp_suspend(void) int swsusp_resume(void) { int error; + local_irq_disable(); - if (device_power_down(PMSG_FREEZE)) + /* NOTE: device_power_down() is just a suspend() with irqs off; + * it has no special "power things down" semantics + */ + if (device_power_down(PMSG_PRETHAW)) 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(); - /* Code below is only ever reached in case of failure. Otherwise - * execution continues at place where swsusp_arch_suspend was called - */ - BUG_ON(!error); + error = restore_highmem(); + if (!error) { + error = swsusp_arch_resume(); + /* The code below is only ever reached in case of a failure. + * Otherwise execution continues at place where + * swsusp_arch_suspend() was called + */ + BUG_ON(!error); + /* This call to restore_highmem() undos the previous one */ + restore_highmem(); + } /* 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; } - -/** - * On resume, for storing the PBE list and the image, - * we can only use memory pages that do not conflict with the pages - * which had been used before suspend. - * - * We don't know which pages are usable until we allocate them. - * - * Allocated but unusable (ie eaten) memory pages are marked so that - * swsusp_free() can release them - */ - -unsigned long get_safe_page(gfp_t gfp_mask) -{ - unsigned long m; - - do { - m = get_zeroed_page(gfp_mask); - if (m && PageNosaveFree(virt_to_page(m))) - /* This is for swsusp_free() */ - SetPageNosave(virt_to_page(m)); - } while (m && PageNosaveFree(virt_to_page(m))); - if (m) { - /* This is for swsusp_free() */ - SetPageNosave(virt_to_page(m)); - SetPageNosaveFree(virt_to_page(m)); - } - return m; -} - -/** - * check_pagedir - We ensure here that pages that the PBEs point to - * won't collide with pages where we're going to restore from the loaded - * pages later - */ - -static int check_pagedir(struct pbe *pblist) -{ - struct pbe *p; - - /* This is necessary, so that we can free allocated pages - * in case of failure - */ - for_each_pbe (p, pblist) - p->address = 0UL; - - for_each_pbe (p, pblist) { - p->address = get_safe_page(GFP_ATOMIC); - if (!p->address) - return -ENOMEM; - } - return 0; -} - -/** - * swsusp_pagedir_relocate - It is possible, that some memory pages - * occupied by the list of PBEs collide with pages where we're going to - * restore from the loaded pages later. We relocate them here. - */ - -static struct pbe * swsusp_pagedir_relocate(struct pbe *pblist) -{ - struct zone *zone; - unsigned long zone_pfn; - struct pbe *pbpage, *tail, *p; - void *m; - int rel = 0; - - if (!pblist) /* a sanity check */ - return NULL; - - pr_debug("swsusp: Relocating pagedir (%lu pages to check)\n", - swsusp_info.pagedir_pages); - - /* 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)); - } - - /* Mark orig addresses */ - - for_each_pbe (p, pblist) - SetPageNosaveFree(virt_to_page(p->orig_address)); - - tail = pblist + PB_PAGE_SKIP; - - /* Relocate colliding pages */ - - for_each_pb_page (pbpage, pblist) { - if (PageNosaveFree(virt_to_page((unsigned long)pbpage))) { - m = (void *)get_safe_page(GFP_ATOMIC | __GFP_COLD); - if (!m) - return NULL; - memcpy(m, (void *)pbpage, PAGE_SIZE); - if (pbpage == pblist) - pblist = (struct pbe *)m; - else - tail->next = (struct pbe *)m; - pbpage = (struct pbe *)m; - - /* We have to link the PBEs again */ - for (p = pbpage; p < pbpage + PB_PAGE_SKIP; p++) - if (p->next) /* needed to save the end */ - p->next = p + 1; - - rel++; - } - tail = pbpage + PB_PAGE_SKIP; - } - - /* This is for swsusp_free() */ - for_each_pb_page (pbpage, pblist) { - SetPageNosave(virt_to_page(pbpage)); - SetPageNosaveFree(virt_to_page(pbpage)); - } - - printk("swsusp: Relocated %d pages\n", rel); - - return pblist; -} - -/* - * 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. - * The following are to signal the beginning and end of I/O. Bios - * finish asynchronously, while we want them to happen synchronously. - * A simple atomic_t, and a wait loop take care of this problem. - */ - -static atomic_t io_done = ATOMIC_INIT(0); - -static int end_io(struct bio * bio, unsigned int num, int err) -{ - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) - panic("I/O error reading memory image"); - atomic_set(&io_done, 0); - return 0; -} - -static struct block_device * resume_bdev; - -/** - * submit - submit BIO request. - * @rw: READ or WRITE. - * @off physical offset of page. - * @page: page we're reading or writing. - * - * Straight from the textbook - allocate and initialize the bio. - * If we're writing, make sure the page is marked as dirty. - * Then submit it and wait. - */ - -static int submit(int rw, pgoff_t page_off, void * page) -{ - int error = 0; - 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; - - if (bio_add_page(bio, virt_to_page(page), PAGE_SIZE, 0) < PAGE_SIZE) { - printk("swsusp: ERROR: adding page to bio at %ld\n",page_off); - error = -EFAULT; - goto Done; - } - - if (rw == WRITE) - bio_set_pages_dirty(bio); - - atomic_set(&io_done, 1); - submit_bio(rw | (1 << BIO_RW_SYNC), bio); - while (atomic_read(&io_done)) - yield(); - - Done: - bio_put(bio); - return error; -} - -static int bio_read_page(pgoff_t page_off, void * page) -{ - return submit(READ, page_off, 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.. - */ - -static const char * sanity_check(void) -{ - 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 0 - /* We can't use number of online CPUs when we use hotplug to remove them ;-))) */ - if (swsusp_info.cpus != num_possible_cpus()) - return "number of cpus"; -#endif - return NULL; -} - - -static int check_header(void) -{ - const char * reason = NULL; - int error; - - if ((error = bio_read_page(swp_offset(swsusp_header.swsusp_info), &swsusp_info))) - return error; - - /* Is this same machine? */ - if ((reason = sanity_check())) { - printk(KERN_ERR "swsusp: Resume mismatch: %s\n",reason); - return -EPERM; - } - nr_copy_pages = swsusp_info.image_pages; - return error; -} - -static int check_sig(void) -{ - int error; - - 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); - memcpy(key_iv, swsusp_header.key_iv, MAXKEY+MAXIV); - memset(swsusp_header.key_iv, 0, MAXKEY+MAXIV); - - /* - * Reset swap signature now. - */ - error = bio_write_page(0, &swsusp_header); - } else { - return -EINVAL; - } - if (!error) - pr_debug("swsusp: Signature found, resuming\n"); - return error; -} - -/** - * data_read - Read image pages from swap. - * - * You do not need to check for overlaps, check_pagedir() - * already did that. - */ - -static int data_read(struct pbe *pblist) -{ - struct pbe * p; - int error = 0; - int i = 0; - int mod = swsusp_info.image_pages / 100; - void *tfm; - - if ((error = crypto_init(0, &tfm))) - return error; - - if (!mod) - mod = 1; - - printk("swsusp: Reading image data (%lu pages): ", - swsusp_info.image_pages); - - for_each_pbe (p, pblist) { - if (!(i % mod)) - printk("\b\b\b\b%3d%%", i / mod); - - if ((error = crypto_read(p, tfm))) { - crypto_exit(tfm); - return error; - } - - i++; - } - printk("\b\b\b\bdone\n"); - crypto_exit(tfm); - return error; -} - -/** - * read_pagedir - Read page backup list pages from swap - */ - -static int read_pagedir(struct pbe *pblist) -{ - struct pbe *pbpage, *p; - unsigned i = 0; - int error; - - if (!pblist) - return -EFAULT; - - printk("swsusp: Reading pagedir (%lu pages)\n", - swsusp_info.pagedir_pages); - - for_each_pb_page (pbpage, pblist) { - unsigned long offset = swp_offset(swsusp_info.pagedir[i++]); - - error = -EFAULT; - if (offset) { - p = (pbpage + PB_PAGE_SKIP)->next; - error = bio_read_page(offset, (void *)pbpage); - (pbpage + PB_PAGE_SKIP)->next = p; - } - if (error) - break; - } - - if (!error) - BUG_ON(i != swsusp_info.pagedir_pages); - - return error; -} - - -static int check_suspend_image(void) -{ - int error = 0; - - if ((error = check_sig())) - return error; - - if ((error = check_header())) - return error; - - return 0; -} - -static int read_suspend_image(void) -{ - int error = 0; - struct pbe *p; - - if (!(p = alloc_pagedir(nr_copy_pages))) - return -ENOMEM; - - if ((error = read_pagedir(p))) - return error; - - create_pbe_list(p, nr_copy_pages); - - if (!(pagedir_nosave = swsusp_pagedir_relocate(p))) - return -ENOMEM; - - /* Allocate memory for the image and read the data from swap */ - - error = check_pagedir(pagedir_nosave); - - if (!error) - error = data_read(pagedir_nosave); - - return error; -} - -/** - * swsusp_check - Check for saved image in swap - */ - -int swsusp_check(void) -{ - int error; - - resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ); - if (!IS_ERR(resume_bdev)) { - set_blocksize(resume_bdev, PAGE_SIZE); - error = check_suspend_image(); - if (error) - blkdev_put(resume_bdev); - } else - error = PTR_ERR(resume_bdev); - - if (!error) - pr_debug("swsusp: resume file found\n"); - else - pr_debug("swsusp: Error %d check for resume file\n", error); - return error; -} - -/** - * swsusp_read - Read saved image from swap. - */ - -int swsusp_read(void) -{ - int error; - - if (IS_ERR(resume_bdev)) { - pr_debug("swsusp: block device not initialised\n"); - return PTR_ERR(resume_bdev); - } - - error = read_suspend_image(); - blkdev_put(resume_bdev); - memset(key_iv, 0, MAXKEY+MAXIV); - - if (!error) - pr_debug("swsusp: Reading resume file was successful\n"); - else - pr_debug("swsusp: 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); -}