diff options
Diffstat (limited to 'kernel/power')
| -rw-r--r-- | kernel/power/Makefile | 2 | ||||
| -rw-r--r-- | kernel/power/disk.c | 20 | ||||
| -rw-r--r-- | kernel/power/main.c | 2 | ||||
| -rw-r--r-- | kernel/power/pm.c | 21 | ||||
| -rw-r--r-- | kernel/power/power.h | 75 | ||||
| -rw-r--r-- | kernel/power/process.c | 61 | ||||
| -rw-r--r-- | kernel/power/snapshot.c | 335 | ||||
| -rw-r--r-- | kernel/power/swap.c | 544 | ||||
| -rw-r--r-- | kernel/power/swsusp.c | 887 | ||||
| -rw-r--r-- | kernel/power/user.c | 333 |
10 files changed, 1393 insertions, 887 deletions
diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 04be7d0d96a..8d0af3d37a4 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -5,7 +5,7 @@ endif obj-y := main.o process.o console.o obj-$(CONFIG_PM_LEGACY) += pm.o -obj-$(CONFIG_SOFTWARE_SUSPEND) += swsusp.o disk.o snapshot.o +obj-$(CONFIG_SOFTWARE_SUSPEND) += swsusp.o disk.o snapshot.o swap.o user.o obj-$(CONFIG_SUSPEND_SMP) += smp.o diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 0b43847dc98..81d4d982f3f 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -22,17 +22,6 @@ #include "power.h" -extern suspend_disk_method_t pm_disk_mode; - -extern int swsusp_shrink_memory(void); -extern int swsusp_suspend(void); -extern int swsusp_write(struct pbe *pblist, unsigned int nr_pages); -extern int swsusp_check(void); -extern int swsusp_read(struct pbe **pblist_ptr); -extern void swsusp_close(void); -extern int swsusp_resume(void); - - static int noresume = 0; char resume_file[256] = CONFIG_PM_STD_PARTITION; dev_t swsusp_resume_device; @@ -70,10 +59,6 @@ static void power_down(suspend_disk_method_t mode) while(1); } - -static int in_suspend __nosavedata = 0; - - static inline void platform_finish(void) { if (pm_disk_mode == PM_DISK_PLATFORM) { @@ -87,7 +72,6 @@ static int prepare_processes(void) int error; pm_prepare_console(); - sys_sync(); disable_nonboot_cpus(); if (freeze_processes()) { @@ -145,7 +129,7 @@ int pm_suspend_disk(void) if (in_suspend) { device_resume(); pr_debug("PM: writing image.\n"); - error = swsusp_write(pagedir_nosave, nr_copy_pages); + error = swsusp_write(); if (!error) power_down(pm_disk_mode); else { @@ -216,7 +200,7 @@ static int software_resume(void) pr_debug("PM: Reading swsusp image.\n"); - if ((error = swsusp_read(&pagedir_nosave))) { + if ((error = swsusp_read())) { swsusp_free(); goto Thaw; } diff --git a/kernel/power/main.c b/kernel/power/main.c index 9cb235cba4a..ee371f50cca 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -103,7 +103,7 @@ static int suspend_prepare(suspend_state_t state) } -static int suspend_enter(suspend_state_t state) +int suspend_enter(suspend_state_t state) { int error = 0; unsigned long flags; diff --git a/kernel/power/pm.c b/kernel/power/pm.c index 33c508e857d..0f6908cce1d 100644 --- a/kernel/power/pm.c +++ b/kernel/power/pm.c @@ -25,6 +25,7 @@ #include <linux/pm.h> #include <linux/pm_legacy.h> #include <linux/interrupt.h> +#include <linux/mutex.h> int pm_active; @@ -40,7 +41,7 @@ int pm_active; * until a resume but that will be fine. */ -static DECLARE_MUTEX(pm_devs_lock); +static DEFINE_MUTEX(pm_devs_lock); static LIST_HEAD(pm_devs); /** @@ -67,9 +68,9 @@ struct pm_dev *pm_register(pm_dev_t type, dev->id = id; dev->callback = callback; - down(&pm_devs_lock); + mutex_lock(&pm_devs_lock); list_add(&dev->entry, &pm_devs); - up(&pm_devs_lock); + mutex_unlock(&pm_devs_lock); } return dev; } @@ -85,9 +86,9 @@ struct pm_dev *pm_register(pm_dev_t type, void pm_unregister(struct pm_dev *dev) { if (dev) { - down(&pm_devs_lock); + mutex_lock(&pm_devs_lock); list_del(&dev->entry); - up(&pm_devs_lock); + mutex_unlock(&pm_devs_lock); kfree(dev); } @@ -118,7 +119,7 @@ void pm_unregister_all(pm_callback callback) if (!callback) return; - down(&pm_devs_lock); + mutex_lock(&pm_devs_lock); entry = pm_devs.next; while (entry != &pm_devs) { struct pm_dev *dev = list_entry(entry, struct pm_dev, entry); @@ -126,7 +127,7 @@ void pm_unregister_all(pm_callback callback) if (dev->callback == callback) __pm_unregister(dev); } - up(&pm_devs_lock); + mutex_unlock(&pm_devs_lock); } /** @@ -234,7 +235,7 @@ int pm_send_all(pm_request_t rqst, void *data) { struct list_head *entry; - down(&pm_devs_lock); + mutex_lock(&pm_devs_lock); entry = pm_devs.next; while (entry != &pm_devs) { struct pm_dev *dev = list_entry(entry, struct pm_dev, entry); @@ -246,13 +247,13 @@ int pm_send_all(pm_request_t rqst, void *data) */ if (rqst == PM_SUSPEND) pm_undo_all(dev); - up(&pm_devs_lock); + mutex_unlock(&pm_devs_lock); return status; } } entry = entry->next; } - up(&pm_devs_lock); + mutex_unlock(&pm_devs_lock); return 0; } diff --git a/kernel/power/power.h b/kernel/power/power.h index 388dba68084..f06f12f2176 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -8,6 +8,7 @@ struct swsusp_info { int cpus; unsigned long image_pages; unsigned long pages; + unsigned long size; } __attribute__((aligned(PAGE_SIZE))); @@ -37,21 +38,79 @@ extern struct subsystem power_subsys; /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; -extern unsigned int nr_copy_pages; extern struct pbe *pagedir_nosave; /* Preferred image size in bytes (default 500 MB) */ extern unsigned long image_size; +extern int in_suspend; +extern dev_t swsusp_resume_device; extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); extern unsigned int count_data_pages(void); -extern void free_pagedir(struct pbe *pblist); -extern void release_eaten_pages(void); -extern struct pbe *alloc_pagedir(unsigned nr_pages, gfp_t gfp_mask, int safe_needed); + +struct snapshot_handle { + loff_t offset; + unsigned int page; + unsigned int page_offset; + unsigned int prev; + struct pbe *pbe; + void *buffer; + unsigned int buf_offset; +}; + +#define data_of(handle) ((handle).buffer + (handle).buf_offset) + +extern int snapshot_read_next(struct snapshot_handle *handle, size_t count); +extern int snapshot_write_next(struct snapshot_handle *handle, size_t count); +int snapshot_image_loaded(struct snapshot_handle *handle); + +#define SNAPSHOT_IOC_MAGIC '3' +#define SNAPSHOT_FREEZE _IO(SNAPSHOT_IOC_MAGIC, 1) +#define SNAPSHOT_UNFREEZE _IO(SNAPSHOT_IOC_MAGIC, 2) +#define SNAPSHOT_ATOMIC_SNAPSHOT _IOW(SNAPSHOT_IOC_MAGIC, 3, void *) +#define SNAPSHOT_ATOMIC_RESTORE _IO(SNAPSHOT_IOC_MAGIC, 4) +#define SNAPSHOT_FREE _IO(SNAPSHOT_IOC_MAGIC, 5) +#define SNAPSHOT_SET_IMAGE_SIZE _IOW(SNAPSHOT_IOC_MAGIC, 6, unsigned long) +#define SNAPSHOT_AVAIL_SWAP _IOR(SNAPSHOT_IOC_MAGIC, 7, void *) +#define SNAPSHOT_GET_SWAP_PAGE _IOR(SNAPSHOT_IOC_MAGIC, 8, void *) +#define SNAPSHOT_FREE_SWAP_PAGES _IO(SNAPSHOT_IOC_MAGIC, 9) +#define SNAPSHOT_SET_SWAP_FILE _IOW(SNAPSHOT_IOC_MAGIC, 10, unsigned int) +#define SNAPSHOT_S2RAM _IO(SNAPSHOT_IOC_MAGIC, 11) +#define SNAPSHOT_IOC_MAXNR 11 + +/** + * The bitmap is used for tracing allocated swap pages + * + * The entire bitmap consists of a number of bitmap_page + * structures linked with the help of the .next member. + * Thus each page can be allocated individually, so we only + * need to make 0-order memory allocations to create + * the bitmap. + */ + +#define BITMAP_PAGE_SIZE (PAGE_SIZE - sizeof(void *)) +#define BITMAP_PAGE_CHUNKS (BITMAP_PAGE_SIZE / sizeof(long)) +#define BITS_PER_CHUNK (sizeof(long) * 8) +#define BITMAP_PAGE_BITS (BITMAP_PAGE_CHUNKS * BITS_PER_CHUNK) + +struct bitmap_page { + unsigned long chunks[BITMAP_PAGE_CHUNKS]; + struct bitmap_page *next; +}; + +extern void free_bitmap(struct bitmap_page *bitmap); +extern struct bitmap_page *alloc_bitmap(unsigned int nr_bits); +extern unsigned long alloc_swap_page(int swap, struct bitmap_page *bitmap); +extern void free_all_swap_pages(int swap, struct bitmap_page *bitmap); + +extern int swsusp_check(void); +extern int swsusp_shrink_memory(void); extern void swsusp_free(void); -extern int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed); -extern unsigned int snapshot_nr_pages(void); -extern struct pbe *snapshot_pblist(void); -extern void snapshot_pblist_set(struct pbe *pblist); +extern int swsusp_suspend(void); +extern int swsusp_resume(void); +extern int swsusp_read(void); +extern int swsusp_write(void); +extern void swsusp_close(void); +extern int suspend_enter(suspend_state_t state); diff --git a/kernel/power/process.c b/kernel/power/process.c index 28de118f7a0..8ac7c35fad7 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -12,11 +12,12 @@ #include <linux/interrupt.h> #include <linux/suspend.h> #include <linux/module.h> +#include <linux/syscalls.h> /* * Timeout for stopping processes */ -#define TIMEOUT (6 * HZ) +#define TIMEOUT (20 * HZ) static inline int freezeable(struct task_struct * p) @@ -54,38 +55,62 @@ void refrigerator(void) current->state = save; } +static inline void freeze_process(struct task_struct *p) +{ + unsigned long flags; + + if (!freezing(p)) { + freeze(p); + spin_lock_irqsave(&p->sighand->siglock, flags); + signal_wake_up(p, 0); + spin_unlock_irqrestore(&p->sighand->siglock, flags); + } +} + /* 0 = success, else # of processes that we failed to stop */ int freeze_processes(void) { - int todo; + int todo, nr_user, user_frozen; unsigned long start_time; struct task_struct *g, *p; unsigned long flags; printk( "Stopping tasks: " ); start_time = jiffies; + user_frozen = 0; do { - todo = 0; + nr_user = todo = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { if (!freezeable(p)) continue; if (frozen(p)) continue; - - freeze(p); - spin_lock_irqsave(&p->sighand->siglock, flags); - signal_wake_up(p, 0); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - todo++; + if (p->mm && !(p->flags & PF_BORROWED_MM)) { + /* The task is a user-space one. + * Freeze it unless there's a vfork completion + * pending + */ + if (!p->vfork_done) + freeze_process(p); + nr_user++; + } else { + /* Freeze only if the user space is frozen */ + if (user_frozen) + freeze_process(p); + todo++; + } } while_each_thread(g, p); read_unlock(&tasklist_lock); + todo += nr_user; + if (!user_frozen && !nr_user) { + sys_sync(); + start_time = jiffies; + } + user_frozen = !nr_user; yield(); /* Yield is okay here */ - if (todo && time_after(jiffies, start_time + TIMEOUT)) { - printk( "\n" ); - printk(KERN_ERR " stopping tasks failed (%d tasks remaining)\n", todo ); + if (todo && time_after(jiffies, start_time + TIMEOUT)) break; - } } while(todo); /* This does not unfreeze processes that are already frozen @@ -94,8 +119,14 @@ int freeze_processes(void) * but it cleans up leftover PF_FREEZE requests. */ if (todo) { + printk( "\n" ); + printk(KERN_ERR " stopping tasks timed out " + "after %d seconds (%d tasks remaining):\n", + TIMEOUT / HZ, todo); read_lock(&tasklist_lock); - do_each_thread(g, p) + do_each_thread(g, p) { + if (freezeable(p) && !frozen(p)) + printk(KERN_ERR " %s\n", p->comm); if (freezing(p)) { pr_debug(" clean up: %s\n", p->comm); p->flags &= ~PF_FREEZE; @@ -103,7 +134,7 @@ int freeze_processes(void) recalc_sigpending_tsk(p); spin_unlock_irqrestore(&p->sighand->siglock, flags); } - while_each_thread(g, p); + } while_each_thread(g, p); read_unlock(&tasklist_lock); return todo; } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 8d5a5986d62..c5863d02c89 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -10,6 +10,7 @@ */ +#include <linux/version.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/suspend.h> @@ -34,7 +35,9 @@ #include "power.h" struct pbe *pagedir_nosave; -unsigned int nr_copy_pages; +static unsigned int nr_copy_pages; +static unsigned int nr_meta_pages; +static unsigned long *buffer; #ifdef CONFIG_HIGHMEM unsigned int count_highmem_pages(void) @@ -80,7 +83,7 @@ static int save_highmem_zone(struct zone *zone) void *kaddr; unsigned long pfn = zone_pfn + zone->zone_start_pfn; - if (!(pfn%1000)) + if (!(pfn%10000)) printk("."); if (!pfn_valid(pfn)) continue; @@ -119,13 +122,15 @@ int save_highmem(void) struct zone *zone; int res = 0; - pr_debug("swsusp: Saving Highmem\n"); + pr_debug("swsusp: Saving Highmem"); + drain_local_pages(); for_each_zone (zone) { if (is_highmem(zone)) res = save_highmem_zone(zone); if (res) return res; } + printk("\n"); return 0; } @@ -235,7 +240,7 @@ static void copy_data_pages(struct pbe *pblist) * free_pagedir - free pages allocated with alloc_pagedir() */ -void free_pagedir(struct pbe *pblist) +static void free_pagedir(struct pbe *pblist) { struct pbe *pbe; @@ -301,7 +306,7 @@ struct eaten_page { static struct eaten_page *eaten_pages = NULL; -void release_eaten_pages(void) +static void release_eaten_pages(void) { struct eaten_page *p, *q; @@ -376,7 +381,6 @@ struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed if (!nr_pages) return NULL; - pr_debug("alloc_pagedir(): nr_pages = %d\n", nr_pages); pblist = alloc_image_page(gfp_mask, safe_needed); /* FIXME: rewrite this ugly loop */ for (pbe = pblist, num = PBES_PER_PAGE; pbe && num < nr_pages; @@ -388,7 +392,7 @@ struct pbe *alloc_pagedir(unsigned int nr_pages, gfp_t gfp_mask, int safe_needed free_pagedir(pblist); pblist = NULL; } else - create_pbe_list(pblist, nr_pages); + create_pbe_list(pblist, nr_pages); return pblist; } @@ -414,6 +418,10 @@ void swsusp_free(void) } } } + nr_copy_pages = 0; + nr_meta_pages = 0; + pagedir_nosave = NULL; + buffer = NULL; } @@ -437,7 +445,7 @@ static int enough_free_mem(unsigned int nr_pages) (nr_pages + PBES_PER_PAGE - 1) / PBES_PER_PAGE); } -int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed) +static int alloc_data_pages(struct pbe *pblist, gfp_t gfp_mask, int safe_needed) { struct pbe *p; @@ -504,7 +512,318 @@ asmlinkage int swsusp_save(void) */ nr_copy_pages = nr_pages; + nr_meta_pages = (nr_pages * sizeof(long) + PAGE_SIZE - 1) >> PAGE_SHIFT; printk("swsusp: critical section/: done (%d pages copied)\n", nr_pages); return 0; } + +static void init_header(struct swsusp_info *info) +{ + memset(info, 0, sizeof(struct swsusp_info)); + info->version_code = LINUX_VERSION_CODE; + info->num_physpages = num_physpages; + memcpy(&info->uts, &system_utsname, sizeof(system_utsname)); + info->cpus = num_online_cpus(); + info->image_pages = nr_copy_pages; + info->pages = nr_copy_pages + nr_meta_pages + 1; + info->size = info->pages; + info->size <<= PAGE_SHIFT; +} + +/** + * 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 inline struct pbe *pack_orig_addresses(unsigned long *buf, struct pbe *pbe) +{ + 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; +} + +/** + * snapshot_read_next - used for reading the system memory snapshot. + * + * On the first call to it @handle should point to a zeroed + * snapshot_handle structure. The structure gets updated and a pointer + * to it should be passed to this function every next time. + * + * The @count parameter should contain the number of bytes the caller + * wants to read from the snapshot. It must not be zero. + * + * On success the function returns a positive number. Then, the caller + * is allowed to read up to the returned number of bytes from the memory + * location computed by the data_of() macro. The number returned + * may be smaller than @count, but this only happens if the read would + * cross a page boundary otherwise. + * + * The function returns 0 to indicate the end of data stream condition, + * and a negative number is returned on error. In such cases the + * structure pointed to by @handle is not updated and should not be used + * any more. + */ + +int snapshot_read_next(struct snapshot_handle *handle, size_t count) +{ + if (handle->page > nr_meta_pages + nr_copy_pages) + return 0; + if (!buffer) { + /* This makes the buffer be freed by swsusp_free() */ + buffer = alloc_image_page(GFP_ATOMIC, 0); + if (!buffer) + return -ENOMEM; + } + if (!handle->offset) { + init_header((struct swsusp_info *)buffer); + handle->buffer = buffer; + handle->pbe = pagedir_nosave; + } + if (handle->prev < handle->page) { + if (handle->page <= nr_meta_pages) { + handle->pbe = pack_orig_addresses(buffer, handle->pbe); + if (!handle->pbe) + handle->pbe = pagedir_nosave; + } else { + handle->buffer = (void *)handle->pbe->address; + handle->pbe = handle->pbe->next; + } + handle->prev = handle->page; + } + handle->buf_offset = handle->page_offset; + if (handle->page_offset + count >= PAGE_SIZE) { + count = PAGE_SIZE - handle->page_offset; + handle->page_offset = 0; + handle->page++; + } else { + handle->page_offset += count; + } + handle->offset += count; + return count; +} + +/** + * 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 mark_unsafe_pages(struct pbe *pblist) +{ + struct zone *zone; + unsigned long zone_pfn; + struct pbe *p; + + if (!pblist) /* a sanity check */ + return -EINVAL; + + /* 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) { + if (virt_addr_valid(p->orig_address)) + SetPageNosaveFree(virt_to_page(p->orig_address)); + else + return -EFAULT; + } + + return 0; +} + +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; + } +} + +static int check_header(struct swsusp_info *info) +{ + char *reason = NULL; + + if (info->version_code != LINUX_VERSION_CODE) + reason = "kernel version"; + if (info->num_physpages != num_physpages) + reason = "memory size"; + if (strcmp(info->uts.sysname,system_utsname.sysname)) + reason = "system type"; + if (strcmp(info->uts.release,system_utsname.release)) + reason = "kernel release"; + if (strcmp(info->uts.version,system_utsname.version)) + reason = "version"; + if (strcmp(info->uts.machine,system_utsname.machine)) + reason = "machine"; + if (reason) { + printk(KERN_ERR "swsusp: Resume mismatch: %s\n", reason); + return -EPERM; + } + return 0; +} + +/** + * load header - check the image header and copy data from it + */ + +static int load_header(struct snapshot_handle *handle, + struct swsusp_info *info) +{ + int error; + struct pbe *pblist; + + error = check_header(info); + if (!error) { + pblist = alloc_pagedir(info->image_pages, GFP_ATOMIC, 0); + if (!pblist) + return -ENOMEM; + pagedir_nosave = pblist; + handle->pbe = pblist; + nr_copy_pages = info->image_pages; + nr_meta_pages = info->pages - info->image_pages - 1; + } + return error; +} + +/** + * unpack_orig_addresses - copy the elements of @buf[] (1 page) to + * the PBEs in the list starting at @pbe + */ + +static inline struct pbe *unpack_orig_addresses(unsigned long *buf, + struct pbe *pbe) +{ + int j; + + for (j = 0; j < PAGE_SIZE / sizeof(long) && pbe; j++) { + pbe->orig_address = buf[j]; + pbe = pbe->next; + } + return pbe; +} + +/** + * create_image - use metadata contained in the PBE list + * pointed to by pagedir_nosave to mark the pages that will + * be overwritten in the process of restoring the system + * memory state from the image and allocate memory for + * the image avoiding these pages + */ + +static int create_image(struct snapshot_handle *handle) +{ + int error = 0; + struct pbe *p, *pblist; + + p = pagedir_nosave; + error = mark_unsafe_pages(p); + if (!error) { + pblist = alloc_pagedir(nr_copy_pages, GFP_ATOMIC, 1); + if (pblist) + copy_page_backup_list(pblist, p); + free_pagedir(p); + if (!pblist) + error = -ENOMEM; + } + if (!error) + error = alloc_data_pages(pblist, GFP_ATOMIC, 1); + if (!error) { + release_eaten_pages(); + pagedir_nosave = pblist; + } else { + pagedir_nosave = NULL; + handle->pbe = NULL; + nr_copy_pages = 0; + nr_meta_pages = 0; + } + return error; +} + +/** + * snapshot_write_next - used for writing the system memory snapshot. + * + * On the first call to it @handle should point to a zeroed + * snapshot_handle structure. The structure gets updated and a pointer + * to it should be passed to this function every next time. + * + * The @count parameter should contain the number of bytes the caller + * wants to write to the image. It must not be zero. + * + * On success the function returns a positive number. Then, the caller + * is allowed to write up to the returned number of bytes to the memory + * location computed by the data_of() macro. The number returned + * may be smaller than @count, but this only happens if the write would + * cross a page boundary otherwise. + * + * The function returns 0 to indicate the "end of file" condition, + * and a negative number is returned on error. In such cases the + * structure pointed to by @handle is not updated and should not be used + * any more. + */ + +int snapshot_write_next(struct snapshot_handle *handle, size_t count) +{ + int error = 0; + + if (handle->prev && handle->page > nr_meta_pages + nr_copy_pages) + return 0; + if (!buffer) { + /* This makes the buffer be freed by swsusp_free() */ + buffer = alloc_image_page(GFP_ATOMIC, 0); + if (!buffer) + return -ENOMEM; + } + if (!handle->offset) + handle->buffer = buffer; + if (handle->prev < handle->page) { + if (!handle->prev) { + error = load_header(handle, (struct swsusp_info *)buffer); + if (error) + return error; + } else if (handle->prev <= nr_meta_pages) { + handle->pbe = unpack_orig_addresses(buffer, handle->pbe); + if (!handle->pbe) { + error = create_image(handle); + if (error) + return error; + handle->pbe = pagedir_nosave; + handle->buffer = (void *)handle->pbe->address; + } + } else { + handle->pbe = handle->pbe->next; + handle->buffer = (void *)handle->pbe->address; + } + handle->prev = handle->page; + } + handle->buf_offset = handle->page_offset; + if (handle->page_offset + count >= PAGE_SIZE) { + count = PAGE_SIZE - handle->page_offset; + handle->page_offset = 0; + handle->page++; + } else { + handle->page_offset += count; + } + handle->offset += count; + return count; +} + +int snapshot_image_loaded(struct snapshot_handle *handle) +{ + return !(!handle->pbe || handle->pbe->next || !nr_copy_pages || + handle->page <= nr_meta_pages + nr_copy_pages); +} diff --git a/kernel/power/swap.c b/kernel/power/swap.c new file mode 100644 index 00000000000..9177f3f73a6 --- /dev/null +++ b/kernel/power/swap.c @@ -0,0 +1,544 @@ +/* + * linux/kernel/power/swap.c + * + * This file provides functions for reading the suspend image from + * and writing it to a swap partition. + * + * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz> + * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> + * + * This file is released under the GPLv2. + * + */ + +#include <linux/module.h> +#include <linux/smp_lock.h> +#include <linux/file.h> +#include <linux/utsname.h> +#include <linux/version.h> +#include <linux/delay.h> +#include <linux/bitops.h> +#include <linux/genhd.h> +#include <linux/device.h> +#include <linux/buffer_head.h> +#include <linux/bio.h> +#include <linux/swap.h> +#include <linux/swapops.h> +#include <linux/pm.h> + +#include "power.h" + +extern char resume_file[]; + +#define SWSUSP_SIG "S1SUSPEND" + +static struct swsusp_header { + char reserved[PAGE_SIZE - 20 - sizeof(swp_entry_t)]; + swp_entry_t image; + char orig_sig[10]; + char sig[10]; +} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header; + +/* + * Saving part... + */ + +static unsigned short root_swap = 0xffff; + +static int mark_swapfiles(swp_entry_t start) +{ + 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); + swsusp_header.image = start; + 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; +} + +/** + * swsusp_swap_check - check if the resume device is a swap device + * and get its index (if so) + */ + +static int swsusp_swap_check(void) /* This is called before saving image */ +{ + int res = swap_type_of(swsusp_resume_device); + + if (res >= 0) { + root_swap = res; + return 0; + } + return res; +} + +/** + * write_page - Write one page to given swap location. + * @buf: Address we're writing. + * @offset: Offset of the swap page we're writing to. + */ + +static int write_page(void *buf, unsigned long offset) +{ + swp_entry_t entry; + int error = -ENOSPC; + + if (offset) { + entry = swp_entry(root_swap, offset); + error = rw_swap_page_sync(WRITE, entry, virt_to_page(buf)); + } + return error; +} + +/* + * The swap map is a data structure used for keeping track of each page + * written to a swap partition. It consists of many swap_map_page + * structures that contain each an array of MAP_PAGE_SIZE swap entries. + * These structures are stored on the swap and linked together with the + * help of the .next_swap member. + * + * The swap map is created during suspend. The swap map pages are + * allocated and populated one at a time, so we only need one memory + * page to set up the entire structure. + * + * During resume we also only need to use one swap_map_page structure + * at a time. + */ + +#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(long) - 1) + +struct swap_map_page { + unsigned long entries[MAP_PAGE_ENTRIES]; + unsigned long next_swap; +}; + +/** + * The swap_map_handle structure is used for handling swap in + * a file-alike way + */ + +struct swap_map_handle { + struct swap_map_page *cur; + unsigned long cur_swap; + struct bitmap_page *bitmap; + unsigned int k; +}; + +static void release_swap_writer(struct swap_map_handle *handle) +{ + if (handle->cur) + free_page((unsigned long)handle->cur); + handle->cur = NULL; + if (handle->bitmap) + free_bitmap(handle->bitmap); + handle->bitmap = NULL; +} + +static int get_swap_writer(struct swap_map_handle *handle) +{ + handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL); + if (!handle->cur) + return -ENOMEM; + handle->bitmap = alloc_bitmap(count_swap_pages(root_swap, 0)); + if (!handle->bitmap) { + release_swap_writer(handle); + return -ENOMEM; + } + handle->cur_swap = alloc_swap_page(root_swap, handle->bitmap); + if (!handle->cur_swap) { + release_swap_writer(handle); + return -ENOSPC; + } + handle->k = 0; + return 0; +} + +static int swap_write_page(struct swap_map_handle *handle, void *buf) +{ + int error; + unsigned long offset; + + if (!handle->cur) + return -EINVAL; + offset = alloc_swap_page(root_swap, handle->bitmap); + error = write_page(buf, offset); + if (error) + return error; + handle->cur->entries[handle->k++] = offset; + if (handle->k >= MAP_PAGE_ENTRIES) { + offset = alloc_swap_page(root_swap, handle->bitmap); + if (!offset) + return -ENOSPC; + handle->cur->next_swap = offset; + error = write_page(handle->cur, handle->cur_swap); + if (error) + return error; + memset(handle->cur, 0, PAGE_SIZE); + handle->cur_swap = offset; + handle->k = 0; + } + return 0; +} + +static int flush_swap_writer(struct swap_map_handle *handle) +{ + if (handle->cur && handle->cur_swap) + return write_page(handle->cur, handle->cur_swap); + else + return -EINVAL; +} + +/** + * save_image - save the suspend image data + */ + +static int save_image(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_pages) +{ + unsigned int m; + int ret; + int error = 0; + + printk("Saving image data pages (%u pages) ... ", nr_pages); + m = nr_pages / 100; + if (!m) + m = 1; + nr_pages = 0; + do { + ret = snapshot_read_next(snapshot, PAGE_SIZE); + if (ret > 0) { + error = swap_write_page(handle, data_of(*snapshot)); + if (error) + break; + if (!(nr_pages % m)) + printk("\b\b\b\b%3d%%", nr_pages / m); + nr_pages++; + } + } while (ret > 0); + if (!error) + printk("\b\b\b\bdone\n"); + return error; +} + +/** + * enough_swap - Make sure we have enough swap to save the image. + * + * Returns TRUE or FALSE after checking the total amount of swap + * space avaiable from the resume partition. + */ + +static int enough_swap(unsigned int nr_pages) +{ + unsigned int free_swap = count_swap_pages(root_swap, 1); + + 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); +} + +/** + * swsusp_write - Write entire image and metadata. + * + * 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) +{ + struct swap_map_handle handle; + struct snapshot_handle snapshot; + struct swsusp_info *header; + unsigned long start; + int error; + + if ((error = swsusp_swap_check())) { + printk(KERN_ERR "swsusp: Cannot find swap device, try swapon -a.\n"); + return error; + } + memset(&snapshot, 0, sizeof(struct snapshot_handle)); + error = snapshot_read_next(&snapshot, PAGE_SIZE); + if (error < PAGE_SIZE) + return error < 0 ? error : -EFAULT; + header = (struct swsusp_info *)data_of(snapshot); + if (!enough_swap(header->pages)) { + printk(KERN_ERR "swsusp: Not enough free swap\n"); + return -ENOSPC; + } + error = get_swap_writer(&handle); + if (!error) { + start = handle.cur_swap; + error = |