[PATCH] swsusp: low level interface

Introduce the low level interface that can be used for handling the
snapshot of the system memory by the in-kernel swap-writing/reading code of
swsusp and the userland interface code (to be introduced shortly).

Also change the way in which swsusp records the allocated swap pages and,
consequently, simplifies the in-kernel swap-writing/reading code (this is
necessary for the userland interface too).  To this end, it introduces two
helper functions in mm/swapfile.c, so that the swsusp code does not refer
directly to the swap internals.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/swap.h

@@ -234,14 +234,15 @@ extern struct page * read_swap_cache_async(swp_entry_t, struct vm_area_struct *v
 /* linux/mm/swapfile.c */
 extern long total_swap_pages;
 extern unsigned int nr_swapfiles;
-extern struct swap_info_struct swap_info[];
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
-extern swp_entry_t get_swap_page_of_type(int type);
+extern swp_entry_t get_swap_page_of_type(int);
 extern int swap_duplicate(swp_entry_t);
 extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern void swap_free(swp_entry_t);
 extern void free_swap_and_cache(swp_entry_t);
+extern int swap_type_of(dev_t);
+extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct swap_info_struct *, pgoff_t);
 extern struct swap_info_struct *get_swap_info_struct(unsigned);
 extern int can_share_swap_page(struct page *);

kernel/power/disk.c

@@ -26,9 +26,9 @@ 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_write(void);
 extern int swsusp_check(void);
-extern int swsusp_read(struct pbe **pblist_ptr);
+extern int swsusp_read(void);
 extern void swsusp_close(void);
 extern int swsusp_resume(void);
 
@@ -70,10 +70,6 @@ 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) {
@@ -145,7 +141,7 @@ 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 +212,7 @@ 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;
 	}

kernel/power/power.h

@@ -37,21 +37,31 @@ 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 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);
 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);
+
+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);

mm/swapfile.c

@@ -45,7 +45,7 @@ static const char Unused_offset[] = "Unused swap offset entry ";
 
 struct swap_list_t swap_list = {-1, -1};
 
-struct swap_info_struct swap_info[MAX_SWAPFILES];
+static struct swap_info_struct swap_info[MAX_SWAPFILES];
 
 static DEFINE_MUTEX(swapon_mutex);
 
@@ -417,6 +417,59 @@ void free_swap_and_cache(swp_entry_t entry)
 	}
 }
 
+#ifdef CONFIG_SOFTWARE_SUSPEND
+/*
+ * Find the swap type that corresponds to given device (if any)
+ *
+ * This is needed for software suspend and is done in such a way that inode
+ * aliasing is allowed.
+ */
+int swap_type_of(dev_t device)
+{
+	int i;
+
+	if (!device)
+		return -EINVAL;
+	spin_lock(&swap_lock);
+	for (i = 0; i < nr_swapfiles; i++) {
+		struct inode *inode;
+
+		if (!(swap_info[i].flags & SWP_WRITEOK))
+			continue;
+		inode = swap_info->swap_file->f_dentry->d_inode;
+		if (S_ISBLK(inode->i_mode) &&
+		    device == MKDEV(imajor(inode), iminor(inode))) {
+			spin_unlock(&swap_lock);
+			return i;
+		}
+	}
+	spin_unlock(&swap_lock);
+	return -ENODEV;
+}
+
+/*
+ * Return either the total number of swap pages of given type, or the number
+ * of free pages of that type (depending on @free)
+ *
+ * This is needed for software suspend
+ */
+unsigned int count_swap_pages(int type, int free)
+{
+	unsigned int n = 0;
+
+	if (type < nr_swapfiles) {
+		spin_lock(&swap_lock);
+		if (swap_info[type].flags & SWP_WRITEOK) {
+			n = swap_info[type].pages;
+			if (free)
+				n -= swap_info[type].inuse_pages;
+		}
+		spin_unlock(&swap_lock);
+	}
+	return n;
+}
+#endif
+
 /*
  * No need to decide whether this PTE shares the swap entry with others,
  * just let do_wp_page work it out if a write is requested later - to