@@ -174,6 +174,10 @@ prototypes:
 	int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
 	int (*launder_page) (struct page *);
+	int (*swapon) (struct file *);
+	int (*swapoff) (struct file *);
+	int (*swap_out) (struct file *, struct page *, struct writeback_control *);
+	int (*swap_in)  (struct file *, struct page *);
 
 locking rules:
 	All except set_page_dirty may block

@@ -193,6 +197,10 @@ invalidatepage:		no	yes
 releasepage:		no	yes
 direct_IO:		no
 launder_page:		no	yes
+swapon			no
+swapoff			no
+swap_out		no	yes, unlocks
+swap_in			no	yes, unlocks
 
 	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).

@@ -292,6 +300,20 @@ cleaned, or an error value if not. Note that in order to prevent the page
 getting mapped back in and redirtied, it needs to be kept locked
 across the entire operation.
 
+	->swapon() will be called with a non-zero argument on files backing
+(non block device backed) swapfiles. A return value of zero indicates success,
+in which case this file can be used for backing swapspace. The swapspace
+operations will be proxied to the address space operations.
+
+	->swapoff() will be called in the sys_swapoff() path when ->swapon()
+returned success.
+
+	->swap_out() when swapon() returned success, this method is used to
+write the swap page.
+
+	->swap_in() when swapon() returned success, this method is used to
+read the swap page.
+
 	Note: currently almost all instances of address_space methods are
 using BKL for internal serialization and that's one of the worst sources
 of contention. Normally they are calling library functions (in fs/buffer.c)

@@ -542,6 +542,11 @@ struct address_space_operations {
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
 	int (*error_remove_page) (struct mapping *mapping, struct page *page);
+	int (*swapon)(struct file *);
+	int (*swapoff)(struct file *);
+	int (*swap_out)(struct file *file, struct page *page,
+			struct writeback_control *wbc);
+	int (*swap_in)(struct file *file, struct page *page);
 };
 
   writepage: called by the VM to write a dirty page to backing store.

@@ -706,6 +711,19 @@ struct address_space_operations {
 	unless you have them locked or reference counts increased.
 
 
+  swapon: Called when swapon is used on a file. A
+	return value of zero indicates success, in which case this
+	file can be used to back swapspace. The swapspace operations
+	will be proxied to this address space's ->swap_{out,in} methods.
+
+  swapoff: Called during swapoff on files where swapon was successfull.
+
+  swap_out: Called to write a swapcache page to a backing store, similar to
+	writepage.
+
+  swap_in: Called to read a swapcache page from a backing store, similar to
+	readpage.
+
 The File Object
 ===============
 

@@ -329,6 +329,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void block_sync_page(struct page *) { }
 
 #endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */

@@ -612,6 +612,15 @@ struct address_space_operations {
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
+
+	/*
+	 * swapfile support
+	 */
+	int (*swapon)(struct file *file);
+	int (*swapoff)(struct file *file);
+	int (*swap_out)(struct file *file, struct page *page,
+			struct writeback_control *wbc);
+	int (*swap_in)(struct file *file, struct page *page);
 };
 
 /*

@@ -147,7 +147,7 @@ enum {
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
-					/* add others here before... */
+	SWP_FILE	= (1 << 7),	/* file swap area */
 	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
 };
 

@@ -293,6 +293,8 @@ extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
 extern int swap_writepage(struct page *page, struct writeback_control *wbc);
+extern void swap_sync_page(struct page *page);
+extern int swap_set_page_dirty(struct page *page);
 extern void end_swap_bio_read(struct bio *bio, int err);
 
 /* linux/mm/swap_state.c */

@@ -329,6 +331,7 @@ extern int swap_type_of(dev_t, sector_t, struct block_device **);
 extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
+extern struct swap_info_struct *page_swap_info(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;

@@ -18,6 +18,7 @@
 #include <linux/bio.h>
 #include <linux/swapops.h>
 #include <linux/writeback.h>
+#include <linux/buffer_head.h>
 #include <asm/pgtable.h>
 
 static struct bio *get_swap_bio(gfp_t gfp_flags,

@@ -98,6 +99,17 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		unlock_page(page);
 		goto out;
 	}
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		ret = mapping->a_ops->swap_out(swap_file, page, wbc);
+		if (!ret)
+			count_vm_event(PSWPOUT);
+		return ret;
+	}
+
 	bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
 	if (bio == NULL) {
 		set_page_dirty(page);

@@ -115,13 +127,55 @@ out:
 	return ret;
 }
 
+void swap_sync_page(struct page *page)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (!sis)
+		return;
+
+	if (sis->flags & SWP_FILE) {
+		struct address_space *mapping = sis->swap_file->f_mapping;
+
+	if (mapping->a_ops->sync_page)
+		mapping->a_ops->sync_page(page);
+	} else {
+		block_sync_page(page);
+	}
+}
+
+int swap_set_page_dirty(struct page *page)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (sis->flags & SWP_FILE) {
+		struct address_space *mapping = sis->swap_file->f_mapping;
+
+		return mapping->a_ops->set_page_dirty(page);
+	} else {
+		return __set_page_dirty_nobuffers(page);
+	}
+}
+
 int swap_readpage(struct page *page)
 {
 	struct bio *bio;
 	int ret = 0;
+	struct swap_info_struct *sis = page_swap_info(page);
 
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(PageUptodate(page));
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		ret = mapping->a_ops->swap_in(swap_file, page);
+		if (!ret)
+			count_vm_event(PSWPIN);
+		return ret;
+	}
+
 	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
 	if (bio == NULL) {
 		unlock_page(page);

@@ -28,8 +28,8 @@
  */
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.sync_page	= block_sync_page,
-	.set_page_dirty	= __set_page_dirty_nobuffers,
+	.sync_page	= swap_sync_page,
+	.set_page_dirty	= swap_set_page_dirty,
 	.migratepage	= migrate_page,
 };
 

@@ -1353,6 +1353,14 @@ static void destroy_swap_extents(struct swap_info_struct *sis)
 		list_del(&se->list);
 		kfree(se);
 	}
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		sis->flags &= ~SWP_FILE;
+		mapping->a_ops->swapoff(swap_file);
+	}
 }
 
 /*

@@ -1434,7 +1442,9 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
  */
 static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 {
-	struct inode *inode;
+	struct file *swap_file = sis->swap_file;
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
 	unsigned blocks_per_page;
 	unsigned long page_no;
 	unsigned blkbits;

@@ -1445,13 +1455,22 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 	int nr_extents = 0;
 	int ret;
 
-	inode = sis->swap_file->f_mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		ret = add_swap_extent(sis, 0, sis->max, 0);
 		*span = sis->pages;
 		goto out;
 	}
 
+	if (mapping->a_ops->swapon) {
+		ret = mapping->a_ops->swapon(swap_file);
+		if (!ret) {
+			sis->flags |= SWP_FILE;
+			ret = add_swap_extent(sis, 0, sis->max, 0);
+			*span = sis->pages;
+		}
+		goto out;
+	}
+
 	blkbits = inode->i_blkbits;
 	blocks_per_page = PAGE_SIZE >> blkbits;
 

@@ -2228,6 +2247,19 @@ int swapcache_prepare(swp_entry_t entry)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE);
 }
 
+struct swap_info_struct *page_swap_info(struct page *page)
+{
+	swp_entry_t swap = { .val = page_private(page) };
+	if (!PageSwapCache(page) || !swap.val) {
+		/* This should only happen from sync_page.
+		 * In other cases the page should be locked and
+		 * should be in a SwapCache
+		 */
+		return NULL;
+	}
+	return swap_info[swp_type(swap)];
+}
+
 /*
  * swap_lock prevents swap_map being freed. Don't grab an extra
  * reference on the swaphandle, it doesn't matter if it becomes unused.