Page I/O

index 9ddb9fc..7b5bb90 100644
@@ -2879,10 +2879,9 @@ EXPORT_SYMBOL(block_truncate_page);
 
 /*
  * The generic ->writepage function for buffer-backed address_spaces
- * this form passes in the end_io handler used to finish the IO.
  */
-int block_write_full_page_endio(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc, bh_end_io_t *handler)
+int block_write_full_page(struct page *page, get_block_t *get_block,
+			struct writeback_control *wbc)
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);

@@ -2892,7 +2891,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 	/* Is the page fully inside i_size? */
 	if (page->index < end_index)
 		return __block_write_full_page(inode, page, get_block, wbc,
-					       handler);
+					       end_buffer_async_write);
 
 	/* Is the page fully outside i_size? (truncate in progress) */
 	offset = i_size & (PAGE_CACHE_SIZE-1);

@@ -2915,18 +2914,8 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 	 * writes to that region are not written out to the file."
 	 */
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
-	return __block_write_full_page(inode, page, get_block, wbc, handler);
-}
-EXPORT_SYMBOL(block_write_full_page_endio);
-
-/*
- * The generic ->writepage function for buffer-backed address_spaces
- */
-int block_write_full_page(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc)
-{
-	return block_write_full_page_endio(page, get_block, wbc,
-					   end_buffer_async_write);
+	return __block_write_full_page(inode, page, get_block, wbc,
+							end_buffer_async_write);
 }
 EXPORT_SYMBOL(block_write_full_page);
 

index ab95508..11c2ba5 100644
@@ -428,7 +428,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		block_start = bh_offset(bh);
 		if (block_start >= len) {
 			/*
-			 * Comments copied from block_write_full_page_endio:
+			 * Comments copied from block_write_full_page:
 			 *
 			 * The page straddles i_size.  It must be zeroed out on
 			 * each and every writepage invocation because it may

index 8970dcf..8eb6e57 100644
@@ -828,7 +828,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 		/*
 		 * fs-writeback will release the dirty pages without page lock
 		 * whose offset are over inode size, the release happens at
-		 * block_write_full_page_endio().
+		 * block_write_full_page().
 		 */
 		i_size_write(inode, abs_to);
 		inode->i_blocks = ocfs2_inode_sector_count(inode);

index c40302f..e05c7ec 100644
@@ -207,8 +207,6 @@ void block_invalidatepage(struct page *page, unsigned int offset,
 			  unsigned int length);
 int block_write_full_page(struct page *page, get_block_t *get_block,
 				struct writeback_control *wbc);
-int block_write_full_page_endio(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc, bh_end_io_t *handler);
 int block_read_full_page(struct page*, get_block_t*);
 int block_is_partially_uptodate(struct page *page, unsigned long from,
 				unsigned long count);

index 4979ffa..4cc9c5d 100644
@@ -439,6 +439,35 @@ struct mpage_data {
 	unsigned use_writepage;
 };
 
+/*
+ * We have our BIO, so we can now mark the buffers clean.  Make
+ * sure to only clean buffers which we know we'll be writing.
+ */
+static void clean_buffers(struct page *page, unsigned first_unmapped)
+{
+	unsigned buffer_counter = 0;
+	struct buffer_head *bh, *head;
+	if (!page_has_buffers(page))
+		return;
+	head = page_buffers(page);
+	bh = head;
+
+	do {
+		if (buffer_counter++ == first_unmapped)
+			break;
+		clear_buffer_dirty(bh);
+		bh = bh->b_this_page;
+	} while (bh != head);
+
+	/*
+	 * we cannot drop the bh if the page is not uptodate or a concurrent
+	 * readpage would fail to serialize with the bh and it would read from
+	 * disk before we reach the platter.
+	 */
+	if (buffer_heads_over_limit && PageUptodate(page))
+		try_to_free_buffers(page);
+}
+
 static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 		      void *data)
 {

@@ -591,30 +620,7 @@ alloc_new:
 		goto alloc_new;
 	}
 
-	/*
-	 * OK, we have our BIO, so we can now mark the buffers clean.  Make
-	 * sure to only clean buffers which we know we'll be writing.
-	 */
-	if (page_has_buffers(page)) {
-		struct buffer_head *head = page_buffers(page);
-		struct buffer_head *bh = head;
-		unsigned buffer_counter = 0;
-
-		do {
-			if (buffer_counter++ == first_unmapped)
-				break;
-			clear_buffer_dirty(bh);
-			bh = bh->b_this_page;
-		} while (bh != head);
-
-		/*
-		 * we cannot drop the bh if the page is not uptodate
-		 * or a concurrent readpage would fail to serialize with the bh
-		 * and it would read from disk before we reach the platter.
-		 */
-		if (buffer_heads_over_limit && PageUptodate(page))
-			try_to_free_buffers(page);
-	}
+	clean_buffers(page, first_unmapped);
 
 	BUG_ON(PageWriteback(page));
 	set_page_writeback(page);

index 4cc9c5d..10da0da 100644
@@ -48,23 +48,7 @@ static void mpage_end_io(struct bio *bio, int err)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-
-		if (bio_data_dir(bio) == READ) {
-			if (!err) {
-				SetPageUptodate(page);
-			} else {
-				ClearPageUptodate(page);
-				SetPageError(page);
-			}
-			unlock_page(page);
-		} else { /* bio_data_dir(bio) == WRITE */
-			if (err) {
-				SetPageError(page);
-				if (page->mapping)
-					set_bit(AS_EIO, &page->mapping->flags);
-			}
-			end_page_writeback(page);
-		}
+		page_endio(page, bio_data_dir(bio), err);
 	}
 
 	bio_put(bio);

index 45598f1..718214c 100644
@@ -425,6 +425,8 @@ static inline void wait_on_page_writeback(struct page *page)
 extern void end_page_writeback(struct page *page);
 void wait_for_stable_page(struct page *page);
 
+void page_endio(struct page *page, int rw, int err);
+
 /*
  * Add an arbitrary waiter to a page's wait queue
  */

index a82fbe4..ee6a3ce 100644
@@ -762,6 +762,31 @@ void end_page_writeback(struct page *page)
 }
 EXPORT_SYMBOL(end_page_writeback);
 
+/*
+ * After completing I/O on a page, call this routine to update the page
+ * flags appropriately
+ */
+void page_endio(struct page *page, int rw, int err)
+{
+	if (rw == READ) {
+		if (!err) {
+			SetPageUptodate(page);
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
+	} else { /* rw == WRITE */
+		if (err) {
+			SetPageError(page);
+			if (page->mapping)
+				mapping_set_error(page->mapping, err);
+		}
+		end_page_writeback(page);
+	}
+}
+EXPORT_SYMBOL_GPL(page_endio);
+
 /**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock

index 552a8d1..83fba15 100644
@@ -363,6 +363,69 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 }
 EXPORT_SYMBOL(blkdev_fsync);
 
+/**
+ * bdev_read_page() - Start reading a page from a block device
+ * @bdev: The device to read the page from
+ * @sector: The offset on the device to read the page to (need not be aligned)
+ * @page: The page to read
+ *
+ * On entry, the page should be locked.  It will be unlocked when the page
+ * has been read.  If the block driver implements rw_page synchronously,
+ * that will be true on exit from this function, but it need not be.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to read this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_read_page(struct block_device *bdev, sector_t sector,
+			struct page *page)
+{
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	if (!ops->rw_page)
+		return -EOPNOTSUPP;
+	return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+}
+EXPORT_SYMBOL_GPL(bdev_read_page);
+
+/**
+ * bdev_write_page() - Start writing a page to a block device
+ * @bdev: The device to write the page to
+ * @sector: The offset on the device to write the page to (need not be aligned)
+ * @page: The page to write
+ * @wbc: The writeback_control for the write
+ *
+ * On entry, the page should be locked and not currently under writeback.
+ * On exit, if the write started successfully, the page will be unlocked and
+ * under writeback.  If the write failed already (eg the driver failed to
+ * queue the page to the device), the page will still be locked.  If the
+ * caller is a ->writepage implementation, it will need to unlock the page.
+ *
+ * Errors returned by this function are usually "soft", eg out of memory, or
+ * queue full; callers should try a different route to write this page rather
+ * than propagate an error back up the stack.
+ *
+ * Return: negative errno if an error occurs, 0 if submission was successful.
+ */
+int bdev_write_page(struct block_device *bdev, sector_t sector,
+			struct page *page, struct writeback_control *wbc)
+{
+	int result;
+	int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
+	const struct block_device_operations *ops = bdev->bd_disk->fops;
+	if (!ops->rw_page)
+		return -EOPNOTSUPP;
+	set_page_writeback(page);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
+	if (result)
+		end_page_writeback(page);
+	else
+		unlock_page(page);
+	return result;
+}
+EXPORT_SYMBOL_GPL(bdev_write_page);
+
 /*
  * pseudo-fs
  */

index 10da0da..5f9ed62 100644
@@ -269,6 +269,11 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
 
 alloc_new:
 	if (bio == NULL) {
+		if (first_hole == blocks_per_page) {
+			if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9),
+								page))
+				goto out;
+		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
 			  	min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
 				GFP_KERNEL);

@@ -587,6 +592,13 @@ page_is_mapped:
 
 alloc_new:
 	if (bio == NULL) {
+		if (first_unmapped == blocks_per_page) {
+			if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9),
+								page, wbc)) {
+				clean_buffers(page, first_unmapped);
+				goto out;
+			}
+		}
 		bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
 				bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH);
 		if (bio == NULL)

index 0d84981..6d2de38 100644
@@ -1570,6 +1570,7 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g)
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t,

@@ -1588,6 +1589,9 @@ struct block_device_operations {
 
 extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 				 unsigned long);
+extern int bdev_read_page(struct block_device *, sector_t, struct page *);
+extern int bdev_write_page(struct block_device *, sector_t, struct page *,
+						struct writeback_control *);
 #else /* CONFIG_BLOCK */
 /*
  * stubs for when the block layer is configured out

index 7c59ef6..43d7220 100644
@@ -248,11 +248,16 @@ out:
 	return ret;
 }
 
+static sector_t swap_page_sector(struct page *page)
+{
+	return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9);
+}
+
 int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	void (*end_write_func)(struct bio *, int))
 {
 	struct bio *bio;
-	int ret = 0, rw = WRITE;
+	int ret, rw = WRITE;
 	struct swap_info_struct *sis = page_swap_info(page);
 
 	if (sis->flags & SWP_FILE) {

@@ -297,6 +302,13 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		return ret;
 	}
 
+	ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
+	if (!ret) {
+		count_vm_event(PSWPOUT);
+		return 0;
+	}
+
+	ret = 0;
 	bio = get_swap_bio(GFP_NOIO, page, end_write_func);
 	if (bio == NULL) {
 		set_page_dirty(page);

@@ -317,7 +329,7 @@ out:
 int swap_readpage(struct page *page)
 {
 	struct bio *bio;
-	int ret = 0;
+	int ret;
 	struct swap_info_struct *sis = page_swap_info(page);
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);

@@ -338,6 +350,13 @@ int swap_readpage(struct page *page)
 		return ret;
 	}
 
+	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
+	if (!ret) {
+		count_vm_event(PSWPIN);
+		return 0;
+	}
+
+	ret = 0;
 	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
 	if (bio == NULL) {
 		unlock_page(page);

index e73b85c..807d3d5 100644
@@ -360,6 +360,15 @@ out:
 	bio_endio(bio, err);
 }
 
+static int brd_rw_page(struct block_device *bdev, sector_t sector,
+		       struct page *page, int rw)
+{
+	struct brd_device *brd = bdev->bd_disk->private_data;
+	int err = brd_do_bvec(brd, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	page_endio(page, rw & WRITE, err);
+	return err;
+}
+
 #ifdef CONFIG_BLK_DEV_XIP
 static int brd_direct_access(struct block_device *bdev, sector_t sector,
 			void **kaddr, unsigned long *pfn)

@@ -419,6 +428,7 @@ static int brd_ioctl(struct block_device *bdev, fmode_t mode,
 
 static const struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
+	.rw_page =		brd_rw_page,
 	.ioctl =		brd_ioctl,
 #ifdef CONFIG_BLK_DEV_XIP
 	.direct_access =	brd_direct_access,

index 807d3d5..c7d138e 100644
@@ -200,11 +200,11 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
 
 	copy = min_t(size_t, n, PAGE_SIZE - offset);
 	if (!brd_insert_page(brd, sector))
-		return -ENOMEM;
+		return -ENOSPC;
 	if (copy < n) {
 		sector += copy >> SECTOR_SHIFT;
 		if (!brd_insert_page(brd, sector))
-			return -ENOMEM;
+			return -ENOSPC;
 	}
 	return 0;
 }

@@ -384,7 +384,7 @@ static int brd_direct_access(struct block_device *bdev, sector_t sector,
 		return -ERANGE;
 	page = brd_insert_page(brd, sector);
 	if (!page)
-		return -ENOMEM;
+		return -ENOSPC;
 	*kaddr = page_address(page);
 	*pfn = page_to_pfn(page);