fs/block_dev.c: add bdev_read_page() and bdev_write_page()

A block device driver may choose to provide a rw_page operation.  These
will be called when the filesystem is attempting to do page sized I/O to
page cache pages (ie not for direct I/O).  This does preclude I/Os that
are larger than page size, so this may only be a performance gain for
some devices.

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Tested-by: Dheeraj Reddy <dheeraj.reddy@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 75 insertions, 0 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 552a8d13bc32..83fba15cc394 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -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
  */
diff --git a/fs/mpage.c b/fs/mpage.c
index 10da0da73017..5f9ed622274f 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -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)