+
+ssize_t
+__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
+ struct block_device *bdev, const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+ dio_submit_t submit_io, int flags)
+{
+ /*
+ * The block device state is needed in the end to finally
+ * submit everything. Since it's likely to be cache cold
+ * prefetch it here as first thing to hide some of the
+ * latency.
+ *
+ * Attempt to prefetch the pieces we likely need later.
+ */
+ prefetch(&bdev->bd_disk->part_tbl);
+ prefetch(bdev->bd_queue);
+ prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
+
+ return do_blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
+ nr_segs, get_block, end_io,
+ submit_io, flags);
+}
+