block: Add support for DAX reads/writes to block devices

If a block device supports the ->direct_access methods, bypass the normal
DIO path and use DAX to go straight to memcpy() instead of allocating
a DIO and a BIO.

Includes support for the DIO_SKIP_DIO_COUNT flag in DAX, as is done in
do_blockdev_direct_IO().

Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/block_dev.c b/fs/block_dev.c
index c7e4163..5dde6df 100644 (file)
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -151,6 +151,9 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
        struct file *file = iocb->ki_filp;
        struct inode *inode = file->f_mapping->host;
 
+       if (IS_DAX(inode))
+               return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+                               NULL, DIO_SKIP_DIO_COUNT);
        return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
                                    blkdev_get_block, NULL, NULL,
                                    DIO_SKIP_DIO_COUNT);
@@ -1173,6 +1176,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                bdev->bd_disk = disk;
                bdev->bd_queue = disk->queue;
                bdev->bd_contains = bdev;
+               bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
                if (!partno) {
                        ret = -ENXIO;
                        bdev->bd_part = disk_get_part(disk, partno);

diff --git a/fs/dax.c b/fs/dax.c
index 159f796..37a0c48 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -209,7 +209,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
        }
 
        /* Protects against truncate */
-       inode_dio_begin(inode);
+       if (!(flags & DIO_SKIP_DIO_COUNT))
+               inode_dio_begin(inode);
 
        retval = dax_io(inode, iter, pos, end, get_block, &bh);
 
@@ -219,7 +220,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
        if ((retval > 0) && end_io)
                end_io(iocb, pos, retval, bh.b_private);
 
-       inode_dio_end(inode);
+       if (!(flags & DIO_SKIP_DIO_COUNT))
+               inode_dio_end(inode);
  out:
        return retval;
 }