Btrfs: stop providing a bmap operation to avoid swapfile corruptions

Swapfiles use bmap to build a list of extents belonging to the file,
and they assume these extents won't change over the life of the file.
They also use resulting list to do IO directly to the block device.

This causes problems for btrfs in a few ways:

btrfs returns logical block numbers through bmap, and these are not suitable
for IO.  They might translate to different devices, raid etc.

COW means that file block mappings are going to change frequently.

Using swapfiles on btrfs will lead to corruption, so we're avoiding the
problem for now by dropping bmap support entirely.  A later commit
will add fiemap support for people that really want to know how
a file is laid out.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 45cf03ee1bc2281ba17cd96ed246536a24c6d48f..2e25d698bab0d618b26c2387c5279cc6ac34866b 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4156,11 +4156,6 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
        return -EINVAL;
 }
 
-static sector_t btrfs_bmap(struct address_space *mapping, sector_t iblock)
-{
-       return extent_bmap(mapping, iblock, btrfs_get_extent);
-}
-
 int btrfs_readpage(struct file *file, struct page *page)
 {
        struct extent_io_tree *tree;
@@ -4985,13 +4980,24 @@ static struct extent_io_ops btrfs_extent_io_ops = {
        .clear_bit_hook = btrfs_clear_bit_hook,
 };
 
+/*
+ * btrfs doesn't support the bmap operation because swapfiles
+ * use bmap to make a mapping of extents in the file.  They assume
+ * these extents won't change over the life of the file and they
+ * use the bmap result to do IO directly to the drive.
+ *
+ * the btrfs bmap call would return logical addresses that aren't
+ * suitable for IO and they also will change frequently as COW
+ * operations happen.  So, swapfile + btrfs == corruption.
+ *
+ * For now we're avoiding this by dropping bmap.
+ */
 static struct address_space_operations btrfs_aops = {
        .readpage       = btrfs_readpage,
        .writepage      = btrfs_writepage,
        .writepages     = btrfs_writepages,
        .readpages      = btrfs_readpages,
        .sync_page      = block_sync_page,
-       .bmap           = btrfs_bmap,
        .direct_IO      = btrfs_direct_IO,
        .invalidatepage = btrfs_invalidatepage,
        .releasepage    = btrfs_releasepage,