/*
* Link a range of blocks from one file to another.
*/
int
xfs_reflink_remap_range(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
u64 len,
bool is_dedupe)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
struct xfs_mount *mp = src->i_mount;
bool same_inode = (inode_in == inode_out);
xfs_fileoff_t sfsbno, dfsbno;
xfs_filblks_t fsblen;
xfs_extlen_t cowextsize;
ssize_t ret;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return -EOPNOTSUPP;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/* Lock both files against IO */
lock_two_nondirectories(inode_in, inode_out);
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
ret = -EINVAL;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
&len, is_dedupe);
if (ret <= 0)
goto out_unlock;
trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
dfsbno = XFS_B_TO_FSBT(mp, pos_out);
sfsbno = XFS_B_TO_FSBT(mp, pos_in);
fsblen = XFS_B_TO_FSB(mp, len);
ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
pos_out + len);
if (ret)
goto out_unlock;
/* Zap any page cache for the destination file's range. */
truncate_inode_pages_range(&inode_out->i_data, pos_out,
PAGE_ALIGN(pos_out + len) - 1);
/*
* Carry the cowextsize hint from src to dest if we're sharing the
* entire source file to the entire destination file, the source file
* has a cowextsize hint, and the destination file does not.
*/
cowextsize = 0;
if (pos_in == 0 && len == i_size_read(inode_in) &&
(src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
pos_out == 0 && len >= i_size_read(inode_out) &&
!(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
cowextsize = src->i_d.di_cowextsize;
ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
is_dedupe);
out_unlock:
xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
if (!same_inode)
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
unlock_two_nondirectories(inode_in, inode_out);
if (ret)
trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
return ret;
}
/*
* Prepare two files for range cloning. Upon a successful return both inodes
* will have the iolock and mmaplock held, the page cache of the out file will
* be truncated, and any leases on the out file will have been broken. This
* function borrows heavily from xfs_file_aio_write_checks.
*
* The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
* checked that the bytes beyond EOF physically match. Hence we cannot use the
* EOF block in the source dedupe range because it's not a complete block match,
* hence can introduce a corruption into the file that has it's block replaced.
*
* In similar fashion, the VFS file cloning also allows partial EOF blocks to be
* "block aligned" for the purposes of cloning entire files. However, if the
* source file range includes the EOF block and it lands within the existing EOF
* of the destination file, then we can expose stale data from beyond the source
* file EOF in the destination file.
*
* XFS doesn't support partial block sharing, so in both cases we have check
* these cases ourselves. For dedupe, we can simply round the length to dedupe
* down to the previous whole block and ignore the partial EOF block. While this
* means we can't dedupe the last block of a file, this is an acceptible
* tradeoff for simplicity on implementation.
*
* For cloning, we want to share the partial EOF block if it is also the new EOF
* block of the destination file. If the partial EOF block lies inside the
* existing destination EOF, then we have to abort the clone to avoid exposing
* stale data in the destination file. Hence we reject these clone attempts with
* -EINVAL in this case.
*/
int
xfs_reflink_remap_prep(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
loff_t *len,
unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
bool same_inode = (inode_in == inode_out);
ssize_t ret;
/* Lock both files against IO */
ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
if (ret)
return ret;
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
ret = -EINVAL;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
len, remap_flags);
if (ret < 0 || *len == 0)
goto out_unlock;
/* Attach dquots to dest inode before changing block map */
ret = xfs_qm_dqattach(dest);
if (ret)
goto out_unlock;
/*
* Zero existing post-eof speculative preallocations in the destination
* file.
*/
ret = xfs_reflink_zero_posteof(dest, pos_out);
if (ret)
goto out_unlock;
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
/*
* If pos_out > EOF, we may have dirtied blocks between EOF and
* pos_out. In that case, we need to extend the flush and unmap to cover
* from EOF to the end of the copy length.
*/
if (pos_out > XFS_ISIZE(dest)) {
loff_t flen = *len + (pos_out - XFS_ISIZE(dest));
ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen);
} else {
ret = xfs_flush_unmap_range(dest, pos_out, *len);
}
if (ret)
goto out_unlock;
return 1;
out_unlock:
xfs_reflink_remap_unlock(file_in, file_out);
return ret;
}
