/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
* If there's an error, then the usual negative error code is returned.
* Otherwise returns 0 with *len set to the request length.
*/
int generic_remap_file_range_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 inode *inode_out = file_inode(file_out);
bool same_inode = (inode_in == inode_out);
int ret;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
loff_t isize = i_size_read(inode_in);
if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
if (*len == 0)
return 0;
}
/* Check that we don't violate system file offset limits. */
ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
remap_flags);
if (ret)
return ret;
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + *len - 1);
if (ret)
return ret;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + *len - 1);
if (ret)
return ret;
/*
* Check that the extents are the same.
*/
if (remap_flags & REMAP_FILE_DEDUP) {
bool is_same = false;
ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
inode_out, pos_out, *len, &is_same);
if (ret)
return ret;
if (!is_same)
return -EBADE;
}
ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
remap_flags);
if (ret)
return ret;
/* If can't alter the file contents, we're done. */
if (!(remap_flags & REMAP_FILE_DEDUP)) {
/* Update the timestamps, since we can alter file contents. */
if (!(file_out->f_mode & FMODE_NOCMTIME)) {
ret = file_update_time(file_out);
if (ret)
return ret;
}
/*
* Clear the security bits if the process is not being run by
* root. This keeps people from modifying setuid and setgid
* binaries.
*/
ret = file_remove_privs(file_out);
if (ret)
return ret;
}
return 0;
}
/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
* Returns: 0 for "nothing to clone", 1 for "something to clone", or
* the usual negative error code.
*/
int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
struct inode *inode_out, loff_t pos_out,
u64 *len, bool is_dedupe)
{
loff_t bs = inode_out->i_sb->s_blocksize;
loff_t blen;
loff_t isize;
bool same_inode = (inode_in == inode_out);
int ret;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Are we going all the way to the end? */
isize = i_size_read(inode_in);
if (isize == 0)
return 0;
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
if (is_dedupe || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
}
/* Ensure offsets don't wrap and the input is inside i_size */
if (pos_in + *len < pos_in || pos_out + *len < pos_out ||
pos_in + *len > isize)
return -EINVAL;
/* Don't allow dedupe past EOF in the dest file */
if (is_dedupe) {
loff_t disize;
disize = i_size_read(inode_out);
if (pos_out >= disize || pos_out + *len > disize)
return -EINVAL;
}
/* If we're linking to EOF, continue to the block boundary. */
if (pos_in + *len == isize)
blen = ALIGN(isize, bs) - pos_in;
else
blen = *len;
/* Only reflink if we're aligned to block boundaries */
if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
!IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
return -EINVAL;
/* Don't allow overlapped reflink within the same file */
if (same_inode) {
if (pos_out + blen > pos_in && pos_out < pos_in + blen)
return -EINVAL;
}
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + *len - 1);
if (ret)
return ret;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + *len - 1);
if (ret)
return ret;
/*
* Check that the extents are the same.
*/
if (is_dedupe) {
bool is_same = false;
ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
inode_out, pos_out, *len, &is_same);
if (ret)
return ret;
if (!is_same)
return -EBADE;
}
return 1;
}
