/**
* dax_zero_page_range - zero a range within a page of a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @length: The number of bytes to zero
* @get_block: The filesystem method used to translate file offsets to blocks
*
* This function can be called by a filesystem when it is zeroing part of a
* page in a DAX file. This is intended for hole-punch operations. If
* you are truncating a file, the helper function dax_truncate_page() may be
* more convenient.
*
* We work in terms of PAGE_CACHE_SIZE here for commonality with
* block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
* took care of disposing of the unnecessary blocks. Even if the filesystem
* block size is smaller than PAGE_SIZE, we have to zero the rest of the page
* since the file might be mmapped.
*/
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
get_block_t get_block)
{
struct buffer_head bh;
pgoff_t index = from >> PAGE_CACHE_SHIFT;
unsigned offset = from & (PAGE_CACHE_SIZE-1);
int err;
/* Block boundary? Nothing to do */
if (!length)
return 0;
BUG_ON((offset + length) > PAGE_CACHE_SIZE);
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_CACHE_SIZE;
err = get_block(inode, index, &bh, 0);
if (err < 0)
return err;
if (buffer_written(&bh)) {
struct block_device *bdev = bh.b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(&bh, inode),
.size = PAGE_CACHE_SIZE,
};
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
clear_pmem(dax.addr + offset, length);
wmb_pmem();
dax_unmap_atomic(bdev, &dax);
}
return 0;
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);
/**
* dax_truncate_page - handle a partial page being truncated in a DAX file
* @inode: The file being truncated
* @from: The file offset that is being truncated to
* @get_block: The filesystem method used to translate file offsets to blocks
*
* Similar to block_truncate_page(), this function can be called by a
* filesystem when it is truncating a DAX file to handle the partial page.
*
* We work in terms of PAGE_CACHE_SIZE here for commonality with
* block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
* took care of disposing of the unnecessary blocks. Even if the filesystem
* block size is smaller than PAGE_SIZE, we have to zero the rest of the page
* since the file might be mmapped.
*/
int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
{
unsigned length = PAGE_CACHE_ALIGN(from) - from;
return dax_zero_page_range(inode, from, length, get_block);
}
static int cifs_clone_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff, u64 len)
{
struct inode *src_inode = file_inode(src_file);
struct inode *target_inode = file_inode(dst_file);
struct cifsFileInfo *smb_file_src = src_file->private_data;
struct cifsFileInfo *smb_file_target = dst_file->private_data;
struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink);
unsigned int xid;
int rc;
cifs_dbg(FYI, "clone range\n");
xid = get_xid();
if (!src_file->private_data || !dst_file->private_data) {
rc = -EBADF;
cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
goto out;
}
/*
* Note: cifs case is easier than btrfs since server responsible for
* checks for proper open modes and file type and if it wants
* server could even support copy of range where source = target
*/
lock_two_nondirectories(target_inode, src_inode);
if (len == 0)
len = src_inode->i_size - off;
cifs_dbg(FYI, "about to flush pages\n");
/* should we flush first and last page first */
truncate_inode_pages_range(&target_inode->i_data, destoff,
PAGE_CACHE_ALIGN(destoff + len)-1);
if (target_tcon->ses->server->ops->duplicate_extents)
rc = target_tcon->ses->server->ops->duplicate_extents(xid,
smb_file_src, smb_file_target, off, len, destoff);
else
rc = -EOPNOTSUPP;
/* force revalidate of size and timestamps of target file now
that target is updated on the server */
CIFS_I(target_inode)->time = 0;
/* although unlocking in the reverse order from locking is not
strictly necessary here it is a little cleaner to be consistent */
unlock_two_nondirectories(src_inode, target_inode);
out:
free_xid(xid);
return rc;
}
static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
unsigned long srcfd, u64 off, u64 len, u64 destoff)
{
int rc;
struct cifsFileInfo *smb_file_target = dst_file->private_data;
struct inode *target_inode = file_inode(dst_file);
struct cifs_tcon *target_tcon;
struct fd src_file;
struct cifsFileInfo *smb_file_src;
struct inode *src_inode;
struct cifs_tcon *src_tcon;
cifs_dbg(FYI, "ioctl clone range\n");
/* the destination must be opened for writing */
if (!(dst_file->f_mode & FMODE_WRITE)) {
cifs_dbg(FYI, "file target not open for write\n");
return -EINVAL;
}
/* check if target volume is readonly and take reference */
rc = mnt_want_write_file(dst_file);
if (rc) {
cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc);
return rc;
}
src_file = fdget(srcfd);
if (!src_file.file) {
rc = -EBADF;
goto out_drop_write;
}
if ((!src_file.file->private_data) || (!dst_file->private_data)) {
rc = -EBADF;
cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
goto out_fput;
}
rc = -EXDEV;
smb_file_target = dst_file->private_data;
smb_file_src = src_file.file->private_data;
src_tcon = tlink_tcon(smb_file_src->tlink);
target_tcon = tlink_tcon(smb_file_target->tlink);
/* check if source and target are on same tree connection */
if (src_tcon != target_tcon) {
cifs_dbg(VFS, "file copy src and target on different volume\n");
goto out_fput;
}
src_inode = src_file.file->f_dentry->d_inode;
/*
* Note: cifs case is easier than btrfs since server responsible for
* checks for proper open modes and file type and if it wants
* server could even support copy of range where source = target
*/
/* so we do not deadlock racing two ioctls on same files */
if (target_inode < src_inode) {
mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD);
} else {
mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD);
}
/* determine range to clone */
rc = -EINVAL;
if (off + len > src_inode->i_size || off + len < off)
goto out_unlock;
if (len == 0)
len = src_inode->i_size - off;
cifs_dbg(FYI, "about to flush pages\n");
/* should we flush first and last page first */
truncate_inode_pages_range(&target_inode->i_data, destoff,
PAGE_CACHE_ALIGN(destoff + len)-1);
if (target_tcon->ses->server->ops->clone_range)
rc = target_tcon->ses->server->ops->clone_range(xid,
smb_file_src, smb_file_target, off, len, destoff);
/* force revalidate of size and timestamps of target file now
that target is updated on the server */
CIFS_I(target_inode)->time = 0;
out_unlock:
/* although unlocking in the reverse order from locking is not
strictly necessary here it is a little cleaner to be consistent */
if (target_inode < src_inode) {
mutex_unlock(&src_inode->i_mutex);
mutex_unlock(&target_inode->i_mutex);
} else {
mutex_unlock(&target_inode->i_mutex);
mutex_unlock(&src_inode->i_mutex);
}
out_fput:
fdput(src_file);
out_drop_write:
mnt_drop_write_file(dst_file);
return rc;
}
