/*
* copy_file_range() differs from regular file read and write in that it
* specifically allows return partial success. When it does so is up to
* the copy_file_range method.
*/
ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t len, unsigned int flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
ssize_t ret;
if (flags != 0)
return -EINVAL;
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;
ret = rw_verify_area(READ, file_in, &pos_in, len);
if (unlikely(ret))
return ret;
ret = rw_verify_area(WRITE, file_out, &pos_out, len);
if (unlikely(ret))
return ret;
if (!(file_in->f_mode & FMODE_READ) ||
!(file_out->f_mode & FMODE_WRITE) ||
(file_out->f_flags & O_APPEND))
return -EBADF;
/* this could be relaxed once a method supports cross-fs copies */
if (inode_in->i_sb != inode_out->i_sb)
return -EXDEV;
if (len == 0)
return 0;
file_start_write(file_out);
/*
* Try cloning first, this is supported by more file systems, and
* more efficient if both clone and copy are supported (e.g. NFS).
*/
if (file_in->f_op->clone_file_range) {
ret = file_in->f_op->clone_file_range(file_in, pos_in,
file_out, pos_out, len);
if (ret == 0) {
ret = len;
goto done;
}
}
if (file_out->f_op->copy_file_range) {
ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
pos_out, len, flags);
if (ret != -EOPNOTSUPP)
goto done;
}
ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
done:
if (ret > 0) {
fsnotify_access(file_in);
add_rchar(current, ret);
fsnotify_modify(file_out);
add_wchar(current, ret);
}
inc_syscr(current);
inc_syscw(current);
file_end_write(file_out);
return ret;
}
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
struct file * in_file, * out_file;
struct inode * in_inode, * out_inode;
loff_t pos;
ssize_t retval;
int fput_needed_in, fput_needed_out, fl;
/*
* Get input file, and verify that it is ok..
*/
retval = -EBADF;
in_file = fget_light(in_fd, &fput_needed_in);
if (!in_file)
goto out;
if (!(in_file->f_mode & FMODE_READ))
goto fput_in;
retval = -ESPIPE;
if (!ppos)
ppos = &in_file->f_pos;
else
if (!(in_file->f_mode & FMODE_PREAD))
goto fput_in;
retval = rw_verify_area(READ, in_file, ppos, count);
if (retval < 0)
goto fput_in;
count = retval;
/*
* Get output file, and verify that it is ok..
*/
retval = -EBADF;
out_file = fget_light(out_fd, &fput_needed_out);
if (!out_file)
goto fput_in;
if (!(out_file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
in_inode = in_file->f_path.dentry->d_inode;
out_inode = out_file->f_path.dentry->d_inode;
retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
if (retval < 0)
goto fput_out;
count = retval;
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
pos = *ppos;
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
goto fput_out;
count = max - pos;
}
fl = 0;
#if 0
/*
* We need to debate whether we can enable this or not. The
* man page documents EAGAIN return for the output at least,
* and the application is arguably buggy if it doesn't expect
* EAGAIN on a non-blocking file descriptor.
*/
if (in_file->f_flags & O_NONBLOCK)
fl = SPLICE_F_NONBLOCK;
#endif
retval = do_splice_direct(in_file, ppos, out_file, count, fl);
if (retval > 0) {
add_rchar(current, retval);
add_wchar(current, retval);
}
inc_syscr(current);
inc_syscw(current);
if (*ppos > max)
retval = -EOVERFLOW;
fput_out:
fput_light(out_file, fput_needed_out);
fput_in:
fput_light(in_file, fput_needed_in);
out:
return retval;
}
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
struct fd in, out;
struct inode *in_inode, *out_inode;
loff_t pos;
loff_t out_pos;
ssize_t retval;
int fl;
/*
* Get input file, and verify that it is ok..
*/
retval = -EBADF;
in = fdget(in_fd);
if (!in.file)
goto out;
if (!(in.file->f_mode & FMODE_READ))
goto fput_in;
retval = -ESPIPE;
if (!ppos) {
pos = in.file->f_pos;
} else {
pos = *ppos;
if (!(in.file->f_mode & FMODE_PREAD))
goto fput_in;
}
retval = rw_verify_area(READ, in.file, &pos, count);
if (retval < 0)
goto fput_in;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
/*
* Get output file, and verify that it is ok..
*/
retval = -EBADF;
out = fdget(out_fd);
if (!out.file)
goto fput_in;
if (!(out.file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
in_inode = file_inode(in.file);
out_inode = file_inode(out.file);
out_pos = out.file->f_pos;
retval = rw_verify_area(WRITE, out.file, &out_pos, count);
if (retval < 0)
goto fput_out;
if (!max)
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
goto fput_out;
count = max - pos;
}
fl = 0;
#if 0
/*
* We need to debate whether we can enable this or not. The
* man page documents EAGAIN return for the output at least,
* and the application is arguably buggy if it doesn't expect
* EAGAIN on a non-blocking file descriptor.
*/
if (in.file->f_flags & O_NONBLOCK)
fl = SPLICE_F_NONBLOCK;
#endif
file_start_write(out.file);
retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
file_end_write(out.file);
if (retval > 0) {
add_rchar(current, retval);
add_wchar(current, retval);
fsnotify_access(in.file);
fsnotify_modify(out.file);
out.file->f_pos = out_pos;
if (ppos)
*ppos = pos;
else
in.file->f_pos = pos;
}
inc_syscr(current);
inc_syscw(current);
if (pos > max)
retval = -EOVERFLOW;
fput_out:
fdput(out);
fput_in:
fdput(in);
out:
return retval;
}