ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret >= 0) {
count = ret;
file_start_write(file);
if (file->f_op->write)
ret = file->f_op->write(file, buf, count, pos);
else
ret = do_sync_write(file, buf, count, pos);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
file_end_write(file);
}
return ret;
}
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (!ret) {
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
file_start_write(file);
ret = __vfs_write(file, buf, count, pos);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
file_end_write(file);
}
return ret;
}
static ssize_t compat_do_readv_writev(int type, struct file *file,
const struct compat_iovec __user *uvector,
unsigned long nr_segs, loff_t *pos)
{
compat_ssize_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
ssize_t ret;
io_fn_t fn;
iov_fn_t fnv;
ret = -EINVAL;
if (!file->f_op)
goto out;
ret = -EFAULT;
if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
goto out;
ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
UIO_FASTIOV, iovstack, &iov);
if (ret <= 0)
goto out;
tot_len = ret;
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
fnv = file->f_op->aio_read;
} else {
fn = (io_fn_t)file->f_op->write;
fnv = file->f_op->aio_write;
file_start_write(file);
}
if (fnv)
ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
pos, fnv);
else
ret = do_loop_readv_writev(file, iov, nr_segs, pos, fn);
if (type != READ)
file_end_write(file);
out:
if (iov != iovstack)
kfree(iov);
if ((ret + (type == READ)) > 0) {
if (type == READ)
fsnotify_access(file);
else
fsnotify_modify(file);
}
return ret;
}
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec __user * uvector,
unsigned long nr_segs, loff_t *pos)
{
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
io_fn_t fn;
iov_fn_t fnv;
iter_fn_t iter_fn;
ret = import_iovec(type, uvector, nr_segs,
ARRAY_SIZE(iovstack), &iov, &iter);
if (ret < 0)
return ret;
tot_len = iov_iter_count(&iter);
if (!tot_len)
goto out;
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
fnv = NULL;
if (type == READ) {
fn = file->f_op->read;
fnv = file->f_op->aio_read;
iter_fn = file->f_op->read_iter;
} else {
fn = (io_fn_t)file->f_op->write;
fnv = file->f_op->aio_write;
iter_fn = file->f_op->write_iter;
file_start_write(file);
}
if (iter_fn)
ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
else if (fnv)
ret = do_sync_readv_writev(file, &iter, pos, fnv);
else
ret = do_loop_readv_writev(file, &iter, pos, fn);
if (type != READ)
file_end_write(file);
out:
kfree(iov);
if ((ret + (type == READ)) > 0) {
if (type == READ)
fsnotify_access(file);
else
fsnotify_modify(file);
}
return ret;
}
loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags)
{
loff_t ret;
file_start_write(file_out);
ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
remap_flags);
file_end_write(file_out);
return ret;
}
static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret >= 0) {
file_start_write(file);
ret = do_iter_write(file, &iter, pos, flags);
file_end_write(file);
kfree(iov);
}
return ret;
}
/**
* __do_lo_send_write - helper for writing data to a loop device
*
* This helper just factors out common code between do_lo_send_direct_write()
* and do_lo_send_write().
*/
static int __do_lo_send_write(struct file *file,
u8 *buf, const int len, loff_t pos)
{
ssize_t bw;
mm_segment_t old_fs = get_fs();
file_start_write(file);
set_fs(get_ds());
bw = file->f_op->write(file, buf, len, &pos);
set_fs(old_fs);
file_end_write(file);
if (likely(bw == len))
return 0;
printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
(unsigned long long)pos, len);
if (bw >= 0)
bw = -EIO;
return bw;
}
static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
{
struct iov_iter i;
ssize_t bw;
iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len);
file_start_write(file);
bw = vfs_iter_write(file, &i, ppos);
file_end_write(file);
if (likely(bw == bvec->bv_len))
return 0;
printk_ratelimited(KERN_ERR
"loop: Write error at byte offset %llu, length %i.\n",
(unsigned long long)*ppos, bvec->bv_len);
if (bw >= 0)
bw = -EIO;
return bw;
}
static size_t compat_writev(struct file *file,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
if (ret >= 0) {
file_start_write(file);
ret = do_iter_write(file, &iter, pos, flags);
file_end_write(file);
kfree(iov);
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct fd real;
const struct cred *old_cred;
ssize_t ret;
if (!iov_iter_count(iter))
return 0;
inode_lock(inode);
/* Update mode */
ovl_copyattr(ovl_inode_real(inode), inode);
ret = file_remove_privs(file);
if (ret)
goto out_unlock;
ret = ovl_real_fdget(file, &real);
if (ret)
goto out_unlock;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
file_start_write(real.file);
ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
ovl_iocb_to_rwf(iocb));
file_end_write(real.file);
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode), inode);
fdput(real);
out_unlock:
inode_unlock(inode);
return ret;
}
static ssize_t
coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *coda_file = iocb->ki_filp;
struct inode *coda_inode = file_inode(coda_file);
struct coda_file_info *cfi = CODA_FTOC(coda_file);
struct file *host_file;
ssize_t ret;
BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
host_file = cfi->cfi_container;
file_start_write(host_file);
inode_lock(coda_inode);
ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos);
coda_inode->i_size = file_inode(host_file)->i_size;
coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9;
coda_inode->i_mtime = coda_inode->i_ctime = current_time(coda_inode);
inode_unlock(coda_inode);
file_end_write(host_file);
return ret;
}
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;
count = retval;
/*
* 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;
count = retval;
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;
}
ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
struct kiocb kiocb;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
ret = filp->f_op->aio_write(&kiocb, &iov, 1, kiocb.ki_pos);
BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
EXPORT_SYMBOL(do_sync_write);
ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
{
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
struct kiocb kiocb;
struct iov_iter iter;
ssize_t ret;
init_sync_kiocb(&kiocb, filp);
kiocb.ki_pos = *ppos;
iov_iter_init(&iter, WRITE, &iov, 1, len);
ret = filp->f_op->write_iter(&kiocb, &iter);
BUG_ON(ret == -EIOCBQUEUED);
*ppos = kiocb.ki_pos;
return ret;
}
EXPORT_SYMBOL(new_sync_write);
ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
{
mm_segment_t old_fs;
const char __user *p;
ssize_t ret;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
old_fs = get_fs();
set_fs(get_ds());
p = (__force const char __user *)buf;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
if (file->f_op->write)
ret = file->f_op->write(file, p, count, pos);
else if (file->f_op->aio_write)
ret = do_sync_write(file, p, count, pos);
else
ret = new_sync_write(file, p, count, pos);
set_fs(old_fs);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
return ret;
}
EXPORT_SYMBOL(__kernel_write);
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
ret = rw_verify_area(WRITE, file, pos, count);
if (ret >= 0) {
count = ret;
file_start_write(file);
if (file->f_op->write)
ret = file->f_op->write(file, buf, count, pos);
else if (file->f_op->aio_write)
ret = do_sync_write(file, buf, count, pos);
else
ret = new_sync_write(file, buf, count, pos);
if (ret > 0) {
fsnotify_modify(file);
add_wchar(current, ret);
}
inc_syscw(current);
file_end_write(file);
}
return ret;
}
/*
* 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->remap_file_range) {
loff_t cloned;
cloned = file_in->f_op->remap_file_range(file_in, pos_in,
file_out, pos_out,
min_t(loff_t, MAX_RW_COUNT, len),
REMAP_FILE_CAN_SHORTEN);
if (cloned > 0) {
ret = cloned;
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;
}
int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
return -EINVAL;
/* Return error if mode is not supported */
if (mode & ~FALLOC_FL_SUPPORTED_MASK)
return -EOPNOTSUPP;
/* Punch hole and zero range are mutually exclusive */
if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
(FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
/* Punch hole must have keep size set */
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
/* Collapse range should only be used exclusively. */
if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
(mode & ~FALLOC_FL_COLLAPSE_RANGE))
return -EINVAL;
/* Insert range should only be used exclusively. */
if ((mode & FALLOC_FL_INSERT_RANGE) &&
(mode & ~FALLOC_FL_INSERT_RANGE))
return -EINVAL;
/* Unshare range should only be used with allocate mode. */
if ((mode & FALLOC_FL_UNSHARE_RANGE) &&
(mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE)))
return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/*
* We can only allow pure fallocate on append only files
*/
if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* We cannot allow any fallocate operation on an active swapfile
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
if (S_ISDIR(inode->i_mode))
return -EISDIR;
if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
return -ENODEV;
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
file_start_write(file);
ret = file->f_op->fallocate(file, mode, offset, len);
/*
* Create inotify and fanotify events.
*
* To keep the logic simple always create events if fallocate succeeds.
* This implies that events are even created if the file size remains
* unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE.
*/
if (ret == 0)
fsnotify_modify(file);
file_end_write(file);
return ret;
}