/* ARGSUSED */
static int
fdcreate(vnode_t *dvp, char *comp, vattr_t *vap, enum vcexcl excl,
int mode, vnode_t **vpp, cred_t *cr, int flag, caller_context_t *ct,
vsecattr_t *vsecp)
{
return (fdget(dvp, comp, vpp));
}
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned long, offset_low, loff_t __user *, result,
unsigned int, whence)
{
int retval;
struct fd f = fdget(fd);
loff_t offset;
if (!f.file)
return -EBADF;
retval = -EINVAL;
if (whence > SEEK_MAX)
goto out_putf;
offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
whence);
retval = (int)offset;
if (offset >= 0) {
retval = -EFAULT;
if (!copy_to_user(result, &offset, sizeof(offset)))
retval = 0;
}
out_putf:
fdput(f);
return retval;
}
int hpux_getdents(unsigned int fd, struct hpux_dirent __user *dirent, unsigned int count)
{
struct fd arg;
struct hpux_dirent __user * lastdirent;
struct getdents_callback buf;
int error;
arg = fdget(fd);
if (!arg.file)
return -EBADF;
buf.current_dir = dirent;
buf.previous = NULL;
buf.count = count;
buf.error = 0;
buf.ctx.actor = filldir;
error = iterate_dir(arg.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
if (put_user(buf.ctx.pos, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
}
fdput(arg);
return error;
}
struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
{
struct bpf_map *inner_map, *inner_map_meta;
u32 inner_map_meta_size;
struct fd f;
f = fdget(inner_map_ufd);
inner_map = __bpf_map_get(f);
if (IS_ERR(inner_map))
return inner_map;
/* prog_array->owner_prog_type and owner_jited
* is a runtime binding. Doing static check alone
* in the verifier is not enough.
*/
if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}
/* Does not support >1 level map-in-map */
if (inner_map->inner_map_meta) {
fdput(f);
return ERR_PTR(-EINVAL);
}
if (map_value_has_spin_lock(inner_map)) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}
inner_map_meta_size = sizeof(*inner_map_meta);
/* In some cases verifier needs to access beyond just base map. */
if (inner_map->ops == &array_map_ops)
inner_map_meta_size = sizeof(struct bpf_array);
inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER);
if (!inner_map_meta) {
fdput(f);
return ERR_PTR(-ENOMEM);
}
inner_map_meta->map_type = inner_map->map_type;
inner_map_meta->key_size = inner_map->key_size;
inner_map_meta->value_size = inner_map->value_size;
inner_map_meta->map_flags = inner_map->map_flags;
inner_map_meta->max_entries = inner_map->max_entries;
inner_map_meta->spin_lock_off = inner_map->spin_lock_off;
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
if (inner_map->ops == &array_map_ops) {
inner_map_meta->unpriv_array = inner_map->unpriv_array;
container_of(inner_map_meta, struct bpf_array, map)->index_mask =
container_of(inner_map, struct bpf_array, map)->index_mask;
}
/**
* eventfd_ctx_fdget - Acquires a reference to the internal eventfd context.
* @fd: [in] Eventfd file descriptor.
*
* Returns a pointer to the internal eventfd context, otherwise the error
* pointers returned by the following functions:
*
* eventfd_fget
*/
struct eventfd_ctx *eventfd_ctx_fdget(int fd)
{
struct eventfd_ctx *ctx;
struct fd f = fdget(fd);
if (!f.file)
return ERR_PTR(-EBADF);
ctx = eventfd_ctx_fileget(f.file);
fdput(f);
return ctx;
}
static int do_fsync(unsigned int fd, int datasync)
{
struct fd f = fdget(fd);
int ret = -EBADF;
if (f.file) {
ret = vfs_fsync(f.file, datasync);
fdput(f);
}
return ret;
}
int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (f.file) {
error = vfs_fallocate(f.file, mode, offset, len);
fdput(f);
}
return error;
}
SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (f.file) {
error = do_fallocate(f.file, mode, offset, len);
fdput(f);
}
return error;
}
static int do_fsync(unsigned int fd, int datasync)
{
struct fd f = fdget(fd);
int ret = -EBADF;
#ifdef CONFIG_ASYNC_FSYNC
struct fsync_work *fwork;
#endif
if (!fsync_enabled)
return 0;
if (f.file) {
ktime_t fsync_t, fsync_diff;
char pathname[256], *path;
path = d_path(&(f.file->f_path), pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
#ifdef CONFIG_ASYNC_FSYNC
else if (async_fsync(f.file, fd)) {
if (!fsync_workqueue)
fsync_workqueue =
create_singlethread_workqueue("fsync");
if (!fsync_workqueue)
goto no_async;
if (IS_ERR(path))
goto no_async;
fwork = kmalloc(sizeof(*fwork), GFP_KERNEL);
if (fwork) {
strncpy(fwork->pathname, path,
sizeof(fwork->pathname) - 1);
INIT_WORK(&fwork->work, do_afsync_work);
queue_work(fsync_workqueue, &fwork->work);
fput(f.file);
return 0;
}
}
no_async:
#endif
fsync_t = ktime_get();
ret = vfs_fsync(f.file, datasync);
fdput(f);
fsync_diff = ktime_sub(ktime_get(), fsync_t);
if (ktime_to_ms(fsync_diff) >= 5000) {
pr_info("VFS: %s pid:%d(%s)(parent:%d/%s)\
takes %lld ms to fsync %s.\n", __func__,
current->pid, current->comm,
current->parent->pid, current->parent->comm,
ktime_to_ms(fsync_diff), path);
}
}
return ret;
}
int ksys_fchmod(unsigned int fd, umode_t mode)
{
struct fd f = fdget(fd);
int err = -EBADF;
if (f.file) {
audit_file(f.file);
err = chmod_common(&f.file->f_path, mode);
fdput(f);
}
return err;
}
SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask,
size_t, sizemask, int, flags)
{
sigset_t sigmask;
struct signalfd_ctx *ctx;
/* Check the SFD_* constants for consistency. */
BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC);
BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK);
if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK))
return -EINVAL;
if (sizemask != sizeof(sigset_t) ||
copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
return -EINVAL;
sigdelsetmask(&sigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
signotset(&sigmask);
if (ufd == -1) {
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->sigmask = sigmask;
/*
* When we call this, the initialization must be complete, since
* anon_inode_getfd() will install the fd.
*/
ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx,
O_RDWR | (flags & (O_CLOEXEC | O_NONBLOCK)));
if (ufd < 0)
kfree(ctx);
} else {
struct fd f = fdget(ufd);
if (!f.file)
return -EBADF;
ctx = f.file->private_data;
if (f.file->f_op != &signalfd_fops) {
fdput(f);
return -EINVAL;
}
spin_lock_irq(¤t->sighand->siglock);
ctx->sigmask = sigmask;
spin_unlock_irq(¤t->sighand->siglock);
wake_up(¤t->sighand->signalfd_wqh);
fdput(f);
}
return ufd;
}
SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
{
struct fd f = fdget(fd);
int err = -EBADF;
if (f.file) {
audit_inode(NULL, f.file->f_path.dentry, 0);
err = chmod_common(&f.file->f_path, mode);
fdput(f);
}
return err;
}
/* ARGSUSED */
static int
fdlookup(vnode_t *dp, char *comp, vnode_t **vpp, pathname_t *pnp,
int flags, vnode_t *rdir, cred_t *cr, caller_context_t *ct,
int *direntflags, pathname_t *realpnp)
{
if (comp[0] == 0 || strcmp(comp, ".") == 0 || strcmp(comp, "..") == 0) {
VN_HOLD(dp);
*vpp = dp;
return (0);
}
return (fdget(dp, comp, vpp));
}
static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
u64 off, u64 olen, u64 destoff)
{
struct fd src_file = fdget(srcfd);
int ret;
if (!src_file.file)
return -EBADF;
ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
fdput(src_file);
return ret;
}
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
int error;
struct fd f = fdget(fd);
if (!f.file)
return -EBADF;
error = security_file_ioctl(f.file, cmd, arg);
if (!error)
error = do_vfs_ioctl(f.file, fd, cmd, arg);
fdput(f);
return error;
}
static int do_fsync(unsigned int fd, int datasync)
{
struct fd f = fdget(fd);
int ret = -EBADF;
#ifdef CONFIG_FSYNC_OFF
return 0;
#endif
if (f.file) {
ret = vfs_fsync(f.file, datasync);
fdput(f);
}
return ret;
}
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_read(f.file, buf, count, &pos);
file_pos_write(f.file, pos);
fdput(f);
}
return ret;
}
int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
{
int error;
struct fd f = fdget(fd);
if (!f.file)
return -EBADF;
error = security_file_ioctl(f.file, cmd, arg);
if (!error)
error = do_vfs_ioctl(f.file, fd, cmd, arg);
fdput(f);
return error;
}
static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
unsigned long srcfd)
{
int rc;
struct fd src_file;
struct inode *src_inode;
cifs_dbg(FYI, "ioctl copychunk 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->f_op->unlocked_ioctl != cifs_ioctl) {
rc = -EBADF;
cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
goto out_fput;
}
src_inode = file_inode(src_file.file);
rc = -EINVAL;
if (S_ISDIR(src_inode->i_mode))
goto out_fput;
rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0,
src_inode->i_size, 0);
if (rc > 0)
rc = 0;
out_fput:
fdput(src_file);
out_drop_write:
mnt_drop_write_file(dst_file);
return rc;
}
/*
* do_utimes - change times on filename or file descriptor
* @dfd: open file descriptor, -1 or AT_FDCWD
* @filename: path name or NULL
* @times: new times or NULL
* @flags: zero or more flags (only AT_SYMLINK_NOFOLLOW for the moment)
*
* If filename is NULL and dfd refers to an open file, then operate on
* the file. Otherwise look up filename, possibly using dfd as a
* starting point.
*
* If times==NULL, set access and modification to current time,
* must be owner or have write permission.
* Else, update from *times, must be owner or super user.
*/
long do_utimes(int dfd, const char __user *filename, struct timespec *times,
int flags)
{
int error = -EINVAL;
if (times && (!nsec_valid(times[0].tv_nsec) ||
!nsec_valid(times[1].tv_nsec))) {
goto out;
}
if (flags & ~AT_SYMLINK_NOFOLLOW)
goto out;
if (filename == NULL && dfd != AT_FDCWD) {
struct fd f;
if (flags & AT_SYMLINK_NOFOLLOW)
goto out;
f = fdget(dfd);
error = -EBADF;
if (!f.file)
goto out;
error = utimes_common(&f.file->f_path, times);
fdput(f);
} else {
struct path path;
int lookup_flags = 0;
if (!(flags & AT_SYMLINK_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = utimes_common(&path, times);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
}
out:
return error;
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
struct vfsmount *mnt;
struct fd f;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
f = fdget(fd);
if (!f.file)
goto out;
/* explicitly opened as large or we are on 64-bit box */
if (f.file->f_flags & O_LARGEFILE)
small = 0;
dentry = f.file->f_path.dentry;
mnt = f.file->f_path.mnt;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
error = do_truncate2(mnt, dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
out:
return error;
}
COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
const struct compat_iovec __user *, vec,
compat_ulong_t, vlen)
{
struct fd f = fdget(fd);
ssize_t ret;
loff_t pos;
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
ret = compat_writev(f.file, vec, vlen, &pos);
f.file->f_pos = pos;
fdput(f);
return ret;
}
COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen)
{
struct fd f = fdget(fd);
ssize_t ret;
loff_t pos;
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
ret = compat_readv(f.file, vec, vlen, &pos);
f.file->f_pos = pos;
fdput(f);
return ret;
}
/*
* sync a single super
*/
SYSCALL_DEFINE1(syncfs, int, fd)
{
struct fd f = fdget(fd);
struct super_block *sb;
int ret;
if (!f.file)
return -EBADF;
sb = f.file->f_dentry->d_sb;
down_read(&sb->s_umount);
ret = sync_filesystem(sb);
up_read(&sb->s_umount);
fdput(f);
return ret;
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
struct fd f;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
f = fdget(fd);
if (!f.file)
goto out;
if (f.file->f_flags & O_LARGEFILE)
small = 0;
dentry = f.file->f_path.dentry;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
out:
return error;
}
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
struct fd f = fdget(fd);
if (!f.file)
return -EBADF;
retval = -EINVAL;
if (whence <= SEEK_MAX) {
loff_t res = vfs_llseek(f.file, offset, whence);
retval = res;
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
fdput(f);
return retval;
}
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
struct fd f = fdget(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
ret = vfs_writev(f.file, vec, vlen, &pos);
file_pos_write(f.file, pos);
fdput(f);
}
if (ret > 0)
add_wchar(current, ret);
inc_syscw(current);
return ret;
}
static long __compat_sys_pwritev64(unsigned long fd,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t pos)
{
struct fd f;
ssize_t ret;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (!f.file)
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
ret = compat_writev(f.file, vec, vlen, &pos);
fdput(f);
return ret;
}
static struct vfsmount *get_vfsmount_from_fd(int fd)
{
struct vfsmount *mnt;
if (fd == AT_FDCWD) {
struct fs_struct *fs = current->fs;
spin_lock(&fs->lock);
mnt = mntget(fs->pwd.mnt);
spin_unlock(&fs->lock);
} else {
struct fd f = fdget(fd);
if (!f.file)
return ERR_PTR(-EBADF);
mnt = mntget(f.file->f_path.mnt);
fdput(f);
}
return mnt;
}
COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
struct fd f;
ssize_t ret;
if (pos < 0)
return -EINVAL;
f = fdget(fd);
if (!f.file)
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
ret = compat_readv(f.file, vec, vlen, &pos);
fdput(f);
return ret;
}
