void *ns_get_path(struct path *path, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct vfsmount *mnt = mntget(nsfs_mnt);
struct qstr qname = { .name = "", };
struct dentry *dentry;
struct inode *inode;
struct ns_common *ns;
unsigned long d;
again:
ns = ns_ops->get(task);
if (!ns) {
mntput(mnt);
return ERR_PTR(-ENOENT);
}
rcu_read_lock();
d = atomic_long_read(&ns->stashed);
if (!d)
goto slow;
dentry = (struct dentry *)d;
if (!lockref_get_not_dead(&dentry->d_lockref))
goto slow;
rcu_read_unlock();
ns_ops->put(ns);
got_it:
path->mnt = mnt;
path->dentry = dentry;
return NULL;
slow:
rcu_read_unlock();
inode = new_inode_pseudo(mnt->mnt_sb);
if (!inode) {
ns_ops->put(ns);
mntput(mnt);
return ERR_PTR(-ENOMEM);
}
inode->i_ino = ns->inum;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_flags |= S_IMMUTABLE;
inode->i_mode = S_IFREG | S_IRUGO;
inode->i_fop = &ns_file_operations;
inode->i_private = ns;
dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
if (!dentry) {
iput(inode);
mntput(mnt);
return ERR_PTR(-ENOMEM);
}
d_instantiate(dentry, inode);
dentry->d_fsdata = (void *)ns_ops;
d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
if (d) {
d_delete(dentry); /* make sure ->d_prune() does nothing */
dput(dentry);
cpu_relax();
goto again;
}
goto got_it;
}
int ns_get_name(char *buf, size_t size, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct ns_common *ns;
int res = -ENOENT;
ns = ns_ops->get(task);
if (ns) {
res = snprintf(buf, size, "%s:[%u]", ns_ops->name, ns->inum);
ns_ops->put(ns);
}
return res;
}
struct file *proc_ns_fget(int fd)
{
struct file *file;
file = fget(fd);
if (!file)
return ERR_PTR(-EBADF);
if (file->f_op != &ns_file_operations)
goto out_invalid;
return file;
out_invalid:
fput(file);
return ERR_PTR(-EINVAL);
}
static const struct super_operations nsfs_ops = {
.statfs = simple_statfs,
.evict_inode = nsfs_evict,
};
static struct dentry *nsfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_pseudo(fs_type, "nsfs:", &nsfs_ops,
&ns_dentry_operations, NSFS_MAGIC);
}
static struct file_system_type nsfs = {
.name = "nsfs",
.mount = nsfs_mount,
.kill_sb = kill_anon_super,
};
void __init nsfs_init(void)
{
nsfs_mnt = kern_mount(&nsfs);
if (IS_ERR(nsfs_mnt))
panic("can't set nsfs up\n");
nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
}
ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
const char __user *buf,
int in_len, int out_len)
{
struct ib_uverbs_get_context cmd;
struct ib_uverbs_get_context_resp resp;
struct ib_udata udata;
struct ib_device *ibdev = file->device->ib_dev;
struct ib_ucontext *ucontext;
struct file *filp;
int ret;
if (out_len < sizeof resp)
return -ENOSPC;
if (copy_from_user(&cmd, buf, sizeof cmd))
return -EFAULT;
mutex_lock(&file->mutex);
if (file->ucontext) {
ret = -EINVAL;
goto err;
}
INIT_UDATA(&udata, buf + sizeof cmd,
(unsigned long) cmd.response + sizeof resp,
in_len - sizeof cmd, out_len - sizeof resp);
ucontext = ibdev->alloc_ucontext(ibdev, &udata);
if (IS_ERR(ucontext))
return PTR_ERR(file->ucontext);
ucontext->device = ibdev;
INIT_LIST_HEAD(&ucontext->pd_list);
INIT_LIST_HEAD(&ucontext->mr_list);
INIT_LIST_HEAD(&ucontext->mw_list);
INIT_LIST_HEAD(&ucontext->cq_list);
INIT_LIST_HEAD(&ucontext->qp_list);
INIT_LIST_HEAD(&ucontext->srq_list);
INIT_LIST_HEAD(&ucontext->ah_list);
resp.num_comp_vectors = file->device->num_comp_vectors;
filp = ib_uverbs_alloc_event_file(file, 1, &resp.async_fd);
if (IS_ERR(filp)) {
ret = PTR_ERR(filp);
goto err_free;
}
if (copy_to_user((void __user *) (unsigned long) cmd.response,
&resp, sizeof resp)) {
ret = -EFAULT;
goto err_file;
}
file->async_file = filp->private_data;
INIT_IB_EVENT_HANDLER(&file->event_handler, file->device->ib_dev,
ib_uverbs_event_handler);
ret = ib_register_event_handler(&file->event_handler);
if (ret)
goto err_file;
kref_get(&file->async_file->ref);
kref_get(&file->ref);
file->ucontext = ucontext;
fd_install(resp.async_fd, filp);
mutex_unlock(&file->mutex);
return in_len;
err_file:
put_unused_fd(resp.async_fd);
fput(filp);
err_free:
ibdev->dealloc_ucontext(ucontext);
err:
mutex_unlock(&file->mutex);
return ret;
}
int
cifs_atomic_open(struct inode *inode, struct dentry *direntry,
struct file *file, unsigned oflags, umode_t mode,
int *opened)
{
int rc;
unsigned int xid;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifs_fid fid;
struct cifs_pending_open open;
__u32 oplock;
struct cifsFileInfo *file_info;
/*
* Posix open is only called (at lookup time) for file create now. For
* opens (rather than creates), because we do not know if it is a file
* or directory yet, and current Samba no longer allows us to do posix
* open on dirs, we could end up wasting an open call on what turns out
* to be a dir. For file opens, we wait to call posix open till
* cifs_open. It could be added to atomic_open in the future but the
* performance tradeoff of the extra network request when EISDIR or
* EACCES is returned would have to be weighed against the 50% reduction
* in network traffic in the other paths.
*/
if (!(oflags & O_CREAT)) {
struct dentry *res;
/*
* Check for hashed negative dentry. We have already revalidated
* the dentry and it is fine. No need to perform another lookup.
*/
if (!d_unhashed(direntry))
return -ENOENT;
res = cifs_lookup(inode, direntry, 0);
if (IS_ERR(res))
return PTR_ERR(res);
return finish_no_open(file, res);
}
rc = check_name(direntry);
if (rc)
return rc;
xid = get_xid();
cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
inode, direntry, direntry);
tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
if (IS_ERR(tlink)) {
rc = PTR_ERR(tlink);
goto out_free_xid;
}
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
if (server->ops->new_lease_key)
server->ops->new_lease_key(&fid);
cifs_add_pending_open(&fid, tlink, &open);
rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
&oplock, &fid);
if (rc) {
cifs_del_pending_open(&open);
goto out;
}
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
*opened |= FILE_CREATED;
rc = finish_open(file, direntry, generic_file_open, opened);
if (rc) {
if (server->ops->close)
server->ops->close(xid, tcon, &fid);
cifs_del_pending_open(&open);
goto out;
}
if (file->f_flags & O_DIRECT &&
CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
if (CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
file->f_op = &cifs_file_direct_nobrl_ops;
else
file->f_op = &cifs_file_direct_ops;
}
file_info = cifs_new_fileinfo(&fid, file, tlink, oplock);
if (file_info == NULL) {
if (server->ops->close)
server->ops->close(xid, tcon, &fid);
cifs_del_pending_open(&open);
fput(file);
rc = -ENOMEM;
}
out:
cifs_put_tlink(tlink);
out_free_xid:
free_xid(xid);
return rc;
}
long ext4_ioctl(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg)
{
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
#if EXT4_PORT
switch (cmd) {
case EXT4_IOC_GETFLAGS:
ext4_get_inode_flags(ei);
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
handle_t *handle = NULL;
int err, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags;
unsigned int jflag;
if (!is_owner_or_cap(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
flags = ext4_mask_flags(inode->i_mode, flags);
err = -EPERM;
mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
goto flags_out;
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
jflag = flags & EXT4_JOURNAL_DATA_FL;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE))
goto flags_out;
}
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
if (oldflags & EXT4_EXTENTS_FL) {
/* We don't support clearning extent flags */
if (!(flags & EXT4_EXTENTS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (flags & EXT4_EXTENTS_FL) {
/* migrate the file */
migrate = 1;
flags &= ~EXT4_EXTENTS_FL;
}
if (flags & EXT4_EOFBLOCKS_FL) {
/* we don't support adding EOFBLOCKS flag */
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
flags = flags & EXT4_FL_USER_MODIFIABLE;
flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE;
ei->i_flags = flags;
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext4_journal_stop(handle);
if (err)
goto flags_out;
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
err = ext4_change_inode_journal_flag(inode, jflag);
if (err)
goto flags_out;
if (migrate)
err = ext4_ext_migrate(inode);
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write(filp->f_path.mnt);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!is_owner_or_cap(inode))
return -EPERM;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto setversion_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = ext4_current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
setversion_out:
mnt_drop_write(filp->f_path.mnt);
return err;
}
#ifdef CONFIG_JBD2_DEBUG
case EXT4_IOC_WAIT_FOR_READONLY:
/*
* This is racy - by the time we're woken up and running,
* the superblock could be released. And the module could
* have been unloaded. So sue me.
*
* Returns 1 if it slept, else zero.
*/
{
struct super_block *sb = inode->i_sb;
DECLARE_WAITQUEUE(wait, current);
int ret = 0;
set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
schedule();
ret = 1;
}
remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
return ret;
}
#endif
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
struct super_block *sb = inode->i_sb;
int err, err2=0;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (get_user(n_blocks_count, (__u32 __user *)arg))
return -EFAULT;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write(filp->f_path.mnt);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct file *donor_filp;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
donor_filp = fget(me.donor_fd);
if (!donor_filp)
return -EBADF;
if (!(donor_filp->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
err = mnt_want_write(filp->f_path.mnt);
if (err)
goto mext_out;
me.moved_len = 0;
err = ext4_move_extents(filp, donor_filp, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write(filp->f_path.mnt);
if (me.moved_len > 0)
file_remove_suid(donor_filp);
if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
err = -EFAULT;
mext_out:
fput(donor_filp);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
struct super_block *sb = inode->i_sb;
int err, err2=0;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input)))
return -EFAULT;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
err = ext4_group_add(sb, &input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write(filp->f_path.mnt);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!is_owner_or_cap(inode))
return -EACCES;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
mutex_lock(&(inode->i_mutex));
err = ext4_ext_migrate(inode);
mutex_unlock(&(inode->i_mutex));
mnt_drop_write(filp->f_path.mnt);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!is_owner_or_cap(inode))
return -EACCES;
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write(filp->f_path.mnt);
return err;
}
case FITRIM:
{
struct super_block *sb = inode->i_sb;
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&range, (struct fstrim_range *)arg,
sizeof(range)))
return -EFAULT;
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
default:
return -ENOTTY;
}
#endif
return (-EINVAL);
}
static int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
{
int ro;
struct file *filp = NULL;
int rc = -EINVAL;
struct inode *inode = NULL;
loff_t size;
loff_t num_sectors;
loff_t min_sectors;
unsigned int blkbits;
unsigned int blksize;
/* R/W if we can, R/O if we must */
ro = curlun->initially_ro;
if (!ro) {
filp = filp_open(filename, O_RDWR | O_LARGEFILE, 0);
if (PTR_ERR(filp) == -EROFS || PTR_ERR(filp) == -EACCES)
ro = 1;
}
if (ro)
filp = filp_open(filename, O_RDONLY | O_LARGEFILE, 0);
if (IS_ERR(filp)) {
LINFO(curlun, "unable to open backing file: %s\n", filename);
return PTR_ERR(filp);
}
if (!(filp->f_mode & FMODE_WRITE))
ro = 1;
inode = file_inode(filp);
if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) {
LINFO(curlun, "invalid file type: %s\n", filename);
goto out;
}
/*
* If we can't read the file, it's no good.
* If we can't write the file, use it read-only.
*/
if (!(filp->f_op->read || filp->f_op->aio_read)) {
LINFO(curlun, "file not readable: %s\n", filename);
goto out;
}
if (!(filp->f_op->write || filp->f_op->aio_write))
ro = 1;
size = i_size_read(inode->i_mapping->host);
if (size < 0) {
LINFO(curlun, "unable to find file size: %s\n", filename);
rc = (int) size;
goto out;
}
if (curlun->cdrom) {
blksize = 2048;
blkbits = 11;
} else if (inode->i_bdev) {
blksize = bdev_logical_block_size(inode->i_bdev);
blkbits = blksize_bits(blksize);
} else {
blksize = 512;
blkbits = 9;
}
num_sectors = size >> blkbits; /* File size in logic-block-size blocks */
min_sectors = 1;
if (curlun->cdrom) {
min_sectors = 300; /* Smallest track is 300 frames */
if (num_sectors >= 256*60*75) {
num_sectors = 256*60*75 - 1;
LINFO(curlun, "file too big: %s\n", filename);
LINFO(curlun, "using only first %d blocks\n",
(int) num_sectors);
}
}
if (num_sectors < min_sectors) {
LINFO(curlun, "file too small: %s\n", filename);
rc = -ETOOSMALL;
goto out;
}
if (fsg_lun_is_open(curlun))
fsg_lun_close(curlun);
curlun->blksize = blksize;
curlun->blkbits = blkbits;
curlun->ro = ro;
curlun->filp = filp;
curlun->file_length = size;
curlun->num_sectors = num_sectors;
LDBG(curlun, "open backing file: %s\n", filename);
return 0;
out:
fput(filp);
return rc;
}
static void *__ns_get_path(struct path *path, struct ns_common *ns)
{
struct vfsmount *mnt = nsfs_mnt;
struct qstr qname = { .name = "", };
struct dentry *dentry;
struct inode *inode;
unsigned long d;
rcu_read_lock();
d = atomic_long_read(&ns->stashed);
if (!d)
goto slow;
dentry = (struct dentry *)d;
if (!lockref_get_not_dead(&dentry->d_lockref))
goto slow;
rcu_read_unlock();
ns->ops->put(ns);
got_it:
path->mnt = mntget(mnt);
path->dentry = dentry;
return NULL;
slow:
rcu_read_unlock();
inode = new_inode_pseudo(mnt->mnt_sb);
if (!inode) {
ns->ops->put(ns);
return ERR_PTR(-ENOMEM);
}
inode->i_ino = ns->inum;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_flags |= S_IMMUTABLE;
inode->i_mode = S_IFREG | S_IRUGO;
inode->i_fop = &ns_file_operations;
inode->i_private = ns;
dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
if (!dentry) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
d_instantiate(dentry, inode);
dentry->d_flags |= DCACHE_RCUACCESS;
dentry->d_fsdata = (void *)ns->ops;
d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
if (d) {
d_delete(dentry); /* make sure ->d_prune() does nothing */
dput(dentry);
cpu_relax();
return ERR_PTR(-EAGAIN);
}
goto got_it;
}
void *ns_get_path(struct path *path, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct ns_common *ns;
void *ret;
again:
ns = ns_ops->get(task);
if (!ns)
return ERR_PTR(-ENOENT);
ret = __ns_get_path(path, ns);
if (IS_ERR(ret) && PTR_ERR(ret) == -EAGAIN)
goto again;
return ret;
}
int open_related_ns(struct ns_common *ns,
struct ns_common *(*get_ns)(struct ns_common *ns))
{
struct path path = {};
struct file *f;
void *err;
int fd;
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
return fd;
while (1) {
struct ns_common *relative;
relative = get_ns(ns);
if (IS_ERR(relative)) {
put_unused_fd(fd);
return PTR_ERR(relative);
}
err = __ns_get_path(&path, relative);
if (IS_ERR(err) && PTR_ERR(err) == -EAGAIN)
continue;
break;
}
if (IS_ERR(err)) {
put_unused_fd(fd);
return PTR_ERR(err);
}
f = dentry_open(&path, O_RDONLY, current_cred());
path_put(&path);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else
fd_install(fd, f);
return fd;
}
static long ns_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
struct user_namespace *user_ns;
struct ns_common *ns = get_proc_ns(file_inode(filp));
uid_t __user *argp;
uid_t uid;
switch (ioctl) {
case NS_GET_USERNS:
return open_related_ns(ns, ns_get_owner);
case NS_GET_PARENT:
if (!ns->ops->get_parent)
return -EINVAL;
return open_related_ns(ns, ns->ops->get_parent);
case NS_GET_NSTYPE:
return ns->ops->type;
case NS_GET_OWNER_UID:
if (ns->ops->type != CLONE_NEWUSER)
return -EINVAL;
user_ns = container_of(ns, struct user_namespace, ns);
argp = (uid_t __user *) arg;
uid = from_kuid_munged(current_user_ns(), user_ns->owner);
return put_user(uid, argp);
default:
return -ENOTTY;
}
}
int ns_get_name(char *buf, size_t size, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct ns_common *ns;
int res = -ENOENT;
ns = ns_ops->get(task);
if (ns) {
res = snprintf(buf, size, "%s:[%u]", ns_ops->name, ns->inum);
ns_ops->put(ns);
}
return res;
}
struct file *proc_ns_fget(int fd)
{
struct file *file;
file = fget(fd);
if (!file)
return ERR_PTR(-EBADF);
if (file->f_op != &ns_file_operations)
goto out_invalid;
return file;
out_invalid:
fput(file);
return ERR_PTR(-EINVAL);
}
static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino);
return 0;
}
static const struct super_operations nsfs_ops = {
.statfs = simple_statfs,
.evict_inode = nsfs_evict,
.show_path = nsfs_show_path,
};
static struct dentry *nsfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_pseudo(fs_type, "nsfs:", &nsfs_ops,
&ns_dentry_operations, NSFS_MAGIC);
}
static struct file_system_type nsfs = {
.name = "nsfs",
.mount = nsfs_mount,
.kill_sb = kill_anon_super,
};
void __init nsfs_init(void)
{
nsfs_mnt = kern_mount(&nsfs);
if (IS_ERR(nsfs_mnt))
panic("can't set nsfs up\n");
nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
}
struct super_block *autofs_read_super(struct super_block *s, void *data,
int silent)
{
struct inode * root_inode;
struct dentry * root;
struct file * pipe;
int pipefd;
struct autofs_sb_info *sbi;
int minproto, maxproto;
sbi = (struct autofs_sb_info *) kmalloc(sizeof(struct autofs_sb_info), GFP_KERNEL);
if ( !sbi )
goto fail_unlock;
DPRINTK(("autofs: starting up, sbi = %p\n",sbi));
s->u.generic_sbp = sbi;
sbi->magic = AUTOFS_SBI_MAGIC;
sbi->catatonic = 0;
sbi->exp_timeout = 0;
sbi->oz_pgrp = current->pgrp;
autofs_initialize_hash(&sbi->dirhash);
sbi->queues = NULL;
memset(sbi->symlink_bitmap, 0, sizeof(long)*AUTOFS_SYMLINK_BITMAP_LEN);
sbi->next_dir_ino = AUTOFS_FIRST_DIR_INO;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = AUTOFS_SUPER_MAGIC;
s->s_op = &autofs_sops;
root_inode = iget(s, AUTOFS_ROOT_INO);
root = d_alloc_root(root_inode);
pipe = NULL;
if (!root)
goto fail_iput;
/* Can this call block? - WTF cares? s is locked. */
if ( parse_options(data,&pipefd,&root_inode->i_uid,&root_inode->i_gid,&sbi->oz_pgrp,&minproto,&maxproto) ) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
/* Couldn't this be tested earlier? */
if ( minproto > AUTOFS_PROTO_VERSION ||
maxproto < AUTOFS_PROTO_VERSION ) {
printk("autofs: kernel does not match daemon version\n");
goto fail_dput;
}
DPRINTK(("autofs: pipe fd = %d, pgrp = %u\n", pipefd, sbi->oz_pgrp));
pipe = fget(pipefd);
if ( !pipe ) {
printk("autofs: could not open pipe file descriptor\n");
goto fail_dput;
}
if ( !pipe->f_op || !pipe->f_op->write )
goto fail_fput;
sbi->pipe = pipe;
/*
* Success! Install the root dentry now to indicate completion.
*/
s->s_root = root;
return s;
fail_fput:
printk("autofs: pipe file descriptor does not contain proper ops\n");
fput(pipe);
fail_dput:
dput(root);
goto fail_free;
fail_iput:
printk("autofs: get root dentry failed\n");
iput(root_inode);
fail_free:
kfree(sbi);
fail_unlock:
return NULL;
}
/* Move priv file to the alien_ni stack.
* Should be called with the locked priv stack and socket;
* the function returns with this stack being unlocked.
* If rc=0, it returns with alien_ni stack locked;
* otherwise, both stacks are unlocked.
* Socket is always unlocked on return. */
int efab_file_move_to_alien_stack(ci_private_t *priv, ci_netif *alien_ni)
{
tcp_helper_resource_t *old_thr = priv->thr;
tcp_helper_resource_t *new_thr = netif2tcp_helper_resource(alien_ni);
ci_sock_cmn *old_s = SP_TO_SOCK(&old_thr->netif, priv->sock_id);
ci_sock_cmn *new_s;
ci_sock_cmn *mid_s;
tcp_helper_endpoint_t *old_ep, *new_ep;
int rc, i;
int pollwait_register = 0;
#if CI_CFG_FD_CACHING
oo_p sp;
#endif
OO_DEBUG_TCPH(ci_log("%s: move %d:%d to %d", __func__,
old_thr->id, priv->sock_id, new_thr->id));
/* Poll the old stack - deliver all data to our socket */
ci_netif_poll(&old_thr->netif);
/* Endpoints in epoll list should not be moved, because waitq is already
* in the epoll internal structures (bug 41152). */
if( !list_empty(&priv->_filp->f_ep_links) ) {
rc = -EBUSY;
goto fail1;
}
if( !efab_file_move_supported(&old_thr->netif, old_s) ) {
rc = -EINVAL;
goto fail1;
}
/* Lock the second stack */
i = 0;
while( ! ci_netif_trylock(alien_ni) ) {
ci_netif_unlock(&old_thr->netif);
if( i++ >= 1000 ) {
rc = -EBUSY;
goto fail1_ni_unlocked;
}
rc = ci_netif_lock(&old_thr->netif);
if( rc != 0 )
goto fail1_ni_unlocked;
}
/* Allocate a new socket in the alien_ni stack */
rc = -ENOMEM;
if( old_s->b.state == CI_TCP_STATE_UDP ) {
ci_udp_state *new_us = ci_udp_get_state_buf(alien_ni);
if( new_us == NULL )
goto fail2;
new_s = &new_us->s;
}
else {
ci_tcp_state *new_ts = ci_tcp_get_state_buf(alien_ni);
if( new_ts == NULL )
goto fail2;
new_s = &new_ts->s;
}
/* Allocate an intermediate "socket" outside of everything */
mid_s = ci_alloc(CI_MAX(sizeof(ci_tcp_state), sizeof(ci_udp_state)));
if( mid_s == NULL )
goto fail3;
OO_DEBUG_TCPH(ci_log("%s: move %d:%d to %d:%d", __func__,
old_thr->id, priv->sock_id,
new_thr->id, new_s->b.bufid));
/* Copy TCP/UDP state */
memcpy(mid_s, old_s, CI_MAX(sizeof(ci_tcp_state), sizeof(ci_udp_state)));
/* do not copy old_s->b.bufid
* and other fields in stack adress space */
mid_s->b.sb_aflags |= CI_SB_AFLAG_ORPHAN;
mid_s->b.bufid = new_s->b.bufid;
mid_s->b.post_poll_link = new_s->b.post_poll_link;
mid_s->b.ready_link = new_s->b.ready_link;
mid_s->reap_link = new_s->reap_link;
if( old_s->b.state & CI_TCP_STATE_TCP ) {
ci_tcp_state *new_ts = SOCK_TO_TCP(new_s);
ci_tcp_state *mid_ts = SOCK_TO_TCP(mid_s);
mid_ts->timeout_q_link = new_ts->timeout_q_link;
mid_ts->tx_ready_link = new_ts->tx_ready_link;
mid_ts->rto_tid = new_ts->rto_tid;
mid_ts->delack_tid = new_ts->delack_tid;
mid_ts->zwin_tid = new_ts->zwin_tid;
mid_ts->kalive_tid = new_ts->kalive_tid;
mid_ts->cork_tid = new_ts->cork_tid;
ci_ip_queue_init(&mid_ts->recv1);
ci_ip_queue_init(&mid_ts->recv2);
ci_ip_queue_init(&mid_ts->send);
ci_ip_queue_init(&mid_ts->retrans);
mid_ts->send_prequeue = OO_PP_ID_NULL;
new_ts->retrans_ptr = OO_PP_NULL;
mid_ts->tmpl_head = OO_PP_NULL;
oo_atomic_set(&mid_ts->send_prequeue_in, 0);
*new_ts = *mid_ts;
ci_pmtu_state_init(alien_ni, &new_ts->s, &new_ts->pmtus,
CI_IP_TIMER_PMTU_DISCOVER);
#if CI_CFG_FD_CACHING
sp = TS_OFF(alien_ni, new_ts);
OO_P_ADD(sp, CI_MEMBER_OFFSET(ci_tcp_state, epcache_link));
ci_ni_dllist_link_init(alien_ni, &new_ts->epcache_link, sp, "epch");
ci_ni_dllist_self_link(alien_ni, &new_ts->epcache_link);
sp = TS_OFF(alien_ni, new_ts);
OO_P_ADD(sp, CI_MEMBER_OFFSET(ci_tcp_state, epcache_fd_link));
ci_ni_dllist_link_init(alien_ni, &new_ts->epcache_fd_link, sp, "ecfd");
ci_ni_dllist_self_link(alien_ni, &new_ts->epcache_fd_link);
#endif
/* free temporary mid_ts storage */
CI_FREE_OBJ(mid_ts);
}
else {
ci_udp_state *mid_us = SOCK_TO_UDP(mid_s);
*SOCK_TO_UDP(new_s) = *mid_us;
CI_FREE_OBJ(mid_us);
}
/* Move the filter */
old_ep = ci_trs_ep_get(old_thr, priv->sock_id);
new_ep = ci_trs_ep_get(new_thr, new_s->b.bufid);
rc = tcp_helper_endpoint_move_filters_pre(old_ep, new_ep);
if( rc != 0 ) {
rc = -EINVAL;
goto fail3;
}
/* Allocate a new file for the new endpoint */
rc = onload_alloc_file(new_thr, new_s->b.bufid, priv->_filp->f_flags,
priv->fd_type, &old_ep->alien_ref);
if( rc != 0 )
goto fail4;
ci_assert(old_ep->alien_ref);
/* Copy F_SETOWN_EX, F_SETSIG to the new file */
#ifdef F_SETOWN_EX
rcu_read_lock();
__f_setown(old_ep->alien_ref->_filp, priv->_filp->f_owner.pid,
priv->_filp->f_owner.pid_type, 1);
rcu_read_unlock();
#endif
old_ep->alien_ref->_filp->f_owner.signum = priv->_filp->f_owner.signum;
old_ep->alien_ref->_filp->f_flags |= priv->_filp->f_flags & O_NONBLOCK;
/* Move os_socket from one ep to another */
if( tcp_helper_endpoint_set_aflags(new_ep, OO_THR_EP_AFLAG_ATTACHED) &
OO_THR_EP_AFLAG_ATTACHED ) {
fput(old_ep->alien_ref->_filp);
rc = -EBUSY;
goto fail2; /* state & filters are cleared by fput() */
}
/********* Point of no return **********/
ci_wmb();
priv->fd_type = CI_PRIV_TYPE_ALIEN_EP;
priv->_filp->f_op = &linux_tcp_helper_fops_alien;
ci_wmb();
oo_file_moved(priv);
/* Read all already-arrived packets after the filters move but before
* copying of the receive queue. */
ci_netif_poll(&old_thr->netif);
tcp_helper_endpoint_move_filters_post(old_ep, new_ep);
ci_assert( efab_file_move_supported(&old_thr->netif, old_s));
/* There's a gap between un-registering the old ep, and registering the
* the new. However, the notifications shouldn't be in use for sockets
* that are in a state that can be moved, so this shouldn't be a problem.
*/
if( old_ep->os_sock_pt.whead ) {
pollwait_register = 1;
efab_tcp_helper_os_pollwait_unregister(old_ep);
}
ci_assert_equal(new_ep->os_socket, NULL);
new_ep->os_socket = oo_file_ref_xchg(&old_ep->os_socket, NULL);
ci_assert_equal(old_ep->os_socket, NULL);
if( pollwait_register )
efab_tcp_helper_os_pollwait_register(new_ep);
ci_bit_clear(&new_s->b.sb_aflags, CI_SB_AFLAG_ORPHAN_BIT);
if( new_s->b.state == CI_TCP_ESTABLISHED )
CI_TCP_STATS_INC_CURR_ESTAB(alien_ni);
/* Copy recv queue */
if( new_s->b.state & CI_TCP_STATE_TCP ) {
ci_tcp_state *new_ts = SOCK_TO_TCP(new_s);
ci_tcp_state *old_ts = SOCK_TO_TCP(old_s);
int i;
/* Stop timers */
ci_ip_timer_clear(&old_thr->netif, &old_ts->kalive_tid);
ci_ip_timer_clear(&old_thr->netif, &old_ts->delack_tid);
efab_ip_queue_copy(alien_ni, &new_ts->recv1,
&old_thr->netif, &old_ts->recv1);
efab_ip_queue_copy(alien_ni, &new_ts->recv2,
&old_thr->netif, &old_ts->recv2);
new_ts->recv1_extract = new_ts->recv1.head;
/* Drop reorder buffer */
ci_ip_queue_init(&new_ts->rob);
new_ts->dsack_block = OO_PP_INVALID;
new_ts->dsack_start = new_ts->dsack_end = 0;
for( i = 0; i <= CI_TCP_SACK_MAX_BLOCKS; i++ )
new_ts->last_sack[i] = OO_PP_NULL;
}
else {
/* There should not be any recv q, but drop it to be sure */
ci_udp_recv_q_init(&SOCK_TO_UDP(new_s)->recv_q);
}
/* Old stack can be unlocked */
old_s->b.sb_flags |= CI_SB_FLAG_MOVED;
ci_netif_unlock(&old_thr->netif);
ci_assert( efab_file_move_supported(alien_ni, new_s) );
/* Move done: poll for any new data. */
ci_netif_poll(alien_ni);
if( new_s->b.state & CI_TCP_STATE_TCP ) {
ci_tcp_state *new_ts = SOCK_TO_TCP(new_s);
/* Timers setup: delack, keepalive */
if( (new_ts->acks_pending & CI_TCP_ACKS_PENDING_MASK) > 0)
ci_tcp_timeout_delack(alien_ni, new_ts);
ci_tcp_kalive_reset(alien_ni, new_ts);
}
/* Old ep: we are done. */
ci_bit_set(&old_s->b.sb_aflags, CI_SB_AFLAG_MOVED_AWAY_BIT);
old_s->b.moved_to_stack_id = alien_ni->state->stack_id;
old_s->b.moved_to_sock_id = new_s->b.bufid;
if( ! list_empty(&priv->_filp->f_ep_links) )
ci_bit_set(&old_s->b.sb_aflags, CI_SB_AFLAG_MOVED_AWAY_IN_EPOLL_BIT);
ci_sock_unlock(&old_thr->netif, &old_s->b);
ci_sock_unlock(alien_ni, &new_s->b);
ci_assert(ci_netif_is_locked(alien_ni));
OO_DEBUG_TCPH(ci_log("%s: -> [%d:%d] %s", __func__,
new_thr->id, new_s->b.bufid,
ci_tcp_state_str(new_s->b.state)));
return 0;
fail4:
/* We clear the filters from the new ep.
* For now, we do not need to re-insert old filters because hw filters
* are alredy here (in case of accepted socket) or not needed.
* We have not removed old sw filters yet. */
tcp_helper_endpoint_move_filters_undo(old_ep, new_ep);
fail3:
if( new_s->b.state & CI_TCP_STATE_TCP )
ci_tcp_state_free(alien_ni, SOCK_TO_TCP(new_s));
else
ci_udp_state_free(alien_ni, SOCK_TO_UDP(new_s));
fail2:
ci_netif_unlock(alien_ni);
fail1:
ci_netif_unlock(&old_thr->netif);
fail1_ni_unlocked:
ci_sock_unlock(&old_thr->netif, &old_s->b);
OO_DEBUG_TCPH(ci_log("%s: rc=%d", __func__, rc));
return rc;
}
int efab_file_move_to_alien_stack_rsop(ci_private_t *stack_priv, void *arg)
{
ci_fixed_descriptor_t sock_fd = *(ci_fixed_descriptor_t *)arg;
struct file *sock_file = fget(sock_fd);
ci_private_t *sock_priv;
tcp_helper_resource_t *old_thr;
tcp_helper_resource_t *new_thr;
citp_waitable *w;
int rc;
if( sock_file == NULL )
return -EINVAL;
if( !FILE_IS_ENDPOINT_SOCK(sock_file) ||
stack_priv->fd_type != CI_PRIV_TYPE_NETIF ) {
fput(sock_file);
return -EINVAL;
}
sock_priv = sock_file->private_data;
ci_assert(sock_priv->fd_type == CI_PRIV_TYPE_TCP_EP ||
sock_priv->fd_type == CI_PRIV_TYPE_UDP_EP);
old_thr = sock_priv->thr;
new_thr = stack_priv->thr;
ci_assert(old_thr);
ci_assert(new_thr);
if( old_thr == new_thr ) {
fput(sock_file);
return 0;
}
if( tcp_helper_cluster_from_cluster(old_thr) != 0 ) {
LOG_S(ci_log("%s: move_fd() not permitted on clustered stacks", __func__));
fput(sock_file);
return -EINVAL;
}
w = SP_TO_WAITABLE(&old_thr->netif, sock_priv->sock_id);
rc = ci_sock_lock(&old_thr->netif, w);
if( rc != 0 ) {
fput(sock_file);
return rc;
}
rc = ci_netif_lock(&old_thr->netif);
if( rc != 0 ) {
ci_sock_unlock(&old_thr->netif, w);
fput(sock_file);
return rc;
}
efab_thr_ref(new_thr);
rc = efab_file_move_to_alien_stack(sock_priv, &stack_priv->thr->netif);
fput(sock_file);
if( rc != 0 )
efab_thr_release(new_thr);
else
ci_netif_unlock(&new_thr->netif);
return rc;
}
/* We use the SunOS mmap() semantics. */
asmlinkage unsigned long sunos_mmap(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags,
unsigned long fd, unsigned long off)
{
struct file * file = NULL;
unsigned long retval, ret_type;
if (flags & MAP_NORESERVE) {
static int cnt;
if (cnt++ < 10)
printk("%s: unimplemented SunOS MAP_NORESERVE mmap() flag\n",
current->comm);
flags &= ~MAP_NORESERVE;
}
retval = -EBADF;
if (!(flags & MAP_ANONYMOUS)) {
if (fd >= SUNOS_NR_OPEN)
goto out;
file = fget(fd);
if (!file)
goto out;
}
retval = -EINVAL;
/* If this is ld.so or a shared library doing an mmap
* of /dev/zero, transform it into an anonymous mapping.
* SunOS is so stupid some times... hmph!
*/
if (file) {
if (imajor(file->f_dentry->d_inode) == MEM_MAJOR &&
iminor(file->f_dentry->d_inode) == 5) {
flags |= MAP_ANONYMOUS;
fput(file);
file = 0;
}
}
ret_type = flags & _MAP_NEW;
flags &= ~_MAP_NEW;
if (!(flags & MAP_FIXED))
addr = 0;
else {
if (ARCH_SUN4C_SUN4 &&
(len > 0x20000000 ||
((flags & MAP_FIXED) &&
addr < 0xe0000000 && addr + len > 0x20000000)))
goto out_putf;
/* See asm-sparc/uaccess.h */
if (len > TASK_SIZE - PAGE_SIZE ||
addr + len > TASK_SIZE - PAGE_SIZE)
goto out_putf;
}
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
down_write(¤t->mm->mmap_sem);
retval = do_mmap(file, addr, len, prot, flags, off);
up_write(¤t->mm->mmap_sem);
if (!ret_type)
retval = ((retval < PAGE_OFFSET) ? 0 : retval);
out_putf:
if (file)
fput(file);
out:
return retval;
}
/*
* This function implements the mmap(2) syscall, but only
* supports the MAP_SHARED, MAP_PRIVATE, MAP_FIXED, and
* MAP_ANON flags.
*
* Add a mapping to the current process's address space.
* You need to do some error checking; see the ERRORS section
* of the manpage for the problems you should anticipate.
* After error checking most of the work of this function is
* done by vmmap_map(), but remember to clear the TLB.
*/
int
do_mmap(void *addr, size_t len, int prot, int flags,
int fd, off_t off, void **ret)
{
dbg(DBG_PRINT,"go into do_mmap\n");
file_t* file = NULL;
if(!PAGE_ALIGNED(off))
{
dbg(DBG_PRINT,"(GRADING3C)\n");
return -EINVAL;
}
if(len <= 0||len > 0xc0000000)
{
dbg(DBG_PRINT,"(GRADING3C)\n");
return -EINVAL;
}
if (((uint32_t)addr < USER_MEM_LOW || (uint32_t)addr > USER_MEM_HIGH) && flags& MAP_FIXED)
{
dbg(DBG_PRINT,"(GRADING3C)\n");
return -1;
}
if(!(flags & MAP_SHARED || flags & MAP_PRIVATE))
{
dbg(DBG_PRINT,"(GRADING3C)\n");
return -EINVAL;
}
file = NULL;
vnode_t *vn = NULL;
int status = 0;
uint32_t lopages = 0;
size_t npages = (len - 1)/PAGE_SIZE + 1;
vmarea_t *newvma = NULL;
if(flags & MAP_FIXED)
{
dbg(DBG_PRINT,"(GRADING3C)\n");
lopages = ADDR_TO_PN( addr );
}
if(!(flags & MAP_ANON))
{
dbg(DBG_PRINT,"(GRADING3B)\n");
if(fd < 0 || fd > NFILES)
{
dbg(DBG_PRINT,"(GRADING3C)\n");
return -1;
}
file = fget(fd);
if((prot & PROT_WRITE && MAP_SHARED & flags) && (file->f_mode == FMODE_READ))
{
dbg(DBG_PRINT,"(GRADING3C)\n");
fput(file);
return -1;
}
if(file == NULL)
{
dbg(DBG_PRINT,"(GRADING3C)\n");
return -1;
}
vn = file->f_vnode;
}
status = vmmap_map(curproc->p_vmmap, vn, lopages, npages, prot, flags, off, VMMAP_DIR_HILO, &newvma);
if(file != NULL)
{
dbg(DBG_PRINT,"(GRADING3B)\n");
fput(file);
}
if(newvma != NULL)
{
dbg(DBG_PRINT,"(GRADING3B)\n");
*ret = PN_TO_ADDR(newvma->vma_start);
}
if(status < 0)
{
dbg(DBG_PRINT,"(GRADING3C)\n");
KASSERT(file == NULL);
return status;
}
tlb_flush_all();
KASSERT(curproc->p_pagedir != NULL);
dbg(DBG_VM, "(GRADING3A 2.a)\n");
return 0;
}
/**
* sync_file_merge() - merge two sync_files
* @name: name of new fence
* @a: sync_file a
* @b: sync_file b
*
* Creates a new sync_file which contains copies of all the fences in both
* @a and @b. @a and @b remain valid, independent sync_file. Returns the
* new merged sync_file or NULL in case of error.
*/
static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
struct sync_file *b)
{
struct sync_file *sync_file;
struct dma_fence **fences, **nfences, **a_fences, **b_fences;
int i, i_a, i_b, num_fences, a_num_fences, b_num_fences;
sync_file = sync_file_alloc();
if (!sync_file)
return NULL;
a_fences = get_fences(a, &a_num_fences);
b_fences = get_fences(b, &b_num_fences);
if (a_num_fences > INT_MAX - b_num_fences)
return NULL;
num_fences = a_num_fences + b_num_fences;
fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL);
if (!fences)
goto err;
/*
* Assume sync_file a and b are both ordered and have no
* duplicates with the same context.
*
* If a sync_file can only be created with sync_file_merge
* and sync_file_create, this is a reasonable assumption.
*/
for (i = i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) {
struct dma_fence *pt_a = a_fences[i_a];
struct dma_fence *pt_b = b_fences[i_b];
if (pt_a->context < pt_b->context) {
add_fence(fences, &i, pt_a);
i_a++;
} else if (pt_a->context > pt_b->context) {
add_fence(fences, &i, pt_b);
i_b++;
} else {
if (pt_a->seqno - pt_b->seqno <= INT_MAX)
add_fence(fences, &i, pt_a);
else
add_fence(fences, &i, pt_b);
i_a++;
i_b++;
}
}
for (; i_a < a_num_fences; i_a++)
add_fence(fences, &i, a_fences[i_a]);
for (; i_b < b_num_fences; i_b++)
add_fence(fences, &i, b_fences[i_b]);
if (i == 0)
fences[i++] = dma_fence_get(a_fences[0]);
if (num_fences > i) {
nfences = krealloc(fences, i * sizeof(*fences),
GFP_KERNEL);
if (!nfences)
goto err;
fences = nfences;
}
if (sync_file_set_fence(sync_file, fences, i) < 0) {
kfree(fences);
goto err;
}
strlcpy(sync_file->name, name, sizeof(sync_file->name));
return sync_file;
err:
fput(sync_file->file);
return NULL;
}
static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
{
char *cp, *i_name, *i_arg;
struct file *file;
char interp[BINPRM_BUF_SIZE];
int retval;
if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!') || (bprm->sh_bang))
return -ENOEXEC;
/*
* This section does the #! interpretation.
* Sorta complicated, but hopefully it will work. -TYT
*/
bprm->sh_bang++;
allow_write_access(bprm->file);
fput(bprm->file);
bprm->file = NULL;
bprm->buf[BINPRM_BUF_SIZE - 1] = '\0';
if ((cp = strchr(bprm->buf, '\n')) == NULL)
cp = bprm->buf+BINPRM_BUF_SIZE-1;
*cp = '\0';
while (cp > bprm->buf) {
cp--;
if ((*cp == ' ') || (*cp == '\t'))
*cp = '\0';
else
break;
}
for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++);
if (*cp == '\0')
return -ENOEXEC; /* No interpreter name found */
i_name = cp;
i_arg = NULL;
for ( ; *cp && (*cp != ' ') && (*cp != '\t'); cp++)
/* nothing */ ;
while ((*cp == ' ') || (*cp == '\t'))
*cp++ = '\0';
if (*cp)
i_arg = cp;
strcpy (interp, i_name);
/*
* OK, we've parsed out the interpreter name and
* (optional) argument.
* Splice in (1) the interpreter's name for argv[0]
* (2) (optional) argument to interpreter
* (3) filename of shell script (replace argv[0])
*
* This is done in reverse order, because of how the
* user environment and arguments are stored.
*/
remove_arg_zero(bprm);
retval = copy_strings_kernel(1, &bprm->interp, bprm);
if (retval < 0) return retval;
bprm->argc++;
if (i_arg) {
retval = copy_strings_kernel(1, &i_arg, bprm);
if (retval < 0) return retval;
bprm->argc++;
}
retval = copy_strings_kernel(1, &i_name, bprm);
if (retval) return retval;
bprm->argc++;
bprm->interp = interp;
/*
* OK, now restart the process with the interpreter's dentry.
*/
file = open_exec(interp);
if (IS_ERR(file))
return PTR_ERR(file);
bprm->file = file;
retval = prepare_binprm(bprm);
if (retval < 0)
return retval;
return search_binary_handler(bprm,regs);
}
/*
* Syssgi interface for swapext
*/
int
xfs_swapext(
xfs_swapext_t *sxp)
{
xfs_inode_t *ip, *tip;
struct file *file, *target_file;
int error = 0;
/* Pull information for the target fd */
file = fget((int)sxp->sx_fdtarget);
if (!file) {
error = XFS_ERROR(EINVAL);
goto out;
}
if (!(file->f_mode & FMODE_WRITE) ||
!(file->f_mode & FMODE_READ) ||
(file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
goto out_put_file;
}
target_file = fget((int)sxp->sx_fdtmp);
if (!target_file) {
error = XFS_ERROR(EINVAL);
goto out_put_file;
}
if (!(target_file->f_mode & FMODE_WRITE) ||
!(target_file->f_mode & FMODE_READ) ||
(target_file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
goto out_put_target_file;
}
ip = XFS_I(file->f_dentry->d_inode);
tip = XFS_I(target_file->f_dentry->d_inode);
if (ip->i_mount != tip->i_mount) {
error = XFS_ERROR(EINVAL);
goto out_put_target_file;
}
if (ip->i_ino == tip->i_ino) {
error = XFS_ERROR(EINVAL);
goto out_put_target_file;
}
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
error = XFS_ERROR(EIO);
goto out_put_target_file;
}
error = xfs_swap_extents(ip, tip, sxp);
out_put_target_file:
fput(target_file);
out_put_file:
fput(file);
out:
return error;
}
/*
* Copy up a dentry to a file of specified name.
*
* @dir: used to pull the ->i_sb to access other branches
* @dentry: the non-negative dentry whose lower_inode we should copy
* @bstart: the branch of the lower_inode to copy from
* @new_bindex: the branch to create the new file in
* @name: the name of the file to create
* @namelen: length of @name
* @copyup_file: the "struct file" to return (optional)
* @len: how many bytes to copy-up?
*/
int copyup_dentry(struct inode *dir, struct dentry *dentry, int bstart,
int new_bindex, const char *name, int namelen,
struct file **copyup_file, loff_t len)
{
struct dentry *new_lower_dentry;
struct dentry *old_lower_dentry = NULL;
struct super_block *sb;
int err = 0;
int old_bindex;
int old_bstart;
int old_bend;
struct dentry *new_lower_parent_dentry = NULL;
mm_segment_t oldfs;
char *symbuf = NULL;
verify_locked(dentry);
old_bindex = bstart;
old_bstart = dbstart(dentry);
old_bend = dbend(dentry);
BUG_ON(new_bindex < 0);
BUG_ON(new_bindex >= old_bindex);
sb = dir->i_sb;
err = is_robranch_super(sb, new_bindex);
if (err)
goto out;
/* Create the directory structure above this dentry. */
new_lower_dentry = create_parents(dir, dentry, name, new_bindex);
if (IS_ERR(new_lower_dentry)) {
err = PTR_ERR(new_lower_dentry);
goto out;
}
old_lower_dentry = unionfs_lower_dentry_idx(dentry, old_bindex);
/* we conditionally dput this old_lower_dentry at end of function */
dget(old_lower_dentry);
/* For symlinks, we must read the link before we lock the directory. */
if (S_ISLNK(old_lower_dentry->d_inode->i_mode)) {
symbuf = kmalloc(PATH_MAX, GFP_KERNEL);
if (unlikely(!symbuf)) {
__clear(dentry, old_lower_dentry,
old_bstart, old_bend,
new_lower_dentry, new_bindex);
err = -ENOMEM;
goto out_free;
}
oldfs = get_fs();
set_fs(KERNEL_DS);
err = old_lower_dentry->d_inode->i_op->readlink(
old_lower_dentry,
(char __user *)symbuf,
PATH_MAX);
set_fs(oldfs);
if (err < 0) {
__clear(dentry, old_lower_dentry,
old_bstart, old_bend,
new_lower_dentry, new_bindex);
goto out_free;
}
symbuf[err] = '\0';
}
/* Now we lock the parent, and create the object in the new branch. */
new_lower_parent_dentry = lock_parent(new_lower_dentry);
/* create the new inode */
err = __copyup_ndentry(old_lower_dentry, new_lower_dentry,
new_lower_parent_dentry, symbuf);
if (err) {
__clear(dentry, old_lower_dentry,
old_bstart, old_bend,
new_lower_dentry, new_bindex);
goto out_unlock;
}
/* We actually copyup the file here. */
if (S_ISREG(old_lower_dentry->d_inode->i_mode))
err = __copyup_reg_data(dentry, new_lower_dentry, new_bindex,
old_lower_dentry, old_bindex,
copyup_file, len);
if (err)
goto out_unlink;
/* Set permissions. */
err = copyup_permissions(sb, old_lower_dentry, new_lower_dentry);
if (err)
goto out_unlink;
#ifdef CONFIG_UNION_FS_XATTR
/* Selinux uses extended attributes for permissions. */
err = copyup_xattrs(old_lower_dentry, new_lower_dentry);
if (err)
goto out_unlink;
#endif /* CONFIG_UNION_FS_XATTR */
/* do not allow files getting deleted to be re-interposed */
if (!d_deleted(dentry))
unionfs_reinterpose(dentry);
goto out_unlock;
out_unlink:
/*
* copyup failed, because we possibly ran out of space or
* quota, or something else happened so let's unlink; we don't
* really care about the return value of vfs_unlink
*/
vfs_unlink(new_lower_parent_dentry->d_inode, new_lower_dentry);
if (copyup_file) {
/* need to close the file */
fput(*copyup_file);
branchput(sb, new_bindex);
}
/*
* TODO: should we reset the error to something like -EIO?
*
* If we don't reset, the user may get some nonsensical errors, but
* on the other hand, if we reset to EIO, we guarantee that the user
* will get a "confusing" error message.
*/
out_unlock:
unlock_dir(new_lower_parent_dentry);
out_free:
/*
* If old_lower_dentry was not a file, then we need to dput it. If
* it was a file, then it was already dput indirectly by other
* functions we call above which operate on regular files.
*/
if (old_lower_dentry && old_lower_dentry->d_inode &&
!S_ISREG(old_lower_dentry->d_inode->i_mode))
dput(old_lower_dentry);
kfree(symbuf);
if (err) {
/*
* if directory creation succeeded, but inode copyup failed,
* then purge new dentries.
*/
if (dbstart(dentry) < old_bstart &&
ibstart(dentry->d_inode) > dbstart(dentry))
__clear(dentry, NULL, old_bstart, old_bend,
unionfs_lower_dentry(dentry), dbstart(dentry));
goto out;
}
if (!S_ISDIR(dentry->d_inode->i_mode)) {
unionfs_postcopyup_release(dentry);
if (!unionfs_lower_inode(dentry->d_inode)) {
/*
* If we got here, then we copied up to an
* unlinked-open file, whose name is .unionfsXXXXX.
*/
struct inode *inode = new_lower_dentry->d_inode;
atomic_inc(&inode->i_count);
unionfs_set_lower_inode_idx(dentry->d_inode,
ibstart(dentry->d_inode),
inode);
}
}
unionfs_postcopyup_setmnt(dentry);
/* sync inode times from copied-up inode to our inode */
unionfs_copy_attr_times(dentry->d_inode);
unionfs_check_inode(dir);
unionfs_check_dentry(dentry);
out:
return err;
}
void
drm_gem_object_release(struct drm_gem_object *obj)
{
fput(obj->filp);
}
struct super_block *autofs4_read_super(struct super_block *s, void *data,
int silent)
{
struct inode * root_inode;
struct dentry * root;
struct file * pipe;
int pipefd;
struct autofs_sb_info *sbi;
int minproto, maxproto;
sbi = (struct autofs_sb_info *) kmalloc(sizeof(*sbi), GFP_KERNEL);
if ( !sbi )
goto fail_unlock;
DPRINTK(("autofs: starting up, sbi = %p\n",sbi));
memset(sbi, 0, sizeof(*sbi));
s->u.generic_sbp = sbi;
sbi->magic = AUTOFS_SBI_MAGIC;
sbi->catatonic = 0;
sbi->exp_timeout = 0;
sbi->oz_pgrp = current->pgrp;
sbi->sb = s;
sbi->version = 0;
sbi->queues = NULL;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = AUTOFS_SUPER_MAGIC;
s->s_op = &autofs4_sops;
/*
* Get the root inode and dentry, but defer checking for errors.
*/
root_inode = autofs4_get_inode(s, autofs4_mkroot(sbi));
root_inode->i_op = &autofs4_root_inode_operations;
root_inode->i_fop = &autofs4_root_operations;
root = d_alloc_root(root_inode);
pipe = NULL;
if (!root)
goto fail_iput;
/* Can this call block? */
if (parse_options(data, &pipefd,
&root_inode->i_uid, &root_inode->i_gid,
&sbi->oz_pgrp,
&minproto, &maxproto)) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
/* Couldn't this be tested earlier? */
if (maxproto < AUTOFS_MIN_PROTO_VERSION ||
minproto > AUTOFS_MAX_PROTO_VERSION) {
printk("autofs: kernel does not match daemon version "
"daemon (%d, %d) kernel (%d, %d)\n",
minproto, maxproto,
AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
goto fail_dput;
}
sbi->version = maxproto > AUTOFS_MAX_PROTO_VERSION ? AUTOFS_MAX_PROTO_VERSION : maxproto;
DPRINTK(("autofs: pipe fd = %d, pgrp = %u\n", pipefd, sbi->oz_pgrp));
pipe = fget(pipefd);
if ( !pipe ) {
printk("autofs: could not open pipe file descriptor\n");
goto fail_dput;
}
if ( !pipe->f_op || !pipe->f_op->write )
goto fail_fput;
sbi->pipe = pipe;
/*
* Success! Install the root dentry now to indicate completion.
*/
s->s_root = root;
return s;
/*
* Failure ... clean up.
*/
fail_fput:
printk("autofs: pipe file descriptor does not contain proper ops\n");
/*
* fput() can block, so we clear the super block first.
*/
fput(pipe);
/* fall through */
fail_dput:
/*
* dput() can block, so we clear the super block first.
*/
dput(root);
goto fail_free;
fail_iput:
printk("autofs: get root dentry failed\n");
/*
* iput() can block, so we clear the super block first.
*/
iput(root_inode);
fail_free:
kfree(sbi);
fail_unlock:
return NULL;
}
static void put_clock_desc(struct posix_clock_desc *cd)
{
put_posix_clock(cd->clk);
fput(cd->fp);
}
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
struct vhost_ubuf_ref *ubufs, *oldubufs = NULL;
int r;
mutex_lock(&n->dev.mutex);
r = vhost_dev_check_owner(&n->dev);
if (r)
goto err;
if (index >= VHOST_NET_VQ_MAX) {
r = -ENOBUFS;
goto err;
}
vq = n->vqs + index;
mutex_lock(&vq->mutex);
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
goto err_vq;
}
sock = get_socket(fd);
if (IS_ERR(sock)) {
r = PTR_ERR(sock);
goto err_vq;
}
/* start polling new socket */
oldsock = vq->private_data;
if (sock != oldsock) {
ubufs = vhost_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock));
if (IS_ERR(ubufs)) {
r = PTR_ERR(ubufs);
goto err_ubufs;
}
oldubufs = vq->ubufs;
vq->ubufs = ubufs;
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, sock);
vhost_net_enable_vq(n, vq);
r = vhost_init_used(vq);
if (r)
goto err_vq;
}
mutex_unlock(&vq->mutex);
if (oldubufs) {
vhost_ubuf_put_and_wait(oldubufs);
mutex_lock(&vq->mutex);
vhost_zerocopy_signal_used(vq);
mutex_unlock(&vq->mutex);
}
if (oldsock) {
vhost_net_flush_vq(n, index);
fput(oldsock->file);
}
mutex_unlock(&n->dev.mutex);
return 0;
err_ubufs:
fput(sock->file);
err_vq:
mutex_unlock(&vq->mutex);
err:
mutex_unlock(&n->dev.mutex);
return r;
}
int isert_conn_alloc(struct iscsi_session *session,
struct iscsi_kern_conn_info *info,
struct iscsi_conn **new_conn,
struct iscsit_transport *t)
{
int res = 0;
struct isert_conn_dev *dev;
struct iscsi_conn *conn;
struct iscsi_cmnd *cmnd;
struct file *filp = fget(info->fd);
TRACE_ENTRY();
lockdep_assert_held(&session->target->target_mutex);
if (unlikely(!filp)) {
res = -EBADF;
goto out;
}
dev = filp->private_data;
cmnd = dev->login_rsp;
sBUG_ON(cmnd == NULL);
dev->login_rsp = NULL;
*new_conn = dev->conn;
res = isert_set_session_params(dev->conn, &session->sess_params,
&session->tgt_params);
if (!res)
set_bit(ISERT_CONN_PASSED, &dev->flags);
fput(filp);
conn = *new_conn;
if (unlikely(res))
goto cleanup_conn;
conn->transport = t;
res = iscsi_init_conn(session, info, conn);
if (unlikely(res))
goto cleanup_conn;
conn->rd_state = 1;
isert_del_timer(dev);
isert_dev_release(dev);
isert_set_priv(conn, NULL);
res = isert_login_rsp_tx(cmnd, true, false);
vunmap(dev->sg_virt);
dev->sg_virt = NULL;
if (unlikely(res))
goto cleanup_iscsi_conn;
#ifndef CONFIG_SCST_PROC
res = conn_sysfs_add(conn);
if (unlikely(res))
goto cleanup_iscsi_conn;
#endif
list_add_tail(&conn->conn_list_entry, &session->conn_list);
goto out;
cleanup_iscsi_conn:
conn->rd_state = 0;
if (conn->nop_in_interval > 0)
cancel_delayed_work_sync(&conn->nop_in_delayed_work);
cleanup_conn:
conn->session = NULL;
isert_close_connection(conn);
out:
TRACE_EXIT_RES(res);
return res;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT4_IOC_GETFLAGS:
ext4_get_inode_flags(ei);
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
handle_t *handle = NULL;
int err, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
unsigned int jflag;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write_file(filp);
if (err)
return err;
flags = ext4_mask_flags(inode->i_mode, flags);
err = -EPERM;
mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
goto flags_out;
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
jflag = flags & EXT4_JOURNAL_DATA_FL;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE))
goto flags_out;
}
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
if (oldflags & EXT4_EXTENTS_FL) {
/* We don't support clearning extent flags */
if (!(flags & EXT4_EXTENTS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (flags & EXT4_EXTENTS_FL) {
/* migrate the file */
migrate = 1;
flags &= ~EXT4_EXTENTS_FL;
}
if (flags & EXT4_EOFBLOCKS_FL) {
/* we don't support adding EOFBLOCKS flag */
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
if (!(mask & EXT4_FL_USER_MODIFIABLE))
continue;
if (mask & flags)
ext4_set_inode_flag(inode, i);
else
ext4_clear_inode_flag(inode, i);
}
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext4_journal_stop(handle);
if (err)
goto flags_out;
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
err = ext4_change_inode_journal_flag(inode, jflag);
if (err)
goto flags_out;
if (migrate)
err = ext4_ext_migrate(inode);
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
mutex_lock(&inode->i_mutex);
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = ext4_current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
mutex_unlock(&inode->i_mutex);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct file *donor_filp;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor_filp = fget(me.donor_fd);
if (!donor_filp)
return -EBADF;
if (!(donor_filp->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
return -EOPNOTSUPP;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor_filp, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fput(donor_filp);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input))) {
err = -EFAULT;
goto group_add_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_add_out;
err = ext4_group_add(sb, &input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_add_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
mutex_lock(&(inode->i_mutex));
err = ext4_ext_migrate(inode);
mutex_unlock(&(inode->i_mutex));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
struct super_block *sb = inode->i_sb;
int err = 0, err2 = 0;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not (yet) supported with bigalloc");
return -EOPNOTSUPP;
}
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_META_BG)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not (yet) supported with meta_bg");
return -EOPNOTSUPP;
}
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
if (n_blocks_count > MAX_32_NUM &&
!EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR,
"File system only supports 32-bit block numbers");
return -EOPNOTSUPP;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FIDTRIM:
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"FITRIM not supported with bigalloc");
return -EOPNOTSUPP;
}
if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range, flags);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
default:
return -ENOTTY;
}
}
static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
struct autofs_wait_queue *wq,
int type)
{
union {
struct autofs_packet_hdr hdr;
union autofs_packet_union v4_pkt;
union autofs_v5_packet_union v5_pkt;
} pkt;
struct file *pipe = NULL;
size_t pktsz;
DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
wq->wait_queue_token, wq->name.len, wq->name.name, type);
memset(&pkt,0,sizeof pkt); /* For security reasons */
pkt.hdr.proto_version = sbi->version;
pkt.hdr.type = type;
switch (type) {
/* Kernel protocol v4 missing and expire packets */
case autofs_ptype_missing:
{
struct autofs_packet_missing *mp = &pkt.v4_pkt.missing;
pktsz = sizeof(*mp);
mp->wait_queue_token = wq->wait_queue_token;
mp->len = wq->name.len;
memcpy(mp->name, wq->name.name, wq->name.len);
mp->name[wq->name.len] = '\0';
break;
}
case autofs_ptype_expire_multi:
{
struct autofs_packet_expire_multi *ep = &pkt.v4_pkt.expire_multi;
pktsz = sizeof(*ep);
ep->wait_queue_token = wq->wait_queue_token;
ep->len = wq->name.len;
memcpy(ep->name, wq->name.name, wq->name.len);
ep->name[wq->name.len] = '\0';
break;
}
/*
* Kernel protocol v5 packet for handling indirect and direct
* mount missing and expire requests
*/
case autofs_ptype_missing_indirect:
case autofs_ptype_expire_indirect:
case autofs_ptype_missing_direct:
case autofs_ptype_expire_direct:
{
struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet;
pktsz = sizeof(*packet);
packet->wait_queue_token = wq->wait_queue_token;
packet->len = wq->name.len;
memcpy(packet->name, wq->name.name, wq->name.len);
packet->name[wq->name.len] = '\0';
packet->dev = wq->dev;
packet->ino = wq->ino;
packet->uid = wq->uid;
packet->gid = wq->gid;
packet->pid = wq->pid;
packet->tgid = wq->tgid;
break;
}
default:
printk(KERN_INFO "autofs4_notify_daemon: bad type %d!\n", type);
return;
}
/* Check if we have become catatonic */
mutex_lock(&sbi->wq_mutex);
if (!sbi->catatonic) {
pipe = sbi->pipe;
get_file(pipe);
}
mutex_unlock(&sbi->wq_mutex);
if (pipe) {
if (autofs4_write(pipe, &pkt, pktsz))
autofs4_catatonic_mode(sbi);
fput(pipe);
}
}
int autofs4_fill_super(struct super_block *s, void *data, int silent)
{
struct inode * root_inode;
struct dentry * root;
struct file * pipe;
int pipefd;
struct autofs_sb_info *sbi;
struct autofs_info *ino;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
goto fail_unlock;
DPRINTK("starting up, sbi = %p",sbi);
s->s_fs_info = sbi;
sbi->magic = AUTOFS_SBI_MAGIC;
sbi->pipefd = -1;
sbi->pipe = NULL;
sbi->catatonic = 1;
sbi->exp_timeout = 0;
sbi->oz_pgrp = task_pgrp_nr(current);
sbi->sb = s;
sbi->version = 0;
sbi->sub_version = 0;
set_autofs_type_indirect(&sbi->type);
sbi->min_proto = 0;
sbi->max_proto = 0;
mutex_init(&sbi->wq_mutex);
spin_lock_init(&sbi->fs_lock);
sbi->queues = NULL;
spin_lock_init(&sbi->lookup_lock);
INIT_LIST_HEAD(&sbi->active_list);
INIT_LIST_HEAD(&sbi->expiring_list);
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = AUTOFS_SUPER_MAGIC;
s->s_op = &autofs4_sops;
s->s_d_op = &autofs4_dentry_operations;
s->s_time_gran = 1;
/*
* Get the root inode and dentry, but defer checking for errors.
*/
ino = autofs4_mkroot(sbi);
if (!ino)
goto fail_free;
root_inode = autofs4_get_inode(s, ino);
if (!root_inode)
goto fail_ino;
root = d_alloc_root(root_inode);
if (!root)
goto fail_iput;
pipe = NULL;
root->d_fsdata = ino;
/* Can this call block? */
if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid,
&sbi->oz_pgrp, &sbi->type, &sbi->min_proto,
&sbi->max_proto)) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
if (autofs_type_trigger(sbi->type))
__managed_dentry_set_managed(root);
root_inode->i_fop = &autofs4_root_operations;
root_inode->i_op = &autofs4_dir_inode_operations;
/* Couldn't this be tested earlier? */
if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION ||
sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) {
printk("autofs: kernel does not match daemon version "
"daemon (%d, %d) kernel (%d, %d)\n",
sbi->min_proto, sbi->max_proto,
AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION);
goto fail_dput;
}
/* Establish highest kernel protocol version */
if (sbi->max_proto > AUTOFS_MAX_PROTO_VERSION)
sbi->version = AUTOFS_MAX_PROTO_VERSION;
else
sbi->version = sbi->max_proto;
sbi->sub_version = AUTOFS_PROTO_SUBVERSION;
DPRINTK("pipe fd = %d, pgrp = %u", pipefd, sbi->oz_pgrp);
pipe = fget(pipefd);
if (!pipe) {
printk("autofs: could not open pipe file descriptor\n");
goto fail_dput;
}
if (!pipe->f_op || !pipe->f_op->write)
goto fail_fput;
sbi->pipe = pipe;
sbi->pipefd = pipefd;
sbi->catatonic = 0;
/*
* Success! Install the root dentry now to indicate completion.
*/
s->s_root = root;
return 0;
/*
* Failure ... clean up.
*/
fail_fput:
printk("autofs: pipe file descriptor does not contain proper ops\n");
fput(pipe);
/* fall through */
fail_dput:
dput(root);
goto fail_free;
fail_iput:
printk("autofs: get root dentry failed\n");
iput(root_inode);
fail_ino:
kfree(ino);
fail_free:
kfree(sbi);
s->s_fs_info = NULL;
fail_unlock:
return -EINVAL;
}
static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct bnep_connlist_req cl;
struct bnep_connadd_req ca;
struct bnep_conndel_req cd;
struct bnep_conninfo ci;
struct socket *nsock;
void __user *argp = (void __user *)arg;
int err;
BT_DBG("cmd %x arg %lx", cmd, arg);
switch (cmd) {
case BNEPCONNADD:
if (!capable(CAP_NET_ADMIN))
return -EACCES;
if (copy_from_user(&ca, argp, sizeof(ca)))
return -EFAULT;
nsock = sockfd_lookup(ca.sock, &err);
if (!nsock)
return err;
if (nsock->sk->sk_state != BT_CONNECTED) {
fput(nsock->file);
return -EBADFD;
}
err = bnep_add_connection(&ca, nsock);
if (!err) {
if (copy_to_user(argp, &ca, sizeof(ca)))
err = -EFAULT;
} else
fput(nsock->file);
return err;
case BNEPCONNDEL:
if (!capable(CAP_NET_ADMIN))
return -EACCES;
if (copy_from_user(&cd, argp, sizeof(cd)))
return -EFAULT;
return bnep_del_connection(&cd);
case BNEPGETCONNLIST:
if (copy_from_user(&cl, argp, sizeof(cl)))
return -EFAULT;
if (cl.cnum <= 0)
return -EINVAL;
err = bnep_get_connlist(&cl);
if (!err && copy_to_user(argp, &cl, sizeof(cl)))
return -EFAULT;
return err;
case BNEPGETCONNINFO:
if (copy_from_user(&ci, argp, sizeof(ci)))
return -EFAULT;
err = bnep_get_conninfo(&ci);
if (!err && copy_to_user(argp, &ci, sizeof(ci)))
return -EFAULT;
return err;
default:
return -EINVAL;
}
return 0;
}
/*
* xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
* a file or fs handle.
*
* XFS_IOC_PATH_TO_FSHANDLE
* returns fs handle for a mount point or path within that mount point
* XFS_IOC_FD_TO_HANDLE
* returns full handle for a FD opened in user space
* XFS_IOC_PATH_TO_HANDLE
* returns full handle for a path
*/
int
xfs_find_handle(
unsigned int cmd,
xfs_fsop_handlereq_t *hreq)
{
int hsize;
xfs_handle_t handle;
struct inode *inode;
struct file *file = NULL;
struct path path;
int error;
struct xfs_inode *ip;
if (cmd == XFS_IOC_FD_TO_HANDLE) {
file = fget(hreq->fd);
if (!file)
return -EBADF;
inode = file->f_path.dentry->d_inode;
} else {
error = user_lpath((const char __user *)hreq->path, &path);
if (error)
return error;
inode = path.dentry->d_inode;
}
ip = XFS_I(inode);
/*
* We can only generate handles for inodes residing on a XFS filesystem,
* and only for regular files, directories or symbolic links.
*/
error = -EINVAL;
if (inode->i_sb->s_magic != XFS_SB_MAGIC)
goto out_put;
error = -EBADF;
if (!S_ISREG(inode->i_mode) &&
!S_ISDIR(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
goto out_put;
memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t));
if (cmd == XFS_IOC_PATH_TO_FSHANDLE) {
/*
* This handle only contains an fsid, zero the rest.
*/
memset(&handle.ha_fid, 0, sizeof(handle.ha_fid));
hsize = sizeof(xfs_fsid_t);
} else {
int lock_mode;
lock_mode = xfs_ilock_map_shared(ip);
handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
sizeof(handle.ha_fid.fid_len);
handle.ha_fid.fid_pad = 0;
handle.ha_fid.fid_gen = ip->i_d.di_gen;
handle.ha_fid.fid_ino = ip->i_ino;
xfs_iunlock_map_shared(ip, lock_mode);
hsize = XFS_HSIZE(handle);
}
error = -EFAULT;
if (copy_to_user(hreq->ohandle, &handle, hsize) ||
copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32)))
goto out_put;
error = 0;
out_put:
if (cmd == XFS_IOC_FD_TO_HANDLE)
fput(file);
else
path_put(&path);
return error;
}
/*
* MS_SYNC syncs the entire file - including mappings.
*
* MS_ASYNC does not start I/O (it used to, up to 2.5.67).
* Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
* Now it doesn't do anything, since dirty pages are properly tracked.
*
* The application may now run fsync() to
* write out the dirty pages and wait on the writeout and check the result.
* Or the application may run fadvise(FADV_DONTNEED) against the fd to start
* async writeout immediately.
* So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
* applications.
*/
SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
{
unsigned long end;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int unmapped_error = 0;
int error = -EINVAL;
if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
goto out;
if (start & ~PAGE_MASK)
goto out;
if ((flags & MS_ASYNC) && (flags & MS_SYNC))
goto out;
error = -ENOMEM;
len = (len + ~PAGE_MASK) & PAGE_MASK;
end = start + len;
if (end < start)
goto out;
error = 0;
if (end == start)
goto out;
/*
* If the interval [start,end) covers some unmapped address ranges,
* just ignore them, but return -ENOMEM at the end.
*/
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
for (;;) {
struct file *file;
/* Still start < end. */
error = -ENOMEM;
if (!vma)
goto out_unlock;
/* Here start < vma->vm_end. */
if (start < vma->vm_start) {
start = vma->vm_start;
if (start >= end)
goto out_unlock;
unmapped_error = -ENOMEM;
}
/* Here vma->vm_start <= start < vma->vm_end. */
if ((flags & MS_INVALIDATE) &&
(vma->vm_flags & VM_LOCKED)) {
error = -EBUSY;
goto out_unlock;
}
file = vma->vm_file;
start = vma->vm_end;
if ((flags & MS_SYNC) && file &&
(vma->vm_flags & VM_SHARED)) {
get_file(file);
up_read(&mm->mmap_sem);
error = vfs_fsync(file, 0);
fput(file);
if (error || start >= end)
goto out;
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
} else {
if (start >= end) {
error = 0;
goto out_unlock;
}
vma = vma->vm_next;
}
}
out_unlock:
up_read(&mm->mmap_sem);
out:
return error ? : unmapped_error;
}
static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
struct file *f,
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
static const struct file_operations empty_fops = {};
struct inode *inode;
int error;
f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
if (unlikely(f->f_flags & O_PATH))
f->f_mode = FMODE_PATH;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = __get_file_write_access(inode, mnt);
if (error)
goto cleanup_file;
if (!special_file(inode->i_mode))
file_take_write(f);
}
f->f_mapping = inode->i_mapping;
f->f_path.dentry = dentry;
f->f_path.mnt = mnt;
f->f_pos = 0;
file_sb_list_add(f, inode->i_sb);
if (unlikely(f->f_mode & FMODE_PATH)) {
f->f_op = &empty_fops;
return f;
}
f->f_op = fops_get(inode->i_fop);
error = security_dentry_open(f, cred);
if (error)
goto cleanup_all;
error = break_lease(inode, f->f_flags);
if (error)
goto cleanup_all;
if (!open && f->f_op)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(inode);
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
/* NB: we're sure to have correct a_ops only after f_op->open */
if (f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops ||
((!f->f_mapping->a_ops->direct_IO) &&
(!f->f_mapping->a_ops->get_xip_mem))) {
fput(f);
f = ERR_PTR(-EINVAL);
}
}
return f;
cleanup_all:
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITE) {
put_write_access(inode);
if (!special_file(inode->i_mode)) {
/*
* We don't consider this a real
* mnt_want/drop_write() pair
* because it all happenend right
* here, so just reset the state.
*/
file_reset_write(f);
mnt_drop_write(mnt);
}
}
file_sb_list_del(f);
f->f_path.dentry = NULL;
f->f_path.mnt = NULL;
cleanup_file:
put_filp(f);
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
static int __copyup_reg_data(struct dentry *dentry,
struct dentry *new_lower_dentry, int new_bindex,
struct dentry *old_lower_dentry, int old_bindex,
struct file **copyup_file, loff_t len)
{
struct super_block *sb = dentry->d_sb;
struct file *input_file;
struct file *output_file;
struct vfsmount *output_mnt;
mm_segment_t old_fs;
char *buf = NULL;
ssize_t read_bytes, write_bytes;
loff_t size;
int err = 0;
/* open old file */
unionfs_mntget(dentry, old_bindex);
branchget(sb, old_bindex);
/* dentry_open calls dput and mntput if it returns an error */
input_file = dentry_open(old_lower_dentry,
unionfs_lower_mnt_idx(dentry, old_bindex),
O_RDONLY | O_LARGEFILE, current_cred());
if (IS_ERR(input_file)) {
dput(old_lower_dentry);
err = PTR_ERR(input_file);
goto out;
}
if (unlikely(!input_file->f_op || !input_file->f_op->read)) {
err = -EINVAL;
goto out_close_in;
}
/* open new file */
dget(new_lower_dentry);
output_mnt = unionfs_mntget(sb->s_root, new_bindex);
branchget(sb, new_bindex);
output_file = dentry_open(new_lower_dentry, output_mnt,
O_RDWR | O_LARGEFILE, current_cred());
if (IS_ERR(output_file)) {
err = PTR_ERR(output_file);
goto out_close_in2;
}
if (unlikely(!output_file->f_op || !output_file->f_op->write)) {
err = -EINVAL;
goto out_close_out;
}
/* allocating a buffer */
buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (unlikely(!buf)) {
err = -ENOMEM;
goto out_close_out;
}
input_file->f_pos = 0;
output_file->f_pos = 0;
old_fs = get_fs();
set_fs(KERNEL_DS);
size = len;
err = 0;
do {
if (len >= PAGE_SIZE)
size = PAGE_SIZE;
else if ((len < PAGE_SIZE) && (len > 0))
size = len;
len -= PAGE_SIZE;
read_bytes =
input_file->f_op->read(input_file,
(char __user *)buf, size,
&input_file->f_pos);
if (read_bytes <= 0) {
err = read_bytes;
break;
}
/* see Documentation/filesystems/unionfs/issues.txt */
lockdep_off();
write_bytes =
output_file->f_op->write(output_file,
(char __user *)buf,
read_bytes,
&output_file->f_pos);
lockdep_on();
if ((write_bytes < 0) || (write_bytes < read_bytes)) {
err = write_bytes;
break;
}
} while ((read_bytes > 0) && (len > 0));
set_fs(old_fs);
kfree(buf);
if (!err)
err = output_file->f_op->fsync(output_file,
new_lower_dentry, 0);
if (err)
goto out_close_out;
if (copyup_file) {
*copyup_file = output_file;
goto out_close_in;
}
out_close_out:
fput(output_file);
out_close_in2:
branchput(sb, new_bindex);
out_close_in:
fput(input_file);
out:
branchput(sb, old_bindex);
return err;
}
int do_select(int n, fd_set_bits *fds, long *timeout)
{
poll_table table, *wait;
int retval, i, off;
long __timeout = *timeout;
read_lock(¤t->files->file_lock);
retval = max_select_fd(n, fds);
read_unlock(¤t->files->file_lock);
if (retval < 0)
return retval;
n = retval;
poll_initwait(&table);
wait = &table;
if (!__timeout)
wait = NULL;
retval = 0;
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
for (i = 0 ; i < n; i++) {
unsigned long bit = BIT(i);
unsigned long mask;
struct file *file;
off = i / __NFDBITS;
if (!(bit & BITS(fds, off)))
continue;
file = fget(i);
mask = POLLNVAL;
if (file) {
mask = DEFAULT_POLLMASK;
if (file->f_op && file->f_op->poll)
mask = file->f_op->poll(file, wait);
fput(file);
}
if ((mask & POLLIN_SET) && ISSET(bit, __IN(fds,off))) {
SET(bit, __RES_IN(fds,off));
retval++;
wait = NULL;
}
if ((mask & POLLOUT_SET) && ISSET(bit, __OUT(fds,off))) {
SET(bit, __RES_OUT(fds,off));
retval++;
wait = NULL;
}
if ((mask & POLLEX_SET) && ISSET(bit, __EX(fds,off))) {
SET(bit, __RES_EX(fds,off));
retval++;
wait = NULL;
}
}
wait = NULL;
if (retval || !__timeout || signal_pending(current))
break;
if(table.error) {
retval = table.error;
break;
}
__timeout = schedule_timeout(__timeout);
}
current->state = TASK_RUNNING;
poll_freewait(&table);
/*
* Up-to-date the caller timeout.
*/
*timeout = __timeout;
return retval;
}
/* 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, char __user *filename, struct timespec *times, int flags)
{
int error;
struct nameidata nd;
struct dentry *dentry;
struct inode *inode;
struct iattr newattrs;
struct file *f = NULL;
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) {
error = -EINVAL;
if (flags & AT_SYMLINK_NOFOLLOW)
goto out;
error = -EBADF;
f = fget(dfd);
if (!f)
goto out;
dentry = f->f_path.dentry;
} else {
error = __user_walk_fd(dfd, filename, (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW, &nd);
if (error)
goto out;
dentry = nd.dentry;
}
inode = dentry->d_inode;
error = -EROFS;
if (IS_RDONLY(inode))
goto dput_and_out;
/* Don't worry, the checks are done in inode_change_ok() */
newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
if (times) {
error = -EPERM;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
goto dput_and_out;
if (times[0].tv_nsec == UTIME_OMIT)
newattrs.ia_valid &= ~ATTR_ATIME;
else if (times[0].tv_nsec != UTIME_NOW) {
newattrs.ia_atime.tv_sec = times[0].tv_sec;
newattrs.ia_atime.tv_nsec = times[0].tv_nsec;
newattrs.ia_valid |= ATTR_ATIME_SET;
}
if (times[1].tv_nsec == UTIME_OMIT)
newattrs.ia_valid &= ~ATTR_MTIME;
else if (times[1].tv_nsec != UTIME_NOW) {
newattrs.ia_mtime.tv_sec = times[1].tv_sec;
newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
newattrs.ia_valid |= ATTR_MTIME_SET;
}
} else {
error = -EACCES;
if (IS_IMMUTABLE(inode))
goto dput_and_out;
if (!is_owner_or_cap(inode)) {
if (f) {
if (!(f->f_mode & FMODE_WRITE))
goto dput_and_out;
} else {
error = vfs_permission(&nd, MAY_WRITE);
if (error)
goto dput_and_out;
}
}
}
mutex_lock(&inode->i_mutex);
error = notify_change(dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
dput_and_out:
if (f)
fput(f);
else
path_release(&nd);
out:
return error;
}