/*
* Create new nsproxy and all of its the associated namespaces.
* Return the newly created nsproxy. Do not attach this to the task,
* leave it to the caller to do proper locking and attach it to task.
*/
static struct nsproxy *create_new_namespaces(unsigned long flags,
struct task_struct *tsk, struct user_namespace *user_ns,
struct fs_struct *new_fs)
{
struct nsproxy *new_nsp;
int err;
new_nsp = create_nsproxy();
if (!new_nsp)
return ERR_PTR(-ENOMEM);
new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
if (IS_ERR(new_nsp->mnt_ns)) {
err = PTR_ERR(new_nsp->mnt_ns);
goto out_ns;
}
new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
if (IS_ERR(new_nsp->uts_ns)) {
err = PTR_ERR(new_nsp->uts_ns);
goto out_uts;
}
new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
if (IS_ERR(new_nsp->ipc_ns)) {
err = PTR_ERR(new_nsp->ipc_ns);
goto out_ipc;
}
new_nsp->pid_ns_for_children =
copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
if (IS_ERR(new_nsp->pid_ns_for_children)) {
err = PTR_ERR(new_nsp->pid_ns_for_children);
goto out_pid;
}
new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
goto out_net;
}
return new_nsp;
out_net:
if (new_nsp->pid_ns_for_children)
put_pid_ns(new_nsp->pid_ns_for_children);
out_pid:
if (new_nsp->ipc_ns)
put_ipc_ns(new_nsp->ipc_ns);
out_ipc:
if (new_nsp->uts_ns)
put_uts_ns(new_nsp->uts_ns);
out_uts:
if (new_nsp->mnt_ns)
put_mnt_ns(new_nsp->mnt_ns);
out_ns:
kmem_cache_free(nsproxy_cachep, new_nsp);
return ERR_PTR(err);
}
/*
* Create new nsproxy and all of its the associated namespaces.
* Return the newly created nsproxy. Do not attach this to the task,
* leave it to the caller to do proper locking and attach it to task.
*/
static struct nsproxy *create_new_namespaces(unsigned long flags,
struct task_struct *tsk, struct fs_struct *new_fs)
{
struct nsproxy *new_nsp;
int err;
//创建一个新的命名空间,并把old赋值给新分配的，设置引用count值为1.
new_nsp = clone_nsproxy(tsk->nsproxy);
if (!new_nsp)
return ERR_PTR(-ENOMEM);
//查看flag的CLONE_NEWNS标记，看是否设置新的mnt
new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, new_fs);
if (IS_ERR(new_nsp->mnt_ns)) {
err = PTR_ERR(new_nsp->mnt_ns);
goto out_ns;
}
//查看flag的CLONE_NEWUTS标记，看是否设置新的uts
new_nsp->uts_ns = copy_utsname(flags, tsk->nsproxy->uts_ns);
if (IS_ERR(new_nsp->uts_ns)) {
err = PTR_ERR(new_nsp->uts_ns);
goto out_uts;
}
//查看flag的CLONE_NEWIPC标记，看是否设置新的ipc
new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns);
if (IS_ERR(new_nsp->ipc_ns)) {
err = PTR_ERR(new_nsp->ipc_ns);
goto out_ipc;
}
//查看flag的CLONE_NEWPID标记，看是否设置新的pid
new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk));
if (IS_ERR(new_nsp->pid_ns)) {
err = PTR_ERR(new_nsp->pid_ns);
goto out_pid;
}
//查看flag的CLONE_NEWNET标记，看是否设置新的net
new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
goto out_net;
}
return new_nsp;
out_net:
if (new_nsp->pid_ns)
put_pid_ns(new_nsp->pid_ns);
out_pid:
if (new_nsp->ipc_ns)
put_ipc_ns(new_nsp->ipc_ns);
out_ipc:
if (new_nsp->uts_ns)
put_uts_ns(new_nsp->uts_ns);
out_uts:
if (new_nsp->mnt_ns)
put_mnt_ns(new_nsp->mnt_ns);
out_ns:
kmem_cache_free(nsproxy_cachep, new_nsp);
return ERR_PTR(err);
}
void free_nsproxy(struct nsproxy *ns)
{
if (ns->mnt_ns)
put_mnt_ns(ns->mnt_ns);
if (ns->uts_ns)
put_uts_ns(ns->uts_ns);
if (ns->ipc_ns)
put_ipc_ns(ns->ipc_ns);
if (ns->pid_ns)
put_pid_ns(ns->pid_ns);
put_net(ns->net_ns);
kmem_cache_free(nsproxy_cachep, ns);
}
void free_nsproxy(struct nsproxy *ns)
{
if (ns->mnt_ns)
put_mnt_ns(ns->mnt_ns);
if (ns->uts_ns)
put_uts_ns(ns->uts_ns);
if (ns->ipc_ns)
put_ipc_ns(ns->ipc_ns);
if (ns->pid_ns_for_children)
put_pid_ns(ns->pid_ns_for_children);
put_cgroup_ns(ns->cgroup_ns);
put_net(ns->net_ns);
kmem_cache_free(nsproxy_cachep, ns);
}
static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt)
{
struct mount *r = real_mount(mnt);
int err = 0;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
struct super_block *sb = mnt_path.dentry->d_sb;
if (sb->s_op->show_devname) {
err = sb->s_op->show_devname(m, mnt_path.dentry);
if (err)
goto out;
} else {
mangle(m, r->mnt_devname ? r->mnt_devname : "none");
}
seq_putc(m, ' ');
seq_path(m, &mnt_path, " \t\n\\");
seq_putc(m, ' ');
show_type(m, sb);
seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
err = show_sb_opts(m, sb);
if (err)
goto out;
show_mnt_opts(m, mnt);
if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt_path.dentry);
seq_puts(m, " 0 0\n");
out:
return err;
}
static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
{
struct proc_mounts *p = proc_mounts(m);
struct mount *r = real_mount(mnt);
struct super_block *sb = mnt->mnt_sb;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
struct path root = p->root;
int err = 0;
seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id,
MAJOR(sb->s_dev), MINOR(sb->s_dev));
if (sb->s_op->show_path)
err = sb->s_op->show_path(m, mnt->mnt_root);
else
seq_dentry(m, mnt->mnt_root, " \t\n\\");
if (err)
goto out;
seq_putc(m, ' ');
/* mountpoints outside of chroot jail will give SEQ_SKIP on this */
err = seq_path_root(m, &mnt_path, &root, " \t\n\\");
if (err)
goto out;
seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
show_mnt_opts(m, mnt);
/* Tagged fields ("foo:X" or "bar") */
if (IS_MNT_SHARED(r))
seq_printf(m, " shared:%i", r->mnt_group_id);
if (IS_MNT_SLAVE(r)) {
int master = r->mnt_master->mnt_group_id;
int dom = get_dominating_id(r, &p->root);
seq_printf(m, " master:%i", master);
if (dom && dom != master)
seq_printf(m, " propagate_from:%i", dom);
}
if (IS_MNT_UNBINDABLE(r))
seq_puts(m, " unbindable");
/* Filesystem specific data */
seq_puts(m, " - ");
show_type(m, sb);
seq_putc(m, ' ');
if (sb->s_op->show_devname)
err = sb->s_op->show_devname(m, mnt->mnt_root);
else
mangle(m, r->mnt_devname ? r->mnt_devname : "none");
if (err)
goto out;
seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
err = show_sb_opts(m, sb);
if (err)
goto out;
if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt->mnt_root);
seq_putc(m, '\n');
out:
return err;
}
static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
{
struct mount *r = real_mount(mnt);
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
struct super_block *sb = mnt_path.dentry->d_sb;
int err = 0;
/* device */
if (sb->s_op->show_devname) {
seq_puts(m, "device ");
err = sb->s_op->show_devname(m, mnt_path.dentry);
} else {
if (r->mnt_devname) {
seq_puts(m, "device ");
mangle(m, r->mnt_devname);
} else
seq_puts(m, "no device");
}
/* mount point */
seq_puts(m, " mounted on ");
seq_path(m, &mnt_path, " \t\n\\");
seq_putc(m, ' ');
/* file system type */
seq_puts(m, "with fstype ");
show_type(m, sb);
/* optional statistics */
if (sb->s_op->show_stats) {
seq_putc(m, ' ');
if (!err)
err = sb->s_op->show_stats(m, mnt_path.dentry);
}
seq_putc(m, '\n');
return err;
}
static int mounts_open_common(struct inode *inode, struct file *file,
int (*show)(struct seq_file *, struct vfsmount *))
{
struct task_struct *task = get_proc_task(inode);
struct nsproxy *nsp;
struct mnt_namespace *ns = NULL;
struct path root;
struct proc_mounts *p;
int ret = -EINVAL;
if (!task)
goto err;
task_lock(task);
nsp = task->nsproxy;
if (!nsp || !nsp->mnt_ns) {
task_unlock(task);
put_task_struct(task);
goto err;
}
ns = nsp->mnt_ns;
get_mnt_ns(ns);
if (!task->fs) {
task_unlock(task);
put_task_struct(task);
ret = -ENOENT;
goto err_put_ns;
}
get_fs_root(task->fs, &root);
task_unlock(task);
put_task_struct(task);
ret = -ENOMEM;
p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL);
if (!p)
goto err_put_path;
file->private_data = &p->m;
ret = seq_open(file, &mounts_op);
if (ret)
goto err_free;
p->ns = ns;
p->root = root;
p->m.poll_event = ns->event;
p->show = show;
return 0;
err_free:
kfree(p);
err_put_path:
path_put(&root);
err_put_ns:
put_mnt_ns(ns);
err:
return ret;
}
static int mounts_release(struct inode *inode, struct file *file)
{
struct proc_mounts *p = proc_mounts(file->private_data);
path_put(&p->root);
put_mnt_ns(p->ns);
return seq_release(inode, file);
}
static int mounts_open(struct inode *inode, struct file *file)
{
return mounts_open_common(inode, file, show_vfsmnt);
}
static int mountinfo_open(struct inode *inode, struct file *file)
{
return mounts_open_common(inode, file, show_mountinfo);
}
static int mountstats_open(struct inode *inode, struct file *file)
{
return mounts_open_common(inode, file, show_vfsstat);
}
const struct file_operations proc_mounts_operations = {
.open = mounts_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
.poll = mounts_poll,
};
const struct file_operations proc_mountinfo_operations = {
.open = mountinfo_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
.poll = mounts_poll,
};
const struct file_operations proc_mountstats_operations = {
.open = mountstats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = mounts_release,
};
/*
* unshare allows a process to 'unshare' part of the process
* context which was originally shared using clone. copy_*
* functions used by do_fork() cannot be used here directly
* because they modify an inactive task_struct that is being
* constructed. Here we are modifying the current, active,
* task_struct.
*/
asmlinkage long sys_unshare(unsigned long unshare_flags)
{
int err = 0;
struct fs_struct *fs, *new_fs = NULL;
struct mnt_namespace *ns, *new_ns = NULL;
struct sighand_struct *new_sigh = NULL;
struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
struct files_struct *fd, *new_fd = NULL;
struct sem_undo_list *new_ulist = NULL;
struct nsproxy *new_nsproxy = NULL, *old_nsproxy = NULL;
struct uts_namespace *uts, *new_uts = NULL;
struct ipc_namespace *ipc, *new_ipc = NULL;
check_unshare_flags(&unshare_flags);
/* Return -EINVAL for all unsupported flags */
err = -EINVAL;
if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
CLONE_NEWUTS|CLONE_NEWIPC))
goto bad_unshare_out;
if ((err = unshare_thread(unshare_flags)))
goto bad_unshare_out;
if ((err = unshare_fs(unshare_flags, &new_fs)))
goto bad_unshare_cleanup_thread;
if ((err = unshare_mnt_namespace(unshare_flags, &new_ns, new_fs)))
goto bad_unshare_cleanup_fs;
if ((err = unshare_sighand(unshare_flags, &new_sigh)))
goto bad_unshare_cleanup_ns;
if ((err = unshare_vm(unshare_flags, &new_mm)))
goto bad_unshare_cleanup_sigh;
if ((err = unshare_fd(unshare_flags, &new_fd)))
goto bad_unshare_cleanup_vm;
if ((err = unshare_semundo(unshare_flags, &new_ulist)))
goto bad_unshare_cleanup_fd;
if ((err = unshare_utsname(unshare_flags, &new_uts)))
goto bad_unshare_cleanup_semundo;
if ((err = unshare_ipcs(unshare_flags, &new_ipc)))
goto bad_unshare_cleanup_uts;
if (new_ns || new_uts || new_ipc) {
old_nsproxy = current->nsproxy;
new_nsproxy = dup_namespaces(old_nsproxy);
if (!new_nsproxy) {
err = -ENOMEM;
goto bad_unshare_cleanup_ipc;
}
}
if (new_fs || new_ns || new_mm || new_fd || new_ulist ||
new_uts || new_ipc) {
task_lock(current);
if (new_nsproxy) {
current->nsproxy = new_nsproxy;
new_nsproxy = old_nsproxy;
}
if (new_fs) {
fs = current->fs;
current->fs = new_fs;
new_fs = fs;
}
if (new_ns) {
ns = current->nsproxy->mnt_ns;
current->nsproxy->mnt_ns = new_ns;
new_ns = ns;
}
if (new_mm) {
mm = current->mm;
active_mm = current->active_mm;
current->mm = new_mm;
current->active_mm = new_mm;
activate_mm(active_mm, new_mm);
new_mm = mm;
}
if (new_fd) {
fd = current->files;
current->files = new_fd;
new_fd = fd;
}
if (new_uts) {
uts = current->nsproxy->uts_ns;
current->nsproxy->uts_ns = new_uts;
new_uts = uts;
}
if (new_ipc) {
ipc = current->nsproxy->ipc_ns;
current->nsproxy->ipc_ns = new_ipc;
new_ipc = ipc;
}
task_unlock(current);
}
if (new_nsproxy)
put_nsproxy(new_nsproxy);
bad_unshare_cleanup_ipc:
if (new_ipc)
put_ipc_ns(new_ipc);
bad_unshare_cleanup_uts:
if (new_uts)
put_uts_ns(new_uts);
bad_unshare_cleanup_semundo:
bad_unshare_cleanup_fd:
if (new_fd)
put_files_struct(new_fd);
bad_unshare_cleanup_vm:
if (new_mm)
mmput(new_mm);
bad_unshare_cleanup_sigh:
if (new_sigh)
if (atomic_dec_and_test(&new_sigh->count))
kmem_cache_free(sighand_cachep, new_sigh);
bad_unshare_cleanup_ns:
if (new_ns)
put_mnt_ns(new_ns);
bad_unshare_cleanup_fs:
if (new_fs)
put_fs_struct(new_fs);
bad_unshare_cleanup_thread:
bad_unshare_out:
return err;
}
