Setting up an isolated namespace environment from a multithreaded manager process currently requires helper processes to call unshare() and pass file descriptors back over sockets. Add the rootns_create() system call to allocate a detached rootns instance owning a fresh user namespace alongside dedicated empty mount (CLONE_EMPTY_MNTNS), PID, UTS, IPC, network, cgroup, and time namespaces, and return its control file descriptor. Finalize the nsproxy time namespace and pin active references for the lifetime of the rootns. Co-developed-by: David Howells Signed-off-by: David Howells Signed-off-by: Jarkko Sakkinen --- include/linux/syscalls.h | 1 + include/linux/time_namespace.h | 13 ++++ kernel/rootns.c | 106 +++++++++++++++++++++++++++++++++ kernel/sys_ni.c | 3 + 4 files changed, 123 insertions(+) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 552d9710a0d5..272d54bddbe2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1006,6 +1006,7 @@ asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx __user * asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx __user *ctx, u32 size, u32 flags); asmlinkage long sys_lsm_list_modules(u64 __user *ids, u32 __user *size, u32 flags); +asmlinkage long sys_rootns_create(unsigned int flags); /* * Architecture-specific system calls diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index 58bd9728df58..bdc185543893 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -60,6 +60,15 @@ static inline void put_time_ns(struct time_namespace *ns) free_time_ns(ns); } +static inline void timens_activate_nsproxy(struct nsproxy *nsproxy) +{ + if (nsproxy->time_ns != nsproxy->time_ns_for_children) { + get_time_ns(nsproxy->time_ns_for_children); + put_time_ns(nsproxy->time_ns); + nsproxy->time_ns = nsproxy->time_ns_for_children; + } +} + void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); struct proc_timens_offset { @@ -125,6 +134,10 @@ static inline void put_time_ns(struct time_namespace *ns) { } +static inline void timens_activate_nsproxy(struct nsproxy *nsproxy) +{ +} + static inline struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, diff --git a/kernel/rootns.c b/kernel/rootns.c index 4f40dac4225f..c420e36af603 100644 --- a/kernel/rootns.c +++ b/kernel/rootns.c @@ -199,3 +199,109 @@ void exit_rootns(struct pid_namespace *pid_ns, struct task_struct *tsk) wake_up_poll(&c->waitq, EPOLLHUP); put_rootns(c); } + +static struct user_namespace *create_rootns_user_ns(void) +{ + struct user_namespace *user_ns; + struct cred *new; + int ret; + + new = prepare_creds(); + if (!new) + return ERR_PTR(-ENOMEM); + + ret = create_user_ns(new); + if (ret < 0) { + abort_creds(new); + return ERR_PTR(ret); + } + + user_ns = get_user_ns(new->user_ns); + abort_creds(new); + return user_ns; +} + +/* + * Create a new rootns. + */ +static struct rootns *create_rootns(unsigned int flags) +{ + u64 clone_flags = CLONE_NEWNS | CLONE_EMPTY_MNTNS | CLONE_NEWPID | + CLONE_NEWCGROUP | CLONE_NEWUTS | CLONE_NEWIPC | + CLONE_NEWNET | + (IS_ENABLED(CONFIG_TIME_NS) ? CLONE_NEWTIME : 0); + struct user_namespace *user_ns; + struct nsproxy *ns; + struct rootns *c; + int ret; + + c = kzalloc_obj(*c, GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + init_waitqueue_head(&c->waitq); + spin_lock_init(&c->lock); + refcount_set(&c->usage, 1); + c->flags = flags; + + user_ns = create_rootns_user_ns(); + if (IS_ERR(user_ns)) { + ret = PTR_ERR(user_ns); + goto err_put; + } + c->user_ns = user_ns; + ns_ref_active_get(user_ns); + + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) { + ret = -EPERM; + goto err_put; + } + + ns = create_new_namespaces(clone_flags, current->nsproxy, user_ns, + NULL); + if (IS_ERR(ns)) { + ret = PTR_ERR(ns); + goto err_put; + } + + timens_activate_nsproxy(ns); + c->ns = ns; + nsproxy_ns_active_get(ns); + + return c; + +err_put: + put_rootns(c); + return ERR_PTR(ret); +} + +/** + * sys_rootns_create - Create a detached root namespace + * @flags: Combination of &enum rootns_flags values + * + * Allocate a detached root namespace owning a fresh user namespace and + * dedicated empty mount, PID, UTS, IPC, network, cgroup, and time namespaces. + * + * Return: Control file descriptor on success, negative error code on failure. + */ +SYSCALL_DEFINE1(rootns_create, unsigned int, flags) +{ + struct rootns *c; + int fd; + + if (flags & ~ROOTNS_ALL_FLAGS) + return -EINVAL; + if (unlikely(!current->nsproxy)) + return -EOPNOTSUPP; + + c = create_rootns(flags); + if (IS_ERR(c)) + return PTR_ERR(c); + + fd = anon_inode_getfd("rootns", &rootns_fops, c, + O_RDWR | (flags & ROOTNS_CLOSE_ON_EXEC ? O_CLOEXEC : 0)); + if (fd < 0) + put_rootns(c); + + return fd; +} diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index c8be0abaa407..4a6c4337cc74 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -398,3 +398,6 @@ COND_SYSCALL(rseq_slice_yield); COND_SYSCALL(uretprobe); COND_SYSCALL(uprobe); + +/* kernel/rootns.c */ +COND_SYSCALL(rootns_create); -- 2.47.3