Linux namespaces can be created and entered individually, but userspace orchestrators lack a single kernel object that binds a namespace set, a root mount, and an init process behind a pollable file descriptor. Add struct rootns, its lifecycle states, reference counting, uAPI creation flags, and anonymous inode file operations under CONFIG_ROOTNS. Drop active and passive namespace references on final release, send SIGKILL to the rootns init thread group on close when ROOTNS_KILL_ON_CLOSE is set, and report EPOLLHUP from poll() once the rootns reaches ROOTNS_DEAD. Co-developed-by: David Howells Signed-off-by: David Howells Signed-off-by: Jarkko Sakkinen --- include/linux/nsproxy.h | 3 + include/linux/rootns.h | 66 ++++++++++++++++++++++ include/uapi/linux/rootns.h | 38 +++++++++++++ init/Kconfig | 9 +++ kernel/Makefile | 2 + kernel/rootns.c | 107 ++++++++++++++++++++++++++++++++++++ 6 files changed, 225 insertions(+) create mode 100644 include/linux/rootns.h create mode 100644 include/uapi/linux/rootns.h create mode 100644 kernel/rootns.c diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index cacbbbe3f1ce..23cbeee6b1e4 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -91,6 +91,9 @@ static inline struct cred *nsset_cred(struct nsset *set) * * / * task_unlock(task); * + * 4. Root namespace membership is carried by nsproxy and inherited by + * namespaces derived from it. + * */ struct nsproxy *create_new_namespaces(u64 flags, diff --git a/include/linux/rootns.h b/include/linux/rootns.h new file mode 100644 index 000000000000..8464c90863ac --- /dev/null +++ b/include/linux/rootns.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2017-2019 Red Hat, Inc. All Rights Reserved. + */ + +#ifndef _LINUX_ROOTNS_H +#define _LINUX_ROOTNS_H + +#include +#include +#include +#include +#include + +struct cred; +struct file; +struct nsproxy; +struct pid; +struct task_struct; + +enum rootns_state { + ROOTNS_EMPTY = 0, + ROOTNS_READY = 1, + ROOTNS_FORKING = 2, + ROOTNS_RUNNING = 3, + ROOTNS_DEAD = 4, +}; + +/* + * The rootns object. + */ +struct rootns { + refcount_t usage; + int exit_code; /* The exit code of 'init' */ + struct rusage rusage; /* Resource usage of 'init' */ + const struct cred *cred; /* Creds for this rootns, including userns */ + struct nsproxy *ns; /* This rootns's namespaces */ + struct path root; /* The root of the rootns's fs namespace */ + struct pid *init_pid; /* The 'init' task's TGID (pid ref) */ + spinlock_t lock; /* Guards rootns lifecycle state */ + wait_queue_head_t waitq; /* Someone waiting for init to exit waits here */ + unsigned int flags; /* Validated rootns_create() flags */ + enum rootns_state state; /* Root namespace lifecycle state */ +}; + +#ifdef CONFIG_ROOTNS +struct rootns *get_rootns(struct rootns *c); +void put_rootns(struct rootns *c); +bool is_rootns_file(struct file *file); +#else +static inline struct rootns *get_rootns(struct rootns *c) +{ + return NULL; +} + +static inline void put_rootns(struct rootns *c) +{ +} + +static inline bool is_rootns_file(struct file *file) +{ + return false; +} +#endif /* CONFIG_ROOTNS */ + +#endif /* _LINUX_ROOTNS_H */ diff --git a/include/uapi/linux/rootns.h b/include/uapi/linux/rootns.h new file mode 100644 index 000000000000..bde89d183578 --- /dev/null +++ b/include/uapi/linux/rootns.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2017-2019 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2026 Opinsys Oy + */ + +#ifndef _UAPI_LINUX_ROOTNS_H +#define _UAPI_LINUX_ROOTNS_H + +/** + * enum rootns_flags - Flags for rootns_create() + * @ROOTNS_CGROUP: Create a fresh cgroup namespace instead of inheriting. + * @ROOTNS_UTS: Create a fresh UTS namespace instead of inheriting. + * @ROOTNS_IPC: Create a fresh IPC namespace instead of inheriting. + * @ROOTNS_USER: Create a fresh user namespace owned by the caller. + * @ROOTNS_NET: Create a fresh network namespace instead of inheriting. + * @ROOTNS_KILL_ON_CLOSE: Send %SIGKILL to rootns init on final fd release. + * @ROOTNS_CLOSE_ON_EXEC: Set %O_CLOEXEC on the returned control fd. + * @ROOTNS_ALL_NAMESPACES: Mask of all optional namespace selection flags. + * @ROOTNS_ALL_FLAGS: Mask of all valid flags accepted by rootns_create(). + * + * Every root namespace unconditionally owns dedicated mount and PID + * namespaces. Optional namespace flags allocate fresh instances of the + * remaining namespaces instead of inheriting them from the caller. + */ +enum rootns_flags { + ROOTNS_CGROUP = 0x00000001, + ROOTNS_UTS = 0x00000002, + ROOTNS_IPC = 0x00000004, + ROOTNS_USER = 0x00000008, + ROOTNS_NET = 0x00000010, + ROOTNS_KILL_ON_CLOSE = 0x00000100, + ROOTNS_CLOSE_ON_EXEC = 0x00000200, + ROOTNS_ALL_NAMESPACES = 0x0000001f, + ROOTNS_ALL_FLAGS = 0x0000031f, +}; + +#endif /* _UAPI_LINUX_ROOTNS_H */ diff --git a/init/Kconfig b/init/Kconfig index 4013781e0a02..f1f3a6d1755c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1280,6 +1280,15 @@ config NET_NS Allow user space to create what appear to be multiple instances of the network stack. +config ROOTNS + bool "Root namespace" + depends on USER_NS && PID_NS && UTS_NS && IPC_NS && NET_NS && CGROUPS + help + Allow user space to create and manage isolated root namespaces + with their own mount tree, credentials, namespace set, and init + process lifecycle via the rootns_create(), rootns_enter(), + rootns_wait(), and rootns_kill() system calls. + endif # NAMESPACES config CHECKPOINT_RESTORE diff --git a/kernel/Makefile b/kernel/Makefile index 4ff92e24680c..7074d2664ce7 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -152,6 +152,8 @@ KCOV_INSTRUMENT_kstack_erase.o := n obj-$(CONFIG_SCF_TORTURE_TEST) += scftorture.o +obj-$(CONFIG_ROOTNS) += rootns.o + $(obj)/configs.o: $(obj)/config_data.gz # .config is small, so it is compressed with gzip rather than the image compressor. diff --git a/kernel/rootns.c b/kernel/rootns.c new file mode 100644 index 000000000000..e75d918b93ec --- /dev/null +++ b/kernel/rootns.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017-2019 Red Hat, Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Get a reference to a rootns. + */ +struct rootns *get_rootns(struct rootns *c) +{ + refcount_inc(&c->usage); + return c; +} + +/* + * Drop a reference on a rootns and clear it if it is no longer in use. + */ +void put_rootns(struct rootns *c) +{ + if (!c || !refcount_dec_and_test(&c->usage)) + return; + + if (c->ns) + put_nsproxy(c->ns); + path_put(&c->root); + + if (c->init_pid) + put_pid(c->init_pid); + if (c->cred) { + ns_ref_active_put(c->cred->user_ns); + put_cred(c->cred); + } + kfree(c); +} + +/* + * Allow the user to poll for the rootns dying. + */ +static __poll_t rootns_poll(struct file *file, poll_table *wait) +{ + struct rootns *rootns = file->private_data; + __poll_t mask = 0; + + poll_wait(file, &rootns->waitq, wait); + + if (READ_ONCE(rootns->state) == ROOTNS_DEAD) + mask |= EPOLLHUP; + + return mask; +} + +static int __rootns_kill(struct rootns *rootns, int sig, bool priv) +{ + struct pid *pid = NULL; + int ret; + + scoped_guard(spinlock, &rootns->lock) { + if (rootns->state == ROOTNS_RUNNING) + pid = get_pid(rootns->init_pid); + } + if (!pid) + return -ESRCH; + + ret = kill_pid(pid, sig, priv); + put_pid(pid); + return ret; +} + +static int rootns_release(struct inode *inode, struct file *file) +{ + struct rootns *rootns = file->private_data; + + if (rootns->flags & ROOTNS_KILL_ON_CLOSE) + __rootns_kill(rootns, SIGKILL, true); + put_rootns(rootns); + return 0; +} + +static const struct file_operations rootns_fops = { + .poll = rootns_poll, + .release = rootns_release, +}; + +/* + * Returns true if the file is a rootns. + */ +bool is_rootns_file(struct file *file) +{ + return file->f_op == &rootns_fops; +} -- 2.47.3