Standalone namespace operations such as userns_set_idmap() and move_mount(..., MOVE_MOUNT_T_MNTNS) operate on nsfs file descriptors, requiring a way to obtain member namespace fds from a userland file descriptor before any process has entered it. Add the USERLAND_GET_NSFD ioctl to open an O_CLOEXEC nsfs file descriptor for a requested member namespace when the caller holds CAP_SYS_ADMIN in the userland's user namespace, additionally requiring an ancestor active PID namespace and a running init process for CLONE_NEWPID. Signed-off-by: Jarkko Sakkinen --- fs/internal.h | 1 - include/linux/nsfs.h | 1 + include/uapi/linux/userland.h | 19 +++++++++ kernel/userland.c | 76 +++++++++++++++++++++++++++++++++++ 4 files changed, 96 insertions(+), 1 deletion(-) diff --git a/fs/internal.h b/fs/internal.h index 3f2fbac40f8e..ee3f796241ac 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -250,7 +250,6 @@ extern void mnt_pin_kill(struct mount *m); * fs/nsfs.c */ extern const struct dentry_operations ns_dentry_operations; -int open_namespace(struct ns_common *ns); struct file *open_namespace_file(struct ns_common *ns); /* diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h index 731b67fc2fec..40912c1eb5ff 100644 --- a/include/linux/nsfs.h +++ b/include/linux/nsfs.h @@ -23,6 +23,7 @@ bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops); void nsfs_init(void); +int open_namespace(struct ns_common *ns); #define __current_namespace_from_type(__ns) \ _Generic((__ns), \ diff --git a/include/uapi/linux/userland.h b/include/uapi/linux/userland.h index 4a9031f81dda..e81a06d6e9eb 100644 --- a/include/uapi/linux/userland.h +++ b/include/uapi/linux/userland.h @@ -7,6 +7,8 @@ #ifndef _UAPI_LINUX_USERLAND_H #define _UAPI_LINUX_USERLAND_H +#include + /** * enum userland_flags - Flags for userland_open() * @USERLAND_KILL_ON_CLOSE: Send %SIGKILL to userland init on final fd release. @@ -22,4 +24,21 @@ enum userland_flags { USERLAND_ALL_FLAGS = 0x00000003, }; +#define USERLAND_IOCTL_MAGIC 0xB9 + +/** + * DOC: USERLAND_GET_NSFD + * + * ``ioctl(userland_fd, USERLAND_GET_NSFD, nstype)`` opens an ``nsfs`` file + * descriptor (with ``O_CLOEXEC``) for the member namespace identified by + * ``nstype`` (one of ``CLONE_NEWNS``, ``CLONE_NEWCGROUP``, + * ``CLONE_NEWUTS``, ``CLONE_NEWIPC``, ``CLONE_NEWUSER``, ``CLONE_NEWPID``, + * ``CLONE_NEWNET``, or ``CLONE_NEWTIME``). + * + * Requires ``CAP_SYS_ADMIN`` in the userland's user namespace. + * Opening ``CLONE_NEWPID`` additionally requires running in an ancestor + * active PID namespace and that userland init is running. + */ +#define USERLAND_GET_NSFD _IO(USERLAND_IOCTL_MAGIC, 0x01) + #endif /* _UAPI_LINUX_USERLAND_H */ diff --git a/kernel/userland.c b/kernel/userland.c index 472d75423b95..fd5f67c0245e 100644 --- a/kernel/userland.c +++ b/kernel/userland.c @@ -23,6 +23,8 @@ #include #include #include +#include +#include #include #include #include @@ -31,6 +33,8 @@ #include #include #include +#include +#include #include #include @@ -63,6 +67,76 @@ static __poll_t userland_poll(struct file *file, poll_table *wait) return mask; } +static long userland_get_nsfd(struct userland *userland, unsigned long nstype) +{ + struct ns_common *ns = NULL; + + if (nstype > UINT_MAX) + return -EINVAL; + if (!ns_capable(userland->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + if (nstype == CLONE_NEWPID) { + if (!pidns_is_ancestor(userland->ns->pid_ns_for_children, + task_active_pid_ns(current))) + return -EXDEV; + if (READ_ONCE(userland->state) != USERLAND_RUNNING) + return -ESRCH; + } + + scoped_guard(spinlock, &userland->lock) { + switch (nstype) { + case CLONE_NEWNS: + ns = from_mnt_ns(userland->ns->mnt_ns); + break; + case CLONE_NEWCGROUP: + ns = to_ns_common(userland->ns->cgroup_ns); + break; + case CLONE_NEWUTS: + ns = to_ns_common(userland->ns->uts_ns); + break; + case CLONE_NEWIPC: + ns = to_ns_common(userland->ns->ipc_ns); + break; + case CLONE_NEWUSER: + ns = to_ns_common(userland->user_ns); + break; + case CLONE_NEWPID: + ns = to_ns_common(userland->ns->pid_ns_for_children); + break; + case CLONE_NEWNET: + ns = to_ns_common(userland->ns->net_ns); + break; + case CLONE_NEWTIME: +#ifdef CONFIG_TIME_NS + ns = to_ns_common(userland->ns->time_ns); + break; +#else + return -EOPNOTSUPP; +#endif + default: + return -EINVAL; + } + + if (!__ns_ref_get(ns)) + return -ESRCH; + } + + return open_namespace(ns); +} + +static long userland_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct userland *userland = file->private_data; + + switch (cmd) { + case USERLAND_GET_NSFD: + return userland_get_nsfd(userland, arg); + default: + return -ENOIOCTLCMD; + } +} + static int userland_release(struct inode *inode, struct file *file) { struct userland *userland = file->private_data; @@ -85,6 +159,8 @@ static int userland_release(struct inode *inode, struct file *file) static const struct file_operations userland_fops = { .poll = userland_poll, + .unlocked_ioctl = userland_ioctl, + .compat_ioctl = userland_ioctl, .release = userland_release, }; -- 2.47.3