From: "Serge E. Hallyn" When a task enters a new namespace via a clone() or unshare(), a new container is created and the task moves into it. This version names containers which are automatically created using container_clone() as "node_" where pid is the pid of the unsharing or cloned process. (Thanks Pavel for the idea) This is safe because if the process unshares again, it will create /containers/(...)/node_/node_ The only possibilities (AFAICT) for a -EEXIST on unshare are 1. pid wraparound 2. a process fails an unshare, then tries again. Case 1 is unlikely enough that I ignore it (at least for now). In case 2, the node_ will be empty and can be rmdir'ed to make the subsequent unshare() succeed. Changelog: Name cloned containers as "node_". Signed-off-by: Serge E. Hallyn Cc: Paul Menage Signed-off-by: Andrew Morton --- include/linux/container_subsys.h | 6 + include/linux/nsproxy.h | 7 ++ init/Kconfig | 9 ++ kernel/Makefile | 1 kernel/ns_container.c | 100 +++++++++++++++++++++++++++++ kernel/nsproxy.c | 17 ++++ 6 files changed, 139 insertions(+), 1 deletion(-) diff -puN include/linux/container_subsys.h~containers-implement-namespace-tracking-subsystem include/linux/container_subsys.h --- a/include/linux/container_subsys.h~containers-implement-namespace-tracking-subsystem +++ a/include/linux/container_subsys.h @@ -24,3 +24,9 @@ SUBSYS(debug) #endif /* */ + +#ifdef CONFIG_CONTAINER_NS +SUBSYS(ns) +#endif + +/* */ diff -puN include/linux/nsproxy.h~containers-implement-namespace-tracking-subsystem include/linux/nsproxy.h --- a/include/linux/nsproxy.h~containers-implement-namespace-tracking-subsystem +++ a/include/linux/nsproxy.h @@ -55,4 +55,11 @@ static inline void exit_task_namespaces( put_nsproxy(ns); } } + +#ifdef CONFIG_CONTAINER_NS +int ns_container_clone(struct task_struct *tsk); +#else +static inline int ns_container_clone(struct task_struct *tsk) { return 0; } +#endif + #endif diff -puN init/Kconfig~containers-implement-namespace-tracking-subsystem init/Kconfig --- a/init/Kconfig~containers-implement-namespace-tracking-subsystem +++ a/init/Kconfig @@ -341,6 +341,15 @@ config SYSFS_DEPRECATED If you are using a distro that was released in 2006 or later, it should be safe to say N here. +config CONTAINER_NS + bool "Namespace container subsystem" + select CONTAINERS + help + Provides a simple namespace container subsystem to + provide hierarchical naming of sets of namespaces, + for instance virtual servers and checkpoint/restart + jobs. + config PROC_PID_CPUSET bool "Include legacy /proc//cpuset file" depends on CPUSETS diff -puN kernel/Makefile~containers-implement-namespace-tracking-subsystem kernel/Makefile --- a/kernel/Makefile~containers-implement-namespace-tracking-subsystem +++ a/kernel/Makefile @@ -42,6 +42,7 @@ obj-$(CONFIG_CONTAINERS) += container.o obj-$(CONFIG_CONTAINER_DEBUG) += container_debug.o obj-$(CONFIG_CPUSETS) += cpuset.o obj-$(CONFIG_CONTAINER_CPUACCT) += cpu_acct.o +obj-$(CONFIG_CONTAINER_NS) += ns_container.o obj-$(CONFIG_IKCONFIG) += configs.o obj-$(CONFIG_STOP_MACHINE) += stop_machine.o obj-$(CONFIG_AUDIT) += audit.o auditfilter.o diff -puN /dev/null kernel/ns_container.c --- /dev/null +++ a/kernel/ns_container.c @@ -0,0 +1,100 @@ +/* + * ns_container.c - namespace container subsystem + * + * Copyright 2006, 2007 IBM Corp + */ + +#include +#include +#include + +struct ns_container { + struct container_subsys_state css; + spinlock_t lock; +}; + +struct container_subsys ns_subsys; + +static inline struct ns_container *container_to_ns( + struct container *container) +{ + return container_of(container_subsys_state(container, ns_subsys_id), + struct ns_container, css); +} + +int ns_container_clone(struct task_struct *task) +{ + return container_clone(task, &ns_subsys); +} + +/* + * Rules: + * 1. you can only enter a container which is a child of your current + * container + * 2. you can only place another process into a container if + * a. you have CAP_SYS_ADMIN + * b. your container is an ancestor of task's destination container + * (hence either you are in the same container as task, or in an + * ancestor container thereof) + */ +static int ns_can_attach(struct container_subsys *ss, + struct container *new_container, struct task_struct *task) +{ + struct container *orig; + + if (current != task) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!container_is_descendant(new_container)) + return -EPERM; + } + + if (atomic_read(&new_container->count) != 0) + return -EPERM; + + orig = task_container(task, ns_subsys_id); + if (orig && orig != new_container->parent) + return -EPERM; + + return 0; +} + +/* + * Rules: you can only create a container if + * 1. you are capable(CAP_SYS_ADMIN) + * 2. the target container is a descendant of your own container + */ +static struct container_subsys_state *ns_create(struct container_subsys *ss, + struct container *container) +{ + struct ns_container *ns_container; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + if (!container_is_descendant(container)) + return ERR_PTR(-EPERM); + + ns_container = kzalloc(sizeof(*ns_container), GFP_KERNEL); + if (!ns_container) + return ERR_PTR(-ENOMEM); + spin_lock_init(&ns_container->lock); + return &ns_container->css; +} + +static void ns_destroy(struct container_subsys *ss, + struct container *container) +{ + struct ns_container *ns_container; + + ns_container = container_to_ns(container); + kfree(ns_container); +} + +struct container_subsys ns_subsys = { + .name = "ns", + .can_attach = ns_can_attach, + .create = ns_create, + .destroy = ns_destroy, + .subsys_id = ns_subsys_id, +}; diff -puN kernel/nsproxy.c~containers-implement-namespace-tracking-subsystem kernel/nsproxy.c --- a/kernel/nsproxy.c~containers-implement-namespace-tracking-subsystem +++ a/kernel/nsproxy.c @@ -146,7 +146,14 @@ int copy_namespaces(unsigned long flags, goto out; } + err = ns_container_clone(tsk); + if (err) { + put_nsproxy(new_ns); + goto out; + } + tsk->nsproxy = new_ns; + out: put_nsproxy(old_ns); return err; @@ -185,8 +192,16 @@ int unshare_nsproxy_namespaces(unsigned *new_nsp = create_new_namespaces(unshare_flags, current, new_fs ? new_fs : current->fs); - if (IS_ERR(*new_nsp)) + if (IS_ERR(*new_nsp)) { err = PTR_ERR(*new_nsp); + goto out; + } + + err = ns_container_clone(current); + if (err) + put_nsproxy(*new_nsp); + +out: return err; } _