From 59607db367c57f515183cb203642291bb14d9c40 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:16 -0700 Subject: userns: add a user_namespace as creator/owner of uts_namespace The expected course of development for user namespaces targeted capabilities is laid out at https://wiki.ubuntu.com/UserNamespace. Goals: - Make it safe for an unprivileged user to unshare namespaces. They will be privileged with respect to the new namespace, but this should only include resources which the unprivileged user already owns. - Provide separate limits and accounting for userids in different namespaces. Status: Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and CAP_SETGID capabilities. What this gets you is a whole new set of userids, meaning that user 500 will have a different 'struct user' in your namespace than in other namespaces. So any accounting information stored in struct user will be unique to your namespace. However, throughout the kernel there are checks which - simply check for a capability. Since root in a child namespace has all capabilities, this means that a child namespace is not constrained. - simply compare uid1 == uid2. Since these are the integer uids, uid 500 in namespace 1 will be said to be equal to uid 500 in namespace 2. As a result, the lxc implementation at lxc.sf.net does not use user namespaces. This is actually helpful because it leaves us free to develop user namespaces in such a way that, for some time, user namespaces may be unuseful. Bugs aside, this patchset is supposed to not at all affect systems which are not actively using user namespaces, and only restrict what tasks in child user namespace can do. They begin to limit privilege to a user namespace, so that root in a container cannot kill or ptrace tasks in the parent user namespace, and can only get world access rights to files. Since all files currently belong to the initila user namespace, that means that child user namespaces can only get world access rights to *all* files. While this temporarily makes user namespaces bad for system containers, it starts to get useful for some sandboxing. I've run the 'runltplite.sh' with and without this patchset and found no difference. This patch: copy_process() handles CLONE_NEWUSER before the rest of the namespaces. So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace will have the new user namespace as its owner. That is what we want, since we want root in that new userns to be able to have privilege over it. Changelog: Feb 15: don't set uts_ns->user_ns if we didn't create a new uts_ns. Feb 23: Move extern init_user_ns declaration from init/version.c to utsname.h. Signed-off-by: Serge E. Hallyn Acked-by: "Eric W. Biederman" Acked-by: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/utsname.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/utsname.c') diff --git a/kernel/utsname.c b/kernel/utsname.c index 8a82b4b8ea5..a7b3a8d1ad2 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -14,6 +14,7 @@ #include #include #include +#include static struct uts_namespace *create_uts_ns(void) { @@ -40,6 +41,8 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); + ns->user_ns = old_ns->user_ns; + get_user_ns(ns->user_ns); up_read(&uts_sem); return ns; } @@ -71,5 +74,6 @@ void free_uts_ns(struct kref *kref) struct uts_namespace *ns; ns = container_of(kref, struct uts_namespace, kref); + put_user_ns(ns->user_ns); kfree(ns); } -- cgit v1.2.3-70-g09d2 From bb96a6f50be27390dc959ff67d9ea0ea0cfbe177 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:18 -0700 Subject: userns: allow sethostname in a container Changelog: Feb 23: let clone_uts_ns() handle setting uts->user_ns To do so we need to pass in the task_struct who'll get the utsname, so we can get its user_ns. Feb 23: As per Oleg's coment, just pass in tsk, instead of two of its members. Signed-off-by: Serge E. Hallyn Acked-by: "Eric W. Biederman" Acked-by: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/utsname.h | 6 +++--- kernel/nsproxy.c | 7 +------ kernel/sys.c | 2 +- kernel/utsname.c | 12 +++++++----- 4 files changed, 12 insertions(+), 15 deletions(-) (limited to 'kernel/utsname.c') diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 2c3c0f54370..4e5b0213fdc 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -54,7 +54,7 @@ static inline void get_uts_ns(struct uts_namespace *ns) } extern struct uts_namespace *copy_utsname(unsigned long flags, - struct uts_namespace *ns); + struct task_struct *tsk); extern void free_uts_ns(struct kref *kref); static inline void put_uts_ns(struct uts_namespace *ns) @@ -71,12 +71,12 @@ static inline void put_uts_ns(struct uts_namespace *ns) } static inline struct uts_namespace *copy_utsname(unsigned long flags, - struct uts_namespace *ns) + struct task_struct *tsk) { if (flags & CLONE_NEWUTS) return ERR_PTR(-EINVAL); - return ns; + return tsk->nsproxy->uts_ns; } #endif diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 034dc2ed13a..b97fc9d04dd 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -69,16 +69,11 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_ns; } - new_nsp->uts_ns = copy_utsname(flags, tsk->nsproxy->uts_ns); + new_nsp->uts_ns = copy_utsname(flags, tsk); if (IS_ERR(new_nsp->uts_ns)) { err = PTR_ERR(new_nsp->uts_ns); goto out_uts; } - if (new_nsp->uts_ns != tsk->nsproxy->uts_ns) { - put_user_ns(new_nsp->uts_ns->user_ns); - new_nsp->uts_ns->user_ns = task_cred_xxx(tsk, user)->user_ns; - get_user_ns(new_nsp->uts_ns->user_ns); - } new_nsp->ipc_ns = copy_ipcs(flags, tsk->nsproxy->ipc_ns); if (IS_ERR(new_nsp->ipc_ns)) { diff --git a/kernel/sys.c b/kernel/sys.c index 1ad48b3b906..5761c53e19e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1181,7 +1181,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) int errno; char tmp[__NEW_UTS_LEN]; - if (!capable(CAP_SYS_ADMIN)) + if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; diff --git a/kernel/utsname.c b/kernel/utsname.c index a7b3a8d1ad2..44646179eab 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -31,7 +31,8 @@ static struct uts_namespace *create_uts_ns(void) * @old_ns: namespace to clone * Return NULL on error (failure to kmalloc), new ns otherwise */ -static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) +static struct uts_namespace *clone_uts_ns(struct task_struct *tsk, + struct uts_namespace *old_ns) { struct uts_namespace *ns; @@ -41,8 +42,7 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); - ns->user_ns = old_ns->user_ns; - get_user_ns(ns->user_ns); + ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns); up_read(&uts_sem); return ns; } @@ -53,8 +53,10 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns) * utsname of this process won't be seen by parent, and vice * versa. */ -struct uts_namespace *copy_utsname(unsigned long flags, struct uts_namespace *old_ns) +struct uts_namespace *copy_utsname(unsigned long flags, + struct task_struct *tsk) { + struct uts_namespace *old_ns = tsk->nsproxy->uts_ns; struct uts_namespace *new_ns; BUG_ON(!old_ns); @@ -63,7 +65,7 @@ struct uts_namespace *copy_utsname(unsigned long flags, struct uts_namespace *ol if (!(flags & CLONE_NEWUTS)) return old_ns; - new_ns = clone_uts_ns(old_ns); + new_ns = clone_uts_ns(tsk, old_ns); put_uts_ns(old_ns); return new_ns; -- cgit v1.2.3-70-g09d2