From 5e4a08476b50fa39210fca82e03325cc46b9c235 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Dec 2012 07:55:36 -0800 Subject: userns: Require CAP_SYS_ADMIN for most uses of setns. Andy Lutomirski found a nasty little bug in the permissions of setns. With unprivileged user namespaces it became possible to create new namespaces without privilege. However the setns calls were relaxed to only require CAP_SYS_ADMIN in the user nameapce of the targed namespace. Which made the following nasty sequence possible. pid = clone(CLONE_NEWUSER | CLONE_NEWNS); if (pid == 0) { /* child */ system("mount --bind /home/me/passwd /etc/passwd"); } else if (pid != 0) { /* parent */ char path[PATH_MAX]; snprintf(path, sizeof(path), "/proc/%u/ns/mnt"); fd = open(path, O_RDONLY); setns(fd, 0); system("su -"); } Prevent this possibility by requiring CAP_SYS_ADMIN in the current user namespace when joing all but the user namespace. Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- kernel/pid_namespace.c | 3 ++- kernel/utsname.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 560da0dab230..fdbd0cdf271a 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -325,7 +325,8 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns) struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *ancestor, *new = ns; - if (!ns_capable(new->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) return -EPERM; /* diff --git a/kernel/utsname.c b/kernel/utsname.c index f6336d51d64c..08b197e8c485 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -113,7 +113,8 @@ static int utsns_install(struct nsproxy *nsproxy, void *new) { struct uts_namespace *ns = new; - if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !nsown_capable(CAP_SYS_ADMIN)) return -EPERM; get_uts_ns(ns); -- cgit v1.2.3-70-g09d2 From aa6d054e5ce94720797ca260392a74dbced56412 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 14 Dec 2012 08:50:54 -0800 Subject: userns: Add a more complete capability subset test to commit_creds When unsharing a user namespace we reduce our credentials to just what can be done in that user namespace. This is a subset of the credentials we previously had. Teach commit_creds to recognize this is a subset of the credentials we have had before and don't clear the dumpability flag. This allows an unprivileged program to do: unshare(CLONE_NEWUSER); fd = open("/proc/self/uid_map", O_RDWR); Where previously opening the uid_map writable would fail because the the task had been made non-dumpable. Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- kernel/cred.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index 48cea3da6d05..709d521903f6 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -455,6 +455,31 @@ error_put: return ret; } +static bool cred_cap_issubset(const struct cred *set, const struct cred *subset) +{ + const struct user_namespace *set_ns = set->user_ns; + const struct user_namespace *subset_ns = subset->user_ns; + + /* If the two credentials are in the same user namespace see if + * the capabilities of subset are a subset of set. + */ + if (set_ns == subset_ns) + return cap_issubset(subset->cap_permitted, set->cap_permitted); + + /* The credentials are in a different user namespaces + * therefore one is a subset of the other only if a set is an + * ancestor of subset and set->euid is owner of subset or one + * of subsets ancestors. + */ + for (;subset_ns != &init_user_ns; subset_ns = subset_ns->parent) { + if ((set_ns == subset_ns->parent) && + uid_eq(subset_ns->owner, set->euid)) + return true; + } + + return false; +} + /** * commit_creds - Install new credentials upon the current task * @new: The credentials to be assigned @@ -493,7 +518,7 @@ int commit_creds(struct cred *new) !gid_eq(old->egid, new->egid) || !uid_eq(old->fsuid, new->fsuid) || !gid_eq(old->fsgid, new->fsgid) || - !cap_issubset(new->cap_permitted, old->cap_permitted)) { + !cred_cap_issubset(old, new)) { if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; -- cgit v1.2.3-70-g09d2 From 5155040ed349950e16c093ba8e65ad534994df2a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 9 Dec 2012 17:19:52 -0800 Subject: userns: Fix typo in description of the limitation of userns_install Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- kernel/user_namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index f5975ccf9348..2b042c42fbc4 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -799,7 +799,7 @@ static int userns_install(struct nsproxy *nsproxy, void *ns) if (user_ns == current_user_ns()) return -EINVAL; - /* Threaded many not enter a different user namespace */ + /* Threaded processes may not enter a different user namespace */ if (atomic_read(¤t->mm->mm_users) > 1) return -EINVAL; -- cgit v1.2.3-70-g09d2