From 3486740a4f32a6a466f5ac931654d154790ba648 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:17 -0700 Subject: userns: security: make capabilities relative to the user namespace - Introduce ns_capable to test for a capability in a non-default user namespace. - Teach cap_capable to handle capabilities in a non-default user namespace. The motivation is to get to the unprivileged creation of new namespaces. It looks like this gets us 90% of the way there, with only potential uid confusion issues left. I still need to handle getting all caps after creation but otherwise I think I have a good starter patch that achieves all of your goals. Changelog: 11/05/2010: [serge] add apparmor 12/14/2010: [serge] fix capabilities to created user namespaces Without this, if user serge creates a user_ns, he won't have capabilities to the user_ns he created. THis is because we were first checking whether his effective caps had the caps he needed and returning -EPERM if not, and THEN checking whether he was the creator. Reverse those checks. 12/16/2010: [serge] security_real_capable needs ns argument in !security case 01/11/2011: [serge] add task_ns_capable helper 01/11/2011: [serge] add nsown_capable() helper per Bastian Blank suggestion 02/16/2011: [serge] fix a logic bug: the root user is always creator of init_user_ns, but should not always have capabilities to it! Fix the check in cap_capable(). 02/21/2011: Add the required user_ns parameter to security_capable, fixing a compile failure. 02/23/2011: Convert some macros to functions as per akpm comments. Some couldn't be converted because we can't easily forward-declare them (they are inline if !SECURITY, extern if SECURITY). Add a current_user_ns function so we can use it in capability.h without #including cred.h. Move all forward declarations together to the top of the #ifdef __KERNEL__ section, and use kernel-doc format. 02/23/2011: Per dhowells, clean up comment in cap_capable(). 02/23/2011: Per akpm, remove unreachable 'return -EPERM' in cap_capable. (Original written and signed off by Eric; latest, modified version acked by him) [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: export current_user_ns() for ecryptfs] [serge.hallyn@canonical.com: remove unneeded extra argument in selinux's task_has_capability] Signed-off-by: Eric W. Biederman 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: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- security/commoncap.c | 38 +++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) (limited to 'security/commoncap.c') diff --git a/security/commoncap.c b/security/commoncap.c index 49c57fd60ae..43a205bc7d7 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * If a non-root user executes a setuid-root binary in @@ -67,6 +68,7 @@ EXPORT_SYMBOL(cap_netlink_recv); * cap_capable - Determine whether a task has a particular effective capability * @tsk: The task to query * @cred: The credentials to use + * @ns: The user namespace in which we need the capability * @cap: The capability to check for * @audit: Whether to write an audit message or not * @@ -78,10 +80,30 @@ EXPORT_SYMBOL(cap_netlink_recv); * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ -int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap, - int audit) +int cap_capable(struct task_struct *tsk, const struct cred *cred, + struct user_namespace *targ_ns, int cap, int audit) { - return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; + for (;;) { + /* The creator of the user namespace has all caps. */ + if (targ_ns != &init_user_ns && targ_ns->creator == cred->user) + return 0; + + /* Do we have the necessary capabilities? */ + if (targ_ns == cred->user->user_ns) + return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; + + /* Have we tried all of the parent namespaces? */ + if (targ_ns == &init_user_ns) + return -EPERM; + + /* + *If you have a capability in a parent user ns, then you have + * it over all children user namespaces as well. + */ + targ_ns = targ_ns->creator->user_ns; + } + + /* We never get here */ } /** @@ -176,7 +198,8 @@ static inline int cap_inh_is_capped(void) /* they are so limited unless the current task has the CAP_SETPCAP * capability */ - if (cap_capable(current, current_cred(), CAP_SETPCAP, + if (cap_capable(current, current_cred(), + current_cred()->user->user_ns, CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0) return 0; return 1; @@ -828,7 +851,8 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, & (new->securebits ^ arg2)) /*[1]*/ || ((new->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ - || (cap_capable(current, current_cred(), CAP_SETPCAP, + || (cap_capable(current, current_cred(), + current_cred()->user->user_ns, CAP_SETPCAP, SECURITY_CAP_AUDIT) != 0) /*[4]*/ /* * [1] no changing of bits that are locked @@ -893,7 +917,7 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; - if (cap_capable(current, current_cred(), CAP_SYS_ADMIN, + if (cap_capable(current, current_cred(), &init_user_ns, CAP_SYS_ADMIN, SECURITY_CAP_NOAUDIT) == 0) cap_sys_admin = 1; return __vm_enough_memory(mm, pages, cap_sys_admin); @@ -920,7 +944,7 @@ int cap_file_mmap(struct file *file, unsigned long reqprot, int ret = 0; if (addr < dac_mmap_min_addr) { - ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO, + ret = cap_capable(current, current_cred(), &init_user_ns, CAP_SYS_RAWIO, SECURITY_CAP_AUDIT); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) -- cgit v1.2.3-70-g09d2 From 8409cca7056113bee3236cb6a8e4d8d4d1eef102 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:20 -0700 Subject: userns: allow ptrace from non-init user namespaces ptrace is allowed to tasks in the same user namespace according to the usual rules (i.e. the same rules as for two tasks in the init user namespace). ptrace is also allowed to a user namespace to which the current task the has CAP_SYS_PTRACE capability. Changelog: Dec 31: Address feedback by Eric: . Correct ptrace uid check . Rename may_ptrace_ns to ptrace_capable . Also fix the cap_ptrace checks. Jan 1: Use const cred struct Jan 11: use task_ns_capable() in place of ptrace_capable(). Feb 23: same_or_ancestore_user_ns() was not an appropriate check to constrain cap_issubset. Rather, cap_issubset() only is meaningful when both capsets are in the same user_ns. Signed-off-by: Serge E. Hallyn Cc: "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/capability.h | 2 ++ kernel/ptrace.c | 27 +++++++++++++++------------ security/commoncap.c | 40 ++++++++++++++++++++++++++++++++-------- 3 files changed, 49 insertions(+), 20 deletions(-) (limited to 'security/commoncap.c') diff --git a/include/linux/capability.h b/include/linux/capability.h index 7c9c8290301..2ec4a8cc86a 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -553,6 +553,8 @@ static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a, */ #define has_capability(t, cap) (security_real_capable((t), &init_user_ns, (cap)) == 0) +#define has_ns_capability(t, ns, cap) (security_real_capable((t), (ns), (cap)) == 0) + /** * has_capability_noaudit - Determine if a task has a superior capability available (unaudited) * @t: The task in question diff --git a/kernel/ptrace.c b/kernel/ptrace.c index e2302e40b36..0fc1eed28d2 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -134,21 +134,24 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) return 0; rcu_read_lock(); tcred = __task_cred(task); - if ((cred->uid != tcred->euid || - cred->uid != tcred->suid || - cred->uid != tcred->uid || - cred->gid != tcred->egid || - cred->gid != tcred->sgid || - cred->gid != tcred->gid) && - !capable(CAP_SYS_PTRACE)) { - rcu_read_unlock(); - return -EPERM; - } + if (cred->user->user_ns == tcred->user->user_ns && + (cred->uid == tcred->euid && + cred->uid == tcred->suid && + cred->uid == tcred->uid && + cred->gid == tcred->egid && + cred->gid == tcred->sgid && + cred->gid == tcred->gid)) + goto ok; + if (ns_capable(tcred->user->user_ns, CAP_SYS_PTRACE)) + goto ok; + rcu_read_unlock(); + return -EPERM; +ok: rcu_read_unlock(); smp_rmb(); if (task->mm) dumpable = get_dumpable(task->mm); - if (!dumpable && !capable(CAP_SYS_PTRACE)) + if (!dumpable && !task_ns_capable(task, CAP_SYS_PTRACE)) return -EPERM; return security_ptrace_access_check(task, mode); @@ -198,7 +201,7 @@ static int ptrace_attach(struct task_struct *task) goto unlock_tasklist; task->ptrace = PT_PTRACED; - if (capable(CAP_SYS_PTRACE)) + if (task_ns_capable(task, CAP_SYS_PTRACE)) task->ptrace |= PT_PTRACE_CAP; __ptrace_link(task, current); diff --git a/security/commoncap.c b/security/commoncap.c index 43a205bc7d7..f20e984ccfb 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -127,18 +127,30 @@ int cap_settime(const struct timespec *ts, const struct timezone *tz) * @child: The process to be accessed * @mode: The mode of attachment. * + * If we are in the same or an ancestor user_ns and have all the target + * task's capabilities, then ptrace access is allowed. + * If we have the ptrace capability to the target user_ns, then ptrace + * access is allowed. + * Else denied. + * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; + const struct cred *cred, *child_cred; rcu_read_lock(); - if (!cap_issubset(__task_cred(child)->cap_permitted, - current_cred()->cap_permitted) && - !capable(CAP_SYS_PTRACE)) - ret = -EPERM; + cred = current_cred(); + child_cred = __task_cred(child); + if (cred->user->user_ns == child_cred->user->user_ns && + cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) + goto out; + if (ns_capable(child_cred->user->user_ns, CAP_SYS_PTRACE)) + goto out; + ret = -EPERM; +out: rcu_read_unlock(); return ret; } @@ -147,18 +159,30 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * + * If parent is in the same or an ancestor user_ns and has all current's + * capabilities, then ptrace access is allowed. + * If parent has the ptrace capability to current's user_ns, then ptrace + * access is allowed. + * Else denied. + * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; + const struct cred *cred, *child_cred; rcu_read_lock(); - if (!cap_issubset(current_cred()->cap_permitted, - __task_cred(parent)->cap_permitted) && - !has_capability(parent, CAP_SYS_PTRACE)) - ret = -EPERM; + cred = __task_cred(parent); + child_cred = current_cred(); + if (cred->user->user_ns == child_cred->user->user_ns && + cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) + goto out; + if (has_ns_capability(parent, child_cred->user->user_ns, CAP_SYS_PTRACE)) + goto out; + ret = -EPERM; +out: rcu_read_unlock(); return ret; } -- cgit v1.2.3-70-g09d2