87c31b39ab
Pull user namespace related fixes from Eric Biederman:
"As these are bug fixes almost all of thes changes are marked for
backporting to stable.
The first change (implicitly adding MNT_NODEV on remount) addresses a
regression that was created when security issues with unprivileged
remount were closed. I go on to update the remount test to make it
easy to detect if this issue reoccurs.
Then there are a handful of mount and umount related fixes.
Then half of the changes deal with the a recently discovered design
bug in the permission checks of gid_map. Unix since the beginning has
allowed setting group permissions on files to less than the user and
other permissions (aka ---rwx---rwx). As the unix permission checks
stop as soon as a group matches, and setgroups allows setting groups
that can not later be dropped, results in a situtation where it is
possible to legitimately use a group to assign fewer privileges to a
process. Which means dropping a group can increase a processes
privileges.
The fix I have adopted is that gid_map is now no longer writable
without privilege unless the new file /proc/self/setgroups has been
set to permanently disable setgroups.
The bulk of user namespace using applications even the applications
using applications using user namespaces without privilege remain
unaffected by this change. Unfortunately this ix breaks a couple user
space applications, that were relying on the problematic behavior (one
of which was tools/selftests/mount/unprivileged-remount-test.c).
To hopefully prevent needing a regression fix on top of my security
fix I rounded folks who work with the container implementations mostly
like to be affected and encouraged them to test the changes.
> So far nothing broke on my libvirt-lxc test bed. :-)
> Tested with openSUSE 13.2 and libvirt 1.2.9.
> Tested-by: Richard Weinberger <richard@nod.at>
> Tested on Fedora20 with libvirt 1.2.11, works fine.
> Tested-by: Chen Hanxiao <chenhanxiao@cn.fujitsu.com>
> Ok, thanks - yes, unprivileged lxc is working fine with your kernels.
> Just to be sure I was testing the right thing I also tested using
> my unprivileged nsexec testcases, and they failed on setgroup/setgid
> as now expected, and succeeded there without your patches.
> Tested-by: Serge Hallyn <serge.hallyn@ubuntu.com>
> I tested this with Sandstorm. It breaks as is and it works if I add
> the setgroups thing.
> Tested-by: Andy Lutomirski <luto@amacapital.net> # breaks things as designed :("
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
userns: Unbreak the unprivileged remount tests
userns; Correct the comment in map_write
userns: Allow setting gid_maps without privilege when setgroups is disabled
userns: Add a knob to disable setgroups on a per user namespace basis
userns: Rename id_map_mutex to userns_state_mutex
userns: Only allow the creator of the userns unprivileged mappings
userns: Check euid no fsuid when establishing an unprivileged uid mapping
userns: Don't allow unprivileged creation of gid mappings
userns: Don't allow setgroups until a gid mapping has been setablished
userns: Document what the invariant required for safe unprivileged mappings.
groups: Consolidate the setgroups permission checks
mnt: Clear mnt_expire during pivot_root
mnt: Carefully set CL_UNPRIVILEGED in clone_mnt
mnt: Move the clear of MNT_LOCKED from copy_tree to it's callers.
umount: Do not allow unmounting rootfs.
umount: Disallow unprivileged mount force
mnt: Update unprivileged remount test
mnt: Implicitly add MNT_NODEV on remount when it was implicitly added by mount
105 lines
2.6 KiB
C
105 lines
2.6 KiB
C
#ifndef _LINUX_USER_NAMESPACE_H
|
|
#define _LINUX_USER_NAMESPACE_H
|
|
|
|
#include <linux/kref.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/ns_common.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/err.h>
|
|
|
|
#define UID_GID_MAP_MAX_EXTENTS 5
|
|
|
|
struct uid_gid_map { /* 64 bytes -- 1 cache line */
|
|
u32 nr_extents;
|
|
struct uid_gid_extent {
|
|
u32 first;
|
|
u32 lower_first;
|
|
u32 count;
|
|
} extent[UID_GID_MAP_MAX_EXTENTS];
|
|
};
|
|
|
|
#define USERNS_SETGROUPS_ALLOWED 1UL
|
|
|
|
#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
|
|
|
|
struct user_namespace {
|
|
struct uid_gid_map uid_map;
|
|
struct uid_gid_map gid_map;
|
|
struct uid_gid_map projid_map;
|
|
atomic_t count;
|
|
struct user_namespace *parent;
|
|
int level;
|
|
kuid_t owner;
|
|
kgid_t group;
|
|
struct ns_common ns;
|
|
unsigned long flags;
|
|
|
|
/* Register of per-UID persistent keyrings for this namespace */
|
|
#ifdef CONFIG_PERSISTENT_KEYRINGS
|
|
struct key *persistent_keyring_register;
|
|
struct rw_semaphore persistent_keyring_register_sem;
|
|
#endif
|
|
};
|
|
|
|
extern struct user_namespace init_user_ns;
|
|
|
|
#ifdef CONFIG_USER_NS
|
|
|
|
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
|
|
{
|
|
if (ns)
|
|
atomic_inc(&ns->count);
|
|
return ns;
|
|
}
|
|
|
|
extern int create_user_ns(struct cred *new);
|
|
extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred);
|
|
extern void free_user_ns(struct user_namespace *ns);
|
|
|
|
static inline void put_user_ns(struct user_namespace *ns)
|
|
{
|
|
if (ns && atomic_dec_and_test(&ns->count))
|
|
free_user_ns(ns);
|
|
}
|
|
|
|
struct seq_operations;
|
|
extern const struct seq_operations proc_uid_seq_operations;
|
|
extern const struct seq_operations proc_gid_seq_operations;
|
|
extern const struct seq_operations proc_projid_seq_operations;
|
|
extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
|
|
extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
|
|
extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
|
|
extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
|
|
extern int proc_setgroups_show(struct seq_file *m, void *v);
|
|
extern bool userns_may_setgroups(const struct user_namespace *ns);
|
|
#else
|
|
|
|
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
|
|
{
|
|
return &init_user_ns;
|
|
}
|
|
|
|
static inline int create_user_ns(struct cred *new)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
static inline int unshare_userns(unsigned long unshare_flags,
|
|
struct cred **new_cred)
|
|
{
|
|
if (unshare_flags & CLONE_NEWUSER)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static inline void put_user_ns(struct user_namespace *ns)
|
|
{
|
|
}
|
|
|
|
static inline bool userns_may_setgroups(const struct user_namespace *ns)
|
|
{
|
|
return true;
|
|
}
|
|
#endif
|
|
|
|
#endif /* _LINUX_USER_H */
|