remarkable-linux/include/linux/capability.h
Eric Paris 7d8b6c6375 CAPABILITIES: remove undefined caps from all processes
This is effectively a revert of 7b9a7ec565
plus fixing it a different way...

We found, when trying to run an application from an application which
had dropped privs that the kernel does security checks on undefined
capability bits.  This was ESPECIALLY difficult to debug as those
undefined bits are hidden from /proc/$PID/status.

Consider a root application which drops all capabilities from ALL 4
capability sets.  We assume, since the application is going to set
eff/perm/inh from an array that it will clear not only the defined caps
less than CAP_LAST_CAP, but also the higher 28ish bits which are
undefined future capabilities.

The BSET gets cleared differently.  Instead it is cleared one bit at a
time.  The problem here is that in security/commoncap.c::cap_task_prctl()
we actually check the validity of a capability being read.  So any task
which attempts to 'read all things set in bset' followed by 'unset all
things set in bset' will not even attempt to unset the undefined bits
higher than CAP_LAST_CAP.

So the 'parent' will look something like:
CapInh:	0000000000000000
CapPrm:	0000000000000000
CapEff:	0000000000000000
CapBnd:	ffffffc000000000

All of this 'should' be fine.  Given that these are undefined bits that
aren't supposed to have anything to do with permissions.  But they do...

So lets now consider a task which cleared the eff/perm/inh completely
and cleared all of the valid caps in the bset (but not the invalid caps
it couldn't read out of the kernel).  We know that this is exactly what
the libcap-ng library does and what the go capabilities library does.
They both leave you in that above situation if you try to clear all of
you capapabilities from all 4 sets.  If that root task calls execve()
the child task will pick up all caps not blocked by the bset.  The bset
however does not block bits higher than CAP_LAST_CAP.  So now the child
task has bits in eff which are not in the parent.  These are
'meaningless' undefined bits, but still bits which the parent doesn't
have.

The problem is now in cred_cap_issubset() (or any operation which does a
subset test) as the child, while a subset for valid cap bits, is not a
subset for invalid cap bits!  So now we set durring commit creds that
the child is not dumpable.  Given it is 'more priv' than its parent.  It
also means the parent cannot ptrace the child and other stupidity.

The solution here:
1) stop hiding capability bits in status
	This makes debugging easier!

2) stop giving any task undefined capability bits.  it's simple, it you
don't put those invalid bits in CAP_FULL_SET you won't get them in init
and you won't get them in any other task either.
	This fixes the cap_issubset() tests and resulting fallout (which
	made the init task in a docker container untraceable among other
	things)

3) mask out undefined bits when sys_capset() is called as it might use
~0, ~0 to denote 'all capabilities' for backward/forward compatibility.
	This lets 'capsh --caps="all=eip" -- -c /bin/bash' run.

4) mask out undefined bit when we read a file capability off of disk as
again likely all bits are set in the xattr for forward/backward
compatibility.
	This lets 'setcap all+pe /bin/bash; /bin/bash' run

Signed-off-by: Eric Paris <eparis@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Andrew G. Morgan <morgan@kernel.org>
Cc: Serge E. Hallyn <serge.hallyn@canonical.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Steve Grubb <sgrubb@redhat.com>
Cc: Dan Walsh <dwalsh@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: James Morris <james.l.morris@oracle.com>
2014-07-24 21:53:47 +10:00

223 lines
6.7 KiB
C

/*
* This is <linux/capability.h>
*
* Andrew G. Morgan <morgan@kernel.org>
* Alexander Kjeldaas <astor@guardian.no>
* with help from Aleph1, Roland Buresund and Andrew Main.
*
* See here for the libcap library ("POSIX draft" compliance):
*
* ftp://www.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/
*/
#ifndef _LINUX_CAPABILITY_H
#define _LINUX_CAPABILITY_H
#include <uapi/linux/capability.h>
#define _KERNEL_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_3
#define _KERNEL_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3
extern int file_caps_enabled;
typedef struct kernel_cap_struct {
__u32 cap[_KERNEL_CAPABILITY_U32S];
} kernel_cap_t;
/* exact same as vfs_cap_data but in cpu endian and always filled completely */
struct cpu_vfs_cap_data {
__u32 magic_etc;
kernel_cap_t permitted;
kernel_cap_t inheritable;
};
#define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct))
#define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t))
struct file;
struct inode;
struct dentry;
struct user_namespace;
struct user_namespace *current_user_ns(void);
extern const kernel_cap_t __cap_empty_set;
extern const kernel_cap_t __cap_init_eff_set;
/*
* Internal kernel functions only
*/
#define CAP_FOR_EACH_U32(__capi) \
for (__capi = 0; __capi < _KERNEL_CAPABILITY_U32S; ++__capi)
/*
* CAP_FS_MASK and CAP_NFSD_MASKS:
*
* The fs mask is all the privileges that fsuid==0 historically meant.
* At one time in the past, that included CAP_MKNOD and CAP_LINUX_IMMUTABLE.
*
* It has never meant setting security.* and trusted.* xattrs.
*
* We could also define fsmask as follows:
* 1. CAP_FS_MASK is the privilege to bypass all fs-related DAC permissions
* 2. The security.* and trusted.* xattrs are fs-related MAC permissions
*/
# define CAP_FS_MASK_B0 (CAP_TO_MASK(CAP_CHOWN) \
| CAP_TO_MASK(CAP_MKNOD) \
| CAP_TO_MASK(CAP_DAC_OVERRIDE) \
| CAP_TO_MASK(CAP_DAC_READ_SEARCH) \
| CAP_TO_MASK(CAP_FOWNER) \
| CAP_TO_MASK(CAP_FSETID))
# define CAP_FS_MASK_B1 (CAP_TO_MASK(CAP_MAC_OVERRIDE))
#if _KERNEL_CAPABILITY_U32S != 2
# error Fix up hand-coded capability macro initializers
#else /* HAND-CODED capability initializers */
#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1)
#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1)
# define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }})
# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }})
# define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \
| CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
CAP_FS_MASK_B1 } })
# define CAP_NFSD_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \
| CAP_TO_MASK(CAP_SYS_RESOURCE), \
CAP_FS_MASK_B1 } })
#endif /* _KERNEL_CAPABILITY_U32S != 2 */
# define cap_clear(c) do { (c) = __cap_empty_set; } while (0)
#define cap_raise(c, flag) ((c).cap[CAP_TO_INDEX(flag)] |= CAP_TO_MASK(flag))
#define cap_lower(c, flag) ((c).cap[CAP_TO_INDEX(flag)] &= ~CAP_TO_MASK(flag))
#define cap_raised(c, flag) ((c).cap[CAP_TO_INDEX(flag)] & CAP_TO_MASK(flag))
#define CAP_BOP_ALL(c, a, b, OP) \
do { \
unsigned __capi; \
CAP_FOR_EACH_U32(__capi) { \
c.cap[__capi] = a.cap[__capi] OP b.cap[__capi]; \
} \
} while (0)
#define CAP_UOP_ALL(c, a, OP) \
do { \
unsigned __capi; \
CAP_FOR_EACH_U32(__capi) { \
c.cap[__capi] = OP a.cap[__capi]; \
} \
} while (0)
static inline kernel_cap_t cap_combine(const kernel_cap_t a,
const kernel_cap_t b)
{
kernel_cap_t dest;
CAP_BOP_ALL(dest, a, b, |);
return dest;
}
static inline kernel_cap_t cap_intersect(const kernel_cap_t a,
const kernel_cap_t b)
{
kernel_cap_t dest;
CAP_BOP_ALL(dest, a, b, &);
return dest;
}
static inline kernel_cap_t cap_drop(const kernel_cap_t a,
const kernel_cap_t drop)
{
kernel_cap_t dest;
CAP_BOP_ALL(dest, a, drop, &~);
return dest;
}
static inline kernel_cap_t cap_invert(const kernel_cap_t c)
{
kernel_cap_t dest;
CAP_UOP_ALL(dest, c, ~);
return dest;
}
static inline int cap_isclear(const kernel_cap_t a)
{
unsigned __capi;
CAP_FOR_EACH_U32(__capi) {
if (a.cap[__capi] != 0)
return 0;
}
return 1;
}
/*
* Check if "a" is a subset of "set".
* return 1 if ALL of the capabilities in "a" are also in "set"
* cap_issubset(0101, 1111) will return 1
* return 0 if ANY of the capabilities in "a" are not in "set"
* cap_issubset(1111, 0101) will return 0
*/
static inline int cap_issubset(const kernel_cap_t a, const kernel_cap_t set)
{
kernel_cap_t dest;
dest = cap_drop(a, set);
return cap_isclear(dest);
}
/* Used to decide between falling back on the old suser() or fsuser(). */
static inline int cap_is_fs_cap(int cap)
{
const kernel_cap_t __cap_fs_set = CAP_FS_SET;
return !!(CAP_TO_MASK(cap) & __cap_fs_set.cap[CAP_TO_INDEX(cap)]);
}
static inline kernel_cap_t cap_drop_fs_set(const kernel_cap_t a)
{
const kernel_cap_t __cap_fs_set = CAP_FS_SET;
return cap_drop(a, __cap_fs_set);
}
static inline kernel_cap_t cap_raise_fs_set(const kernel_cap_t a,
const kernel_cap_t permitted)
{
const kernel_cap_t __cap_fs_set = CAP_FS_SET;
return cap_combine(a,
cap_intersect(permitted, __cap_fs_set));
}
static inline kernel_cap_t cap_drop_nfsd_set(const kernel_cap_t a)
{
const kernel_cap_t __cap_fs_set = CAP_NFSD_SET;
return cap_drop(a, __cap_fs_set);
}
static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a,
const kernel_cap_t permitted)
{
const kernel_cap_t __cap_nfsd_set = CAP_NFSD_SET;
return cap_combine(a,
cap_intersect(permitted, __cap_nfsd_set));
}
extern bool has_capability(struct task_struct *t, int cap);
extern bool has_ns_capability(struct task_struct *t,
struct user_namespace *ns, int cap);
extern bool has_capability_noaudit(struct task_struct *t, int cap);
extern bool has_ns_capability_noaudit(struct task_struct *t,
struct user_namespace *ns, int cap);
extern bool capable(int cap);
extern bool ns_capable(struct user_namespace *ns, int cap);
extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
/* audit system wants to get cap info from files as well */
extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
#endif /* !_LINUX_CAPABILITY_H */