mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-11-01 17:08:10 +00:00
72c2d5823f
The non-filesystem capability meaning of CAP_SETPCAP is that a process, p1, can change the capabilities of another process, p2. This is not the meaning that was intended for this capability at all, and this implementation came about purely because, without filesystem capabilities, there was no way to use capabilities without one process bestowing them on another. Since we now have a filesystem support for capabilities we can fix the implementation of CAP_SETPCAP. The most significant thing about this change is that, with it in effect, no process can set the capabilities of another process. The capabilities of a program are set via the capability convolution rules: pI(post-exec) = pI(pre-exec) pP(post-exec) = (X(aka cap_bset) & fP) | (pI(post-exec) & fI) pE(post-exec) = fE ? pP(post-exec) : 0 at exec() time. As such, the only influence the pre-exec() program can have on the post-exec() program's capabilities are through the pI capability set. The correct implementation for CAP_SETPCAP (and that enabled by this patch) is that it can be used to add extra pI capabilities to the current process - to be picked up by subsequent exec()s when the above convolution rules are applied. Here is how it works: Let's say we have a process, p. It has capability sets, pE, pP and pI. Generally, p, can change the value of its own pI to pI' where (pI' & ~pI) & ~pP = 0. That is, the only new things in pI' that were not present in pI need to be present in pP. The role of CAP_SETPCAP is basically to permit changes to pI beyond the above: if (pE & CAP_SETPCAP) { pI' = anything; /* ie., even (pI' & ~pI) & ~pP != 0 */ } This capability is useful for things like login, which (say, via pam_cap) might want to raise certain inheritable capabilities for use by the children of the logged-in user's shell, but those capabilities are not useful to or needed by the login program itself. One such use might be to limit who can run ping. You set the capabilities of the 'ping' program to be "= cap_net_raw+i", and then only shells that have (pI & CAP_NET_RAW) will be able to run it. Without CAP_SETPCAP implemented as described above, login(pam_cap) would have to also have (pP & CAP_NET_RAW) in order to raise this capability and pass it on through the inheritable set. Signed-off-by: Andrew Morgan <morgan@kernel.org> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Stephen Smalley <sds@tycho.nsa.gov> Cc: James Morris <jmorris@namei.org> Cc: Casey Schaufler <casey@schaufler-ca.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
382 lines
11 KiB
C
382 lines
11 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://linux.kernel.org/pub/linux/libs/security/linux-privs/kernel-2.6/
|
|
*/
|
|
|
|
#ifndef _LINUX_CAPABILITY_H
|
|
#define _LINUX_CAPABILITY_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/compiler.h>
|
|
|
|
struct task_struct;
|
|
|
|
/* User-level do most of the mapping between kernel and user
|
|
capabilities based on the version tag given by the kernel. The
|
|
kernel might be somewhat backwards compatible, but don't bet on
|
|
it. */
|
|
|
|
/* XXX - Note, cap_t, is defined by POSIX to be an "opaque" pointer to
|
|
a set of three capability sets. The transposition of 3*the
|
|
following structure to such a composite is better handled in a user
|
|
library since the draft standard requires the use of malloc/free
|
|
etc.. */
|
|
|
|
#define _LINUX_CAPABILITY_VERSION 0x19980330
|
|
|
|
typedef struct __user_cap_header_struct {
|
|
__u32 version;
|
|
int pid;
|
|
} __user *cap_user_header_t;
|
|
|
|
typedef struct __user_cap_data_struct {
|
|
__u32 effective;
|
|
__u32 permitted;
|
|
__u32 inheritable;
|
|
} __user *cap_user_data_t;
|
|
|
|
#define XATTR_CAPS_SUFFIX "capability"
|
|
#define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX
|
|
|
|
#define XATTR_CAPS_SZ (3*sizeof(__le32))
|
|
#define VFS_CAP_REVISION_MASK 0xFF000000
|
|
#define VFS_CAP_REVISION_1 0x01000000
|
|
|
|
#define VFS_CAP_REVISION VFS_CAP_REVISION_1
|
|
|
|
#define VFS_CAP_FLAGS_MASK ~VFS_CAP_REVISION_MASK
|
|
#define VFS_CAP_FLAGS_EFFECTIVE 0x000001
|
|
|
|
struct vfs_cap_data {
|
|
__u32 magic_etc; /* Little endian */
|
|
struct {
|
|
__u32 permitted; /* Little endian */
|
|
__u32 inheritable; /* Little endian */
|
|
} data[1];
|
|
};
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
/* #define STRICT_CAP_T_TYPECHECKS */
|
|
|
|
#ifdef STRICT_CAP_T_TYPECHECKS
|
|
|
|
typedef struct kernel_cap_struct {
|
|
__u32 cap;
|
|
} kernel_cap_t;
|
|
|
|
#else
|
|
|
|
typedef __u32 kernel_cap_t;
|
|
|
|
#endif
|
|
|
|
#define _USER_CAP_HEADER_SIZE (2*sizeof(__u32))
|
|
#define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t))
|
|
|
|
#endif
|
|
|
|
|
|
/**
|
|
** POSIX-draft defined capabilities.
|
|
**/
|
|
|
|
/* In a system with the [_POSIX_CHOWN_RESTRICTED] option defined, this
|
|
overrides the restriction of changing file ownership and group
|
|
ownership. */
|
|
|
|
#define CAP_CHOWN 0
|
|
|
|
/* Override all DAC access, including ACL execute access if
|
|
[_POSIX_ACL] is defined. Excluding DAC access covered by
|
|
CAP_LINUX_IMMUTABLE. */
|
|
|
|
#define CAP_DAC_OVERRIDE 1
|
|
|
|
/* Overrides all DAC restrictions regarding read and search on files
|
|
and directories, including ACL restrictions if [_POSIX_ACL] is
|
|
defined. Excluding DAC access covered by CAP_LINUX_IMMUTABLE. */
|
|
|
|
#define CAP_DAC_READ_SEARCH 2
|
|
|
|
/* Overrides all restrictions about allowed operations on files, where
|
|
file owner ID must be equal to the user ID, except where CAP_FSETID
|
|
is applicable. It doesn't override MAC and DAC restrictions. */
|
|
|
|
#define CAP_FOWNER 3
|
|
|
|
/* Overrides the following restrictions that the effective user ID
|
|
shall match the file owner ID when setting the S_ISUID and S_ISGID
|
|
bits on that file; that the effective group ID (or one of the
|
|
supplementary group IDs) shall match the file owner ID when setting
|
|
the S_ISGID bit on that file; that the S_ISUID and S_ISGID bits are
|
|
cleared on successful return from chown(2) (not implemented). */
|
|
|
|
#define CAP_FSETID 4
|
|
|
|
/* Used to decide between falling back on the old suser() or fsuser(). */
|
|
|
|
#define CAP_FS_MASK 0x1f
|
|
|
|
/* Overrides the restriction that the real or effective user ID of a
|
|
process sending a signal must match the real or effective user ID
|
|
of the process receiving the signal. */
|
|
|
|
#define CAP_KILL 5
|
|
|
|
/* Allows setgid(2) manipulation */
|
|
/* Allows setgroups(2) */
|
|
/* Allows forged gids on socket credentials passing. */
|
|
|
|
#define CAP_SETGID 6
|
|
|
|
/* Allows set*uid(2) manipulation (including fsuid). */
|
|
/* Allows forged pids on socket credentials passing. */
|
|
|
|
#define CAP_SETUID 7
|
|
|
|
|
|
/**
|
|
** Linux-specific capabilities
|
|
**/
|
|
|
|
/* Transfer any capability in your permitted set to any pid,
|
|
remove any capability in your permitted set from any pid */
|
|
|
|
#define CAP_SETPCAP 8
|
|
|
|
/* Allow modification of S_IMMUTABLE and S_APPEND file attributes */
|
|
|
|
#define CAP_LINUX_IMMUTABLE 9
|
|
|
|
/* Allows binding to TCP/UDP sockets below 1024 */
|
|
/* Allows binding to ATM VCIs below 32 */
|
|
|
|
#define CAP_NET_BIND_SERVICE 10
|
|
|
|
/* Allow broadcasting, listen to multicast */
|
|
|
|
#define CAP_NET_BROADCAST 11
|
|
|
|
/* Allow interface configuration */
|
|
/* Allow administration of IP firewall, masquerading and accounting */
|
|
/* Allow setting debug option on sockets */
|
|
/* Allow modification of routing tables */
|
|
/* Allow setting arbitrary process / process group ownership on
|
|
sockets */
|
|
/* Allow binding to any address for transparent proxying */
|
|
/* Allow setting TOS (type of service) */
|
|
/* Allow setting promiscuous mode */
|
|
/* Allow clearing driver statistics */
|
|
/* Allow multicasting */
|
|
/* Allow read/write of device-specific registers */
|
|
/* Allow activation of ATM control sockets */
|
|
|
|
#define CAP_NET_ADMIN 12
|
|
|
|
/* Allow use of RAW sockets */
|
|
/* Allow use of PACKET sockets */
|
|
|
|
#define CAP_NET_RAW 13
|
|
|
|
/* Allow locking of shared memory segments */
|
|
/* Allow mlock and mlockall (which doesn't really have anything to do
|
|
with IPC) */
|
|
|
|
#define CAP_IPC_LOCK 14
|
|
|
|
/* Override IPC ownership checks */
|
|
|
|
#define CAP_IPC_OWNER 15
|
|
|
|
/* Insert and remove kernel modules - modify kernel without limit */
|
|
/* Modify cap_bset */
|
|
#define CAP_SYS_MODULE 16
|
|
|
|
/* Allow ioperm/iopl access */
|
|
/* Allow sending USB messages to any device via /proc/bus/usb */
|
|
|
|
#define CAP_SYS_RAWIO 17
|
|
|
|
/* Allow use of chroot() */
|
|
|
|
#define CAP_SYS_CHROOT 18
|
|
|
|
/* Allow ptrace() of any process */
|
|
|
|
#define CAP_SYS_PTRACE 19
|
|
|
|
/* Allow configuration of process accounting */
|
|
|
|
#define CAP_SYS_PACCT 20
|
|
|
|
/* Allow configuration of the secure attention key */
|
|
/* Allow administration of the random device */
|
|
/* Allow examination and configuration of disk quotas */
|
|
/* Allow configuring the kernel's syslog (printk behaviour) */
|
|
/* Allow setting the domainname */
|
|
/* Allow setting the hostname */
|
|
/* Allow calling bdflush() */
|
|
/* Allow mount() and umount(), setting up new smb connection */
|
|
/* Allow some autofs root ioctls */
|
|
/* Allow nfsservctl */
|
|
/* Allow VM86_REQUEST_IRQ */
|
|
/* Allow to read/write pci config on alpha */
|
|
/* Allow irix_prctl on mips (setstacksize) */
|
|
/* Allow flushing all cache on m68k (sys_cacheflush) */
|
|
/* Allow removing semaphores */
|
|
/* Used instead of CAP_CHOWN to "chown" IPC message queues, semaphores
|
|
and shared memory */
|
|
/* Allow locking/unlocking of shared memory segment */
|
|
/* Allow turning swap on/off */
|
|
/* Allow forged pids on socket credentials passing */
|
|
/* Allow setting readahead and flushing buffers on block devices */
|
|
/* Allow setting geometry in floppy driver */
|
|
/* Allow turning DMA on/off in xd driver */
|
|
/* Allow administration of md devices (mostly the above, but some
|
|
extra ioctls) */
|
|
/* Allow tuning the ide driver */
|
|
/* Allow access to the nvram device */
|
|
/* Allow administration of apm_bios, serial and bttv (TV) device */
|
|
/* Allow manufacturer commands in isdn CAPI support driver */
|
|
/* Allow reading non-standardized portions of pci configuration space */
|
|
/* Allow DDI debug ioctl on sbpcd driver */
|
|
/* Allow setting up serial ports */
|
|
/* Allow sending raw qic-117 commands */
|
|
/* Allow enabling/disabling tagged queuing on SCSI controllers and sending
|
|
arbitrary SCSI commands */
|
|
/* Allow setting encryption key on loopback filesystem */
|
|
/* Allow setting zone reclaim policy */
|
|
|
|
#define CAP_SYS_ADMIN 21
|
|
|
|
/* Allow use of reboot() */
|
|
|
|
#define CAP_SYS_BOOT 22
|
|
|
|
/* Allow raising priority and setting priority on other (different
|
|
UID) processes */
|
|
/* Allow use of FIFO and round-robin (realtime) scheduling on own
|
|
processes and setting the scheduling algorithm used by another
|
|
process. */
|
|
/* Allow setting cpu affinity on other processes */
|
|
|
|
#define CAP_SYS_NICE 23
|
|
|
|
/* Override resource limits. Set resource limits. */
|
|
/* Override quota limits. */
|
|
/* Override reserved space on ext2 filesystem */
|
|
/* Modify data journaling mode on ext3 filesystem (uses journaling
|
|
resources) */
|
|
/* NOTE: ext2 honors fsuid when checking for resource overrides, so
|
|
you can override using fsuid too */
|
|
/* Override size restrictions on IPC message queues */
|
|
/* Allow more than 64hz interrupts from the real-time clock */
|
|
/* Override max number of consoles on console allocation */
|
|
/* Override max number of keymaps */
|
|
|
|
#define CAP_SYS_RESOURCE 24
|
|
|
|
/* Allow manipulation of system clock */
|
|
/* Allow irix_stime on mips */
|
|
/* Allow setting the real-time clock */
|
|
|
|
#define CAP_SYS_TIME 25
|
|
|
|
/* Allow configuration of tty devices */
|
|
/* Allow vhangup() of tty */
|
|
|
|
#define CAP_SYS_TTY_CONFIG 26
|
|
|
|
/* Allow the privileged aspects of mknod() */
|
|
|
|
#define CAP_MKNOD 27
|
|
|
|
/* Allow taking of leases on files */
|
|
|
|
#define CAP_LEASE 28
|
|
|
|
#define CAP_AUDIT_WRITE 29
|
|
|
|
#define CAP_AUDIT_CONTROL 30
|
|
|
|
#define CAP_SETFCAP 31
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
/*
|
|
* Internal kernel functions only
|
|
*/
|
|
|
|
#ifdef STRICT_CAP_T_TYPECHECKS
|
|
|
|
#define to_cap_t(x) { x }
|
|
#define cap_t(x) (x).cap
|
|
|
|
#else
|
|
|
|
#define to_cap_t(x) (x)
|
|
#define cap_t(x) (x)
|
|
|
|
#endif
|
|
|
|
#define CAP_EMPTY_SET to_cap_t(0)
|
|
#define CAP_FULL_SET to_cap_t(~0)
|
|
#define CAP_INIT_EFF_SET to_cap_t(~0 & ~CAP_TO_MASK(CAP_SETPCAP))
|
|
#define CAP_INIT_INH_SET to_cap_t(0)
|
|
|
|
#define CAP_TO_MASK(x) (1 << (x))
|
|
#define cap_raise(c, flag) (cap_t(c) |= CAP_TO_MASK(flag))
|
|
#define cap_lower(c, flag) (cap_t(c) &= ~CAP_TO_MASK(flag))
|
|
#define cap_raised(c, flag) (cap_t(c) & CAP_TO_MASK(flag))
|
|
|
|
static inline kernel_cap_t cap_combine(kernel_cap_t a, kernel_cap_t b)
|
|
{
|
|
kernel_cap_t dest;
|
|
cap_t(dest) = cap_t(a) | cap_t(b);
|
|
return dest;
|
|
}
|
|
|
|
static inline kernel_cap_t cap_intersect(kernel_cap_t a, kernel_cap_t b)
|
|
{
|
|
kernel_cap_t dest;
|
|
cap_t(dest) = cap_t(a) & cap_t(b);
|
|
return dest;
|
|
}
|
|
|
|
static inline kernel_cap_t cap_drop(kernel_cap_t a, kernel_cap_t drop)
|
|
{
|
|
kernel_cap_t dest;
|
|
cap_t(dest) = cap_t(a) & ~cap_t(drop);
|
|
return dest;
|
|
}
|
|
|
|
static inline kernel_cap_t cap_invert(kernel_cap_t c)
|
|
{
|
|
kernel_cap_t dest;
|
|
cap_t(dest) = ~cap_t(c);
|
|
return dest;
|
|
}
|
|
|
|
#define cap_isclear(c) (!cap_t(c))
|
|
#define cap_issubset(a,set) (!(cap_t(a) & ~cap_t(set)))
|
|
|
|
#define cap_clear(c) do { cap_t(c) = 0; } while(0)
|
|
#define cap_set_full(c) do { cap_t(c) = ~0; } while(0)
|
|
#define cap_mask(c,mask) do { cap_t(c) &= cap_t(mask); } while(0)
|
|
|
|
#define cap_is_fs_cap(c) (CAP_TO_MASK(c) & CAP_FS_MASK)
|
|
|
|
int capable(int cap);
|
|
int __capable(struct task_struct *t, int cap);
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* !_LINUX_CAPABILITY_H */
|