mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 19:15:04 +07:00
8db6c34f1d
Root in a non-initial user ns cannot be trusted to write a traditional
security.capability xattr. If it were allowed to do so, then any
unprivileged user on the host could map his own uid to root in a private
namespace, write the xattr, and execute the file with privilege on the
host.
However supporting file capabilities in a user namespace is very
desirable. Not doing so means that any programs designed to run with
limited privilege must continue to support other methods of gaining and
dropping privilege. For instance a program installer must detect
whether file capabilities can be assigned, and assign them if so but set
setuid-root otherwise. The program in turn must know how to drop
partial capabilities, and do so only if setuid-root.
This patch introduces v3 of the security.capability xattr. It builds a
vfs_ns_cap_data struct by appending a uid_t rootid to struct
vfs_cap_data. This is the absolute uid_t (that is, the uid_t in user
namespace which mounted the filesystem, usually init_user_ns) of the
root id in whose namespaces the file capabilities may take effect.
When a task asks to write a v2 security.capability xattr, if it is
privileged with respect to the userns which mounted the filesystem, then
nothing should change. Otherwise, the kernel will transparently rewrite
the xattr as a v3 with the appropriate rootid. This is done during the
execution of setxattr() to catch user-space-initiated capability writes.
Subsequently, any task executing the file which has the noted kuid as
its root uid, or which is in a descendent user_ns of such a user_ns,
will run the file with capabilities.
Similarly when asking to read file capabilities, a v3 capability will
be presented as v2 if it applies to the caller's namespace.
If a task writes a v3 security.capability, then it can provide a uid for
the xattr so long as the uid is valid in its own user namespace, and it
is privileged with CAP_SETFCAP over its namespace. The kernel will
translate that rootid to an absolute uid, and write that to disk. After
this, a task in the writer's namespace will not be able to use those
capabilities (unless rootid was 0), but a task in a namespace where the
given uid is root will.
Only a single security.capability xattr may exist at a time for a given
file. A task may overwrite an existing xattr so long as it is
privileged over the inode. Note this is a departure from previous
semantics, which required privilege to remove a security.capability
xattr. This check can be re-added if deemed useful.
This allows a simple setxattr to work, allows tar/untar to work, and
allows us to tar in one namespace and untar in another while preserving
the capability, without risking leaking privilege into a parent
namespace.
Example using tar:
$ cp /bin/sleep sleepx
$ mkdir b1 b2
$ lxc-usernsexec -m b:0:100000:1 -m b:1:$(id -u):1 -- chown 0:0 b1
$ lxc-usernsexec -m b:0:100001:1 -m b:1:$(id -u):1 -- chown 0:0 b2
$ lxc-usernsexec -m b:0:100000:1000 -- tar --xattrs-include=security.capability --xattrs -cf b1/sleepx.tar sleepx
$ lxc-usernsexec -m b:0:100001:1000 -- tar --xattrs-include=security.capability --xattrs -C b2 -xf b1/sleepx.tar
$ lxc-usernsexec -m b:0:100001:1000 -- getcap b2/sleepx
b2/sleepx = cap_sys_admin+ep
# /opt/ltp/testcases/bin/getv3xattr b2/sleepx
v3 xattr, rootid is 100001
A patch to linux-test-project adding a new set of tests for this
functionality is in the nsfscaps branch at github.com/hallyn/ltp
Changelog:
Nov 02 2016: fix invalid check at refuse_fcap_overwrite()
Nov 07 2016: convert rootid from and to fs user_ns
(From ebiederm: mar 28 2017)
commoncap.c: fix typos - s/v4/v3
get_vfs_caps_from_disk: clarify the fs_ns root access check
nsfscaps: change the code split for cap_inode_setxattr()
Apr 09 2017:
don't return v3 cap for caps owned by current root.
return a v2 cap for a true v2 cap in non-init ns
Apr 18 2017:
. Change the flow of fscap writing to support s_user_ns writing.
. Remove refuse_fcap_overwrite(). The value of the previous
xattr doesn't matter.
Apr 24 2017:
. incorporate Eric's incremental diff
. move cap_convert_nscap to setxattr and simplify its usage
May 8, 2017:
. fix leaking dentry refcount in cap_inode_getsecurity
Signed-off-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
382 lines
12 KiB
C
382 lines
12 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 _UAPI_LINUX_CAPABILITY_H
|
|
#define _UAPI_LINUX_CAPABILITY_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
/* 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. */
|
|
|
|
/* Note, cap_t, is defined by POSIX (draft) 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_1 0x19980330
|
|
#define _LINUX_CAPABILITY_U32S_1 1
|
|
|
|
#define _LINUX_CAPABILITY_VERSION_2 0x20071026 /* deprecated - use v3 */
|
|
#define _LINUX_CAPABILITY_U32S_2 2
|
|
|
|
#define _LINUX_CAPABILITY_VERSION_3 0x20080522
|
|
#define _LINUX_CAPABILITY_U32S_3 2
|
|
|
|
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 VFS_CAP_REVISION_MASK 0xFF000000
|
|
#define VFS_CAP_REVISION_SHIFT 24
|
|
#define VFS_CAP_FLAGS_MASK ~VFS_CAP_REVISION_MASK
|
|
#define VFS_CAP_FLAGS_EFFECTIVE 0x000001
|
|
|
|
#define VFS_CAP_REVISION_1 0x01000000
|
|
#define VFS_CAP_U32_1 1
|
|
#define XATTR_CAPS_SZ_1 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_1))
|
|
|
|
#define VFS_CAP_REVISION_2 0x02000000
|
|
#define VFS_CAP_U32_2 2
|
|
#define XATTR_CAPS_SZ_2 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2))
|
|
|
|
#define VFS_CAP_REVISION_3 0x03000000
|
|
#define VFS_CAP_U32_3 2
|
|
#define XATTR_CAPS_SZ_3 (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3))
|
|
|
|
#define XATTR_CAPS_SZ XATTR_CAPS_SZ_3
|
|
#define VFS_CAP_U32 VFS_CAP_U32_3
|
|
#define VFS_CAP_REVISION VFS_CAP_REVISION_3
|
|
|
|
struct vfs_cap_data {
|
|
__le32 magic_etc; /* Little endian */
|
|
struct {
|
|
__le32 permitted; /* Little endian */
|
|
__le32 inheritable; /* Little endian */
|
|
} data[VFS_CAP_U32];
|
|
};
|
|
|
|
/*
|
|
* same as vfs_cap_data but with a rootid at the end
|
|
*/
|
|
struct vfs_ns_cap_data {
|
|
__le32 magic_etc;
|
|
struct {
|
|
__le32 permitted; /* Little endian */
|
|
__le32 inheritable; /* Little endian */
|
|
} data[VFS_CAP_U32];
|
|
__le32 rootid;
|
|
};
|
|
|
|
#ifndef __KERNEL__
|
|
|
|
/*
|
|
* Backwardly compatible definition for source code - trapped in a
|
|
* 32-bit world. If you find you need this, please consider using
|
|
* libcap to untrap yourself...
|
|
*/
|
|
#define _LINUX_CAPABILITY_VERSION _LINUX_CAPABILITY_VERSION_1
|
|
#define _LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_1
|
|
|
|
#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
|
|
|
|
/* 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
|
|
**/
|
|
|
|
/* Without VFS support for capabilities:
|
|
* Transfer any capability in your permitted set to any pid,
|
|
* remove any capability in your permitted set from any pid
|
|
* With VFS support for capabilities (neither of above, but)
|
|
* Add any capability from current's capability bounding set
|
|
* to the current process' inheritable set
|
|
* Allow taking bits out of capability bounding set
|
|
* Allow modification of the securebits for a process
|
|
*/
|
|
|
|
#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 (also via NET_RAW) */
|
|
/* 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 */
|
|
/* Allow binding to any address for transparent proxying (also via NET_ADMIN) */
|
|
|
|
#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 */
|
|
#define CAP_SYS_MODULE 16
|
|
|
|
/* Allow ioperm/iopl access */
|
|
/* Allow sending USB messages to any device via /dev/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 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
|
|
|
|
/* Allow writing the audit log via unicast netlink socket */
|
|
|
|
#define CAP_AUDIT_WRITE 29
|
|
|
|
/* Allow configuration of audit via unicast netlink socket */
|
|
|
|
#define CAP_AUDIT_CONTROL 30
|
|
|
|
#define CAP_SETFCAP 31
|
|
|
|
/* Override MAC access.
|
|
The base kernel enforces no MAC policy.
|
|
An LSM may enforce a MAC policy, and if it does and it chooses
|
|
to implement capability based overrides of that policy, this is
|
|
the capability it should use to do so. */
|
|
|
|
#define CAP_MAC_OVERRIDE 32
|
|
|
|
/* Allow MAC configuration or state changes.
|
|
The base kernel requires no MAC configuration.
|
|
An LSM may enforce a MAC policy, and if it does and it chooses
|
|
to implement capability based checks on modifications to that
|
|
policy or the data required to maintain it, this is the
|
|
capability it should use to do so. */
|
|
|
|
#define CAP_MAC_ADMIN 33
|
|
|
|
/* Allow configuring the kernel's syslog (printk behaviour) */
|
|
|
|
#define CAP_SYSLOG 34
|
|
|
|
/* Allow triggering something that will wake the system */
|
|
|
|
#define CAP_WAKE_ALARM 35
|
|
|
|
/* Allow preventing system suspends */
|
|
|
|
#define CAP_BLOCK_SUSPEND 36
|
|
|
|
/* Allow reading the audit log via multicast netlink socket */
|
|
|
|
#define CAP_AUDIT_READ 37
|
|
|
|
|
|
#define CAP_LAST_CAP CAP_AUDIT_READ
|
|
|
|
#define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
|
|
|
|
/*
|
|
* Bit location of each capability (used by user-space library and kernel)
|
|
*/
|
|
|
|
#define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */
|
|
#define CAP_TO_MASK(x) (1 << ((x) & 31)) /* mask for indexed __u32 */
|
|
|
|
|
|
#endif /* _UAPI_LINUX_CAPABILITY_H */
|