alistair23-linux/include/linux/capability.h
Adrian Reber 124ea650d3 capabilities: Introduce CAP_CHECKPOINT_RESTORE
This patch introduces CAP_CHECKPOINT_RESTORE, a new capability facilitating
checkpoint/restore for non-root users.

Over the last years, The CRIU (Checkpoint/Restore In Userspace) team has
been asked numerous times if it is possible to checkpoint/restore a
process as non-root. The answer usually was: 'almost'.

The main blocker to restore a process as non-root was to control the PID
of the restored process. This feature available via the clone3 system
call, or via /proc/sys/kernel/ns_last_pid is unfortunately guarded by
CAP_SYS_ADMIN.

In the past two years, requests for non-root checkpoint/restore have
increased due to the following use cases:
* Checkpoint/Restore in an HPC environment in combination with a
  resource manager distributing jobs where users are always running as
  non-root. There is a desire to provide a way to checkpoint and
  restore long running jobs.
* Container migration as non-root
* We have been in contact with JVM developers who are integrating
  CRIU into a Java VM to decrease the startup time. These
  checkpoint/restore applications are not meant to be running with
  CAP_SYS_ADMIN.

We have seen the following workarounds:
* Use a setuid wrapper around CRIU:
  See https://github.com/FredHutch/slurm-examples/blob/master/checkpointer/lib/checkpointer/checkpointer-suid.c
* Use a setuid helper that writes to ns_last_pid.
  Unfortunately, this helper delegation technique is impossible to use
  with clone3, and is thus prone to races.
  See https://github.com/twosigma/set_ns_last_pid
* Cycle through PIDs with fork() until the desired PID is reached:
  This has been demonstrated to work with cycling rates of 100,000 PIDs/s
  See https://github.com/twosigma/set_ns_last_pid
* Patch out the CAP_SYS_ADMIN check from the kernel
* Run the desired application in a new user and PID namespace to provide
  a local CAP_SYS_ADMIN for controlling PIDs. This technique has limited
  use in typical container environments (e.g., Kubernetes) as /proc is
  typically protected with read-only layers (e.g., /proc/sys) for
  hardening purposes. Read-only layers prevent additional /proc mounts
  (due to proc's SB_I_USERNS_VISIBLE property), making the use of new
  PID namespaces limited as certain applications need access to /proc
  matching their PID namespace.

The introduced capability allows to:
* Control PIDs when the current user is CAP_CHECKPOINT_RESTORE capable
  for the corresponding PID namespace via ns_last_pid/clone3.
* Open files in /proc/pid/map_files when the current user is
  CAP_CHECKPOINT_RESTORE capable in the root namespace, useful for
  recovering files that are unreachable via the file system such as
  deleted files, or memfd files.

See corresponding selftest for an example with clone3().

Signed-off-by: Adrian Reber <areber@redhat.com>
Signed-off-by: Nicolas Viennot <Nicolas.Viennot@twosigma.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20200719100418.2112740-2-areber@redhat.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2020-07-19 20:14:42 +02:00

276 lines
8.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* 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>
#include <linux/uidgid.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;
/* same as vfs_ns_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;
kuid_t rootid;
};
#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 task_struct;
struct user_namespace;
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 bool cap_isclear(const kernel_cap_t a)
{
unsigned __capi;
CAP_FOR_EACH_U32(__capi) {
if (a.cap[__capi] != 0)
return false;
}
return true;
}
/*
* Check if "a" is a subset of "set".
* return true if ALL of the capabilities in "a" are also in "set"
* cap_issubset(0101, 1111) will return true
* return false if ANY of the capabilities in "a" are not in "set"
* cap_issubset(1111, 0101) will return false
*/
static inline bool 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 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));
}
#ifdef CONFIG_MULTIUSER
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 ns_capable_noaudit(struct user_namespace *ns, int cap);
extern bool ns_capable_setid(struct user_namespace *ns, int cap);
#else
static inline bool has_capability(struct task_struct *t, int cap)
{
return true;
}
static inline bool has_ns_capability(struct task_struct *t,
struct user_namespace *ns, int cap)
{
return true;
}
static inline bool has_capability_noaudit(struct task_struct *t, int cap)
{
return true;
}
static inline bool has_ns_capability_noaudit(struct task_struct *t,
struct user_namespace *ns, int cap)
{
return true;
}
static inline bool capable(int cap)
{
return true;
}
static inline bool ns_capable(struct user_namespace *ns, int cap)
{
return true;
}
static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap)
{
return true;
}
static inline bool ns_capable_setid(struct user_namespace *ns, int cap)
{
return true;
}
#endif /* CONFIG_MULTIUSER */
extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode);
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);
extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
static inline bool perfmon_capable(void)
{
return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN);
}
static inline bool bpf_capable(void)
{
return capable(CAP_BPF) || capable(CAP_SYS_ADMIN);
}
static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns)
{
return ns_capable(ns, CAP_CHECKPOINT_RESTORE) ||
ns_capable(ns, CAP_SYS_ADMIN);
}
/* 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);
extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size);
#endif /* !_LINUX_CAPABILITY_H */