kernel-ark/include/linux/prctl.h
Serge E. Hallyn 3b7391de67 capabilities: introduce per-process capability bounding set
The capability bounding set is a set beyond which capabilities cannot grow.
 Currently cap_bset is per-system.  It can be manipulated through sysctl,
but only init can add capabilities.  Root can remove capabilities.  By
default it includes all caps except CAP_SETPCAP.

This patch makes the bounding set per-process when file capabilities are
enabled.  It is inherited at fork from parent.  Noone can add elements,
CAP_SETPCAP is required to remove them.

One example use of this is to start a safer container.  For instance, until
device namespaces or per-container device whitelists are introduced, it is
best to take CAP_MKNOD away from a container.

The bounding set will not affect pP and pE immediately.  It will only
affect pP' and pE' after subsequent exec()s.  It also does not affect pI,
and exec() does not constrain pI'.  So to really start a shell with no way
of regain CAP_MKNOD, you would do

	prctl(PR_CAPBSET_DROP, CAP_MKNOD);
	cap_t cap = cap_get_proc();
	cap_value_t caparray[1];
	caparray[0] = CAP_MKNOD;
	cap_set_flag(cap, CAP_INHERITABLE, 1, caparray, CAP_DROP);
	cap_set_proc(cap);
	cap_free(cap);

The following test program will get and set the bounding
set (but not pI).  For instance

	./bset get
		(lists capabilities in bset)
	./bset drop cap_net_raw
		(starts shell with new bset)
		(use capset, setuid binary, or binary with
		file capabilities to try to increase caps)

************************************************************
cap_bound.c
************************************************************
 #include <sys/prctl.h>
 #include <linux/capability.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>

 #ifndef PR_CAPBSET_READ
 #define PR_CAPBSET_READ 23
 #endif

 #ifndef PR_CAPBSET_DROP
 #define PR_CAPBSET_DROP 24
 #endif

int usage(char *me)
{
	printf("Usage: %s get\n", me);
	printf("       %s drop <capability>\n", me);
	return 1;
}

 #define numcaps 32
char *captable[numcaps] = {
	"cap_chown",
	"cap_dac_override",
	"cap_dac_read_search",
	"cap_fowner",
	"cap_fsetid",
	"cap_kill",
	"cap_setgid",
	"cap_setuid",
	"cap_setpcap",
	"cap_linux_immutable",
	"cap_net_bind_service",
	"cap_net_broadcast",
	"cap_net_admin",
	"cap_net_raw",
	"cap_ipc_lock",
	"cap_ipc_owner",
	"cap_sys_module",
	"cap_sys_rawio",
	"cap_sys_chroot",
	"cap_sys_ptrace",
	"cap_sys_pacct",
	"cap_sys_admin",
	"cap_sys_boot",
	"cap_sys_nice",
	"cap_sys_resource",
	"cap_sys_time",
	"cap_sys_tty_config",
	"cap_mknod",
	"cap_lease",
	"cap_audit_write",
	"cap_audit_control",
	"cap_setfcap"
};

int getbcap(void)
{
	int comma=0;
	unsigned long i;
	int ret;

	printf("i know of %d capabilities\n", numcaps);
	printf("capability bounding set:");
	for (i=0; i<numcaps; i++) {
		ret = prctl(PR_CAPBSET_READ, i);
		if (ret < 0)
			perror("prctl");
		else if (ret==1)
			printf("%s%s", (comma++) ? ", " : " ", captable[i]);
	}
	printf("\n");
	return 0;
}

int capdrop(char *str)
{
	unsigned long i;

	int found=0;
	for (i=0; i<numcaps; i++) {
		if (strcmp(captable[i], str) == 0) {
			found=1;
			break;
		}
	}
	if (!found)
		return 1;
	if (prctl(PR_CAPBSET_DROP, i)) {
		perror("prctl");
		return 1;
	}
	return 0;
}

int main(int argc, char *argv[])
{
	if (argc<2)
		return usage(argv[0]);
	if (strcmp(argv[1], "get")==0)
		return getbcap();
	if (strcmp(argv[1], "drop")!=0 || argc<3)
		return usage(argv[0]);
	if (capdrop(argv[2])) {
		printf("unknown capability\n");
		return 1;
	}
	return execl("/bin/bash", "/bin/bash", NULL);
}
************************************************************

[serue@us.ibm.com: fix typo]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew G. Morgan <morgan@kernel.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: James Morris <jmorris@namei.org>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Casey Schaufler <casey@schaufler-ca.com>a
Signed-off-by: "Serge E. Hallyn" <serue@us.ibm.com>
Tested-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 09:44:20 -08:00

71 lines
2.7 KiB
C

#ifndef _LINUX_PRCTL_H
#define _LINUX_PRCTL_H
/* Values to pass as first argument to prctl() */
#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */
#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */
/* Get/set current->mm->dumpable */
#define PR_GET_DUMPABLE 3
#define PR_SET_DUMPABLE 4
/* Get/set unaligned access control bits (if meaningful) */
#define PR_GET_UNALIGN 5
#define PR_SET_UNALIGN 6
# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */
# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */
/* Get/set whether or not to drop capabilities on setuid() away from uid 0 */
#define PR_GET_KEEPCAPS 7
#define PR_SET_KEEPCAPS 8
/* Get/set floating-point emulation control bits (if meaningful) */
#define PR_GET_FPEMU 9
#define PR_SET_FPEMU 10
# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */
# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */
/* Get/set floating-point exception mode (if meaningful) */
#define PR_GET_FPEXC 11
#define PR_SET_FPEXC 12
# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */
# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */
# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */
# define PR_FP_EXC_UND 0x040000 /* floating point underflow */
# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */
# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */
# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */
# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */
# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */
# define PR_FP_EXC_PRECISE 3 /* precise exception mode */
/* Get/set whether we use statistical process timing or accurate timestamp
* based process timing */
#define PR_GET_TIMING 13
#define PR_SET_TIMING 14
# define PR_TIMING_STATISTICAL 0 /* Normal, traditional,
statistical process timing */
# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based
process timing */
#define PR_SET_NAME 15 /* Set process name */
#define PR_GET_NAME 16 /* Get process name */
/* Get/set process endian */
#define PR_GET_ENDIAN 19
#define PR_SET_ENDIAN 20
# define PR_ENDIAN_BIG 0
# define PR_ENDIAN_LITTLE 1 /* True little endian mode */
# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */
/* Get/set process seccomp mode */
#define PR_GET_SECCOMP 21
#define PR_SET_SECCOMP 22
/* Get/set the capability bounding set */
#define PR_CAPBSET_READ 23
#define PR_CAPBSET_DROP 24
#endif /* _LINUX_PRCTL_H */