aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/sysctl.h
diff options
context:
space:
mode:
authorSerge E. Hallyn <serue@us.ibm.com>2008-02-05 01:29:45 -0500
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2008-02-05 12:44:20 -0500
commit3b7391de67da515c91f48aa371de77cb6cc5c07e (patch)
tree22b9f5d9d1c36b374eb5765219aca3c7e1f23486 /include/linux/sysctl.h
parent46c383cc4530ccc438cb325e92e11eb21dd3d4fc (diff)
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>
Diffstat (limited to 'include/linux/sysctl.h')
-rw-r--r--include/linux/sysctl.h3
1 files changed, 0 insertions, 3 deletions
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index bf4ae4e138f7..571f01d20a86 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -102,7 +102,6 @@ enum
102 KERN_NODENAME=7, 102 KERN_NODENAME=7,
103 KERN_DOMAINNAME=8, 103 KERN_DOMAINNAME=8,
104 104
105 KERN_CAP_BSET=14, /* int: capability bounding set */
106 KERN_PANIC=15, /* int: panic timeout */ 105 KERN_PANIC=15, /* int: panic timeout */
107 KERN_REALROOTDEV=16, /* real root device to mount after initrd */ 106 KERN_REALROOTDEV=16, /* real root device to mount after initrd */
108 107
@@ -965,8 +964,6 @@ extern int proc_dostring(struct ctl_table *, int, struct file *,
965 void __user *, size_t *, loff_t *); 964 void __user *, size_t *, loff_t *);
966extern int proc_dointvec(struct ctl_table *, int, struct file *, 965extern int proc_dointvec(struct ctl_table *, int, struct file *,
967 void __user *, size_t *, loff_t *); 966 void __user *, size_t *, loff_t *);
968extern int proc_dointvec_bset(struct ctl_table *, int, struct file *,
969 void __user *, size_t *, loff_t *);
970extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *, 967extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *,
971 void __user *, size_t *, loff_t *); 968 void __user *, size_t *, loff_t *);
972extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *, 969extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *,