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>

6 files changed, 27 insertions, 11 deletions

diff --git a/include/linux/capability.h b/include/linux/capability.h
index a1d93da..ffe7bab8 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -152,7 +152,9 @@ typedef struct kernel_cap_struct {
  *   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 to the current process' inheritable set
+ *   Add any capability from current's capability bounding set
+ *       to the current process' inheritable set
+ *   Allow taking bits out of capability bounding set
  */
 
 #define CAP_SETPCAP          8
@@ -202,7 +204,6 @@ typedef struct kernel_cap_struct {
 #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 */
@@ -314,6 +315,10 @@ typedef struct kernel_cap_struct {
 
 #define CAP_SETFCAP	     31
 
+#define CAP_LAST_CAP         CAP_SETFCAP
+
+#define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
+
 /*
  * Bit location of each capability (used by user-space library and kernel)
  */
@@ -465,6 +470,8 @@ extern const kernel_cap_t __cap_init_eff_set;
 int capable(int cap);
 int __capable(struct task_struct *t, int cap);
 
+extern long cap_prctl_drop(unsigned long cap);
+
 #endif /* __KERNEL__ */
 
 #endif /* !_LINUX_CAPABILITY_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f42663e..1f74e1d 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -121,6 +121,18 @@ extern struct group_info init_groups;
 #else
 #define INIT_IDS
 #endif
+
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+/*
+ * Because of the reduced scope of CAP_SETPCAP when filesystem
+ * capabilities are in effect, it is safe to allow CAP_SETPCAP to
+ * be available in the default configuration.
+ */
+# define CAP_INIT_BSET  CAP_FULL_SET
+#else
+# define CAP_INIT_BSET  CAP_INIT_EFF_SET
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -156,6 +168,7 @@ extern struct group_info init_groups;
 	.cap_effective	= CAP_INIT_EFF_SET,				\
 	.cap_inheritable = CAP_INIT_INH_SET,				\
 	.cap_permitted	= CAP_FULL_SET,					\
+	.cap_bset 	= CAP_INIT_BSET,				\
 	.keep_capabilities = 0,						\
 	.user		= INIT_USER,					\
 	.comm		= "swapper",					\
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index e2eff90..3800639 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -63,4 +63,8 @@
 #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 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c30d174..9c13be3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1098,7 +1098,7 @@ struct task_struct {
 	uid_t uid,euid,suid,fsuid;
 	gid_t gid,egid,sgid,fsgid;
 	struct group_info *group_info;
-	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted;
+	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted, cap_bset;
 	unsigned keep_capabilities:1;
 	struct user_struct *user;
 #ifdef CONFIG_KEYS
diff --git a/include/linux/security.h b/include/linux/security.h
index 9d289e7..fe52cde 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -40,11 +40,6 @@
 #define ROOTCONTEXT_MNT		0x04
 #define DEFCONTEXT_MNT		0x08
 
-/*
- * Bounding set
- */
-extern kernel_cap_t cap_bset;
-
 extern unsigned securebits;
 
 struct ctl_table;
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index bf4ae4e..571f01d 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -102,7 +102,6 @@ enum
 	KERN_NODENAME=7,
 	KERN_DOMAINNAME=8,
 
-	KERN_CAP_BSET=14,	/* int: capability bounding set */
 	KERN_PANIC=15,		/* int: panic timeout */
 	KERN_REALROOTDEV=16,	/* real root device to mount after initrd */
 
@@ -965,8 +964,6 @@ extern int proc_dostring(struct ctl_table *, int, struct file *,
 			 void __user *, size_t *, loff_t *);
 extern int proc_dointvec(struct ctl_table *, int, struct file *,
 			 void __user *, size_t *, loff_t *);
-extern int proc_dointvec_bset(struct ctl_table *, int, struct file *,
-			      void __user *, size_t *, loff_t *);
 extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *,
 				void __user *, size_t *, loff_t *);
 extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *,