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>

4 files changed, 13 insertions, 43 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 1160f87..2b55b74 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1118,6 +1118,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_SECURITY
 	p->security = NULL;
 #endif
+	p->cap_bset = current->cap_bset;
 	p->io_context = NULL;
 	p->audit_context = NULL;
 	cgroup_fork(p);
diff --git a/kernel/sys.c b/kernel/sys.c
index d1fe71e..4162d12 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1637,7 +1637,7 @@ asmlinkage long sys_umask(int mask)
 	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
 	return mask;
 }
-    
+
 asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5)
 {
@@ -1742,6 +1742,17 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 			error = prctl_set_seccomp(arg2);
 			break;
 
+		case PR_CAPBSET_READ:
+			if (!cap_valid(arg2))
+				return -EINVAL;
+			return !!cap_raised(current->cap_bset, arg2);
+		case PR_CAPBSET_DROP:
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+			return cap_prctl_drop(arg2);
+#else
+			return -EINVAL;
+#endif
+
 		default:
 			error = -EINVAL;
 			break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index d0b47b8..5e2ad5b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -419,15 +419,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_SECURITY_CAPABILITIES
-	{
-		.procname	= "cap-bound",
-		.data		= &cap_bset,
-		.maxlen		= sizeof(kernel_cap_t),
-		.mode		= 0600,
-		.proc_handler	= &proc_dointvec_bset,
-	},
-#endif /* def CONFIG_SECURITY_CAPABILITIES */
 #ifdef CONFIG_BLK_DEV_INITRD
 	{
 		.ctl_name	= KERN_REALROOTDEV,
@@ -2096,26 +2087,6 @@ static int do_proc_dointvec_bset_conv(int *negp, unsigned long *lvalp,
 	return 0;
 }
 
-#ifdef CONFIG_SECURITY_CAPABILITIES
-/*
- *	init may raise the set.
- */
-
-int proc_dointvec_bset(struct ctl_table *table, int write, struct file *filp,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	int op;
-
-	if (write && !capable(CAP_SYS_MODULE)) {
-		return -EPERM;
-	}
-
-	op = is_global_init(current) ? OP_SET : OP_AND;
-	return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
-				do_proc_dointvec_bset_conv,&op);
-}
-#endif /* def CONFIG_SECURITY_CAPABILITIES */
-
 /*
  *	Taint values can only be increased
  */
@@ -2529,12 +2500,6 @@ int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
 	return -ENOSYS;
 }
 
-int proc_dointvec_bset(struct ctl_table *table, int write, struct file *filp,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return -ENOSYS;
-}
-
 int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index c3206fa..006365b 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -37,10 +37,6 @@ static struct trans_ctl_table trans_kern_table[] = {
 	{ KERN_NODENAME,		"hostname" },
 	{ KERN_DOMAINNAME,		"domainname" },
 
-#ifdef CONFIG_SECURITY_CAPABILITIES
-	{ KERN_CAP_BSET,		"cap-bound" },
-#endif /* def CONFIG_SECURITY_CAPABILITIES */
-
 	{ KERN_PANIC,			"panic" },
 	{ KERN_REALROOTDEV,		"real-root-dev" },
 
@@ -1498,9 +1494,6 @@ int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
 			    (table->strategy == sysctl_ms_jiffies) ||
 			    (table->proc_handler == proc_dostring) ||
 			    (table->proc_handler == proc_dointvec) ||
-#ifdef CONFIG_SECURITY_CAPABILITIES
-			    (table->proc_handler == proc_dointvec_bset) ||
-#endif /* def CONFIG_SECURITY_CAPABILITIES */
 			    (table->proc_handler == proc_dointvec_minmax) ||
 			    (table->proc_handler == proc_dointvec_jiffies) ||
 			    (table->proc_handler == proc_dointvec_userhz_jiffies) ||