userns: security: make capabilities relative to the user namespace

- Introduce ns_capable to test for a capability in a non-default
  user namespace.
- Teach cap_capable to handle capabilities in a non-default
  user namespace.

The motivation is to get to the unprivileged creation of new
namespaces.  It looks like this gets us 90% of the way there, with
only potential uid confusion issues left.

I still need to handle getting all caps after creation but otherwise I
think I have a good starter patch that achieves all of your goals.

Changelog:
	11/05/2010: [serge] add apparmor
	12/14/2010: [serge] fix capabilities to created user namespaces
	Without this, if user serge creates a user_ns, he won't have
	capabilities to the user_ns he created.  THis is because we
	were first checking whether his effective caps had the caps
	he needed and returning -EPERM if not, and THEN checking whether
	he was the creator.  Reverse those checks.
	12/16/2010: [serge] security_real_capable needs ns argument in !security case
	01/11/2011: [serge] add task_ns_capable helper
	01/11/2011: [serge] add nsown_capable() helper per Bastian Blank suggestion
	02/16/2011: [serge] fix a logic bug: the root user is always creator of
		    init_user_ns, but should not always have capabilities to
		    it!  Fix the check in cap_capable().
	02/21/2011: Add the required user_ns parameter to security_capable,
		    fixing a compile failure.
	02/23/2011: Convert some macros to functions as per akpm comments.  Some
		    couldn't be converted because we can't easily forward-declare
		    them (they are inline if !SECURITY, extern if SECURITY).  Add
		    a current_user_ns function so we can use it in capability.h
		    without #including cred.h.  Move all forward declarations
		    together to the top of the #ifdef __KERNEL__ section, and use
		    kernel-doc format.
	02/23/2011: Per dhowells, clean up comment in cap_capable().
	02/23/2011: Per akpm, remove unreachable 'return -EPERM' in cap_capable.

(Original written and signed off by Eric;  latest, modified version
acked by him)

[[email protected]: fix build]
[[email protected]: export current_user_ns() for ecryptfs]
[[email protected]: remove unneeded extra argument in selinux's task_has_capability]
Signed-off-by: Eric W. Biederman <[email protected]>
Signed-off-by: Serge E. Hallyn <[email protected]>
Acked-by: "Eric W. Biederman" <[email protected]>
Acked-by: Daniel Lezcano <[email protected]>
Acked-by: David Howells <[email protected]>
Cc: James Morris <[email protected]>
Signed-off-by: Serge E. Hallyn <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

security/apparmor/lsm.c

@@ -22,6 +22,7 @@
 #include <linux/ctype.h>
 #include <linux/sysctl.h>
 #include <linux/audit.h>
+#include <linux/user_namespace.h>
 #include <net/sock.h>
 
 #include "include/apparmor.h"
@@ -136,11 +137,11 @@ static int apparmor_capget(struct task_struct *target, kernel_cap_t *effective,
 }
 
 static int apparmor_capable(struct task_struct *task, const struct cred *cred,
-			    int cap, int audit)
+			    struct user_namespace *ns, int cap, int audit)
 {
 	struct aa_profile *profile;
 	/* cap_capable returns 0 on success, else -EPERM */
-	int error = cap_capable(task, cred, cap, audit);
+	int error = cap_capable(task, cred, ns, cap, audit);
 	if (!error) {
 		profile = aa_cred_profile(cred);
 		if (!unconfined(profile))

security/commoncap.c

@@ -27,6 +27,7 @@
 #include <linux/sched.h>
 #include <linux/prctl.h>
 #include <linux/securebits.h>
+#include <linux/user_namespace.h>
 
 /*
  * If a non-root user executes a setuid-root binary in
@@ -67,6 +68,7 @@ EXPORT_SYMBOL(cap_netlink_recv);
  * cap_capable - Determine whether a task has a particular effective capability
  * @tsk: The task to query
  * @cred: The credentials to use
+ * @ns:  The user namespace in which we need the capability
  * @cap: The capability to check for
  * @audit: Whether to write an audit message or not
  *
@@ -78,10 +80,30 @@ EXPORT_SYMBOL(cap_netlink_recv);
  * cap_has_capability() returns 0 when a task has a capability, but the
  * kernel's capable() and has_capability() returns 1 for this case.
  */
-int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
-		int audit)
+int cap_capable(struct task_struct *tsk, const struct cred *cred,
+		struct user_namespace *targ_ns, int cap, int audit)
 {
-	return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+	for (;;) {
+		/* The creator of the user namespace has all caps. */
+		if (targ_ns != &init_user_ns && targ_ns->creator == cred->user)
+			return 0;
+
+		/* Do we have the necessary capabilities? */
+		if (targ_ns == cred->user->user_ns)
+			return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+
+		/* Have we tried all of the parent namespaces? */
+		if (targ_ns == &init_user_ns)
+			return -EPERM;
+
+		/*
+		 *If you have a capability in a parent user ns, then you have
+		 * it over all children user namespaces as well.
+		 */
+		targ_ns = targ_ns->creator->user_ns;
+	}
+
+	/* We never get here */
 }
 
 /**
@@ -176,7 +198,8 @@ static inline int cap_inh_is_capped(void)
 	/* they are so limited unless the current task has the CAP_SETPCAP
 	 * capability
 	 */
-	if (cap_capable(current, current_cred(), CAP_SETPCAP,
+	if (cap_capable(current, current_cred(),
+			current_cred()->user->user_ns, CAP_SETPCAP,
 			SECURITY_CAP_AUDIT) == 0)
 		return 0;
 	return 1;
@@ -828,7 +851,8 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 		     & (new->securebits ^ arg2))			/*[1]*/
 		    || ((new->securebits & SECURE_ALL_LOCKS & ~arg2))	/*[2]*/
 		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS))	/*[3]*/
-		    || (cap_capable(current, current_cred(), CAP_SETPCAP,
+		    || (cap_capable(current, current_cred(),
+				    current_cred()->user->user_ns, CAP_SETPCAP,
 				    SECURITY_CAP_AUDIT) != 0)		/*[4]*/
 			/*
 			 * [1] no changing of bits that are locked
@@ -893,7 +917,7 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages)
 {
 	int cap_sys_admin = 0;
 
-	if (cap_capable(current, current_cred(), CAP_SYS_ADMIN,
+	if (cap_capable(current, current_cred(), &init_user_ns, CAP_SYS_ADMIN,
 			SECURITY_CAP_NOAUDIT) == 0)
 		cap_sys_admin = 1;
 	return __vm_enough_memory(mm, pages, cap_sys_admin);
@@ -920,7 +944,7 @@ int cap_file_mmap(struct file *file, unsigned long reqprot,
 	int ret = 0;
 
 	if (addr < dac_mmap_min_addr) {
-		ret = cap_capable(current, current_cred(), CAP_SYS_RAWIO,
+		ret = cap_capable(current, current_cred(), &init_user_ns, CAP_SYS_RAWIO,
 				  SECURITY_CAP_AUDIT);
 		/* set PF_SUPERPRIV if it turns out we allow the low mmap */
 		if (ret == 0)

security/security.c

@@ -154,29 +154,33 @@ int security_capset(struct cred *new, const struct cred *old,
 				    effective, inheritable, permitted);
 }
 
-int security_capable(const struct cred *cred, int cap)
+int security_capable(struct user_namespace *ns, const struct cred *cred,
+		     int cap)
 {
-	return security_ops->capable(current, cred, cap, SECURITY_CAP_AUDIT);
+	return security_ops->capable(current, cred, ns, cap,
+				     SECURITY_CAP_AUDIT);
 }
 
-int security_real_capable(struct task_struct *tsk, int cap)
+int security_real_capable(struct task_struct *tsk, struct user_namespace *ns,
+			  int cap)
 {
 	const struct cred *cred;
 	int ret;
 
 	cred = get_task_cred(tsk);
-	ret = security_ops->capable(tsk, cred, cap, SECURITY_CAP_AUDIT);
+	ret = security_ops->capable(tsk, cred, ns, cap, SECURITY_CAP_AUDIT);
 	put_cred(cred);
 	return ret;
 }
 
-int security_real_capable_noaudit(struct task_struct *tsk, int cap)
+int security_real_capable_noaudit(struct task_struct *tsk,
+				  struct user_namespace *ns, int cap)
 {
 	const struct cred *cred;
 	int ret;
 
 	cred = get_task_cred(tsk);
-	ret = security_ops->capable(tsk, cred, cap, SECURITY_CAP_NOAUDIT);
+	ret = security_ops->capable(tsk, cred, ns, cap, SECURITY_CAP_NOAUDIT);
 	put_cred(cred);
 	return ret;
 }

security/selinux/hooks.c

@@ -79,6 +79,7 @@
 #include <linux/mutex.h>
 #include <linux/posix-timers.h>
 #include <linux/syslog.h>
+#include <linux/user_namespace.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -1846,11 +1847,11 @@ static int selinux_capset(struct cred *new, const struct cred *old,
  */
 
 static int selinux_capable(struct task_struct *tsk, const struct cred *cred,
-			   int cap, int audit)
+			   struct user_namespace *ns, int cap, int audit)
 {
 	int rc;
 
-	rc = cap_capable(tsk, cred, cap, audit);
+	rc = cap_capable(tsk, cred, ns, cap, audit);
 	if (rc)
 		return rc;
 
@@ -1931,7 +1932,8 @@ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
 {
 	int rc, cap_sys_admin = 0;
 
-	rc = selinux_capable(current, current_cred(), CAP_SYS_ADMIN,
+	rc = selinux_capable(current, current_cred(),
+			     &init_user_ns, CAP_SYS_ADMIN,
 			     SECURITY_CAP_NOAUDIT);
 	if (rc == 0)
 		cap_sys_admin = 1;
@@ -2834,7 +2836,8 @@ static int selinux_inode_getsecurity(const struct inode *inode, const char *name
 	 * and lack of permission just means that we fall back to the
 	 * in-core context value, not a denial.
 	 */
-	error = selinux_capable(current, current_cred(), CAP_MAC_ADMIN,
+	error = selinux_capable(current, current_cred(),
+				&init_user_ns, CAP_MAC_ADMIN,
 				SECURITY_CAP_NOAUDIT);
 	if (!error)
 		error = security_sid_to_context_force(isec->sid, &context,
@@ -2968,7 +2971,7 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	case KDSKBENT:
 	case KDSKBSENT:
 		error = task_has_capability(current, cred, CAP_SYS_TTY_CONFIG,
-					    SECURITY_CAP_AUDIT);
+					SECURITY_CAP_AUDIT);
 		break;
 
 	/* default case assumes that the command will go