UPSTREAM: capabilities: ambient capabilities

fs/proc/array.c

@@ -312,20 +312,23 @@ static void render_cap_t(struct seq_file *m, const char *header,
 static inline void task_cap(struct seq_file *m, struct task_struct *p)
 {
 	const struct cred *cred;
-	kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset;
+	kernel_cap_t cap_inheritable, cap_permitted, cap_effective,
+			cap_bset, cap_ambient;
 
 	rcu_read_lock();
 	cred = __task_cred(p);
 	cap_inheritable	= cred->cap_inheritable;
 	cap_permitted	= cred->cap_permitted;
 	cap_effective	= cred->cap_effective;
 	cap_bset	= cred->cap_bset;
+	cap_ambient	= cred->cap_ambient;
 	rcu_read_unlock();
 
 	render_cap_t(m, "CapInh:\t", &cap_inheritable);
 	render_cap_t(m, "CapPrm:\t", &cap_permitted);
 	render_cap_t(m, "CapEff:\t", &cap_effective);
 	render_cap_t(m, "CapBnd:\t", &cap_bset);
+	render_cap_t(m, "CapAmb:\t", &cap_ambient);
 }
 
 static inline void task_seccomp(struct seq_file *m, struct task_struct *p)

include/linux/cred.h

@@ -122,6 +122,7 @@ struct cred {
 	kernel_cap_t	cap_permitted;	/* caps we're permitted */
 	kernel_cap_t	cap_effective;	/* caps we can actually use */
 	kernel_cap_t	cap_bset;	/* capability bounding set */
+	kernel_cap_t	cap_ambient;	/* Ambient capability set */
 #ifdef CONFIG_KEYS
 	unsigned char	jit_keyring;	/* default keyring to attach requested
 					 * keys to */
@@ -197,6 +198,13 @@ static inline void validate_process_creds(void)
 }
 #endif
 
+static inline bool cap_ambient_invariant_ok(const struct cred *cred)
+{
+	return cap_issubset(cred->cap_ambient,
+			    cap_intersect(cred->cap_permitted,
+					  cred->cap_inheritable));
+}
+
 /**
  * get_new_cred - Get a reference on a new set of credentials
  * @cred: The new credentials to reference

include/uapi/linux/prctl.h

@@ -158,4 +158,11 @@
 #define PR_SET_VMA		0x53564d41
 # define PR_SET_VMA_ANON_NAME		0
 
+/* Control the ambient capability set */
+#define PR_CAP_AMBIENT			47
+# define PR_CAP_AMBIENT_IS_SET		1
+# define PR_CAP_AMBIENT_RAISE		2
+# define PR_CAP_AMBIENT_LOWER		3
+# define PR_CAP_AMBIENT_CLEAR_ALL	4
+
 #endif /* _LINUX_PRCTL_H */

kernel/user_namespace.c

@@ -39,6 +39,7 @@ static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
 	cred->cap_inheritable = CAP_EMPTY_SET;
 	cred->cap_permitted = CAP_FULL_SET;
 	cred->cap_effective = CAP_FULL_SET;
+	cred->cap_ambient = CAP_EMPTY_SET;
 	cred->cap_bset = CAP_FULL_SET;
 #ifdef CONFIG_KEYS
 	key_put(cred->request_key_auth);

security/commoncap.c

@@ -300,6 +300,16 @@ int cap_capset(struct cred *new,
 	new->cap_effective   = *effective;
 	new->cap_inheritable = *inheritable;
 	new->cap_permitted   = *permitted;
+
+	/*
+	 * Mask off ambient bits that are no longer both permitted and
+	 * inheritable.
+	 */
+	new->cap_ambient = cap_intersect(new->cap_ambient,
+					 cap_intersect(*permitted,
+						       *inheritable));
+	if (WARN_ON(!cap_ambient_invariant_ok(new)))
+		return -EINVAL;
 	return 0;
 }
 
@@ -380,6 +390,7 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 
 		/*
 		 * pP' = (X & fP) | (pI & fI)
+		 * The addition of pA' is handled later.
 		 */
 		new->cap_permitted.cap[i] =
 			(new->cap_bset.cap[i] & permitted) |
@@ -511,10 +522,13 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 {
 	const struct cred *old = current_cred();
 	struct cred *new = bprm->cred;
-	bool effective, has_cap = false;
+	bool effective, has_cap = false, is_setid;
 	int ret;
 	kuid_t root_uid;
 
+	if (WARN_ON(!cap_ambient_invariant_ok(old)))
+		return -EPERM;
+
 	effective = false;
 	ret = get_file_caps(bprm, &effective, &has_cap);
 	if (ret < 0)
@@ -559,8 +573,9 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	 *
 	 * In addition, if NO_NEW_PRIVS, then ensure we get no new privs.
 	 */
-	if ((!uid_eq(new->euid, old->uid) ||
-	     !gid_eq(new->egid, old->gid) ||
+	is_setid = !uid_eq(new->euid, old->uid) || !gid_eq(new->egid, old->gid);
+
+	if ((is_setid ||
 	     !cap_issubset(new->cap_permitted, old->cap_permitted)) &&
 	    bprm->unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
 		/* downgrade; they get no more than they had, and maybe less */
@@ -575,11 +590,30 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 
 	new->suid = new->fsuid = new->euid;
 	new->sgid = new->fsgid = new->egid;
+
+	/* File caps or setid cancels ambient. */
+	if (has_cap || is_setid)
+		cap_clear(new->cap_ambient);
+
+	/*
+	 * Now that we've computed pA', update pP' to give:
+	 *   pP' = (X & fP) | (pI & fI) | pA'
+	 */
+	new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient);
+
+	/*
+	 * Set pE' = (fE ? pP' : pA').  Because pA' is zero if fE is set,
+	 * this is the same as pE' = (fE ? pP' : 0) | pA'.
+	 */
 
 	if (effective)
 		new->cap_effective = new->cap_permitted;
 	else
-		cap_clear(new->cap_effective);
+		new->cap_effective = new->cap_ambient;
+
+	if (WARN_ON(!cap_ambient_invariant_ok(new)))
+		return -EPERM;
+
 	bprm->cap_effective = effective;
 
 	/*
@@ -594,7 +628,7 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	 * Number 1 above might fail if you don't have a full bset, but I think
 	 * that is interesting information to audit.
 	 */
-	if (!cap_isclear(new->cap_effective)) {
+	if (!cap_issubset(new->cap_effective, new->cap_ambient)) {
 		if (!cap_issubset(CAP_FULL_SET, new->cap_effective) ||
 		    !uid_eq(new->euid, root_uid) || !uid_eq(new->uid, root_uid) ||
 		    issecure(SECURE_NOROOT)) {
@@ -605,6 +639,10 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 	}
 
 	new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+
+	if (WARN_ON(!cap_ambient_invariant_ok(new)))
+		return -EPERM;
+
 	return 0;
 }
 
@@ -626,7 +664,7 @@ int cap_bprm_secureexec(struct linux_binprm *bprm)
 	if (!uid_eq(cred->uid, root_uid)) {
 		if (bprm->cap_effective)
 			return 1;
-		if (!cap_isclear(cred->cap_permitted))
+		if (!cap_issubset(cred->cap_permitted, cred->cap_ambient))
 			return 1;
 	}
 
@@ -728,10 +766,18 @@ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old)
 	     uid_eq(old->suid, root_uid)) &&
 	    (!uid_eq(new->uid, root_uid) &&
 	     !uid_eq(new->euid, root_uid) &&
-	     !uid_eq(new->suid, root_uid)) &&
-	    !issecure(SECURE_KEEP_CAPS)) {
-		cap_clear(new->cap_permitted);
-		cap_clear(new->cap_effective);
+	     	     !uid_eq(new->suid, root_uid))) {
+		if (!issecure(SECURE_KEEP_CAPS)) {
+			cap_clear(new->cap_permitted);
+			cap_clear(new->cap_effective);
+		}
+
+		/*
+		 * Pre-ambient programs expect setresuid to nonroot followed
+		 * by exec to drop capabilities.  We should make sure that
+		 * this remains the case.
+		 */
+		cap_clear(new->cap_ambient);
 	}
 	if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid))
 		cap_clear(new->cap_effective);
@@ -979,6 +1025,43 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 		else
 			new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
 		goto changed;
+
+		case PR_CAP_AMBIENT:
+		if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) {
+			if (arg3 | arg4 | arg5)
+				return -EINVAL;
+
+			new = prepare_creds();
+			if (!new)
+				return -ENOMEM;
+			cap_clear(new->cap_ambient);
+			return commit_creds(new);
+		}
+
+		if (((!cap_valid(arg3)) | arg4 | arg5))
+			return -EINVAL;
+
+		if (arg2 == PR_CAP_AMBIENT_IS_SET) {
+			return !!cap_raised(current_cred()->cap_ambient, arg3);
+		} else if (arg2 != PR_CAP_AMBIENT_RAISE &&
+			   arg2 != PR_CAP_AMBIENT_LOWER) {
+			return -EINVAL;
+		} else {
+			if (arg2 == PR_CAP_AMBIENT_RAISE &&
+			    (!cap_raised(current_cred()->cap_permitted, arg3) ||
+			     !cap_raised(current_cred()->cap_inheritable,
+					 arg3)))
+				return -EPERM;
+
+			new = prepare_creds();
+			if (!new)
+				return -ENOMEM;
+			if (arg2 == PR_CAP_AMBIENT_RAISE)
+				cap_raise(new->cap_ambient, arg3);
+			else
+				cap_lower(new->cap_ambient, arg3);
+			return commit_creds(new);
+		}
 
 	default:
 		/* No functionality available - continue with default */

security/keys/process_keys.c

@@ -847,6 +847,7 @@ void key_change_session_keyring(struct callback_head *twork)
 	new->cap_inheritable	= old->cap_inheritable;
 	new->cap_permitted	= old->cap_permitted;
 	new->cap_effective	= old->cap_effective;
+	new->cap_ambient	= old->cap_ambient;
 	new->cap_bset		= old->cap_bset;
 
 	new->jit_keyring	= old->jit_keyring;