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)

[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: export current_user_ns() for ecryptfs]
[serge.hallyn@canonical.com: remove unneeded extra argument in selinux's task_has_capability]
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Daniel Lezcano <daniel.lezcano@free.fr>
Acked-by: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 48 insertions, 20 deletions

diff --git a/include/linux/capability.h b/include/linux/capability.h
index fb16a3699b99..7c9c82903012 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -368,6 +368,17 @@ struct cpu_vfs_cap_data {
 
 #ifdef __KERNEL__
 
+struct dentry;
+struct user_namespace;
+
+extern struct user_namespace init_user_ns;
+
+struct user_namespace *current_user_ns(void);
+
+extern const kernel_cap_t __cap_empty_set;
+extern const kernel_cap_t __cap_full_set;
+extern const kernel_cap_t __cap_init_eff_set;
+
 /*
  * Internal kernel functions only
  */
@@ -530,10 +541,6 @@ static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a,
 			   cap_intersect(permitted, __cap_nfsd_set));
 }
 
-extern const kernel_cap_t __cap_empty_set;
-extern const kernel_cap_t __cap_full_set;
-extern const kernel_cap_t __cap_init_eff_set;
-
 /**
  * has_capability - Determine if a task has a superior capability available
  * @t: The task in question
@@ -544,7 +551,7 @@ extern const kernel_cap_t __cap_init_eff_set;
  *
  * Note that this does not set PF_SUPERPRIV on the task.
  */
-#define has_capability(t, cap) (security_real_capable((t), (cap)) == 0)
+#define has_capability(t, cap) (security_real_capable((t), &init_user_ns, (cap)) == 0)
 
 /**
  * has_capability_noaudit - Determine if a task has a superior capability available (unaudited)
@@ -558,12 +565,25 @@ extern const kernel_cap_t __cap_init_eff_set;
  * Note that this does not set PF_SUPERPRIV on the task.
  */
 #define has_capability_noaudit(t, cap) \
-	(security_real_capable_noaudit((t), (cap)) == 0)
+	(security_real_capable_noaudit((t), &init_user_ns, (cap)) == 0)
 
-extern int capable(int cap);
+extern bool capable(int cap);
+extern bool ns_capable(struct user_namespace *ns, int cap);
+extern bool task_ns_capable(struct task_struct *t, int cap);
+
+/**
+ * nsown_capable - Check superior capability to one's own user_ns
+ * @cap: The capability in question
+ *
+ * Return true if the current task has the given superior capability
+ * targeted at its own user namespace.
+ */
+static inline bool nsown_capable(int cap)
+{
+	return ns_capable(current_user_ns(), cap);
+}
 
 /* audit system wants to get cap info from files as well */
-struct dentry;
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 4aaeab376446..9aeeb0ba2003 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -354,9 +354,11 @@ static inline void put_cred(const struct cred *_cred)
 #define current_fsgid() 	(current_cred_xxx(fsgid))
 #define current_cap()		(current_cred_xxx(cap_effective))
 #define current_user()		(current_cred_xxx(user))
-#define current_user_ns()	(current_cred_xxx(user)->user_ns)
+#define _current_user_ns()	(current_cred_xxx(user)->user_ns)
 #define current_security()	(current_cred_xxx(security))
 
+extern struct user_namespace *current_user_ns(void);
+
 #define current_uid_gid(_uid, _gid)		\
 do {						\
 	const struct cred *__cred;		\
diff --git a/include/linux/security.h b/include/linux/security.h
index 56cac520d014..ca02f1716736 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -47,13 +47,14 @@
 
 struct ctl_table;
 struct audit_krule;
+struct user_namespace;
 
 /*
  * These functions are in security/capability.c and are used
  * as the default capabilities functions
  */
 extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
-		       int cap, int audit);
+		       struct user_namespace *ns, int cap, int audit);
 extern int cap_settime(const struct timespec *ts, const struct timezone *tz);
 extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode);
 extern int cap_ptrace_traceme(struct task_struct *parent);
@@ -1262,6 +1263,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	credentials.
  *	@tsk contains the task_struct for the process.
  *	@cred contains the credentials to use.
+ *      @ns contains the user namespace we want the capability in
  *	@cap contains the capability <include/linux/capability.h>.
  *	@audit: Whether to write an audit message or not
  *	Return 0 if the capability is granted for @tsk.
@@ -1384,7 +1386,7 @@ struct security_operations {
 		       const kernel_cap_t *inheritable,
 		       const kernel_cap_t *permitted);
 	int (*capable) (struct task_struct *tsk, const struct cred *cred,
-			int cap, int audit);
+			struct user_namespace *ns, int cap, int audit);
 	int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
 	int (*quota_on) (struct dentry *dentry);
 	int (*syslog) (int type);
@@ -1665,9 +1667,12 @@ int security_capset(struct cred *new, const struct cred *old,
 		    const kernel_cap_t *effective,
 		    const kernel_cap_t *inheritable,
 		    const kernel_cap_t *permitted);
-int security_capable(const struct cred *cred, int cap);
-int security_real_capable(struct task_struct *tsk, int cap);
-int security_real_capable_noaudit(struct task_struct *tsk, int cap);
+int security_capable(struct user_namespace *ns, const struct cred *cred,
+			int cap);
+int security_real_capable(struct task_struct *tsk, struct user_namespace *ns,
+			int cap);
+int security_real_capable_noaudit(struct task_struct *tsk,
+			struct user_namespace *ns, int cap);
 int security_quotactl(int cmds, int type, int id, struct super_block *sb);
 int security_quota_on(struct dentry *dentry);
 int security_syslog(int type);
@@ -1860,28 +1865,29 @@ static inline int security_capset(struct cred *new,
 	return cap_capset(new, old, effective, inheritable, permitted);
 }
 
-static inline int security_capable(const struct cred *cred, int cap)
+static inline int security_capable(struct user_namespace *ns,
+				   const struct cred *cred, int cap)
 {
-	return cap_capable(current, cred, cap, SECURITY_CAP_AUDIT);
+	return cap_capable(current, cred, ns, cap, SECURITY_CAP_AUDIT);
 }
 
-static inline int security_real_capable(struct task_struct *tsk, int cap)
+static inline int security_real_capable(struct task_struct *tsk, struct user_namespace *ns, int cap)
 {
 	int ret;
 
 	rcu_read_lock();
-	ret = cap_capable(tsk, __task_cred(tsk), cap, SECURITY_CAP_AUDIT);
+	ret = cap_capable(tsk, __task_cred(tsk), ns, cap, SECURITY_CAP_AUDIT);
 	rcu_read_unlock();
 	return ret;
 }
 
 static inline
-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)
 {
 	int ret;
 
 	rcu_read_lock();
-	ret = cap_capable(tsk, __task_cred(tsk), cap,
+	ret = cap_capable(tsk, __task_cred(tsk), ns, cap,
 			       SECURITY_CAP_NOAUDIT);
 	rcu_read_unlock();
 	return ret;