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>

drivers/pci/pci-sysfs.c

@@ -369,7 +369,7 @@ pci_read_config(struct file *filp, struct kobject *kobj,
 	u8 *data = (u8*) buf;
 
 	/* Several chips lock up trying to read undefined config space */
-	if (security_capable(filp->f_cred, CAP_SYS_ADMIN) == 0) {
+	if (security_capable(&init_user_ns, filp->f_cred, CAP_SYS_ADMIN) == 0) {
 		size = dev->cfg_size;
 	} else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) {
 		size = 128;

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__ */

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;		\

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;

kernel/capability.c

@@ -14,6 +14,7 @@
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
 /*
@@ -299,17 +300,48 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
  * This sets PF_SUPERPRIV on the task if the capability is available on the
  * assumption that it's about to be used.
  */
-int capable(int cap)
+bool capable(int cap)
+{
+	return ns_capable(&init_user_ns, cap);
+}
+EXPORT_SYMBOL(capable);
+
+/**
+ * ns_capable - Determine if the current task has a superior capability in effect
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool ns_capable(struct user_namespace *ns, int cap)
 {
 	if (unlikely(!cap_valid(cap))) {
 		printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
 		BUG();
 	}
 
-	if (security_capable(current_cred(), cap) == 0) {
+	if (security_capable(ns, current_cred(), cap) == 0) {
 		current->flags |= PF_SUPERPRIV;
-		return 1;
+		return true;
 	}
-	return 0;
+	return false;
 }
-EXPORT_SYMBOL(capable);
+EXPORT_SYMBOL(ns_capable);
+
+/**
+ * task_ns_capable - Determine whether current task has a superior
+ * capability targeted at a specific task's user namespace.
+ * @t: The task whose user namespace is targeted.
+ * @cap: The capability in question.
+ *
+ *  Return true if it does, false otherwise.
+ */
+bool task_ns_capable(struct task_struct *t, int cap)
+{
+	return ns_capable(task_cred_xxx(t, user)->user_ns, cap);
+}
+EXPORT_SYMBOL(task_ns_capable);

kernel/cred.c

@@ -741,6 +741,12 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 }
 EXPORT_SYMBOL(set_create_files_as);
 
+struct user_namespace *current_user_ns(void)
+{
+	return _current_user_ns();
+}
+EXPORT_SYMBOL(current_user_ns);
+
 #ifdef CONFIG_DEBUG_CREDENTIALS
 
 bool creds_are_invalid(const struct cred *cred)

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