1 files changed, 70 insertions, 50 deletions

diff --git a/security/commoncap.c b/security/commoncap.c
index 9d172e6e330c..a93b3b733079 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -27,7 +27,7 @@
 #include <linux/sched.h>
 #include <linux/prctl.h>
 #include <linux/securebits.h>
-#include <linux/syslog.h>
+#include <linux/user_namespace.h>
 
 /*
  * If a non-root user executes a setuid-root binary in
@@ -53,13 +53,12 @@ static void warn_setuid_and_fcaps_mixed(const char *fname)
 
 int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-        NETLINK_CB(skb).eff_cap = current_cap();
         return 0;
 }
 
 int cap_netlink_recv(struct sk_buff *skb, int cap)
 {
-        if (!cap_raised(NETLINK_CB(skb).eff_cap, cap))
+        if (!cap_raised(current_cap(), cap))
                 return -EPERM;
         return 0;
 }
@@ -69,6 +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
  *
@@ -80,10 +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 */
 }
 
 /**
@@ -94,7 +114,7 @@ int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
  * Determine whether the current process may set the system clock and timezone
  * information, returning 0 if permission granted, -ve if denied.
  */
-int cap_settime(struct timespec *ts, struct timezone *tz)
+int cap_settime(const struct timespec *ts, const struct timezone *tz)
 {
         if (!capable(CAP_SYS_TIME))
                 return -EPERM;
@@ -107,18 +127,30 @@ int cap_settime(struct timespec *ts, struct timezone *tz)
  * @child: The process to be accessed
  * @mode: The mode of attachment.
  *
+ * If we are in the same or an ancestor user_ns and have all the target
+ * task's capabilities, then ptrace access is allowed.
+ * If we have the ptrace capability to the target user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
  * Determine whether a process may access another, returning 0 if permission
  * granted, -ve if denied.
  */
 int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
 {
         int ret = 0;
+        const struct cred *cred, *child_cred;
 
         rcu_read_lock();
-        if (!cap_issubset(__task_cred(child)->cap_permitted,
-                          current_cred()->cap_permitted) &&
-            !capable(CAP_SYS_PTRACE))
-                ret = -EPERM;
+        cred = current_cred();
+        child_cred = __task_cred(child);
+        if (cred->user->user_ns == child_cred->user->user_ns &&
+            cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+                goto out;
+        if (ns_capable(child_cred->user->user_ns, CAP_SYS_PTRACE))
+                goto out;
+        ret = -EPERM;
+out:
         rcu_read_unlock();
         return ret;
 }
@@ -127,18 +159,30 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
  * cap_ptrace_traceme - Determine whether another process may trace the current
  * @parent: The task proposed to be the tracer
  *
+ * If parent is in the same or an ancestor user_ns and has all current's
+ * capabilities, then ptrace access is allowed.
+ * If parent has the ptrace capability to current's user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
  * Determine whether the nominated task is permitted to trace the current
  * process, returning 0 if permission is granted, -ve if denied.
  */
 int cap_ptrace_traceme(struct task_struct *parent)
 {
         int ret = 0;
+        const struct cred *cred, *child_cred;
 
         rcu_read_lock();
-        if (!cap_issubset(current_cred()->cap_permitted,
-                          __task_cred(parent)->cap_permitted) &&
-            !has_capability(parent, CAP_SYS_PTRACE))
-                ret = -EPERM;
+        cred = __task_cred(parent);
+        child_cred = current_cred();
+        if (cred->user->user_ns == child_cred->user->user_ns &&
+            cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+                goto out;
+        if (has_ns_capability(parent, child_cred->user->user_ns, CAP_SYS_PTRACE))
+                goto out;
+        ret = -EPERM;
+out:
         rcu_read_unlock();
         return ret;
 }
@@ -178,7 +222,8 @@ 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;
@@ -484,15 +529,10 @@ skip:
         new->suid = new->fsuid = new->euid;
         new->sgid = new->fsgid = new->egid;
 
-        /* For init, we want to retain the capabilities set in the initial
-         * task.  Thus we skip the usual capability rules
-         */
-        if (!is_global_init(current)) {
-                if (effective)
-                        new->cap_effective = new->cap_permitted;
-                else
-                        cap_clear(new->cap_effective);
-        }
+        if (effective)
+                new->cap_effective = new->cap_permitted;
+        else
+                cap_clear(new->cap_effective);
         bprm->cap_effective = effective;
 
         /*
@@ -719,14 +759,11 @@ static int cap_safe_nice(struct task_struct *p)
 /**
  * cap_task_setscheduler - Detemine if scheduler policy change is permitted
  * @p: The task to affect
- * @policy: The policy to effect
- * @lp: The parameters to the scheduling policy
  *
  * Detemine if the requested scheduler policy change is permitted for the
  * specified task, returning 0 if permission is granted, -ve if denied.
  */
-int cap_task_setscheduler(struct task_struct *p, int policy,
-                           struct sched_param *lp)
+int cap_task_setscheduler(struct task_struct *p)
 {
         return cap_safe_nice(p);
 }
@@ -833,7 +870,8 @@ 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
@@ -887,24 +925,6 @@ error:
 }
 
 /**
- * cap_syslog - Determine whether syslog function is permitted
- * @type: Function requested
- * @from_file: Whether this request came from an open file (i.e. /proc)
- *
- * Determine whether the current process is permitted to use a particular
- * syslog function, returning 0 if permission is granted, -ve if not.
- */
-int cap_syslog(int type, bool from_file)
-{
-        if (type != SYSLOG_ACTION_OPEN && from_file)
-                return 0;
-        if ((type != SYSLOG_ACTION_READ_ALL &&
-             type != SYSLOG_ACTION_SIZE_BUFFER) && !capable(CAP_SYS_ADMIN))
-                return -EPERM;
-        return 0;
-}
-
-/**
  * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted
  * @mm: The VM space in which the new mapping is to be made
  * @pages: The size of the mapping
@@ -916,7 +936,7 @@ 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);
@@ -943,7 +963,7 @@ 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)