userns: security: make capabilities relative to the user namespace

[firefly-linux-kernel-4.4.55.git] / security / commoncap.c

diff --git a/security/commoncap.c b/security/commoncap.c
index dbfdaed4cc663c6ed40836f69da8f35a9f27245a..43a205bc7d7c52645a4dfa1fa4172fb770059fbf 100644 (file)
--- a/security/commoncap.c
+++ b/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
@@ -52,13 +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;
 }
@@ -68,6 +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
  *
@@ -79,10 +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 */
 }
 
 /**
@@ -177,7 +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;
@@ -829,7 +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
@@ -894,7 +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);
@@ -921,7 +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)