+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+/*
+ * Rationale: code calling task_setscheduler, task_setioprio, and
+ * task_setnice, assumes that
+ * . if capable(cap_sys_nice), then those actions should be allowed
+ * . if not capable(cap_sys_nice), but acting on your own processes,
+ * then those actions should be allowed
+ * This is insufficient now since you can call code without suid, but
+ * yet with increased caps.
+ * So we check for increased caps on the target process.
+ */
+static int cap_safe_nice(struct task_struct *p)
+{
+ if (!cap_issubset(p->cap_permitted, current->cap_permitted) &&
+ !capable(CAP_SYS_NICE))
+ return -EPERM;
+ return 0;
+}
+
+int cap_task_setscheduler (struct task_struct *p, int policy,
+ struct sched_param *lp)
+{
+ return cap_safe_nice(p);
+}
+
+int cap_task_setioprio (struct task_struct *p, int ioprio)
+{
+ return cap_safe_nice(p);
+}
+
+int cap_task_setnice (struct task_struct *p, int nice)
+{
+ return cap_safe_nice(p);
+}
+
+/*
+ * called from kernel/sys.c for prctl(PR_CABSET_DROP)
+ * done without task_capability_lock() because it introduces
+ * no new races - i.e. only another task doing capget() on
+ * this task could get inconsistent info. There can be no
+ * racing writer bc a task can only change its own caps.
+ */
+static long cap_prctl_drop(unsigned long cap)
+{
+ if (!capable(CAP_SETPCAP))
+ return -EPERM;
+ if (!cap_valid(cap))
+ return -EINVAL;
+ cap_lower(current->cap_bset, cap);
+ return 0;
+}
+
+#else
+int cap_task_setscheduler (struct task_struct *p, int policy,
+ struct sched_param *lp)
+{
+ return 0;
+}
+int cap_task_setioprio (struct task_struct *p, int ioprio)
+{
+ return 0;
+}
+int cap_task_setnice (struct task_struct *p, int nice)
+{
+ return 0;
+}
+#endif
+
+int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5, long *rc_p)
+{
+ long error = 0;
+
+ switch (option) {
+ case PR_CAPBSET_READ:
+ if (!cap_valid(arg2))
+ error = -EINVAL;
+ else
+ error = !!cap_raised(current->cap_bset, arg2);
+ break;
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+ case PR_CAPBSET_DROP:
+ error = cap_prctl_drop(arg2);
+ break;
+
+ /*
+ * The next four prctl's remain to assist with transitioning a
+ * system from legacy UID=0 based privilege (when filesystem
+ * capabilities are not in use) to a system using filesystem
+ * capabilities only - as the POSIX.1e draft intended.
+ *
+ * Note:
+ *
+ * PR_SET_SECUREBITS =
+ * issecure_mask(SECURE_KEEP_CAPS_LOCKED)
+ * | issecure_mask(SECURE_NOROOT)
+ * | issecure_mask(SECURE_NOROOT_LOCKED)
+ * | issecure_mask(SECURE_NO_SETUID_FIXUP)
+ * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)
+ *
+ * will ensure that the current process and all of its
+ * children will be locked into a pure
+ * capability-based-privilege environment.
+ */
+ case PR_SET_SECUREBITS:
+ if ((((current->securebits & SECURE_ALL_LOCKS) >> 1)
+ & (current->securebits ^ arg2)) /*[1]*/
+ || ((current->securebits & SECURE_ALL_LOCKS
+ & ~arg2)) /*[2]*/
+ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/
+ || (cap_capable(current, CAP_SETPCAP) != 0)) { /*[4]*/
+ /*
+ * [1] no changing of bits that are locked
+ * [2] no unlocking of locks
+ * [3] no setting of unsupported bits
+ * [4] doing anything requires privilege (go read about
+ * the "sendmail capabilities bug")
+ */
+ error = -EPERM; /* cannot change a locked bit */
+ } else {
+ current->securebits = arg2;
+ }
+ break;
+ case PR_GET_SECUREBITS:
+ error = current->securebits;
+ break;
+
+#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */
+
+ case PR_GET_KEEPCAPS:
+ if (issecure(SECURE_KEEP_CAPS))
+ error = 1;
+ break;
+ case PR_SET_KEEPCAPS:
+ if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */
+ error = -EINVAL;
+ else if (issecure(SECURE_KEEP_CAPS_LOCKED))
+ error = -EPERM;
+ else if (arg2)
+ current->securebits |= issecure_mask(SECURE_KEEP_CAPS);
+ else
+ current->securebits &=
+ ~issecure_mask(SECURE_KEEP_CAPS);
+ break;
+
+ default:
+ /* No functionality available - continue with default */
+ return 0;
+ }
+
+ /* Functionality provided */
+ *rc_p = error;
+ return 1;
+}
+