Return EPERM not ECHILD on security_task_wait failure

wait* syscalls return -ECHILD even when an individual PID of a live child
was requested explicitly, when security_task_wait denies the operation.
This means that something like a broken SELinux policy can produce an
unexpected failure that looks just like a bug with wait or ptrace or
something.

This patch makes do_wait return -EACCES (or other appropriate error returned
from security_task_wait() instead of -ECHILD if some children were ruled out
solely because security_task_wait failed.

[jmorris@namei.org: switch error code to EACCES]
Signed-off-by: Roland McGrath <roland@redhat.com>
Acked-by: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/exit.c b/kernel/exit.c
index b55ed4cc91044803a45b74d568d83f9727575b8b..92369240d91d3a9582b490da701be24a6f81795f 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1033,6 +1033,8 @@ asmlinkage void sys_exit_group(int error_code)
 
 static int eligible_child(pid_t pid, int options, struct task_struct *p)
 {
+       int err;
+
        if (pid > 0) {
                if (p->pid != pid)
                        return 0;
@@ -1066,8 +1068,9 @@ static int eligible_child(pid_t pid, int options, struct task_struct *p)
        if (delay_group_leader(p))
                return 2;
 
-       if (security_task_wait(p))
-               return 0;
+       err = security_task_wait(p);
+       if (err)
+               return err;
 
        return 1;
 }
@@ -1449,6 +1452,7 @@ static long do_wait(pid_t pid, int options, struct siginfo __user *infop,
        DECLARE_WAITQUEUE(wait, current);
        struct task_struct *tsk;
        int flag, retval;
+       int allowed, denied;
 
        add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
@@ -1457,6 +1461,7 @@ repeat:
         * match our criteria, even if we are not able to reap it yet.
         */
        flag = 0;
+       allowed = denied = 0;
        current->state = TASK_INTERRUPTIBLE;
        read_lock(&tasklist_lock);
        tsk = current;
@@ -1472,6 +1477,12 @@ repeat:
                        if (!ret)
                                continue;
 
+                       if (unlikely(ret < 0)) {
+                               denied = ret;
+                               continue;
+                       }
+                       allowed = 1;
+
                        switch (p->state) {
                        case TASK_TRACED:
                                /*
@@ -1570,6 +1581,8 @@ check_continued:
                goto repeat;
        }
        retval = -ECHILD;
+       if (unlikely(denied) && !allowed)
+               retval = denied;
 end:
        current->state = TASK_RUNNING;
        remove_wait_queue(&current->signal->wait_chldexit,&wait);