On Tue, 2010-06-29 at 17:23 +0200, Oleg Nesterov wrote:
> On 06/29, Ben Hutchings wrote:
> >
> > I've attempted to cherry-pick and adjust these for 2.6.26; patches
> > below. Do these look reasonable or are additional changes required?
>
> Confused. please see below.
>
> > Subject: [PATCH 1/2] pid_ns: zap_pid_ns_processes: fix the ->child_reaper changing
> >
> > commit add0d4dfd660e9e4fd0af3eac3cad23583c9558f upstream.
> > ...
> >
> > @@ -182,9 +182,12 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
> > rc = sys_wait4(-1, NULL, __WALL, NULL);
> > } while (rc != -ECHILD);
> >
> > -
> > - /* Child reaper for the pid namespace is going away */
> > - pid_ns->child_reaper = NULL;
> > + /*
> > + * We can not clear ->child_reaper or leave it alone.
> > + * There may by stealth EXIT_DEAD tasks on ->children,
> > + * forget_original_parent() must move them somewhere.
> > + */
> > + pid_ns->child_reaper = init_pid_ns.child_reaper;
>
> This is correct, but the second patch
>
> > @@ -182,12 +182,6 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
> > rc = sys_wait4(-1, NULL, __WALL, NULL);
> > } while (rc != -ECHILD);
> >
> > - /*
> > - * We can not clear ->child_reaper or leave it alone.
> > - * There may by stealth EXIT_DEAD tasks on ->children,
> > - * forget_original_parent() must move them somewhere.
> > - */
> > - pid_ns->child_reaper = init_pid_ns.child_reaper;
>
> Removes this code?
That's what your commit 950bbabb5a804690a0201190de5c22837f72f83f did.
> This doesn't look right, or I missed something.
>
>
> I think you are right, you need these 2 commits
>
> 950bbabb5a804690a0201190de5c22837f72f83f
> add0d4dfd660e9e4fd0af3eac3cad23583c9558f
>
> (in that order).
That is the opposite of the order in which they were originally applied!
> I'd suggest you to adjust these commits and make
> a single patch. In that case I can try to see if it is correct
> against the 2.6.26.
The combined diff is:
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -758,23 +758,48 @@ static void reparent_thread(struct task_struct *p, struct task_struct *father)
* the child reaper process (ie "init") in our pid
* space.
*/
+static struct task_struct *find_new_reaper(struct task_struct *father)
+{
+ struct pid_namespace *pid_ns = task_active_pid_ns(father);
+ struct task_struct *thread;
+
+ thread = father;
+ while_each_thread(father, thread) {
+ if (thread->flags & PF_EXITING)
+ continue;
+ if (unlikely(pid_ns->child_reaper == father))
+ pid_ns->child_reaper = thread;
+ return thread;
+ }
+
+ if (unlikely(pid_ns->child_reaper == father)) {
+ write_unlock_irq(&tasklist_lock);
+ if (unlikely(pid_ns == &init_pid_ns))
+ panic("Attempted to kill init!");
+
+ zap_pid_ns_processes(pid_ns);
+ write_lock_irq(&tasklist_lock);
+ /*
+ * We can not clear ->child_reaper or leave it alone.
+ * There may by stealth EXIT_DEAD tasks on ->children,
+ * forget_original_parent() must move them somewhere.
+ */
+ pid_ns->child_reaper = init_pid_ns.child_reaper;
+ }
+
+ return pid_ns->child_reaper;
+}
+
static void forget_original_parent(struct task_struct *father)
{
- struct task_struct *p, *n, *reaper = father;
+ struct task_struct *p, *n, *reaper;
struct list_head ptrace_dead;
INIT_LIST_HEAD(&ptrace_dead);
write_lock_irq(&tasklist_lock);
+ reaper = find_new_reaper(father);
- do {
- reaper = next_thread(reaper);
- if (reaper == father) {
- reaper = task_child_reaper(father);
- break;
- }
- } while (reaper->flags & PF_EXITING);
-
/*
* There are only two places where our children can be:
*
@@ -929,39 +954,6 @@ static void check_stack_usage(void)
static inline void check_stack_usage(void) {}
#endif
-static inline void exit_child_reaper(struct task_struct *tsk)
-{
- if (likely(tsk->group_leader != task_child_reaper(tsk)))
- return;
-
- if (tsk->nsproxy->pid_ns == &init_pid_ns)
- panic("Attempted to kill init!");
-
- /*
- * @tsk is the last thread in the 'cgroup-init' and is exiting.
- * Terminate all remaining processes in the namespace and reap them
- * before exiting @tsk.
- *
- * Note that @tsk (last thread of cgroup-init) may not necessarily
- * be the child-reaper (i.e main thread of cgroup-init) of the
- * namespace i.e the child_reaper may have already exited.
- *
- * Even after a child_reaper exits, we let it inherit orphaned children,
- * because, pid_ns->child_reaper remains valid as long as there is
- * at least one living sub-thread in the cgroup init.
-
- * This living sub-thread of the cgroup-init will be notified when
- * a child inherited by the 'child-reaper' exits (do_notify_parent()
- * uses __group_send_sig_info()). Further, when reaping child processes,
- * do_wait() iterates over children of all living sub threads.
-
- * i.e even though 'child_reaper' thread is listed as the parent of the
- * orphaned children, any living sub-thread in the cgroup-init can
- * perform the role of the child_reaper.
- */
- zap_pid_ns_processes(tsk->nsproxy->pid_ns);
-}
-
NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
@@ -1024,7 +1016,6 @@ NORET_TYPE void do_exit(long code)
}
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
- exit_child_reaper(tsk);
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
}
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -182,9 +182,6 @@
rc = sys_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
-
- /* Child reaper for the pid namespace is going away */
- pid_ns->child_reaper = NULL;
return;
}
--
Ben.
--
Ben Hutchings
Once a job is fouled up, anything done to improve it makes it worse.
Attachment:
signature.asc
Description: This is a digitally signed message part