diff options
author | Eric W. Biederman <ebiederm@xmission.com> | 2012-06-20 15:53:03 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-06-20 17:39:36 -0400 |
commit | 6347e90091041e34bea625370794c92f4ce71228 (patch) | |
tree | 20614d4eedd2993248be3c3562177c7e00f24b68 /kernel/exit.c | |
parent | f39cdaebb89dc3e6dd4f3e75b6d4e87ef12190af (diff) |
pidns: guarantee that the pidns init will be the last pidns process reaped
Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid
namespace can run before other processes in a pid namespace have had
release task called. With the result that pid_ns_release_proc can be
called before the last proc_flus_task() is done using upid->ns->proc_mnt,
resulting in the use of a stale pointer. This same set of circumstances
can lead to waitpid(...) returning for a processes started with
clone(CLONE_NEWPID) before the every process in the pid namespace has
actually exited.
To fix this modify zap_pid_ns_processess wait until all other processes in
the pid namespace have exited, even EXIT_DEAD zombies.
The delay_group_leader and related tests ensure that the thread gruop
leader will be the last thread of a process group to be reaped, or to
become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes
we get the guarantee that pid == 1 in a pid namespace will be the last
task that release_task is called on.
With pid == 1 being the last task to pass through release_task
pid_ns_release_proc can no longer be called too early nor can wait return
before all of the EXIT_DEAD tasks in a pid namespace have exited.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Louis Rilling <louis.rilling@kerlabs.com>
Cc: Mike Galbraith <efault@gmx.de>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Tested-by: Andrew Wagin <avagin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/exit.c')
-rw-r--r-- | kernel/exit.c | 14 |
1 files changed, 13 insertions, 1 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index c0277d3f1aaa..a85efd2348bd 100644 --- a/kernel/exit.c +++ b/kernel/exit.c | |||
@@ -64,7 +64,6 @@ static void exit_mm(struct task_struct * tsk); | |||
64 | static void __unhash_process(struct task_struct *p, bool group_dead) | 64 | static void __unhash_process(struct task_struct *p, bool group_dead) |
65 | { | 65 | { |
66 | nr_threads--; | 66 | nr_threads--; |
67 | detach_pid(p, PIDTYPE_PID); | ||
68 | if (group_dead) { | 67 | if (group_dead) { |
69 | detach_pid(p, PIDTYPE_PGID); | 68 | detach_pid(p, PIDTYPE_PGID); |
70 | detach_pid(p, PIDTYPE_SID); | 69 | detach_pid(p, PIDTYPE_SID); |
@@ -72,7 +71,20 @@ static void __unhash_process(struct task_struct *p, bool group_dead) | |||
72 | list_del_rcu(&p->tasks); | 71 | list_del_rcu(&p->tasks); |
73 | list_del_init(&p->sibling); | 72 | list_del_init(&p->sibling); |
74 | __this_cpu_dec(process_counts); | 73 | __this_cpu_dec(process_counts); |
74 | /* | ||
75 | * If we are the last child process in a pid namespace to be | ||
76 | * reaped, notify the reaper sleeping zap_pid_ns_processes(). | ||
77 | */ | ||
78 | if (IS_ENABLED(CONFIG_PID_NS)) { | ||
79 | struct task_struct *parent = p->real_parent; | ||
80 | |||
81 | if ((task_active_pid_ns(p)->child_reaper == parent) && | ||
82 | list_empty(&parent->children) && | ||
83 | (parent->flags & PF_EXITING)) | ||
84 | wake_up_process(parent); | ||
85 | } | ||
75 | } | 86 | } |
87 | detach_pid(p, PIDTYPE_PID); | ||
76 | list_del_rcu(&p->thread_group); | 88 | list_del_rcu(&p->thread_group); |
77 | } | 89 | } |
78 | 90 | ||