Re: [PATCH] kernel: release ptraced tasks before zap_pid_ns_processes

From: Andrei Vagin
Date: Wed Jan 02 2019 - 16:16:35 EST


Hello,

The reproducer for this problem is attached to this message.

Below you can find its effect without this fix:

We have one alive process which stucks in
zap_pid_ns_processes:

$ ps axf
...
11831 pts/0 S 0:00 [ptrace_pidns]
11833 pts/0 Zl 0:00 \_ [ptrace_pidns] <defunct>

$ cat /proc/11831/stack
[<0>] do_wait+0x1fa/0x2c0
[<0>] kernel_wait4+0x9e/0x150
[<0>] zap_pid_ns_processes+0x17d/0x270
[<0>] do_exit+0xa15/0xbd0
[<0>] do_group_exit+0x47/0xc0
[<0>] get_signal+0x28c/0x850
[<0>] do_signal+0x36/0x630
[<0>] exit_to_usermode_loop+0x62/0xc0
[<0>] prepare_exit_to_usermode+0xb4/0xe0
[<0>] retint_user+0x8/0x18
[<0>] 0xffffffffffffffff


The child process has two threads which were ptraced by parent:
$ ls /proc/11833/task/
11833 11834

The parent can't wait the child, becase a thread group isn't empty, but
a thread is in the dead list:

$ cat /proc/1183{1,3,4}/status | grep '\(NSpid\|TracerPid\|State\)'
State: S (sleeping)
TracerPid: 0
NSpid: 11831 1
State: Z (zombie)
TracerPid: 0
NSpid: 11833 2
State: X (dead)
TracerPid: 0
NSpid: 11834 3

On Wed, Jan 02, 2019 at 12:59:39PM -0800, Andrei Vagin wrote:
> Currently, exit_ptrace() adds all ptraced tasks in a dead list, than
> zap_pid_ns_processes() waits all tasks in a current pid ns, and only
> then tasks from the dead list are released.
>
> zap_pid_ns_processes() can stuck on waiting tasks from the dead list. In
> this case, we will have one unkillable process with one or more dead
> children.
>
> Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
> Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Signed-off-by: Andrei Vagin <avagin@xxxxxxxxx>
> ---
> kernel/exit.c | 15 +++++++++++----
> 1 file changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/exit.c b/kernel/exit.c
> index 0e21e6d21f35..ccaa6f6549ba 100644
> --- a/kernel/exit.c
> +++ b/kernel/exit.c
> @@ -664,9 +664,6 @@ static void forget_original_parent(struct task_struct *father,
> {
> struct task_struct *p, *t, *reaper;
>
> - if (unlikely(!list_empty(&father->ptraced)))
> - exit_ptrace(father, dead);
> -
> /* Can drop and reacquire tasklist_lock */
> reaper = find_child_reaper(father);
> if (list_empty(&father->children))
> @@ -705,8 +702,18 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
> LIST_HEAD(dead);
>
> write_lock_irq(&tasklist_lock);
> - forget_original_parent(tsk, &dead);
> + if (unlikely(!list_empty(&tsk->ptraced)))
> + exit_ptrace(tsk, &dead);
> + write_unlock_irq(&tasklist_lock);
> +
> + /* Ptraced tasks have to be released before zap_pid_ns_processes(). */
> + list_for_each_entry_safe(p, n, &dead, ptrace_entry) {
> + list_del_init(&p->ptrace_entry);
> + release_task(p);
> + }
>
> + write_lock_irq(&tasklist_lock);
> + forget_original_parent(tsk, &dead);
> if (group_dead)
> kill_orphaned_pgrp(tsk->group_leader, NULL);
>
> --
> 2.17.2
>
#define _GNU_SOURCE /* See feature_test_macros(7) */
#include <unistd.h>
#include <sys/ptrace.h>
#include <sys/types.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/wait.h>
#include <sys/syscall.h> /* For SYS_xxx definitions */
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>


int pfd[2];
void *thread_fn()
{
pid_t tid = syscall(SYS_gettid);
write(pfd[1], &tid, sizeof(tid));
sleep(1000);
return NULL;
}

int main()
{
pid_t pid, tid, ppid = getpid();
pthread_t t;

if (pipe(pfd))
return 1;

pid = fork();
if (pid < 0)
return 1;
if (pid == 0) {
pthread_create(&t, NULL, thread_fn, (void *)(unsigned long)ppid);
sleep(1000);
return 0;
}
printf("fork: %d\n", pid);

if (read(pfd[0], &tid, sizeof(tid)) != sizeof(tid))
return 1;
printf("thread: %d\n", tid);
if (ptrace(PTRACE_ATTACH, tid, 0, 0))
return 1;
if (wait4(tid, NULL, __WALL, NULL) != tid)
return 1;
if (ptrace(PTRACE_ATTACH, pid, 0, 0))
return 1;
if (wait4(pid, NULL, __WALL, NULL) != pid)
return 1;

kill(pid, SIGKILL);

*((int *)(0)) = 0xdead;

return 0;
}