cgroup_exit() needs to do this only if the exiting task is a leader and it
is not the last live thread. The patch doesn't use delay_group_leader(),
atomic_read(signal->live) matches the code css_task_iter_advance() more.
cgroup_release() can now check list_empty(task->cg_list) before it takes
css_set_lock and calls ss_set_skip_task_iters().
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
---
kernel/cgroup/cgroup.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index e32b6972c478..0cbee8118c95 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6686,8 +6686,10 @@ void cgroup_exit(struct task_struct *tsk)
WARN_ON_ONCE(list_empty(&tsk->cg_list));
cset = task_css_set(tsk);
css_set_move_task(tsk, cset, NULL, false);
- list_add_tail(&tsk->cg_list, &cset->dying_tasks);
cset->nr_tasks--;
+ /* matches the signal->live check in css_task_iter_advance() */
+ if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live))
+ list_add_tail(&tsk->cg_list, &cset->dying_tasks);
if (dl_task(tsk))
dec_dl_tasks_cs(tsk);
@@ -6714,10 +6716,12 @@ void cgroup_release(struct task_struct *task)
ss->release(task);
} while_each_subsys_mask();
- spin_lock_irq(&css_set_lock);
- css_set_skip_task_iters(task_css_set(task), task);
- list_del_init(&task->cg_list);
- spin_unlock_irq(&css_set_lock);
+ if (!list_empty(&task->cg_list)) {
+ spin_lock_irq(&css_set_lock);
+ css_set_skip_task_iters(task_css_set(task), task);
+ list_del_init(&task->cg_list);
+ spin_unlock_irq(&css_set_lock);
+ }
}
void cgroup_free(struct task_struct *task)
--
2.25.1.362.g51ebf55
