rcu-tasks: Maintain lists to eliminate RCU-tasks/do_exit() deadlocks

This commit continues the elimination of deadlocks involving do_exit()
and RCU tasks by causing exit_tasks_rcu_start() to add the current
task to a per-CPU list and causing exit_tasks_rcu_stop() to remove the
current task from whatever list it is on.  These lists will be used to
track tasks that are exiting, while still accounting for any RCU-tasks
quiescent states that these tasks pass though.

[ paulmck: Apply Frederic Weisbecker feedback. ]

Link: https://lore.kernel.org/all/20240118021842.290665-1-chenzhongjin@huawei.com/

Reported-by: Chen Zhongjin <chenzhongjin@huawei.com>
Reported-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Yang Jihong <yangjihong1@huawei.com>
Tested-by: Chen Zhongjin <chenzhongjin@huawei.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
This commit is contained in:
Paul E. McKenney 2024-02-02 11:28:45 -08:00 committed by Boqun Feng
parent 46faf9d8e1
commit 6b70399f9e
1 changed files with 33 additions and 10 deletions

View File

@ -1147,25 +1147,48 @@ struct task_struct *get_rcu_tasks_gp_kthread(void)
EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);
/*
* Contribute to protect against tasklist scan blind spot while the
* task is exiting and may be removed from the tasklist. See
* corresponding synchronize_srcu() for further details.
* Protect against tasklist scan blind spot while the task is exiting and
* may be removed from the tasklist. Do this by adding the task to yet
* another list.
*
* Note that the task will remove itself from this list, so there is no
* need for get_task_struct(), except in the case where rcu_tasks_pertask()
* adds it to the holdout list, in which case rcu_tasks_pertask() supplies
* the needed get_task_struct().
*/
void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
void exit_tasks_rcu_start(void)
{
current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
unsigned long flags;
struct rcu_tasks_percpu *rtpcp;
struct task_struct *t = current;
WARN_ON_ONCE(!list_empty(&t->rcu_tasks_exit_list));
preempt_disable();
rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu);
t->rcu_tasks_exit_cpu = smp_processor_id();
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
if (!rtpcp->rtp_exit_list.next)
INIT_LIST_HEAD(&rtpcp->rtp_exit_list);
list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
preempt_enable();
}
/*
* Contribute to protect against tasklist scan blind spot while the
* task is exiting and may be removed from the tasklist. See
* corresponding synchronize_srcu() for further details.
* Remove the task from the "yet another list" because do_exit() is now
* non-preemptible, allowing synchronize_rcu() to wait beyond this point.
*/
void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu)
void exit_tasks_rcu_stop(void)
{
unsigned long flags;
struct rcu_tasks_percpu *rtpcp;
struct task_struct *t = current;
__srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
WARN_ON_ONCE(list_empty(&t->rcu_tasks_exit_list));
rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, t->rcu_tasks_exit_cpu);
raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
list_del_init(&t->rcu_tasks_exit_list);
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
}
/*