From b9014deb33e6a26a6fb11e0464b0376bd4ede9af Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 5 Feb 2024 13:08:22 -0800 Subject: [PATCH] rcu-tasks: Add data to eliminate RCU-tasks/do_exit() deadlocks BugLink: https://bugs.launchpad.net/bugs/2089884 [ Upstream commit bfe93930ea1ea3c6c115a7d44af6e4fea609067e ] Holding a mutex across synchronize_rcu_tasks() and acquiring that same mutex in code called from do_exit() after its call to exit_tasks_rcu_start() but before its call to exit_tasks_rcu_stop() results in deadlock. This is by design, because tasks that are far enough into do_exit() are no longer present on the tasks list, making it a bit difficult for RCU Tasks to find them, let alone wait on them to do a voluntary context switch. However, such deadlocks are becoming more frequent. In addition, lockdep currently does not detect such deadlocks and they can be difficult to reproduce. In addition, if a task voluntarily context switches during that time (for example, if it blocks acquiring a mutex), then this task is in an RCU Tasks quiescent state. And with some adjustments, RCU Tasks could just as well take advantage of that fact. This commit therefore adds the data structures that will be needed to rely on these quiescent states and to eliminate these deadlocks. Link: https://lore.kernel.org/all/20240118021842.290665-1-chenzhongjin@huawei.com/ Reported-by: Chen Zhongjin Reported-by: Yang Jihong Signed-off-by: Paul E. McKenney Tested-by: Yang Jihong Tested-by: Chen Zhongjin Reviewed-by: Frederic Weisbecker Signed-off-by: Boqun Feng Stable-dep-of: fd70e9f1d85f ("rcu-tasks: Fix access non-existent percpu rtpcp variable in rcu_tasks_need_gpcb()") Signed-off-by: Sasha Levin (cherry picked from commit dc5d4d4c12246b802177742e965fcf81691d2da8 linux-6.6.y) [koichiroden: pulled from v6.6.60 as prerequisite for the subsequent commit] Signed-off-by: Koichiro Den Signed-off-by: Roxana Nicolescu --- include/linux/sched.h | 2 ++ kernel/rcu/tasks.h | 2 ++ 2 files changed, 4 insertions(+) diff --git a/include/linux/sched.h b/include/linux/sched.h index 620c335b7099..19e7848678c6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -858,6 +858,8 @@ struct task_struct { u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; + int rcu_tasks_exit_cpu; + struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index e6be90cf0e2b..ac76664d5499 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -32,6 +32,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp); * @rtp_irq_work: IRQ work queue for deferred wakeups. * @barrier_q_head: RCU callback for barrier operation. * @rtp_blkd_tasks: List of tasks blocked as readers. + * @rtp_exit_list: List of tasks in the latter portion of do_exit(). * @cpu: CPU number corresponding to this entry. * @rtpp: Pointer to the rcu_tasks structure. */ @@ -46,6 +47,7 @@ struct rcu_tasks_percpu { struct irq_work rtp_irq_work; struct rcu_head barrier_q_head; struct list_head rtp_blkd_tasks; + struct list_head rtp_exit_list; int cpu; struct rcu_tasks *rtpp; };