RE: [PATCH] rcu-tasks: Directly invoke rcuwait_wake_up() in call_rcu_tasks_generic()

[Zhuo, Qiuxu]

> From: Zqiang <qiang1.zhang@xxxxxxxxx>
> Sent: Thursday, February 23, 2023 2:30 PM
> To: paulmck@xxxxxxxxxx; frederic@xxxxxxxxxx; quic_neeraju@xxxxxxxxxxx;
> joel@xxxxxxxxxxxxxxxxx
> Cc: rcu@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx
> Subject: [PATCH] rcu-tasks: Directly invoke rcuwait_wake_up() in
> call_rcu_tasks_generic()
> 
> According to commit '3063b33a347c ("Avoid raw-spinlocked wakeups from
> call_rcu_tasks_generic()")', the grace-period kthread is delayed to wakeup
> using irq_work_queue() is because if the caller of
> call_rcu_tasks_generic() holds a raw spinlock, when the kernel is built with
> CONFIG_PROVE_RAW_LOCK_NESTING=y, due to a spinlock will be hold in
> wake_up(), so the lockdep splats will happen. but now using
> rcuwait_wake_up() to wakeup grace-period kthread instead of wake_up(), in
> rcuwait_wake_up() no spinlock will be acquired, so this commit remove using

There are still spinlock-acquisition and spinlock-release invocations within the call path from rcuwait_wake_up().

rcuwait_wake_up() -> wake_up_process() -> try_to_wake_up(), then:

    raw_spin_lock_irqsave()
    ...
    raw_spin_unlock_irqrestore


> irq_work_queue(), invoke rcuwait_wake_up() directly in
> call_rcu_tasks_generic().
> 
> Signed-off-by: Zqiang <qiang1.zhang@xxxxxxxxx>
> ---
>  kernel/rcu/tasks.h | 16 +---------------
>  1 file changed, 1 insertion(+), 15 deletions(-)
> 
> diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index
> baf7ec178155..757b8c6da1ad 100644
> --- a/kernel/rcu/tasks.h
> +++ b/kernel/rcu/tasks.h
> @@ -39,7 +39,6 @@ struct rcu_tasks_percpu {
>  	unsigned long rtp_jiffies;
>  	unsigned long rtp_n_lock_retries;
>  	struct work_struct rtp_work;
> -	struct irq_work rtp_irq_work;
>  	struct rcu_head barrier_q_head;
>  	struct list_head rtp_blkd_tasks;
>  	int cpu;
> @@ -112,12 +111,9 @@ struct rcu_tasks {
>  	char *kname;
>  };
> 
> -static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp);
> -
>  #define DEFINE_RCU_TASKS(rt_name, gp, call, n)
> 			\
>  static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = {
> 			\
>  	.lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name ##
> __percpu.cbs_pcpu_lock),		\
> -	.rtp_irq_work = IRQ_WORK_INIT_HARD(call_rcu_tasks_iw_wakeup),
> 			\
>  };
> 		\
>  static struct rcu_tasks rt_name =
> 		\
>  {
> 		\
> @@ -273,16 +269,6 @@ static void cblist_init_generic(struct rcu_tasks *rtp)
>  	pr_info("%s: Setting shift to %d and lim to %d.\n", __func__,
> data_race(rtp->percpu_enqueue_shift), data_race(rtp-
> >percpu_enqueue_lim));
>  }
> 
> -// IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
> -static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp) -{
> -	struct rcu_tasks *rtp;
> -	struct rcu_tasks_percpu *rtpcp = container_of(iwp, struct
> rcu_tasks_percpu, rtp_irq_work);
> -
> -	rtp = rtpcp->rtpp;
> -	rcuwait_wake_up(&rtp->cbs_wait);
> -}
> -
>  // Enqueue a callback for the specified flavor of Tasks RCU.
>  static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
>  				   struct rcu_tasks *rtp)
> @@ -334,7 +320,7 @@ static void call_rcu_tasks_generic(struct rcu_head
> *rhp, rcu_callback_t func,
>  	rcu_read_unlock();
>  	/* We can't create the thread unless interrupts are enabled. */
>  	if (needwake && READ_ONCE(rtp->kthread_ptr))
> -		irq_work_queue(&rtpcp->rtp_irq_work);
> +		rcuwait_wake_up(&rtp->cbs_wait);
>  }
> 
>  // RCU callback function for rcu_barrier_tasks_generic().
> --
> 2.25.1