Re: [PATCH] rcu-tasks: Inspect stalled task's trc state in locked state

[Paul E. McKenney]

On Tue, Nov 09, 2021 at 04:52:14PM +0530, Neeraj Upadhyay wrote:
> On RCU tasks trace stall, inspect the RCU-tasks-trace specific
> states of stalled task in locked down state, using try_invoke_
> on_locked_down_task(), to get reliable trc state of a non-running
> stalled task.
> 
> Signed-off-by: Neeraj Upadhyay <quic_neeraju@xxxxxxxxxxx>

Queued for further review and testing, thank you!

Along those lines, what did you do to test this?  I would like to
add that to the commit message.  (The usual approach is to use the
rcutorture.stall_cpu module parameter, in case I have not yet passed
that along.)

							Thanx, Paul

> ---
>  kernel/rcu/tasks.h | 43 ++++++++++++++++++++++++++++++++++---------
>  1 file changed, 34 insertions(+), 9 deletions(-)
> 
> diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
> index e4a32db9f712..4e49b847971b 100644
> --- a/kernel/rcu/tasks.h
> +++ b/kernel/rcu/tasks.h
> @@ -1073,25 +1073,50 @@ static void rcu_tasks_trace_postscan(struct list_head *hop)
>  	// Any tasks that exit after this point will set ->trc_reader_checked.
>  }
>  
> +/* Communicate task state back to the RCU tasks trace stall warning request. */
> +struct trc_stall_chk_rdr {
> +	int nesting;
> +	int ipi_to_cpu;
> +	u8 needqs;
> +};
> +
> +static bool trc_check_slow_task(struct task_struct *t, void *arg)
> +{
> +	struct trc_stall_chk_rdr *trc_rdrp = arg;
> +
> +	if (task_curr(t))
> +		return false; // It is running, so decline to inspect it.
> +	trc_rdrp->nesting = READ_ONCE(t->trc_reader_nesting);
> +	trc_rdrp->ipi_to_cpu = READ_ONCE(t->trc_ipi_to_cpu);
> +	trc_rdrp->needqs = READ_ONCE(t->trc_reader_special.b.need_qs);
> +	return true;
> +}
> +
>  /* Show the state of a task stalling the current RCU tasks trace GP. */
>  static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
>  {
>  	int cpu;
> +	struct trc_stall_chk_rdr trc_rdr;
> +	bool is_idle_tsk = is_idle_task(t);
>  
>  	if (*firstreport) {
>  		pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
>  		*firstreport = false;
>  	}
> -	// FIXME: This should attempt to use try_invoke_on_nonrunning_task().
>  	cpu = task_cpu(t);
> -	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
> -		 t->pid,
> -		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) >= 0],
> -		 ".i"[is_idle_task(t)],
> -		 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
> -		 READ_ONCE(t->trc_reader_nesting),
> -		 " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
> -		 cpu);
> +	if (!try_invoke_on_locked_down_task(t, trc_check_slow_task, &trc_rdr))
> +		pr_alert("P%d: %c\n",
> +			 t->pid,
> +			 ".i"[is_idle_tsk]);
> +	else
> +		pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
> +			 t->pid,
> +			 ".I"[trc_rdr.ipi_to_cpu >= 0],
> +			 ".i"[is_idle_tsk],
> +			 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
> +			 trc_rdr.nesting,
> +			 " N"[!!trc_rdr.needqs],
> +			 cpu);
>  	sched_show_task(t);
>  }
>  
> -- 
> 2.17.1
>