Re: [PATCH v6 1/2] rcu: Add RCU stall diagnosis information

From: Frederic Weisbecker <frederic@kernel.org>
To: Zhen Lei <thunder.leizhen@huawei.com>
Cc: "Paul E . McKenney" <paulmck@kernel.org>,
	Neeraj Upadhyay <quic_neeraju@quicinc.com>,
	Josh Triplett <josh@joshtriplett.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Lai Jiangshan <jiangshanlai@gmail.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	rcu@vger.kernel.org, linux-kernel@vger.kernel.org,
	Robert Elliott <elliott@hpe.com>
Subject: Re: [PATCH v6 1/2] rcu: Add RCU stall diagnosis information
Date: Wed, 9 Nov 2022 16:20:17 +0100	[thread overview]
Message-ID: <20221109152017.GA298612@lothringen> (raw)
In-Reply-To: <20221109093739.187-2-thunder.leizhen@huawei.com>

On Wed, Nov 09, 2022 at 05:37:37PM +0800, Zhen Lei wrote:
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index ed93ddb8203d42c..e1ff23b2a14d71d 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -866,6 +866,23 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
>  			rdp->rcu_iw_gp_seq = rnp->gp_seq;
>  			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
>  		}
> +
> +		if (rcu_cpu_stall_cputime && rdp->snap_record.gp_seq != rdp->gp_seq) {
> +			u64 *cpustat;
> +			struct rcu_snap_record *rsrp;
> +
> +			cpustat = kcpustat_cpu(rdp->cpu).cpustat;
> +
> +			rsrp = &rdp->snap_record;
> +			rsrp->cputime_irq     = cpustat[CPUTIME_IRQ];
> +			rsrp->cputime_softirq = cpustat[CPUTIME_SOFTIRQ];
> +			rsrp->cputime_system  = cpustat[CPUTIME_SYSTEM];

You need to use kcpustat_field(), otherwise you'll get stalled values on nohz_full CPUs.

> +			rsrp->nr_hardirqs = kstat_cpu_irqs_sum(rdp->cpu);
> +			rsrp->nr_softirqs = kstat_cpu_softirqs_sum(rdp->cpu);
> +			rsrp->nr_csw = nr_context_switches_cpu(rdp->cpu);
> +			rsrp->jiffies = jiffies;
> +			rsrp->gp_seq = rdp->gp_seq;
> +		}
>  	}
>  
>  	return 0;
> diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
> index 5653560573e22d6..7b6afb9c7b96dbe 100644
> --- a/kernel/rcu/tree_stall.h
> +++ b/kernel/rcu/tree_stall.h
> @@ -428,6 +428,33 @@ static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp
>  	return j > 2 * HZ;
>  }
>  
> +static void print_cpu_stat_info(int cpu)
> +{
> +	u64 *cpustat;
> +	struct rcu_snap_record *rsrp;
> +	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
> +
> +	if (!rcu_cpu_stall_cputime)
> +		return;
> +
> +	rsrp = &rdp->snap_record;
> +	if (rsrp->gp_seq != rdp->gp_seq)
> +		return;
> +
> +	cpustat = kcpustat_cpu(cpu).cpustat;
> +
> +	pr_err("         hardirqs   softirqs   csw/system\n");
> +	pr_err(" number: %8ld %10d %12lld\n",
> +		kstat_cpu_irqs_sum(cpu) - rsrp->nr_hardirqs,
> +		kstat_cpu_softirqs_sum(cpu) - rsrp->nr_softirqs,
> +		nr_context_switches_cpu(cpu) - rsrp->nr_csw);
> +	pr_err("cputime: %8lld %10lld %12lld   ==> %lld(ms)\n",
> +		div_u64(cpustat[CPUTIME_IRQ] - rsrp->cputime_irq, NSEC_PER_MSEC),
> +		div_u64(cpustat[CPUTIME_SOFTIRQ] - rsrp->cputime_softirq, NSEC_PER_MSEC),
> +		div_u64(cpustat[CPUTIME_SYSTEM] - rsrp->cputime_system,
> NSEC_PER_MSEC),

Same here.

Thanks.