Re: [PATCH v2] sched/debug, sys_info: Introduce SYS_INFO_CPU_RUNQUEUES

[Peter Zijlstra]

On Fri, Sep 11, 2026 at 09:32:40PM -0400, Aaron Tomlin wrote:
> When investigating kernel panics, inspectability of per-CPU runqueues
> and runnable task states is valuable for diagnosing CPU starvation
> priority inversion, etc.
> 
> While debugfs (/sys/kernel/debug/sched/debug) exposes runqueue metrics
> to userspace, these details are not captured during an automated kernel
> panic or crash dump. Capturing per-CPU runqueue state directly into
> log_buf fills this diagnostic gap for post-mortem crash analysis.

Uh, crash-dump preserves everything.


>  	rcu_read_lock();
>  	for_each_process_thread(g, p) {
>  		if (task_cpu(p) != rq_cpu)
>  			continue;
>  
> -		print_task(m, rq, p);
> +		if (queued_only && !task_current(rq, p) && !task_on_rq_queued(p))
> +			continue;
> +
> +		print_task(m, rq, p, show_cgroup_path);
>  	}
>  	rcu_read_unlock();
>  }
> @@ -1234,7 +1242,7 @@ do {									\
>  	print_rt_stats(m, cpu);
>  	print_dl_stats(m, cpu);
>  
> -	print_rq(m, rq, cpu);
> +	print_rq(m, rq, cpu, true, false);
>  	SEQ_printf(m, "\n");
>  }
>  
> @@ -1322,6 +1330,48 @@ void sysrq_sched_debug_show(void)
>  	}
>  }
>  
> +void sched_show_runqueues(void)
> +{
> +	int cpu;
> +
> +	pr_info("CPU Runqueues:\n");
> +	for_each_online_cpu(cpu) {
> +		struct rq *rq = cpu_rq(cpu);
> +		struct task_struct *curr;
> +		unsigned int nr_running;
> +		u64 nr_switches;
> +		unsigned long flags;
> +		bool locked;
> +
> +		touch_nmi_watchdog();
> +		touch_all_softlockup_watchdogs();
> +
> +		rcu_read_lock();
> +		local_irq_save(flags);
> +		locked = raw_spin_rq_trylock(rq);
> +		if (locked) {
> +			nr_running = rq->nr_running;
> +			nr_switches = rq->nr_switches;
> +			curr = rcu_dereference(rq->curr);
> +			raw_spin_rq_unlock(rq);
> +		} else {
> +			nr_running = READ_ONCE(rq->nr_running);
> +			nr_switches = READ_ONCE(rq->nr_switches);
> +			curr = rcu_dereference(rq->curr);
> +		}
> +		local_irq_restore(flags);

This seems to want to avoid deadlocking on rq->lock, but then
print_rq()->print_cfs_stats() will unconditionally take rq->lock again.

So meh.

> +
> +		pr_info("cpu#%d: nr_running:%u switches:%llu curr:%s[%d]%s\n",
> +			cpu, nr_running, nr_switches,
> +			curr ? curr->comm : "<none>",
> +			curr ? task_pid_nr(curr) : -1,
> +			locked ? "" : " (contended)");
> +
> +		print_rq(NULL, rq, cpu, false, true);
> +		rcu_read_unlock();
> +	}
> +}
> +
>  /*
>   * This iterator needs some explanation.
>   * It returns 1 for the header position.
> diff --git a/lib/sys_info.c b/lib/sys_info.c
> index f32a06ec9ed4..fc5bfcc121de 100644
> --- a/lib/sys_info.c
> +++ b/lib/sys_info.c
> @@ -22,6 +22,7 @@ static const char * const si_names[] = {
>  	[ilog2(SYS_INFO_PANIC_CONSOLE_REPLAY)]	= "",
>  	[ilog2(SYS_INFO_ALL_BT)]		= "all_bt",
>  	[ilog2(SYS_INFO_BLOCKED_TASKS)]		= "blocked_tasks",
> +	[ilog2(SYS_INFO_CPU_RUNQUEUES)]		= "cpu_runqueues",
>  };
>  
>  /*
> @@ -158,6 +159,9 @@ static void __sys_info(unsigned long si_mask)
>  
>  	if (si_mask & SYS_INFO_BLOCKED_TASKS)
>  		show_state_filter(TASK_UNINTERRUPTIBLE);
> +
> +	if (si_mask & SYS_INFO_CPU_RUNQUEUES)
> +		sched_show_runqueues();
>  }

I really don't know if this is worth the trouble. I have *never* needed
this.