On Mon, Feb 15, 2021 at 05:53:25PM +0900, Sangmoon Kim wrote:
> The event allows us to trace the RCU stall when
> sysctl_panic_on_rcu_stall is disabled.
>
> The first parameter is the name of RCU flavour like other trace
> events. The second one shows us which function detected stalls.
>
> The RCU stall is mainly caused by external factors such as interrupt
> handling or task scheduling or something else. Therefore, this event
> uses TRACE_EVENT macro, not dedicated one, so that someone interested
> in the RCU stall can use it without CONFIG_RCU_TRACE.
>
> Signed-off-by: Sangmoon Kim <sangmoon.kim@xxxxxxxxxxx>
The patch looks plausible, but I have to ask... Why not instead just
get the existing information out of the console log?
Thanx, Paul
> ---
> include/trace/events/rcu.h | 28 ++++++++++++++++++++++++++++
> kernel/rcu/tree_exp.h | 2 ++
> kernel/rcu/tree_stall.h | 2 ++
> 3 files changed, 32 insertions(+)
>
> diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
> index 155b5cb43cfd..8476f3161bd0 100644
> --- a/include/trace/events/rcu.h
> +++ b/include/trace/events/rcu.h
> @@ -432,6 +432,34 @@ TRACE_EVENT_RCU(rcu_fqs,
> __entry->cpu, __entry->qsevent)
> );
>
> +/*
> + * Tracepoint for RCU stall events. Takes a string identifying the RCU flavor
> + * and a string identifying which function detected the RCU stall as follows:
> + *
> + * "StallDetected": Scheduler-tick detects other CPU's stalls.
> + * "SelfDetected": Scheduler-tick detects a current CPU's stall.
> + * "ExpeditedStall": Expedited grace period detects stalls.
> + */
> +TRACE_EVENT(rcu_stall_warning,
> +
> + TP_PROTO(const char *rcuname, const char *msg),
> +
> + TP_ARGS(rcuname, msg),
> +
> + TP_STRUCT__entry(
> + __field(const char *, rcuname)
> + __field(const char *, msg)
> + ),
> +
> + TP_fast_assign(
> + __entry->rcuname = rcuname;
> + __entry->msg = msg;
> + ),
> +
> + TP_printk("%s %s",
> + __entry->rcuname, __entry->msg)
> +);
> +
> #endif /* #if defined(CONFIG_TREE_RCU) */
>
> /*
> diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> index 8760b6ead770..c16618284cb2 100644
> --- a/kernel/rcu/tree_exp.h
> +++ b/kernel/rcu/tree_exp.h
> @@ -566,6 +566,8 @@ static void synchronize_rcu_expedited_wait(void)
> dump_cpu_task(cpu);
> }
> }
> + trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
> +
> jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
> }
> }
> diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
> index 70d48c52fabc..e93df4fac5b1 100644
> --- a/kernel/rcu/tree_stall.h
> +++ b/kernel/rcu/tree_stall.h
> @@ -531,6 +531,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
>
> rcu_check_gp_kthread_starvation();
>
> + trace_rcu_stall_warning(rcu_state.name, TPS("StallDetected"));
> panic_on_rcu_stall();
>
> rcu_force_quiescent_state(); /* Kick them all. */
> @@ -575,6 +576,7 @@ static void print_cpu_stall(unsigned long gps)
> jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
> raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
>
> + trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected"));
> panic_on_rcu_stall();
>
> /*
> --
> 2.17.1
>
