rcu/tree: Add a trace event for RCU CPU stall warnings

This commit adds a trace event which allows tracing the beginnings of RCU
CPU stall warnings on systems where sysctl_panic_on_rcu_stall is disabled.

The first parameter is the name of RCU flavor like other trace events.
The second parameter indicates whether this is a stall of an expedited
grace period, a self-detected stall of a normal grace period, or a stall
of a normal grace period detected by some CPU other than the one that
is stalled.

RCU CPU stall warnings are often caused by external-to-RCU issues,
for example, in interrupt handling or task scheduling.  Therefore,
this event uses TRACE_EVENT, not TRACE_EVENT_RCU, to avoid requiring
those interested in tracing RCU CPU stalls to rebuild their kernels
with CONFIG_RCU_TRACE=y.

Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Signed-off-by: Sangmoon Kim <sangmoon.kim@samsung.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit is contained in:
Sangmoon Kim 2021-03-02 20:55:15 +09:00 committed by Paul E. McKenney
parent 7e937220af
commit 565cfb9e64
3 changed files with 31 additions and 0 deletions

View File

@ -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) */
/*

View File

@ -521,6 +521,7 @@ static void synchronize_rcu_expedited_wait(void)
if (rcu_stall_is_suppressed())
continue;
panic_on_rcu_stall();
trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
rcu_state.name);
ndetected = 0;

View File

@ -536,6 +536,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
* See Documentation/RCU/stallwarn.rst for info on how to debug
* RCU CPU stall warnings.
*/
trace_rcu_stall_warning(rcu_state.name, TPS("StallDetected"));
pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
@ -606,6 +607,7 @@ static void print_cpu_stall(unsigned long gps)
* See Documentation/RCU/stallwarn.rst for info on how to debug
* RCU CPU stall warnings.
*/
trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected"));
pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
print_cpu_stall_info(smp_processor_id());