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>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
---
Thank you for reviewing this.
Changes in v2:
- Move the tracepoints before printing out stall messages.
Changes in v3:
- Rebase on dev in linux-rcu.git
include/trace/events/rcu.h | 28 ++++++++++++++++++++++++++++
kernel/rcu/tree_exp.h | 1 +
kernel/rcu/tree_stall.h | 2 ++
3 files changed, 31 insertions(+)
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5fc29400e1a2..c7711e9b6900 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 6c6ff06d4ae6..2796084ef85a 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -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;
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 475b26171b20..59b95cc5cbdf 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -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());
--
2.17.1
