rcu: Add per-CPU rcuc task dumps to RCU CPU stall warnings

When the rcutree.use_softirq kernel boot parameter is set to zero, all
RCU_SOFTIRQ processing is carried out by the per-CPU rcuc kthreads.
If these kthreads are being starved, quiescent states will not be
reported, which in turn means that the grace period will not end, which
can in turn trigger RCU CPU stall warnings.  This commit therefore dumps
stack traces of stalled CPUs' rcuc kthreads, which can help identify
what is preventing those kthreads from running.

Suggested-by: Ammar Faizi <ammarfaizi2@gnuweeb.org>
Reviewed-by: Ammar Faizi <ammarfaizi2@gnuweeb.org>
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

4 files changed, 42 insertions, 0 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9e4c5b281f00..bd9b2af247ab 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2850,10 +2850,12 @@ static void rcu_cpu_kthread(unsigned int cpu)
 {
 	unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
 	char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
+	unsigned long *j = this_cpu_ptr(&rcu_data.rcuc_activity);
 	int spincnt;
 
 	trace_rcu_utilization(TPS("Start CPU kthread@rcu_run"));
 	for (spincnt = 0; spincnt < 10; spincnt++) {
+		WRITE_ONCE(*j, jiffies);
 		local_bh_disable();
 		*statusp = RCU_KTHREAD_RUNNING;
 		local_irq_disable();
@@ -2874,6 +2876,7 @@ static void rcu_cpu_kthread(unsigned int cpu)
 	schedule_timeout_idle(2);
 	trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
 	*statusp = RCU_KTHREAD_WAITING;
+	WRITE_ONCE(*j, jiffies);
 }
 
 static struct smp_hotplug_thread rcu_cpu_thread_spec = {
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index e9990945483f..b84cc5742c31 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -239,6 +239,7 @@ struct rcu_data {
 					/* rcuc per-CPU kthread or NULL. */
 	unsigned int rcu_cpu_kthread_status;
 	char rcu_cpu_has_work;
+	unsigned long rcuc_activity;
 
 	/* 7) Diagnostic data, including RCU CPU stall warnings. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 02ac057ba3f8..8167cab1bffc 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -996,12 +996,15 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
  */
 static void rcu_cpu_kthread_setup(unsigned int cpu)
 {
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 #ifdef CONFIG_RCU_BOOST
 	struct sched_param sp;
 
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
+
+	WRITE_ONCE(rdp->rcuc_activity, jiffies);
 }
 
 #ifdef CONFIG_RCU_BOOST
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 21bebf7c9030..0c5d8516516a 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -379,6 +379,15 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp)
 	return j > 2 * HZ;
 }
 
+static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp)
+{
+	unsigned long j = jiffies - READ_ONCE(rdp->rcuc_activity);
+
+	if (jp)
+		*jp = j;
+	return j > 2 * HZ;
+}
+
 /*
  * Print out diagnostic information for the specified stalled CPU.
  *
@@ -430,6 +439,29 @@ static void print_cpu_stall_info(int cpu)
 	       falsepositive ? " (false positive?)" : "");
 }
 
+static void rcuc_kthread_dump(struct rcu_data *rdp)
+{
+	int cpu;
+	unsigned long j;
+	struct task_struct *rcuc;
+
+	rcuc = rdp->rcu_cpu_kthread_task;
+	if (!rcuc)
+		return;
+
+	cpu = task_cpu(rcuc);
+	if (cpu_is_offline(cpu) || idle_cpu(cpu))
+		return;
+
+	if (!rcu_is_rcuc_kthread_starving(rdp, &j))
+		return;
+
+	pr_err("%s kthread starved for %ld jiffies\n", rcuc->comm, j);
+	sched_show_task(rcuc);
+	if (!trigger_single_cpu_backtrace(cpu))
+		dump_cpu_task(cpu);
+}
+
 /* Complain about starvation of grace-period kthread.  */
 static void rcu_check_gp_kthread_starvation(void)
 {
@@ -601,6 +633,9 @@ static void print_cpu_stall(unsigned long gps)
 	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();
 
+	if (!use_softirq)
+		rcuc_kthread_dump(rdp);
+
 	rcu_dump_cpu_stacks();
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);