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>

1 files changed, 35 insertions, 0 deletions

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);