rcu: Check callback-invocation time limit for rcuc kthreads

Currently, a callback-invocation time limit is enforced only for
callbacks invoked from the softirq environment, the rationale being
that when callbacks are instead invoked from rcuc and rcuoc kthreads,
these callbacks cannot be holding up other softirq vectors.

Which is in fact true.  However, if an rcuc kthread spends too much time
invoking callbacks, it can delay quiescent-state reports from its CPU,
which can also be a problem.

This commit therefore applies the callback-invocation time limit to
callback invocation from the rcuc kthreads as well as from softirq.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

1 files changed, 19 insertions, 9 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f52ff7241041..9a5c160186d1 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2046,6 +2046,13 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
 	rcu_report_qs_rdp(rdp);
 }
 
+/* Return true if callback-invocation time limit exceeded. */
+static bool rcu_do_batch_check_time(long count, long tlimit)
+{
+	// Invoke local_clock() only once per 32 consecutive callbacks.
+	return unlikely(tlimit) && !likely(count & 31) && local_clock() >= tlimit;
+}
+
 /*
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Throttle as specified by rdp->blimit.
@@ -2082,7 +2089,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	div = READ_ONCE(rcu_divisor);
 	div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
 	bl = max(rdp->blimit, pending >> div);
-	if (in_serving_softirq() && unlikely(bl > 100)) {
+	if ((in_serving_softirq() || rdp->rcu_cpu_kthread_status == RCU_KTHREAD_RUNNING) &&
+	    unlikely(bl > 100)) {
 		long rrn = READ_ONCE(rcu_resched_ns);
 
 		rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
@@ -2126,21 +2134,23 @@ static void rcu_do_batch(struct rcu_data *rdp)
 			 * Make sure we don't spend too much time here and deprive other
 			 * softirq vectors of CPU cycles.
 			 */
-			if (unlikely(tlimit)) {
-				/* only call local_clock() every 32 callbacks */
-				if (likely((count & 31) || local_clock() < tlimit))
-					continue;
-				/* Exceeded the time limit, so leave. */
+			if (rcu_do_batch_check_time(count, tlimit))
 				break;
-			}
 		} else {
-			// In rcuoc context, so no worries about depriving
-			// other softirq vectors of CPU cycles.
+			// In rcuc/rcuoc context, so no worries about
+			// depriving other softirq vectors of CPU cycles.
 			local_bh_enable();
 			lockdep_assert_irqs_enabled();
 			cond_resched_tasks_rcu_qs();
 			lockdep_assert_irqs_enabled();
 			local_bh_disable();
+			// But rcuc kthreads can delay quiescent-state
+			// reporting, so check time limits for them.
+			if (rdp->rcu_cpu_kthread_status == RCU_KTHREAD_RUNNING &&
+			    rcu_do_batch_check_time(count, tlimit)) {
+				rdp->rcu_cpu_has_work = 1;
+				break;
+			}
 		}
 	}