net: sch: eliminate unnecessary RCU waits in mini_qdisc_pair_swap()

Currently rcu_barrier() is used to ensure that no readers of the
inactive mini_Qdisc buffer remain before it is reused. This waits for
any pending RCU callbacks to complete, when all that is actually
required is to wait for one RCU grace period to elapse after the buffer
was made inactive. This means that using rcu_barrier() may result in
unnecessary waits.

To improve this, store the current RCU state when a buffer is made
inactive and use poll_state_synchronize_rcu() to check whether a full
grace period has elapsed before reusing it. If a full grace period has
not elapsed, wait for a grace period to elapse, and in the non-RT case
use synchronize_rcu_expedited() to hasten it.

Since this approach eliminates the RCU callback it is no longer
necessary to synchronize_rcu() in the tp_head==NULL case. However, the
RCU state should still be saved for the previously active buffer.

Before this change I would typically see mini_qdisc_pair_swap() take
tens of milliseconds to complete. After this change it typcially
finishes in less than 1 ms, and often it takes just a few microseconds.

Thanks to Paul for walking me through the options for improving this.

Cc: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Seth Forshee <sforshee@digitalocean.com>
Link: https://lore.kernel.org/r/20211026130700.121189-1-seth@forshee.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 19 insertions, 19 deletions

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index b0ff0dff2773..24899efc51be 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1487,10 +1487,6 @@ void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64)
 }
 EXPORT_SYMBOL(psched_ppscfg_precompute);
 
-static void mini_qdisc_rcu_func(struct rcu_head *head)
-{
-}
-
 void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 			  struct tcf_proto *tp_head)
 {
@@ -1503,28 +1499,30 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 
 	if (!tp_head) {
 		RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
-		/* Wait for flying RCU callback before it is freed. */
-		rcu_barrier();
-		return;
-	}
+	} else {
+		miniq = !miniq_old || miniq_old == &miniqp->miniq2 ?
+			&miniqp->miniq1 : &miniqp->miniq2;
 
-	miniq = !miniq_old || miniq_old == &miniqp->miniq2 ?
-		&miniqp->miniq1 : &miniqp->miniq2;
+		/* We need to make sure that readers won't see the miniq
+		 * we are about to modify. So ensure that at least one RCU
+		 * grace period has elapsed since the miniq was made
+		 * inactive.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			cond_synchronize_rcu(miniq->rcu_state);
+		else if (!poll_state_synchronize_rcu(miniq->rcu_state))
+			synchronize_rcu_expedited();
 
-	/* We need to make sure that readers won't see the miniq
-	 * we are about to modify. So wait until previous call_rcu callback
-	 * is done.
-	 */
-	rcu_barrier();
-	miniq->filter_list = tp_head;
-	rcu_assign_pointer(*miniqp->p_miniq, miniq);
+		miniq->filter_list = tp_head;
+		rcu_assign_pointer(*miniqp->p_miniq, miniq);
+	}
 
 	if (miniq_old)
-		/* This is counterpart of the rcu barriers above. We need to
+		/* This is counterpart of the rcu sync above. We need to
 		 * block potential new user of miniq_old until all readers
 		 * are not seeing it.
 		 */
-		call_rcu(&miniq_old->rcu, mini_qdisc_rcu_func);
+		miniq_old->rcu_state = start_poll_synchronize_rcu();
 }
 EXPORT_SYMBOL(mini_qdisc_pair_swap);
 
@@ -1543,6 +1541,8 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
 	miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats;
 	miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats;
 	miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats;
+	miniqp->miniq1.rcu_state = get_state_synchronize_rcu();
+	miniqp->miniq2.rcu_state = miniqp->miniq1.rcu_state;
 	miniqp->p_miniq = p_miniq;
 }
 EXPORT_SYMBOL(mini_qdisc_pair_init);