net_sched: add the ability to defer skb freeing

qdisc are changed under RTNL protection and often
while blocking BH and root qdisc spinlock.

When lots of skbs need to be dropped, we free
them under these locks causing TX/RX freezes,
and more generally latency spikes.

This commit adds rtnl_kfree_skbs(), used to queue
skbs for deferred freeing.

Actual freeing happens right after RTNL is released,
with appropriate scheduling points.

rtnl_qdisc_drop() can also be used in place
of disc_drop() when RTNL is held.

qdisc_reset_queue() and __qdisc_reset_queue() get
the new behavior, so standard qdiscs like pfifo, pfifo_fast...
have their ->reset() method automatically handled.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 4 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 9a0d177884c6..4f7cee8344c4 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -683,19 +683,21 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 	return skb;
 }
 
-static inline void __qdisc_reset_queue(struct Qdisc *sch,
-				       struct sk_buff_head *list)
+static inline void __qdisc_reset_queue(struct sk_buff_head *list)
 {
 	/*
 	 * We do not know the backlog in bytes of this list, it
 	 * is up to the caller to correct it
 	 */
-	__skb_queue_purge(list);
+	if (!skb_queue_empty(list)) {
+		rtnl_kfree_skbs(list->next, list->prev);
+		__skb_queue_head_init(list);
+	}
 }
 
 static inline void qdisc_reset_queue(struct Qdisc *sch)
 {
-	__qdisc_reset_queue(sch, &sch->q);
+	__qdisc_reset_queue(&sch->q);
 	sch->qstats.backlog = 0;
 }
 
@@ -716,6 +718,12 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	return old;
 }
 
+static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
+{
+	rtnl_kfree_skbs(skb, skb);
+	qdisc_qstats_drop(sch);
+}
+
 static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
 {
 	kfree_skb(skb);