diff mbox series

[net,v7,3/3] net: sched: fix tx action reschedule issue with stopped queue

Message ID 1620868260-32984-4-git-send-email-linyunsheng@huawei.com
State Superseded
Headers show
Series fix packet stuck problem for lockless qdisc | expand

Commit Message

Yunsheng Lin May 13, 2021, 1:11 a.m. UTC
The netdev qeueue might be stopped when byte queue limit has
reached or tx hw ring is full, net_tx_action() may still be
rescheduled endlessly if STATE_MISSED is set, which consumes
a lot of cpu without dequeuing and transmiting any skb because
the netdev queue is stopped, see qdisc_run_end().

This patch fixes it by checking the netdev queue state before
calling qdisc_run() and clearing STATE_MISSED if netdev queue is
stopped during qdisc_run(), the net_tx_action() is recheduled
again when netdev qeueue is restarted, see netif_tx_wake_queue().

As there is time window betewwn netif_xmit_frozen_or_stopped()
checking and STATE_MISSED clearing, between which STATE_MISSED
is set by net_tx_action() scheduled by netif_tx_wake_queue(),
so set the STATE_MISSED again if netdev queue is restarted.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
V7: Fix the netif_tx_wake_queue() data race noted by Jakub.
V6: Drop NET_XMIT_DROP checking for it is not really relevant
    to this patch, and it may cause performance performance
    regression with multi pktgen threads on dummy netdev with
    pfifo_fast qdisc case.
---
 net/core/dev.c          |  3 ++-
 net/sched/sch_generic.c | 27 ++++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/net/core/dev.c b/net/core/dev.c
index d596cd7..ef8cf76 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3853,7 +3853,8 @@  static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	if (q->flags & TCQ_F_NOLOCK) {
 		rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-		qdisc_run(q);
+		if (likely(!netif_xmit_frozen_or_stopped(txq)))
+			qdisc_run(q);
 
 		if (unlikely(to_free))
 			kfree_skb_list(to_free);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index d86c4cc..b129d9b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -35,6 +35,25 @@ 
 const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
 EXPORT_SYMBOL(default_qdisc_ops);
 
+static void qdisc_maybe_stop_tx(struct Qdisc *q,
+				const struct netdev_queue *txq)
+{
+	clear_bit(__QDISC_STATE_MISSED, &q->state);
+
+	/* Make sure the below netif_xmit_frozen_or_stopped()
+	 * checking happens after clearing STATE_MISSED.
+	 */
+	smp_mb__after_atomic();
+
+	/* Checking netif_xmit_frozen_or_stopped() again to
+	 * make sure STATE_MISSED is set if the STATE_MISSED
+	 * set by netif_tx_wake_queue()'s rescheduling of
+	 * net_tx_action() is cleared by the above clear_bit().
+	 */
+	if (!netif_xmit_frozen_or_stopped(txq))
+		set_bit(__QDISC_STATE_MISSED, &q->state);
+}
+
 /* Main transmission queue. */
 
 /* Modifications to data participating in scheduling must be protected with
@@ -74,6 +93,7 @@  static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 			}
 		} else {
 			skb = SKB_XOFF_MAGIC;
+			qdisc_maybe_stop_tx(q, txq);
 		}
 	}
 
@@ -242,6 +262,7 @@  static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			}
 		} else {
 			skb = NULL;
+			qdisc_maybe_stop_tx(q, txq);
 		}
 		if (lock)
 			spin_unlock(lock);
@@ -251,8 +272,10 @@  static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 	*validate = true;
 
 	if ((q->flags & TCQ_F_ONETXQUEUE) &&
-	    netif_xmit_frozen_or_stopped(txq))
+	    netif_xmit_frozen_or_stopped(txq)) {
+		qdisc_maybe_stop_tx(q, txq);
 		return skb;
+	}
 
 	skb = qdisc_dequeue_skb_bad_txq(q);
 	if (unlikely(skb)) {
@@ -311,6 +334,8 @@  bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (!netif_xmit_frozen_or_stopped(txq))
 			skb = dev_hard_start_xmit(skb, dev, txq, &ret);
+		else
+			qdisc_maybe_stop_tx(q, txq);
 
 		HARD_TX_UNLOCK(dev, txq);
 	} else {