net: sched: fix skb leak in dev_requeue_skb()

When dev_requeue_skb() is called with bulked skb list, only the
first skb of the list will be requeued to qdisc layer, and leak
the others without free them.

TCP is broken due to skb leak since no free skb will be considered
as still in the host queue and never be retransmitted. This happend
when dev_requeue_skb() called from qdisc_restart().
  qdisc_restart
  |-- dequeue_skb
  |-- sch_direct_xmit()
      |-- dev_requeue_skb() <-- skb may bluked

Fix dev_requeue_skb() to requeue the full bluked list. Also change
to use __skb_queue_tail() in __dev_requeue_skb() to avoid skb out
of order.

Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index cc069b2acf0e36ed091f853d0f3fb9951f48c8ba..a883c501d5ec2721764a1fc5e89e5ce1614876bc 100644 (file)
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -112,10 +112,16 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 
 static inline int __dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-       __skb_queue_head(&q->gso_skb, skb);
-       q->qstats.requeues++;
-       qdisc_qstats_backlog_inc(q, skb);
-       q->q.qlen++;    /* it's still part of the queue */
+       while (skb) {
+               struct sk_buff *next = skb->next;
+
+               __skb_queue_tail(&q->gso_skb, skb);
+               q->qstats.requeues++;
+               qdisc_qstats_backlog_inc(q, skb);
+               q->q.qlen++;    /* it's still part of the queue */
+
+               skb = next;
+       }
        __netif_schedule(q);
 
        return 0;
@@ -126,12 +132,19 @@ static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
        spinlock_t *lock = qdisc_lock(q);
 
        spin_lock(lock);
-       __skb_queue_tail(&q->gso_skb, skb);
+       while (skb) {
+               struct sk_buff *next = skb->next;
+
+               __skb_queue_tail(&q->gso_skb, skb);
+
+               qdisc_qstats_cpu_requeues_inc(q);
+               qdisc_qstats_cpu_backlog_inc(q, skb);
+               qdisc_qstats_cpu_qlen_inc(q);
+
+               skb = next;
+       }
        spin_unlock(lock);
 
-       qdisc_qstats_cpu_requeues_inc(q);
-       qdisc_qstats_cpu_backlog_inc(q, skb);
-       qdisc_qstats_cpu_qlen_inc(q);
        __netif_schedule(q);
 
        return 0;