Re: [PATCH net v8 1/3] net: sched: fix packet stuck problem for lockless qdisc

[Cong Wang <xiyou.wangcong@gmail.com>]

On Thu, May 13, 2021 at 7:27 PM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>  struct qdisc_size_table {
> @@ -159,8 +160,33 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
>  static inline bool qdisc_run_begin(struct Qdisc *qdisc)
>  {
>         if (qdisc->flags & TCQ_F_NOLOCK) {
> +               if (spin_trylock(&qdisc->seqlock))
> +                       goto nolock_empty;
> +
> +               /* If the MISSED flag is set, it means other thread has
> +                * set the MISSED flag before second spin_trylock(), so
> +                * we can return false here to avoid multi cpus doing
> +                * the set_bit() and second spin_trylock() concurrently.
> +                */
> +               if (test_bit(__QDISC_STATE_MISSED, &qdisc->state))
> +                       return false;
> +
> +               /* Set the MISSED flag before the second spin_trylock(),
> +                * if the second spin_trylock() return false, it means
> +                * other cpu holding the lock will do dequeuing for us
> +                * or it will see the MISSED flag set after releasing
> +                * lock and reschedule the net_tx_action() to do the
> +                * dequeuing.
> +                */
> +               set_bit(__QDISC_STATE_MISSED, &qdisc->state);
> +
> +               /* Retry again in case other CPU may not see the new flag
> +                * after it releases the lock at the end of qdisc_run_end().
> +                */
>                 if (!spin_trylock(&qdisc->seqlock))
>                         return false;
> +
> +nolock_empty:
>                 WRITE_ONCE(qdisc->empty, false);
>         } else if (qdisc_is_running(qdisc)) {
>                 return false;
> @@ -176,8 +202,15 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
>  static inline void qdisc_run_end(struct Qdisc *qdisc)
>  {
>         write_seqcount_end(&qdisc->running);
> -       if (qdisc->flags & TCQ_F_NOLOCK)
> +       if (qdisc->flags & TCQ_F_NOLOCK) {
>                 spin_unlock(&qdisc->seqlock);
> +
> +               if (unlikely(test_bit(__QDISC_STATE_MISSED,
> +                                     &qdisc->state))) {
> +                       clear_bit(__QDISC_STATE_MISSED, &qdisc->state);


We have test_and_clear_bit() which is atomic, test_bit()+clear_bit()
is not.


> +                       __netif_schedule(qdisc);
> +               }
> +       }
>  }
>
>  static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
> diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
> index 44991ea..795d986 100644
> --- a/net/sched/sch_generic.c
> +++ b/net/sched/sch_generic.c
> @@ -640,8 +640,10 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
>  {
>         struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
>         struct sk_buff *skb = NULL;
> +       bool need_retry = true;
>         int band;
>
> +retry:
>         for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
>                 struct skb_array *q = band2list(priv, band);
>
> @@ -652,6 +654,23 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
>         }
>         if (likely(skb)) {
>                 qdisc_update_stats_at_dequeue(qdisc, skb);
> +       } else if (need_retry &&
> +                  test_bit(__QDISC_STATE_MISSED, &qdisc->state)) {
> +               /* Delay clearing the STATE_MISSED here to reduce
> +                * the overhead of the second spin_trylock() in
> +                * qdisc_run_begin() and __netif_schedule() calling
> +                * in qdisc_run_end().
> +                */
> +               clear_bit(__QDISC_STATE_MISSED, &qdisc->state);

Ditto.

> +
> +               /* Make sure dequeuing happens after clearing
> +                * STATE_MISSED.
> +                */
> +               smp_mb__after_atomic();
> +
> +               need_retry = false;
> +
> +               goto retry;

Two concurrent pfifo_fast_dequeue() would possibly retry it at the
same time when they test __QDISC_STATE_MISSED at the same
time and get true. Is this a problem?

Also, any reason why you want pfifo_fast to handle a generic
Qdisc flag? IOW, why not handle this logic in, for example,
qdisc_restart()?

Thanks.