From a90c57f2cedd52a511f739fb55e6244e22e1a2fb Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 14 May 2021 11:16:59 +0800 Subject: net: sched: fix packet stuck problem for lockless qdisc Lockless qdisc has below concurrent problem: cpu0 cpu1 . . q->enqueue . . . qdisc_run_begin() . . . dequeue_skb() . . . sch_direct_xmit() . . . . q->enqueue . qdisc_run_begin() . return and do nothing . . qdisc_run_end() . cpu1 enqueue a skb without calling __qdisc_run() because cpu0 has not released the lock yet and spin_trylock() return false for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb enqueued by cpu1 when calling dequeue_skb() because cpu1 may enqueue the skb after cpu0 calling dequeue_skb() and before cpu0 calling qdisc_run_end(). Lockless qdisc has below another concurrent problem when tx_action is involved: cpu0(serving tx_action) cpu1 cpu2 . . . . q->enqueue . . qdisc_run_begin() . . dequeue_skb() . . . q->enqueue . . . . sch_direct_xmit() . . . qdisc_run_begin() . . return and do nothing . . . clear __QDISC_STATE_SCHED . . qdisc_run_begin() . . return and do nothing . . . . . . qdisc_run_end() . This patch fixes the above data race by: 1. If the first spin_trylock() return false and STATE_MISSED is not set, set STATE_MISSED and retry another spin_trylock() in case other CPU may not see STATE_MISSED after it releases the lock. 2. reschedule if STATE_MISSED is set after the lock is released at the end of qdisc_run_end(). For tx_action case, STATE_MISSED is also set when cpu1 is at the end if qdisc_run_end(), so tx_action will be rescheduled again to dequeue the skb enqueued by cpu2. Clear STATE_MISSED before retrying a dequeuing when dequeuing returns NULL in order to reduce the overhead of the second spin_trylock() and __netif_schedule() calling. Also clear the STATE_MISSED before calling __netif_schedule() at the end of qdisc_run_end() to avoid doing another round of dequeuing in the pfifo_fast_dequeue(). The performance impact of this patch, tested using pktgen and dummy netdev with pfifo_fast qdisc attached: threads without+this_patch with+this_patch delta 1 2.61Mpps 2.60Mpps -0.3% 2 3.97Mpps 3.82Mpps -3.7% 4 5.62Mpps 5.59Mpps -0.5% 8 2.78Mpps 2.77Mpps -0.3% 16 2.22Mpps 2.22Mpps -0.0% Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski Tested-by: Juergen Gross Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- include/net/sch_generic.h | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index f7a6e14491fb..1e625519ae96 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -36,6 +36,7 @@ struct qdisc_rate_table { enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, + __QDISC_STATE_MISSED, }; 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); + __netif_schedule(qdisc); + } + } } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) -- cgit v1.2.3