| Message ID | 20220526070145.127019-1-gjfang@linux.alibaba.com (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [v2] net: sched: add barrier to fix packet stuck problem for lockless qdisc | expand |
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9bab396c1f3b..8a8738642ca0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -229,6 +229,9 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); + /* ensure ordering between spin_unlock() and test_bit() */ + smp_mb(); + if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc);
In qdisc_run_end(), the spin_unlock() only has store-release semantic, which guarantees all earlier memory access are visible before it. But the subsequent test_bit() may be reordered ahead of the spin_unlock(), and may cause a packet stuck problem. The concurrent operations can be described as below, CPU 0 | CPU 1 qdisc_run_end() | qdisc_run_begin() . | . ----> /* may be reorderd here */ | . | . | . | spin_unlock() | set_bit() | . | smp_mb__after_atomic() ---- test_bit() | spin_trylock() . | . Consider the following sequence of events: CPU 0 reorder test_bit() ahead and see MISSED = 0 CPU 1 calls set_bit() CPU 1 calls spin_trylock() and return fail CPU 0 executes spin_unlock() At the end of the sequence, CPU 0 calls spin_unlock() and does nothing because it see MISSED = 0. The skb on CPU 1 has beed enqueued but no one take it, until the next cpu pushing to the qdisc (if ever ...) will notice and dequeue it. So one explicit barrier is needed between spin_unlock() and test_bit() to ensure the correct order. Fixes: 89837eb4b246 ("net: sched: add barrier to ensure correct ordering for lockless qdisc") Signed-off-by: Guoju Fang <gjfang@linux.alibaba.com> --- include/net/sch_generic.h | 3 +++ 1 file changed, 3 insertions(+)