Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK
flag set, but queue discipline by-pass does not work for lockless
qdisc because skb is always enqueued to qdisc even when the qdisc
is empty, see __dev_xmit_skb().

This patch calles sch_direct_xmit() to transmit the skb directly
to the driver for empty lockless qdisc too, which aviod enqueuing
and dequeuing operation. qdisc->empty is set to false whenever a
skb is enqueued, and is set to true when skb dequeuing return NULL,
see pfifo_fast_dequeue().

Also, qdisc is scheduled at the end of qdisc_run_end() when q->empty
is false to avoid packet stuck problem.

The performance for ip_forward test increases about 10% with this
patch.

Signed-off-by: Yunsheng Lin <linyunsh...@huawei.com>
---
 include/net/sch_generic.h |  7 +++++--
 net/core/dev.c            | 11 +++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 2d6eb60..6591356 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -161,7 +161,6 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
        if (qdisc->flags & TCQ_F_NOLOCK) {
                if (!spin_trylock(&qdisc->seqlock))
                        return false;
-               WRITE_ONCE(qdisc->empty, false);
        } else if (qdisc_is_running(qdisc)) {
                return false;
        }
@@ -176,8 +175,12 @@ 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(!READ_ONCE(qdisc->empty)))
+                       __netif_schedule(qdisc);
+       }
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2bfdd52..fa8504d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3791,7 +3791,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, 
struct Qdisc *q,
        qdisc_calculate_pkt_len(skb, q);
 
        if (q->flags & TCQ_F_NOLOCK) {
+               if (q->flags & TCQ_F_CAN_BYPASS && READ_ONCE(q->empty) && 
qdisc_run_begin(q)) {
+                       qdisc_bstats_cpu_update(q, skb);
+
+                       if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && 
!READ_ONCE(q->empty))
+                               __qdisc_run(q);
+
+                       qdisc_run_end(q);
+                       return NET_XMIT_SUCCESS;
+               }
+
                rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+               WRITE_ONCE(q->empty, false);
                qdisc_run(q);
 
                if (unlikely(to_free))
-- 
2.7.4

Reply via email to