diff options
| author |   Paolo Abeni <pabeni@redhat.com> | 2019-04-10 14:32:41 +0200 |
|---|---|---|
| committer |   David S. Miller <davem@davemloft.net> | 2019-04-10 12:20:46 -0700 |
| commit | 73eb628ddfd3884d1e58a8022de2e78de7807fc6 (patch) | |
| tree | f9963afb03df6761396729cfad94621e7d3d5ab0 /net/sched/sch_generic.c | |
| parent | net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too (diff) | |
| download | linux-dev-73eb628ddfd3884d1e58a8022de2e78de7807fc6.tar.xz linux-dev-73eb628ddfd3884d1e58a8022de2e78de7807fc6.zip | |
Revert: "net: sched: put back q.qlen into a single location"
This revert commit 46b1c18f9deb ("net: sched: put back q.qlen into
a single location").
After the previous patch, when a NOLOCK qdisc is enslaved to a
locking qdisc it switches to global stats accounting. As a consequence,
when a classful qdisc accesses directly a child qdisc's qlen, such
qdisc is not doing per CPU accounting and qlen value is consistent.
In the control path nobody uses directly qlen since commit
e5f0e8f8e45 ("net: sched: introduce and use qdisc tree flush/purge
helpers"), so we can remove the contented atomic ops from the
datapath.
v1 -> v2:
- complete the qdisc_qstats_atomic_qlen_dec() ->
qdisc_qstats_cpu_qlen_dec() replacement, fix build issue
- more descriptive commit message
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/sch_generic.c')
| -rw-r--r-- | net/sched/sch_generic.c | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 12a6e1a39fa0..848aab3693bd 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) skb = __skb_dequeue(&q->skb_bad_txq); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); - qdisc_qstats_atomic_qlen_dec(q); + qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; @@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_inc(q, skb); - qdisc_qstats_atomic_qlen_inc(q); + qdisc_qstats_cpu_qlen_inc(q); } else { qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; @@ -136,7 +136,7 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_requeues_inc(q); qdisc_qstats_cpu_backlog_inc(q, skb); - qdisc_qstats_atomic_qlen_inc(q); + qdisc_qstats_cpu_qlen_inc(q); } else { q->qstats.requeues++; qdisc_qstats_backlog_inc(q, skb); @@ -236,7 +236,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, skb = __skb_dequeue(&q->gso_skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); - qdisc_qstats_atomic_qlen_dec(q); + qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; @@ -694,6 +694,7 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); q->backlog = 0; + q->qlen = 0; } } |