net: sched: avoid costly atomic operation in fq_dequeue()

Standard qdisc API to setup a timer implies an atomic operation on every
packet dequeue : qdisc_unthrottled()

It turns out this is not really needed for FQ, as FQ has no concept of
global qdisc throttling, being a qdisc handling many different flows,
some of them can be throttled, while others are not.

Fix is straightforward : add a 'bool throttle' to
qdisc_watchdog_schedule_ns(), and remove calls to qdisc_unthrottled()
in sch_fq.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 3 insertions, 2 deletions

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c79a226cc25c..2cf61b3e633c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -594,13 +594,14 @@ void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
 }
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
-void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
+void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle)
 {
         if (test_bit(__QDISC_STATE_DEACTIVATED,
                      &qdisc_root_sleeping(wd->qdisc)->state))
                 return;
 
-        qdisc_throttled(wd->qdisc);
+        if (throttle)
+                qdisc_throttled(wd->qdisc);
 
         hrtimer_start(&wd->timer,
                       ns_to_ktime(expires),