net: sched: avoid unnecessary seqcount operation for lockless qdisc

qdisc->running seqcount operation is mainly used to do heuristic
locking on q->busylock for locked qdisc, see qdisc_is_running()
and __dev_xmit_skb().

So avoid doing seqcount operation for qdisc with TCQ_F_NOLOCK
flag.
Acked-by: Jakub Kicinski <kuba@kernel.org>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sch_generic.h

@@ -188,6 +188,7 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 
 nolock_empty:
 		WRITE_ONCE(qdisc->empty, false);
+		return true;
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
 	}
@@ -201,7 +202,6 @@ 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) {
 		spin_unlock(&qdisc->seqlock);
 
@@ -210,6 +210,8 @@ static inline void qdisc_run_end(struct Qdisc *qdisc)
 			clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
 			__netif_schedule(qdisc);
 		}
+	} else {
+		write_seqcount_end(&qdisc->running);
 	}
 }