Re: [RFC v3] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc

2021-03-23 Thread Vladimir Oltean
On Mon, Mar 22, 2021 at 10:00:33PM +0200, Vladimir Oltean wrote: > Hi Yunsheng, > > On Mon, Mar 22, 2021 at 05:09:16PM +0800, Yunsheng Lin wrote: > > 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 beca

Re: [RFC v3] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc

2021-03-23 Thread Yunsheng Lin
On 2021/3/23 14:37, Ahmad Fatoum wrote: > Hi, > > On 22.03.21 10:09, Yunsheng Lin wrote: >> 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 >> i

Re: [RFC v3] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc

2021-03-22 Thread Ahmad Fatoum
Hi, On 22.03.21 10:09, Yunsheng Lin wrote: > 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 cal

Re: [RFC v3] net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc

2021-03-22 Thread Vladimir Oltean
Hi Yunsheng, On Mon, Mar 22, 2021 at 05:09:16PM +0800, Yunsheng Lin wrote: > 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