On Wed, Oct 23, 2019 at 3:52 AM Vincent Prince <vincent.prince.fr@xxxxxxxxx> wrote: > > There is networking hardware that isn't based on Ethernet for layers 1 and 2. > > For example CAN. > > CAN is a multi-master serial bus standard for connecting Electronic Control > Units [ECUs] also known as nodes. A frame on the CAN bus carries up to 8 bytes > of payload. Frame corruption is detected by a CRC. However frame loss due to > corruption is possible, but a quite unusual phenomenon. > > While fq_codel works great for TCP/IP, it doesn't for CAN. There are a lot of > legacy protocols on top of CAN, which are not build with flow control or high > CAN frame drop rates in mind. > > When using fq_codel, as soon as the queue reaches a certain delay based length, > skbs from the head of the queue are silently dropped. Silently meaning that the > user space using a send() or similar syscall doesn't get an error. However > TCP's flow control algorithm will detect dropped packages and adjust the > bandwidth accordingly. > > When using fq_codel and sending raw frames over CAN, which is the common use > case, the user space thinks the package has been sent without problems, because > send() returned without an error. pfifo_fast will drop skbs, if the queue > length exceeds the maximum. But with this scheduler the skbs at the tail are > dropped, an error (-ENOBUFS) is propagated to user space. So that the user > space can slow down the package generation. > > On distributions, where fq_codel is made default via CONFIG_DEFAULT_NET_SCH > during compile time, or set default during runtime with sysctl > net.core.default_qdisc (see [1]), we get a bad user experience. In my test case > with pfifo_fast, I can transfer thousands of million CAN frames without a frame > drop. On the other hand with fq_codel there is more then one lost CAN frame per > thousand frames. > > As pointed out fq_codel is not suited for CAN hardware, so this patch changes > attach_one_default_qdisc() to use pfifo_fast for "ARPHRD_CAN" network devices. > > During transition of a netdev from down to up state the default queuing > discipline is attached by attach_default_qdiscs() with the help of > attach_one_default_qdisc(). This patch modifies attach_one_default_qdisc() to > attach the pfifo_fast (pfifo_fast_ops) if the network device type is > "ARPHRD_CAN". > > [1] https://github.com/systemd/systemd/issues/9194 > > Suggested-by: Marc Kleine-Budde <mkl@xxxxxxxxxxxxxx> > Signed-off-by: Marc Kleine-Budde <mkl@xxxxxxxxxxxxxx> > Signed-off-by: Vincent Prince <vincent.prince.fr@xxxxxxxxx> > --- > Changes in v4: > - add Marc credit to commit log > > Changes in v3: > - add description > > Changes in v2: > - reformat patch > > net/sched/sch_generic.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c > index 77b289d..dfb2982 100644 > --- a/net/sched/sch_generic.c > +++ b/net/sched/sch_generic.c > @@ -1008,6 +1008,8 @@ static void attach_one_default_qdisc(struct net_device *dev, > > if (dev->priv_flags & IFF_NO_QUEUE) > ops = &noqueue_qdisc_ops; > + else if(dev->type == ARPHRD_CAN) > + ops = &pfifo_fast_ops; > > qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); > if (!qdisc) { > -- > 2.7.4 > While I'm delighted to see such a simple patch emerge, openwrt long ago patched out pfifo_fast. pfifo_fast has additional semantics not needed in the can use case either (I think) and "pfifo" is fine, but sure, pfifo_fast if you must. anyway, regardless, that's an easy fix and I hope this fix goes to stable, as I've had nightmares about cars exploding due to out of order can bus operations ever since I learned of this bug. Acked-by: Dave Taht <dave.taht@xxxxxxxxx> -- Dave Täht CTO, TekLibre, LLC http://www.teklibre.com Tel: 1-831-205-9740
