netdev - Re: [next-queue PATCH v4 3/4] net/sched: Introduce Credit Based Shaper (CBS) qdisc

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 05 Oct 2017 12:57:34 -0700
From:   Vinicius Costa Gomes <vinicius.gomes@...el.com>
To:     Jiri Pirko <jiri@...nulli.us>
Cc:     netdev@...r.kernel.org, intel-wired-lan@...ts.osuosl.org,
        jhs@...atatu.com, xiyou.wangcong@...il.com, andre.guedes@...el.com,
        ivan.briano@...el.com, jesus.sanchez-palencia@...el.com,
        boon.leong.ong@...el.com, richardcochran@...il.com,
        henrik@...tad.us, levipearson@...il.com, rodney.cummings@...com
Subject: Re: [next-queue PATCH v4 3/4] net/sched: Introduce Credit Based Shaper (CBS) qdisc

Hi Jiri,

Jiri Pirko <jiri@...nulli.us> writes:

> Wed, Oct 04, 2017 at 02:28:30AM CEST, vinicius.gomes@...el.com wrote:
>>This queueing discipline implements the shaper algorithm defined by
>>the 802.1Q-2014 Section 8.6.8.2 and detailed in Annex L.
>>
>>It's primary usage is to apply some bandwidth reservation to user
>>defined traffic classes, which are mapped to different queues via the
>>mqprio qdisc.
>>
>>Initially, it only supports offloading the traffic shaping work to
>>supporting controllers.
>>
>>Later, when a software implementation is added, the current dependency
>>on being installed "under" mqprio can be lifted.
>>
>>Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@...el.com>
>>Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@...el.com>
>>---
>> include/linux/netdevice.h      |   1 +
>> include/net/pkt_sched.h        |   9 ++
>> include/uapi/linux/pkt_sched.h |  17 ++++
>> net/sched/Kconfig              |  11 ++
>> net/sched/Makefile             |   1 +
>> net/sched/sch_cbs.c            | 225 +++++++++++++++++++++++++++++++++++++++++
>> 6 files changed, 264 insertions(+)
>> create mode 100644 net/sched/sch_cbs.c
>>
>>diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
>>index e1d6ef130611..b8798adc214f 100644
>>--- a/include/linux/netdevice.h
>>+++ b/include/linux/netdevice.h
>>@@ -775,6 +775,7 @@ enum tc_setup_type {
>> 	TC_SETUP_CLSFLOWER,
>> 	TC_SETUP_CLSMATCHALL,
>> 	TC_SETUP_CLSBPF,
>>+	TC_SETUP_CBS,
>
> Please split this into 2 patches. One will introduce the new qdisc,
> second will add offload capabilities.
>

Of course.

> [...]
>
>
>>+static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
>>+	.next		=	NULL,
>>+	.id		=	"cbs",
>>+	.priv_size	=	sizeof(struct cbs_sched_data),
>>+	.enqueue	=	cbs_enqueue,
>>+	.dequeue	=	qdisc_dequeue_head,
>>+	.peek		=	qdisc_peek_dequeued,
>>+	.init		=	cbs_init,
>>+	.reset		=	qdisc_reset_queue,
>>+	.destroy	=	cbs_destroy,
>>+	.change		=	cbs_change,
>>+	.dump		=	cbs_dump,
>>+	.owner		=	THIS_MODULE,
>>+};
>
> I don't see a software implementation for this. Looks like you are
> trying abuse tc subsystem to bypass kernel. Could you please explain
> this? The golden rule is: implement in kernel, then offload.

The reason was that we didn't have a use case for the software
implementation right now, it would be added in a later series.

But as that was requested (and it makes sense), I will add it for the
next version of this series (it is already written, just need to test it
better).


Cheers,
--
Vinicius