netdev - Re: [patch net-next RFC 0/4] introduce infrastructure for support of switch chip datapath

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]

Message-ID: <CAGVrzcavFLyQC6A_6hqGa-iqXkkTyZK2V7Zq9UiOix1Y0xEK2w@mail.gmail.com>
Date:	Wed, 26 Mar 2014 16:21:57 -0700
From:	Florian Fainelli <f.fainelli@...il.com>
To:	Thomas Graf <tgraf@...g.ch>
Cc:	Jamal Hadi Salim <jhs@...atatu.com>,
	Neil Horman <nhorman@...driver.com>,
	Jiri Pirko <jiri@...nulli.us>, netdev <netdev@...r.kernel.org>,
	David Miller <davem@...emloft.net>,
	Andy Gospodarek <andy@...yhouse.net>,
	dborkman <dborkman@...hat.com>, ogerlitz <ogerlitz@...lanox.com>,
	jesse <jesse@...ira.com>, pshelar <pshelar@...ira.com>,
	azhou <azhou@...ira.com>, Ben Hutchings <ben@...adent.org.uk>,
	Stephen Hemminger <stephen@...workplumber.org>,
	jeffrey.t.kirsher@...el.com, vyasevic <vyasevic@...hat.com>,
	Cong Wang <xiyou.wangcong@...il.com>,
	John Fastabend <john.r.fastabend@...el.com>,
	Eric Dumazet <edumazet@...gle.com>,
	Scott Feldman <sfeldma@...ulusnetworks.com>,
	Lennert Buytenhek <buytenh@...tstofly.org>,
	Felix Fietkau <nbd@...nwrt.org>
Subject: Re: [patch net-next RFC 0/4] introduce infrastructure for support of
 switch chip datapath

2014-03-26 16:15 GMT-07:00 Thomas Graf <tgraf@...g.ch>:
> On 03/26/14 at 06:44pm, Jamal Hadi Salim wrote:
>> OTOH, the owrt view is probably because (If i understood correctly
>> last time), there are cases where there is no way to even pass packets
>> and attribute them to the originating switch ports. Infact, in some
>> cases  there may be no way at all to even pass packets to the kernel.
>> Did i  understand that part correctly?
>> I suppose this is eventually all part of that capability discovery.
>
> Listening to Florian it sounds like the fact that a separate control
> path was chosen early on in owrt got rid of the main driver to abstract
> everything through globally visible net_devices. Reusing existing
> tools was never an objective.

Correct. OpenWrt already has a fairly custom user-space, so it was
deemed reasonable to have another lightweight, yet custom control
interfaces for switches. The ability to use an unmodified Ethernet
driver was also a key goal. The reasons for putting that in the kernel
versus using e.g: an ioctl(SIOCGMIIREG) based approach in user-space,
is that it allows for better abstraction between control paths (MDIO,
I2C, SPI, memory-mapped I/O ...), and preserves the "kernel has
hardware ownership" paradigm.

>
> I believe that the question whether a particular port will send
> packets to the cpu does not matter that much. We'll see both and we'll
> see various forms of hybrid models with software based learnings paths,
> slow paths, and deliberate upcalls.
>
> The simpler the model, the better. If the desire to hide some of the
> complexity is driven by usability when I believe that hiding should
> happen in user space.
-- 
Florian
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html