Date:   Thu, 29 Nov 2018 14:27:26 +0100
From:   Toke Høiland-Jørgensen <toke@...e.dk>
To:     Lorenzo Bianconi <lorenzo.bianconi@...hat.com>,
        Jesper Dangaard Brouer <brouer@...hat.com>
Cc:     Kalle Valo <kvalo@...eaurora.org>, linux-wireless@...r.kernel.org,
        nbd@....name, Daniel Borkmann <borkmann@...earbox.net>,
        Alexei Starovoitov <alexei.starovoitov@...il.com>,
        "netdev\@vger.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [RFC 0/5] add XDP support to mt76x2e/mt76x0e drivers

Lorenzo Bianconi <lorenzo.bianconi@...hat.com> writes:

>> On Wed, 28 Nov 2018 13:36:26 +0100
>> Toke Høiland-Jørgensen <toke@...e.dk> wrote:
>> 
>> > Lorenzo Bianconi <lorenzo.bianconi@...hat.com> writes:
>> > 
>> > >> Lorenzo Bianconi <lorenzo.bianconi@...hat.com> writes:
>> > >>   
>> > >> > This series is intended as a playground to start experimenting/developing
>> > >> > with XDP/eBPF over WiFi and collect ideas/concerns about it.
>> > >> > Introduce XDP support to mt76x2e/mt76x0e drivers. Currently supported
>> > >> > actions are:
>> > >> > - XDP_PASS
>> > >> > - XDP_ABORTED
>> > >> > - XDP_DROP
>> > >> > Introduce ndo_bpf mac80211 callback in order to to load a bpf
>> > >> > program into low level driver XDP rx hook.
>> > >> > This series has been tested through a simple bpf program (available here:
>> > >> > https://github.com/LorenzoBianconi/bpf-workspace/tree/master/mt76_xdp_stats)
>> > >> > used to count frame types received by the device.
>> > >> > Possible eBPF use cases could be:
>> > >> > - implement new statistics through bpf maps
>> > >> > - implement fast packet filtering (e.g in monitor mode)
>> > >> > - ...  
>> > >
>> > > Hi Kalle,
>> > >  
>> > >> 
>> > >> This is most likely a stupid question, but why do this in the driver and
>> > >> not in mac80211 so that all drivers could benefit from it? I guess there
>> > >> are reasons for that, I just can't figure that out.  
>> > 
>> > XDP achieves its speedup by running the eBPF program inside the driver
>> > NAPI loop, before the kernel even touches the data in any other capacity
>> > (and in particular, before it allocates an SKB). Which kinda means the
>> > hook needs to be in the driver... Could be a fallback in mac80211,
>> > though; although we'd have to figure out how that interacts with Generic
>> > XDP.
>> > 
>> > > This is an early stage implementation, at this point I would collect
>> > > other people opinions/concerns about using bpf/xdp directly on 802.11
>> > > frames.  
>> > 
>> > Thanks for looking into this!
>> > 
>> > I have two concerns with running XDP on 802.11 frames:
>> > 
>> > 1. It makes it more difficult to add other XDP actions (such as
>> >    REDIRECT), as the XDP program would then have to make sure that the
>> >    outer packet headers are removed before, say, redirecting the packet
>> >    out of an ethernet interface. Also, if we do add redirect, we would
>> >    be bypassing mac80211 entirely; to what extent would that mess up
>> >    internal state?
>> > 
>> > 2. UI consistency; suddenly, the user needs to know which kind of
>> >    frames to expect, and XDP program reuse becomes more difficult. This
>> >    may be unavoidable given the nature of XDP, but some thought needs to
>> >    go into this. Especially since we wouldn't necessarily be consistent
>> >    between WiFi drivers (there are fullmac devices that remove 802.11
>> >    headers before sending up the frame, right?).
>> > 
>> > 
>> > Adding in Jesper; maybe he has some thoughts on this?
>
> Hi Jesper,
>
>> 
>> Today XDP assumes the frame is an Ethernet frame.  With WiFi I guess
>> this assumption change, right?
>
> yes correct, SoftMAC devices report 802.11 frames to the stack
>
>>   I worry a bit about this, as XDP is all about performance, and I don't
>> want to add performance regressions, by requiring all XDP programs or
>> core-code to having to check-frame-type before proceeding. That said, I
>> do think it is doable, without adding performance regressions.
>> 
>> Option #1 is to move the check-frame-type to setup time.  By either
>> having frame-type be part of eBPF prog, or supply frame-type as option
>> XDP attach call.  And then reject attaching XDP prog to a device, where
>> the expected frame-type does not match.
>> 
>
> I guess it will be enough to avoid loading a 'non-WiFi' bpf program on
> a 802.11 netdevice (and vice versa). We could add a flag (or something
> similar) in XDP_SETUP_PROG section of netdev_bpf data structure and
> use ieee80211_ptr netdevice pointer in order to guarantee that the bpf
> program will work on the expected 'frame-type'

Yeah, a flag would be good; we've been discussing that for other XDP use
cases; it's not a done deal yet, but I think it would be useful.
>
>> Option#2, leave it up to eBPF-programmer if they want to add runtime
>> checks.  By extending xdp_rxq_info with frame-type (default to
>> Ethernet), which allow the eBPF-programmer choose to write a generic
>> XDP program that both work on Ethernet and WiFi, or skip-check as they
>> know this will e.g. only run on Wifi.  (Note xdp_rxq_info is static
>> read-only info per RX-queue, will all Wifi frames have same frame-type?.
>> 
>
> 802.11 standards define three frame subtype (data, management and control).
> Subtypes could be detected parsing 802.11 header
>
>> 
>> Also consider what happens in case of XDP_REDIRECT, from a Wifi NIC to
>> an Ethernet NIC.  It would of-cause be cool to get this working cross,
>> Wifi-Ethernet.
>> 
>
> Very cool :) On tx side the driver will accept standard ethernet frames in
> ndo_xdp_xmit pointer

How do you envision that will work with drivers that build software
802.11 frames? The TX hook would have to be in mac80211 somewhere,
wouldn't it?

>> Option#3 is to say, Wifi XDP is so different that we should create a
>> new (enum) bpf_prog_type.  And then still see if we can leverage some
>> of the same core-code (as long as it doesn't slowdown performance).
>> 
>
> Do you think that Option#3 will be more 'future-proof' respect to
> Option#1?

My feeling is that WiFi devices are not sufficiently different to
warrant a whole new program type. We risk combinatorial explosion for
all the stuff that is the same, but now need to be tested for two (or N)
types...

-Toke

Powered by blists - more mailing lists