On 11/9/20 4:44 PM, Jakub Kicinski wrote:
> On Fri, 6 Nov 2020 08:30:30 +0100 Martin Willi wrote:
>> VRF devices use an optimized direct path on output if a default qdisc
>> is involved, calling Netfilter hooks directly. This path, however, does
>> not consider Netfilter rules completing asynchronously, such as with
>> NFQUEUE. The Netfilter okfn() is called for asynchronously accepted
>> packets, but the VRF never passes that packet down the stack to send
>> it out over the slave device. Using the slower redirect path for this
>> seems not feasible, as we do not know beforehand if a Netfilter hook
>> has asynchronously completing rules.
>>
>> Fix the use of asynchronously completing Netfilter rules in OUTPUT and
>> POSTROUTING by using a special completion function that additionally
>> calls dst_output() to pass the packet down the stack. Also, slightly
>> adjust the use of nf_reset_ct() so that is called in the asynchronous
>> case, too.
>>
>> Fixes: dcdd43c41e60 ("net: vrf: performance improvements for IPv4")
>> Fixes: a9ec54d1b0cd ("net: vrf: performance improvements for IPv6")
>> Signed-off-by: Martin Willi <martin@xxxxxxxxxxxxxx>
>
> David, can we get an ack?
>
It would be good to get a netfilter maintainer to review; I think it is ok.
