Re: [PATCH net-next v5 6/7] net/sched: act_ct: offload UDP NEW connections

[Vlad Buslov <vladbu@nvidia.com>]

On Sat 28 Jan 2023 at 20:09, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> On Sat, Jan 28, 2023 at 05:31:40PM +0200, Vlad Buslov wrote:
>> 
>> On Sat 28 Jan 2023 at 16:26, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
>> > Hi Vlad,
>> >
>> > On Fri, Jan 27, 2023 at 07:38:44PM +0100, Vlad Buslov wrote:
>> >> Modify the offload algorithm of UDP connections to the following:
>> >> 
>> >> - Offload NEW connection as unidirectional.
>> >> 
>> >> - When connection state changes to ESTABLISHED also update the hardware
>> >> flow. However, in order to prevent act_ct from spamming offload add wq for
>> >> every packet coming in reply direction in this state verify whether
>> >> connection has already been updated to ESTABLISHED in the drivers. If that
>> >> it the case, then skip flow_table and let conntrack handle such packets
>> >> which will also allow conntrack to potentially promote the connection to
>> >> ASSURED.
>> >> 
>> >> - When connection state changes to ASSURED set the flow_table flow
>> >> NF_FLOW_HW_BIDIRECTIONAL flag which will cause refresh mechanism to offload
>> >> the reply direction.
>> >> 
>> >> All other protocols have their offload algorithm preserved and are always
>> >> offloaded as bidirectional.
>> >> 
>> >> Note that this change tries to minimize the load on flow_table add
>> >> workqueue. First, it tracks the last ctinfo that was offloaded by using new
>> >> flow 'ext_data' field and doesn't schedule the refresh for reply direction
>> >> packets when the offloads have already been updated with current ctinfo.
>> >> Second, when 'add' task executes on workqueue it always update the offload
>> >> with current flow state (by checking 'bidirectional' flow flag and
>> >> obtaining actual ctinfo/cookie through meta action instead of caching any
>> >> of these from the moment of scheduling the 'add' work) preventing the need
>> >> from scheduling more updates if state changed concurrently while the 'add'
>> >> work was pending on workqueue.
>> >
>> > Could you use a flag to achieve what you need instead of this ext_data
>> > field? Better this ext_data and the flag, I prefer the flags.
>> 
>> Sure, np. Do you prefer the functionality to be offloaded to gc (as in
>> earlier versions of this series) or leverage 'refresh' code as in
>> versions 4-5?
>
> No, I prefer generic gc/refresh mechanism is not used for this.
>
> What I mean is: could you replace this new ->ext_data generic pointer
> by a flag to annotate what you need?

Yes, will do.

> Between this generic pointer and a flag, I prefer a flag.

Got it.