Re: [dpdk-dev] [PATCH v3 0/5] A means to negotiate delivery of Rx meta data

[Thomas Monjalon <thomas@monjalon.net>]

01/10/2021 12:15, Andrew Rybchenko:
> On 10/1/21 12:48 PM, Thomas Monjalon wrote:
> > 01/10/2021 10:55, Ivan Malov:
> >> On 01/10/2021 11:11, Thomas Monjalon wrote:
> >>> 01/10/2021 08:47, Andrew Rybchenko:
> >>>> On 9/30/21 10:30 PM, Ivan Malov wrote:
> >>>>> On 30/09/2021 19:18, Thomas Monjalon wrote:
> >>>>>> 23/09/2021 13:20, Ivan Malov:
> >>>>>>> Patch [1/5] of this series adds a generic API to let applications
> >>>>>>> negotiate delivery of Rx meta data during initialisation period.
> >>>
> >>> What is a metadata?
> >>> Do you mean RTE_FLOW_ITEM_TYPE_META and RTE_FLOW_ITEM_TYPE_MARK?
> >>> Metadata word could cover any field in the mbuf struct so it is vague.
> >>
> >> Metadata here is *any* additional information provided by the NIC for 
> >> each received packet. For example, Rx flag, Rx mark, RSS hash, packet 
> >> classification info, you name it. I'd like to stress out that the 
> >> suggested API comes with flags each of which is crystal clear on what 
> >> concrete kind of metadata it covers, eg. Rx mark.
> > 
> > I missed the flags.
> > You mean these 3 flags?
> 
> Yes
> 
> > +/** The ethdev sees flagged packets if there are flows with action FLAG. */
> > +#define RTE_ETH_RX_META_USER_FLAG (UINT64_C(1) << 0)
> > +
> > +/** The ethdev sees mark IDs in packets if there are flows with action MARK. */
> > +#define RTE_ETH_RX_META_USER_MARK (UINT64_C(1) << 1)
> > +
> > +/** The ethdev detects missed packets if there are "tunnel_set" flows in use. */
> > +#define RTE_ETH_RX_META_TUNNEL_ID (UINT64_C(1) << 2)
> > 
> > It is not crystal clear because it does not reference the API,
> > like RTE_FLOW_ACTION_TYPE_MARK.
> 
> Thanks, it is easy to fix. Please, note that there is no action
> for tunnel ID case.

I don't understand the tunnel ID meta.
Is it an existing offload? API?

> > And it covers a limited set of metadata.
> 
> Yes which are not covered by offloads, packet classification
> etc. Anything else?
> 
> > Do you intend to extend to all mbuf metadata?
> 
> No. It should be discussed case-by-case separately.

Ah, it makes the intent clearer.
Why not planning to do something truly generic?

> >>>>>>> This way, an application knows right from the start which parts
> >>>>>>> of Rx meta data won't be delivered. Hence, no necessity to try
> >>>>>>> inserting flows requesting such data and handle the failures.
> >>>>>>
> >>>>>> Sorry I don't understand the problem you want to solve.
> >>>>>> And sorry for not noticing earlier.
> >>>>>
> >>>>> No worries. *Some* PMDs do not enable delivery of, say, Rx mark with the
> >>>>> packets by default (for performance reasons). If the application tries
> >>>>> to insert a flow with action MARK, the PMD may not be able to enable
> >>>>> delivery of Rx mark without the need to re-start Rx sub-system. And
> >>>>> that's fraught with traffic disruption and similar bad consequences. In
> >>>>> order to address it, we need to let the application express its interest
> >>>>> in receiving mark with packets as early as possible. This way, the PMD
> >>>>> can enable Rx mark delivery in advance. And, as an additional benefit,
> >>>>> the application can learn *from the very beginning* whether it will be
> >>>>> possible to use the feature or not. If this API tells the application
> >>>>> that no mark delivery will be enabled, then the application can just
> >>>>> skip many unnecessary attempts to insert wittingly unsupported flows
> >>>>> during runtime.
> >>>
> >>> I'm puzzled, because we could have the same reasoning for any offload.
> >>
> >> We're not discussing *offloads*. An offload is when NIC *computes 
> >> something* and *delivers* it. We are discussing precisely *delivery*.
> > 
> > OK but still, there are a lot more mbuf metadata delivered.
> 
> Yes, and some are not controlled yet early enough, and
> we do here.
> 
> > 
> >>> I don't understand why we are focusing on mark only
> >>
> >> We are not focusing on mark on purpose. It's just how our discussion 
> >> goes. I chose mark (could've chosen flag or anything else) just to show 
> >> you an example.
> >>
> >>> I would prefer we find a generic solution using the rte_flow API. > Can we make rte_flow_validate() working before port start?
> >>> If validating a fake rule doesn't make sense,
> >>> why not having a new function accepting a single action as parameter?
> >>
> >> A noble idea, but if we feed the entire flow rule to the driver for 
> >> validation, then the driver must not look specifically for actions FLAG 
> >> or MARK in it (to enable or disable metadata delivery). This way, the 
> >> driver is obliged to also validate match criteria, attributes, etc. And, 
> >> if something is unsupported (say, some specific item), the driver will 
> >> have to reject the rule as a whole thus leaving the application to join 
> >> the dots itself.
> >>
> >> Say, you ask the driver to validate the following rule:
> >> pattern blah-blah-1 / blah-blah-2 / end action flag / end
> >> intending to check support for FLAG delivery. Suppose, the driver 
> >> doesn't support pattern item "blah-blah-1". It will throw an error right 
> >> after seeing this unsupported item and won't even go further to see the 
> >> action FLAG. How can application know whether its request for FLAG was 
> >> heard or not?
> > 
> > No, I'm proposing a new function to validate the action alone,
> > without any match etc.
> > Example:
> > 	rte_flow_action_request(RTE_FLOW_ACTION_TYPE_MARK)
> 
> When about tunnel ID?
> 
> Also negotiation in terms of bitmask natively allows to
> provide everything required at once and it simplifies
> implementation in the driver. No dependency on order of
> checks etc. Also it allows to renegotiate without any
> extra API functions.

You mean there is a single function call with all bits set?

> >> And I'd not bind delivery of metadata to flow API. Consider the 
> >> following example. We have a DPDK application sitting at the *host* and 
> >> we have a *guest* with its *own* DPDK instance. The guest DPDK has asked 
> >> the NIC (by virtue of flow API) to mark all outgoing packets. This 
> >> packets reach the *host* DPDK. Say, the host application just wants to 
> >> see the marked packets from the guest. Its own, (the host's) use of flow 
> >> API is a don't care here. The host doesn't want to mark packets itself, 
> >> it wants to see packets marked by the guest.
> > 
> > It does not make sense to me. We are talking about a DPDK API.
> > My concern is to avoid redefining new flags
> > while we already have rte_flow actions.
> 
> See above.