[dpdk-stable] [PATCH v5] app/testpmd: fix setting maximum packet length

[Li, Xiaoyun]

> -----Original Message-----
> From: Lance Richardson <lance.richardson at broadcom.com>
> Sent: Tuesday, January 26, 2021 11:45
> To: Yigit, Ferruh <ferruh.yigit at intel.com>
> Cc: Lu, Wenzhuo <wenzhuo.lu at intel.com>; Li, Xiaoyun <xiaoyun.li at intel.com>;
> Iremonger, Bernard <bernard.iremonger at intel.com>; Yang, SteveX
> <stevex.yang at intel.com>; dev at dpdk.org; stable at dpdk.org;
> oulijun at huawei.com; wisamm at mellanox.com; lihuisong at huawei.com
> Subject: Re: [PATCH v5] app/testpmd: fix setting maximum packet length
> 
> On Mon, Jan 25, 2021 at 7:44 PM Ferruh Yigit <ferruh.yigit at intel.com> wrote:
> >
> > >> +       if (rx_offloads != port->dev_conf.rxmode.offloads) {
> > >> +               uint16_t qid;
> > >> +
> > >> +               port->dev_conf.rxmode.offloads = rx_offloads;
> > >> +
> > >> +               /* Apply JUMBO_FRAME offload configuration to Rx queue(s) */
> > >> +               for (qid = 0; qid < port->dev_info.nb_rx_queues; qid++) {
> > >> +                       if (on)
> > >> +                               port->rx_conf[qid].offloads |=
> DEV_RX_OFFLOAD_JUMBO_FRAME;
> > >> +                       else
> > >> +                               port->rx_conf[qid].offloads &=
> ~DEV_RX_OFFLOAD_JUMBO_FRAME;
> > >> +               }
> > >
> > > Is it correct to set per-queue offloads that aren't advertised by the PMD
> > > as supported in rx_queue_offload_capa?
> > >
> >
> > 'port->rx_conf[]' is testpmd struct, and 'port->dev_conf.rxmode.offloads'
> values
> > are reflected to 'port->rx_conf[].offloads' for all queues.
> >
> > We should set the offload in 'port->rx_conf[].offloads' if it is set in
> > 'port->dev_conf.rxmode.offloads'.
> >
> > If a port has capability for 'JUMBO_FRAME', 'port->rx_conf[].offloads' can
> have
> > it. And the port level capability is already checked above.
> >
> 
> I'm still not 100% clear about the per-queue offload question.
> 
> With this patch, and jumbo max packet size configured (on the command
> line in this case), I see:
> 
> testpmd> show port 0 rx_offload configuration
> Rx Offloading Configuration of port 0 :
>   Port : JUMBO_FRAME
>   Queue[ 0] : JUMBO_FRAME
> 
> testpmd> show port 0 rx_offload capabilities
> Rx Offloading Capabilities of port 0 :
>   Per Queue :
>   Per Port  : VLAN_STRIP IPV4_CKSUM UDP_CKSUM TCP_CKSUM TCP_LRO
> OUTER_IPV4_CKSUM VLAN_FILTER VLAN_EXTEND JUMBO_FRAME SCATTER
> TIMESTAMP
> KEEP_CRC OUTER_UDP_CKSUM RSS_HASH
> 
> Yet if I configure a jumbo MTU starting with standard max packet size,
> jumbo is only enabled at the port level:
> testpmd> port config mtu 0 9000
> testpmd> port start all
> 
> testpmd> show port 0 rx_offload configuration
> Rx Offloading Configuration of port 0 :
>   Port : JUMBO_FRAME
>   Queue[ 0] :
> 
> It still seems odd for a per-queue offload to be enabled on a PMD that
> doesn't support per-queue receive offloads.

In struct rte_eth_dev_info, rx_offload_capa means All RX offload capabilities including all per-queue ones.
And rx_queue_offload_capa means Device per-queue RX offload capabilities.

The meaning of rx_queue_offload_capa is a bit of confusing between here and driver.
I think here rx_queue_offload_capa means whether a queue supports offloads.

But some drivers like i40e don't use rx_queue_offload_capa, set this as 0 and only use global rx_offload_capa.
I guess it's because the driver doesn't want to support different offloads settings for different queues?
Then rx_queue_offload_capa means differently.

Actually for i40e, it can support different offloads for different queues since there is 'offloads' in struct i40e_rx_queue.
I40e can just set rx_queue_offload_capa as the value for rx_offload_capa.
But maybe some drivers really don't want this? Not sure on this.