[dpdk-dev] [PATCH v3 1/2] net/i40e: support VF request more queues

[Yan, Zhirun]

Hi Qi,

> -----Original Message-----
> From: Zhang, Qi Z
> Sent: Thursday, December 13, 2018 6:49 PM
> To: Yan, Zhirun <zhirun.yan at intel.com>; dev at dpdk.org
> Cc: Wang, Haiyue <haiyue.wang at intel.com>
> Subject: RE: [PATCH v3 1/2] net/i40e: support VF request more queues
> 
> 
> 
> > -----Original Message-----
> > From: Yan, Zhirun
> > Sent: Thursday, December 13, 2018 10:05 PM
> > To: dev at dpdk.org; Zhang, Qi Z <qi.z.zhang at intel.com>
> > Cc: Yan, Zhirun <zhirun.yan at intel.com>; Wang, Haiyue
> > <haiyue.wang at intel.com>
> > Subject: [PATCH v3 1/2] net/i40e: support VF request more queues
> >
> > Before this patch, VF gets a default number of queues from the PF.
> > This patch enables VF to request a different number. When VF
> > configures more queues, it will send VIRTCHNL_OP_REQUEST_QUEUES to PF
> > to request more queues, if success, PF will reset the VF.
> >
> > User can run "port stop all", "port config port_id rxq/txq queue_num"
> > and "port start all" to reconfigure queue number.
> >
> > Signed-off-by: Zhirun Yan <zhirun.yan at intel.com>
> > Signed-off-by: Haiyue Wang <haiyue.wang at intel.com>
> > ---
> >  drivers/net/i40e/i40e_ethdev_vf.c | 56
> > ++++++++++++++++++++++++++++---
> >  1 file changed, 52 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
> > b/drivers/net/i40e/i40e_ethdev_vf.c
> > index cecedc91f..50e3f1f4f 100644
> > --- a/drivers/net/i40e/i40e_ethdev_vf.c
> > +++ b/drivers/net/i40e/i40e_ethdev_vf.c
> > @@ -343,6 +343,7 @@ i40evf_execute_vf_cmd(struct rte_eth_dev *dev,
> > struct vf_cmd_info *args)
> >  		err = 0;
> >  		break;
> >  	case VIRTCHNL_OP_VERSION:
> > +	case VIRTCHNL_OP_REQUEST_QUEUES:
> >  	case VIRTCHNL_OP_GET_VF_RESOURCES:
> >  		/* for init adminq commands, need to poll the response */
> >  		err = -1;
> > @@ -350,8 +351,15 @@ i40evf_execute_vf_cmd(struct rte_eth_dev *dev,
> > struct vf_cmd_info *args)
> >  			ret = i40evf_read_pfmsg(dev, &info);
> >  			vf->cmd_retval = info.result;
> >  			if (ret == I40EVF_MSG_CMD) {
> > -				err = 0;
> > +				if (info.ops !=
> VIRTCHNL_OP_REQUEST_QUEUES)
> > +					err = 0;
> >  				break;
> > +			} else if (ret == I40EVF_MSG_SYS) {
> > +				if (args->ops ==
> VIRTCHNL_OP_REQUEST_QUEUES &&
> 
> OK, for VIRTCHNL_OP_REQUEST_QUEUES, we will ignore async reply
> (I40EVF_MSG_CMD) but only wait for system message (I40EVF_MSG_SYS) I
> think it's better to create new branch for case
> VIRTCHNL_OP_REQUEST_QUEUES to make code more readable.
> 

Yes, I will send a new version without it and create new patchs for handling msg from pf.

> > +					vf->vf_reset) {
> > +					err = 0;
> > +					break;
> > +				}
> >  			} else if (ret == I40EVF_MSG_ERR)
> >  				break;
> >  			rte_delay_ms(ASQ_DELAY_MS);