Hi Chenbo

Thanks for your reply, my reply inline.

> -----Original Message-----
> From: Xia, Chenbo <chenbo....@intel.com>
> Sent: Wednesday, October 12, 2022 4:08 PM
> To: Pei, Andy <andy....@intel.com>; dev@dpdk.org
> Cc: Xu, Rosen <rosen...@intel.com>; Huang, Wei <wei.hu...@intel.com>;
> Cao, Gang <gang....@intel.com>; maxime.coque...@redhat.com
> Subject: RE: [PATCH v3 4/8] vdpa/ifc: write queue count to MQ register
> 
> > -----Original Message-----
> > From: Pei, Andy <andy....@intel.com>
> > Sent: Friday, September 16, 2022 2:16 PM
> > To: dev@dpdk.org
> > Cc: Xia, Chenbo <chenbo....@intel.com>; Xu, Rosen
> > <rosen...@intel.com>; Huang, Wei <wei.hu...@intel.com>; Cao, Gang
> > <gang....@intel.com>; maxime.coque...@redhat.com
> > Subject: [PATCH v3 4/8] vdpa/ifc: write queue count to MQ register
> >
> > Write queue count to IFCVF_MQ_OFFSET register to enable multi queue
> > feature.
> 
> Multi-queue
> 
Sure.
> >
> > Signed-off-by: Andy Pei <andy....@intel.com>
> > Signed-off-by: Huang Wei <wei.hu...@intel.com>
> > ---
> >  drivers/vdpa/ifc/base/ifcvf.c | 30 ++++++++++++++++++++++++++++++
> >  1 file changed, 30 insertions(+)
> >
> > diff --git a/drivers/vdpa/ifc/base/ifcvf.c
> > b/drivers/vdpa/ifc/base/ifcvf.c index 34c8226..7efb408 100644
> > --- a/drivers/vdpa/ifc/base/ifcvf.c
> > +++ b/drivers/vdpa/ifc/base/ifcvf.c
> > @@ -198,6 +198,35 @@
> >     IFCVF_WRITE_REG32(val >> 32, hi);
> >  }
> >
> > +STATIC void
> > +ifcvf_enable_multiqueue(struct ifcvf_hw *hw)
> 
> Maybe ifcvf_enable_mq?
> 
OK.
> > +{
> > +   u8 *mq_cfg;
> > +   int qid;
> 
> Qid should be the same type as nr_vring, so u8
> 
> > +   int nr_queue_pair = 0;
> > +
> > +   for (qid = 0; qid < hw->nr_vring; qid++) {
> > +           if (!hw->vring[qid].enable)
> > +                   continue;
> > +           nr_queue_pair++;
> > +   }
> > +
> > +   if (nr_queue_pair == 0) {
> > +           WARNINGOUT("no enabled vring\n");
> > +           return;
> > +   }
> > +
> > +   if (hw->device_type == IFCVF_NET)
> > +           nr_queue_pair = (nr_queue_pair + 1) / 2;
> 
> Why +1?
> 
> > +
> > +   mq_cfg = hw->mq_cfg;
> > +   if (mq_cfg) {
> > +           *(u32 *)mq_cfg = nr_queue_pair;
> > +           RTE_LOG(INFO, PMD, "%d queue pairs are enabled\n",
> > +                   nr_queue_pair);
> > +   }
> 
> As blk does not have queue pair, the log should be different for net/blk.
> 
> The variable nr_queue_pair should be nr_queue as it's the number of
> queues.
> When device type is net, you can make *(u32 *)mq_cfg equal to nr_queue / 2
> 
OK. I will sent a new version to address it.

> Thanks,
> Chenbo
> 
> > +}
> > +
> >  STATIC int
> >  ifcvf_hw_enable(struct ifcvf_hw *hw)
> >  {
> > @@ -215,6 +244,7 @@
> >             return -1;
> >     }
> >
> > +   ifcvf_enable_multiqueue(hw);
> >     for (i = 0; i < hw->nr_vring; i++) {
> >             IFCVF_WRITE_REG16(i, &cfg->queue_select);
> >             io_write64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo,
> > --
> > 1.8.3.1

Reply via email to