DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Zhao, Bing" <ilovethull@163.com>
To: Yuanhan Liu <yliu@fridaylinux.org>
Cc: "Chen, Junjie J" <junjie.j.chen@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	Maxime Coquelin <maxime.coquelin@redhat.com>,
	"Loftus, Ciara" <ciara.loftus@intel.com>
Subject: Re: [dpdk-dev] [PATCH] vhost: fix dequeue zero copy not work with virtio1
Date: Wed, 20 Dec 2017 13:58:22 +0800	[thread overview]
Message-ID: <7304a91b-468c-ccaf-83ab-e1d74bb37500@163.com> (raw)
In-Reply-To: <20171215124804.GB2439@yliu-mob>

On 2017/12/15 20:48, Yuanhan Liu wrote:
> On Fri, Dec 15, 2017 at 10:33:41AM +0000, Loftus, Ciara wrote:
> >>
> >> Hi Junjie,
> >>
> >> On 12/13/2017 05:50 PM, Junjie Chen wrote:
> >>> This fix dequeue zero copy can not work with Qemu
> >>> version >= 2.7. Since from Qemu 2.7 virtio device
> >>> use virtio-1 protocol, the zero copy code path
> >>> forget to add offset to buffer address.
> >>>
> >>> Signed-off-by: Junjie Chen <junjie.j.chen@intel.com>
> >>> ---
> >>>    lib/librte_vhost/virtio_net.c | 3 ++-
> >>>    1 file changed, 2 insertions(+), 1 deletion(-)
> >>>
> >>> diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
> >>> index 6fee16e..79d80f7 100644
> >>> --- a/lib/librte_vhost/virtio_net.c
> >>> +++ b/lib/librte_vhost/virtio_net.c
> >>> @@ -977,7 +977,8 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct
> >> vhost_virtqueue *vq,
> >>>                        desc->addr + desc_offset,
> >> cpy_len)))) {
> >>>                cur->data_len = cpy_len;
> >>>                cur->data_off = 0;
> >>> -            cur->buf_addr = (void *)(uintptr_t)desc_addr;
> >>> +            cur->buf_addr = (void *)(uintptr_t)(desc_addr
> >>> +                + desc_offset);
> >>>                cur->buf_iova = hpa;
> >>>
> >>>                /*
> >>>
> >>
> >> Thanks for fixing this.
> >>
> >> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> >>
> >> Maxime
> >
> > Thanks for the fix. Can this be considered for the stable branch?
>
> Yes, I think so. Applied to dpdk-next-virtio, with
>
> Fixes: b0a985d1f340 ("vhost: add dequeue zero copy")
> Cc: stable@dpdk.org
>
> Thanks.
>
>     --yliu
>
@Yuanhan & Maxime, sorry to interrupt here. I meet the same issue recently. Could the "cur->data_off" field be used here with the value "desc_offset"? (I don't go through all the code and am a little confused about the "0". Is there any detail description about the "data_off" field?)
Thanks

      reply	other threads:[~2017-12-20  5:58 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-13 16:50 Junjie Chen
2017-12-13 11:12 ` Maxime Coquelin
2017-12-15 10:33   ` Loftus, Ciara
2017-12-15 12:48     ` Yuanhan Liu
2017-12-20  5:58       ` Zhao, Bing [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=7304a91b-468c-ccaf-83ab-e1d74bb37500@163.com \
    --to=ilovethull@163.com \
    --cc=ciara.loftus@intel.com \
    --cc=dev@dpdk.org \
    --cc=junjie.j.chen@intel.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=yliu@fridaylinux.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).