DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Liu, Jijiang" <jijiang.liu@intel.com>
To: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, "Michael S. Tsirkin" <mst@redhat.com>
Subject: Re: [dpdk-dev] [PATCH v4 7/8] virtio/lib:add virtio guest offload capabilities
Date: Wed, 11 Nov 2015 08:53:08 +0000	[thread overview]
Message-ID: <1ED644BD7E0A5F4091CF203DAFB8E4CC22BDA74A@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <20151111084419.GC2326@yliu-dev.sh.intel.com>



> -----Original Message-----
> From: Yuanhan Liu [mailto:yuanhan.liu@linux.intel.com]
> Sent: Wednesday, November 11, 2015 4:44 PM
> To: Liu, Jijiang
> Cc: Michael S. Tsirkin; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v4 7/8] virtio/lib:add virtio guest offload
> capabilities
> 
> On Wed, Nov 11, 2015 at 08:38:29AM +0000, Liu, Jijiang wrote:
> >
> >
> > > -----Original Message-----
> > > From: Yuanhan Liu [mailto:yuanhan.liu@linux.intel.com]
> > > Sent: Wednesday, November 11, 2015 4:31 PM
> > > To: Liu, Jijiang; Michael S. Tsirkin
> > > Cc: dev@dpdk.org
> > > Subject: Re: [dpdk-dev] [PATCH v4 7/8] virtio/lib:add virtio guest
> > > offload capabilities
> > >
> > > On Wed, Nov 11, 2015 at 02:40:45PM +0800, Jijiang Liu wrote:
> > > > Add virtio guest offload capabilities.
> > > >
> > > > Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
> > > > ---
> > > >  lib/librte_vhost/virtio-net.c |    5 ++++-
> > > >  1 files changed, 4 insertions(+), 1 deletions(-)
> > > >
> > > > diff --git a/lib/librte_vhost/virtio-net.c
> > > > b/lib/librte_vhost/virtio-net.c index 81bd309..839a333 100644
> > > > --- a/lib/librte_vhost/virtio-net.c
> > > > +++ b/lib/librte_vhost/virtio-net.c
> > > > @@ -80,7 +80,10 @@ static struct virtio_net_config_ll *ll_root;
> > > >  				(1ULL <<
> > > VHOST_USER_F_PROTOCOL_FEATURES) | \
> > > >  				(1ULL << VIRTIO_NET_F_HOST_TSO4) | \
> > > >  				(1ULL << VIRTIO_NET_F_HOST_TSO6) | \
> > > > -				(1ULL << VIRTIO_NET_F_CSUM))
> > > > +				(1ULL << VIRTIO_NET_F_CSUM)    | \
> > > > +				(1ULL << VIRTIO_NET_F_GUEST_CSUM) | \
> > > > +				(1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
> > > > +				(1ULL << VIRTIO_NET_F_GUEST_TSO6))
> > >
> > > I don't think we need that, and it might be wrong to set those fields at
> vhost.
> > >
> > > And, TBH, I am not 100% sure that I understand what those flags
> > > truely are and for. All I know is that they seem have something to
> > > do with QEMU/TAP device.
> >
> > According to virtio standard, those fileds should be set.
> 
> If so, you'd better quote them here, or even to your patch commit.

In the Virtual I/O Device (VIRTIO) Version 1.0 Committee Specification 02, 

(1) VIRTIO_NET_F_GUEST_CSUM (1) Driver handles packets with partial checksum.

(2) If the VIRTIO_NET_F_GUEST_CSUM feature was negotiated, the VIRTIO_NET_HDR_F_NEEDS_-
CSUM bit in flags MAY be set: if so, the checksum on the packet is incomplete and csum_start
and csum_offset indicate how to calculate it (see Packet Transmission point 1).

(3) If the VIRTIO_NET_F_GUEST_TSO4, TSO6 or UFO options were negotiated, then gso_type
MAY be something other than VIRTIO_NET_HDR_GSO_NONE, and gso_size field indicates
the desired MSS (see Packet Transmission point 2).

The information can be included in the next version of patch set.

> 	--yliu
> 
> > Yes, I'd like to listen other guys comments.
> >
> > > Hopefully the virtio expert, Michael, could shine some lights on that.
> > >
> > > 	--yliu
> > >
> > > >
> > > >  static uint64_t VHOST_FEATURES = VHOST_SUPPORTED_FEATURES;
> > > >
> > > > --
> > > > 1.7.7.6

  reply	other threads:[~2015-11-11  8:53 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-11  6:40 [dpdk-dev] [PATCH v4 0/8] add virtio offload support in us-vhost Jijiang Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 1/8] driver/virtio:add virtual address for virtio net header Jijiang Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 2/8] driver/virtio:record virtual address of " Jijiang Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 3/8] virtio/lib:add vhost TX checksum support capabilities Jijiang Liu
2015-11-11  8:26   ` Yuanhan Liu
2015-11-11 17:31     ` Stephen Hemminger
2015-11-12  1:41       ` Yuanhan Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 4/8] virtio/lib:dequeue vhost TX offload Jijiang Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 5/8] sample/vhost:remove ip_hdr structure defination Jijiang Liu
2015-11-11  8:34   ` Yuanhan Liu
2015-11-11 10:05     ` Thomas Monjalon
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 6/8] examples/vhost:support TX offload in vhost sample Jijiang Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 7/8] virtio/lib:add virtio guest offload capabilities Jijiang Liu
2015-11-11  8:31   ` Yuanhan Liu
2015-11-11  8:38     ` Liu, Jijiang
2015-11-11  8:44       ` Yuanhan Liu
2015-11-11  8:53         ` Liu, Jijiang [this message]
2015-11-11  8:57           ` Xu, Qian Q
2015-11-11 11:10             ` Liu, Jijiang
2015-11-11 10:08           ` Thomas Monjalon
2015-11-11 12:53           ` Yuanhan Liu
2015-11-11  6:40 ` [dpdk-dev] [PATCH v4 8/8] virtio/lib:add guest offload handle Jijiang Liu
2015-11-11  8:23   ` Yuanhan Liu
2015-11-11 10:19     ` Thomas Monjalon

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=1ED644BD7E0A5F4091CF203DAFB8E4CC22BDA74A@SHSMSX101.ccr.corp.intel.com \
    --to=jijiang.liu@intel.com \
    --cc=dev@dpdk.org \
    --cc=mst@redhat.com \
    --cc=yuanhan.liu@linux.intel.com \
    /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).