From: "Liu, Jijiang" <jijiang.liu@intel.com>
To: "Ouyang, Changchun" <changchun.ouyang@intel.com>,
"dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [RFC PATCH 5/8] lib/librte_vhost:dequeue vhost TSO offload
Date: Mon, 7 Sep 2015 06:16:06 +0000 [thread overview]
Message-ID: <1ED644BD7E0A5F4091CF203DAFB8E4CC057D9881@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <F52918179C57134FAEC9EA62FA2F962511CEF004@shsmsx102.ccr.corp.intel.com>
> -----Original Message-----
> From: Ouyang, Changchun
> Sent: Monday, August 31, 2015 8:40 PM
> To: Liu, Jijiang; dev@dpdk.org
> Cc: Ouyang, Changchun
> Subject: RE: [dpdk-dev] [RFC PATCH 5/8] lib/librte_vhost:dequeue vhost TSO
> offload
>
>
>
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Jijiang Liu
> > Sent: Monday, August 31, 2015 5:42 PM
> > To: dev@dpdk.org
> > Subject: [dpdk-dev] [RFC PATCH 5/8] lib/librte_vhost:dequeue vhost TSO
> > offload
> >
> > Dequeue vhost TSO offload
> >
> > Signed-off-by: Jijiang Liu <jijiang.liu@intel.com>
> > ---
> > lib/librte_vhost/vhost_rxtx.c | 29 ++++++++++++++++++++++++++++-
> > 1 files changed, 28 insertions(+), 1 deletions(-)
> >
> > diff --git a/lib/librte_vhost/vhost_rxtx.c
> > b/lib/librte_vhost/vhost_rxtx.c index 0d07338..9adfdb1 100644
> > --- a/lib/librte_vhost/vhost_rxtx.c
> > +++ b/lib/librte_vhost/vhost_rxtx.c
> > @@ -545,6 +545,30 @@ rte_vhost_enqueue_burst(struct virtio_net *dev,
> > uint16_t queue_id,
> > return virtio_dev_rx(dev, queue_id, pkts, count); }
> >
> > +static inline void __attribute__((always_inline))
> > +vhost_dequeue_offload(uint64_t addr, struct rte_mbuf *m) {
> > + struct virtio_net_hdr *hdr =
> > + (struct virtio_net_hdr *)((uintptr_t)addr);
> > +
> > + if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
> > + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
> > + case VIRTIO_NET_HDR_GSO_TCPV4:
> > + m->ol_flags |= (PKT_TX_IPV4 | PKT_TX_TCP_SEG);
> > + m->tso_segsz = hdr->gso_size;
> > + break;
> > + case VIRTIO_NET_HDR_GSO_TCPV6:
> > + m->ol_flags |= (PKT_TX_IPV6 | PKT_TX_TCP_SEG);
> > + m->tso_segsz = hdr->gso_size;
> > + break;
> > + default:
> > + RTE_LOG(ERR, VHOST_DATA,
> > + "bad gso type %u.\n", hdr->gso_type);
> > + break;
>
> Do we need special handling for the bad gso type?
Yes, we need return error, and log it and break this operation.
I will change it in next version.
>
> > + }
> > + }
> > +}
> > +
> > uint16_t
> > rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t queue_id,
> > struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t
> > count) @@ -553,6 +577,7 @@ rte_vhost_dequeue_burst(struct virtio_net
> > *dev, uint16_t queue_id,
> > struct vhost_virtqueue *vq;
> > struct vring_desc *desc;
> > uint64_t vb_addr = 0;
> > + uint64_t vb_net_hdr_addr = 0;
> > uint32_t head[MAX_PKT_BURST];
> > uint32_t used_idx;
> > uint32_t i;
> > @@ -604,6 +629,8 @@ rte_vhost_dequeue_burst(struct virtio_net *dev,
> > uint16_t queue_id,
> >
> > desc = &vq->desc[head[entry_success]];
> >
> > + vb_net_hdr_addr = gpa_to_vva(dev, desc->addr);
> > +
> > /* Discard first buffer as it is the virtio header */
> > if (desc->flags & VRING_DESC_F_NEXT) {
> > desc = &vq->desc[desc->next];
> > @@ -742,7 +769,7 @@ rte_vhost_dequeue_burst(struct virtio_net *dev,
> > uint16_t queue_id,
> > break;
> >
> > m->nb_segs = seg_num;
> > -
> > + vhost_dequeue_offload(vb_net_hdr_addr, m);
> > pkts[entry_success] = m;
> > vq->last_used_idx++;
> > entry_success++;
> > --
> > 1.7.7.6
next prev parent reply other threads:[~2015-09-07 6:16 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-31 9:41 [dpdk-dev] [RFC PATCH 0/8] Add vhost TSO capability Jijiang Liu
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 1/8] driver/virtio:add vhost TSO support capability Jijiang Liu
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 2/8] driver/virtio: add virtual addr for virtio net header Jijiang Liu
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 3/8] driver/virtio: record virtual address of " Jijiang Liu
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 4/8] driver/virtio:enqueue TSO offload Jijiang Liu
2015-09-01 3:28 ` Ouyang, Changchun
2015-09-07 6:11 ` Liu, Jijiang
2015-09-09 1:17 ` Ouyang, Changchun
2015-09-09 17:21 ` Liu, Jijiang
2015-09-09 23:03 ` Ouyang, Changchun
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 5/8] lib/librte_vhost:dequeue vhost " Jijiang Liu
2015-09-01 3:40 ` Ouyang, Changchun
2015-09-07 6:16 ` Liu, Jijiang [this message]
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 6/8] lib/librte_vhost:extend supported vhost features Jijiang Liu
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 7/8] examples/vhost:support tso in vhost sample Jijiang Liu
2015-08-31 9:41 ` [dpdk-dev] [RFC PATCH 8/8] app/testpmd: modify the mac of csum forwarding Jijiang Liu
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=1ED644BD7E0A5F4091CF203DAFB8E4CC057D9881@SHSMSX101.ccr.corp.intel.com \
--to=jijiang.liu@intel.com \
--cc=changchun.ouyang@intel.com \
--cc=dev@dpdk.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).