From: Thomas Monjalon <thomas.monjalon@6wind.com>
To: Jijiang Liu <jijiang.liu@intel.com>
Cc: dev@dpdk.org, "Michael S. Tsirkin" <mst@redhat.com>
Subject: Re: [dpdk-dev] [PATCH v3 6/8] driver/virtio:enqueue vhost TX offload
Date: Wed, 04 Nov 2015 12:17:40 +0100 [thread overview]
Message-ID: <2611781.I9AKvK5K3K@xps13> (raw)
In-Reply-To: <1446634456-413-7-git-send-email-jijiang.liu@intel.com>
2015-11-04 18:54, Jijiang Liu:
> + /* if vhost TX checksum offload is required */
> + if (m->ol_flags & PKT_TX_IP_CKSUM) {
> + hdr->csum_start = m->l2_len;
> + hdr->csum_offset = offsetof(struct ipv4_hdr, hdr_checksum);
> + } else if (m->ol_flags & PKT_TX_L4_MASK) {
> + hdr->csum_start = m->l2_len + m->l3_len;
> + switch (m->ol_flags & PKT_TX_L4_MASK) {
> + case PKT_TX_TCP_CKSUM:
> + hdr->csum_offset = offsetof(struct tcp_hdr, cksum);
> + break;
> + case PKT_TX_UDP_CKSUM:
> + hdr->csum_offset = offsetof(struct udp_hdr,
> + dgram_cksum);
> + break;
> + case PKT_TX_SCTP_CKSUM:
> + hdr->csum_offset = offsetof(struct sctp_hdr, cksum);
> + break;
> + default:
> + break;
> + }
The header checksum to offload is deduced from csum_offset.
Your vhost implementation do some parsing to deduce it:
> + parse_ethernet(m, &l4_proto, &l4_hdr);
> + if (hdr->flags == VIRTIO_NET_HDR_F_NEEDS_CSUM) {
> + if ((hdr->csum_start == m->l2_len) &&
> + (hdr->csum_offset == offsetof(struct ipv4_hdr,
> + hdr_checksum)))
> + m->ol_flags |= PKT_TX_IP_CKSUM;
> + else if (hdr->csum_start == (m->l2_len + m->l3_len)) {
> + switch (hdr->csum_offset) {
> + case (offsetof(struct tcp_hdr, cksum)):
> + if (l4_proto == IPPROTO_TCP)
> + m->ol_flags |= PKT_TX_TCP_CKSUM;
> + break;
> + case (offsetof(struct udp_hdr, dgram_cksum)):
> + if (l4_proto == IPPROTO_UDP)
> + m->ol_flags |= PKT_TX_UDP_CKSUM;
> + break;
> + case (offsetof(struct sctp_hdr, cksum)):
> + if (l4_proto == IPPROTO_SCTP)
> + m->ol_flags |= PKT_TX_SCTP_CKSUM;
> + break;
> + default:
> + break;
> + }
> + }
The kernel doesn't work this way.
Please could you check that your virtio implementation works with a
vanilla Linux with or without vhost?
Thanks
next prev parent reply other threads:[~2015-11-04 11:18 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-11-04 10:54 [dpdk-dev] [PATCH v3 0/8] add vhost TX offload support Jijiang Liu
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 1/8] driver/virtio:add virtual addr for virtio net header Jijiang Liu
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 2/8] driver/virtio: record virtual address of " Jijiang Liu
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 3/8] driver/virtio:add vhost TX checksum support capability in virtio-net Jijiang Liu
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 4/8] driver/virtio:fill virtio device info for TX offload Jijiang Liu
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 5/8] driver/virtio:enqueue vhost " Jijiang Liu
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 6/8] " Jijiang Liu
2015-11-04 11:17 ` Thomas Monjalon [this message]
2015-11-04 12:52 ` Liu, Jijiang
2015-11-04 13:18 ` Thomas Monjalon
2015-11-05 8:49 ` Xu, Qian Q
2015-11-05 9:02 ` Thomas Monjalon
2015-11-05 10:44 ` Xu, Qian Q
2015-11-06 8:24 ` Xu, Qian Q
2015-11-04 13:06 ` Liu, Jijiang
2015-11-04 13:08 ` Liu, Jijiang
2015-11-04 13:15 ` Liu, Jijiang
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 7/8] lib/librte_vhost:dequeue " Jijiang Liu
2015-11-09 4:00 ` Yuanhan Liu
2015-11-09 5:27 ` Liu, Jijiang
2015-11-04 10:54 ` [dpdk-dev] [PATCH v3 8/8] examples/vhost:support TX offload in vhost sample Jijiang Liu
2015-11-09 4:17 ` Yuanhan Liu
2015-11-09 8:17 ` Liu, Jijiang
2015-11-09 8:51 ` Yuanhan Liu
2015-11-09 8:18 ` Liu, Jijiang
2015-11-11 6:47 ` Liu, Jijiang
2015-11-04 11:14 ` [dpdk-dev] [PATCH v3 0/8] add vhost TX offload support Tan, Jianfeng
2015-11-05 14:24 ` Glynn, Michael J
-- strict thread matches above, loose matches on Subject: below --
2015-11-04 8:35 Jijiang Liu
2015-11-04 8:35 ` [dpdk-dev] [PATCH v3 6/8] driver/virtio:enqueue vhost TX offload 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=2611781.I9AKvK5K3K@xps13 \
--to=thomas.monjalon@6wind.com \
--cc=dev@dpdk.org \
--cc=jijiang.liu@intel.com \
--cc=mst@redhat.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).