From patchwork Wed Nov 11 06:40:42 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jijiang Liu X-Patchwork-Id: 8859 Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id E68D08E7E; Wed, 11 Nov 2015 07:41:04 +0100 (CET) Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id B7A8F8E7B for ; Wed, 11 Nov 2015 07:41:03 +0100 (CET) Received: from orsmga003.jf.intel.com ([10.7.209.27]) by fmsmga102.fm.intel.com with ESMTP; 10 Nov 2015 22:41:02 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.20,274,1444719600"; d="scan'208";a="682755768" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by orsmga003.jf.intel.com with ESMTP; 10 Nov 2015 22:41:02 -0800 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id tAB6exbN027469; Wed, 11 Nov 2015 14:40:59 +0800 Received: from shecgisg004.sh.intel.com (localhost [127.0.0.1]) by shecgisg004.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id tAB6euur001232; Wed, 11 Nov 2015 14:40:58 +0800 Received: (from jijiangl@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id tAB6eub7001228; Wed, 11 Nov 2015 14:40:56 +0800 From: Jijiang Liu To: dev@dpdk.org Date: Wed, 11 Nov 2015 14:40:42 +0800 Message-Id: <1447224046-1169-5-git-send-email-jijiang.liu@intel.com> X-Mailer: git-send-email 1.7.12.2 In-Reply-To: <1447224046-1169-1-git-send-email-jijiang.liu@intel.com> References: <1447224046-1169-1-git-send-email-jijiang.liu@intel.com> Subject: [dpdk-dev] [PATCH v4 4/8] virtio/lib:dequeue vhost TX offload X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Dequeue vhost TX offload(CSUM and TSO) in vhost lib Signed-off-by: Jijiang Liu --- lib/librte_vhost/vhost_rxtx.c | 104 ++++++++++++++++++++++++++++++++++++++++- 1 files changed, 103 insertions(+), 1 deletions(-) diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c index 9322ce6..9e70990 100644 --- a/lib/librte_vhost/vhost_rxtx.c +++ b/lib/librte_vhost/vhost_rxtx.c @@ -37,7 +37,12 @@ #include #include +#include +#include #include +#include +#include +#include #include "vhost-net.h" @@ -568,6 +573,97 @@ rte_vhost_enqueue_burst(struct virtio_net *dev, uint16_t queue_id, return virtio_dev_rx(dev, queue_id, pkts, count); } +static void +parse_ethernet(struct rte_mbuf *m, uint16_t *l4_proto, void **l4_hdr) +{ + struct ipv4_hdr *ipv4_hdr; + struct ipv6_hdr *ipv6_hdr; + void *l3_hdr = NULL; + struct ether_hdr *eth_hdr; + uint16_t ethertype; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + + m->l2_len = sizeof(struct ether_hdr); + ethertype = rte_be_to_cpu_16(eth_hdr->ether_type); + + if (ethertype == ETHER_TYPE_VLAN) { + struct vlan_hdr *vlan_hdr = (struct vlan_hdr *)(eth_hdr + 1); + + m->l2_len += sizeof(struct vlan_hdr); + ethertype = rte_be_to_cpu_16(vlan_hdr->eth_proto); + } + + l3_hdr = (char *)eth_hdr + m->l2_len; + + switch (ethertype) { + case ETHER_TYPE_IPv4: + ipv4_hdr = (struct ipv4_hdr *)l3_hdr; + *l4_proto = ipv4_hdr->next_proto_id; + m->l3_len = (ipv4_hdr->version_ihl & 0x0f) * 4; + *l4_hdr = (char *)l3_hdr + m->l3_len; + m->ol_flags |= PKT_TX_IPV4; + break; + case ETHER_TYPE_IPv6: + ipv6_hdr = (struct ipv6_hdr *)l3_hdr; + *l4_proto = ipv6_hdr->proto; + m->ol_flags |= PKT_TX_IPV6; + m->l3_len = sizeof(struct ipv6_hdr); + *l4_hdr = (char *)l3_hdr + m->l3_len; + break; + default: + m->l3_len = 0; + *l4_proto = 0; + break; + } +} + +static inline void __attribute__((always_inline)) +vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m) +{ + uint16_t l4_proto = 0; + void *l4_hdr = NULL; + struct tcp_hdr *tcp_hdr = NULL; + + parse_ethernet(m, &l4_proto, &l4_hdr); + if (hdr->flags == VIRTIO_NET_HDR_F_NEEDS_CSUM) { + 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; + } + } + } + + if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + case VIRTIO_NET_HDR_GSO_TCPV6: + tcp_hdr = (struct tcp_hdr *)l4_hdr; + m->ol_flags |= PKT_TX_TCP_SEG; + m->tso_segsz = hdr->gso_size; + m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2; + break; + default: + RTE_LOG(WARNING, VHOST_DATA, + "unsupported gso type %u.\n", hdr->gso_type); + break; + } + } +} + 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) @@ -576,11 +672,13 @@ 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; uint16_t free_entries, entry_success = 0; uint16_t avail_idx; + struct virtio_net_hdr *hdr = NULL; if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->virt_qp_nb))) { RTE_LOG(ERR, VHOST_DATA, @@ -632,6 +730,9 @@ 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); + hdr = (struct virtio_net_hdr *)((uintptr_t)vb_net_hdr_addr); + /* Discard first buffer as it is the virtio header */ if (desc->flags & VRING_DESC_F_NEXT) { desc = &vq->desc[desc->next]; @@ -770,7 +871,8 @@ rte_vhost_dequeue_burst(struct virtio_net *dev, uint16_t queue_id, break; m->nb_segs = seg_num; - + if ((hdr->flags != 0) || (hdr->gso_type != 0)) + vhost_dequeue_offload(hdr, m); pkts[entry_success] = m; vq->last_used_idx++; entry_success++;