Add vhost TX offload(CSUM and TSO) support capabilities in vhost lib.
Refer to feature bits in Virtual I/O Device (VIRTIO) Version 1.0 below,
VIRTIO_NET_F_CSUM (0) Device handles packets with partial checksum. This
"checksum offload" is a common feature on modern network cards.
VIRTIO_NET_F_HOST_TSO4 (11) Device can receive TSOv4.
VIRTIO_NET_F_HOST_TSO6 (12) Device can receive TSOv6.
In order to support these features, and the following changes are added,
1. Extend 'VHOST_SUPPORTED_FEATURES' macro to add the offload features
negotiation.
2. Dequeue TX offload: convert the fileds in virtio_net_hdr to the related
fileds in mbuf.
Signed-off-by: Jijiang Liu <jijiang.liu at intel.com>
---
lib/librte_vhost/vhost_rxtx.c | 103 +++++++++++++++++++++++++++++++++++++++++
lib/librte_vhost/virtio-net.c | 6 ++-
2 files changed, 108 insertions(+), 1 deletions(-)
diff --git a/lib/librte_vhost/vhost_rxtx.c b/lib/librte_vhost/vhost_rxtx.c
index 9322ce6..47d5f85 100644
--- a/lib/librte_vhost/vhost_rxtx.c
+++ b/lib/librte_vhost/vhost_rxtx.c
@@ -37,7 +37,12 @@
#include <rte_mbuf.h>
#include <rte_memcpy.h>
+#include <rte_ether.h>
+#include <rte_ip.h>
#include <rte_virtio_net.h>
+#include <rte_tcp.h>
+#include <rte_udp.h>
+#include <rte_sctp.h>
#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->l3_len = sizeof(struct ipv6_hdr);
+ *l4_hdr = (char *)l3_hdr + m->l3_len;
+ m->ol_flags |= PKT_TX_IPV6;
+ 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];
@@ -770,6 +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 !=
VIRTIO_NET_HDR_GSO_NONE))
+ vhost_dequeue_offload(hdr, m);
pkts[entry_success] = m;
vq->last_used_idx++;
diff --git a/lib/librte_vhost/virtio-net.c b/lib/librte_vhost/virtio-net.c
index 14278de..81bd309 100644
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -77,7 +77,11 @@ static struct virtio_net_config_ll *ll_root;
(VHOST_SUPPORTS_MQ) | \
(1ULL << VIRTIO_F_VERSION_1) | \
(1ULL << VHOST_F_LOG_ALL) | \
- (1ULL << VHOST_USER_F_PROTOCOL_FEATURES))
+ (1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \
+ (1ULL << VIRTIO_NET_F_HOST_TSO4) | \
+ (1ULL << VIRTIO_NET_F_HOST_TSO6) | \
+ (1ULL << VIRTIO_NET_F_CSUM))
+
static uint64_t VHOST_FEATURES = VHOST_SUPPORTED_FEATURES;
--
1.7.7.6
