From: Tiago Lam
Previously, TSO was being explicity disabled on vhost interfaces,
meaning the guests wouldn't have TSO support negotiated in. With TSO
negotiated and enabled, packets are now marked for TSO, through the
PKT_TX_TCP_SEG flag.
In order to deal with this type of packets, a new function,
netdev_dpdk_prep_tso_packet(), has been introduced, with the main
purpose of setting correctly the l2, l3 and l4 length members of the
mbuf struct, and the appropriate ol_flags. This function supports TSO
both in IPv4 and IPv6.
netdev_dpdk_prep_tso_packet() is then only called when packets are
marked with the PKT_TX_TCP_SEG flag, meaning they have been marked for
TSO, and when the packet will be traversing the NIC.
Additionally, if a packet is marked for TSO but the egress netdev
doesn't support it, the packet is dropped.
Co-authored-by: Mark Kavanagh
Signed-off-by: Mark Kavanagh
Signed-off-by: Tiago Lam
Signed-off-by: Michal Obrembski
---
lib/dp-packet.h| 16 +++
lib/netdev-bsd.c | 11 -
lib/netdev-dpdk.c | 122 ++---
lib/netdev-dummy.c | 11 -
lib/netdev-linux.c | 15 +++
5 files changed, 149 insertions(+), 26 deletions(-)
diff --git a/lib/dp-packet.h b/lib/dp-packet.h
index f091265..96136ed 100644
--- a/lib/dp-packet.h
+++ b/lib/dp-packet.h
@@ -122,6 +122,8 @@ static inline void dp_packet_set_size(struct dp_packet *,
uint32_t);
static inline uint16_t dp_packet_get_allocated(const struct dp_packet *);
static inline void dp_packet_set_allocated(struct dp_packet *, uint16_t);
+static inline bool dp_packet_is_tso(struct dp_packet *b);
+
void *dp_packet_resize_l2(struct dp_packet *, int increment);
void *dp_packet_resize_l2_5(struct dp_packet *, int increment);
static inline void *dp_packet_eth(const struct dp_packet *);
@@ -797,6 +799,14 @@ dp_packet_set_allocated(struct dp_packet *b, uint16_t s)
b->mbuf.buf_len = s;
}
+static inline bool
+dp_packet_is_tso(struct dp_packet *b)
+{
+return (b->mbuf.ol_flags & (PKT_TX_TCP_SEG | PKT_TX_L4_MASK))
+ ? true
+ : false;
+}
+
static inline void
dp_packet_copy_mbuf_flags(struct dp_packet *dst, const struct dp_packet *src)
{
@@ -1007,6 +1017,12 @@ dp_packet_get_allocated(const struct dp_packet *b)
return b->allocated_;
}
+static inline bool
+dp_packet_is_tso(struct dp_packet *b OVS_UNUSED)
+{
+return false;
+}
+
static inline void
dp_packet_set_allocated(struct dp_packet *b, uint16_t s)
{
diff --git a/lib/netdev-bsd.c b/lib/netdev-bsd.c
index 6224dab..a1172a5 100644
--- a/lib/netdev-bsd.c
+++ b/lib/netdev-bsd.c
@@ -700,11 +700,20 @@ netdev_bsd_send(struct netdev *netdev_, int qid
OVS_UNUSED,
}
DP_PACKET_BATCH_FOR_EACH (i, packet, batch) {
+size_t size = dp_packet_size(packet);
+
+/* TSO not supported in BSD netdev */
+if (dp_packet_is_tso(packet)) {
+VLOG_WARN_RL(, "%s: No TSO support on port, TSO packet of size "
+ "%" PRIuSIZE " dropped", name, size);
+
+continue;
+}
+
/* We need the whole data to send the packet on the device */
dp_packet_linearize(packet);
const void *data = dp_packet_data(packet);
-size_t size = dp_packet_size(packet);
while (!error) {
ssize_t retval;
diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 6797081..2304f28 100644
--- a/lib/netdev-dpdk.c
+++ b/lib/netdev-dpdk.c
@@ -1384,14 +1384,16 @@ netdev_dpdk_vhost_construct(struct netdev *netdev)
goto out;
}
-err = rte_vhost_driver_disable_features(dev->vhost_id,
-1ULL << VIRTIO_NET_F_HOST_TSO4
-| 1ULL << VIRTIO_NET_F_HOST_TSO6
-| 1ULL << VIRTIO_NET_F_CSUM);
-if (err) {
-VLOG_ERR("rte_vhost_driver_disable_features failed for vhost user "
- "port: %s\n", name);
-goto out;
+if (!dpdk_multi_segment_mbufs) {
+err = rte_vhost_driver_disable_features(dev->vhost_id,
+1ULL << VIRTIO_NET_F_HOST_TSO4
+| 1ULL << VIRTIO_NET_F_HOST_TSO6
+| 1ULL << VIRTIO_NET_F_CSUM);
+if (err) {
+VLOG_ERR("rte_vhost_driver_disable_features failed for vhost user "
+ "client port: %s\n", dev->up.name);
+goto out;
+}
}
err = rte_vhost_driver_start(dev->vhost_id);
@@ -2104,6 +2106,44 @@ netdev_dpdk_rxq_dealloc(struct netdev_rxq *rxq)
rte_free(rx);
}
+/* Should only be called if PKT_TX_TCP_SEG is set in ol_flags.
+ * Furthermore, it also sets the PKT_TX_TCP_CKSUM and PKT_TX_IP_CKSUM flags,
+ * and PKT_TX_IPV4 and PKT_TX_IPV6 in case the packet is IPv4 or IPv6,
+ * respectively. */
+static void
+netdev_dpdk_prep_tso_packet(struct rte_mbuf *mbuf, int mtu)
+{
+struct dp_packet *pkt;
+