mir/ovs
2
0
Fork 0
mirror of https://github.com/openvswitch/ovs synced 2025-09-05 00:35:33 +00:00
Code Issues Releases Wiki Activity

userspace: Enable L4 checksum offloading by default.

Browse Source 
The netdev receiving packets is supposed to provide the flags
indicating if the L4 checksum was verified and it is OK or BAD,
otherwise the stack will check when appropriate by software.

If the packet comes with good checksum, then postpone the
checksum calculation to the egress device if needed.

When encapsulate a packet with that flag, set the checksum
of the inner L4 header since that is not yet supported.

Calculate the L4 checksum when the packet is going to be sent
over a device that doesn't support the feature.

Linux tap devices allows enabling L3 and L4 offload, so this
patch enables the feature. However, Linux socket interface
remains disabled because the API doesn't allow enabling
those two features without enabling TSO too.

Signed-off-by: Flavio Leitner <fbl@sysclose.org>
Co-authored-by: Flavio Leitner <fbl@sysclose.org>
Signed-off-by: Mike Pattrick <mkp@redhat.com>
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
This commit is contained in:
Mike Pattrick
2023-06-14 15:03:27 -04:00
committed by Ilya Maximets
parent 5d11c47d3e
commit 3337e6d91c
13 changed files with 715 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

172
lib/netdev-dpdk.c
View File

@@ -412,8 +412,10 @@ enum dpdk_hw_ol_features {
NETDEV_RX_HW_CRC_STRIP = 1 << 1,
NETDEV_RX_HW_SCATTER = 1 << 2,
NETDEV_TX_IPV4_CKSUM_OFFLOAD = 1 << 3,
NETDEV_TX_TSO_OFFLOAD = 1 << 4,
NETDEV_TX_SCTP_CHECKSUM_OFFLOAD = 1 << 5,
NETDEV_TX_TCP_CKSUM_OFFLOAD = 1 << 4,
NETDEV_TX_UDP_CKSUM_OFFLOAD = 1 << 5,
NETDEV_TX_SCTP_CKSUM_OFFLOAD = 1 << 6,
NETDEV_TX_TSO_OFFLOAD = 1 << 7,
};
/*
@@ -1008,6 +1010,37 @@ dpdk_watchdog(void *dummy OVS_UNUSED)
return NULL;
}
static void
netdev_dpdk_update_netdev_flag(struct netdev_dpdk *dev,
enum dpdk_hw_ol_features hw_ol_features,
enum netdev_ol_flags flag)
OVS_REQUIRES(dev->mutex)
{
struct netdev *netdev = &dev->up;
if (dev->hw_ol_features & hw_ol_features) {
netdev->ol_flags |= flag;
} else {
netdev->ol_flags &= ~flag;
}
}
static void
netdev_dpdk_update_netdev_flags(struct netdev_dpdk *dev)
OVS_REQUIRES(dev->mutex)
{
netdev_dpdk_update_netdev_flag(dev, NETDEV_TX_IPV4_CKSUM_OFFLOAD,
NETDEV_TX_OFFLOAD_IPV4_CKSUM);
netdev_dpdk_update_netdev_flag(dev, NETDEV_TX_TCP_CKSUM_OFFLOAD,
NETDEV_TX_OFFLOAD_TCP_CKSUM);
netdev_dpdk_update_netdev_flag(dev, NETDEV_TX_UDP_CKSUM_OFFLOAD,
NETDEV_TX_OFFLOAD_UDP_CKSUM);
netdev_dpdk_update_netdev_flag(dev, NETDEV_TX_SCTP_CKSUM_OFFLOAD,
NETDEV_TX_OFFLOAD_SCTP_CKSUM);
netdev_dpdk_update_netdev_flag(dev, NETDEV_TX_TSO_OFFLOAD,
NETDEV_TX_OFFLOAD_TCP_TSO);
}
static int
dpdk_eth_dev_port_config(struct netdev_dpdk *dev, int n_rxq, int n_txq)
{
@@ -1044,11 +1077,20 @@ dpdk_eth_dev_port_config(struct netdev_dpdk *dev, int n_rxq, int n_txq)
conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_IPV4_CKSUM;
}
if (dev->hw_ol_features & NETDEV_TX_TCP_CKSUM_OFFLOAD) {
conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_TCP_CKSUM;
}
if (dev->hw_ol_features & NETDEV_TX_UDP_CKSUM_OFFLOAD) {
conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_UDP_CKSUM;
}
if (dev->hw_ol_features & NETDEV_TX_SCTP_CKSUM_OFFLOAD) {
conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_SCTP_CKSUM;
}
if (dev->hw_ol_features & NETDEV_TX_TSO_OFFLOAD) {
conf.txmode.offloads |= DPDK_TX_TSO_OFFLOAD_FLAGS;
if (dev->hw_ol_features & NETDEV_TX_SCTP_CHECKSUM_OFFLOAD) {
conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_SCTP_CKSUM;
}
conf.txmode.offloads |= RTE_ETH_TX_OFFLOAD_TCP_TSO;
}
/* Limit configured rss hash functions to only those supported
@@ -1154,7 +1196,6 @@ dpdk_eth_dev_init(struct netdev_dpdk *dev)
struct rte_ether_addr eth_addr;
int diag;
int n_rxq, n_txq;
uint32_t tx_tso_offload_capa = DPDK_TX_TSO_OFFLOAD_FLAGS;
uint32_t rx_chksm_offload_capa = RTE_ETH_RX_OFFLOAD_UDP_CKSUM |
RTE_ETH_RX_OFFLOAD_TCP_CKSUM |
RTE_ETH_RX_OFFLOAD_IPV4_CKSUM;
@@ -1190,18 +1231,28 @@ dpdk_eth_dev_init(struct netdev_dpdk *dev)
dev->hw_ol_features &= ~NETDEV_TX_IPV4_CKSUM_OFFLOAD;
}
if (info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_TCP_CKSUM) {
dev->hw_ol_features |= NETDEV_TX_TCP_CKSUM_OFFLOAD;
} else {
dev->hw_ol_features &= ~NETDEV_TX_TCP_CKSUM_OFFLOAD;
}
if (info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_UDP_CKSUM) {
dev->hw_ol_features |= NETDEV_TX_UDP_CKSUM_OFFLOAD;
} else {
dev->hw_ol_features &= ~NETDEV_TX_UDP_CKSUM_OFFLOAD;
}
if (info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_SCTP_CKSUM) {
dev->hw_ol_features |= NETDEV_TX_SCTP_CKSUM_OFFLOAD;
} else {
dev->hw_ol_features &= ~NETDEV_TX_SCTP_CKSUM_OFFLOAD;
}
dev->hw_ol_features &= ~NETDEV_TX_TSO_OFFLOAD;
if (userspace_tso_enabled()) {
if ((info.tx_offload_capa & tx_tso_offload_capa)
== tx_tso_offload_capa) {
if (info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_TCP_TSO) {
dev->hw_ol_features |= NETDEV_TX_TSO_OFFLOAD;
if (info.tx_offload_capa & RTE_ETH_TX_OFFLOAD_SCTP_CKSUM) {
dev->hw_ol_features |= NETDEV_TX_SCTP_CHECKSUM_OFFLOAD;
} else {
VLOG_WARN("%s: Tx SCTP checksum offload is not supported, "
"SCTP packets sent to this device will be dropped",
netdev_get_name(&dev->up));
}
} else {
VLOG_WARN("%s: Tx TSO offload is not supported.",
netdev_get_name(&dev->up));
@@ -2245,6 +2296,7 @@ netdev_dpdk_prep_hwol_packet(struct netdev_dpdk *dev, struct rte_mbuf *mbuf)
mbuf->l2_len = (char *) dp_packet_l3(pkt) - (char *) dp_packet_eth(pkt);
mbuf->l3_len = (char *) dp_packet_l4(pkt) - (char *) dp_packet_l3(pkt);
mbuf->l4_len = 0;
mbuf->outer_l2_len = 0;
mbuf->outer_l3_len = 0;
@@ -4181,6 +4233,7 @@ new_device(int vid)
ovs_mutex_lock(&dev->mutex);
if (nullable_string_is_equal(ifname, dev->vhost_id)) {
uint32_t qp_num = rte_vhost_get_vring_num(vid) / VIRTIO_QNUM;
uint64_t features;
/* Get NUMA information */
newnode = rte_vhost_get_numa_node(vid);
@@ -4205,6 +4258,36 @@ new_device(int vid)
dev->vhost_reconfigured = true;
}
if (rte_vhost_get_negotiated_features(vid, &features)) {
VLOG_INFO("Error checking guest features for "
"vHost Device '%s'", dev->vhost_id);
} else {
if (features & (1ULL << VIRTIO_NET_F_GUEST_CSUM)) {
dev->hw_ol_features |= NETDEV_TX_TCP_CKSUM_OFFLOAD;
dev->hw_ol_features |= NETDEV_TX_UDP_CKSUM_OFFLOAD;
dev->hw_ol_features |= NETDEV_TX_SCTP_CKSUM_OFFLOAD;
}
if (userspace_tso_enabled()) {
if (features & (1ULL << VIRTIO_NET_F_GUEST_TSO4)
&& features & (1ULL << VIRTIO_NET_F_GUEST_TSO6)) {
dev->hw_ol_features |= NETDEV_TX_TSO_OFFLOAD;
VLOG_DBG("%s: TSO enabled on vhost port",
netdev_get_name(&dev->up));
} else {
VLOG_WARN("%s: Tx TSO offload is not supported.",
netdev_get_name(&dev->up));
}
}
}
/* There is no support in virtio net to offload IPv4 csum,
* but the vhost library handles IPv4 csum offloading fine. */
dev->hw_ol_features |= NETDEV_TX_IPV4_CKSUM_OFFLOAD;
netdev_dpdk_update_netdev_flags(dev);
ovsrcu_index_set(&dev->vid, vid);
exists = true;
@@ -4268,6 +4351,10 @@ destroy_device(int vid)
dev->up.n_rxq * sizeof *dev->vhost_rxq_enabled);
netdev_dpdk_txq_map_clear(dev);
/* Clear offload capabilities before next new_device. */
dev->hw_ol_features = 0;
netdev_dpdk_update_netdev_flags(dev);
netdev_change_seq_changed(&dev->up);
ovs_mutex_unlock(&dev->mutex);
exists = true;
@@ -5278,22 +5365,7 @@ netdev_dpdk_reconfigure(struct netdev *netdev)
}
err = dpdk_eth_dev_init(dev);
if (dev->hw_ol_features & NETDEV_TX_IPV4_CKSUM_OFFLOAD) {
netdev->ol_flags |= NETDEV_TX_OFFLOAD_IPV4_CKSUM;
} else {
netdev->ol_flags &= ~NETDEV_TX_OFFLOAD_IPV4_CKSUM;
}
if (dev->hw_ol_features & NETDEV_TX_TSO_OFFLOAD) {
netdev->ol_flags |= NETDEV_TX_OFFLOAD_TCP_TSO;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_TCP_CKSUM;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_UDP_CKSUM;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_IPV4_CKSUM;
if (dev->hw_ol_features & NETDEV_TX_SCTP_CHECKSUM_OFFLOAD) {
netdev->ol_flags |= NETDEV_TX_OFFLOAD_SCTP_CKSUM;
}
}
netdev_dpdk_update_netdev_flags(dev);
/* If both requested and actual hwaddr were previously
* unset (initialized to 0), then first device init above
@@ -5340,11 +5412,6 @@ dpdk_vhost_reconfigure_helper(struct netdev_dpdk *dev)
memset(dev->sw_stats, 0, sizeof *dev->sw_stats);
rte_spinlock_unlock(&dev->stats_lock);
if (userspace_tso_enabled()) {
dev->hw_ol_features |= NETDEV_TX_TSO_OFFLOAD;
VLOG_DBG("%s: TSO enabled on vhost port", netdev_get_name(&dev->up));
}
netdev_dpdk_remap_txqs(dev);
if (netdev_dpdk_get_vid(dev) >= 0) {
@@ -5365,6 +5432,8 @@ dpdk_vhost_reconfigure_helper(struct netdev_dpdk *dev)
}
}
netdev_dpdk_update_netdev_flags(dev);
return 0;
}
@@ -5386,8 +5455,6 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
int err;
uint64_t vhost_flags = 0;
uint64_t vhost_unsup_flags;
ovs_mutex_lock(&dev->mutex);
@@ -5397,6 +5464,9 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
* 2. A path has been specified.
*/
if (!(dev->vhost_driver_flags & RTE_VHOST_USER_CLIENT) && dev->vhost_id) {
uint64_t virtio_unsup_features = 0;
uint64_t vhost_flags = 0;
/* Register client-mode device. */
vhost_flags |= RTE_VHOST_USER_CLIENT;
@@ -5443,22 +5513,22 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
}
if (userspace_tso_enabled()) {
netdev->ol_flags |= NETDEV_TX_OFFLOAD_TCP_TSO;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_TCP_CKSUM;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_UDP_CKSUM;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_SCTP_CKSUM;
netdev->ol_flags |= NETDEV_TX_OFFLOAD_IPV4_CKSUM;
vhost_unsup_flags = 1ULL << VIRTIO_NET_F_HOST_ECN
| 1ULL << VIRTIO_NET_F_HOST_UFO;
virtio_unsup_features = 1ULL << VIRTIO_NET_F_HOST_ECN
| 1ULL << VIRTIO_NET_F_HOST_UFO;
VLOG_DBG("%s: TSO enabled on vhost port",
netdev_get_name(&dev->up));
} else {
/* This disables checksum offloading and all the features
* that depends on it (TSO, UFO, ECN) according to virtio
* specification. */
vhost_unsup_flags = 1ULL << VIRTIO_NET_F_CSUM;
/* Advertise checksum offloading to the guest, but explicitly
* disable TSO and friends.
* NOTE: we can't disable HOST_ECN which may have been wrongly
* negotiated by a running guest. */
virtio_unsup_features = 1ULL << VIRTIO_NET_F_HOST_TSO4
| 1ULL << VIRTIO_NET_F_HOST_TSO6
| 1ULL << VIRTIO_NET_F_HOST_UFO;
}
err = rte_vhost_driver_disable_features(dev->vhost_id,
vhost_unsup_flags);
virtio_unsup_features);
if (err) {
VLOG_ERR("rte_vhost_driver_disable_features failed for "
"vhost user client port: %s\n", dev->up.name);