netdev-dpdk: Enable Rx checksum offloading feature on DPDK physical ports.

Add Rx checksum offloading feature support on DPDK physical ports. By default,
the Rx checksum offloading is enabled if NIC supports. However,
the checksum offloading can be turned OFF either while adding a new DPDK
physical port to OVS or at runtime.

The rx checksum offloading can be turned off by setting the parameter to
'false'. For eg: To disable the rx checksum offloading when adding a port,

     'ovs-vsctl add-port br0 dpdk0 -- \
      set Interface dpdk0 type=dpdk options:rx-checksum-offload=false'

OR (to disable at run time after port is being added to OVS)

    'ovs-vsctl set Interface dpdk0 options:rx-checksum-offload=false'

Similarly to turn ON rx checksum offloading at run time,
    'ovs-vsctl set Interface dpdk0 options:rx-checksum-offload=true'

The Tx checksum offloading support is not implemented due to the following
reasons.

1) Checksum offloading and vectorization are mutually exclusive in DPDK poll
mode driver. Vector packet processing is turned OFF when checksum offloading
is enabled which causes significant performance drop at Tx side.

2) Normally, OVS generates checksum for tunnel packets in software at the
'tunnel push' operation, where the tunnel headers are created. However
enabling Tx checksum offloading involves,

*) Mark every packets for tx checksum offloading at 'tunnel_push' and
recirculate.
*) At the time of xmit, validate the same flag and instruct the NIC to do the
checksum calculation.  In case NIC doesnt support Tx checksum offloading,
the checksum calculation has to be done in software before sending out the
packets.

No significant performance improvement noticed with Tx checksum offloading
due to the e overhead of additional validations + non vector packet processing.
In some test scenarios, it introduces performance drop too.

Rx checksum offloading still offers 8-9% of improvement on VxLAN tunneling
decapsulation even though the SSE vector Rx function is disabled in DPDK poll
mode driver.

Signed-off-by: Sugesh Chandran <sugesh.chandran@intel.com>
Acked-by: Jesse Gross <jesse@kernel.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>

Documentation/howto/dpdk.rst

@@ -273,6 +273,31 @@ largest frame size supported by Fortville NIC using the DPDK i40e driver, but
 larger frames and other DPDK NIC drivers may be supported. These cases are
 common for use cases involving East-West traffic only.
 
+Rx Checksum Offload
+-------------------
+
+By default, DPDK physical ports are enabled with Rx checksum offload. Rx
+checksum offload can be configured on a DPDK physical port either when adding
+or at run time.
+
+To disable Rx checksum offload when adding a DPDK port dpdk0::
+
+    $ ovs-vsctl add-port br0 dpdk0 -- set Interface dpdk0 type=dpdk \
+      options:rx-checksum-offload=false
+
+Similarly to disable the Rx checksum offloading on a existing DPDK port dpdk0::
+
+    $ ovs-vsctl set Interface dpdk0 type=dpdk options:rx-checksum-offload=false
+
+Rx checksum offload can offer performance improvement only for tunneling
+traffic in OVS-DPDK because the checksum validation of tunnel packets is
+offloaded to the NIC. Also enabling Rx checksum may slightly reduce the
+performance of non-tunnel traffic, specifically for smaller size packet.
+DPDK vectorization is disabled when checksum offloading is configured on DPDK
+physical ports which in turn effects the non-tunnel traffic performance.
+So it is advised to turn off the Rx checksum offload for non-tunnel traffic use
+cases to achieve the best performance.
+
 .. _dpdk-ovs-in-guest:
 
 OVS with DPDK Inside VMs

NEWS

@@ -46,6 +46,7 @@ Post-v2.6.0
      * New option 'n_rxq_desc' and 'n_txq_desc' fields for DPDK interfaces
        which set the number of rx and tx descriptors to use for the given port.
      * Support for DPDK v16.11.
+     * Support for rx checksum offload. Refer DPDK HOWTO for details.
    - Fedora packaging:
      * A package upgrade does not automatically restart OVS service.
    - ovs-vswitchd/ovs-vsctl:

lib/dp-packet.h

@@ -598,6 +598,37 @@ dp_packet_rss_invalidate(struct dp_packet *p)
 #endif
 }
 
+static inline bool
+dp_packet_ip_checksum_valid(struct dp_packet *p)
+{
+#ifdef DPDK_NETDEV
+    return p->mbuf.ol_flags & PKT_RX_IP_CKSUM_GOOD;
+#else
+    return 0 && p;
+#endif
+}
+
+static inline bool
+dp_packet_l4_checksum_valid(struct dp_packet *p)
+{
+#ifdef DPDK_NETDEV
+    return p->mbuf.ol_flags & PKT_RX_L4_CKSUM_GOOD;
+#else
+    return 0 && p;
+#endif
+}
+
+#ifdef DPDK_NETDEV
+static inline void
+reset_dp_packet_checksum_ol_flags(struct dp_packet *p)
+{
+    p->mbuf.ol_flags &= ~(PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
+                          PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD);
+}
+#else
+#define reset_dp_packet_checksum_ol_flags(arg)
+#endif
+
 enum { NETDEV_MAX_BURST = 32 }; /* Maximum number packets in a batch. */
 
 struct dp_packet_batch {

lib/netdev-dpdk.c

@@ -319,6 +319,10 @@ struct ingress_policer {
     rte_spinlock_t policer_lock;
 };
 
+enum dpdk_hw_ol_features {
+    NETDEV_RX_CHECKSUM_OFFLOAD = 1 << 0,
+};
+
 struct netdev_dpdk {
     struct netdev up;
     int port_id;
@@ -384,6 +388,10 @@ struct netdev_dpdk {
 
     /* DPDK-ETH Flow control */
     struct rte_eth_fc_conf fc_conf;
+
+    /* DPDK-ETH hardware offload features,
+     * from the enum set 'dpdk_hw_ol_features' */
+    uint32_t hw_ol_features;
 };
 
 struct netdev_rxq_dpdk {
@@ -633,6 +641,8 @@ dpdk_eth_dev_queue_setup(struct netdev_dpdk *dev, int n_rxq, int n_txq)
         conf.rxmode.jumbo_frame = 0;
         conf.rxmode.max_rx_pkt_len = 0;
     }
+    conf.rxmode.hw_ip_checksum = (dev->hw_ol_features &
+                                  NETDEV_RX_CHECKSUM_OFFLOAD) != 0;
     /* A device may report more queues than it makes available (this has
      * been observed for Intel xl710, which reserves some of them for
      * SRIOV):  rte_eth_*_queue_setup will fail if a queue is not
@@ -692,6 +702,29 @@ dpdk_eth_dev_queue_setup(struct netdev_dpdk *dev, int n_rxq, int n_txq)
     return diag;
 }
 
+static void
+dpdk_eth_checksum_offload_configure(struct netdev_dpdk *dev)
+    OVS_REQUIRES(dev->mutex)
+{
+    struct rte_eth_dev_info info;
+    bool rx_csum_ol_flag = false;
+    uint32_t rx_chksm_offload_capa = DEV_RX_OFFLOAD_UDP_CKSUM |
+                                     DEV_RX_OFFLOAD_TCP_CKSUM |
+                                     DEV_RX_OFFLOAD_IPV4_CKSUM;
+    rte_eth_dev_info_get(dev->port_id, &info);
+    rx_csum_ol_flag = (dev->hw_ol_features & NETDEV_RX_CHECKSUM_OFFLOAD) != 0;
+
+    if (rx_csum_ol_flag &&
+        (info.rx_offload_capa & rx_chksm_offload_capa) !=
+         rx_chksm_offload_capa) {
+        VLOG_WARN_ONCE("Rx checksum offload is not supported on device %d",
+                   dev->port_id);
+        dev->hw_ol_features &= ~NETDEV_RX_CHECKSUM_OFFLOAD;
+        return;
+    }
+    netdev_request_reconfigure(&dev->up);
+}
+
 static void
 dpdk_eth_flow_ctrl_setup(struct netdev_dpdk *dev) OVS_REQUIRES(dev->mutex)
 {
@@ -851,6 +884,9 @@ netdev_dpdk_init(struct netdev *netdev, unsigned int port_no,
 
     /* Initialize the flow control to NULL */
     memset(&dev->fc_conf, 0, sizeof dev->fc_conf);
+
+    /* Initilize the hardware offload flags to 0 */
+    dev->hw_ol_features = 0;
     if (type == DPDK_DEV_ETH) {
         err = dpdk_eth_dev_init(dev);
         if (err) {
@@ -1072,6 +1108,9 @@ netdev_dpdk_get_config(const struct netdev *netdev, struct smap *args)
                         dev->requested_txq_size);
         smap_add_format(args, "configured_txq_descriptors", "%d",
                         dev->txq_size);
+        if (dev->hw_ol_features & NETDEV_RX_CHECKSUM_OFFLOAD) {
+            smap_add(args, "rx_csum_offload", "true");
+        }
     }
     ovs_mutex_unlock(&dev->mutex);
 
@@ -1118,6 +1157,8 @@ netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args)
         {RTE_FC_NONE,     RTE_FC_TX_PAUSE},
         {RTE_FC_RX_PAUSE, RTE_FC_FULL    }
     };
+    bool rx_chksm_ofld;
+    bool temp_flag;
 
     ovs_mutex_lock(&dev->mutex);
 
@@ -1141,6 +1182,15 @@ netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args)
         dpdk_eth_flow_ctrl_setup(dev);
     }
 
+    /* Rx checksum offload configuration */
+    /* By default the Rx checksum offload is ON */
+    rx_chksm_ofld = smap_get_bool(args, "rx-checksum-offload", true);
+    temp_flag = (dev->hw_ol_features & NETDEV_RX_CHECKSUM_OFFLOAD)
+                        != 0;
+    if (temp_flag != rx_chksm_ofld) {
+        dev->hw_ol_features ^= NETDEV_RX_CHECKSUM_OFFLOAD;
+        dpdk_eth_checksum_offload_configure(dev);
+    }
     ovs_mutex_unlock(&dev->mutex);
 
     return 0;

lib/netdev-native-tnl.c

@@ -85,9 +85,11 @@ netdev_tnl_ip_extract_tnl_md(struct dp_packet *packet, struct flow_tnl *tnl,
 
         ovs_be32 ip_src, ip_dst;
 
-        if (csum(ip, IP_IHL(ip->ip_ihl_ver) * 4)) {
-            VLOG_WARN_RL(&err_rl, "ip packet has invalid checksum");
-            return NULL;
+        if (OVS_UNLIKELY(!dp_packet_ip_checksum_valid(packet))) {
+            if (csum(ip, IP_IHL(ip->ip_ihl_ver) * 4)) {
+                VLOG_WARN_RL(&err_rl, "ip packet has invalid checksum");
+                return NULL;
+            }
         }
 
         if (ntohs(ip->ip_tot_len) > l3_size) {
@@ -179,18 +181,21 @@ udp_extract_tnl_md(struct dp_packet *packet, struct flow_tnl *tnl,
     }
 
     if (udp->udp_csum) {
-        uint32_t csum;
-        if (netdev_tnl_is_header_ipv6(dp_packet_data(packet))) {
-            csum = packet_csum_pseudoheader6(dp_packet_l3(packet));
-        } else {
-            csum = packet_csum_pseudoheader(dp_packet_l3(packet));
-        }
+        if (OVS_UNLIKELY(!dp_packet_l4_checksum_valid(packet))) {
+            uint32_t csum;
+            if (netdev_tnl_is_header_ipv6(dp_packet_data(packet))) {
+                csum = packet_csum_pseudoheader6(dp_packet_l3(packet));
+            } else {
+                csum = packet_csum_pseudoheader(dp_packet_l3(packet));
+            }
 
-        csum = csum_continue(csum, udp, dp_packet_size(packet) -
-                             ((const unsigned char *)udp -
-                              (const unsigned char *)dp_packet_l2(packet)));
-        if (csum_finish(csum)) {
-            return NULL;
+            csum = csum_continue(csum, udp, dp_packet_size(packet) -
+                                 ((const unsigned char *)udp -
+                                  (const unsigned char *)dp_packet_l2(packet)
+                                 ));
+            if (csum_finish(csum)) {
+                return NULL;
+            }
         }
         tnl->flags |= FLOW_TNL_F_CSUM;
     }

lib/netdev.c

@@ -741,6 +741,10 @@ netdev_pop_header(struct netdev *netdev, struct dp_packet_batch *batch)
     for (i = 0; i < batch->count; i++) {
         buffers[i] = netdev->netdev_class->pop_header(buffers[i]);
         if (buffers[i]) {
+            /* Reset the checksum offload flags if present, to avoid wrong
+             * interpretation in the further packet processing when
+             * recirculated.*/
+            reset_dp_packet_checksum_ol_flags(buffers[i]);
             buffers[n_cnt++] = buffers[i];
         }
     }

vswitchd/vswitch.xml

@@ -3186,6 +3186,20 @@
       </column>
     </group>
 
+    <group title="Rx Checksum Offload Configuration">
+      <p>
+        The checksum validation on the incoming packets are performed on NIC
+        using Rx checksum offload feature. Implemented only for <code>dpdk
+        </code>physical interfaces.
+      </p>
+
+      <column name="options" key="rx-checksum-offload"
+              type='{"type": "boolean"}'>
+        Set to <code>false</code> to disble Rx checksum offloading on <code>
+        dpdk</code>physical ports. By default, Rx checksum offload is enabled.
+      </column>
+    </group>
+
     <group title="Common Columns">
       The overall purpose of these columns is described under <code>Common
       Columns</code> at the beginning of this document.