22. I40E Poll Mode Driver

The i40e PMD (librte_net_i40e) provides poll mode driver support for 10/25/40 Gbps Intel® Ethernet 700 Series Network Adapters based on the Intel Ethernet Controller X710/XL710/XXV710 and Intel Ethernet Connection X722 (only support part of features).

22.1. Features

Features of the i40e PMD are:

  • Multiple queues for TX and RX
  • Receiver Side Scaling (RSS)
  • MAC/VLAN filtering
  • Packet type information
  • Flow director
  • Cloud filter
  • Checksum offload
  • VLAN/QinQ stripping and inserting
  • TSO offload
  • Promiscuous mode
  • Multicast mode
  • Port hardware statistics
  • Jumbo frames
  • Link state information
  • Link flow control
  • Mirror on port, VLAN and VSI
  • Interrupt mode for RX
  • Scattered and gather for TX and RX
  • Vector Poll mode driver
  • DCB
  • VMDQ
  • SR-IOV VF
  • Hot plug
  • IEEE1588/802.1AS timestamping
  • VF Daemon (VFD) - EXPERIMENTAL
  • Dynamic Device Personalization (DDP)
  • Queue region configuration
  • Virtual Function Port Representors
  • Malicious Device Drive event catch and notify
  • Generic flow API

22.2. Linux Prerequisites

22.3. Windows Prerequisites

  • Follow the DPDK Getting Started Guide for Windows to setup the basic DPDK environment.
  • Identify the Intel® Ethernet adapter and get the latest NVM/FW version.
  • To access any Intel® Ethernet hardware, load the NetUIO driver in place of existing built-in (inbox) driver.
  • To load NetUIO driver, follow the steps mentioned in dpdk-kmods repository.

22.5. Pre-Installation Configuration

22.5.1. Config File Options

The following options can be modified in the config/rte_config.h file.

  • RTE_LIBRTE_I40E_QUEUE_NUM_PER_PF (default 64)

    Number of queues reserved for PF.

  • RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM (default 4)

    Number of queues reserved for each VMDQ Pool.

22.5.2. Runtime Config Options

  • Reserved number of Queues per VF (default 4)

    The number of reserved queue per VF is determined by its host PF. If the PCI address of an i40e PF is aaaa:bb.cc, the number of reserved queues per VF can be configured with EAL parameter like -a aaaa:bb.cc,queue-num-per-vf=n. The value n can be 1, 2, 4, 8 or 16. If no such parameter is configured, the number of reserved queues per VF is 4 by default. If VF request more than reserved queues per VF, PF will able to allocate max to 16 queues after a VF reset.

  • Support multiple driver (default disable)

    There was a multiple driver support issue during use of 700 series Ethernet Adapter with both Linux kernel and DPDK PMD. To fix this issue, devargs parameter support-multi-driver is introduced, for example:

    -a 84:00.0,support-multi-driver=1

    With the above configuration, DPDK PMD will not change global registers, and will switch PF interrupt from IntN to Int0 to avoid interrupt conflict between DPDK and Linux Kernel.

  • Support VF Port Representor (default not enabled)

    The i40e PF PMD supports the creation of VF port representors for the control and monitoring of i40e virtual function devices. Each port representor corresponds to a single virtual function of that device. Using the devargs option representor the user can specify which virtual functions to create port representors for on initialization of the PF PMD by passing the VF IDs of the VFs which are required.:

    -a DBDF,representor=[0,1,4]

    Currently hot-plugging of representor ports is not supported so all required representors must be specified on the creation of the PF.

  • Enable validation for VF message (default not enabled)

    The PF counts messages from each VF. If in any period of seconds the message statistic from a VF exceeds maximal limitation, the PF will ignore any new message from that VF for some seconds. Format – “maximal-message@period-seconds:ignore-seconds” For example:

    -a 84:00.0,vf_msg_cfg=80@120:180

22.5.3. Vector RX Pre-conditions

For Vector RX it is assumed that the number of descriptor rings will be a power of 2. With this pre-condition, the ring pointer can easily scroll back to the head after hitting the tail without a conditional check. In addition Vector RX can use this assumption to do a bit mask using ring_size - 1.

22.6. Driver compilation and testing

Refer to the document compiling and testing a PMD for a NIC for details.

22.7. SR-IOV: Prerequisites and sample Application Notes

  1. Load the kernel module:

    modprobe i40e

    Check the output in dmesg:

    i40e 0000:83:00.1 ens802f0: renamed from eth0

  2. Bring up the PF ports:

    ifconfig ens802f0 up

  3. Create VF device(s):

    Echo the number of VFs to be created into the sriov_numvfs sysfs entry of the parent PF.

    Example:

    echo 2 > /sys/devices/pci0000:00/0000:00:03.0/0000:81:00.0/sriov_numvfs

  4. Assign VF MAC address:

    Assign MAC address to the VF using iproute2 utility. The syntax is:

    ip link set <PF netdev id> vf <VF id> mac <macaddr>

    Example:

    ip link set ens802f0 vf 0 mac a0:b0:c0:d0:e0:f0

  5. Assign VF to VM, and bring up the VM. Please see the documentation for the I40E/IXGBE/IGB Virtual Function Driver.

  6. Running testpmd:

    Follow instructions available in the document compiling and testing a PMD for a NIC to run testpmd.

    Example output:

    ...
EAL: PCI device 0000:83:00.0 on NUMA socket 1
EAL: probe driver: 8086:1572 rte_i40e_pmd
EAL: PCI memory mapped at 0x7f7f80000000
EAL: PCI memory mapped at 0x7f7f80800000
PMD: eth_i40e_dev_init(): FW 5.0 API 1.5 NVM 05.00.02 eetrack 8000208a
Interactive-mode selected
Configuring Port 0 (socket 0)
...

PMD: i40e_dev_rx_queue_setup(): Rx Burst Bulk Alloc Preconditions are
satisfied.Rx Burst Bulk Alloc function will be used on port=0, queue=0.

...
Port 0: 68:05:CA:26:85:84
Checking link statuses...
Port 0 Link Up - speed 10000 Mbps - full-duplex
Done

testpmd>

22.8. Sample Application Notes

22.8.1. Vlan filter

Vlan filter only works when Promiscuous mode is off.

To start testpmd, and add vlan 10 to port 0:

./<build_dir>/app/dpdk-testpmd -l 0-15 -n 4 -- -i --forward-mode=mac
...

testpmd> set promisc 0 off
testpmd> rx_vlan add 10 0

22.8.2. Flow Director

The Flow Director works in receive mode to identify specific flows or sets of flows and route them to specific queues. The Flow Director filters can match the different fields for different type of packet: flow type, specific input set per flow type and the flexible payload.

The default input set of each flow type is:

ipv4-other : src_ip_address, dst_ip_address
ipv4-frag  : src_ip_address, dst_ip_address
ipv4-tcp   : src_ip_address, dst_ip_address, src_port, dst_port
ipv4-udp   : src_ip_address, dst_ip_address, src_port, dst_port
ipv4-sctp  : src_ip_address, dst_ip_address, src_port, dst_port,
             verification_tag
ipv6-other : src_ip_address, dst_ip_address
ipv6-frag  : src_ip_address, dst_ip_address
ipv6-tcp   : src_ip_address, dst_ip_address, src_port, dst_port
ipv6-udp   : src_ip_address, dst_ip_address, src_port, dst_port
ipv6-sctp  : src_ip_address, dst_ip_address, src_port, dst_port,
             verification_tag
l2_payload : ether_type

The flex payload is selected from offset 0 to 15 of packet’s payload by default, while it is masked out from matching.

Start testpmd with --disable-rss and --pkt-filter-mode=perfect:

./<build_dir>/app/dpdk-testpmd -l 0-15 -n 4 -- -i --disable-rss \
              --pkt-filter-mode=perfect --rxq=8 --txq=8 --nb-cores=8 \
              --nb-ports=1

Add a rule to direct ipv4-udp packet whose dst_ip=2.2.2.5, src_ip=2.2.2.3, src_port=32, dst_port=32 to queue 1:

testpmd> flow create 0 ingress pattern eth / ipv4 src is 2.2.2.3 \
         dst is 2.2.2.5 / udp src is 32 dst is 32 / end \
         actions mark id 1 / queue index 1 / end

Check the flow director status:

testpmd> show port fdir 0

######################## FDIR infos for port 0      ####################
  MODE:   PERFECT
  SUPPORTED FLOW TYPE:  ipv4-frag ipv4-tcp ipv4-udp ipv4-sctp ipv4-other
                        ipv6-frag ipv6-tcp ipv6-udp ipv6-sctp ipv6-other
                        l2_payload
  FLEX PAYLOAD INFO:
  max_len:       16          payload_limit: 480
  payload_unit:  2           payload_seg:   3
  bitmask_unit:  2           bitmask_num:   2
  MASK:
    vlan_tci: 0x0000,
    src_ipv4: 0x00000000,
    dst_ipv4: 0x00000000,
    src_port: 0x0000,
    dst_port: 0x0000
    src_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000,
    dst_ipv6: 0x00000000,0x00000000,0x00000000,0x00000000
  FLEX PAYLOAD SRC OFFSET:
    L2_PAYLOAD:    0      1      2      3      4      5      6  ...
    L3_PAYLOAD:    0      1      2      3      4      5      6  ...
    L4_PAYLOAD:    0      1      2      3      4      5      6  ...
  FLEX MASK CFG:
    ipv4-udp:    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv4-tcp:    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv4-sctp:   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv4-other:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv4-frag:   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv6-udp:    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv6-tcp:    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv6-sctp:   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv6-other:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    ipv6-frag:   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    l2_payload:  00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  guarant_count: 1           best_count:    0
  guarant_space: 512         best_space:    7168
  collision:     0           free:          0
  maxhash:       0           maxlen:        0
  add:           0           remove:        0
  f_add:         0           f_remove:      0

22.8.3. Floating VEB

The Intel® Ethernet 700 Series support a feature called “Floating VEB”.

A Virtual Ethernet Bridge (VEB) is an IEEE Edge Virtual Bridging (EVB) term for functionality that allows local switching between virtual endpoints within a physical endpoint and also with an external bridge/network.

A “Floating” VEB doesn’t have an uplink connection to the outside world so all switching is done internally and remains within the host. As such, this feature provides security benefits.

In addition, a Floating VEB overcomes a limitation of normal VEBs where they cannot forward packets when the physical link is down. Floating VEBs don’t need to connect to the NIC port so they can still forward traffic from VF to VF even when the physical link is down.

Therefore, with this feature enabled VFs can be limited to communicating with each other but not an outside network, and they can do so even when there is no physical uplink on the associated NIC port.

To enable this feature, the user should pass a devargs parameter to the EAL, for example:

-a 84:00.0,enable_floating_veb=1

In this configuration the PMD will use the floating VEB feature for all the VFs created by this PF device.

Alternatively, the user can specify which VFs need to connect to this floating VEB using the floating_veb_list argument:

-a 84:00.0,enable_floating_veb=1,floating_veb_list=1;3-4

In this example VF1, VF3 and VF4 connect to the floating VEB, while other VFs connect to the normal VEB.

The current implementation only supports one floating VEB and one regular VEB. VFs can connect to a floating VEB or a regular VEB according to the configuration passed on the EAL command line.

The floating VEB functionality requires a NIC firmware version of 5.0 or greater.

22.8.4. Dynamic Device Personalization (DDP)

The Intel® Ethernet 700 Series except for the Intel Ethernet Connection X722 support a feature called “Dynamic Device Personalization (DDP)”, which is used to configure hardware by downloading a profile to support protocols/filters which are not supported by default. The DDP functionality requires a NIC firmware version of 6.0 or greater.

Current implementation supports GTP-C/GTP-U/PPPoE/PPPoL2TP/ESP, steering can be used with rte_flow API.

GTPv1 package is released, and it can be downloaded from https://downloadcenter.intel.com/download/27587.

PPPoE package is released, and it can be downloaded from https://downloadcenter.intel.com/download/28040.

ESP-AH package is released, and it can be downloaded from https://downloadcenter.intel.com/download/29446.

Load a profile which supports GTP and store backup profile:

testpmd> ddp add 0 ./gtp.pkgo,./backup.pkgo

Delete a GTP profile and restore backup profile:

testpmd> ddp del 0 ./backup.pkgo

Get loaded DDP package info list:

testpmd> ddp get list 0

Display information about a GTP profile:

testpmd> ddp get info ./gtp.pkgo

22.8.5. Input set configuration

Input set for any PCTYPE can be configured with user defined configuration, For example, to use only 48bit prefix for IPv6 src address for IPv6 TCP RSS:

testpmd> port config 0 pctype 43 hash_inset clear all
testpmd> port config 0 pctype 43 hash_inset set field 13
testpmd> port config 0 pctype 43 hash_inset set field 14
testpmd> port config 0 pctype 43 hash_inset set field 15

22.8.6. Queue region configuration

The Intel® Ethernet 700 Series supports a feature of queue regions configuration for RSS in the PF, so that different traffic classes or different packet classification types can be separated to different queues in different queue regions. There is an API for configuration of queue regions in RSS with a command line. It can parse the parameters of the region index, queue number, queue start index, user priority, traffic classes and so on. Depending on commands from the command line, it will call i40e private APIs and start the process of setting or flushing the queue region configuration. As this feature is specific for i40e only private APIs are used. These new test_pmd commands are as shown below. For details please refer to Testpmd Application User Guide.

testpmd> set port (port_id) queue-region region_id (value) \
             queue_start_index (value) queue_num (value)
testpmd> set port (port_id) queue-region region_id (value) flowtype (value)
testpmd> set port (port_id) queue-region UP (value) region_id (value)
testpmd> set port (port_id) queue-region flush (on|off)
testpmd> show port (port_id) queue-region

22.8.7. Generic flow API

  • RSS Flow

    RSS Flow supports to set hash input set, hash function, enable hash and configure queues. For example: Configure queues as queue 0, 1, 2, 3.

    testpmd> flow create 0 ingress pattern end actions rss types end \
  queues 0 1 2 3 end / end

    Enable hash and set input set for ipv4-tcp.

    testpmd> flow create 0 ingress pattern eth / ipv4 / tcp / end \
  actions rss types ipv4-tcp l3-src-only end queues end / end

    Set symmetric hash enable for flow type ipv4-tcp.

    testpmd> flow create 0 ingress pattern eth / ipv4 / tcp / end \
  actions rss types ipv4-tcp end queues end func symmetric_toeplitz / end

    Set hash function as simple xor.

    testpmd> flow create 0 ingress pattern end actions rss types end \
  queues end func simple_xor / end

22.9. Limitations or Known issues

22.9.1. MPLS packet classification

For firmware versions prior to 5.0, MPLS packets are not recognized by the NIC. The L2 Payload flow type in flow director can be used to classify MPLS packet by using a command in testpmd like:

testpmd> flow_director_filter 0 mode IP add flow l2_payload ether
0x8847 flexbytes () fwd pf queue <N> fd_id <M>

With the NIC firmware version 5.0 or greater, some limited MPLS support is added: Native MPLS (MPLS in Ethernet) skip is implemented, while no new packet type, no classification or offload are possible. With this change, L2 Payload flow type in flow director cannot be used to classify MPLS packet as with previous firmware versions. Meanwhile, the Ethertype filter can be used to classify MPLS packet by using a command in testpmd like:

testpmd> flow create 0 ingress pattern eth type is 0x8847 / end
actions queue index <M> / end

22.9.2. 16 Byte RX Descriptor setting on DPDK VF

Currently the VF’s RX descriptor mode is decided by PF. There’s no PF-VF interface for VF to request the RX descriptor mode, also no interface to notify VF its own RX descriptor mode. For all available versions of the i40e driver, these drivers don’t support 16 byte RX descriptor. If the Linux i40e kernel driver is used as host driver, while DPDK i40e PMD is used as the VF driver, DPDK cannot choose 16 byte receive descriptor. The reason is that the RX descriptor is already set to 32 byte by the i40e kernel driver. In the future, if the Linux i40e driver supports 16 byte RX descriptor, user should make sure the DPDK VF uses the same RX descriptor mode, 16 byte or 32 byte, as the PF driver.

The same rule for DPDK PF + DPDK VF. The PF and VF should use the same RX descriptor mode. Or the VF RX will not work.

22.9.3. Receive packets with Ethertype 0x88A8

Due to the FW limitation, PF can receive packets with Ethertype 0x88A8 only when floating VEB is disabled.

22.9.4. Incorrect Rx statistics when packet is oversize

When a packet is over maximum frame size, the packet is dropped. However, the Rx statistics, when calling rte_eth_stats_get incorrectly shows it as received.

22.9.5. RX/TX statistics may be incorrect when register overflowed

The rx_bytes/tx_bytes statistics register is 48 bit length. Although this limitation is enlarged to 64 bit length on the software side, but there is no way to detect if the overflow occurred more than once. So rx_bytes/tx_bytes statistics data is correct when statistics are updated at least once between two overflows.

22.9.6. VF & TC max bandwidth setting

The per VF max bandwidth and per TC max bandwidth cannot be enabled in parallel. The behavior is different when handling per VF and per TC max bandwidth setting. When enabling per VF max bandwidth, SW will check if per TC max bandwidth is enabled. If so, return failure. When enabling per TC max bandwidth, SW will check if per VF max bandwidth is enabled. If so, disable per VF max bandwidth and continue with per TC max bandwidth setting.

22.9.7. TC TX scheduling mode setting

There are 2 TX scheduling modes for TCs, round robin and strict priority mode. If a TC is set to strict priority mode, it can consume unlimited bandwidth. It means if APP has set the max bandwidth for that TC, it comes to no effect. It’s suggested to set the strict priority mode for a TC that is latency sensitive but no consuming much bandwidth.

22.9.8. VF performance is impacted by PCI extended tag setting

To reach maximum NIC performance in the VF the PCI extended tag must be enabled. The DPDK i40e PF driver will set this feature during initialization, but the kernel PF driver does not. So when running traffic on a VF which is managed by the kernel PF driver, a significant NIC performance downgrade has been observed (for 64 byte packets, there is about 25% line-rate downgrade for a 25GbE device and about 35% for a 40GbE device).

For kernel version >= 4.11, the kernel’s PCI driver will enable the extended tag if it detects that the device supports it. So by default, this is not an issue. For kernels <= 4.11 or when the PCI extended tag is disabled it can be enabled using the steps below.

  1. Get the current value of the PCI configure register:

    setpci -s <XX:XX.X> a8.w

  2. Set bit 8:

    value = value | 0x100

  3. Set the PCI configure register with new value:

    setpci -s <XX:XX.X> a8.w=<value>

22.9.9. Vlan strip of VF

The VF vlan strip function is only supported in the i40e kernel driver >= 2.1.26.

22.9.10. DCB function

DCB works only when RSS is enabled.

22.9.11. Global configuration warning

I40E PMD will set some global registers to enable some function or set some configure. Then when using different ports of the same NIC with Linux kernel and DPDK, the port with Linux kernel will be impacted by the port with DPDK. For example, register I40E_GL_SWT_L2TAGCTRL is used to control L2 tag, i40e PMD uses I40E_GL_SWT_L2TAGCTRL to set vlan TPID. If setting TPID in port A with DPDK, then the configuration will also impact port B in the NIC with kernel driver, which don’t want to use the TPID. So PMD reports warning to clarify what is changed by writing global register.

22.9.12. Cloud Filter

When programming cloud filters for IPv4/6_UDP/TCP/SCTP with SRC port only or DST port only, it will make any cloud filter using inner_vlan or tunnel key invalid. Default configuration will be recovered only by NIC core reset.

22.9.13. Mirror rule limitation for X722

Due to firmware restriction of X722, the same VSI cannot have more than one mirror rule.

22.10. High Performance of Small Packets on 40GbE NIC

As there might be firmware fixes for performance enhancement in latest version of firmware image, the firmware update might be needed for getting high performance. Check the Intel support website for the latest firmware updates. Users should consult the release notes specific to a DPDK release to identify the validated firmware version for a NIC using the i40e driver.

22.10.1. Use 16 Bytes RX Descriptor Size

As i40e PMD supports both 16 and 32 bytes RX descriptor sizes, and 16 bytes size can provide helps to high performance of small packets. In config/rte_config.h set the following to use 16 bytes size RX descriptors:

#define RTE_LIBRTE_I40E_16BYTE_RX_DESC 1

22.10.2. Input set requirement of each pctype for FDIR

Each PCTYPE can only have one specific FDIR input set at one time. For example, if creating 2 rte_flow rules with different input set for one PCTYPE, it will fail and return the info “Conflict with the first rule’s input set”, which means the current rule’s input set conflicts with the first rule’s. Remove the first rule if want to change the input set of the PCTYPE.

22.11. Example of getting best performance with l3fwd example

The following is an example of running the DPDK l3fwd sample application to get high performance with a server with Intel Xeon processors and Intel Ethernet CNA XL710.

The example scenario is to get best performance with two Intel Ethernet CNA XL710 40GbE ports. See Fig. 22.8 for the performance test setup.

../_images/intel_perf_test_setup.svg

Fig. 22.8 Performance Test Setup

  1. Add two Intel Ethernet CNA XL710 to the platform, and use one port per card to get best performance. The reason for using two NICs is to overcome a PCIe v3.0 limitation since it cannot provide 80GbE bandwidth for two 40GbE ports, but two different PCIe v3.0 x8 slot can. Refer to the sample NICs output above, then we can select 82:00.0 and 85:00.0 as test ports:

    82:00.0 Ethernet [0200]: Intel XL710 for 40GbE QSFP+ [8086:1583]
85:00.0 Ethernet [0200]: Intel XL710 for 40GbE QSFP+ [8086:1583]

  2. Connect the ports to the traffic generator. For high speed testing, it’s best to use a hardware traffic generator.

  3. Check the PCI devices numa node (socket id) and get the cores number on the exact socket id. In this case, 82:00.0 and 85:00.0 are both in socket 1, and the cores on socket 1 in the referenced platform are 18-35 and 54-71. Note: Don’t use 2 logical cores on the same core (e.g core18 has 2 logical cores, core18 and core54), instead, use 2 logical cores from different cores (e.g core18 and core19).

  4. Bind these two ports to igb_uio.

  5. As to Intel Ethernet CNA XL710 40GbE port, we need at least two queue pairs to achieve best performance, then two queues per port will be required, and each queue pair will need a dedicated CPU core for receiving/transmitting packets.

  6. The DPDK sample application l3fwd will be used for performance testing, with using two ports for bi-directional forwarding. Compile the l3fwd sample with the default lpm mode.

  7. The command line of running l3fwd would be something like the following:

    ./dpdk-l3fwd -l 18-21 -n 4 -a 82:00.0 -a 85:00.0 \
        -- -p 0x3 --config '(0,0,18),(0,1,19),(1,0,20),(1,1,21)'

    This means that the application uses core 18 for port 0, queue pair 0 forwarding, core 19 for port 0, queue pair 1 forwarding, core 20 for port 1, queue pair 0 forwarding, and core 21 for port 1, queue pair 1 forwarding.

  8. Configure the traffic at a traffic generator.

    • Start creating a stream on packet generator.
    • Set the Ethernet II type to 0x0800.