23. ICE Poll Mode Driver

The ice PMD (librte_pmd_ice) provides poll mode driver support for 10/25/50/100 Gbps Intel® Ethernet 810 Series Network Adapters based on the Intel Ethernet Controller E810.

23.1. Prerequisites

  • The E810 is currently in sampling state only. To obtain early samples and/or get further information about kernel drivers, firmware and DDP support, please speak to your Intel representative.
  • Follow the DPDK Getting Started Guide for Linux to setup the basic DPDK environment.
  • To get better performance on Intel platforms, please follow the “How to get best performance with NICs on Intel platforms” section of the Getting Started Guide for Linux.

23.2. Pre-Installation Configuration

23.2.1. Config File Options

The following options can be modified in the config file. Please note that enabling debugging options may affect system performance.

  • CONFIG_RTE_LIBRTE_ICE_PMD (default y)

    Toggle compilation of the librte_pmd_ice driver.

  • CONFIG_RTE_LIBRTE_ICE_DEBUG_* (default n)

    Toggle display of generic debugging messages.

  • CONFIG_RTE_LIBRTE_ICE_16BYTE_RX_DESC (default n)

    Toggle to use a 16-byte RX descriptor, by default the RX descriptor is 32 byte.

23.2.2. Runtime Config Options

  • Safe Mode Support (default 0)

    If driver failed to load OS package, by default driver’s initialization failed. But if user intend to use the device without OS package, user can take devargs parameter safe-mode-support, for example:

    -w 80:00.0,safe-mode-support=1

    Then the driver will be initialized successfully and the device will enter Safe Mode. NOTE: In Safe mode, only very limited features are available, features like RSS, checksum, fdir, tunneling ... are all disabled.

  • Generic Flow Pipeline Mode Support (default 0)

    In pipeline mode, a flow can be set at one specific stage by setting parameter priority. Currently, we support two stages: priority = 0 or !0. Flows with priority 0 located at the first pipeline stage which typically be used as a firewall to drop the packet on a blacklist(we called it permission stage). At this stage, flow rules are created for the device’s exact match engine: switch. Flows with priority !0 located at the second stage, typically packets are classified here and be steered to specific queue or queue group (we called it distribution stage), At this stage, flow rules are created for device’s flow director engine. For none-pipeline mode, priority is ignored, a flow rule can be created as a flow director rule or a switch rule depends on its pattern/action and the resource allocation situation, all flows are virtually at the same pipeline stage. By default, generic flow API is enabled in none-pipeline mode, user can choose to use pipeline mode by setting devargs parameter pipeline-mode-support, for example:

    -w 80:00.0,pipeline-mode-support=1

  • Flow Mark Support (default 0)

    This is a hint to the driver to select the data path that supports flow mark extraction by default. NOTE: This is an experimental devarg, it will be removed when any of below conditions is ready. 1) all data paths support flow mark (currently vPMD does not) 2) a new offload like RTE_DEV_RX_OFFLOAD_FLOW_MARK be introduced as a standard way to hint. Example:

    -w 80:00.0,flow-mark-support=1

  • Protocol extraction for per queue

    Configure the RX queues to do protocol extraction into mbuf for protocol handling acceleration, like checking the TCP SYN packets quickly.

    The argument format is:

    -w 18:00.0,proto_xtr=<queues:protocol>[<queues:protocol>...]
-w 18:00.0,proto_xtr=<protocol>

    Queues are grouped by ( and ) within the group. The - character is used as a range separator and , is used as a single number separator. The grouping () can be omitted for single element group. If no queues are specified, PMD will use this protocol extraction type for all queues.

    Protocol is : vlan, ipv4, ipv6, ipv6_flow, tcp.

    testpmd -w 18:00.0,proto_xtr='[(1,2-3,8-9):tcp,10-13:vlan]'

    This setting means queues 1, 2-3, 8-9 are TCP extraction, queues 10-13 are VLAN extraction, other queues run with no protocol extraction.

    testpmd -w 18:00.0,proto_xtr=vlan,proto_xtr='[(1,2-3,8-9):tcp,10-23:ipv6]'

    This setting means queues 1, 2-3, 8-9 are TCP extraction, queues 10-23 are IPv6 extraction, other queues use the default VLAN extraction.

    The extraction metadata is copied into the registered dynamic mbuf field, and the related dynamic mbuf flags is set.

    Table 23.1 Protocol extraction : vlan
    VLAN2 VLAN1
    PCP D VID PCP D VID

    VLAN1 - single or EVLAN (first for QinQ).

    VLAN2 - C-VLAN (second for QinQ).

    Table 23.2 Protocol extraction : ipv4
    IPHDR2 IPHDR1
    Ver Hdr Len ToS TTL Protocol

    IPHDR1 - IPv4 header word 4, “TTL” and “Protocol” fields.

    IPHDR2 - IPv4 header word 0, “Ver”, “Hdr Len” and “Type of Service” fields.

    Table 23.3 Protocol extraction : ipv6
    IPHDR2 IPHDR1
    Ver Traffic class Flow Next Header Hop Limit

    IPHDR1 - IPv6 header word 3, “Next Header” and “Hop Limit” fields.

    IPHDR2 - IPv6 header word 0, “Ver”, “Traffic class” and high 4 bits of “Flow Label” fields.

    Table 23.4 Protocol extraction : ipv6_flow
    IPHDR2 IPHDR1
    Ver Traffic class Flow Label

    IPHDR1 - IPv6 header word 1, 16 low bits of the “Flow Label” field.

    IPHDR2 - IPv6 header word 0, “Ver”, “Traffic class” and high 4 bits of “Flow Label” fields.

    Table 23.5 Protocol extraction : tcp
    TCPHDR2 TCPHDR1
    Reserved Offset RSV Flags

    TCPHDR1 - TCP header word 6, “Data Offset” and “Flags” fields.

    TCPHDR2 - Reserved

    Use rte_net_ice_dynf_proto_xtr_metadata_get to access the protocol extraction metadata, and use RTE_PKT_RX_DYNF_PROTO_XTR_* to get the metadata type of struct rte_mbuf::ol_flags.

    The rte_net_ice_dump_proto_xtr_metadata routine shows how to access the protocol extraction result in struct rte_mbuf.

23.3. Driver compilation and testing

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

23.4. Features

23.4.1. Vector PMD

Vector PMD for RX and TX path are selected automatically. The paths are chosen based on 2 conditions.

  • CPU On the X86 platform, the driver checks if the CPU supports AVX2. If it’s supported, AVX2 paths will be chosen. If not, SSE is chosen.
  • Offload features The supported HW offload features are described in the document ice_vec.ini. If any not supported features are used, ICE vector PMD is disabled and the normal paths are chosen.

23.4.2. Malicious driver detection (MDD)

It’s not appropriate to send a packet, if this packet’s destination MAC address is just this port’s MAC address. If SW tries to send such packets, HW will report a MDD event and drop the packets.

The APPs based on DPDK should avoid providing such packets.

23.4.3. Device Config Function (DCF)

This section demonstrates ICE DCF PMD, which shares the core module with ICE PMD and iAVF PMD.

A DCF (Device Config Function) PMD bounds to the device’s trusted VF with ID 0, it can act as a sole controlling entity to exercise advance functionality (such as switch, ACL) for the rest VFs.

The DCF PMD needs to advertise and acquire DCF capability which allows DCF to send AdminQ commands that it would like to execute over to the PF and receive responses for the same from PF.

../_images/ice_dcf.svg

Fig. 23.1 DCF Communication flow.

  1. Create the VFs:

    echo 4 > /sys/bus/pci/devices/0000\:18\:00.0/sriov_numvfs

  2. Enable the VF0 trust on:

    ip link set dev enp24s0f0 vf 0 trust on

  3. Bind the VF0, and run testpmd with ‘cap=dcf’ devarg:

    testpmd -l 22-25 -n 4 -w 18:01.0,cap=dcf -- -i

  4. Monitor the VF2 interface network traffic:

    tcpdump -e -nn -i enp24s1f2

  5. Create one flow to redirect the traffic to VF2 by DCF:

    flow create 0 priority 0 ingress pattern eth / ipv4 src is 192.168.0.2 \
dst is 192.168.0.3 / end actions vf id 2 / end

  6. Send the packet, and it should be displayed on tcpdump:

    sendp(Ether(src='3c:fd:fe:aa:bb:78', dst='00:00:00:01:02:03')/IP(src=' \
192.168.0.2', dst="192.168.0.3")/TCP(flags='S')/Raw(load='XXXXXXXXXX'), \
iface="enp24s0f0", count=10)

23.5. Sample Application Notes

23.5.1. Vlan filter

Vlan filter only works when Promiscuous mode is off.

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

./app/testpmd -l 0-15 -n 4 -- -i
...

testpmd> rx_vlan add 10 0

23.6. Limitations or Known issues

The Intel E810 requires a programmable pipeline package be downloaded by the driver to support normal operations. The E810 has a limited functionality built in to allow PXE boot and other use cases, but the driver must download a package file during the driver initialization stage.

The default DDP package file name is ice.pkg. For a specific NIC, the DDP package supposed to be loaded can have a filename: ice-xxxxxx.pkg, where ‘xxxxxx’ is the 64-bit PCIe Device Serial Number of the NIC. For example, if the NIC’s device serial number is 00-CC-BB-FF-FF-AA-05-68, the device-specific DDP package filename is ice-00ccbbffffaa0568.pkg (in hex and all low case). During initialization, the driver searches in the following paths in order: /lib/firmware/updates/intel/ice/ddp and /lib/firmware/intel/ice/ddp. The corresponding device-specific DDP package will be downloaded first if the file exists. If not, then the driver tries to load the default package. The type of loaded package is stored in ice_adapter->active_pkg_type.

A symbolic link to the DDP package file is also ok. The same package file is used by both the kernel driver and the DPDK PMD.

23.6.1. limitation

Ice code released is for evaluation only currently.