AT_COPYRIGHT([Copyright (c) 2025 Red Hat, Inc.

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at:

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.])

# Macro to exclude tests that will fail with dpdk offload enabled.
# We currently have the below tests disabled in system-traffic.at
# for the following reasons:
#
#  For dpdk offload_mutex there is no kernel side of the simulated VETH
#  interface.  Therefore the following tests are disabled, as they assume
#  kernel ports exist since they have dependencies on their behavior.
#    - 'datapath - netdev offload software fallback'
#
#  DPDK offload does not update flow statistics when a hardware offloaded flow
#  is removed, which means the statistics are incorrect. Until this changes,
#  the following test needs to be disabled:
#    - 'datapath - simulated flow action update'
#
#  The dpdk offload test cases use VF interfaces, which are Ethernet devices
#  with a minimum frame size of 64 bytes.  As a result, received packets appear
#  larger than expected.  Virtual interfaces, however, report the actual size.
#  To avoid adding complex counter adjustments in tests that rely on these
#  values, we skip them.
#    - 'conntrack - ICMP related'
#    - 'conntrack - resubmit to ct multiple times'
#    - 'conntrack - ICMP related with NAT'
#    - 'conntrack - Multiple ICMP traverse'
#
# There is a kernel problem where it will not accept fragmented ICMPv6 packets
# for the same session if they are batched together. Due to DUT-specific
# circumstances, this can occasionally happen for the test below. To avoid
# adding complex detection for this, we simply skip the test.
#    - 'conntrack - IPv6 fragmentation + vlan'
#
m4_define([CHECK_NO_DPDK_OFFLOAD],
[
     AT_SKIP_IF([:])
])

# OVS_DPDK_OFFLOAD_PRE_CHECK()
#
# Check prerequisites for DPDK rte_flow tests. Following settings are checked:
#  - Existence of at least six VFs and their representors.
#
m4_define([OVS_DPDK_OFFLOAD_PRE_CHECK], [
  OVS_DPDK_PRE_CHECK()
  AT_SKIP_IF(
    [test "$(printf '%s' "$OVS_DPDK_VF_PCI_ADDRS" | wc -w)" -ne 6])

  AT_SKIP_IF([! ovs_dpdk_verify_vf_cfg "$OVS_DPDK_VF_PCI_ADDRS"])
])

# OVS_TRAFFIC_VSWITCHD_START([vsctl-args], [vsctl-output], [dbinit-aux-args])
#
# This is a copy from system-dpdk-macro.at with two small changes:
#  1) Use OVS_DPDK_OFFLOAD_PRE_CHECK() instead of OVS_DPDK_PRE_CHECK().
#  2) Start with pci enabled for PF devices.
#
m4_define([OVS_TRAFFIC_VSWITCHD_START],
  [
   OVS_DPDK_OFFLOAD_PRE_CHECK()
   OVS_WAIT_WHILE([ip link show ovs-netdev])
   ALLOW_LIST=$(echo "$OVS_DPDK_VF_PCI_ADDRS" | awk '{
     for (i=1; i<=NF; i++) {
       split($i, parts, ",");
       addr = parts[1];
       if (addr != "" && !seen[addr]) {
         seen[addr] = 1;
         if (result == "")
           result = "--allow " addr;
         else
           result = result " --allow " addr;
        }
     }
     print result;
   }')
   OVS_DPDK_START([$ALLOW_LIST], [--disable-system],
                  [-- set Open_vSwitch . other_config:hw-offload=true $3])
   dnl Add bridges, ports, etc.
   OVS_WAIT_WHILE([ip link show br0])
   AT_CHECK([ovs-vsctl -- _ADD_BR([br0]) -- $1 m4_if([$2], [], [],
            [| uuidfilt])], [0], [$2])
])

# OVS_TRAFFIC_VSWITCHD_STOP([ALLOWLIST], [extra_cmds])
#
# This is a copy from system-dpdk-macro.at adding some dpdk offload specific
# error message exclusion.
#
m4_define([OVS_TRAFFIC_VSWITCHD_STOP],
  [OVS_DPDK_STOP_VSWITCHD([dnl
$1";/mlx5_net: Failed to update link status: /d"])
   AT_CHECK([:; $2])
])

# ADD_{VF|VETH}([port], [namespace], [ovs-br], [ip_addr] [mac_addr], [gateway],
#               [ip_addr_flags])
#
# Simulate the ADD_VETH() macro defined in system-common-macros.at, allowing
# us to run the existing system-traffic unit tests without any test-specific
# changes.  This is consistent with how DPDK and AF_XDP run the system tests,
# except that we are not using actual veth devices, but VF representer ports.
#
m4_define([ADD_VF],
    [ USER_PORT=$1
      case "$USER_PORT" in
        client) PORT_NO=0 ;;
        server) PORT_NO=1 ;;
        *) PORT_NO=${USER_PORT##*[!0-9]} ;;
      esac

      AT_CHECK([[[ "$PORT_NO" -ge 0 ]] && [[ "$PORT_NO" -le 6 ]] || return 66])
      PORT_CFG=$(echo $OVS_DPDK_VF_PCI_ADDRS | cut -d' ' -f$((PORT_NO+1)))
      PF_PCI=$(ovs_dpdk_get_pci_id "$PORT_CFG")
      VF_IDX=$(ovs_dpdk_get_vf_idx "$PORT_CFG")
      REP=$(ovs_dpdk_get_representor_netdev $PF_PCI $VF_IDX)
      AT_CHECK([test $? -eq 0])

      AT_CHECK([ip link set $REP name $1])
      AT_CHECK([ip link set $1 netns $2])
      AT_CHECK([ovs-vsctl add-port $3 ovs-$1 -- \
                set interface ovs-$1 external-ids:iface-id="$1" -- \
                set interface ovs-$1 type=dpdk -- \
                set interface ovs-$1 \
                  options:dpdk-devargs=$PF_PCI,representor=vf$VF_IDX])
      NS_CHECK_EXEC([$2], [ip addr add $4 dev $1 $7])
      NS_CHECK_EXEC([$2], [ip link set dev $1 up])
      if test -n "$5"; then
        NS_CHECK_EXEC([$2], [ip link set dev $1 address $5])
      else
        NS_CHECK_EXEC([$2],
                      [ip link set dev $1 address 02:00:00:00:EC:0$PORT_NO])
      fi
      if test -n "$6"; then
        NS_CHECK_EXEC([$2], [ip route add default via $6])
      fi
      on_exit "ip netns exec $2 ip link set $1 netns 1; \
               ip link property del dev $1 altname $REP; \
               ip link set $1 name $REP"
    ]
)
m4_define([ADD_VETH], [ADD_VF($@)])

# DUMP_DP_IP_CLEAN_SORTED()
#
# Clean up and sort the ovs-dpctl dump-flow output for comparing.
#
m4_define([DUMP_DP_IP_CLEAN_SORTED], [dnl
  grep 'eth_type(0x0800)' \
    | sed -e 's/eth(src=[[a-z0-9:]]*,dst=[[a-z0-9:]]*)/eth(macs)/;s/recirc_id(0),//' \
    | strip_used | strip_ptype | sort])

OVS_START_SHELL_HELPERS

# ovs_dpdk_is_valid_pci_vf_addr()
#
# Check if the given PF PCI address and the VF number are valid.
#
ovs_dpdk_is_valid_pci_vf_addr() {
    PCI_ID='[[0-9a-fA-F]]{4}:[[0-9a-fA-F]]{2}:[[0-9a-fA-F]]{2}\.[[0-7]]'
    echo "$1" | grep -E -q "^$PCI_ID,[[0-9]]+$" && return 0 || return 1
}

# ovs_dpdk_get_pci_id()
#
ovs_dpdk_get_pci_id() {
    printf '%s\n' "${1%%,*}"
}

# ovs_dpdk_get_vf_idx()
#
ovs_dpdk_get_vf_idx() {
    printf '%s\n' "${1##*,}"
}

# ovs_dpdk_get_representor_netdev(<PF_PCI>, <VF_INDEX>)
#
# This function tries to find the representor netdev for the given PF's VF.
#
ovs_dpdk_get_representor_netdev() {
    PF_PCI=$1
    VF_IDX=$2

    VF_NET_DIR="/sys/bus/pci/devices/$PF_PCI/virtfn$VF_IDX/net"

    if [[ ! -d "$VF_NET_DIR" ]]; then
        echo "ERROR: VF $VF_IDX for PF $PF_PCI does not exist" >&2
        return 1
    fi

    for iface in "$VF_NET_DIR"/*; do
        if [[ -e "$iface" ]]; then
            basename "$iface"
            return 0
        fi
    done

    echo "ERROR: No representor netdev found for VF $VF_IDX on PF $PF_PCI" >&2
    return 1
}

# ovs_dpdk_verify_vf_cfg()
#
# Verify that the given PF PCI addresses and corresponding VF IDs in
# OVS_DPDK_VF_PCI_ADDRS are valid, exist, and have corresponding
# representor ports.
#
ovs_dpdk_verify_vf_cfg() {
    i=0

    for addr in $1; do
        ovs_dpdk_is_valid_pci_vf_addr "$addr" || return 1

        PCI_ID=$(ovs_dpdk_get_pci_id "$addr")
        VF_IDX=$(ovs_dpdk_get_vf_idx "$addr")

        REP=$(ovs_dpdk_get_representor_netdev $PCI_ID $VF_IDX) || return 1

        echo "ovs-p$i: PF PCI $PCI_ID with VF $VF_IDX has representor $REP"
        i=$((i + 1))
    done

    return 0
}

OVS_END_SHELL_HELPERS