pxe-server/playbook/pxe-server-helpers/pxe-nic-carrier

#!/bin/bash
#
# pxe-nic-carrier - re-check the imaging NIC whenever its cable moves.
#
# The dnsmasq guard (pxe-nic-check --guard) runs only when dnsmasq starts,
# and the watch timer only every 5 min. If the imaging cable is moved into
# a GE port while dnsmasq runs, dnsmasq would answer DHCP on the GE LAN
# until the next watch. This hook closes that gap:
#
#   carrier lost   dnsmasq is stopped at once (if it was running) and a
#                  marker remembers that this hook stopped it.
#   carrier back   pxe-nic-carrier.service runs "pxe-nic-carrier --gain":
#                  after a 2 s settle, if dnsmasq is running or the marker
#                  is set, "systemctl restart dnsmasq" - its ExecStartPre
#                  guard checks the NIC while dnsmasq is down and refuses
#                  to start it on the GE network. Otherwise it only runs
#                  the guard to refresh /run/pxe-nic-status.json. dnsmasq
#                  that an operator or the watch stopped stays stopped.
#
# Only the imaging NIC (and, for a bridge, its ports) counts, as resolved
# by "pxe-nic-check --print-imaging" from /etc/pxe-server/nic.conf or the
# dnsmasq interface= pin. Events on any other NIC (the GE NIC) exit at
# once and touch nothing. Link state is read from sysfs, not from the
# event name, and remembered per interface, so the same transition seen
# twice (carrier, then routable) acts once.
#
# Called by networkd-dispatcher with IFACE and STATE in the environment
# (installed as /etc/networkd-dispatcher/<state>.d/50-pxe-nic-carrier for
# carrier, degraded, degraded-carrier, enslaved, routable, no-carrier and
# off), or by hand: pxe-nic-carrier IFACE. Logs: journalctl -t pxe-nic-carrier
#
# The dispatcher waits for this script, so the event path never runs a
# check itself: loss is two systemctl calls, gain hands off to the service.

set -u

CHECK="${PXE_NIC_CHECK:-/usr/local/sbin/pxe-nic-check}"
SYS_NET="${PXE_SYS_NET:-/sys/class/net}"
RUN="${PXE_NIC_CARRIER_RUN:-/run/pxe-nic-carrier}"
SYSTEMCTL="${PXE_SYSTEMCTL:-systemctl}"
SETTLE="${PXE_NIC_CARRIER_SETTLE:-2}"
GAIN_UNIT="pxe-nic-carrier.service"
TAG="pxe-nic-carrier"

PATH="${PATH:+$PATH:}/usr/local/sbin:/usr/sbin:/usr/bin:/sbin:/bin"

log() {  # log PRIORITY MESSAGE
    logger -t "$TAG" -p "daemon.$1" -- "$2" 2>/dev/null || \
        echo "$TAG: $2" >&2
}

imaging_ifaces() {
    "$CHECK" --print-imaging 2>/dev/null
}

carrier_of() {  # 1 if the interface has carrier, else 0 (down reads EINVAL)
    local c
    c=$(cat "$SYS_NET/$1/carrier" 2>/dev/null) || c=0
    [ "$c" = 1 ] && echo 1 || echo 0
}

any_carrier() {  # any imaging interface or port with carrier
    local i
    for i in "$@"; do
        [ "$(carrier_of "$i")" = 1 ] && return 0
    done
    return 1
}

dnsmasq_running() {  # active, starting or reloading
    case "$("$SYSTEMCTL" is-active dnsmasq 2>/dev/null)" in
        active|activating|reloading) return 0 ;;
    esac
    return 1
}

on_event() {
    local iface="$1" list=() match="" i now prev
    mapfile -t list < <(imaging_ifaces)
    for i in "${list[@]}"; do
        [ -n "$i" ] && [ "$i" = "$iface" ] && match=1
    done
    [ -n "$match" ] || exit 0        # not the imaging NIC: hands off

    mkdir -p "$RUN" || exit 0
    exec 9>"$RUN/event.lock"
    flock -w 10 9 || log warning "lock busy, handling $iface anyway"

    now=$(carrier_of "$iface")
    prev=$(cat "$RUN/link.$iface" 2>/dev/null) || prev=unknown
    echo "$now" > "$RUN/link.$iface"
    [ "$now" = "$prev" ] && exit 0   # same state again: already handled

    if [ "$now" = 0 ]; then
        # an in-flight gain check must not restart dnsmasq after this
        "$SYSTEMCTL" stop "$GAIN_UNIT" >/dev/null 2>&1
        if dnsmasq_running; then
            : > "$RUN/stopped-dnsmasq"
            "$SYSTEMCTL" stop --no-block dnsmasq
            log warning "carrier lost on imaging NIC $iface (${STATE:-event}): stopped dnsmasq; it restarts after the guard passes when the link returns"
        else
            log info "carrier lost on imaging NIC $iface (${STATE:-event}); dnsmasq not running"
        fi
    else
        log notice "carrier up on imaging NIC $iface (${STATE:-event}, was $prev): re-checking before dnsmasq serves"
        "$SYSTEMCTL" restart --no-block "$GAIN_UNIT"
    fi
    exit 0
}

on_gain() {
    local list=() rc
    sleep "$SETTLE"
    mapfile -t list < <(imaging_ifaces)
    if [ "${#list[@]}" -eq 0 ] || [ -z "${list[0]}" ]; then
        log err "imaging NIC unknown, nothing to re-check"
        exit 0
    fi
    if ! any_carrier "${list[@]}"; then
        log info "imaging NIC ${list[0]} lost carrier again, nothing to do"
        exit 0
    fi
    if dnsmasq_running || [ -e "$RUN/stopped-dnsmasq" ]; then
        # restart = stop, then the ExecStartPre guard with dnsmasq down
        "$SYSTEMCTL" restart dnsmasq
        rc=$?
        rm -f "$RUN/stopped-dnsmasq"
        if [ "$rc" -eq 0 ]; then
            log notice "imaging NIC ${list[0]}: guard passed, dnsmasq (re)started"
        else
            log crit "imaging NIC ${list[0]}: dnsmasq NOT started (guard refused or start failed, rc $rc); see journalctl -u dnsmasq. Fix the cabling, then systemctl start dnsmasq"
        fi
    else
        "$CHECK" --guard >/dev/null 2>&1
        rc=$?
        log info "imaging NIC ${list[0]}: dnsmasq was not running, left stopped (guard rc $rc, status refreshed)"
    fi
    exit 0
}

case "${1:-}" in
    --gain) on_gain ;;
    -h|--help) sed -n '2,36p' "$0"; exit 0 ;;
    *) on_event "${1:-${IFACE:-}}" ;;
esac