fruix/tests/system/run-phase11-shepherd-pid1-qemu.sh

#!/bin/sh
set -eu

repo_root=${PROJECT_ROOT:-$(pwd)}
os_template=$repo_root/tests/system/phase11-shepherd-pid1-operating-system.scm.in
system_name=${SYSTEM_NAME:-phase11-operating-system}
metadata_target=${METADATA_OUT:-}
root_authorized_key_file=${ROOT_AUTHORIZED_KEY_FILE:-$HOME/.ssh/id_ed25519.pub}
root_ssh_private_key_file=${ROOT_SSH_PRIVATE_KEY_FILE:-$HOME/.ssh/id_ed25519}
ssh_port=${QEMU_SSH_PORT:-10022}
disk_capacity=${DISK_CAPACITY:-5g}
cleanup=0

if [ -n "${WORKDIR:-}" ]; then
  workdir=$WORKDIR
  mkdir -p "$workdir"
else
  workdir=$(mktemp -d /tmp/fruix-phase11-pid1-qemu.XXXXXX)
  cleanup=1
fi
if [ "${KEEP_WORKDIR:-0}" -eq 1 ]; then
  cleanup=0
fi

phase11_os_file=$workdir/phase11-shepherd-pid1-operating-system.scm
phase8_log=$workdir/phase8-system-image.log
phase8_metadata=$workdir/phase8-system-image-metadata.txt
serial_log=$workdir/serial.log
qemu_pidfile=$workdir/qemu.pid
metadata_file=$workdir/phase11-shepherd-pid1-qemu-metadata.txt
uefi_vars=$workdir/QEMU_UEFI_VARS.fd

cleanup_workdir() {
  if [ -f "$qemu_pidfile" ]; then
    sudo kill "$(sudo cat "$qemu_pidfile")" >/dev/null 2>&1 || true
  fi
  if [ "$cleanup" -eq 1 ]; then
    rm -rf "$workdir" 2>/dev/null || sudo rm -rf "$workdir"
  fi
}
trap cleanup_workdir EXIT INT TERM

[ -f "$root_authorized_key_file" ] || {
  echo "missing root authorized key file: $root_authorized_key_file" >&2
  exit 1
}
[ -f "$root_ssh_private_key_file" ] || {
  echo "missing root SSH private key file: $root_ssh_private_key_file" >&2
  exit 1
}
command -v qemu-system-x86_64 >/dev/null 2>&1 || {
  echo "qemu-system-x86_64 is required" >&2
  exit 1
}
[ -f /usr/local/share/edk2-qemu/QEMU_UEFI_CODE-x86_64.fd ] || {
  echo "missing QEMU UEFI firmware" >&2
  exit 1
}
cp /usr/local/share/edk2-qemu/QEMU_UEFI_VARS-x86_64.fd "$uefi_vars"
root_authorized_key=$(tr -d '\n' < "$root_authorized_key_file")
sed "s|__ROOT_AUTHORIZED_KEY__|$root_authorized_key|g" "$os_template" > "$phase11_os_file"

KEEP_WORKDIR=1 WORKDIR="$workdir/phase8-build" OS_FILE="$phase11_os_file" SYSTEM_NAME="$system_name" DISK_CAPACITY="$disk_capacity" \
  METADATA_OUT="$phase8_metadata" "$repo_root/tests/system/run-phase8-system-image.sh" >"$phase8_log" 2>&1

disk_image=$(sed -n 's/^disk_image=//p' "$phase8_metadata")
closure_path=$(sed -n 's/^closure_path=//p' "$phase8_metadata")
closure_base=$(basename "$closure_path")
raw_sha256=$(sed -n 's/^raw_sha256=//p' "$phase8_metadata")
image_store_path=$(sed -n 's/^image_store_path=//p' "$phase8_metadata")

sudo qemu-system-x86_64 \
  -machine q35,accel=tcg \
  -cpu max \
  -m 2048 \
  -smp 2 \
  -display none \
  -serial "file:$serial_log" \
  -monitor none \
  -pidfile "$qemu_pidfile" \
  -daemonize \
  -drive if=pflash,format=raw,readonly=on,file=/usr/local/share/edk2-qemu/QEMU_UEFI_CODE-x86_64.fd \
  -drive if=pflash,format=raw,file="$uefi_vars" \
  -drive if=virtio,format=raw,file="$disk_image" \
  -netdev user,id=net0,hostfwd=tcp::${ssh_port}-:22 \
  -device virtio-net-pci,netdev=net0

ssh_guest() {
  ssh -p "$ssh_port" -i "$root_ssh_private_key_file" \
    -o BatchMode=yes \
    -o StrictHostKeyChecking=no \
    -o UserKnownHostsFile=/dev/null \
    -o ConnectTimeout=5 \
    root@127.0.0.1 "$@"
}

for attempt in $(jot 120 1 120); do
  if ssh_guest 'test -f /var/lib/fruix/ready' >/dev/null 2>&1; then
    break
  fi
  sleep 2
done

ready_marker=$(ssh_guest 'cat /var/lib/fruix/ready')
run_current_system_target=$(ssh_guest 'readlink /run/current-system')
pid1_command=$(ssh_guest 'ps -p 1 -o command= | sed "s/^ *//"')
pid1_binary=$(ssh_guest 'procstat -b 1 2>/dev/null | awk "NR==2 {print \$2}"')
shepherd_pid=$(ssh_guest 'cat /var/run/shepherd.pid')
shepherd_socket=$(ssh_guest 'test -S /var/run/shepherd.sock && echo present || echo missing')
shepherd_status=$(ssh_guest 'test -f /var/run/shepherd.pid && kill -0 "$(cat /var/run/shepherd.pid)" >/dev/null 2>&1 && echo running || echo stopped')
sshd_status=$(ssh_guest 'service sshd onestatus >/dev/null 2>&1 && echo running || echo stopped')
logger_log=$(ssh_guest 'cat /var/log/fruix-shepherd.log' | tr '\n' ' ')
uname_output=$(ssh_guest 'uname -sr')
operator_home_listing=$(ssh_guest 'ls -d /home/operator')

[ "$ready_marker" = ready ] || { echo "unexpected ready marker contents: $ready_marker" >&2; exit 1; }
[ "$run_current_system_target" = "/frx/store/$closure_base" ] || {
  echo "unexpected /run/current-system target in guest: $run_current_system_target" >&2
  exit 1
}
[ "$shepherd_pid" = 1 ] || {
  echo "shepherd is not PID 1: shepherd.pid=$shepherd_pid pid1_command=$pid1_command pid1_binary=$pid1_binary" >&2
  exit 1
}
[ "$shepherd_socket" = present ] || { echo "shepherd socket is missing" >&2; exit 1; }
[ "$shepherd_status" = running ] || { echo "shepherd is not running" >&2; exit 1; }
[ "$sshd_status" = running ] || { echo "sshd is not running" >&2; exit 1; }
[ "$operator_home_listing" = /home/operator ] || { echo "operator home missing" >&2; exit 1; }

cat >"$metadata_file" <<EOF
workdir=$workdir
phase11_os_file=$phase11_os_file
phase8_log=$phase8_log
phase8_metadata=$phase8_metadata
image_store_path=$image_store_path
disk_image=$disk_image
closure_path=$closure_path
closure_base=$closure_base
raw_sha256=$raw_sha256
serial_log=$serial_log
qemu_pidfile=$qemu_pidfile
ssh_port=$ssh_port
ready_marker=$ready_marker
run_current_system_target=$run_current_system_target
pid1_command=$pid1_command
pid1_binary=$pid1_binary
shepherd_pid=$shepherd_pid
shepherd_socket=$shepherd_socket
shepherd_status=$shepherd_status
sshd_status=$sshd_status
logger_log=$logger_log
uname_output=$uname_output
operator_home_listing=$operator_home_listing
boot_backend=qemu-uefi-tcg
init_mode=shepherd-pid1
EOF

if [ -n "$metadata_target" ]; then
  mkdir -p "$(dirname "$metadata_target")"
  cp "$metadata_file" "$metadata_target"
fi

printf 'PASS phase11-shepherd-pid1-qemu\n'
printf 'Work directory: %s\n' "$workdir"
printf 'Metadata file: %s\n' "$metadata_file"
if [ -n "$metadata_target" ]; then
  printf 'Copied metadata to: %s\n' "$metadata_target"
fi
printf '%s\n' '--- metadata ---'
cat "$metadata_file"