kubesolo-os/test/qemu/test-boot-arm64-disk.sh

#!/bin/bash
# test-boot-arm64-disk.sh — Boot the ARM64 .arm64.img via UEFI + GRUB and
# verify the init system reaches stage 90.
#
# This is the full-stack integration test: UEFI firmware -> GRUB -> kernel ->
# initramfs -> staged init. Contrast with test-boot-arm64.sh which skips the
# bootloader and loads kernel/initramfs directly.
#
# Exit 0 = PASS, Exit 1 = FAIL.
#
# Usage: ./test/qemu/test-boot-arm64-disk.sh [disk.img]
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
VERSION="$(cat "$PROJECT_ROOT/VERSION")"

DISK_IMAGE="${1:-$PROJECT_ROOT/output/kubesolo-os-${VERSION}.arm64.img}"
TIMEOUT=180

echo "==> ARM64 UEFI Disk Boot Test"
echo "    Disk image: $DISK_IMAGE"
echo "    Timeout:    ${TIMEOUT}s"

if [ ! -f "$DISK_IMAGE" ]; then
    echo "ERROR: Disk image not found: $DISK_IMAGE"
    echo "  Run 'make disk-image-arm64' to build it."
    exit 1
fi

if ! command -v qemu-system-aarch64 >/dev/null 2>&1; then
    echo "ERROR: qemu-system-aarch64 not found."
    echo "  apt install qemu-system-arm   # Debian/Ubuntu"
    echo "  dnf install qemu-system-aarch64  # Fedora/RHEL"
    exit 1
fi

# --- Locate UEFI firmware ---
UEFI_FW=""
for candidate in \
    /usr/share/qemu-efi-aarch64/QEMU_EFI.fd \
    /usr/share/AAVMF/AAVMF_CODE.fd \
    /usr/share/edk2/aarch64/QEMU_EFI.fd \
    /usr/share/qemu/edk2-aarch64-code.fd \
    /opt/homebrew/share/qemu/edk2-aarch64-code.fd \
    /usr/local/share/qemu/edk2-aarch64-code.fd
do
    if [ -f "$candidate" ]; then
        UEFI_FW="$candidate"
        break
    fi
done

if [ -z "$UEFI_FW" ]; then
    echo "ERROR: No ARM64 UEFI firmware found."
    echo "  apt install qemu-efi-aarch64"
    exit 1
fi

echo "    UEFI fw:    $UEFI_FW"

# Copy disk image to a scratch file so the test doesn't mutate the source.
# UEFI will write to grubenv on the EFI partition; we don't want to bake those
# changes into the canonical build artifact.
SCRATCH_DISK=$(mktemp /tmp/kubesolo-arm64-disk-test-XXXXXX.img)
SERIAL_LOG=$(mktemp /tmp/kubesolo-arm64-disk-serial-XXXXXX.log)
QEMU_PID=""

cleanup() {
    [ -n "$QEMU_PID" ] && kill "$QEMU_PID" 2>/dev/null || true
    rm -f "$SCRATCH_DISK" "$SERIAL_LOG"
}
trap cleanup EXIT

cp --reflink=auto "$DISK_IMAGE" "$SCRATCH_DISK" 2>/dev/null || cp "$DISK_IMAGE" "$SCRATCH_DISK"

# --- Launch QEMU ---
qemu-system-aarch64 \
    -machine virt \
    -cpu cortex-a72 \
    -m 2048 \
    -smp 2 \
    -nographic \
    -bios "$UEFI_FW" \
    -drive "file=$SCRATCH_DISK,format=raw,if=virtio,media=disk" \
    -net nic,model=virtio \
    -net user \
    -serial "file:$SERIAL_LOG" &
QEMU_PID=$!

echo "    Waiting for boot (PID $QEMU_PID)..."
ELAPSED=0
SUCCESS=0
while [ "$ELAPSED" -lt "$TIMEOUT" ]; do
    if grep -q "\[kubesolo-init\] \[OK\] Stage 90-kubesolo.sh complete" "$SERIAL_LOG" 2>/dev/null; then
        SUCCESS=1
        break
    fi
    if grep -q "KubeSolo is running" "$SERIAL_LOG" 2>/dev/null; then
        SUCCESS=1
        break
    fi
    if ! kill -0 "$QEMU_PID" 2>/dev/null; then
        echo ""
        echo "==> FAIL: QEMU exited prematurely"
        echo "    Last 30 lines of serial output:"
        tail -30 "$SERIAL_LOG" 2>/dev/null || echo "    (no output)"
        exit 1
    fi
    sleep 2
    ELAPSED=$((ELAPSED + 2))
    printf "\r    Elapsed: %ds / %ds" "$ELAPSED" "$TIMEOUT"
done
echo ""

kill "$QEMU_PID" 2>/dev/null || true
wait "$QEMU_PID" 2>/dev/null || true
QEMU_PID=""

if [ "$SUCCESS" = "1" ]; then
    echo "==> ARM64 UEFI Disk Boot Test PASSED (${ELAPSED}s)"
    exit 0
fi

echo "==> ARM64 UEFI Disk Boot Test FAILED (timeout ${TIMEOUT}s)"
echo ""
echo "==> Last 50 lines of serial output:"
tail -50 "$SERIAL_LOG" 2>/dev/null || echo "    (no output)"
exit 1