bot-bottle/bot_bottle/backend/firecracker/setup.py

"""Host setup + status for the Firecracker backend.

`setup()` prints the host-appropriate config for the privileged,
one-time network pool (TAP devices + isolation nftables table) the
backend needs. On NixOS it points at the flake module (and prints a
paste-able fallback); elsewhere it prints the sudo command for the
bundled setup script. `status()` reports what's present, including
whether the pool range collides with an existing route.

Called through `FirecrackerBottleBackend.setup` / `.status`, which the
generic `./cli.py backend {setup,status}` command dispatches to.
"""

from __future__ import annotations

import os
import shutil
import subprocess
import sys
from pathlib import Path

from . import netpool
from . import util


_FC_RELEASES = "https://github.com/firecracker-microvm/firecracker/releases"
_UNIT_PATH = Path("/etc/systemd/system") / netpool.SYSTEMD_UNIT


def _owner() -> str:
    # Under `sudo`, USER is root but SUDO_USER is the real invoker — the
    # TAPs must be owned by them so `./cli.py start` stays rootless.
    return os.environ.get("SUDO_USER") or os.environ.get("USER") or "youruser"


def _has_systemd() -> bool:
    return Path("/run/systemd/system").is_dir()


def _module_path() -> str:
    """Absolute path to the importable NixOS module in this checkout."""
    return str(Path(__file__).resolve().parents[3] / "nix" / "firecracker-netpool.nix")


def _script_path() -> str:
    """Absolute path to the bundled bring-up script in this checkout."""
    return str(Path(__file__).resolve().parents[3] / "scripts" / "firecracker-netpool.sh")


def _print_prereqs() -> None:
    """The firecracker binary + KVM + guest artifacts, shown before the
    privileged network-pool step so operators see the full picture."""
    fc = shutil.which("firecracker")
    if fc:
        sys.stderr.write(f"1) firecracker binary: found ({fc}).\n")
    else:
        sys.stderr.write(
            "1) firecracker binary: NOT found on PATH. Install a release binary "
            "and put it on PATH:\n"
            f"     {_FC_RELEASES}\n"
            "   e.g.: download firecracker-vX.Y.Z-$(uname -m).tgz, extract, and\n"
            "     install -m755 release-*/firecracker-* ~/.local/bin/firecracker\n"
            "   (NixOS: not packaged as a user binary — fetch the release, pin\n"
            "    the version, and add it to PATH.)\n"
        )
    if util.is_host_capable():
        sys.stderr.write("   KVM: /dev/kvm present.\n")
    else:
        sys.stderr.write(
            "   KVM: /dev/kvm missing/unusable — load kvm-intel/kvm-amd, enable\n"
            "   virtualization in firmware, and add your user to the `kvm` group.\n"
        )
    sys.stderr.write(
        "   Guest artifacts: a kernel (BOT_BOTTLE_FC_KERNEL) and static dropbear\n"
        "   (BOT_BOTTLE_FC_DROPBEAR) must be cached, and `mke2fs` (e2fsprogs) is\n"
        "   needed to build the rootfs.\n\n"
    )


def _is_nixos() -> bool:
    if Path("/etc/NIXOS").exists():
        return True
    try:
        return "ID=nixos" in Path("/etc/os-release").read_text()
    except OSError:
        return False


def _warn_overlaps() -> None:
    """Warn if the chosen pool range collides with an existing host route
    (Tailscale CGNAT peer, a docker/libvirt bridge, the LAN…)."""
    conflicts = netpool.overlapping_routes()
    if not conflicts:
        return
    detail = "\n".join(f"    {c.dst} dev {c.dev}" for c in conflicts)
    sys.stderr.write(
        f"WARNING: pool range (base {netpool.ip_base()}, "
        f"{netpool.pool_size()} slots) overlaps existing routes:\n"
        f"{detail}\n"
        "Set BOT_BOTTLE_FC_IP_BASE to a free range before setup, or the "
        "pool may shadow / be shadowed by the above.\n\n"
    )


def setup() -> int:
    sys.stderr.write("Firecracker backend — one-time host setup.\n\n")
    _print_prereqs()
    slots = netpool.all_slots()
    sys.stderr.write(
        f"2) network pool: {len(slots)} slots "
        f"({slots[0].iface}..{slots[-1].iface}), base {netpool.ip_base()} — "
        f"TAP devices + nft isolation table, privileged (needs root once).\n\n"
    )
    _warn_overlaps()
    if _is_nixos():
        sys.stderr.write(
            "Detected NixOS. Import the module — it is NON-INVASIVE: it does "
            "not flip networking.nftables.enable or systemd.network.enable, so "
            "your existing (iptables) firewall and Docker are untouched. A "
            "systemd oneshot brings the pool up alongside them.\n\n"
            "  # flake users:\n"
            "  inputs.bot-bottle.url = \"git+ssh://<your-bot-bottle-remote>\";\n"
            "  imports = [ inputs.bot-bottle.nixosModules.firecracker-netpool ];\n"
            "  # channel (non-flake) users — import the file directly:\n"
            f"  imports = [ {_module_path()} ];\n\n"
            f"  services.bot-bottle-firecracker = {{ enable = true; owner = \"{_owner()}\"; }};\n\n"
            "Then `nixos-rebuild switch`.\n"
        )
    elif _has_systemd():
        _setup_systemd()
    else:
        sys.stderr.write(
            "No systemd detected. Run the one-time bring-up as root (and add "
            "your own boot persistence — e.g. an OpenRC/runit service):\n\n"
        )
        sys.stdout.write(netpool.render_shell_setup() + "\n")
    return 0


def _setup_systemd() -> None:
    """Install the pool as a persistent systemd unit — the portable path,
    identical on every systemd distro. Performs the install directly when
    run as root; otherwise prints a self-contained copy-paste block."""
    unit = netpool.render_systemd_unit(_owner(), _script_path())
    sys.stderr.write(
        f"Persistent install (systemd — same on every systemd distro). Needs "
        f"`nft` (nftables) and `ip` (iproute2); install via your package "
        f"manager if `backend status` reports them missing.\n\n"
    )
    if os.geteuid() == 0:
        _UNIT_PATH.write_text(unit)
        subprocess.run(["systemctl", "daemon-reload"], check=False)
        rc = subprocess.run(
            ["systemctl", "enable", "--now", netpool.SYSTEMD_UNIT], check=False,
        ).returncode
        if rc == 0:
            sys.stderr.write(
                f"Installed and started {netpool.SYSTEMD_UNIT}. Verify with "
                f"`./cli.py backend status --backend=firecracker`.\n"
            )
        else:
            sys.stderr.write(
                f"Wrote {_UNIT_PATH} but `systemctl enable --now` failed — "
                f"check `systemctl status {netpool.SYSTEMD_UNIT}`.\n"
            )
        return
    sys.stderr.write(
        "Install the unit (one copy-paste; enables it on boot too):\n\n"
    )
    sys.stdout.write(
        f"sudo tee {_UNIT_PATH} >/dev/null <<'UNIT'\n"
        f"{unit}"
        f"UNIT\n"
        f"sudo systemctl daemon-reload\n"
        f"sudo systemctl enable --now {netpool.SYSTEMD_UNIT}\n"
    )
    sys.stderr.write(
        f"\n(Or re-run this as root to install it directly: "
        f"sudo ./cli.py backend setup --backend=firecracker)\n"
    )


def teardown() -> int:
    slots = netpool.all_slots()
    sys.stderr.write(
        f"Undo the Firecracker network pool ({len(slots)} slots, base "
        f"{netpool.ip_base()}) — a privileged operation.\n\n"
    )
    if _is_nixos():
        sys.stderr.write(
            "On NixOS: set `services.bot-bottle-firecracker.enable = false;` "
            "(or drop the module import) and `nixos-rebuild switch`. The TAP "
            "netdevs and nft table are removed declaratively.\n\n"
            "To tear down imperatively before a rebuild (does not persist):\n\n"
        )
        sys.stdout.write("sudo ./scripts/firecracker-netpool.sh down\n")
        return 0
    if _has_systemd():
        if os.geteuid() == 0:
            subprocess.run(
                ["systemctl", "disable", "--now", netpool.SYSTEMD_UNIT],
                check=False,
            )
            _UNIT_PATH.unlink(missing_ok=True)
            subprocess.run(["systemctl", "daemon-reload"], check=False)
            sys.stderr.write(
                f"Stopped, disabled, and removed {netpool.SYSTEMD_UNIT}.\n"
            )
        else:
            sys.stderr.write("Remove the persistent unit (one copy-paste):\n\n")
            sys.stdout.write(
                f"sudo systemctl disable --now {netpool.SYSTEMD_UNIT}\n"
                f"sudo rm -f {_UNIT_PATH}\n"
                f"sudo systemctl daemon-reload\n"
            )
        return 0
    sys.stderr.write("Run the teardown as root:\n\n")
    sys.stdout.write("sudo ./scripts/firecracker-netpool.sh down\n")
    return 0


def status() -> int:
    # Readiness == what the launch preflight hard-requires: the TAP pool
    # present (unprivileged, authoritative) and no range overlap. Listing
    # the nft table usually needs root, so — like the preflight — an
    # unconfirmable table is reported but NOT treated as not-ready; the
    # post-boot isolation probe is the authoritative check. This keeps an
    # unprivileged `backend status` usable as a launch gate.
    ok = True
    missing = netpool.missing_taps()
    total = netpool.pool_size()
    if missing:
        sys.stderr.write(f"TAP pool: {total - len(missing)}/{total} present "
                         f"(missing: {', '.join(missing)})\n")
        ok = False
    else:
        sys.stderr.write(f"TAP pool: {total}/{total} present\n")
    if shutil.which("nft") is None:
        sys.stderr.write(f"nft table inet {netpool.NFT_TABLE}: unverified "
                         f"(nft not on PATH; enforced + checked post-boot)\n")
    elif netpool.nft_table_present():
        sys.stderr.write(f"nft table inet {netpool.NFT_TABLE}: present\n")
    else:
        sys.stderr.write(f"nft table inet {netpool.NFT_TABLE}: not confirmable "
                         f"unprivileged (listing needs root; verified post-boot)\n")
    conflicts = netpool.overlapping_routes()
    if conflicts:
        detail = ", ".join(f"{c.dst} dev {c.dev}" for c in conflicts)
        sys.stderr.write(f"range overlap: base {netpool.ip_base()} CLASHES "
                         f"with {detail}\n")
        ok = False
    else:
        sys.stderr.write(f"range overlap: none (base {netpool.ip_base()})\n")
    _report_persistence()
    if not ok:
        sys.stderr.write("\nRun: ./cli.py backend setup --backend=firecracker\n")
    return 0 if ok else 1


def _report_persistence() -> None:
    """Report whether the pool is installed as the persistent systemd
    unit (so it survives reboot) vs brought up imperatively. Advisory —
    doesn't affect launch readiness."""
    if not _has_systemd():
        return
    state = subprocess.run(
        ["systemctl", "is-active", netpool.SYSTEMD_UNIT],
        capture_output=True, text=True, check=False,
    ).stdout.strip() or "unknown"
    if state == "active":
        sys.stderr.write(f"persistence: {netpool.SYSTEMD_UNIT} active "
                         f"(survives reboot)\n")
    else:
        sys.stderr.write(f"persistence: {netpool.SYSTEMD_UNIT} {state} — pool "
                         f"is not installed as a persistent unit (install with "
                         f"`backend setup` so it survives reboot)\n")