Files
bot-bottle/bot_bottle/backend/firecracker/util.py
T
didericis 39d47b8108
lint / lint (push) Successful in 2m14s
test / unit (pull_request) Successful in 1m7s
test / integration (pull_request) Successful in 23s
test / coverage (pull_request) Successful in 1m17s
fix(firecracker): harden committed-snapshot resume against guest-controlled data
Address the codex review on #398:

- P1: inject_guest_boot no longer follows a symlink at bb-init/bb-dropbear.
  A committed snapshot is guest-controlled and could plant those paths as
  symlinks aimed at a host file (e.g. bb-init -> ~/.bashrc); write_text /
  copy2 would then overwrite the target as the host user during resume.
  Replace any pre-existing entry and create the files with
  O_EXCL|O_NOFOLLOW so the write stays inside the staging tree.

- P2: write the snapshot tar owner-only (0600). It can contain the bottle's
  private workspace; it was being created world-readable (0644).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoEZHDjv84ChoZbozQERhJ
2026-07-17 00:44:06 -04:00

399 lines
16 KiB
Python

"""Host-side primitives for the Firecracker backend.
Covers the pieces that don't need root at launch time: locating the
firecracker binary / guest kernel / injected dropbear, the fail-closed
preflight (KVM + kernel + isolation table + TAP pool must all be
present before a VM boots), the rootless rootfs pipeline
(`docker export` -> `mke2fs -d`, no mount), and per-bottle SSH key
generation.
The privileged network setup (TAP pool + nft table) is a one-time
operator step — see `netpool.py`, `scripts/firecracker-netpool.sh`,
and `./cli.py backend setup --backend=firecracker`.
"""
from __future__ import annotations
import hashlib
import os
import platform
import shutil
import subprocess
from pathlib import Path
from ...log import die, info, warn
from . import netpool
# Guest agent images are Debian-family with USER node; the VM is
# reached over SSH as root (init drops the pubkey into both root's and
# node's authorized_keys) and commands `runuser` down to node.
GUEST_SSH_USER = "root"
# `/dev/kvm` must exist and be openable by the invoking user.
_KVM_DEVICE = "/dev/kvm"
def cache_dir() -> Path:
d = Path(
os.environ.get(
"BOT_BOTTLE_FC_CACHE",
str(Path.home() / ".cache" / "bot-bottle" / "firecracker"),
)
)
d.mkdir(parents=True, exist_ok=True)
return d
def kernel_path() -> Path:
return Path(os.environ.get("BOT_BOTTLE_FC_KERNEL", str(cache_dir() / "vmlinux")))
def dropbear_path() -> Path:
"""The static dropbear injected into every guest rootfs as its SSH
server. Must be statically linked — the guest has none of the
host's shared libraries."""
return Path(
os.environ.get("BOT_BOTTLE_FC_DROPBEAR", str(cache_dir() / "dropbear"))
)
# --- availability + preflight ---------------------------------------
def is_linux() -> bool:
return platform.system() == "Linux"
def is_host_capable() -> bool:
"""Whether this host *could* run firecracker — Linux with KVM —
regardless of whether the `firecracker` binary is installed. Used
for default-backend selection so a KVM Linux host that hasn't
installed firecracker yet still selects it and gets an install
pointer at launch (see `require_firecracker`), rather than silently
falling back to docker."""
return is_linux() and os.path.exists(_KVM_DEVICE)
def is_available() -> bool:
"""Cheap capability probe used by cross-backend enumeration —
firecracker on PATH, on Linux, with KVM. Does not check the
(operator-provisioned) kernel / pool, so an available-but-unset
host still shows up and gets an actionable error at launch."""
return is_host_capable() and shutil.which("firecracker") is not None
def require_firecracker() -> None:
"""Fail-closed preflight. Every check that gates the security
boundary (the isolation table, the TAP pool) errors rather than
booting a VM without it."""
if not is_linux():
die("firecracker backend is only supported on Linux (KVM). "
"On macOS use --backend=macos-container.")
if shutil.which("firecracker") is None:
info("Firecracker is required but was not found on PATH.")
info("Install: https://github.com/firecracker-microvm/firecracker/releases")
die("firecracker not found on PATH")
_require_kvm()
if not kernel_path().is_file():
die(f"guest kernel not found at {kernel_path()}. Set "
"BOT_BOTTLE_FC_KERNEL or place a vmlinux there.")
if not dropbear_path().is_file():
die(f"static dropbear not found at {dropbear_path()}. Set "
"BOT_BOTTLE_FC_DROPBEAR or cache one there.")
if shutil.which("mke2fs") is None:
die("mke2fs (e2fsprogs) not found — required to build guest rootfs")
_require_network_pool()
def _require_kvm() -> None:
if not os.path.exists(_KVM_DEVICE):
die(f"{_KVM_DEVICE} is missing. Enable KVM (load kvm-intel/kvm-amd; "
"confirm virtualization is on in firmware).")
if not os.access(_KVM_DEVICE, os.R_OK | os.W_OK):
die(f"{_KVM_DEVICE} exists but is not accessible. Add your user to "
"the `kvm` group and re-login.")
def _require_network_pool() -> None:
"""Fail-closed on the parts we can check unprivileged; defer the
rest to the post-boot isolation probe.
The TAP pool is verified here (`ip link show` is unprivileged). The
nft table can only be *confirmed present* here when `nft` is
queryable — which usually needs root — so a missing/absent nft is
not treated as fatal at this stage: the authoritative check is the
empirical isolation probe run after boot, before the agent starts
(see isolation_probe.verify_isolation). What we must never do is
boot without the TAP pool."""
conflicts = netpool.overlapping_routes()
if conflicts:
detail = "; ".join(f"{c.dst} dev {c.dev}" for c in conflicts)
warn(f"Firecracker pool range ({netpool.ip_base()}, "
f"{netpool.pool_size()} slots) overlaps existing routes: "
f"{detail}. This can shadow or be shadowed by that route; "
f"set BOT_BOTTLE_FC_IP_BASE to a free range and re-run "
f"./cli.py backend setup --backend=firecracker.")
missing = netpool.missing_taps()
if missing:
die(f"network pool incomplete — missing TAP devices: "
f"{', '.join(missing)}.\n ./cli.py backend setup --backend=firecracker")
if shutil.which("nft") is not None and not netpool.nft_table_present():
# nft is queryable and says the table is absent — that's a
# definite, catchable misconfiguration; fail early.
warn(f"isolation table `inet {netpool.NFT_TABLE}` not found via nft. "
"If this is a permissions issue it will be re-checked "
"empirically after boot; otherwise run: "
"./cli.py backend setup --backend=firecracker")
# --- rootfs pipeline (rootless) -------------------------------------
def docker_image_id(ref: str) -> str:
"""The image's content digest, used as the rootfs cache key."""
result = subprocess.run(
["docker", "image", "inspect", "--format", "{{.Id}}", ref],
capture_output=True, text=True, check=False,
)
if result.returncode != 0 or not result.stdout.strip():
die(f"docker image inspect for {ref!r} failed: "
f"{(result.stderr or '').strip() or '<no output>'}")
return result.stdout.strip().replace("sha256:", "")[:16]
def build_base_rootfs_dir(
image_ref: str, *, variant: str = "", init_script: str | None = None,
) -> Path:
"""Export the image's filesystem and inject the guest init + static
dropbear. Cached by image digest — the per-bottle bits
(authorized_keys, IP) are passed at boot via the kernel cmdline, so
this tree carries nothing bottle-specific and is safely shared.
`variant` suffixes the cache key so the same image can be prepared
with a different `init_script` (e.g. the infra VM boots the same
orchestrator image as the builder but runs the control plane as
PID 1, not the SSH-only agent init) without a cache collision.
Returns the prepared directory (read as the `mke2fs -d` source)."""
digest = docker_image_id(image_ref)
base = cache_dir() / "rootfs" / f"{digest}{variant}"
ready = base / ".bb-ready"
if ready.is_file():
return base
if base.exists():
shutil.rmtree(base, ignore_errors=True)
base.mkdir(parents=True)
info(f"exporting {image_ref} rootfs -> {base}")
cid = subprocess.run(
["docker", "create", image_ref, "sleep", "infinity"],
capture_output=True, text=True, check=False,
)
if cid.returncode != 0 or not cid.stdout.strip():
die(f"docker create {image_ref!r} failed: {cid.stderr.strip()}")
container = cid.stdout.strip()
try:
export = subprocess.Popen(
["docker", "export", container], stdout=subprocess.PIPE,
)
untar = subprocess.run(
["tar", "-x", "-C", str(base)], stdin=export.stdout, check=False,
)
export.wait()
if export.returncode != 0 or untar.returncode != 0:
die(f"exporting rootfs for {image_ref!r} failed")
finally:
subprocess.run(
["docker", "rm", "-f", container],
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
)
inject_guest_boot(base, init_script=init_script)
ready.write_text("ok\n")
return base
def build_committed_rootfs_dir(tar_path: Path) -> Path:
"""Prepare a base rootfs dir from a frozen-bottle snapshot tar (the
freeze/resume path — no Docker). Extracts the snapshot, recreates the
virtual mount points the freezer excluded, and injects the guest init +
static dropbear, mirroring `build_base_rootfs_dir` but sourced from a tar
we control rather than a Docker image.
Cached under the rootfs cache, keyed by the tar's size+mtime so a
re-freeze re-extracts but repeated resumes of the same snapshot don't.
Returns the prepared directory (read as the `mke2fs -d` source)."""
st = tar_path.stat()
fingerprint = hashlib.sha256(
f"{tar_path}:{st.st_size}:{st.st_mtime_ns}".encode()
).hexdigest()[:16]
base = cache_dir() / "rootfs" / f"committed-{fingerprint}"
ready = base / ".bb-ready"
if ready.is_file():
return base
if base.exists():
shutil.rmtree(base, ignore_errors=True)
base.mkdir(parents=True)
info(f"extracting committed rootfs {tar_path} -> {base}")
result = subprocess.run(
["tar", "-x", "-f", str(tar_path), "-C", str(base)],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(f"extracting committed rootfs {tar_path} failed: "
f"{result.stderr.strip() or '<no stderr>'}")
# The freezer excludes the live/virtual filesystems from the snapshot;
# recreate them as empty mount points so the guest init can mount
# proc/sys/dev and dropbear has a writable /run.
for mount_point in ("proc", "sys", "dev", "run"):
(base / mount_point).mkdir(mode=0o755, exist_ok=True)
inject_guest_boot(base)
ready.write_text("ok\n")
return base
def inject_guest_boot(rootfs: Path, init_script: str | None = None) -> None:
"""Drop the static dropbear and the PID-1 init into the rootfs.
`init_script` defaults to the SSH-only agent init; the infra VM
passes its own (control plane + gateway) init.
A committed snapshot is guest-controlled, so `bb-dropbear`/`bb-init`
may already exist as symlinks aimed at a host file (e.g. bb-init ->
~/.bashrc). Replace whatever is there and create the files with
O_EXCL|O_NOFOLLOW so the write always lands a fresh regular file in
the staging tree and never follows a planted symlink out of it."""
_write_staged_file(rootfs / "bb-dropbear", dropbear_path().read_bytes())
_write_staged_file(rootfs / "bb-init", (init_script or _GUEST_INIT).encode())
def _write_staged_file(path: Path, data: bytes) -> None:
"""Write `data` to `path` (mode 0755) as a fresh regular file inside a
staging rootfs, replacing any pre-existing entry without following a
symlink at `path`. Fails closed on anything unexpected there."""
if path.is_symlink() or path.exists():
if path.is_dir() and not path.is_symlink():
shutil.rmtree(path)
else:
path.unlink()
fd = os.open(
path, os.O_WRONLY | os.O_CREAT | os.O_EXCL | os.O_NOFOLLOW, 0o755
)
try:
os.write(fd, data)
finally:
os.close(fd)
os.chmod(path, 0o755)
def build_rootfs_ext4(base_dir: Path, out_path: Path, *, slack_mib: int = 1024) -> None:
"""Build a fresh, writable ext4 for one bottle from the cached base
dir. Rootless: `mke2fs -d` populates the image from a directory
without mounting. Each call produces an independent disk, so the
shared base dir stays untouched and concurrent bottles don't race."""
used_mib = _dir_size_mib(base_dir)
size_mib = used_mib + slack_mib
out_path.parent.mkdir(parents=True, exist_ok=True)
result = subprocess.run(
["mke2fs", "-q", "-t", "ext4", "-d", str(base_dir), "-F",
str(out_path), f"{size_mib}M"],
capture_output=True, text=True, check=False,
)
if result.returncode != 0:
die(f"mke2fs for {out_path} failed: {result.stderr.strip()}")
def _dir_size_mib(path: Path) -> int:
result = subprocess.run(
["du", "-sm", str(path)], capture_output=True, text=True, check=False,
)
try:
return int(result.stdout.split()[0])
except (ValueError, IndexError):
return 2048
# --- per-bottle SSH keys --------------------------------------------
def generate_keypair(dest_dir: Path) -> tuple[Path, str]:
"""Mint a per-bottle ed25519 keypair. Returns (private_key_path,
public_key_line). The public line is injected into the guest via
the boot cmdline; the private key authenticates host->guest SSH."""
dest_dir.mkdir(parents=True, exist_ok=True)
key = dest_dir / "bottle_id_ed25519"
if key.exists():
key.unlink()
(dest_dir / "bottle_id_ed25519.pub").unlink(missing_ok=True)
subprocess.run(
["ssh-keygen", "-t", "ed25519", "-N", "", "-q", "-f", str(key),
"-C", "bot-bottle-firecracker"],
check=True,
)
pub = (dest_dir / "bottle_id_ed25519.pub").read_text().strip()
return key, pub
def ssh_base_argv(private_key: Path, guest_ip: str) -> list[str]:
"""Common SSH options for host->guest control. The VM is ephemeral
and per-bottle, so host-key TOFU is meaningless — pin no known_hosts
and skip the check rather than accumulate churn."""
return [
"ssh",
"-i", str(private_key),
# Only offer the per-bottle key — don't let an agent or the
# operator's ~/.ssh/config inject other identities (newer
# OpenSSH otherwise may not reliably present the -i key).
"-o", "IdentitiesOnly=yes",
"-o", "StrictHostKeyChecking=no",
"-o", "UserKnownHostsFile=/dev/null",
"-o", "LogLevel=ERROR",
"-o", "ConnectTimeout=5",
f"{GUEST_SSH_USER}@{guest_ip}",
]
# PID-1 init injected into every guest. Kept dependency-light: relies
# only on coreutils + a POSIX shell (present in the Debian-family agent
# images). The kernel `ip=` cmdline configures eth0 before init runs,
# so no iproute2 is needed. The per-bottle SSH pubkey arrives base64 on
# the cmdline; dropbear generates ephemeral host keys with -R.
_GUEST_INIT = r"""#!/bin/sh
# bot-bottle Firecracker guest init (PID 1).
mount -t proc proc /proc 2>/dev/null
mount -t sysfs sys /sys 2>/dev/null
mount -t devtmpfs dev /dev 2>/dev/null
mkdir -p /dev/pts && mount -t devpts devpts /dev/pts 2>/dev/null
mount -o remount,rw / 2>/dev/null
# Install the per-bottle SSH pubkey from the kernel cmdline.
KEY=$(sed -n 's/.*bb_pubkey=\([^ ]*\).*/\1/p' /proc/cmdline | base64 -d 2>/dev/null)
if [ -n "$KEY" ]; then
for home in /root /home/node; do
mkdir -p "$home/.ssh"
printf '%s\n' "$KEY" > "$home/.ssh/authorized_keys"
chmod 700 "$home/.ssh"
chmod 600 "$home/.ssh/authorized_keys"
done
chown -R node:node /home/node/.ssh 2>/dev/null || true
fi
# The rootless rootfs build (`docker export | tar` as a non-root user)
# can't preserve uid 0, so every path lands owned by the build uid,
# which maps to `node` (uid 1000) in-guest — including /root. dropbear
# (like OpenSSH) refuses root's authorized_keys unless the home dir is
# owned by root, so restore root's ownership of its own home.
chown -R 0:0 /root 2>/dev/null || true
mkdir -p /etc/dropbear /run
# -R: generate host keys on demand. -E: log auth failures to stderr,
# captured in the host-side console.log for debugging.
/bb-dropbear -R -E -p 22 &
# Reap zombies as PID 1. dropbear is always a child, so `wait` blocks
# rather than busy-looping.
while : ; do wait ; done
"""