feat(firecracker): add Linux microVM backend to replace smolmachines
Adds a Firecracker-based backend for Linux, providing mature KVM-based microVM isolation to replace smolmachines/libkrun (issue #342, closes the dead-end tracked in #332). Architecture: - Guest control over SSH (dropbear injected into the rootfs) on a point-to-point TAP link. `ssh -t` forwards SIGWINCH natively, so no resize bridge is needed. - Networking: a one-time, root-provisioned pool of user-owned TAP devices (no shared bridge → no docker0/virbr0/cni0 collisions) plus a dedicated `table inet bot_bottle_fc` nftables table (independent of Docker/ufw/firewalld rules). `./cli.py firecracker setup` prints the host-appropriate config (NixOS module or sudo script). - Rootfs: `docker export` → ext4 via `mke2fs -d` (rootless, no mount), cached by image digest; per-bottle SSH pubkey + IP passed via the kernel cmdline. - Sidecar: reuses the Docker bundle, published on the slot's host TAP IP. - Fail-closed isolation: TAP pool verified at preflight; the egress boundary is proven empirically post-boot (before the agent runs) by a canary probe — the VM must fail to reach the host directly, or launch is refused. Linux hosts with Firecracker + KVM now default to this backend; macOS stays on macos-container. Not yet validated end-to-end on live hardware (requires the one-time network pool). Unit tests + pyright pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01G8p32HJgPoS1hLPWubbftM
This commit is contained in:
@@ -0,0 +1,173 @@
|
||||
"""Firecracker microVM process lifecycle.
|
||||
|
||||
A bottle VM is one `firecracker` process booted from a JSON config
|
||||
(kernel + writable rootfs ext4 + one TAP network interface). We run it
|
||||
`--no-api`: all configuration is in the config file, and teardown is a
|
||||
process signal — the microVM dies with its VMM, which is exactly the
|
||||
ephemeral-bottle semantics we want. No API socket, no runtime
|
||||
reconfiguration.
|
||||
|
||||
The guest gets its IP from the kernel `ip=` cmdline (kernel-level
|
||||
autoconfig, no in-guest iproute2) and its SSH pubkey from a `bb_pubkey=`
|
||||
cmdline arg the init decodes.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import json
|
||||
import signal
|
||||
import subprocess
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ...log import die, info
|
||||
from . import util
|
||||
|
||||
|
||||
# Serial console off the critical path but captured to a log for
|
||||
# debugging boot failures. `reboot=k panic=1 pci=off` are the standard
|
||||
# Firecracker guest args; `i8042.*` skip the (absent) PS/2 probe to
|
||||
# shave boot time.
|
||||
_BASE_BOOT_ARGS = (
|
||||
"console=ttyS0 reboot=k panic=1 pci=off "
|
||||
"i8042.noaux i8042.nomux i8042.nopnp i8042.dumbkbd "
|
||||
"root=/dev/vda rw init=/bb-init"
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class VmHandle:
|
||||
"""A running microVM: its VMM process, guest IP, and console log."""
|
||||
|
||||
process: subprocess.Popen[bytes]
|
||||
guest_ip: str
|
||||
console_log: Path
|
||||
|
||||
def is_alive(self) -> bool:
|
||||
return self.process.poll() is None
|
||||
|
||||
def terminate(self) -> None:
|
||||
"""Stop the VMM (and thus the guest). SIGTERM, then SIGKILL."""
|
||||
if self.process.poll() is not None:
|
||||
return
|
||||
self.process.send_signal(signal.SIGTERM)
|
||||
try:
|
||||
self.process.wait(timeout=5)
|
||||
except subprocess.TimeoutExpired:
|
||||
self.process.kill()
|
||||
self.process.wait(timeout=5)
|
||||
|
||||
|
||||
def _boot_args(guest_ip: str, host_ip: str, pubkey: str) -> str:
|
||||
# ip=<client>::<gw>:<netmask>::<dev>:off — /31 point-to-point link,
|
||||
# so netmask is 255.255.255.254 and the gateway is the host TAP IP.
|
||||
ip_arg = f"ip={guest_ip}::{host_ip}:255.255.255.254::eth0:off"
|
||||
pub_b64 = base64.b64encode(pubkey.encode()).decode()
|
||||
return f"{_BASE_BOOT_ARGS} {ip_arg} bb_pubkey={pub_b64}"
|
||||
|
||||
|
||||
def _config(
|
||||
*,
|
||||
rootfs: Path,
|
||||
tap: str,
|
||||
guest_ip: str,
|
||||
host_ip: str,
|
||||
pubkey: str,
|
||||
vcpus: int,
|
||||
mem_mib: int,
|
||||
guest_mac: str,
|
||||
) -> dict[str, object]:
|
||||
return {
|
||||
"boot-source": {
|
||||
"kernel_image_path": str(util.kernel_path()),
|
||||
"boot_args": _boot_args(guest_ip, host_ip, pubkey),
|
||||
},
|
||||
"drives": [
|
||||
{
|
||||
"drive_id": "rootfs",
|
||||
"path_on_host": str(rootfs),
|
||||
"is_root_device": True,
|
||||
"is_read_only": False,
|
||||
}
|
||||
],
|
||||
"network-interfaces": [
|
||||
{
|
||||
"iface_id": "eth0",
|
||||
"host_dev_name": tap,
|
||||
"guest_mac": guest_mac,
|
||||
}
|
||||
],
|
||||
"machine-config": {
|
||||
"vcpu_count": vcpus,
|
||||
"mem_size_mib": mem_mib,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def boot(
|
||||
*,
|
||||
name: str,
|
||||
rootfs: Path,
|
||||
tap: str,
|
||||
guest_ip: str,
|
||||
host_ip: str,
|
||||
pubkey: str,
|
||||
run_dir: Path,
|
||||
vcpus: int = 2,
|
||||
mem_mib: int = 2048,
|
||||
guest_mac: str = "06:00:AC:10:00:02",
|
||||
) -> VmHandle:
|
||||
"""Write the config and launch the VMM. Returns once the process is
|
||||
spawned; callers wait for SSH readiness separately."""
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
config_path = run_dir / "config.json"
|
||||
console_log = run_dir / "console.log"
|
||||
config_path.write_text(json.dumps(
|
||||
_config(
|
||||
rootfs=rootfs, tap=tap, guest_ip=guest_ip, host_ip=host_ip,
|
||||
pubkey=pubkey, vcpus=vcpus, mem_mib=mem_mib, guest_mac=guest_mac,
|
||||
),
|
||||
indent=2,
|
||||
))
|
||||
|
||||
info(f"booting microVM {name} on {tap} (guest {guest_ip})")
|
||||
log_fh = console_log.open("wb")
|
||||
process = subprocess.Popen(
|
||||
["firecracker", "--no-api", "--config-file", str(config_path)],
|
||||
stdout=log_fh, stderr=subprocess.STDOUT, stdin=subprocess.DEVNULL,
|
||||
)
|
||||
return VmHandle(process=process, guest_ip=guest_ip, console_log=console_log)
|
||||
|
||||
|
||||
def wait_for_ssh(
|
||||
vm: VmHandle, private_key: Path, *, timeout: float = 30.0,
|
||||
) -> None:
|
||||
"""Poll SSH until the guest accepts a command or the deadline
|
||||
passes. Dies (with the console tail) if the VMM exits early or the
|
||||
guest never comes up — a boot failure must be loud, not a hang."""
|
||||
deadline = time.monotonic() + timeout
|
||||
probe = util.ssh_base_argv(private_key, vm.guest_ip) + ["true"]
|
||||
while time.monotonic() < deadline:
|
||||
if not vm.is_alive():
|
||||
die(f"microVM exited during boot (rc={vm.process.returncode}).\n"
|
||||
f"{_console_tail(vm.console_log)}")
|
||||
result = subprocess.run(
|
||||
probe, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
|
||||
check=False,
|
||||
)
|
||||
if result.returncode == 0:
|
||||
return
|
||||
time.sleep(0.5)
|
||||
die(f"microVM {vm.guest_ip} did not accept SSH within {timeout:.0f}s.\n"
|
||||
f"{_console_tail(vm.console_log)}")
|
||||
|
||||
|
||||
def _console_tail(console_log: Path, lines: int = 25) -> str:
|
||||
try:
|
||||
text = console_log.read_text(errors="replace").splitlines()
|
||||
except OSError:
|
||||
return "(no console log)"
|
||||
tail = "\n".join(text[-lines:])
|
||||
return f"--- guest console (last {lines} lines) ---\n{tail}"
|
||||
Reference in New Issue
Block a user