fixing test failures
This commit is contained in:
1 parent
c8ff8b1f25
commit
42e903909c
14 files changed
+791
-79
No files matched your search
@@ -25,3 +25,6 @@ devenv.local.yaml
|
||||
|
||||
# pre-commit
|
||||
.pre-commit-config.yaml
|
||||
|
||||
# tmp
|
||||
.tmp
|
||||
@@ -10,7 +10,7 @@ so.
|
||||
One CLI, `hermenix`, with five subcommands:
|
||||
|
||||
| | For |
|
||||
|---|---|
|
||||
| -------------------------------- | --------------------------------------------------------------- |
|
||||
| `hermenix setup` | one-off host provisioning — disks, cache key, image build |
|
||||
| `hermenix migrate <src>` | carry an existing flat `HERMES_HOME` into the guest |
|
||||
| `hermenix remote <host> "<cmd>"` | run `setup`/`migrate` on a remote host over SSH |
|
||||
@@ -54,7 +54,7 @@ it by hand or something goes sideways.
|
||||
Two of them, and the split is the whole design:
|
||||
|
||||
| | Holds | Size | Snapshotted | Backed up |
|
||||
|---|---|---|---|---|
|
||||
| ---------- | ------------------------------------------- | ---- | ----------- | --------- |
|
||||
| **system** | NixOS, `/nix/store` | 80G | No | No |
|
||||
| **state** | identity, memories, workspace, `/etc/nixos` | 20G | Yes | Yes |
|
||||
|
||||
@@ -159,6 +159,8 @@ services.hermenix = {
|
||||
enable = true;
|
||||
disk.baseDir = "/var/lib/hermes-vm";
|
||||
network.externalInterface = "eno1"; # your uplink
|
||||
# network.bridged = true; # guest takes its own LAN IP via DHCP;
|
||||
# # every port it opens is then LAN-reachable
|
||||
vcpu = 4;
|
||||
mem = 8192;
|
||||
};
|
||||
@@ -305,7 +307,7 @@ Two consequences:
|
||||
|
||||
- Editing `guest/hermes/` after first boot changes nothing by itself. Use
|
||||
`hermenix ctl reseed` when you actually want to overwrite.
|
||||
- The seed is the *starting* identity, not the current one. To see what
|
||||
- The seed is the _starting_ identity, not the current one. To see what
|
||||
Hermes has made of itself, `hermenix ctl soul`.
|
||||
|
||||
### Machine facts vs identity
|
||||
@@ -477,6 +479,94 @@ auth in front of anything that isn't a toy, and keep the list short.
|
||||
|
||||
---
|
||||
|
||||
## Putting the guest directly on your LAN
|
||||
|
||||
The default setup puts the guest on an isolated bridge behind the host's NAT,
|
||||
reachable from outside only through `publish`. This section is for when you
|
||||
want the VM to be a first-class device on your LAN instead: its own address
|
||||
from the LAN's DHCP, reachable on any port from any device on the network.
|
||||
|
||||
Enable it:
|
||||
|
||||
```nix
|
||||
services.hermenix.network.bridged = true;
|
||||
```
|
||||
|
||||
In one sentence, what that does: the bridge absorbs your uplink
|
||||
(`network.externalInterface`), the guest and the host share the LAN, the
|
||||
guest takes a DHCP lease, and inbound traffic to the guest is open on every
|
||||
port. Outbound is still gated by `lanAccess` / `allowLan`, and `hostAccess`
|
||||
plus the host Nix cache still work over the service net at `10.77.0.1`.
|
||||
|
||||
### 1. Ready the guest first (one-time, if the image is older than this repo)
|
||||
|
||||
The guest keeps a static service-net address (`10.77.0.2/24`) for talking to
|
||||
the host and adds DHCP on the same NIC, so one config works in both modes.
|
||||
That is already what `guest/common.nix` does; if your guest image predates
|
||||
it, apply the equivalent change to `/etc/nixos/common.nix` inside the VM:
|
||||
|
||||
```nix
|
||||
systemd.network.networks."10-eth" = {
|
||||
matchConfig.Type = "ether";
|
||||
address = [ "10.77.0.2/24" ]; # service net to the host
|
||||
routes = [ { Gateway = "10.77.0.1"; Metric = 200; } ]; # NAT-mode fallback
|
||||
networkConfig.DHCP = "ipv4"; # LAN lease in bridged mode
|
||||
dhcpV4Config = { # DHCP default route wins (100)
|
||||
UseDNS = false;
|
||||
RouteMetric = 100;
|
||||
};
|
||||
};
|
||||
```
|
||||
|
||||
`cd /etc/nixos && git apply -p1 < patch`, commit, and
|
||||
`sudo nixos-rebuild switch --flake /etc/nixos#hermes`. In NAT mode the DHCP
|
||||
attempt fails quietly (there is no server on the isolated bridge), so check
|
||||
nothing broke: `ip -4 addr` still shows `10.77.0.2` and `ip route` still
|
||||
goes via `10.77.0.1`.
|
||||
|
||||
### 2. Rebuild the host with the toggle on
|
||||
|
||||
Set `services.hermenix.network.bridged = true` alongside
|
||||
`network.externalInterface`, then `sudo nixos-rebuild switch`. On rebuild
|
||||
the host's uplink becomes a bridge port, the host takes a fresh DHCP lease
|
||||
on the bridge, and the guest's DHCP is answered by the LAN router. The
|
||||
network drops briefly while the host reconfigures - plan for it.
|
||||
|
||||
### 3. Verify
|
||||
|
||||
From the host, `hermenix vm ssh`. Inside the guest, `ip -4 addr` shows the
|
||||
service net _and_ a LAN address, and `ip route` shows a default route via
|
||||
your LAN gateway. From any other device on the LAN:
|
||||
|
||||
```bash
|
||||
ssh hermes@<guest-lan-ip> # and any other port the guest opens
|
||||
```
|
||||
|
||||
The guest's own firewall decides what answers - by default it only opens
|
||||
port 22, so the agent must open whatever it wants LAN-reachable. Egress is
|
||||
still gated too: from the guest, `192.168.1.50:11434` only works if it is
|
||||
in `lanAccess` (or `allowLan = true`).
|
||||
|
||||
### Gotchas
|
||||
|
||||
- The LAN needs a working DHCP server.
|
||||
- `publish` does nothing in this mode - every port is reachable, so its
|
||||
entries are ignored. Drop them if you come back to NAT mode.
|
||||
- The host's LAN IP comes from a fresh DHCP lease on the bridge, and the
|
||||
bridge MAC can differ from the uplink's - the host's address may change
|
||||
after the switch. Reserve it in the DHCP server if that matters.
|
||||
- Any network config you had for the uplink interface is replaced by its
|
||||
bridge-port role while bridged (this module's networkd unit for it takes
|
||||
priority over most others).
|
||||
|
||||
### Switching back
|
||||
|
||||
Set `bridged = false` and rebuild the host. The guest's DHCP client finds
|
||||
no server on the isolated bridge and settles onto its static route via the
|
||||
host again; no guest-side change needed.
|
||||
|
||||
---
|
||||
|
||||
## Passing hardware to the guest
|
||||
|
||||
### Before reaching for this
|
||||
@@ -583,7 +673,7 @@ Two things that catch people:
|
||||
enable `hardware.bluetooth` on the host.
|
||||
- **No hotplug.** QEMU resolves these at start, so a device that's unplugged
|
||||
when the VM boots won't appear when you plug it in. `hermenix vm restart`
|
||||
after plugging. Passing a whole USB *controller* through as a PCI device
|
||||
after plugging. Passing a whole USB _controller_ through as a PCI device
|
||||
gets you real hotplug for anything in its ports, at the cost of that
|
||||
controller being exclusive to the guest.
|
||||
|
||||
@@ -648,7 +738,7 @@ services.hermenix.backup = {
|
||||
};
|
||||
```
|
||||
|
||||
This backs up the guest's *state*, not its disk. Files are pulled over the
|
||||
This backs up the guest's _state_, not its disk. Files are pulled over the
|
||||
SSH channel that already exists and streamed into restic.
|
||||
|
||||
Two reasons it works that way. The backup stays portable — it restores onto
|
||||
@@ -658,7 +748,7 @@ host, which would mean the host kernel parsing data the agent controls. That
|
||||
would undo a fair bit of what the rest of this design is for.
|
||||
|
||||
If the repository is on your LAN rather than the internet, note this runs on
|
||||
the *host*, so it needs no `lanAccess` entry — the guest never touches it.
|
||||
the _host_, so it needs no `lanAccess` entry — the guest never touches it.
|
||||
|
||||
### When the guest won't boot at all
|
||||
|
||||
@@ -706,7 +796,7 @@ The host stays on stock Nix. Nothing here requires changing that.
|
||||
## What the guest can and cannot reach
|
||||
|
||||
| | Default |
|
||||
|---|---|
|
||||
| ------------------------- | --------------------------------------------------- |
|
||||
| Public internet | Yes — it needs this for model APIs and messaging |
|
||||
| Host Nix cache | Yes, one port, `hostCache.enable = false` closes it |
|
||||
| Anything else on the host | No, unless in `hostAccess` |
|
||||
@@ -714,6 +804,11 @@ The host stays on stock Nix. Nothing here requires changing that.
|
||||
| Inbound from the network | No, unless in `publish` |
|
||||
| Host hardware | None, unless in `passthrough` |
|
||||
|
||||
With `network.bridged = true` the "Inbound from the network" row changes:
|
||||
with the guest on the LAN, every port it opens is reachable from the LAN;
|
||||
`publish` stops doing anything. The outbound rows are unchanged - the
|
||||
`lanAccess` / `allowLan` gates still apply.
|
||||
|
||||
The guest owns its kernel and its config, so nothing inside it is a security
|
||||
boundary. The nftables rules in `modules/host.nix` are. QEMU runs as an
|
||||
unprivileged `hermes-vm` user with its own seccomp sandbox and systemd
|
||||
@@ -862,7 +957,6 @@ journalctl -fu hermes-install # watch until complete
|
||||
hermes setup
|
||||
```
|
||||
|
||||
|
||||
## Hacking on this repo
|
||||
|
||||
The devshell provides nushell, nufmt, and pre-commit hooks. Enter it once:
|
||||
@@ -882,7 +976,7 @@ on every commit, including:
|
||||
|
||||
### Testing
|
||||
|
||||
Two test suites. Neither is ever run for you by an agent working in this
|
||||
Three test suites. None is ever run for you by an agent working in this
|
||||
repo — they're for you (or CI) to run.
|
||||
|
||||
**CLI tests** (`nu/tests/`), via [nutest](https://github.com/vyadh/nutest):
|
||||
@@ -899,22 +993,56 @@ whole `hermenix`/`vm`/`ctl` subcommand tree parses and dispatches correctly
|
||||
— without ever invoking a subcommand's real body (no ssh, no disk writes,
|
||||
no `nix build`).
|
||||
|
||||
**Guest VM test** (`guest/vm-test.nix`): boots `guest/common.nix` — the same
|
||||
module set `hermes-guest-image` is built from — in an ephemeral, throwaway
|
||||
NixOS test VM. No real disk under `/var/lib/hermes-vm/**` is ever touched:
|
||||
**Guest VM tests** (`guest/vm-tests/test_unbridge.nix` / `guest/vm-tests/test_bridge.nix`):
|
||||
boot `guest/common.nix` — the same module set `hermes-guest-image` is built
|
||||
from — in ephemeral, throwaway NixOS test VMs. No real disk under
|
||||
`/var/lib/hermes-vm/**` is ever touched:
|
||||
|
||||
```bash
|
||||
runvmtest # plain pass/fail (nix build .#checks.x86_64-linux.guest-vm --impure -L)
|
||||
runvmtest-debug # build the interactive driver and drop into it (ptpython REPL)
|
||||
runvmtest # NAT/isolated-bridge mode (plain pass/fail)
|
||||
runvmtest guest-vm-bridged # bridged mode with a simulated LAN
|
||||
runvmtest-debug # interactive driver REPL (ptpython) for the default suite
|
||||
```
|
||||
|
||||
Checks first-boot seeding (`~/.hermes`, `~/workspace`, the `/etc/nixos`
|
||||
symlink), that seeding is idempotent across a reboot (the whole point of
|
||||
the `.seeded` marker), the `hermes` user/sudo setup, and SSH. It
|
||||
deliberately does not cover the real `hermes-install` script (no internet
|
||||
Both tests boot the guest the same way and share every check that must hold
|
||||
in both modes — first-boot seeding (`~/.hermes`, `~/workspace`, the
|
||||
`/etc/nixos` symlink), that seeding is idempotent across a reboot (the whole
|
||||
point of the `.seeded` marker), the `hermes` user/sudo setup, and SSH. That
|
||||
shared node config and assertion script are defined once in
|
||||
`guest/vm-tests/common.nix` and imported by both, so nothing can drift
|
||||
between the two modes' common checks.
|
||||
|
||||
Each test then adds the checks that only make sense for its mode:
|
||||
|
||||
- `guest-vm-unbridged` — the isolated bridge has no DHCP server, so it
|
||||
asserts the guest stands on its static config alone: exactly the one
|
||||
`10.77.0.2/24` address and exactly one default route, via the host.
|
||||
- `guest-vm-bridged` — a second node simulates the LAN (a dnsmasq DHCP
|
||||
server, a throwaway HTTP service, and a plain device). It asserts the
|
||||
guest takes a DHCP lease beside the static service-net address, keeps
|
||||
both default routes (the LAN gateway at metric 100 and the host fallback
|
||||
at metric 200), can reach a service on the LAN, and that a LAN device can
|
||||
connect to a port the guest exposes (the guest's own firewall still
|
||||
decides what answers). The host-side half of bridged mode — the bridge
|
||||
itself, the mark-based rules — is covered statically by the check below.
|
||||
|
||||
Both deliberately do not cover the real `hermes-install` script (no internet
|
||||
route inside the test VM) or `modules/host.nix`'s own `hermes-vm` QEMU
|
||||
service — both stay manual, operator-run checks.
|
||||
service — those stay manual, operator-run checks.
|
||||
|
||||
`runvmtest-debug` gives you `start_all()`, `machine.wait_for_unit(...)`, and
|
||||
`machine.shell_interact()` (a live shell inside the guest) to step through a
|
||||
failure by hand instead of just getting pass/fail.
|
||||
|
||||
**Module evaluation checks** (`tests/network-modes-check.nix`): a static
|
||||
check — no build, no VM boot — that evaluates `modules/host.nix` in both
|
||||
networking modes (NAT and `network.bridged = true`) plus `guest/common.nix`,
|
||||
and asserts on the generated nftables rulesets, the firewall input/forward
|
||||
rules, the networkd units, and the guest's DHCP/route-metric config:
|
||||
|
||||
```bash
|
||||
nix build .#checks.x86_64-linux.network-modes
|
||||
```
|
||||
|
||||
Catches regressions in the bridged-mode flag without booting anything. If
|
||||
it fails, the assertion that broke is named in the error.
|
||||
+8
-5
@@ -1,22 +1,25 @@
|
||||
#!/usr/bin/env nu
|
||||
#
|
||||
# runvmtest — build and run the guest-config VM test (guest/vm-test.nix).
|
||||
# runvmtest — build and run the guest-config VM tests. The mode-independent
|
||||
# assertions (seeding, idempotency, account, SSH) are shared between the two
|
||||
# tests via guest/vm-tests/common.nix; each test adds its own mode's
|
||||
# networking checks.
|
||||
#
|
||||
# Plain pass/fail: the build fails if any testScript assertion fails. For
|
||||
# stepping through it interactively instead, use runvmtest-debug.
|
||||
#
|
||||
# --impure is required because guest/common.nix reads
|
||||
# /etc/hermenix/local.nix if present, same as the real hermes-guest-image
|
||||
# build — a pre-existing property of common.nix, not something this test
|
||||
# introduces.
|
||||
# build — a pre-existing property of common.nix, not something the tests
|
||||
# introduce.
|
||||
#
|
||||
# Not run for you automatically: this needs a real build, which agents in
|
||||
# this repo don't run (see GUIDELINES.md). You (or CI) run this by hand.
|
||||
|
||||
def main [
|
||||
suite?: string # which check to run: guest-vm (default) or migrate-connections-vm
|
||||
suite?: string # which check to run: guest-vm-unbridged (default), guest-vm-bridged, or migrate-connections-vm
|
||||
] {
|
||||
let check = $suite | default "guest-vm"
|
||||
let check = $suite | default "guest-vm-unbridged"
|
||||
let attr = $".#checks.x86_64-linux.($check)"
|
||||
print $"running ($attr)"
|
||||
^nix build $attr --impure -L
|
||||
|
||||
+4
-4
@@ -1,6 +1,6 @@
|
||||
#!/usr/bin/env nu
|
||||
#
|
||||
# runvmtest-debug — build the guest-config VM test's interactive driver and
|
||||
# runvmtest-debug — build a guest-config VM test's interactive driver and
|
||||
# drop into it, instead of just running it for pass/fail (see runvmtest).
|
||||
#
|
||||
# Opens a Python (ptpython) REPL with the test's node defined but not yet
|
||||
@@ -8,16 +8,16 @@
|
||||
# start_all()
|
||||
# machine.wait_for_unit("multi-user.target")
|
||||
# machine.shell_interact() # live shell inside the guest, over the console
|
||||
# machine.succeed("...") # run any assertion from guest/vm-test.nix by hand
|
||||
# machine.succeed("...") # run any assertion from the guest-vm tests by hand
|
||||
#
|
||||
# Same --impure requirement as runvmtest, same reason (guest/common.nix
|
||||
# reads /etc/hermenix/local.nix if present). Not run for you automatically
|
||||
# — needs a real build, which agents in this repo don't run.
|
||||
|
||||
def main [
|
||||
suite?: string # which check to debug: guest-vm (default) or migrate-connections-vm
|
||||
suite?: string # which check to debug: guest-vm-unbridged (default), guest-vm-bridged, or migrate-connections-vm
|
||||
] {
|
||||
let check = $suite | default "guest-vm"
|
||||
let check = $suite | default "guest-vm-unbridged"
|
||||
let attr = $".#checks.x86_64-linux.($check).driverInteractive"
|
||||
print $"building interactive driver for ($attr)"
|
||||
^nix build $attr --impure -L
|
||||
|
||||
@@ -118,13 +118,23 @@
|
||||
};
|
||||
|
||||
# Never run by an agent — operator/CI only:
|
||||
# nix build .#checks.x86_64-linux.guest-vm --impure -L
|
||||
checks.${system} = {
|
||||
guest-vm = import ./guest/vm-test.nix { inherit pkgs determinate; };
|
||||
migrate-connections-vm = import ./guest/migrate-connections-test.nix {
|
||||
inherit pkgs;
|
||||
# nix build .#checks.x86_64-linux.guest-vm-unbridged --impure -L
|
||||
# nix build .#checks.x86_64-linux.guest-vm-bridged --impure -L
|
||||
# nix build .#checks.x86_64-linux.migrate-connections-vm --impure -L
|
||||
#
|
||||
# The guest VM tests (guest/vm-tests/) share their node config and
|
||||
# mode-independent assertions via guest/vm-tests/common.nix; each test
|
||||
# adds the checks that only apply to its mode. default.nix aggregates
|
||||
# them into this attrset, which the static network-modes check joins.
|
||||
checks.${system} =
|
||||
(import ./guest/vm-tests {
|
||||
inherit pkgs determinate;
|
||||
hermenix = self.packages.${system}.hermenix;
|
||||
};
|
||||
})
|
||||
// {
|
||||
# No build, no VM boot: evaluates host.nix in both networking modes
|
||||
# and guest/common.nix, and asserts on the generated rulesets/units.
|
||||
network-modes = import ./tests/network-modes-check.nix { inherit pkgs; };
|
||||
};
|
||||
};
|
||||
}
|
||||
+28
-5
@@ -177,19 +177,39 @@ in
|
||||
};
|
||||
|
||||
# =====================================================================
|
||||
# Networking: static, resolvers that are not the host.
|
||||
# Networking: a static service-net address for talking to the host (nix
|
||||
# cache, hostAccess), plus DHCP so an operator can later switch this VM
|
||||
# onto the LAN (services.hermenix.network.bridged = true on the host).
|
||||
# - NAT mode: no DHCP server on the host bridge; the static default
|
||||
# route via the host is the only one and carries all traffic.
|
||||
# - bridged mode: the LAN's DHCP leases this NIC a real LAN address;
|
||||
# that lease's lower-metric default route (100) wins over the static
|
||||
# fallback (200), and LAN devices reach the VM at the lease address.
|
||||
# Resolvers stay QUAD9 (UseDNS = false) in both modes.
|
||||
# =====================================================================
|
||||
networking.useNetworkd = true;
|
||||
systemd.network.enable = true;
|
||||
systemd.network.networks."10-eth" = {
|
||||
matchConfig.Type = "ether";
|
||||
address = [ "${guestAddress}/${toString prefixLength}" ];
|
||||
routes = [ { Gateway = hostAddress; } ];
|
||||
networkConfig.DNS = [
|
||||
routes = [
|
||||
{
|
||||
Gateway = hostAddress;
|
||||
Metric = 200;
|
||||
}
|
||||
];
|
||||
networkConfig = {
|
||||
DHCP = "ipv4";
|
||||
DNS = [
|
||||
"9.9.9.9"
|
||||
"149.112.112.112"
|
||||
];
|
||||
};
|
||||
dhcpV4Config = {
|
||||
UseDNS = false;
|
||||
RouteMetric = 100;
|
||||
};
|
||||
};
|
||||
networking.nameservers = [
|
||||
"9.9.9.9"
|
||||
"149.112.112.112"
|
||||
@@ -359,8 +379,11 @@ in
|
||||
pointless; it will be replaced. Put durable notes in SOUL.md.
|
||||
- The skill at ~/.hermes/skills/nixos-self-config covers how to change
|
||||
this machine safely. Read it before your first rebuild.
|
||||
- You have no route to the host or to any local network. Public internet
|
||||
only, plus a read-only Nix binary cache on ${hostAddress}.
|
||||
- In NAT mode you have no route to the host or to any local network:
|
||||
public internet only, plus a read-only Nix binary cache on
|
||||
${hostAddress}. In bridged mode (network.bridged = true on the host)
|
||||
you take a LAN address from DHCP instead, LAN devices can reach any
|
||||
port you open, and lanAccess/allowLan still limit what you can reach.
|
||||
- Never put a secret in a Nix expression. Everything in the store is
|
||||
world-readable. Use ${stateDir}/.secrets.env and chmod 0600.
|
||||
'';
|
||||
|
||||
@@ -1,42 +1,42 @@
|
||||
# Guest-config tier VM test: boots guest/common.nix (the same module set
|
||||
# used to build hermes-guest-image, see flake.nix) in an ephemeral,
|
||||
# throwaway NixOS test VM, and checks seeding/services. This never touches
|
||||
# a real disk under /var/lib/hermes-vm/** and never runs `hermenix setup`.
|
||||
# Shared building blocks for the two guest-config VM tests in this
|
||||
# directory: test_unbridge.nix and test_bridge.nix.
|
||||
#
|
||||
# guest/hardware.nix (the real disk-label file) is intentionally not
|
||||
# imported here, same as hermes-guest-image's own build — nixos-generators
|
||||
# and, here, the NixOS test framework both supply their own bootloader and
|
||||
# root filesystem instead.
|
||||
# The guest node's configuration and every assertion that must hold in both
|
||||
# networking modes are defined here, once; each mode test imports this file,
|
||||
# uses guestNode as its machine, and appends only the checks that apply to
|
||||
# its mode (the isolated-bridge NAT setup vs. the DHCP-served LAN bridge).
|
||||
#
|
||||
# Both tests boot guest/common.nix — the same module set hermes-guest-image
|
||||
# is built from — in an ephemeral, throwaway NixOS test VM. No real disk
|
||||
# under /var/lib/hermes-vm/** is ever touched, and `hermenix setup` is never
|
||||
# run. guest/hardware.nix (the real disk-label file) is intentionally not
|
||||
# imported, same as hermes-guest-image's own build — nixos-generators and,
|
||||
# here, the NixOS test framework both supply their own bootloader and root
|
||||
# filesystem instead.
|
||||
#
|
||||
# Build with (never run by an agent, only by the operator/CI):
|
||||
# nix build .#checks.x86_64-linux.guest-vm --impure -L
|
||||
# nix build .#checks.x86_64-linux.guest-vm-unbridged --impure -L
|
||||
# nix build .#checks.x86_64-linux.guest-vm-bridged --impure -L
|
||||
#
|
||||
# --impure is required because guest/common.nix reads /etc/hermenix/local.nix
|
||||
# if present (see its own comment) — a pre-existing property of common.nix,
|
||||
# not something introduced by this test.
|
||||
{ pkgs, determinate }:
|
||||
# not something the tests introduce.
|
||||
{ determinate }:
|
||||
|
||||
pkgs.testers.runNixOSTest {
|
||||
name = "hermenix-guest-config";
|
||||
|
||||
# This test boots, reboots once, and runs only quick local checks — a few
|
||||
# minutes is generous. Bound it far below the framework's 1-hour default so
|
||||
# a genuine hang (boot failure, a blocked prompt, a stuck reboot) fails
|
||||
# fast instead of burning a full hour before being reported.
|
||||
globalTimeout = 600;
|
||||
|
||||
nodes.machine =
|
||||
{
|
||||
# The guest node, exactly as both tests boot it.
|
||||
guestNode =
|
||||
{ lib, ... }:
|
||||
{
|
||||
imports = [
|
||||
determinate.nixosModules.default
|
||||
../guest/common.nix
|
||||
../common.nix
|
||||
];
|
||||
|
||||
# A real, separate, auto-formatted virtual disk for the state dir —
|
||||
# not tmpfs. tmpfs would not survive the in-test reboot below, which
|
||||
# would make the idempotency check below pass for the wrong reason
|
||||
# (nothing to re-seed over, rather than correctly skipping re-seeding).
|
||||
# would make the idempotency check pass for the wrong reason (nothing
|
||||
# to re-seed over, rather than correctly skipping re-seeding).
|
||||
virtualisation.emptyDiskImages = [ 1024 ];
|
||||
fileSystems."/var/lib/hermes" = lib.mkForce {
|
||||
device = "/dev/vdb";
|
||||
@@ -45,6 +45,16 @@ pkgs.testers.runNixOSTest {
|
||||
neededForBoot = true;
|
||||
};
|
||||
|
||||
# The test framework's default topology is not the real guest's: it
|
||||
# adds a SLiRP user-mode NIC (10.0.2.0/24, with its own DHCP server)
|
||||
# alongside the shared vlan, and the guest's networkd config matches
|
||||
# any ethernet NIC. Strip the user-mode NIC and keep only the shared
|
||||
# vlan (which udev names eth0) so the test machine has the production
|
||||
# shape: one virtual NIC, and no stray DHCP server to confuse the
|
||||
# mode-specific networking assertions.
|
||||
virtualisation.qemu.networkingOptions = lib.mkForce [ ];
|
||||
virtualisation.vlans = [ 1 ];
|
||||
|
||||
# nixosTest VMs have no route to the internet by design, so the real
|
||||
# hermes-install body (a third-party curl | bash installer) can't run
|
||||
# hermetically here. Stubbed to just flag itself done; the real
|
||||
@@ -54,7 +64,9 @@ pkgs.testers.runNixOSTest {
|
||||
'';
|
||||
};
|
||||
|
||||
testScript = ''
|
||||
# Assertions that hold in both modes: first-boot seeding, seeding
|
||||
# idempotency across a reboot, the agent's account, and SSH.
|
||||
commonScript = ''
|
||||
# allow_reboot=True: without it, the VM starts with qemu's -no-reboot,
|
||||
# so the guest-initiated machine.reboot() below would just kill the VM
|
||||
# instead of restarting it, and the backdoor shell would never
|
||||
@@ -84,18 +96,9 @@ pkgs.testers.runNixOSTest {
|
||||
machine.succeed("groups hermes | grep -q wheel")
|
||||
machine.succeed("su - hermes -c 'sudo -n true'")
|
||||
|
||||
# SSH is up.
|
||||
# SSH is up (checked over the test backdoor, so it is independent of
|
||||
# whatever address configuration the mode under test produces).
|
||||
machine.wait_for_unit("sshd.service")
|
||||
machine.wait_for_open_port(22)
|
||||
|
||||
# NOTE: not checking /etc/nix/nix.custom.conf's content here. `nix eval`
|
||||
# on environment.etc."nix/nix.custom.conf".text confirms guest/common.nix
|
||||
# itself renders the expected (no-host-cache) content, but the actual
|
||||
# booted guest's copy of that file instead holds the NixOS test
|
||||
# framework's own injected nix.settings (substituters = cache.nixos.org,
|
||||
# trusted-users = root, system-features = nixos-test ...) — needed so
|
||||
# nested Nix operations inside the test VM work at all. That's an
|
||||
# artifact of running under nixosTest, not something guest/common.nix or
|
||||
# this test controls, so it's not a reliable thing to assert on here.
|
||||
'';
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
# guest/vm-tests/default.nix — the granular guest VM test suite.
|
||||
#
|
||||
# Aggregates the three runNixOSTest checks into a single import surface for
|
||||
# flake.nix's checks.${system}. common.nix holds the guest node config and
|
||||
# the mode-independent assertions shared by the two host-networking-mode
|
||||
# tests; test_unbridge.nix / test_bridge.nix add each mode's own checks, and
|
||||
# test_migrate_connections.nix covers `hermenix migrate connections`.
|
||||
#
|
||||
# Run by the operator/CI, never by an agent (see GUIDELINES.md):
|
||||
# nix build .#checks.x86_64-linux.guest-vm-unbridged --impure -L
|
||||
# nix build .#checks.x86_64-linux.guest-vm-bridged --impure -L
|
||||
# nix build .#checks.x86_64-linux.migrate-connections-vm --impure -L
|
||||
#
|
||||
# --impure is required because guest/common.nix reads
|
||||
# /etc/hermenix/local.nix if present (see its own comment) — a pre-existing
|
||||
# property of common.nix, not something the tests introduce.
|
||||
{
|
||||
pkgs,
|
||||
determinate,
|
||||
hermenix,
|
||||
}:
|
||||
|
||||
{
|
||||
guest-vm-unbridged = import ./test_unbridge.nix { inherit pkgs determinate; };
|
||||
guest-vm-bridged = import ./test_bridge.nix { inherit pkgs determinate; };
|
||||
migrate-connections-vm = import ./test_migrate_connections.nix { inherit pkgs hermenix; };
|
||||
}
|
||||
@@ -0,0 +1,124 @@
|
||||
# Guest-config VM test, bridged mode: the guest on a LAN served by DHCP,
|
||||
# with a second node acting as the LAN (a DHCP server, a throwaway HTTP
|
||||
# service, and a plain device that connects back to the guest). This is the
|
||||
# guest-facing half of services.hermenix.network.bridged = true: the module's
|
||||
# own bridge/enforcement rules are covered statically by
|
||||
# tests/network-modes-check.nix.
|
||||
#
|
||||
# The guest node and the mode-independent assertions (seeding, idempotency,
|
||||
# account, SSH) are shared with guest-vm-unbridged via
|
||||
# common.nix.
|
||||
#
|
||||
# Build with (never run by an agent, only by the operator/CI):
|
||||
# nix build .#checks.x86_64-linux.guest-vm-bridged --impure -L
|
||||
{ pkgs, determinate }:
|
||||
|
||||
let
|
||||
common = import ./common.nix { inherit determinate; };
|
||||
in
|
||||
pkgs.testers.runNixOSTest {
|
||||
name = "hermenix-guest-config-bridged";
|
||||
|
||||
# Boots once, reboots once, and waits on DHCP lease negotiation plus a few
|
||||
# cross-node checks - still only minutes. Bound it far below the
|
||||
# framework's 1-hour default so a genuine hang fails fast.
|
||||
globalTimeout = 900;
|
||||
|
||||
nodes = {
|
||||
machine = common.guestNode;
|
||||
|
||||
# The "LAN": serves DHCP to the guest and hosts a throwaway HTTP
|
||||
# service, standing in for the LAN router and another LAN device. Its
|
||||
# firewall is off so the guest<->LAN checks exercise the network path
|
||||
# itself, not this throwaway node's own firewall.
|
||||
lan =
|
||||
{ pkgs, lib, ... }:
|
||||
{
|
||||
networking.firewall.enable = false;
|
||||
|
||||
# Same production-shape networking as the guest node: kill the test
|
||||
# framework's SLiRP user-mode NIC so the only NIC left is the one
|
||||
# shared with the guest.
|
||||
virtualisation.qemu.networkingOptions = lib.mkForce [ ];
|
||||
virtualisation.vlans = [ 1 ];
|
||||
|
||||
# The framework's own name-based static assignment missed the
|
||||
# shared NIC when this suite actually ran (the NIC came up as eth1,
|
||||
# not the eth0 the framework expected), and real interface names
|
||||
# vary anyway - and node numbering is attr order, which is not
|
||||
# something to trust. The shared NIC's MAC is deterministic
|
||||
# (52:54:00:12:<vlan>:<node>, see qemu-common.nix), so pin the
|
||||
# address in networkd by MAC. Two candidate rules cover either node
|
||||
# numbering; the one that matches this node's actual NIC wins, and
|
||||
# nothing depends on an interface name.
|
||||
networking.useNetworkd = true;
|
||||
systemd.network.networks."10-hermes-lan-1" = {
|
||||
matchConfig.MACAddress = "52:54:00:12:01:01"; # vlan 1, node #1
|
||||
address = [ "192.168.1.2/24" ];
|
||||
networkConfig.LinkLocalAddressing = "no";
|
||||
};
|
||||
systemd.network.networks."10-hermes-lan-2" = {
|
||||
matchConfig.MACAddress = "52:54:00:12:01:02"; # vlan 1, node #2
|
||||
address = [ "192.168.1.2/24" ];
|
||||
networkConfig.LinkLocalAddressing = "no";
|
||||
};
|
||||
|
||||
# DHCP only (port = 0 disables dnsmasq's DNS half; the guest keeps
|
||||
# its own QUAD9 resolvers regardless). Bound to the node's static
|
||||
# vlan address rather than an interface name - the framework's
|
||||
# interface naming is not something this test should depend on.
|
||||
services.dnsmasq = {
|
||||
enable = true;
|
||||
settings = {
|
||||
port = 0;
|
||||
listen-address = "192.168.1.2";
|
||||
bind-interfaces = true;
|
||||
dhcp-range = "192.168.1.100,192.168.1.200,12h";
|
||||
dhcp-option = [
|
||||
"3,192.168.1.2" # default gateway -> this node
|
||||
"6,192.168.1.2" # DNS -> this node
|
||||
];
|
||||
};
|
||||
};
|
||||
|
||||
environment.systemPackages = [ pkgs.python3 ];
|
||||
};
|
||||
};
|
||||
|
||||
testScript = ''
|
||||
# Bring the LAN up early so the guest's DHCP client (which retries for
|
||||
# as long as it runs) can get a lease as soon as the guest is online.
|
||||
lan.start()
|
||||
''
|
||||
+ common.commonScript
|
||||
+ ''
|
||||
# --- bridged-mode networking ---------------------------------------
|
||||
# The LAN's DHCP gave the guest a lease alongside its static
|
||||
# service-net address. (Both test nodes share one vlan, standing in for
|
||||
# the bridged uplink on a real host.)
|
||||
machine.wait_until_succeeds("ip -4 route show default | grep -q 'metric 100'")
|
||||
|
||||
addrs = machine.succeed("ip -4 -o addr show | grep -v '^1: lo'").strip().splitlines()
|
||||
guest_lan_ip = None
|
||||
for line in addrs:
|
||||
ip = line.split()[3].split("/")[0]
|
||||
if not ip.startswith("10.77."):
|
||||
guest_lan_ip = ip
|
||||
assert any("10.77.0.2/24" in line for line in addrs), f"static service-net address missing in bridged mode: {addrs}"
|
||||
assert guest_lan_ip is not None, f"guest never took a LAN DHCP lease: {addrs}"
|
||||
|
||||
# Both default routes are in place: the LAN's (metric 100, in use) and
|
||||
# the host service-net fallback (metric 200) that NAT mode relies on.
|
||||
machine.succeed("ip -4 route show default | grep -q 'default via 192.168.1.2'")
|
||||
machine.succeed("ip -4 route show default | grep -q 'default via 10.77.0.1'")
|
||||
|
||||
# Guest -> LAN: the guest reaches a service on the LAN node.
|
||||
lan.succeed("systemd-run --collect -u lanhttpd python3 -m http.server 8000 --bind 0.0.0.0")
|
||||
machine.wait_until_succeeds("curl -fsS http://192.168.1.2:8000/ >/dev/null")
|
||||
|
||||
# LAN -> guest: a plain device on the LAN can connect to a port the
|
||||
# guest exposes - the guest's own firewall still decides what answers
|
||||
# (here, sshd on 22).
|
||||
lan.wait_until_succeeds(f"bash -c 'exec 3<>/dev/tcp/{guest_lan_ip}/22'")
|
||||
'';
|
||||
}
|
||||
File renamed without changes.
@@ -0,0 +1,42 @@
|
||||
# Guest-config VM test, NAT (unbridged) mode: guest/common.nix as it sits on
|
||||
# the host's isolated bridge, where there is no DHCP server and the guest
|
||||
# must be fully served by its static service-net configuration.
|
||||
#
|
||||
# The guest node and the mode-independent assertions (seeding, idempotency,
|
||||
# account, SSH) are shared with guest-vm-bridged via common.nix;
|
||||
# the networking assertions here only make sense in this mode.
|
||||
#
|
||||
# Build with (never run by an agent, only by the operator/CI):
|
||||
# nix build .#checks.x86_64-linux.guest-vm-unbridged --impure -L
|
||||
{ pkgs, determinate }:
|
||||
|
||||
let
|
||||
common = import ./common.nix { inherit determinate; };
|
||||
in
|
||||
pkgs.testers.runNixOSTest {
|
||||
name = "hermenix-guest-config-unbridged";
|
||||
|
||||
# Boots once, reboots once, and runs only quick local checks — a few
|
||||
# minutes is generous. Bound it far below the framework's 1-hour default so
|
||||
# a genuine hang (boot failure, a blocked prompt, a stuck reboot) fails
|
||||
# fast instead of burning a full hour before being reported.
|
||||
globalTimeout = 600;
|
||||
|
||||
nodes.machine = common.guestNode;
|
||||
|
||||
testScript = common.commonScript + ''
|
||||
# --- NAT-mode networking -------------------------------------------
|
||||
# The isolated vlan has no DHCP server, so the guest's NIC must be
|
||||
# self-sufficient: exactly the one static service-net address, and
|
||||
# exactly one default route - via the host - because the DHCP client
|
||||
# found nobody to talk to and contributed nothing. The interface name
|
||||
# is deliberately not hard-coded (the real guest's NIC name varies too;
|
||||
# only the address layout is asserted).
|
||||
addrs = machine.succeed("ip -4 -o addr show | grep -v '^1: lo'").strip().splitlines()
|
||||
assert len(addrs) == 1, f"expected only the static service-net address, got: {addrs}"
|
||||
assert "10.77.0.2/24" in addrs[0], f"static service-net address missing: {addrs}"
|
||||
|
||||
machine.succeed("test \"$(ip -4 route show default | wc -l)\" -eq 1")
|
||||
machine.succeed("ip -4 route show default | grep -q 'default via 10.77.0.1'")
|
||||
'';
|
||||
}
|
||||
+136
-4
@@ -36,6 +36,13 @@ let
|
||||
anyUsb = pt.usb != [ ];
|
||||
earlyIds = lib.filter (i: i != null) (map (d: d.id) pt.pci);
|
||||
|
||||
# Netfilter mark tagging guest-originated traffic in bridged mode. The
|
||||
# guest's only way in is the tap interface, so marking at the bridge
|
||||
# prerouting hook is as specific as an address match - and it is the only
|
||||
# way to identify the guest at the ip-family layer, where its DHCP-issued
|
||||
# LAN address is not statically known. 18501 == 0x4845 ("HE"), for hermenix.
|
||||
bridgeMark = 18501;
|
||||
|
||||
# Graceful ACPI power button via QMP, then wait for QEMU to exit.
|
||||
stopScript = pkgs.writeShellScript "hermes-vm-stop" ''
|
||||
set -eu
|
||||
@@ -330,6 +337,26 @@ in
|
||||
type = types.int;
|
||||
default = 24;
|
||||
};
|
||||
bridged = mkOption {
|
||||
type = types.bool;
|
||||
default = false;
|
||||
description = ''
|
||||
Put the guest directly on your LAN instead of behind the host's
|
||||
NAT. The bridge absorbs `externalInterface`, and the guest takes
|
||||
an address from your LAN's DHCP, so any device on the LAN can
|
||||
reach any port the guest exposes.
|
||||
|
||||
Inbound is no longer limited to `publish` (which is ignored in
|
||||
this mode): the LAN may reach every guest port. Outbound is still
|
||||
governed by `lanAccess` / `allowLan`, and `hostAccess` plus the
|
||||
host cache still work over the host-guest service net
|
||||
(`hostAddress` stays configured on the bridge).
|
||||
|
||||
Requires a working DHCP server on the LAN, and a guest that runs
|
||||
a DHCP client on its NIC (see guest/common.nix - this repo's
|
||||
guest does).
|
||||
'';
|
||||
};
|
||||
externalInterface = mkOption {
|
||||
type = types.nullOr types.str;
|
||||
default = null;
|
||||
@@ -734,11 +761,15 @@ in
|
||||
|
||||
systemd.network.networks."10-${net.bridge}" = {
|
||||
matchConfig.Name = net.bridge;
|
||||
# hostAddress stays on the bridge in both modes: it is the guest's
|
||||
# service net (host cache, hostAccess). In bridged mode the LAN DHCP
|
||||
# lease is added on top of it.
|
||||
address = [ "${net.hostAddress}/${toString net.prefixLength}" ];
|
||||
networkConfig = {
|
||||
ConfigureWithoutCarrier = true;
|
||||
IPv4Forwarding = true;
|
||||
};
|
||||
}
|
||||
// lib.optionalAttrs net.bridged { DHCP = "ipv4"; };
|
||||
};
|
||||
|
||||
systemd.network.networks."11-${net.tapId}" = {
|
||||
@@ -746,6 +777,17 @@ in
|
||||
networkConfig.Bridge = net.bridge;
|
||||
};
|
||||
|
||||
# Bridged mode: the physical uplink becomes a bridge port so the LAN
|
||||
# shares an L2 domain with the guest and the guest's DHCP is answered
|
||||
# by the LAN itself. The port must not carry its own address config -
|
||||
# the bridge owns the LAN address now. Note the bridge takes a fresh
|
||||
# DHCP lease, and because its MAC can differ from the uplink's, the
|
||||
# host's LAN IP may change after the first switch to bridged mode.
|
||||
systemd.network.networks."12-${net.externalInterface}" = lib.mkIf net.bridged {
|
||||
matchConfig.Name = net.externalInterface;
|
||||
networkConfig.Bridge = net.bridge;
|
||||
};
|
||||
|
||||
# ip_forward: use the same sysctl keys networking.nat used (mkOverride 99
|
||||
# so they win over any lower-priority defaults elsewhere in the config).
|
||||
boot.kernel.sysctl."net.ipv4.conf.all.forwarding" = lib.mkOverride 99 true;
|
||||
@@ -764,7 +806,24 @@ in
|
||||
# while covering every legitimate external path.
|
||||
networking.nftables.tables.hermenix-nat = lib.mkIf (net.externalInterface != null) {
|
||||
family = "ip";
|
||||
content = ''
|
||||
content =
|
||||
if net.bridged then
|
||||
# Bridged mode: no DNAT (the guest is directly reachable on the
|
||||
# LAN) and no primary masquerade. Keep one scoped masquerade as a
|
||||
# fallback: if the guest's DHCP lease lapses it falls back to its
|
||||
# static default route via the host, and this keeps that path
|
||||
# working instead of blackholing at the uplink. With a healthy
|
||||
# lease the guest's traffic is L2-bridged and never reaches this
|
||||
# chain. Only traffic handed up from the bridge (i.e. the guest's
|
||||
# service-net traffic) is matched, never the LAN itself.
|
||||
''
|
||||
chain postrouting {
|
||||
type nat hook postrouting priority srcnat;
|
||||
iifname "${net.bridge}" oifname "${net.externalInterface}" masquerade
|
||||
}
|
||||
''
|
||||
else
|
||||
''
|
||||
chain prerouting {
|
||||
type nat hook prerouting priority dstnat;
|
||||
''
|
||||
@@ -780,6 +839,56 @@ in
|
||||
'';
|
||||
};
|
||||
|
||||
# =====================================================================
|
||||
# Bridged mode: bridge-family enforcement.
|
||||
#
|
||||
# With the uplink bridged, guest <-> LAN traffic is switched at L2 and
|
||||
# never traverses the ip-family hooks the NAT-mode rules rely on, so
|
||||
# bridged mode gets its own table where the tap port is unambiguous.
|
||||
# lanAccess / allowLan still gate what the guest may reach; inbound
|
||||
# from the LAN to the guest is open on every port.
|
||||
# =====================================================================
|
||||
networking.nftables.tables."hermenix-bridge" = lib.mkIf net.bridged {
|
||||
family = "bridge";
|
||||
content = ''
|
||||
chain prerouting {
|
||||
type filter hook prerouting priority filter; policy accept;
|
||||
# Tag anything entering from the guest. ip-family input rules
|
||||
# (host cache, hostAccess) match this mark.
|
||||
iifname "${net.tapId}" meta mark set ${toString bridgeMark}
|
||||
}
|
||||
chain forward {
|
||||
type filter hook forward priority filter; policy accept;
|
||||
# Inbound from the LAN to the guest: any device, any port.
|
||||
oifname "${net.tapId}" accept
|
||||
''
|
||||
+ lib.concatMapStrings (s: ''
|
||||
iifname "${net.tapId}" ip daddr ${s.address} ${s.proto} dport ${toString s.port} accept
|
||||
'') cfg.lanAccess
|
||||
+ (
|
||||
if cfg.allowLan then
|
||||
''
|
||||
iifname "${net.tapId}" accept
|
||||
''
|
||||
else
|
||||
''
|
||||
iifname "${net.tapId}" ip daddr {
|
||||
10.0.0.0/8,
|
||||
172.16.0.0/12,
|
||||
192.168.0.0/16,
|
||||
169.254.0.0/16,
|
||||
127.0.0.0/8,
|
||||
100.64.0.0/10
|
||||
} drop
|
||||
iifname "${net.tapId}" ip6 daddr { fc00::/7, fe80::/10, ::1/128 } drop
|
||||
iifname "${net.tapId}" accept
|
||||
''
|
||||
)
|
||||
+ ''
|
||||
}
|
||||
'';
|
||||
};
|
||||
|
||||
# =====================================================================
|
||||
# Firewall
|
||||
#
|
||||
@@ -792,7 +901,23 @@ in
|
||||
|
||||
# The deliberate guest -> host holes: the Nix cache, plus anything listed
|
||||
# in hostAccess.
|
||||
#
|
||||
# NAT mode: the guest always arrives from its fixed service-net address,
|
||||
# so match address + bridge. Bridged mode: the guest's LAN address comes
|
||||
# from DHCP and is not known here, so the bridge table above tags guest
|
||||
# traffic with a netfilter mark as it enters the tap - the rules match
|
||||
# that mark instead. The tap is exclusive to the guest, so the mark is
|
||||
# as specific as an address match: LAN devices can never inherit these
|
||||
# holes.
|
||||
networking.firewall.extraInputRules =
|
||||
if net.bridged then
|
||||
optionalString cfg.hostCache.enable ''
|
||||
meta mark ${toString bridgeMark} tcp dport ${toString cfg.hostCache.port} accept
|
||||
''
|
||||
+ lib.concatMapStrings (s: ''
|
||||
meta mark ${toString bridgeMark} ${s.proto} dport ${toString s.port} accept
|
||||
'') cfg.hostAccess
|
||||
else
|
||||
optionalString cfg.hostCache.enable ''
|
||||
iifname "${net.bridge}" ip saddr ${net.guestAddress} tcp dport ${toString cfg.hostCache.port} accept
|
||||
''
|
||||
@@ -801,6 +926,10 @@ in
|
||||
'') cfg.hostAccess;
|
||||
|
||||
# Order matters here. Allowlists must precede the RFC1918 drop.
|
||||
#
|
||||
# These ip-family rules only ever see routed traffic. They are the whole
|
||||
# story in NAT mode; in bridged mode the guest's LAN traffic is
|
||||
# L2-bridged instead and is governed by the hermenix-bridge table.
|
||||
networking.firewall.extraForwardRules = ''
|
||||
iifname != "${net.bridge}" accept
|
||||
ct state established,related accept
|
||||
@@ -809,10 +938,13 @@ in
|
||||
+ lib.concatMapStrings (s: ''
|
||||
iifname "${net.bridge}" ip daddr ${s.address} ${s.proto} dport ${toString s.port} accept
|
||||
'') cfg.lanAccess
|
||||
# Inbound to guest services published on the uplink.
|
||||
+ lib.concatMapStrings (s: ''
|
||||
# Inbound to guest services published on the uplink. NAT mode only; in
|
||||
# bridged mode the bridge table opens every inbound port instead.
|
||||
+ lib.optionalString (!net.bridged) (
|
||||
lib.concatMapStrings (s: ''
|
||||
oifname "${net.bridge}" ip daddr ${net.guestAddress} ${s.proto} dport ${toString s.guestPort} accept
|
||||
'') cfg.publish
|
||||
)
|
||||
+ (
|
||||
if cfg.allowLan then
|
||||
''
|
||||
|
||||
@@ -375,6 +375,8 @@ def "main setup" [
|
||||
\};
|
||||
"
|
||||
note $"detected uplink: ($uplink) — check that's right before rebuilding"
|
||||
note "network.bridged = true instead puts the guest on your LAN (own DHCP"
|
||||
note "address, every opened port reachable from the LAN) - see the README."
|
||||
|
||||
print $"
|
||||
Then:
|
||||
|
||||
@@ -0,0 +1,215 @@
|
||||
# Static evaluation check for the host module's two networking modes (NAT
|
||||
# and bridged) and the guest's mode-agnostic NIC configuration.
|
||||
#
|
||||
# Nothing here is built or booted: the check evaluates services.hermenix
|
||||
# (modules/host.nix) in both modes plus guest/common.nix, and asserts on the
|
||||
# networking configuration the modules produce - the nftables rulesets, the
|
||||
# ip-family input/forward rules, the systemd-networkd units, and the guest's
|
||||
# DHCP / route-metric setup. Any failing assertion fails the check listing
|
||||
# what broke.
|
||||
#
|
||||
# Run by the operator/CI, never by an agent:
|
||||
# nix build .#checks.x86_64-linux.network-modes
|
||||
#
|
||||
# The host evaluations use minimal stub options for the NixOS modules the
|
||||
# host module's config feeds (networking.nftables, networking.firewall,
|
||||
# systemd.network) because this check only reads those outputs back; every
|
||||
# other option host.nix writes is out of scope and passed through with
|
||||
# _module.check = false. The guest evaluation is different: guest/common.nix
|
||||
# runs against the full NixOS option set (module-list.nix) because its real
|
||||
# imports (qemu-guest profile and friends) need it.
|
||||
{ pkgs }:
|
||||
|
||||
let
|
||||
inherit (pkgs) lib;
|
||||
nixpkgsPath = pkgs.path;
|
||||
has = lib.strings.hasInfix;
|
||||
|
||||
# ------------------------------------------------------------------ #
|
||||
# Host module, evaluated with stub options for what this check reads. #
|
||||
# ------------------------------------------------------------------ #
|
||||
hostOptions = { lib, ... }: {
|
||||
config._module.check = false;
|
||||
options = {
|
||||
networking = {
|
||||
useNetworkd = lib.mkOption {
|
||||
type = lib.types.bool;
|
||||
default = false;
|
||||
};
|
||||
nftables = {
|
||||
enable = lib.mkOption {
|
||||
type = lib.types.bool;
|
||||
default = false;
|
||||
};
|
||||
tables = lib.mkOption {
|
||||
type = lib.types.attrsOf lib.types.anything;
|
||||
default = { };
|
||||
};
|
||||
};
|
||||
firewall = {
|
||||
enable = lib.mkOption {
|
||||
type = lib.types.bool;
|
||||
default = true;
|
||||
};
|
||||
filterForward = lib.mkOption {
|
||||
type = lib.types.bool;
|
||||
default = false;
|
||||
};
|
||||
extraInputRules = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "";
|
||||
};
|
||||
extraForwardRules = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "";
|
||||
};
|
||||
};
|
||||
};
|
||||
systemd.network = {
|
||||
networks = lib.mkOption {
|
||||
type = lib.types.attrsOf lib.types.anything;
|
||||
default = { };
|
||||
};
|
||||
netdevs = lib.mkOption {
|
||||
type = lib.types.attrsOf lib.types.anything;
|
||||
default = { };
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
# The one scenario every assertion is made against.
|
||||
evalHost =
|
||||
bridged:
|
||||
lib.evalModules {
|
||||
modules = [
|
||||
hostOptions
|
||||
../modules/host.nix
|
||||
{
|
||||
services.hermenix = {
|
||||
enable = true;
|
||||
network = {
|
||||
externalInterface = "eno1";
|
||||
inherit bridged;
|
||||
};
|
||||
allowLan = false;
|
||||
publish = [
|
||||
{
|
||||
hostPort = 8080;
|
||||
guestPort = 8080;
|
||||
}
|
||||
];
|
||||
lanAccess = [
|
||||
{
|
||||
address = "192.168.1.50";
|
||||
port = 11434;
|
||||
}
|
||||
];
|
||||
hostAccess = [ { port = 8188; } ];
|
||||
};
|
||||
}
|
||||
];
|
||||
specialArgs = { inherit pkgs; };
|
||||
};
|
||||
|
||||
nat = evalHost false;
|
||||
br = evalHost true;
|
||||
|
||||
natNft = nat.config.networking.nftables.tables;
|
||||
brNft = br.config.networking.nftables.tables;
|
||||
natNat = natNft."hermenix-nat" or { };
|
||||
brNat = brNft."hermenix-nat" or { };
|
||||
brBr = brNft."hermenix-bridge" or { };
|
||||
|
||||
natNetworks = nat.config.systemd.network.networks;
|
||||
brNetworks = br.config.systemd.network.networks;
|
||||
|
||||
natInput = nat.config.networking.firewall.extraInputRules;
|
||||
natForward = nat.config.networking.firewall.extraForwardRules;
|
||||
brInput = br.config.networking.firewall.extraInputRules;
|
||||
brForward = br.config.networking.firewall.extraForwardRules;
|
||||
|
||||
hostResults = {
|
||||
# --- NAT mode: the original behaviour has to be unchanged ----------
|
||||
"nat: no bridged-mode bridge table" = !(natNft ? "hermenix-bridge");
|
||||
"nat: publish is DNATed to the guest" = has "dnat to 10.77.0.2:8080" natNat.content;
|
||||
"nat: outbound masquerades on the uplink" = has "masquerade" natNat.content;
|
||||
"nat: input rules match the fixed service-net address" =
|
||||
has "ip saddr 10.77.0.2 tcp dport 5000 accept" natInput && !(has "meta mark" natInput);
|
||||
"nat: published port has a forward accept" =
|
||||
has "ip daddr 10.77.0.2 tcp dport 8080 accept" natForward;
|
||||
"nat: bridge keeps the static service-net address, no LAN DHCP" =
|
||||
natNetworks."10-hermes-br".address == [ "10.77.0.1/24" ]
|
||||
&& (natNetworks."10-hermes-br".networkConfig.DHCP or null) == null;
|
||||
"nat: uplink is not a bridge port" = !(natNetworks ? "12-eno1");
|
||||
"nat: tap is a bridge port" = natNetworks."11-vm-hermes".networkConfig.Bridge == "hermes-br";
|
||||
"nat: bridge netdev exists" =
|
||||
nat.config.systemd.network.netdevs."10-hermes-br".netdevConfig.Kind == "bridge";
|
||||
|
||||
# --- bridged mode: the guest is directly on the LAN ----------------
|
||||
"bridged: bridge-family table exists" = brNft ? "hermenix-bridge" && brBr.family == "bridge";
|
||||
"bridged: guest traffic is marked as it enters the tap" = has "meta mark set 18501" brBr.content;
|
||||
"bridged: inbound from the LAN is open on every port" =
|
||||
has "oifname \"vm-hermes\" accept" brBr.content;
|
||||
"bridged: lanAccess still gates guest egress" =
|
||||
has "ip daddr 192.168.1.50 tcp dport 11434 accept" brBr.content;
|
||||
"bridged: private-space egress is dropped unless allowlisted" =
|
||||
has "192.168.0.0/16" brBr.content && has "fc00::/7" brBr.content;
|
||||
"bridged: no DNAT for publish" =
|
||||
!(has "dnat to" brNat.content) && !(has "chain prerouting" brNat.content);
|
||||
"bridged: scoped fallback masquerade remains" = has "masquerade" brNat.content;
|
||||
"bridged: input rules match the mark, not the unknown DHCP address" =
|
||||
has "meta mark 18501 tcp dport 5000 accept" brInput
|
||||
&& has "meta mark 18501 tcp dport 8188 accept" brInput
|
||||
&& !(has "ip saddr 10.77.0.2" brInput);
|
||||
"bridged: publish forward rules are dropped" =
|
||||
!(has "ip daddr 10.77.0.2 tcp dport 8080 accept" brForward);
|
||||
"bridged: bridge keeps the service net and takes LAN DHCP" =
|
||||
brNetworks."10-hermes-br".address == [ "10.77.0.1/24" ]
|
||||
&& brNetworks."10-hermes-br".networkConfig.DHCP == "ipv4";
|
||||
"bridged: uplink is a bridge port" = brNetworks."12-eno1".networkConfig.Bridge == "hermes-br";
|
||||
"bridged: tap is still a bridge port" =
|
||||
brNetworks."11-vm-hermes".networkConfig.Bridge == "hermes-br";
|
||||
};
|
||||
|
||||
# ------------------------------------------------------------------- #
|
||||
# Guest module: must produce one NIC config that works in both modes. #
|
||||
# Evaluated against the full NixOS option set. #
|
||||
# ------------------------------------------------------------------- #
|
||||
guest = lib.evalModules {
|
||||
modules = (import "${nixpkgsPath}/nixos/modules/module-list.nix") ++ [
|
||||
{ config._module.check = false; }
|
||||
../guest/common.nix
|
||||
];
|
||||
specialArgs = {
|
||||
inherit pkgs;
|
||||
modulesPath = "${nixpkgsPath}/nixos/modules";
|
||||
};
|
||||
};
|
||||
gEth = guest.config.systemd.network.networks."10-eth";
|
||||
gRoute = builtins.elemAt gEth.routes 0;
|
||||
|
||||
guestResults = {
|
||||
"guest: NIC asks for a DHCP lease (bridged mode)" = gEth.networkConfig.DHCP == "ipv4";
|
||||
"guest: service-net address stays static (both modes)" = gEth.address == [ "10.77.0.2/24" ];
|
||||
"guest: static default route via the host is the NAT fallback" =
|
||||
gRoute.Gateway == "10.77.0.1" && gRoute.Metric == 200;
|
||||
"guest: DHCP default route wins (metric 100)" = gEth.dhcpV4Config.RouteMetric == 100;
|
||||
"guest: resolvers stay QUAD9, DHCP DNS is ignored" =
|
||||
gEth.dhcpV4Config.UseDNS == false
|
||||
&&
|
||||
gEth.networkConfig.DNS == [
|
||||
"9.9.9.9"
|
||||
"149.112.112.112"
|
||||
];
|
||||
};
|
||||
|
||||
results = hostResults // guestResults;
|
||||
|
||||
failing = builtins.filter (n: !results.${n}) (builtins.attrNames results);
|
||||
in
|
||||
assert lib.assertMsg (failing == [ ]) ''
|
||||
hermenix network-modes check FAILED:
|
||||
${lib.concatMapStringsSep "\n" (n: " - " + n) failing}
|
||||
'';
|
||||
pkgs.runCommand "hermenix-network-modes-check" { } "touch $out"
|
||||
Reference in new issue
Block a user