371 lines
13 KiB
Nix
371 lines
13 KiB
Nix
{
|
|
inputs,
|
|
lib,
|
|
self,
|
|
specialArgs,
|
|
bridgeName,
|
|
moduleFiles,
|
|
registry,
|
|
}:
|
|
let
|
|
inherit (lib) escapeShellArg mapAttrsToList;
|
|
|
|
deriveMac =
|
|
name:
|
|
let
|
|
hash = builtins.hashString "sha256" name;
|
|
octet = i: builtins.substring (i * 2) 2 hash;
|
|
in
|
|
lib.concatStringsSep ":" ([ "02" ] ++ map octet [ 0 1 2 3 4 ]);
|
|
|
|
guest =
|
|
{
|
|
name,
|
|
interior ? { },
|
|
}:
|
|
{ config, lib, ... }:
|
|
let
|
|
optionPath = [ "guests" ] ++ lib.splitString "." name;
|
|
cfg = lib.getAttrFromPath optionPath config;
|
|
machineName = lib.replaceStrings [ "." ] [ "-" ] name;
|
|
|
|
networked = cfg.vlan != null;
|
|
|
|
userMounts = lib.mapAttrs (_guestPath: m: {
|
|
inherit (m) hostPath;
|
|
isReadOnly = m.readOnly;
|
|
}) cfg.mounts;
|
|
|
|
secretMounts = lib.listToAttrs (
|
|
map (
|
|
name:
|
|
let
|
|
path = config.sops.secrets.${name}.path;
|
|
in
|
|
lib.nameValuePair path {
|
|
hostPath = path;
|
|
isReadOnly = true;
|
|
}
|
|
) cfg.secrets
|
|
);
|
|
|
|
mountCollisions = lib.attrNames (builtins.intersectAttrs userMounts secretMounts);
|
|
|
|
limitConfig = lib.filterAttrs (_: v: v != null) {
|
|
MemoryMax = cfg.limits.memory;
|
|
CPUQuota = cfg.limits.cpu;
|
|
TasksMax = cfg.limits.tasksMax;
|
|
};
|
|
|
|
createdMounts = lib.filterAttrs (_guestPath: m: m.create != null) cfg.mounts;
|
|
mountCreateScript = lib.concatStringsSep "\n" (
|
|
mapAttrsToList (
|
|
_guestPath: m:
|
|
let
|
|
create = m.create;
|
|
in
|
|
''
|
|
${config.system.path}/bin/install -d -o ${escapeShellArg (toString create.owner)} -g ${escapeShellArg create.group} -m ${escapeShellArg create.mode} ${escapeShellArg m.hostPath}
|
|
''
|
|
) createdMounts
|
|
);
|
|
|
|
guestNet =
|
|
{ lib, ... }:
|
|
{
|
|
config = lib.mkIf networked {
|
|
networking.useNetworkd = true;
|
|
networking.useHostResolvConf = false;
|
|
|
|
systemd.network.networks."20-eth0" = {
|
|
matchConfig.Name = "eth0";
|
|
linkConfig.MACAddress = cfg.mac;
|
|
networkConfig.DHCP = "yes";
|
|
};
|
|
};
|
|
};
|
|
in
|
|
{
|
|
options = lib.setAttrByPath optionPath {
|
|
enable = lib.mkEnableOption "the ${name} guest, run in its own nested container";
|
|
backend = lib.mkOption {
|
|
type = lib.types.enum [
|
|
"container"
|
|
"microvm"
|
|
];
|
|
default = "container";
|
|
description = ''
|
|
How the guest is realized. `container` runs the guest as a
|
|
systemd-nspawn nested container. `microvm` is reserved for a future
|
|
hard-isolation backend and is not built yet.
|
|
'';
|
|
};
|
|
vlan = lib.mkOption {
|
|
type = lib.types.nullOr (lib.types.ints.between 1 4094);
|
|
default = null;
|
|
example = 10;
|
|
description = ''
|
|
The tagged VLAN this guest lives on. The guest attaches to its host's
|
|
`br-vlan<id>` bridge for that VLAN. Left null, the guest keeps a
|
|
private network with no bridge attachment. The id must be one of the
|
|
host's `modules.network.vlans.ids`.
|
|
'';
|
|
};
|
|
mac = lib.mkOption {
|
|
type = lib.types.str;
|
|
default = deriveMac name;
|
|
defaultText = lib.literalMD "a stable address derived from the guest's namespace path";
|
|
example = "bc:24:11:00:00:01";
|
|
description = ''
|
|
The guest's MAC address on its VLAN, pinned inside the guest by its
|
|
own networkd. Set it to reuse an existing address so a router's DHCP
|
|
reservation keeps working. Left unset, a stable address is derived
|
|
from the guest's namespace path in the locally-administered range.
|
|
'';
|
|
};
|
|
address = lib.mkOption {
|
|
type = lib.types.nullOr lib.types.str;
|
|
default = null;
|
|
example = "10.23.20.126";
|
|
description = ''
|
|
Expected IP address assigned outside NixOS for this guest.
|
|
Left null, this guest contributes no address to the address registry.
|
|
'';
|
|
};
|
|
reverseProxy = {
|
|
enable = lib.mkEnableOption "a reverse-proxy route for this guest";
|
|
|
|
route = lib.mkOption {
|
|
type = self.lib.registry.definitions.route.type;
|
|
description = "Route registry entry published for this guest.";
|
|
};
|
|
};
|
|
mounts = lib.mkOption {
|
|
type = lib.types.attrsOf (
|
|
lib.types.submodule {
|
|
options = {
|
|
hostPath = lib.mkOption {
|
|
type = lib.types.str;
|
|
example = "/srv/media";
|
|
description = "The path on the host bind-mounted into the guest.";
|
|
};
|
|
readOnly = lib.mkOption {
|
|
type = lib.types.bool;
|
|
default = false;
|
|
description = ''
|
|
Mount the path read-only. Read-write by default, since a
|
|
service must write to the pool data it owns.
|
|
'';
|
|
};
|
|
create = lib.mkOption {
|
|
type = lib.types.nullOr (lib.types.submodule {
|
|
options = {
|
|
type = lib.mkOption {
|
|
type = lib.types.enum [ "directory" ];
|
|
default = "directory";
|
|
description = "Host path type to create before the guest starts.";
|
|
};
|
|
owner = lib.mkOption {
|
|
type = lib.types.oneOf [
|
|
lib.types.str
|
|
lib.types.ints.positive
|
|
];
|
|
description = "Owner assigned to the created host path.";
|
|
};
|
|
group = lib.mkOption {
|
|
type = lib.types.str;
|
|
description = "Group assigned to the created host path.";
|
|
};
|
|
mode = lib.mkOption {
|
|
type = lib.types.str;
|
|
example = "0770";
|
|
description = "Mode assigned to the created host path.";
|
|
};
|
|
};
|
|
});
|
|
default = null;
|
|
description = ''
|
|
Opt-in host path creation before the guest starts. Existing
|
|
paths are left enabled unless this is set, so served storage
|
|
roots can still be required to exist explicitly.
|
|
'';
|
|
};
|
|
};
|
|
}
|
|
);
|
|
default = { };
|
|
example = lib.literalExpression ''
|
|
{
|
|
"/data/media" = { hostPath = "/srv/media"; };
|
|
"/data/config" = {
|
|
hostPath = "/srv/config/jellyfin";
|
|
readOnly = true;
|
|
};
|
|
}
|
|
'';
|
|
description = ''
|
|
Host paths bind-mounted into the guest, keyed by the path they appear
|
|
at inside the guest, so a guest sees exactly the data it should at any
|
|
granularity — a single folder or a whole pool. Each mount is
|
|
read-write unless `readOnly` is set.
|
|
'';
|
|
};
|
|
secrets = lib.mkOption {
|
|
type = lib.types.listOf lib.types.str;
|
|
default = [ ];
|
|
example = [ "jellyfin-api-key" ];
|
|
description = ''
|
|
Names of the secrets this guest needs. The host is the sole
|
|
decryptor: it decrypts each named secret from its own sops files and
|
|
bind-mounts the plaintext file into the guest read-only at
|
|
`/run/secrets/<name>`, the same path it would occupy on a host, so a
|
|
service reads its credentials at a predictable location. The guest
|
|
names the files it wants and receives exactly those. It holds no age
|
|
key and decrypts nothing itself. Ownership carries across unchanged,
|
|
since the container maps ids one to one, so a secret owned by a uid on
|
|
the host is owned by that same uid inside the guest.
|
|
'';
|
|
};
|
|
limits = {
|
|
memory = lib.mkOption {
|
|
type = lib.types.nullOr lib.types.str;
|
|
default = null;
|
|
example = "2G";
|
|
description = ''
|
|
Cap on the guest's memory, applied to its unit as `MemoryMax`.
|
|
Accepts systemd size suffixes such as `512M` or `2G`. Left null,
|
|
the guest's memory is uncapped.
|
|
'';
|
|
};
|
|
cpu = lib.mkOption {
|
|
type = lib.types.nullOr lib.types.str;
|
|
default = null;
|
|
example = "150%";
|
|
description = ''
|
|
Cap on the guest's CPU, applied to its unit as `CPUQuota`, where
|
|
`100%` is one full core. Left null, the guest's CPU is uncapped.
|
|
'';
|
|
};
|
|
tasksMax = lib.mkOption {
|
|
type = lib.types.nullOr lib.types.ints.positive;
|
|
default = null;
|
|
example = 512;
|
|
description = ''
|
|
Cap on the number of processes and threads the guest may spawn,
|
|
applied to its unit as `TasksMax`. Left null, the task count is
|
|
uncapped.
|
|
'';
|
|
};
|
|
};
|
|
nesting = lib.mkOption {
|
|
type = lib.types.bool;
|
|
default = false;
|
|
description = ''
|
|
Grant the guest's interior the prerequisites to run Podman or other
|
|
OCI containers of its own. Off by default, so a guest cannot nest
|
|
containers. On, the guest's container gains the network-administration
|
|
capability its container runtime uses to build bridges and firewall
|
|
rules, along with the tun and fuse device nodes such a runtime reaches
|
|
for, so the interior's `virtualisation.oci-containers` works with
|
|
Podman as its default runtime.
|
|
'';
|
|
};
|
|
autoStart = lib.mkOption {
|
|
type = lib.types.bool;
|
|
default = true;
|
|
description = ''
|
|
Start the guest at boot. On by default. Disabled, the guest stays
|
|
defined and can be started on demand, but does not come up at boot.
|
|
'';
|
|
};
|
|
};
|
|
|
|
config = lib.mkIf cfg.enable {
|
|
sops.secrets = lib.genAttrs cfg.secrets (_: { });
|
|
|
|
registry.address.${config.networking.hostName}.${machineName} = lib.mkIf (cfg.address != null) cfg.address;
|
|
|
|
registry.route.${config.networking.hostName}.${machineName} = lib.mkIf cfg.reverseProxy.enable cfg.reverseProxy.route;
|
|
|
|
assertions = [
|
|
{
|
|
assertion = mountCollisions == [ ];
|
|
message = ''
|
|
guests.${name} maps a mount at ${lib.concatStringsSep ", " mountCollisions}, colliding with a secret bind-mounted at the same path. Rename the mount or the secret so each in-guest path is used once.
|
|
'';
|
|
}
|
|
{
|
|
assertion = cfg.backend == "container";
|
|
message = ''
|
|
guests.${name}.backend = "${cfg.backend}" is not implemented. Only the "container" backend is built; "microvm" is reserved for future work.
|
|
'';
|
|
}
|
|
{
|
|
assertion = !networked || lib.elem cfg.vlan config.modules.network.vlans.ids;
|
|
message = ''
|
|
guests.${name}.vlan = ${toString cfg.vlan} is not among its host's modules.network.vlans.ids (${lib.concatMapStringsSep ", " toString config.modules.network.vlans.ids}). Declare the VLAN on the host or correct the guest's placement.
|
|
'';
|
|
}
|
|
];
|
|
|
|
systemd.services."container@${machineName}" = lib.mkIf (cfg.backend == "container") (
|
|
lib.mkMerge [
|
|
{
|
|
serviceConfig = limitConfig;
|
|
preStart = lib.mkIf (createdMounts != { }) mountCreateScript;
|
|
}
|
|
(lib.mkIf networked (
|
|
let
|
|
bridgeDevice = "sys-subsystem-net-devices-${lib.replaceStrings [ "-" ] [ "\\x2d" ] (bridgeName cfg.vlan)}.device";
|
|
in
|
|
{
|
|
after = [ bridgeDevice ];
|
|
wants = [ bridgeDevice ];
|
|
}
|
|
))
|
|
]
|
|
);
|
|
|
|
containers.${machineName} = lib.mkIf (cfg.backend == "container") {
|
|
autoStart = cfg.autoStart;
|
|
privateNetwork = lib.mkDefault true;
|
|
hostBridge = lib.mkIf networked (bridgeName cfg.vlan);
|
|
privateUsers = lib.mkDefault "no";
|
|
additionalCapabilities = lib.optionals cfg.nesting [ "CAP_NET_ADMIN" ];
|
|
allowedDevices = lib.optionals cfg.nesting [
|
|
{
|
|
node = "/dev/net/tun";
|
|
modifier = "rwm";
|
|
}
|
|
{
|
|
node = "/dev/fuse";
|
|
modifier = "rwm";
|
|
}
|
|
];
|
|
|
|
bindMounts = userMounts // secretMounts;
|
|
|
|
inherit specialArgs;
|
|
|
|
config = {
|
|
imports =
|
|
moduleFiles
|
|
++ [
|
|
registry.module
|
|
inputs.sops-nix.nixosModules.sops
|
|
inputs.stylix.nixosModules.stylix
|
|
{
|
|
modules.guest.enable = true;
|
|
}
|
|
guestNet
|
|
interior
|
|
];
|
|
};
|
|
};
|
|
};
|
|
};
|
|
in
|
|
{
|
|
inherit deriveMac guest;
|
|
}
|