c2c61b6146
hive-c0re publishes this hive's status to the swarm queue as the OIDC client `hive-<name>`. Its secret came from `deploy.hive-controller.statusPublish.clientSecretFile`, which defaulted to authelia's minted file only on a host running both authelia and the queue. Every other hive had no secret and never published, so the controller showed it `never_reported`. Now `swarm-secret-publish`, beside authelia, also copies each hive's `hive-<name>` secret to `swarm/hives/<hive>/oidc/client`. Its policy already allows `swarm/hives/*`. hive-c0re reads that path under the hive's own store leaf, which the existing `swarm/hives/<hive>/*` grant covers, and holds the value in memory. The shared queue client no longer remembers a failed first connect for the life of the process. A failed attempt is retried with a backoff from 5s, doubling to a cap of 5 minutes; the dashboard banner stays up until an attempt succeeds. The two status publishers wait for the client instead of giving up on the first `None`, so a secret published after boot is picked up without a restart. Removed: the `statusPublish.clientSecretFile` option (both spellings, now removed options with a message), its same-host default, its LoadCredential, the assertion tying it to the other two coordinates, and `swarm_queue_client::QueueConfig::from_env`, whose only caller was this read. Publishing is now on wherever the queue URL and token endpoint are set and the hive holds a store leaf. Refs #5015
381 lines
17 KiB
Nix
381 lines
17 KiB
Nix
# `checks.module-eval-secret-publisher` — see ./lib.nix for the shared
|
|
# rationale (why this suite exists, naming convention, "evaluates
|
|
# not executes").
|
|
{
|
|
pkgs,
|
|
lib,
|
|
self,
|
|
nixosSystem,
|
|
}:
|
|
let
|
|
inherit
|
|
(import ./lib.nix {
|
|
inherit
|
|
pkgs
|
|
lib
|
|
self
|
|
nixosSystem
|
|
;
|
|
})
|
|
hive
|
|
hiveWithController
|
|
runGroup
|
|
;
|
|
|
|
# The IdP and the store on one machine: the shape where minted plaintext and
|
|
# a store identity are both present without an operator placing anything.
|
|
# Two hives in the roster, because the publisher walks it — an arm written
|
|
# against a single-hive fixture passes on a hardcoded name.
|
|
secretPublisherHere = hive {
|
|
deploy.bao.enable = true;
|
|
deploy.authelia.enable = true;
|
|
swarm.hives.h2.domain = "h2.t.local";
|
|
};
|
|
|
|
# The IdP with no store on the box and a leaf placed by hand, which is the
|
|
# deployment this unit exists for: authelia is the one host the store is
|
|
# guaranteed not to share once either has a machine of its own.
|
|
#
|
|
# ⚠️ `enable` is deliberately NOT set here: leaving it unset is what makes
|
|
# this fixture exercise the default rather than mask it.
|
|
secretPublisherRemote = hive {
|
|
deploy.authelia.enable = true;
|
|
deploy.swarm-secret-publisher.baoClientCertFile = "/etc/pki/publisher.pem";
|
|
deploy.swarm-secret-publisher.baoClientKeyFile = "/etc/pki/publisher-key.pem";
|
|
};
|
|
|
|
# The same IdP with the identity taken away. Minting the secrets is not being
|
|
# able to publish them, and this is the arm that separates the two.
|
|
secretPublisherNoIdentity = hive { deploy.authelia.enable = true; };
|
|
# Duplicated from grafana.nix — a case here needs it too.
|
|
|
|
# The same UI with the IdP on ANOTHER host and a store leaf placed by hand.
|
|
# Knowing an IdP is not running one: `swarm.authelia.url` is what says this
|
|
# swarm has SSO, and nothing about this host does. Identical to the fixture
|
|
# above in everything the delivery path reads, which is the point.
|
|
grafanaRemoteAuthelia = hive {
|
|
deploy.grafana.enable = true;
|
|
deploy.grafana.plugins = [ ];
|
|
deploy.grafana.package = pkgs.emptyDirectory;
|
|
swarm.authelia.url = "https://auth.example.invalid";
|
|
deploy.bao.clientCertFile = "/etc/pki/bao-client.pem";
|
|
deploy.bao.clientKeyFile = "/etc/pki/bao-client-key.pem";
|
|
};
|
|
# Duplicated from swarm-otel-core.nix — a case here needs it too.
|
|
|
|
# The same collector with the IdP on ANOTHER host and a store leaf placed by
|
|
# hand. Identical to the fixture above in everything the delivery path
|
|
# reads, which is the point.
|
|
otelBaoRemoteAuthelia = hive {
|
|
deploy.swarm-otel.enable = true;
|
|
swarm.authelia.url = "https://auth.example.invalid";
|
|
deploy.bao.clientCertFile = "/etc/pki/bao-client.pem";
|
|
deploy.bao.clientKeyFile = "/etc/pki/bao-client-key.pem";
|
|
};
|
|
# Duplicated from core-toggle.nix — a case here needs it too.
|
|
|
|
bare = hive { };
|
|
# Duplicated from bao-matrix-reader.nix — a case here needs it too.
|
|
|
|
# The store and a service that reads from it, versus the store alone. The
|
|
# pair is what makes the reader's absence arm mean anything.
|
|
baoWithMatrix = hiveWithController {
|
|
deploy.bao.enable = true;
|
|
deploy.matrix.enable = true;
|
|
};
|
|
cases = [
|
|
{
|
|
# Each hive's hive-c0re reads this exact path
|
|
# (`swarm_secret_client::queue::hive_client_path`, pinned by that crate's
|
|
# own test), for every hive in the roster, not only the one this host is.
|
|
# The agents' client beside it stays a separate path.
|
|
name = "the publisher writes every hive's own client under that hive's prefix";
|
|
ok =
|
|
let
|
|
s = secretPublisherHere.systemd.services.swarm-secret-publish.script;
|
|
in
|
|
lib.all
|
|
(h: lib.hasInfix "secret/swarm/hives/${h}/oidc/client" s && lib.hasInfix "/hive-${h}.secret" s)
|
|
[
|
|
"h1"
|
|
"h2"
|
|
]
|
|
&& lib.hasInfix "secret/swarm/hives/h1/queue/agent" s;
|
|
}
|
|
{
|
|
# The controller reads this exact path
|
|
# (`swarm_secret_client::queue::controller_client_path`, pinned by that
|
|
# crate's own test). Under `controller/`, which no hive reads: this
|
|
# client may read every hive's status.
|
|
name = "the publisher writes the controller's client under controller/, never services/";
|
|
ok =
|
|
let
|
|
s = secretPublisherHere.systemd.services.swarm-secret-publish.script;
|
|
in
|
|
lib.hasInfix "secret/swarm/controller/swarm-controller/oidc/client" s
|
|
&& lib.hasInfix "/swarm-controller.secret" s
|
|
&& !(lib.hasInfix "secret/swarm/services/swarm-controller" s);
|
|
}
|
|
{
|
|
# Both ends of a wire nothing at eval time carries end to end: the
|
|
# publisher on authelia's host writes the path the reader on Grafana's host
|
|
# reads, and the two files agree only because both compose it from the same
|
|
# swarm-wide client id.
|
|
name = "the publisher writes the swarm service path grafana reads";
|
|
ok = lib.hasInfix "secret/swarm/services/swarm-grafana/oidc/client" (
|
|
secretPublisherHere.systemd.services.swarm-secret-publish.script
|
|
);
|
|
}
|
|
{
|
|
# Registering the client cannot live where the rest of grafana's module
|
|
# lives: that block is gated on this host RUNNING grafana, so on the split
|
|
# deployment nothing registered the client, authelia minted no secret, and
|
|
# every layer below had nothing to carry. The second arm is the control —
|
|
# a host with no IdP registers nothing.
|
|
name = "the swarm's grafana client is registered wherever authelia runs";
|
|
ok =
|
|
let
|
|
clients = m: map (c: c.id) m.services.hyperhive.swarm.authelia.oidc.clients;
|
|
in
|
|
lib.elem "swarm-grafana" (clients secretPublisherHere)
|
|
&& !(lib.elem "swarm-grafana" (clients grafanaRemoteAuthelia));
|
|
}
|
|
{
|
|
# The collector's half of the same property: the client is not gated on
|
|
# `deploy.swarm-otel.enable`, which would let a split deployment register
|
|
# it nowhere, so authelia would mint nothing to publish.
|
|
name = "the swarm's collector client is registered wherever authelia runs";
|
|
ok =
|
|
let
|
|
clients = m: map (c: c.id) m.services.hyperhive.swarm.authelia.oidc.clients;
|
|
in
|
|
lib.elem "swarm-collector" (clients secretPublisherHere)
|
|
&& !(lib.elem "swarm-collector" (clients otelBaoRemoteAuthelia));
|
|
}
|
|
{
|
|
# Registration follows authelia, not the service: the IdP host below runs
|
|
# no controller, queue or homeserver (the first arms), and still lists all
|
|
# three clients. The last arm is the control — a host with no IdP lists
|
|
# none of them.
|
|
name = "an authelia host running no controller, queue or homeserver registers all three clients";
|
|
ok =
|
|
let
|
|
d = secretPublisherRemote.services.hyperhive.deploy;
|
|
clients = m: map (c: c.id) m.services.hyperhive.swarm.authelia.oidc.clients;
|
|
byId =
|
|
id:
|
|
lib.findFirst (
|
|
c: c.id == id
|
|
) null secretPublisherRemote.services.hyperhive.swarm.authelia.oidc.clients;
|
|
controller = byId "swarm-controller";
|
|
nats = byId "swarm-nats";
|
|
matrix = byId "tuwunel";
|
|
in
|
|
!d.swarm-controller.enable
|
|
&& !d.nats.enable
|
|
&& !d.matrix.enable
|
|
&& controller.kind == "machine"
|
|
&& controller.audience == [ "swarm-controller" ]
|
|
&& nats.kind == "machine"
|
|
&&
|
|
matrix.redirectUris == [
|
|
"https://chat.t.local/_matrix/client/unstable/login/sso/callback/tuwunel"
|
|
]
|
|
&& matrix.tokenEndpointAuthMethod == "client_secret_post"
|
|
&& !(lib.any (id: lib.elem id (clients grafanaRemoteAuthelia)) [
|
|
"swarm-controller"
|
|
"swarm-nats"
|
|
"tuwunel"
|
|
]);
|
|
}
|
|
{
|
|
# The other half of the queue's and the homeserver's one route: the
|
|
# publisher on an IdP host that runs neither carries both secrets to the
|
|
# paths their readers fetch.
|
|
name = "the publisher on an authelia host carries the queue's and homeserver's secrets";
|
|
ok =
|
|
let
|
|
s = secretPublisherRemote.systemd.services.swarm-secret-publish.script;
|
|
in
|
|
lib.hasInfix "secret/swarm/services/swarm-nats/oidc/client" s
|
|
&& lib.hasInfix "/swarm-nats.secret" s
|
|
&& lib.hasInfix "secret/swarm/services/tuwunel/oidc/client" s
|
|
&& lib.hasInfix "/tuwunel.secret" s;
|
|
}
|
|
{
|
|
# Both ends of a wire nothing at eval time carries end to end: the
|
|
# publisher on authelia's host writes the path the reader on the
|
|
# collector's host reads, and the two files agree only because both
|
|
# compose it from the same swarm-wide client id. `secretPublisherHere`
|
|
# already grew this client when `serviceClientIds` did.
|
|
name = "the publisher writes the swarm service path the collector reads";
|
|
ok = lib.hasInfix "secret/swarm/services/swarm-collector/oidc/client" (
|
|
secretPublisherHere.systemd.services.swarm-secret-publish.script
|
|
);
|
|
}
|
|
{
|
|
# The third swarm service on that list, and the one whose absence is
|
|
# hardest to see: the store's own forwarder holds a client authelia
|
|
# registers and mints for, so every layer above looks complete while
|
|
# the one hop that CARRIES the value skips it and the reader on the
|
|
# store's host waits forever on a path nothing writes.
|
|
name = "the publisher carries the store forwarder's secret too";
|
|
ok = lib.hasInfix "secret/swarm/services/swarm-bao-collector/oidc/client" (
|
|
secretPublisherHere.systemd.services.swarm-secret-publish.script
|
|
);
|
|
}
|
|
{
|
|
# The store's UI login: authelia registers the client with the callback
|
|
# the store's `oidc` role allows, and the publisher carries its secret
|
|
# to the path `swarm-bao-operator-viewer-policy` reads. Not registered
|
|
# where authelia is not.
|
|
name = "the store UI's client is registered interactive at its callback, and the publisher carries its secret";
|
|
ok =
|
|
let
|
|
ui = lib.findFirst (
|
|
c: c.id == "swarm-bao-ui"
|
|
) null secretPublisherHere.services.hyperhive.swarm.authelia.oidc.clients;
|
|
in
|
|
ui != null
|
|
&& ui.kind == "interactive"
|
|
&& ui.redirectUris == [ "https://bao-ui.t.local/ui/vault/auth/oidc/oidc/callback" ]
|
|
&& lib.hasInfix "secret/swarm/services/swarm-bao-ui/oidc/client" (
|
|
secretPublisherHere.systemd.services.swarm-secret-publish.script
|
|
)
|
|
&& !(lib.any (
|
|
c: c.id == "swarm-bao-ui"
|
|
) grafanaRemoteAuthelia.services.hyperhive.swarm.authelia.oidc.clients);
|
|
}
|
|
{
|
|
# The same hole the controller's case above names, open a second time: the
|
|
# PKI script grew a third leaf and no case read it.
|
|
name = "the store mints a leaf for the secret publisher, and the publisher is pointed at it";
|
|
ok =
|
|
let
|
|
m = secretPublisherHere;
|
|
p = m.services.hyperhive.deploy.swarm-secret-publisher;
|
|
in
|
|
lib.hasInfix "secret-publisher.pem" m.systemd.services.swarm-bao-pki.script
|
|
&& p.baoClientCertFile == "/var/lib/swarm-bao-pki/secret-publisher.pem"
|
|
&& p.baoClientKeyFile == "/var/lib/swarm-bao-pki/secret-publisher-key.pem";
|
|
}
|
|
{
|
|
# mara caught this by reading, which means no arm existed for it: the
|
|
# default asked `authelia.enable && bao.enable`, so the split deployment
|
|
# this unit is FOR defaulted off and published nothing, silently.
|
|
#
|
|
# The second clause is the control. Without it this passes on a default
|
|
# of plain `true`, which would be a different bug with the same symptom
|
|
# — an IdP-less host claiming it publishes secrets it never mints.
|
|
name = "the publisher defaults on where secrets are minted, whether or not the store is local";
|
|
ok =
|
|
secretPublisherRemote.services.hyperhive.deploy.swarm-secret-publisher.enable
|
|
&& !bare.services.hyperhive.deploy.swarm-secret-publisher.enable;
|
|
}
|
|
{
|
|
# The one security property of this unit, and why its push cannot be
|
|
# rewritten into the obvious shape: `bao` is an external binary, so an
|
|
# argument is world-readable in /proc for the life of the call.
|
|
# `value=@<path>` hands it the path and bao opens the file itself.
|
|
#
|
|
# The second arm is what makes the first mean anything — `value=@` can
|
|
# sit one line above a command substitution that put the plaintext in
|
|
# argv anyway.
|
|
#
|
|
# ⚠️ Comments are stripped first, and that is not tidiness. A `script`
|
|
# renders its own comments into the text, and this unit's comments name
|
|
# the hazard verbatim so the next editor does not reintroduce it. Without
|
|
# the strip this case reads that warning and fails — a check the artifact
|
|
# defeats by DESCRIBING the thing it is checked for.
|
|
name = "the publisher hands bao the secret's path, never the secret";
|
|
ok =
|
|
let
|
|
s = secretPublisherHere.systemd.services.swarm-secret-publish.script;
|
|
code = lib.concatStringsSep "\n" (
|
|
lib.filter (l: builtins.match "[[:space:]]*#.*" l == null) (lib.splitString "\n" s)
|
|
);
|
|
in
|
|
lib.hasInfix "value=@" code && !(lib.hasInfix "$(cat" code);
|
|
}
|
|
{
|
|
# Two ends of a wire nothing at eval time carries end to end: this is the
|
|
# path `swarm_secret_client::queue` resolves for the reader. Both hives
|
|
# are asserted, so a publisher that knew one name rather than the roster
|
|
# fails here rather than on the second hive ever added to a swarm.
|
|
name = "the publisher writes every hive in the roster to that hive's own queue path";
|
|
ok =
|
|
let
|
|
s = secretPublisherHere.systemd.services.swarm-secret-publish.script;
|
|
in
|
|
lib.hasInfix "secret/swarm/hives/h1/queue/agent" s
|
|
&& lib.hasInfix "secret/swarm/hives/h2/queue/agent" s;
|
|
}
|
|
{
|
|
# A property of the SET, not of one unit: both of these authenticate by
|
|
# certificate, and `BAO_CLIENT_CERT` is transport rather than identity, so
|
|
# a script that reaches `bao kv` without a token asks a token helper this
|
|
# host does not carry and fails before the store ever answers. `-token-only`
|
|
# is what keeps the token off the helper on the way back out.
|
|
#
|
|
# Ordering, not presence: the login has to come first, so the check is
|
|
# that nothing before it is a data command. Comments are stripped because
|
|
# both units explain this in prose directly above the code.
|
|
name = "the cert-identity bao units log in before their first read or write, and keep the token out of the helper";
|
|
ok =
|
|
let
|
|
code =
|
|
s:
|
|
lib.concatStringsSep "\n" (
|
|
lib.filter (l: builtins.match "[[:space:]]*#.*" l == null) (lib.splitString "\n" s)
|
|
);
|
|
holdsTokenFirst =
|
|
s:
|
|
let
|
|
c = code s;
|
|
in
|
|
lib.hasInfix "bao login" c
|
|
&& lib.hasInfix "-token-only" c
|
|
&& !(lib.hasInfix "bao kv" (lib.head (lib.splitString "bao login" c)));
|
|
in
|
|
holdsTokenFirst secretPublisherHere.systemd.services.swarm-secret-publish.script
|
|
&& holdsTokenFirst baoWithMatrix.systemd.services.swarm-bao-queue-agent.script
|
|
# Controls, so a clean verdict above means something. In order: a bare
|
|
# read is refused, a read placed before the login is refused, and a
|
|
# login that exists only in a comment is refused — that last one is the
|
|
# arm the comment-stripping exists for.
|
|
&& !(holdsTokenFirst "bao kv get -field=value secret/x")
|
|
&& !(holdsTokenFirst "bao kv get secret/x\nBAO_TOKEN=\"$(bao login -method=cert -token-only)\"")
|
|
&& !(holdsTokenFirst "# bao login -method=cert -token-only goes here\nbao kv get secret/x")
|
|
&& holdsTokenFirst "BAO_TOKEN=\"$(bao login -method=cert -token-only)\"\nbao kv get secret/x";
|
|
}
|
|
{
|
|
# The doctrine three glue files state, as a property a rewrite has to
|
|
# keep: a client is defined by holding a certificate the store accepts,
|
|
# never by standing next to the store. Gating this on `deploy.bao.enable`
|
|
# would have left the unit rendering only on the one deployment that has
|
|
# no use for it.
|
|
name = "a publisher holding an identity runs on a host with no store";
|
|
ok =
|
|
let
|
|
m = secretPublisherRemote;
|
|
in
|
|
!m.services.hyperhive.deploy.bao.enable
|
|
&& (m.systemd.services ? swarm-secret-publish)
|
|
&& (m.systemd.paths ? swarm-secret-publish);
|
|
}
|
|
{
|
|
# What makes the arm above able to fail. Minting the secrets is not being
|
|
# able to publish them: with no certificate the unit would fail a TLS
|
|
# handshake on every rotation, so it must not exist at all.
|
|
name = "an IdP host with no store identity renders no publisher";
|
|
ok =
|
|
let
|
|
m = secretPublisherNoIdentity;
|
|
in
|
|
m.services.hyperhive.deploy.authelia.enable
|
|
&& !(m.systemd.services ? swarm-secret-publish)
|
|
&& !(m.systemd.paths ? swarm-secret-publish);
|
|
}
|
|
];
|
|
in
|
|
runGroup "secret-publisher" cases
|