11ec050ca8
`cmp` lives in diffutils, not coreutils, so the root-changed test exited 127 with "command not found". Inside `if ! cmp -s`, a 127 reads as "differs" and errexit never sees it, so `rootchanged` was 1 on every run and the trust-bundle rebuild it guards bounced `hive-tls-ca` after each issuance — the exact "only a changed one, or every boot would bounce a unit with nothing to do" the comment there rules out. Found in the journal of a hive that had just issued a leaf successfully: the unit logged "the services root changed" on a run where the store had left the issuer alone.
963 lines
46 KiB
Nix
963 lines
46 KiB
Nix
{
|
||
lib,
|
||
config,
|
||
pkgs,
|
||
...
|
||
}:
|
||
let
|
||
cfg = config.services.hyperhive.deploy.hive-controller.tls;
|
||
hyperhiveCfg = config.services.hyperhive;
|
||
gatewayCfg = config.services.hyperhive.gateway;
|
||
swarmCaCfg = config.services.hyperhive.swarm.ca;
|
||
domain = hyperhiveCfg.domain;
|
||
baoCfg = hyperhiveCfg.swarm.bao;
|
||
baoDeploy = hyperhiveCfg.deploy.bao;
|
||
|
||
# The endpoint the services leaf comes out of. Read off the store's own
|
||
# options rather than spelled here: ./swarm-bao.nix enables the mount,
|
||
# generates its root and writes the grant that names this exact path, and a
|
||
# second module composing its own is how the grant and the caller stop
|
||
# agreeing.
|
||
baoServicesPkiMount = baoDeploy.servicesPkiMountPath;
|
||
baoServicesPkiRole = baoDeploy.servicesPkiRoleName;
|
||
|
||
# Derived once in ./swarm.nix and read here + in ./swarm-bao.nix, so
|
||
# the names this leaf carries as SANs and the names the store's
|
||
# `pki/roles/swarm-services` is narrowed to cannot disagree.
|
||
swarmServiceDomains = hyperhiveCfg.swarm.serviceDomains;
|
||
|
||
# The host-managed hive CA is the trust anchor for self-signed mode.
|
||
# It is only stood up when the gateway actually serves a self-signed
|
||
# cert: the gateway must be in self-signed mode. `domain` is required
|
||
# (asserted in hive-network.nix), so the leaf SANs always have a
|
||
# domain to derive from. The self-signed condition is the gateway
|
||
# module's single source of truth (`gateway.useSelfSigned`): true when
|
||
# neither an operator cert (`tls.certDir`) nor ACME is set.
|
||
active = hyperhiveCfg.enable && gatewayCfg.useSelfSigned;
|
||
|
||
# How this hive's CA comes into existence when it is missing — and it
|
||
# is one of exactly two things, chosen by config rather than by what
|
||
# happens to be on disk.
|
||
#
|
||
# Issuing a sub-CA requires the swarm root's PRIVATE key, so it can
|
||
# only happen where that key legitimately lives: the single-host
|
||
# deployment that `swarm.ca.autoConfigure` describes. A host cannot
|
||
# infer that it is that host — a swarm's services and its hives can
|
||
# sit anywhere — so with the flag off this hive self-signs exactly as
|
||
# it always has, and an operator who wants it in the hierarchy
|
||
# installs the CA themselves. Falling back to self-signed rather than
|
||
# failing keeps a plain hive working out of the box; what it loses is
|
||
# membership of a swarm's trust, which is the correct thing to lose
|
||
# for a hive nobody has federated.
|
||
caGenScript =
|
||
if swarmCaCfg.autoConfigure then
|
||
''
|
||
# The root should exist — `swarm-ca.service` runs before this and
|
||
# is required by it. If it doesn't, something upstream failed and
|
||
# signing with a half-provisioned root would be worse than stopping.
|
||
if [ ! -s "$root" ] || [ ! -s "$rootk" ]; then
|
||
echo "swarm.ca.autoConfigure is set but there is no root CA key at $rootk" >&2
|
||
echo "(swarm-ca.service should have generated it) — refusing to issue a hive CA." >&2
|
||
exit 1
|
||
fi
|
||
|
||
echo "issuing fresh hive CA at $ca under the swarm root"
|
||
cacsr="$(mktemp "$d/ca.csr.XXXXXX")"
|
||
caext="$(mktemp "$d/ca.ext.XXXXXX")"
|
||
trap 'rm -f "$cacsr" "$caext"' EXIT
|
||
|
||
openssl req -newkey rsa:4096 -nodes -sha256 \
|
||
-keyout "$cak" -out "$cacsr" \
|
||
-subj "/CN=hive-ca ${domain}"
|
||
|
||
# printf (not a heredoc) so the ext-file lines carry no leading
|
||
# whitespace once nix has stripped the indented-string indent.
|
||
{
|
||
printf 'basicConstraints=critical,CA:TRUE,pathlen:0\n'
|
||
printf 'keyUsage=critical,keyCertSign,cRLSign\n'
|
||
printf 'subjectKeyIdentifier=hash\n'
|
||
printf 'authorityKeyIdentifier=keyid:always\n'
|
||
# The constraint is the point of the hierarchy, not a
|
||
# flourish: without it a leaked hive CA mints any name in
|
||
# the swarm, and it is verifiers that enforce this, not our
|
||
# good behaviour. The IP exclusions are not redundant — a
|
||
# DNS constraint says nothing about an iPAddress SAN, and a
|
||
# name type nobody constrained is a name type this CA is
|
||
# unconstrained for.
|
||
printf 'nameConstraints=critical,permitted;DNS:%s,excluded;IP:0.0.0.0/0.0.0.0,excluded;IP:0:0:0:0:0:0:0:0/0:0:0:0:0:0:0:0\n' \
|
||
${lib.escapeShellArg domain}
|
||
} > "$caext"
|
||
|
||
openssl x509 -req -in "$cacsr" -CA "$root" -CAkey "$rootk" \
|
||
-CAcreateserial -days ${toString cfg.caValidityDays} -sha256 \
|
||
-extfile "$caext" -out "$ca"
|
||
rm -f "$cacsr" "$caext"
|
||
trap - EXIT
|
||
''
|
||
else
|
||
''
|
||
echo "generating fresh self-signed hive CA at $ca"
|
||
openssl req -x509 -newkey rsa:4096 -nodes -sha256 \
|
||
-days ${toString cfg.caValidityDays} \
|
||
-keyout "$cak" -out "$ca" \
|
||
-subj "/CN=hive-ca ${domain}" \
|
||
-addext "basicConstraints=critical,CA:TRUE,pathlen:0" \
|
||
-addext "keyUsage=critical,keyCertSign,cRLSign"
|
||
'';
|
||
|
||
# Sign one leaf. Parameterised rather than hardcoded to `gateway.*`
|
||
# because there are now two: the hive's own leaf, issued by the hive
|
||
# CA, and the swarm-services leaf, issued by the services sub-CA that
|
||
# ./swarm-ca.nix maintains. Same ceremony, different issuer and names
|
||
# — and one script means the two cannot drift in how they are built.
|
||
#
|
||
# $1 stateDir $2 basename $3 CN $4 SAN list $5 issuer cert $6 issuer key
|
||
signLeafScript = pkgs.writeShellScript "hive-tls-sign-leaf" ''
|
||
set -euo pipefail
|
||
d="$1"
|
||
base="$2"
|
||
cn="$3"
|
||
sans="$4"
|
||
ca="$5"
|
||
cak="$6"
|
||
leaf="$d/$base.pem"
|
||
leafk="$d/$base-key.pem"
|
||
csr="$(mktemp "$d/$base.csr.XXXXXX")"
|
||
ext="$(mktemp "$d/$base.ext.XXXXXX")"
|
||
only="$(mktemp "$d/$base.leaf.XXXXXX")"
|
||
trap 'rm -f "$csr" "$ext" "$only"' EXIT
|
||
|
||
openssl req -newkey rsa:4096 -nodes -sha256 \
|
||
-keyout "$leafk" -out "$csr" \
|
||
-subj "/CN=$cn"
|
||
|
||
# printf (not a heredoc) so the ext-file lines carry no leading
|
||
# whitespace once nix has stripped the indented-string indent.
|
||
{
|
||
printf 'subjectAltName=%s\n' "$sans"
|
||
printf 'basicConstraints=critical,CA:FALSE\n'
|
||
printf 'keyUsage=critical,digitalSignature,keyEncipherment\n'
|
||
printf 'extendedKeyUsage=serverAuth\n'
|
||
} > "$ext"
|
||
|
||
openssl x509 -req -in "$csr" -CA "$ca" -CAkey "$cak" \
|
||
-CAcreateserial -days ${toString cfg.leafValidityDays} -sha256 \
|
||
-extfile "$ext" -out "$only"
|
||
|
||
# nginx serves this file verbatim, so it must carry the leaf AND its
|
||
# issuer: the hive CA is an intermediate under the swarm root, and a
|
||
# client that anchors on the root cannot build the middle of the
|
||
# chain by itself. Agents anchor on the hive CA directly and
|
||
# validated either way — the appended cert is what makes a swarm
|
||
# peer, or anything else holding only the root, work.
|
||
# Leaf first: both `ssl_certificate` and the `openssl x509 -in`
|
||
# expiry checks read the first cert in the file.
|
||
cat "$only" "$ca" > "$leaf"
|
||
chmod 0600 "$leafk"
|
||
chmod 0644 "$leaf"
|
||
'';
|
||
|
||
# The hive's own leaf: signed by the hive CA, covering the hive domain
|
||
# and its sub-domains.
|
||
#
|
||
# `forge.` and `matrix.` were listed here explicitly and both were
|
||
# redundant with the wildcard beside them — a wildcard covers exactly
|
||
# one label, and those are one label. Naming them read as policy
|
||
# ("these two services live under this leaf"), which is the reason they
|
||
# outlived it: a configured service name is no longer necessarily under
|
||
# this domain, and when it isn't, this is the one list it cannot join.
|
||
# The hive CA is `nameConstraints=permitted;DNS:<hive domain>`, and a
|
||
# violation invalidates the CERTIFICATE rather than the offending name
|
||
# — measured with openssl, not reasoned about — so one sibling name
|
||
# added here takes the leaf down for the dashboard and every other
|
||
# vhost sharing it. Configured service names get the swarm-services
|
||
# leaf below, whose sub-CA is constrained to exactly those names.
|
||
signHiveLeaf = ''
|
||
${signLeafScript} "$d" gateway ${lib.escapeShellArg domain} \
|
||
${lib.escapeShellArg "DNS:${domain},DNS:*.${domain}"} \
|
||
"$d/ca.pem" "$d/ca-key.pem"
|
||
'';
|
||
|
||
# Shared by every unit that decides whether to re-issue a leaf. It
|
||
# lives here rather than in one of them because the guards have to
|
||
# agree: they answer the same question at different times
|
||
# (`hive-tls-ca` at service activation, i.e. on the deploy;
|
||
# `hive-tls-resign` from a weekly timer for a host that stays up long
|
||
# enough to drift; `swarm-services-cert` for the leaf the store
|
||
# issues). A rule implemented in one and not the others is worse than
|
||
# one implemented in none — it looks fixed and only fires on whichever
|
||
# path you did not take, which is exactly how a corrected
|
||
# `serviceDomains` still served a stale leaf.
|
||
#
|
||
# Expects `$d` (state dir) to be set; defines `$leaf`-adjacent names and
|
||
# `covers`.
|
||
leafCoverage = ''
|
||
svcleaf="$d/swarm-services.pem"
|
||
svcroot="$d/swarm-services-root.pem"
|
||
hiveNames=${lib.escapeShellArg "${domain} *.${domain}"}
|
||
svcNames=${lib.escapeShellArg (lib.concatStringsSep " " swarmServiceDomains)}
|
||
|
||
# A hive with no configured service names has no services leaf to
|
||
# hold, and its absence there is the correct state rather than a
|
||
# stale one. Anywhere else it is expected: the leaf comes from the
|
||
# secret store's `pki` mount now, not from a sub-CA that exists on
|
||
# one host in the swarm, so "this host cannot issue it" is no longer
|
||
# one of the answers.
|
||
want_svc=${if swarmServiceDomains == [ ] then "0" else "1"}
|
||
|
||
# Expiry is not the only way a leaf goes wrong. One signed when the
|
||
# configured name set was smaller stays valid for its whole lifetime
|
||
# while omitting every name added since — so a config change can
|
||
# evaluate, build and deploy cleanly while the gateway keeps serving a
|
||
# certificate that does not cover the new service.
|
||
#
|
||
# Reads the names out of the CERTIFICATE, not a sidecar file: the pem
|
||
# is what nginx serves, and a bookkeeping file drifts from it the
|
||
# moment anyone replaces a leaf by hand.
|
||
covers() { # $1 = leaf, $2 = space-separated names it must carry
|
||
[ -s "$1" ] || return 1
|
||
_have="$(openssl x509 -in "$1" -noout -ext subjectAltName 2>/dev/null \
|
||
| tr ',' '\n' | sed -n 's/^[[:space:]]*DNS:\(.*\)$/\1/p' || true)"
|
||
[ -n "$_have" ] || return 1
|
||
_missing=0
|
||
# ⚠️ The hive leaf carries `*.<domain>`; without this the shell
|
||
# expands it against the cwd and the comparison silently tests a
|
||
# filename instead of a name.
|
||
set -f
|
||
for _n in $2; do
|
||
printf '%s\n' "$_have" | grep -qxF "$_n" || _missing=1
|
||
done
|
||
set +f
|
||
[ "$_missing" = 0 ]
|
||
}
|
||
|
||
# True when the leaf this host SIGNS is present and carries its
|
||
# configured names. Expiry is the callers' own business — they use
|
||
# different windows.
|
||
#
|
||
# ⚠️ The services leaf is deliberately NOT part of this any more, and
|
||
# the omission is load-bearing rather than a simplification. Its two
|
||
# callers sign under the hive CA's key; the services leaf comes out
|
||
# of the secret store, which neither of them can reach. A guard that
|
||
# went on reporting it stale would make `hive-tls-ca` re-sign the
|
||
# hive leaf forever over a file it has no way to fix. The
|
||
# `swarm-services-cert` unit below holds the same rule for that leaf,
|
||
# using the `covers` helper above so the two cannot drift.
|
||
leavesCoverNames() {
|
||
covers "$leaf" "$hiveNames"
|
||
}
|
||
'';
|
||
in
|
||
{
|
||
# Host-side TLS trust root for the self-signed gateway mode.
|
||
#
|
||
# A bare self-signed leaf would be its own trust anchor, so every
|
||
# regeneration would be a new anchor and every consumer (agents,
|
||
# federation peers) would have to re-trust on each rotation — and a
|
||
# runtime-generated, in-container cert can't be wired into an agent's
|
||
# build-time trust store at all.
|
||
#
|
||
# So the issuer is a long-lived **hive CA** held on the host. The
|
||
# gateway serves a **leaf** signed by that CA (via the `tls.certDir`
|
||
# bind-mount path); agents and federation peers trust the *CA* once,
|
||
# and leaf rotation never re-breaks them. See `docs/networking/gateway.md`
|
||
# ("Self-signed TLS").
|
||
#
|
||
# That CA is self-signed by default. Under
|
||
# `swarm.ca.autoConfigure` — the all-on-one-host case — it is instead
|
||
# an intermediate issued under the swarm root (./swarm-ca.nix owns the
|
||
# why) and name-constrained to this hive's domain, so it stays the
|
||
# anchor agents pin while a peer holding only the root can validate
|
||
# everything this hive serves. Either way an existing CA is left
|
||
# alone; see the issuance comment below.
|
||
|
||
options.services.hyperhive.deploy.hive-controller.tls = {
|
||
stateDir = lib.mkOption {
|
||
type = lib.types.str;
|
||
default = "/var/lib/hive-tls";
|
||
description = ''
|
||
Host directory holding the hive CA + gateway leaf cert for the
|
||
self-signed gateway mode. `ca.pem` (the anchor agents and
|
||
federation peers trust), `ca-key.pem` (0600, never leaves the
|
||
host), `gateway.pem` / `gateway-key.pem` (the leaf the gateway
|
||
container bind-mounts and nginx serves). Persistent so the CA
|
||
survives reboots — re-deriving it would re-break every consumer.
|
||
'';
|
||
};
|
||
|
||
caValidityDays = lib.mkOption {
|
||
type = lib.types.int;
|
||
default = 7300;
|
||
description = ''
|
||
Validity window of the hive CA in days (default ~20y). Kept long
|
||
and well beyond `leafValidityDays` so the CA outlives many leaf
|
||
rotations — the whole point of the CA is to be a stable anchor
|
||
that consumers trust once. The CA is regenerated only if missing
|
||
or already expired.
|
||
'';
|
||
};
|
||
|
||
baoClientCertFile = lib.mkOption {
|
||
type = lib.types.nullOr lib.types.str;
|
||
default = null;
|
||
example = "/var/lib/swarm-bao-pki/services-issuer.pem";
|
||
description = ''
|
||
Certificate `swarm-services-cert` presents to the secret store when it
|
||
asks for the swarm-services leaf the gateway serves.
|
||
|
||
Its subject has to be
|
||
{option}`services.hyperhive.deploy.bao.servicesIssuerCommonName` — cert
|
||
auth matches on the common name, and this is the one role whose policy
|
||
permits `pki/issue/swarm-services`.
|
||
|
||
A **separate** credential from
|
||
{option}`services.hyperhive.deploy.bao.clientCertFile`, which is this
|
||
hive's own reader identity and whose policy reads every secret the
|
||
hive is entitled to. A unit that renews one server certificate has no
|
||
business holding that.
|
||
|
||
On a hive that mints its own store PKI a glue module supplies the leaf
|
||
as a `mkDefault`; everywhere else it is the credential an operator
|
||
places, for the reason the store's own client certificate is.
|
||
|
||
A path, never a value.
|
||
'';
|
||
};
|
||
|
||
baoClientKeyFile = lib.mkOption {
|
||
type = lib.types.nullOr lib.types.str;
|
||
default = null;
|
||
example = "/var/lib/swarm-bao-pki/services-issuer-key.pem";
|
||
description = ''
|
||
Private key for
|
||
{option}`services.hyperhive.deploy.hive-controller.tls.baoClientCertFile`.
|
||
Both or neither — a certificate with no key authenticates nothing.
|
||
'';
|
||
};
|
||
|
||
leafValidityDays = lib.mkOption {
|
||
type = lib.types.int;
|
||
default = 30;
|
||
description = ''
|
||
Validity window of the gateway leaf cert in days (default 30).
|
||
Short-lived by design — ahead of the CA/Browser-Forum's move
|
||
toward ~47-day max lifetimes — which bounds the blast radius of a
|
||
leaf-key compromise. The leaf is re-signed by the (stable) CA
|
||
when it is missing or near expiry; because it shares the CA
|
||
anchor, a rotation does not disturb consumer trust. Agents and
|
||
federation peers validate against the CA, not browser CA/B-forum
|
||
limits. The weekly `hive-tls-resign` timer re-signs the leaf once
|
||
it is within half its validity of expiry and propagates the new
|
||
leaf into the running gateway, so a long-uptime host renews
|
||
automatically without a reboot.
|
||
'';
|
||
};
|
||
};
|
||
|
||
config = lib.mkIf active {
|
||
# 🚫 The "these service names are outside this hive's domain and this
|
||
# host cannot sign for them" warning is GONE, and its absence is the
|
||
# deliverable rather than a tidy-up. It fired on
|
||
# `!swarm.ca.autoConfigure` — i.e. "this host does not hold the swarm
|
||
# root key" — which was the whole reason a hive could end up serving
|
||
# its own leaf on a swarm-service name. The services leaf now comes
|
||
# from the secret store's `pki` mount, which every hive reaches over
|
||
# the network with its own identity, so holding the root key stopped
|
||
# being the thing that decides. Left in place it would warn, on every
|
||
# rebuild of every hive that is not the CA host, about a fallback
|
||
# that no longer happens.
|
||
|
||
# Generate (and rotate) the hive CA + gateway leaf before anything
|
||
# serves it. Idempotent: the CA is created once and reused; the leaf
|
||
# is re-signed on expiry under the same CA so the anchor is stable.
|
||
systemd.services.hive-tls-ca = {
|
||
description = "Generate hive CA + gateway leaf TLS cert (self-signed mode)";
|
||
wantedBy = [ "multi-user.target" ];
|
||
# The consumer is `hive-gateway-self-signed-cert`, which copies the
|
||
# leaf into the gateway's state dir at the mode nginx can read, and
|
||
# which nginx in turn `Requires=`. So this must run first or that
|
||
# copy fails under `set -eu` and takes nginx down with it — order
|
||
# against the unit that reads the file.
|
||
before = [ "hive-gateway-self-signed-cert.service" ];
|
||
requiredBy = [ "hive-gateway-self-signed-cert.service" ];
|
||
# The issuance below needs the swarm root key on disk. When this
|
||
# host generates it (single-host swarm) that unit must have run
|
||
# first; when the operator provides the material there is no unit
|
||
# to wait for, so the dependency is conditional rather than a unit
|
||
# that exists and does nothing.
|
||
#
|
||
# `swarm-services-cert` is NOT ordered against this unit in either
|
||
# direction, and the absence is load-bearing — see the cycle spelled
|
||
# out at that unit. It runs after the store's container, the container
|
||
# runs after this unit, so an edge back to here is a loop and systemd
|
||
# resolves a loop by dropping a job.
|
||
#
|
||
# What that costs: the trust bundle written at the end of this script
|
||
# anchors on every root a consumer must hold, and the services root is
|
||
# one of them, so on a first boot the `cat` below runs before that file
|
||
# exists and the bundle is one restart short of complete. The `if [ -s
|
||
# "$svcroot" ]` guard is what makes that state legal rather than fatal,
|
||
# and `swarm-services-cert` restarts this unit once the root it wrote
|
||
# is new — so the bundle converges instead of being a boot behind.
|
||
after = lib.optionals swarmCaCfg.autoConfigure [ "swarm-ca.service" ];
|
||
requires = lib.optionals swarmCaCfg.autoConfigure [ "swarm-ca.service" ];
|
||
path = [ pkgs.openssl ];
|
||
serviceConfig = {
|
||
Type = "oneshot";
|
||
RemainAfterExit = true;
|
||
UMask = "0077";
|
||
# Pin the journal identity (else it's the `script` store-path wrapper).
|
||
SyslogIdentifier = "hive-tls-ca";
|
||
};
|
||
script = ''
|
||
set -euo pipefail
|
||
d=${lib.escapeShellArg cfg.stateDir}
|
||
install -d -m 0755 "$d"
|
||
|
||
ca="$d/ca.pem"
|
||
cak="$d/ca-key.pem"
|
||
leaf="$d/gateway.pem"
|
||
leafk="$d/gateway-key.pem"
|
||
root=${lib.escapeShellArg "${swarmCaCfg.stateDir}/root.pem"}
|
||
rootk=${lib.escapeShellArg "${swarmCaCfg.stateDir}/root-key.pem"}
|
||
|
||
prev="$d/ca-previous.pem"
|
||
marker="$d/.swarm-ca-adopted"
|
||
|
||
# --- Adoption: a hive whose CA predates the swarm root.
|
||
#
|
||
# Runs ONLY where this host also owns the root (`autoConfigure`),
|
||
# because adoption invalidates an anchor that consumers already
|
||
# trust and they refresh on their own schedule. On one box that
|
||
# schedule is knowable; across hosts it is not, so there the
|
||
# operator does it and this unit only says so, loudly.
|
||
#
|
||
# Guarded by a marker rather than by the state of the world: the
|
||
# marker's ABSENCE is the trigger, so this fires once per hive
|
||
# instead of re-deciding every activation. That is the difference
|
||
# between a migration and a kicking machine.
|
||
if [ -s "$root" ] && [ -s "$ca" ] && [ ! -e "$marker" ] \
|
||
&& ! openssl verify -CAfile "$root" "$ca" >/dev/null 2>&1; then
|
||
${
|
||
if swarmCaCfg.autoConfigure then
|
||
''
|
||
echo "adopting the swarm CA: $ca does not chain to $root" >&2
|
||
# Keep the old CA as an anchor across the overlap. Consumers
|
||
# read the bundle, so adoption is additive before it is
|
||
# subtractive — agents pick up new trust only when their
|
||
# container restarts, which is a window even on one host.
|
||
cp "$ca" "$prev"
|
||
chmod 0644 "$prev"
|
||
rm -f "$ca" "$cak"
|
||
touch "$marker"''
|
||
else
|
||
''
|
||
echo "hive-tls: this hive's CA does not chain to the swarm root." >&2
|
||
echo " hive CA: $ca" >&2
|
||
echo " swarm root: $root" >&2
|
||
echo "Adopting the hierarchy is not automatic here: it invalidates an" >&2
|
||
echo "anchor that peers and agents on OTHER hosts still trust, and they" >&2
|
||
echo "refresh on their own schedule — only you know when that is safe." >&2
|
||
echo "To adopt: rm $ca $cak && systemctl restart hive-tls-ca.service" >&2
|
||
echo "To keep the current CA deliberately: touch $marker" >&2
|
||
exit 1''
|
||
}
|
||
fi
|
||
|
||
# --- CA: generated once and reused across leaf rotations, in
|
||
# whichever of the two shapes `caGenScript` selected.
|
||
# Regenerated only if missing or already expired (checkend 0).
|
||
# A new CA means every consumer must re-trust, so the leaf is
|
||
# dropped to force a re-sign under the fresh CA.
|
||
#
|
||
# An existing CA is never re-rooted here. A hive predating the
|
||
# swarm root carries a self-signed `ca.pem`, and swapping it for
|
||
# a swarm-issued one would break every consumer already trusting
|
||
# it — including agents, whose trust is refreshed only when their
|
||
# container restarts. Adopting the hierarchy on such a hive is
|
||
# therefore an operator step (drop the CA, let this unit
|
||
# re-issue), which is also what keeps this change non-disruptive
|
||
# to hives that never adopt it.
|
||
if [ ! -s "$ca" ] || [ ! -s "$cak" ] \
|
||
|| ! openssl x509 -in "$ca" -noout -checkend 0 >/dev/null 2>&1; then
|
||
${caGenScript}
|
||
chmod 0600 "$cak"
|
||
chmod 0644 "$ca"
|
||
rm -f "$leaf" "$leafk"
|
||
fi
|
||
|
||
# --- Leaf: (re)sign when missing, within 30 days of expiry, or no
|
||
# longer covering the configured names, always under the current
|
||
# (stable) CA.
|
||
${leafCoverage}
|
||
|
||
# ⚠️ This is the guard that runs ON THE DEPLOY — `hive-tls-resign`
|
||
# only fires from a weekly timer, so a rule enforced only there is
|
||
# up to a week late and does nothing for the rebuild that changed
|
||
# the names in the first place.
|
||
#
|
||
resign=0
|
||
{ [ -s "$leaf" ] && [ -s "$leafk" ]; } || resign=1
|
||
openssl x509 -in "$leaf" -noout -checkend 2592000 >/dev/null 2>&1 || resign=1
|
||
leavesCoverNames || resign=1
|
||
|
||
if [ "$resign" = 1 ]; then
|
||
echo "signing gateway leaf at $leaf (missing, near expiry, or missing a configured name)"
|
||
${signHiveLeaf}
|
||
fi
|
||
|
||
# --- Trust bundle: what a consumer must TRUST, as opposed to
|
||
# `ca.pem`, which is what this host SIGNS with. Why they stopped
|
||
# being the same file, and why `ca-previous.pem` stays in the set
|
||
# after an adoption, are in docs/swarm/ca.md. Three constraints
|
||
# the code cannot state:
|
||
#
|
||
# Written IN PLACE, never renamed into position — containers
|
||
# bind-mount this file and a bind mount follows the inode, so a
|
||
# rename leaves every consumer holding the old one.
|
||
#
|
||
# Dropping `ca-previous.pem` is deliberately NOT done here:
|
||
# "long enough" is a deployment fact, not a unit's call.
|
||
#
|
||
# Built as an array with `if` guards, not
|
||
# `[ -s f ] && anchors+=(f)`: under `set -e` an && list whose test
|
||
# fails IS a failing command and kills the unit — on exactly the
|
||
# hive where the optional file is legitimately absent. The
|
||
# reflexive `|| true` is worse; it also swallows a real failure to
|
||
# read the hive CA.
|
||
#
|
||
# `swarm-services-root.pem` joins the set for the reason the swarm
|
||
# root is in it: it is an ANCHOR a consumer terminates at, not an
|
||
# intermediate. It is also what keeps this change from being a
|
||
# flag day — the swarm root stays in the bundle beside it, so a
|
||
# leaf still chaining to the old services sub-CA and one issued by
|
||
# the store both verify against the same file, and a hive can be
|
||
# rebuilt before or after its peers.
|
||
bundle="$d/trust-bundle.pem"
|
||
anchors=("$ca")
|
||
if [ -s "$prev" ]; then anchors+=("$prev"); fi
|
||
if [ -s "$root" ]; then anchors+=("$root"); fi
|
||
if [ -s "$svcroot" ]; then anchors+=("$svcroot"); fi
|
||
cat "''${anchors[@]}" > "$bundle"
|
||
chmod 0644 "$bundle"
|
||
'';
|
||
};
|
||
|
||
# Weekly re-sign of the gateway leaf so short-lived leaves renew
|
||
# without depending on a reboot.
|
||
#
|
||
# `hive-tls-ca` only re-signs at service activation (boot/rebuild); a
|
||
# long-uptime host would otherwise let a 30-day leaf lapse silently.
|
||
# This service re-signs the leaf directly (not by bouncing hive-tls-ca)
|
||
# and propagates the new leaf to nginx when the file actually changed.
|
||
#
|
||
# Propagation mechanism: nginx serves a *copy* of the leaf, written by
|
||
# `hive-gateway-self-signed-cert` at the mode nginx can read. Re-signing
|
||
# the source therefore changes nothing on its own — the copy has to be
|
||
# remade and nginx reloaded, which is what the two calls below do.
|
||
#
|
||
# ⚠️ Neither call is `|| true`: a swallowed propagation failure means
|
||
# the leaf rotates on disk while nginx keeps serving the old copy
|
||
# until it expires, with this unit reporting success the whole time.
|
||
# A failure here must fail the timer.
|
||
systemd.services.hive-tls-resign = {
|
||
description = "Re-sign the gateway TLS leaf and reload nginx";
|
||
# hive-tls-ca must have run first so the CA key exists before we try
|
||
# to re-sign under it. On first boot `Persistent=true` on the weekly
|
||
# timer fires immediately; without this ordering the resign could race
|
||
# the CA initialisation and fail with "no such file" on the CA key.
|
||
after = [ "hive-tls-ca.service" ];
|
||
path = [
|
||
pkgs.openssl
|
||
pkgs.coreutils
|
||
pkgs.systemd
|
||
];
|
||
serviceConfig = {
|
||
Type = "oneshot";
|
||
UMask = "0077";
|
||
SyslogIdentifier = "hive-tls-resign";
|
||
};
|
||
script = ''
|
||
set -euo pipefail
|
||
d=${lib.escapeShellArg cfg.stateDir}
|
||
leaf="$d/gateway.pem"
|
||
|
||
# ⚠️ EVERY leaf this host SIGNS must be covered here. A leaf that
|
||
# first-boot issuance creates and this unit does not know about
|
||
# looks perfect for its entire validity and then expires with no
|
||
# warning — the failure is invisible until it is total. The name
|
||
# checks come from the shared snippet, so this unit and
|
||
# `hive-tls-ca` cannot disagree about what a good leaf is.
|
||
#
|
||
# The services leaf is not one of them any longer: it is issued
|
||
# by the secret store, whose key this unit does not hold and
|
||
# cannot re-sign under. Renewing it is `swarm-services-cert`'s
|
||
# job, at boot, which is a cadence its own issue owns.
|
||
${leafCoverage}
|
||
|
||
# Re-sign only when a leaf is within half its validity of expiry.
|
||
# The weekly cadence catches this window well before one lapses.
|
||
halflife=$(( ${toString cfg.leafValidityDays} * 86400 / 2 ))
|
||
|
||
fresh() { # a leaf is fresh if it exists and is not near expiry
|
||
[ -s "$1" ] && openssl x509 -in "$1" -noout -checkend "$halflife" >/dev/null 2>&1
|
||
}
|
||
|
||
if fresh "$leaf" && leavesCoverNames; then
|
||
echo "leaves valid, and covering the configured names — no resign needed"
|
||
exit 0
|
||
fi
|
||
|
||
echo "a leaf is missing, near expiry, or missing a configured name — re-signing"
|
||
before="$(sha256sum "$leaf" 2>/dev/null || true)"
|
||
|
||
${signHiveLeaf}
|
||
|
||
after="$(sha256sum "$leaf" 2>/dev/null || true)"
|
||
if [ "$before" != "$after" ]; then
|
||
echo "gateway leaf rotated — re-importing and reloading nginx"
|
||
systemctl restart hive-gateway-self-signed-cert.service
|
||
systemctl reload nginx.service
|
||
else
|
||
echo "gateway leaf unchanged (already up to date)"
|
||
fi
|
||
'';
|
||
};
|
||
|
||
# The swarm-services leaf, issued by the secret store's `pki` mount.
|
||
#
|
||
# ⚠️ This unit replaces a chain, not a command. What used to happen
|
||
# was two openssl hops on whichever host held the swarm root key: a
|
||
# name-constrained `swarm-services` sub-CA (../swarm-ca.nix), then a
|
||
# leaf signed under it here. Both are gone. The store's
|
||
# `pki/roles/swarm-services` carries the same narrowing as an
|
||
# `allowed_domains` list enforced at issue time, so the intermediate
|
||
# that used to encode it in x509 `nameConstraints` has nothing left
|
||
# to express — and with the root inside the mount there is nothing
|
||
# for it to be an intermediate OF.
|
||
#
|
||
# The names it may carry are not this unit's to assert: the role
|
||
# refuses anything outside `allowed_domains`, which is read from the
|
||
# same `swarm.serviceDomains` the SANs below are built from. A
|
||
# mismatch is a refusal from the store naming the offending name,
|
||
# not a certificate quietly issued for something nobody configured.
|
||
systemd.services.swarm-services-cert = {
|
||
description = "Issue the swarm-services TLS leaf from the secret store's PKI";
|
||
wantedBy = [ "multi-user.target" ];
|
||
# ⚠️ The ordering the old shape got by ACCIDENT, written down.
|
||
# Nothing used to declare "no TLS until the store is up" — it held
|
||
# because `swarm-services-ca.service` happened to block the gateway.
|
||
# Now it is a real edge: the gateway's certificate comes out of the
|
||
# store, so the store being up is a precondition rather than a
|
||
# coincidence, and `requiredBy` is what makes a store that never
|
||
# comes up an outage that says so instead of a gateway serving the
|
||
# wrong name.
|
||
#
|
||
# 🩸 NOT `Before=hive-tls-ca.service`, however much the trust bundle
|
||
# wants it. That edge closed a cycle — the store's container is
|
||
# `After=hive-tls-ca` (it serves the material that unit writes), and
|
||
# this unit is `After=` the container — so systemd broke the loop the
|
||
# only way it can, by deleting a job:
|
||
#
|
||
# Found ordering cycle: container@swarm-bao.service/start after
|
||
# hive-tls-ca.service/start after swarm-services-cert.service/start
|
||
# Job swarm-services-cert.service/start deleted to break ordering cycle
|
||
#
|
||
# With the job gone the leaf was never issued, `Requires=` took the
|
||
# gateway's cert import down with it, and nginx never started at all —
|
||
# so the swarm served nothing rather than serving the wrong name. The
|
||
# bundle reaches the root the other way round, at the end of the script
|
||
# below: it restarts `hive-tls-ca` when the root CHANGED, which is the
|
||
# same path that already covered a store coming up hours late.
|
||
before = [ "hive-gateway-self-signed-cert.service" ];
|
||
requiredBy = [ "hive-gateway-self-signed-cert.service" ];
|
||
# The store's container, where it runs here. On a hive that reads a
|
||
# store hosted elsewhere no such unit exists and systemd ignores
|
||
# the name, which is the correct behaviour rather than a gap: what
|
||
# this unit actually needs is the store reachable, and on a remote
|
||
# store nothing local can order against that.
|
||
#
|
||
# `swarm-bao-pki` mints the services-issuer leaf the login below
|
||
# presents, and is absent on a hive holding an operator-placed one —
|
||
# ignored there for the same reason, rather than being a dependency
|
||
# only some hives may declare.
|
||
after = [
|
||
"container@${baoCfg.machine}.service"
|
||
"swarm-bao-pki.service"
|
||
"swarm-bao-services-issuer-policy.service"
|
||
];
|
||
wants = [ "container@${baoCfg.machine}.service" ];
|
||
path = [
|
||
baoDeploy.package
|
||
pkgs.jq
|
||
pkgs.openssl
|
||
pkgs.coreutils
|
||
pkgs.systemd
|
||
# `cmp`, which is NOT in coreutils. Without it the root-changed test
|
||
# below is `command not found` — 127, invisible under `if !`, and
|
||
# therefore always "changed", so the bundle rebuild it guards fired
|
||
# on every issuance instead of on a new root.
|
||
pkgs.diffutils
|
||
];
|
||
# Sized like the store's own granting units, and for the same
|
||
# reason: under `seal = "shamir"` an operator unseals BY HAND, and
|
||
# the login below fails for as long as that takes. 2880 × 30s is
|
||
# 24h inside a 25h window — `StartLimit*` are `[Unit]` settings, so
|
||
# the window must exceed `RestartSec × burst` or it closes between
|
||
# attempts and the burst is never reached.
|
||
startLimitBurst = 2880;
|
||
startLimitIntervalSec = 90000;
|
||
serviceConfig = {
|
||
Type = "oneshot";
|
||
RemainAfterExit = true;
|
||
UMask = "0077";
|
||
SyslogIdentifier = "swarm-services-cert";
|
||
Restart = "on-failure";
|
||
RestartSec = 30;
|
||
};
|
||
environment = {
|
||
BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
|
||
}
|
||
// lib.optionalAttrs (cfg.baoClientCertFile != null) {
|
||
BAO_CLIENT_CERT = cfg.baoClientCertFile;
|
||
}
|
||
// lib.optionalAttrs (cfg.baoClientKeyFile != null) {
|
||
BAO_CLIENT_KEY = cfg.baoClientKeyFile;
|
||
}
|
||
# Absent means the system trust store, which is what a deployment
|
||
# with a real CA wants and what a self-signed one must not be left
|
||
# with.
|
||
// lib.optionalAttrs (baoDeploy.serverCaFile != null) {
|
||
BAO_CACERT = baoDeploy.serverCaFile;
|
||
};
|
||
script = ''
|
||
set -euo pipefail
|
||
d=${lib.escapeShellArg cfg.stateDir}
|
||
install -d -m 0755 "$d"
|
||
|
||
${leafCoverage}
|
||
|
||
if [ "$want_svc" = 0 ]; then
|
||
echo "no swarm service domains configured — nothing to issue"
|
||
exit 0
|
||
fi
|
||
|
||
# Same rule as the hive leaf's, at a different cadence: re-issue
|
||
# when the file is missing, within 30 days of expiry, or no
|
||
# longer carrying every configured name. The name check is what
|
||
# makes adding a swarm service take effect on the rebuild that
|
||
# added it rather than whenever the certificate happens to lapse.
|
||
reissue=0
|
||
{ [ -s "$svcleaf" ] && [ -s "$d/swarm-services-key.pem" ]; } || reissue=1
|
||
openssl x509 -in "$svcleaf" -noout -checkend 2592000 >/dev/null 2>&1 || reissue=1
|
||
covers "$svcleaf" "$svcNames" || reissue=1
|
||
[ -s "$svcroot" ] || reissue=1
|
||
|
||
# The ROOT's window, not the leaf's, and it is what keeps the two
|
||
# sides of this from needing to talk. The store replaces an issuer
|
||
# that has less than a leaf's window left (./swarm-bao.nix's
|
||
# regeneration guard) — so a hive testing its own copy of that same
|
||
# certificate against the same threshold asks for a new leaf on the
|
||
# same activation, and gets the replacement root back with it.
|
||
# Without this a leaf stays "valid" while the anchor it chains to no
|
||
# longer exists in the mount, which no expiry check would ever catch.
|
||
openssl x509 -in "$svcroot" -noout -checkend 2592000 >/dev/null 2>&1 || reissue=1
|
||
|
||
if [ "$reissue" = 0 ]; then
|
||
echo "swarm-services leaf valid and covering the configured names — leaving it alone"
|
||
exit 0
|
||
fi
|
||
|
||
${
|
||
if cfg.baoClientCertFile == null || cfg.baoClientKeyFile == null then
|
||
''
|
||
echo "no bao client certificate configured for this host, so the gateway's" >&2
|
||
echo "swarm-services certificate cannot be requested from the store." >&2
|
||
echo "Set services.hyperhive.deploy.hive-controller.tls.baoClient{Cert,Key}File" >&2
|
||
echo "to a leaf the store's CA signed with CN=${baoDeploy.servicesIssuerCommonName}." >&2
|
||
exit 1''
|
||
else
|
||
""
|
||
}
|
||
|
||
# `bao`'s own message is the only thing separating an unreachable
|
||
# store from a refused identity from a role that would not issue
|
||
# these names, and this unit retries on all three — so it reports
|
||
# which one rather than asserting all three in a sentence of ours.
|
||
err="$(mktemp)"
|
||
trap 'rm -f "$err"' EXIT
|
||
|
||
# Cert auth is a login, not a transport setting: the
|
||
# `BAO_CLIENT_*` variables only decide which certificate the
|
||
# handshake presents. Without a token `bao` asks its token
|
||
# helper, and that is a `sh` this unit's `path` does not carry —
|
||
# `-token-only` answers on stdout and skips the helper.
|
||
if ! BAO_TOKEN="$(bao login -method=cert -token-only 2>"$err")"; then
|
||
echo "could not log in to the swarm secret store with this host's services-issuer certificate." >&2
|
||
cat "$err" >&2
|
||
exit 1
|
||
fi
|
||
export BAO_TOKEN
|
||
|
||
echo "requesting the swarm-services leaf from the store"
|
||
resp="$(mktemp "$d/swarm-services.json.XXXXXX")"
|
||
trap 'rm -f "$err" "$resp"' EXIT
|
||
|
||
# ONE call, and the response carries all three artefacts —
|
||
# certificate, private key and issuing CA. Splitting it into a
|
||
# local CSR plus `pki/sign` would buy a key that never crosses
|
||
# the wire, and cost the thing that makes this unit worth having:
|
||
# the store, not this host, decides what the certificate says.
|
||
if ! bao write -format=json \
|
||
${lib.escapeShellArg "${baoServicesPkiMount}/issue/${baoServicesPkiRole}"} \
|
||
common_name=${lib.escapeShellArg (builtins.head swarmServiceDomains)} \
|
||
alt_names=${lib.escapeShellArg (lib.concatStringsSep "," swarmServiceDomains)} \
|
||
> "$resp" 2>"$err"; then
|
||
echo "the store refused to issue the swarm-services certificate." >&2
|
||
cat "$err" >&2
|
||
exit 1
|
||
fi
|
||
|
||
# Three fields out of ONE issuance, which is why the response is
|
||
# captured and then split rather than asked for three times with
|
||
# `bao write -field=…`: each of those calls would mint a separate
|
||
# certificate, and the key would belong to a different one than
|
||
# the leaf.
|
||
#
|
||
# `jq -r` into a file the shell opened, never into a variable and
|
||
# never into an argv — the private key does not become visible in
|
||
# /proc on its way to disk.
|
||
#
|
||
# `// empty` on every one of them: `jq -r` renders a missing
|
||
# field as the four characters `null`, which is a non-empty file
|
||
# and would sail past the check below into a certificate slot.
|
||
umask 077
|
||
jq -r '.data.private_key // empty' < "$resp" > "$d/swarm-services-key.pem.new"
|
||
jq -r '.data.certificate // empty' < "$resp" > "$d/swarm-services-leaf.new"
|
||
jq -r '.data.issuing_ca // empty' < "$resp" > "$svcroot.new"
|
||
|
||
for f in "$d/swarm-services-key.pem.new" "$d/swarm-services-leaf.new" "$svcroot.new"; do
|
||
if [ ! -s "$f" ]; then
|
||
echo "the store's response was missing a field: $f is empty" >&2
|
||
exit 1
|
||
fi
|
||
done
|
||
|
||
# nginx serves this file verbatim. It carries the leaf ALONE and
|
||
# not leaf-plus-issuer, which is the one visible consequence of
|
||
# flattening the chain: the issuer here is a self-signed root, so
|
||
# appending it would ship an anchor a client either already holds
|
||
# — in which case it is redundant — or does not, in which case
|
||
# shipping it proves nothing. The old file appended the services
|
||
# sub-CA because that WAS an intermediate, and a client anchored
|
||
# on the swarm root could not build the middle of the chain by
|
||
# itself.
|
||
mv -f "$d/swarm-services-leaf.new" "$svcleaf"
|
||
mv -f "$d/swarm-services-key.pem.new" "$d/swarm-services-key.pem"
|
||
chmod 0644 "$svcleaf"
|
||
chmod 0600 "$d/swarm-services-key.pem"
|
||
|
||
# The anchor, world-readable, beside the leaf it signed. This is
|
||
# the file an operator adds to a browser's trust store, and the
|
||
# one `hive-tls-ca` folds into `trust-bundle.pem`. Public
|
||
# certificate material only — the private half never leaves the
|
||
# store's `pki` mount, which is what `root/generate/internal`
|
||
# buys.
|
||
rootchanged=0
|
||
if ! cmp -s "$svcroot.new" "$svcroot"; then
|
||
rootchanged=1
|
||
fi
|
||
mv -f "$svcroot.new" "$svcroot"
|
||
chmod 0644 "$svcroot"
|
||
|
||
# Propagation, for the RETRY path only. Ordered before both of
|
||
# these, so on a normal boot they have not run yet, `is-active`
|
||
# is false, and ordering alone does the work. What this covers is
|
||
# the store coming up hours after the gateway did: nginx serves a
|
||
# *copy* of the leaf, so re-issuing the source changes nothing
|
||
# until the copy is remade.
|
||
#
|
||
# ⚠️ `--no-block`, and it is not a preference. This unit declares
|
||
# `Before=` both of these, so a blocking `systemctl restart`
|
||
# enqueues a job that systemd will not start until this unit is
|
||
# active — and this unit is not active until its ExecStart
|
||
# returns, which is waiting on that job. A deadlock, held until
|
||
# the 24h retry window's `TimeoutStartSec` fires. Queueing the
|
||
# job and letting it run once we exit is the only ordering that
|
||
# terminates.
|
||
#
|
||
# The cost is real and is the reason `hive-tls-resign` does NOT
|
||
# do this: a propagation that fails after we return does not fail
|
||
# us, so the leaf can rotate on disk while nginx keeps the old
|
||
# copy. That unit blocks because nothing orders it before its
|
||
# consumers; this one cannot.
|
||
if systemctl is-active --quiet nginx.service; then
|
||
echo "swarm-services leaf rotated — re-importing and reloading nginx"
|
||
systemctl restart --no-block hive-gateway-self-signed-cert.service
|
||
systemctl reload --no-block nginx.service
|
||
fi
|
||
|
||
# The bundle is assembled by `hive-tls-ca`, which runs BEFORE this
|
||
# unit — it has to, or the store's container cannot start and there
|
||
# is nothing to ask for a leaf. So on a first boot it wrote a bundle
|
||
# without the root below, and this restart is what completes it
|
||
# rather than a retry-path fallback. Only on a CHANGED root: every
|
||
# boot otherwise bounces a unit with nothing to do.
|
||
if [ "$rootchanged" = 1 ] && systemctl is-active --quiet hive-tls-ca.service; then
|
||
echo "the services root changed — rebuilding the trust bundle"
|
||
systemctl restart --no-block hive-tls-ca.service
|
||
fi
|
||
'';
|
||
};
|
||
|
||
systemd.timers.hive-tls-resign = {
|
||
description = "Weekly gateway-leaf re-sign and propagation";
|
||
wantedBy = [ "timers.target" ];
|
||
timerConfig = {
|
||
# Run weekly; Persistent=true fires a missed run on next boot if
|
||
# the timer was not active (e.g. the host was off on the scheduled
|
||
# day), preventing a dormant timer from letting the leaf lapse.
|
||
OnCalendar = "weekly";
|
||
Persistent = true;
|
||
};
|
||
};
|
||
|
||
# Signal the hive-c0re lifecycle that a hive CA exists: it bind-mounts
|
||
# this file (read-only, public certs ONLY — never a key) into each
|
||
# agent container so agents + their tools can trust the gateway's
|
||
# self-signed leaf, and the meta flake wires the per-agent trust
|
||
# bundle. It is the ANCHOR bundle rather than `ca.pem` for the reason
|
||
# spelled out where the bundle is written above; no key path is ever
|
||
# exposed (an agent that could read one could mint trusted certs).
|
||
systemd.services.hive-c0re.environment.HIVE_TLS_CA_PATH = "${cfg.stateDir}/trust-bundle.pem";
|
||
|
||
# The same anchor, named for the swarm-queue clients that need it when
|
||
# they mint a token from authelia over TLS. Declared HERE, beside the
|
||
# bundle, rather than in each consumer's module: the path is this
|
||
# module's fact, and two consumers re-deriving `${stateDir}/…` would be
|
||
# two places to fix the day it moves.
|
||
#
|
||
# ⚠️ This is what was missing. `swarm-queue-client` built a bare
|
||
# `reqwest::Client`, so it trusted only the platform roots and died at
|
||
# `invalid peer certificate: UnknownIssuer` against a swarm whose
|
||
# authelia is signed by the swarm CA — while this very bundle sat on
|
||
# disk, already assembled, already handed to hive-c0re under a different
|
||
# variable name. The anchor was never missing; nothing pointed the queue
|
||
# client at it.
|
||
#
|
||
# Set unconditionally within this module's `active` guard, exactly like
|
||
# the line above: where there is no hive CA this module contributes
|
||
# nothing at all, and the clients then fall back to the platform roots —
|
||
# which is correct for a swarm fronted by a public certificate.
|
||
systemd.services.hive-c0re.environment.HIVE_C0RE_OIDC_CA_FILE = "${cfg.stateDir}/trust-bundle.pem";
|
||
# ⚠️ Gated, where the hive-c0re line above is not, and the asymmetry is
|
||
# the point: hive-c0re runs on every hive, the controller runs on one.
|
||
# Defining an environment key on a unit that does not exist CREATES a
|
||
# unit fragment for it — inert (no `ExecStart`, empty `wantedBy`, never
|
||
# activated) but present on every non-controller hive with a CA. Caught
|
||
# in review on this PR; it evaluates and builds clean either way, which
|
||
# is exactly why it needed a reviewer rather than a check.
|
||
systemd.services.swarm-controller.environment.SWARM_CONTROLLER_OIDC_CA_FILE =
|
||
lib.mkIf hyperhiveCfg.deploy.swarm-controller.enable "${cfg.stateDir}/trust-bundle.pem";
|
||
};
|
||
}
|