From 849bf46550c5bb1a6186bfddb6c55a3b50c73eeb Mon Sep 17 00:00:00 2001 From: atlas Date: Sun, 4 Oct 2026 08:35:12 +0200 Subject: [PATCH] hive-tls: fail swarm-services-cert when the store identity is absent A hive fronting no swarm name fetches the store's pki root presenting its reader certificate. When deploy.bao.clientCertFile or clientKeyFile is unset, or either named file is not readable, the unit now exits 1 with a message naming both options and their paths, instead of exiting 0 with the root missing from the trust bundle. The module-eval cases that asserted the quiet skip assert the failure instead, and a new case covers the named-but-absent files. --- docs/swarm/ca.md | 5 ++++- docs/swarm/secrets.md | 2 +- nix/host-modules/hive-tls.nix | 27 +++++++++++++++++++++++---- nix/module-eval/hive-tls.nix | 34 ++++++++++++++++++++++++---------- 4 files changed, 52 insertions(+), 16 deletions(-) diff --git a/docs/swarm/ca.md b/docs/swarm/ca.md index d4420503..ca76dcfe 100644 --- a/docs/swarm/ca.md +++ b/docs/swarm/ca.md @@ -65,7 +65,10 @@ gateway can't serve a swarm service that runs behind another. `/var/lib/hive-tls/swarm-services-root.pem` (0644), written beside the leaf it signed and folded into `trust-bundle.pem`. A hive fronting no swarm name asks for no leaf and reads the root alone, from the store's -`pki/ca/pem`, when it holds a store identity (`deploy.bao.clientCertFile`). +`pki/ca/pem`, presenting its store identity +(`deploy.bao.clientCertFile` / `clientKeyFile`) for the handshake. Every hive +must hold one: without it, or with either file absent, +`swarm-services-cert.service` fails with a message naming both options. On the host running the store it's also at `/var/lib/swarm-bao-services-pki/services-root.pem`. That's the file to diff --git a/docs/swarm/secrets.md b/docs/swarm/secrets.md index ad0c727d..22bc2c0b 100644 --- a/docs/swarm/secrets.md +++ b/docs/swarm/secrets.md @@ -45,7 +45,7 @@ neither is a renaming of the other. | --------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | swarm root CA cert | `swarm-ca.nix` first-boot unit, when the operator sets `autoConfigure` | `/var/lib/swarm-ca/root.pem` | operator copies the **cert** in; it's public | | swarm root CA key | same unit | `/var/lib/swarm-ca/root-key.pem`, `0600` | stays on whichever host holds it — see the constraint below | -| swarm-services root CA (cert + key) | `swarm-bao.nix`'s granting unit, inside the store's `pki` mount | the **key** never leaves the mount; the **cert** lands at `/var/lib/swarm-bao-services-pki/services-root.pem` (0644) and at `/var/lib/hive-tls/swarm-services-root.pem` on every hive | nothing to copy — every hive receives the cert with the leaf it asks the store for, or from `pki/ca/pem` where it fronts no swarm name and holds a store identity | +| swarm-services root CA (cert + key) | `swarm-bao.nix`'s granting unit, inside the store's `pki` mount | the **key** never leaves the mount; the **cert** lands at `/var/lib/swarm-bao-services-pki/services-root.pem` (0644) and at `/var/lib/hive-tls/swarm-services-root.pem` on every hive | nothing to copy — every hive receives the cert with the leaf it asks the store for, or from `pki/ca/pem` where it fronts no swarm name and needs a store identity | | authelia session, JWT and storage-encryption keys | authelia's first-boot unit, in-container | `/var/lib/authelia-swarm/{session,jwt,storage-encryption}.key` | generated in place; nothing outside that container reads them | | authelia OIDC HMAC key | same unit | `/var/lib/authelia-swarm/oidc-hmac.key` | same | | authelia OIDC issuer key (RSA) | same unit | `/var/lib/authelia-swarm/oidc-issuer.key` | same — relying parties verify against the **public** half at `/jwks.json` | diff --git a/nix/host-modules/hive-tls.nix b/nix/host-modules/hive-tls.nix index 40bee15a..0e86bd86 100644 --- a/nix/host-modules/hive-tls.nix +++ b/nix/host-modules/hive-tls.nix @@ -797,12 +797,26 @@ in # `ca/pem` takes no token; the TLS client certificate is the # store's listener's demand, not bao's, so this presents the # hive's reader identity and never logs in with it. - # A hive with no reader identity has no certificate to present, so it - # skips the fetch and the bundle goes without this root. + # A hive without a readable reader identity fails here, naming the + # options: every hive must hold one. if [ "$want_svc" = 0 ]; then ${ if haveReaderIdentity then '' + missing="" + for f in ${ + lib.escapeShellArgs [ + baoDeploy.clientCertFile + baoDeploy.clientKeyFile + ] + }; do + [ -r "$f" ] || missing="$missing $f" + done + if [ -n "$missing" ]; then + echo "this hive has no usable store identity: cannot read$missing." >&2 + echo "place the files named by services.hyperhive.deploy.bao.clientCertFile (${baoDeploy.clientCertFile}) and services.hyperhive.deploy.bao.clientKeyFile (${baoDeploy.clientKeyFile})." >&2 + exit 1 + fi echo "no swarm service domains configured — fetching only the store's pki root" err="$(mktemp)" raw="$(mktemp "$d/swarm-services-root.XXXXXX")" @@ -838,8 +852,13 @@ in exit 0'' else '' - echo "store pki root not staged: this hive has no store identity (services.hyperhive.deploy.bao.clientCertFile/clientKeyFile)" - exit 0'' + echo "this hive has no store identity, so it cannot fetch the store's ${baoServicesPkiMount} root." >&2 + echo "set services.hyperhive.deploy.bao.clientCertFile (${ + if baoDeploy.clientCertFile == null then "unset" else baoDeploy.clientCertFile + }) and services.hyperhive.deploy.bao.clientKeyFile (${ + if baoDeploy.clientKeyFile == null then "unset" else baoDeploy.clientKeyFile + }) and place both files." >&2 + exit 1'' } fi diff --git a/nix/module-eval/hive-tls.nix b/nix/module-eval/hive-tls.nix index 8f2a14dd..8828a81b 100644 --- a/nix/module-eval/hive-tls.nix +++ b/nix/module-eval/hive-tls.nix @@ -50,11 +50,12 @@ let noIdentity = hive { }; noIdFetch = noIdentity.systemd.services.swarm-services-cert.script; - # The `want_svc=0` branch of a rendered script, up to its closing `fi`. + # The `want_svc=0` branch of a rendered script, up to the `fi` that closes it (the + # only one followed by a blank line). noSvcBranch = script: builtins.head ( - lib.splitString "\nfi\n" (lib.last (lib.splitString ''if [ "$want_svc" = 0 ]; then'' script)) + lib.splitString "\nfi\n\n" (lib.last (lib.splitString ''if [ "$want_svc" = 0 ]; then'' script)) ); units = allLocal.systemd.services; @@ -159,20 +160,33 @@ let ) noSvcFetch; } { - # Nothing to present means no fetch to fail: the unit stays green and - # says why the root is missing. The control is the same hive with an - # identity, whose branch does fetch and can fail. - name = "a hive fronting no swarm name with no store identity skips the fetch and cannot fail on it"; + # No identity to present: the unit fails, naming both options, rather + # than leaving the bundle without the root behind a green unit. The + # control is the same hive with an identity, whose branch fetches. + name = "a hive fronting no swarm name with no store identity fails the unit, naming both options"; ok = noIdentity.services.hyperhive.swarm.localServiceDomains == [ ] && noIdentity.services.hyperhive.deploy.bao.clientCertFile == null && !(lib.hasInfix "/v1/pki/ca/pem" noIdFetch) - && lib.hasInfix "store pki root not staged" (noSvcBranch noIdFetch) - && lib.hasInfix "deploy.bao.clientCertFile" (noSvcBranch noIdFetch) - && !(lib.hasInfix "exit 1" (noSvcBranch noIdFetch)) - && lib.hasInfix "exit 1" (noSvcBranch noSvcFetch) + && lib.hasInfix "services.hyperhive.deploy.bao.clientCertFile" (noSvcBranch noIdFetch) + && lib.hasInfix "services.hyperhive.deploy.bao.clientKeyFile" (noSvcBranch noIdFetch) + && lib.hasSuffix "exit 1" (noSvcBranch noIdFetch) + && !(lib.hasInfix "exit 0" (noSvcBranch noIdFetch)) + && !(lib.hasInfix "not staged" noIdFetch) && lib.hasInfix "/v1/pki/ca/pem" (noSvcBranch noSvcFetch); } + { + # An identity named but not on disk fails before curl, naming the paths. + name = "a hive fronting no swarm name whose identity files are absent fails the unit, naming the paths"; + ok = + lib.hasInfix "for f in /etc/pki/bao-client.pem /etc/pki/bao-client-key.pem; do" ( + noSvcBranch noSvcFetch + ) + && lib.hasInfix ''[ -r "$f" ] || missing="$missing $f"'' (noSvcBranch noSvcFetch) + && lib.hasInfix "cannot read$missing" (noSvcBranch noSvcFetch) + && lib.hasInfix "clientCertFile (/etc/pki/bao-client.pem)" (noSvcBranch noSvcFetch) + && lib.hasInfix "clientKeyFile (/etc/pki/bao-client-key.pem)" (noSvcBranch noSvcFetch); + } { # The fetch retries against a sealed store; a gateway `Requires=` on it # would go down with each attempt. The control is a host fronting