Merge pull request 'ca-trust: a machine trusts the mesh's authority because a module put its root there' (#142) from feat/ca-trust into main

modules/ca-trust/module.json

@@ -0,0 +1,56 @@
+{
+  "module": "ca-trust",
+  "version": "1",
+  "slug": "catrust",
+  "capabilities": [
+    "service-manager"
+  ],
+  "requires": [
+    "internal-acme-ca"
+  ],
+  "seats": [
+    {
+      "name": "the-mesh-trust-anchor",
+      "scope": "node"
+    }
+  ],
+  "claims": [
+    {
+      "name": "the-mesh-trust-anchor",
+      "scope": "node"
+    }
+  ],
+  "resources": [
+    {
+      "id": "state",
+      "type": "directory",
+      "mode": "0700",
+      "place": "."
+    },
+    {
+      "id": "anchor",
+      "type": "file",
+      "path": "${dir:state}/anchor",
+      "mode": "0755",
+      "content": "#!/bin/sh\n# The mesh's internal certificate authority, trusted by this machine.\n#\n# Written by the mesh from the ca-trust module's manifest (novox/hq ADR 0147).\n# Editing it here lasts until the next apply.\n#\n# There is no prior trust to verify the fetch against \u2014 this is the thing that\n# establishes it \u2014 so it is made over the mesh's own private network, which is\n# what authenticates it (novox/hq ADR 0098, the same reasoning that lets the\n# route proxy fetch this root for itself). What comes back is checked here: a\n# body that is not a certificate is refused now, rather than believed and then\n# failed by whatever reads the trust store next.\nset -eu\n\nROOTS='https://${bound:internal-acme-ca:at}:${bound:internal-acme-ca:port}${bound:internal-acme-ca:roots}'\nANCHORS=/etc/ca-certificates/trust-source/anchors\nANCHOR=\"$ANCHORS/mesh-internal-ca.crt\"\n\n# Arch's layout, said out loud rather than assumed: a machine that keeps its\n# anchors elsewhere fails here, visibly, instead of writing a file nothing\n# reads. That failure is the signal that this belongs in the host, where one\n# operating system's difference lives (novox/hq ADR 0147, option 2).\n[ -d \"$ANCHORS\" ] || {\n\techo \"this machine keeps no trust anchors in $ANCHORS; ca-trust is written for that layout\" >&2\n\texit 1\n}\n\ncase \"${1:-}\" in\ninstall)\n\ttmp=$(mktemp)\n\ttrap 'rm -f \"$tmp\"' EXIT\n\t# The authority may still be starting, or this machine may have come up\n\t# before it: two minutes of asking, then an honest failure.\n\tn=0\n\twhile [ \"$n\" -lt 60 ]; do\n\t\tif curl --fail --silent --show-error --insecure --max-time 10 \\\n\t\t\t--output \"$tmp\" \"$ROOTS\" &&\n\t\t\tgrep -q 'BEGIN CERTIFICATE' \"$tmp\"; then\n\t\t\tinstall -m 0644 \"$tmp\" \"$ANCHOR\"\n\t\t\tupdate-ca-trust\n\t\t\texit 0\n\t\tfi\n\t\tn=$((n + 1))\n\t\tsleep 2\n\tdone\n\techo \"the authority at $ROOTS did not serve a certificate within two minutes\" >&2\n\texit 1\n\t;;\nremove)\n\t# What stopping the unit does, and therefore what being unassigned does.\n\trm -f \"$ANCHOR\"\n\tupdate-ca-trust\n\t;;\n*)\n\techo \"usage: $(basename \"$0\") install|remove\" >&2\n\texit 2\n\t;;\nesac\n"
+    },
+    {
+      "id": "unit",
+      "type": "file",
+      "path": "/etc/systemd/system/mesh-ca-trust.service",
+      "mode": "0644",
+      "content": "[Unit]\nDescription=The mesh's internal certificate authority, trusted by this machine\n# novox/hq ADR 0147. Starting this unit places the mesh's root among this\n# machine's trust anchors; stopping it takes the root away again, which is what\n# the host does when the module is no longer assigned here.\nWants=network-online.target\nAfter=network-online.target\n\n[Service]\nType=oneshot\nRemainAfterExit=yes\nExecStart=${dir:state}/anchor install\nExecStop=${dir:state}/anchor remove\n\n[Install]\nWantedBy=multi-user.target\n"
+    },
+    {
+      "id": "trust",
+      "type": "service",
+      "unit": "mesh-ca-trust.service",
+      "state": "running",
+      "boot": "enabled",
+      "restart-on": [
+        "anchor",
+        "unit"
+      ]
+    }
+  ]
+}