Fix letsencrypt (#60219)

* nixos/acme: Fix ordering of cert requests

When subsequent certificates would be added, they would
not wake up nginx correctly due to target units only being triggered
once. We now added more fine-grained systemd dependencies to make sure
nginx always is aware of new certificates and doesn't restart too early
resulting in a crash.

Furthermore, the acme module has been refactored. Mostly to get
rid of the deprecated PermissionStartOnly systemd options which were
deprecated. Below is a summary of changes made.

* Use SERVICE_RESULT to determine status
This was added in systemd v232. we don't have to keep track
of the EXITCODE ourselves anymore.

* Add regression test for requesting mutliple domains

* Deprecate 'directory' option
We now use systemd's StateDirectory option to manage
create and permissions of the acme state directory.

* The webroot is created using a systemd.tmpfiles.rules rule
instead of the preStart script.

* Depend on certs directly

By getting rid of the target units, we make sure ordering
is correct in the case that you add new certs after already
having deployed some.

Reason it broke before:  acme-certificates.target would
be in active state, and if you then add a new cert, it
would still be active and hence nginx would restart
without even requesting a new cert. Not good!  We
make the dependencies more fine-grained now. this should fix that

* Remove activationDelay option

It complicated the code a lot, and is rather arbitrary. What if
your activation script takes more than activationDelay seconds?

Instead, one should use systemd dependencies to make sure some
action happens before setting the certificate live.

e.g. If you want to wait until your cert is published in DNS DANE /
TLSA, you could create a unit that blocks until it appears in DNS:

```
RequiredBy=acme-${cert}.service
After=acme-${cert}.service
ExecStart=publish-wait-for-dns-script
```

1 files changed, 87 insertions, 11 deletions

diff --git a/nixos/tests/acme.nix b/nixos/tests/acme.nix
index 4669a092433e7..8cfdea4a16ef6 100644
--- a/nixos/tests/acme.nix
+++ b/nixos/tests/acme.nix
@@ -3,19 +3,49 @@ let
 in import ./make-test.nix {
   name = "acme";
 
-  nodes = {
+  nodes = rec {
     letsencrypt = ./common/letsencrypt;
 
+    acmeStandalone = { config, pkgs, ... }: {
+      imports = [ commonConfig ];
+      networking.firewall.allowedTCPPorts = [ 80 ];
+      networking.extraHosts = ''
+        ${config.networking.primaryIPAddress} standalone.com
+      '';
+      security.acme.certs."standalone.com" = {
+        webroot = "/var/lib/acme/acme-challenges";
+      };
+      systemd.targets."acme-finished-standalone.com" = {};
+      systemd.services."acme-standalone.com" = {
+        wants = [ "acme-finished-standalone.com.target" ];
+        before = [ "acme-finished-standalone.com.target" ];
+      };
+      services.nginx.enable = true;
+      services.nginx.virtualHosts."standalone.com" = {
+        locations."/.well-known/acme-challenge".root = "/var/lib/acme/acme-challenges";
+      };
+    };
+
     webserver = { config, pkgs, ... }: {
       imports = [ commonConfig ];
       networking.firewall.allowedTCPPorts = [ 80 443 ];
 
       networking.extraHosts = ''
-        ${config.networking.primaryIPAddress} example.com
+        ${config.networking.primaryIPAddress} a.example.com
+        ${config.networking.primaryIPAddress} b.example.com
       '';
 
+      # A target remains active. Use this to probe the fact that
+      # a service fired eventhough it is not RemainAfterExit
+      systemd.targets."acme-finished-a.example.com" = {};
+      systemd.services."acme-a.example.com" = {
+        wants = [ "acme-finished-a.example.com.target" ];
+        before = [ "acme-finished-a.example.com.target" ];
+      };
+
       services.nginx.enable = true;
-      services.nginx.virtualHosts."example.com" = {
+
+      services.nginx.virtualHosts."a.example.com" = {
         enableACME = true;
         forceSSL = true;
         locations."/".root = pkgs.runCommand "docroot" {} ''
@@ -23,17 +53,63 @@ in import ./make-test.nix {
           echo hello world > "$out/index.html"
         '';
       };
+
+      nesting.clone = [
+        ({pkgs, ...}: {
+
+          networking.extraHosts = ''
+            ${config.networking.primaryIPAddress} b.example.com
+          '';
+          systemd.targets."acme-finished-b.example.com" = {};
+          systemd.services."acme-b.example.com" = {
+            wants = [ "acme-finished-b.example.com.target" ];
+            before = [ "acme-finished-b.example.com.target" ];
+          };
+          services.nginx.virtualHosts."b.example.com" = {
+            enableACME = true;
+            forceSSL = true;
+            locations."/".root = pkgs.runCommand "docroot" {} ''
+              mkdir -p "$out"
+              echo hello world > "$out/index.html"
+            '';
+          };
+        })
+      ];
     };
 
     client = commonConfig;
   };
 
-  testScript = ''
-    $letsencrypt->waitForUnit("default.target");
-    $letsencrypt->waitForUnit("boulder.service");
-    $webserver->waitForUnit("default.target");
-    $webserver->waitForUnit("acme-certificates.target");
-    $client->waitForUnit("default.target");
-    $client->succeed('curl https://example.com/ | grep -qF "hello world"');
-  '';
+  testScript = {nodes, ...}: 
+    let
+      newServerSystem = nodes.webserver2.config.system.build.toplevel;
+      switchToNewServer = "${newServerSystem}/bin/switch-to-configuration test";
+    in
+    # Note, waitForUnit does not work for oneshot services that do not have RemainAfterExit=true,
+    # this is because a oneshot goes from inactive => activating => inactive, and never
+    # reaches the active state. To work around this, we create some mock target units which
+    # get pulled in by the oneshot units. The target units linger after activation, and hence we
+    # can use them to probe that a oneshot fired. It is a bit ugly, but it is the best we can do
+    ''
+      $client->waitForUnit("default.target");
+      $letsencrypt->waitForUnit("default.target");
+      $letsencrypt->waitForUnit("boulder.service");
+
+      subtest "can request certificate with HTTPS-01 challenge", sub {
+        $acmeStandalone->waitForUnit("default.target");
+        $acmeStandalone->succeed("systemctl start acme-standalone.com.service");
+        $acmeStandalone->waitForUnit("acme-finished-standalone.com.target");
+      };
+
+      subtest "Can request certificate for nginx service", sub {
+        $webserver->waitForUnit("acme-finished-a.example.com.target");
+        $client->succeed('curl https://a.example.com/ | grep -qF "hello world"');
+      };
+
+      subtest "Can add another certificate for nginx service", sub {
+        $webserver->succeed("/run/current-system/fine-tune/child-1/bin/switch-to-configuration test");
+        $webserver->waitForUnit("acme-finished-b.example.com.target");
+        $client->succeed('curl https://b.example.com/ | grep -qF "hello world"');
+      };
+    '';
 }