swarm-bao-agent-pki: decide openbao's restart on the shared locale-independent compare

`swarm-bao-agent-pki` carried its own copy of the mtime-vs-start compare,
with the same `stat -c %.6Y | tr -d .` read: on a comma-locale host the
`-le` errored and, under `seal = "pkcs11"`, openbao was restarted on
every run of the unit.

The compare moves out of `refresh_unit` into `written_after_start`
(0 newer, 1 not newer, 2 unreadable and logged at `err`), and both
`refresh_unit` and the agent-pki unit call it. The agent-pki unit cannot
call `refresh_unit` itself: it restarts with `restart`, not
`try-restart`, runs a fail-closed check of the bundle between the
compare and the restart, and under shamir prints the step instead of
restarting. It acts only on 0, so an unreadable time skips the restart
as `refresh_unit` does.

`script-test-refresh-consumer` covers the three return codes in the
agent-pki call shape; `module-eval-bao-basics` asserts both seal arms
decide on that call and that no `%.6Y` read is left in the unit.

Refs #5230

nix/host-modules/lib/refresh-consumer.nix

@@ -31,15 +31,15 @@
     [ ! -f "$1" ] || [ "$(< "$1")" != "$2" ]
   }
 
-  # <unit> <path> [systemctl option…]. Nothing when <unit> last entered
-  # `active` after <path> was last written. Otherwise a running <unit> is
-  # restarted and a failed one — it may have hit its start limit without the
-  # credential — is reset and started; one stopped on purpose stays stopped.
-  # The options are passed to every `systemctl` call, which is how
-  # `refresh_consumer` reaches into a container. `--no-block` because a
-  # caller ordered `Before=` its consumer must not wait on a job that waits
-  # on the caller (see `swarm-services-cert`'s propagation in ../hive-tls.nix).
-  refresh_unit() {
+  # <unit> <path> [systemctl option…]. Returns 0 when <path> was last
+  # written after <unit> last entered `active` (or <unit> never has), 1 when
+  # it was not, and 2, logged at `err`, when either time does not read. Both
+  # are bare microsecond counts, with no decimal separator for a locale to
+  # change. A caller acts only on 0: the mtime stays, so the first run that
+  # can read both still acts, where acting on doubt acts on every run. The
+  # options are passed to `systemctl`, which is how a caller reaches into a
+  # container.
+  written_after_start() {
     local unit="$1" path="$2" started started_us=0 written_us
     shift 2
     # Empty for a unit that has never been active, which `date` would
@@ -49,17 +49,25 @@
       started_us="$(date -u -d "$started" +%s%6N)" || started_us=
     fi
     written_us="$(date -u -r "$path" +%s%6N)" || written_us=
-    # Both are bare microsecond counts, with no decimal separator for a
-    # locale to change. One that is not is logged at `err` and nothing is
-    # restarted: the mtime stays, so the first run that can read both still
-    # restarts <unit>, where restarting on doubt restarts it on every run.
     if [[ ! "$started_us" =~ ^[0-9]+$ || ! "$written_us" =~ ^[0-9]+$ ]]; then
       echo "<3>cannot compare the mtime of $path ('$written_us') with the last start of $unit ('$started') — leaving $unit as it is" >&2
-      return 0
+      return 2
     fi
     if [ "$written_us" -le "$started_us" ]; then
-      return 0
+      return 1
     fi
+  }
+
+  # <unit> <path> [systemctl option…]. Nothing unless `written_after_start`.
+  # Otherwise a running <unit> is restarted and a failed one — it may have
+  # hit its start limit without the credential — is reset and started; one
+  # stopped on purpose stays stopped. `--no-block` because a caller ordered
+  # `Before=` its consumer must not wait on a job that waits on the caller
+  # (see `swarm-services-cert`'s propagation in ../hive-tls.nix).
+  refresh_unit() {
+    local unit="$1" path="$2"
+    shift 2
+    written_after_start "$unit" "$path" "$@" || return 0
     if systemctl "$@" is-failed --quiet "$unit"; then
       echo "$path changed after $unit last started, and $unit had failed — starting it"
       systemctl "$@" reset-failed "$unit"

nix/host-modules/swarm-bao.nix

@@ -3429,6 +3429,7 @@ in
             echo "wrote ${agentCaCachePath}"
           fi
 
+          ${refreshConsumer}
           ${composeListenerBundle}
           compose_listener_bundle
 
@@ -3437,11 +3438,12 @@ in
             echo "openbao in $machine is not running; it reads ${listenerClientCaPath} when it starts"
             exit 0
           fi
-          started="$(systemctl --machine="$machine" show --timestamp=us+utc -p ActiveEnterTimestamp --value openbao.service)"
-          started_us="$(date -u -d "$started" +%s%6N)"
-          written_us="$(stat -c %.6Y ${listenerClientCaPath} | tr -d .)"
-          if [ "$written_us" -le "$started_us" ]; then
+          newer=0
+          written_after_start openbao.service ${listenerClientCaPath} --machine="$machine" || newer=$?
+          if [ "$newer" = 1 ]; then
             echo "openbao started after ${listenerClientCaPath} last changed; nothing to pick up"
+          fi
+          if [ "$newer" != 0 ]; then
             exit 0
           fi