Fix PolicyStepsRegistry cache concurrency issue

docs/changelog/126840.yaml

@@ -0,0 +1,6 @@
+pr: 126840
+summary: Fix `PolicyStepsRegistry` cache concurrency issue
+area: ILM+SLM
+type: bug
+issues:
+ - 118406

muted-tests.yml

@@ -135,9 +135,6 @@ tests:
 - class: org.elasticsearch.xpack.test.rest.XPackRestIT
  method: test {p0=transform/transforms_unattended/Test unattended put and start}
  issue: https://github.com/elastic/elasticsearch/issues/120019
-- class: org.elasticsearch.xpack.ilm.actions.SearchableSnapshotActionIT
- method: testUpdatePolicyToAddPhasesYieldsInvalidActionsToBeSkipped
- issue: https://github.com/elastic/elasticsearch/issues/118406
 - class: org.elasticsearch.xpack.security.QueryableReservedRolesIT
  method: testConfiguredReservedRolesAfterClosingAndOpeningIndex
  issue: https://github.com/elastic/elasticsearch/issues/120127

x-pack/plugin/ilm/src/main/java/org/elasticsearch/xpack/ilm/PolicyStepsRegistry.java

@@ -105,9 +105,6 @@ Map<String, Map<Step.StepKey, Step>> getStepMap() {
  public void update(IndexLifecycleMetadata meta) {
  assert meta != null : "IndexLifecycleMetadata cannot be null when updating the policy steps registry";
 
- // since the policies (may have) changed, the whole steps cache needs to be thrown out
- cachedSteps.clear();
-
  DiffableUtils.MapDiff<String, LifecyclePolicyMetadata, Map<String, LifecyclePolicyMetadata>> mapDiff = DiffableUtils.diff(
  lifecyclePolicyMap,
  meta.getPolicyMetadatas(),
@@ -163,6 +160,11 @@ public LifecyclePolicyMetadata read(StreamInput in, String key) {
  }
  }
  }
+
+ // Since the policies (may have) changed, the whole steps cache needs to be thrown out.
+ // We do this after we update `lifecyclePolicyMap` to ensure `cachedSteps` does not contain outdated data.
+ // This means we may clear up-to-date data, but that's a lot better than the cache containing outdated entries indefinitely.
+ cachedSteps.clear();
  }
 
  /**