Merge pull request #16262 from Security-Onion-Solutions/TOoSmOotH-patch-4

Add openai_embeddings to the YAML configuration

.github/DISCUSSION_TEMPLATE/3-0.yml

@@ -12,6 +12,8 @@ body:
         - 3.0.0
         - 3.1.0
         - 3.2.0
+        - 3.3.0
+        - 3.4.0
         - Other (please provide detail below)
     validations:
       required: true

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 3.1.0-20260528 ISO image released on 2026/05/28
+### 3.3.0-20260911 ISO image released on 2026/09/11
 
 
 ### Download and Verify
 
-3.1.0-20260528 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-3.1.0-20260528.iso
+3.3.0-20260911 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
  
-MD5: 9D6FF58DEEE24089D722C73169765B3E  
-SHA1: 2B8B816B6CEC3B7F96B3C5E040EBF502DD2C412F  
-SHA256: 62FAB57E247C843D6A04F0796D8162C732B65D82FC3E4A59D087135B9FD32912  
+MD5: 12B18433D3A2198A185892FF79CF638F  
+SHA1: 2B3C2E1FA7A78ED1F956E7EDCC12E32593C14EEE  
+SHA256: 0938C73B76CE30EC9E4394D312C79EA7CAC721B6818541697279A6221F7D870D  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.1.0-20260528.iso.sig
+https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 
 Signing key:  
 https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/main/KEYS  
@@ -25,22 +25,22 @@ wget https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/
 
 Download the signature file for the ISO:  
 ```
-wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.1.0-20260528.iso.sig
+wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 ```
 
 Download the ISO image:  
 ```
-wget https://download.securityonion.net/file/securityonion/securityonion-3.1.0-20260528.iso
+wget https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
 ```
 
 Verify the downloaded ISO image using the signature file:  
 ```
-gpg --verify securityonion-3.1.0-20260528.iso.sig securityonion-3.1.0-20260528.iso
+gpg --verify securityonion-3.3.0-20260911.iso.sig securityonion-3.3.0-20260911.iso
 ```
 
 The output should show "Good signature" and the Primary key fingerprint should match what's shown below:
 ```
-gpg: Signature made Wed 27 May 2026 03:03:59 PM EDT using RSA key ID FE507013
+gpg: Signature made Fri 11 Sep 2026 11:23:56 AM EDT using RSA key ID FE507013
 gpg: Good signature from "Security Onion Solutions, LLC <info@securityonionsolutions.com>"
 gpg: WARNING: This key is not certified with a trusted signature!
 gpg:          There is no indication that the signature belongs to the owner.

VERSION

@@ -1 +1 @@
-3.2.0
+3.4.0

salt/_beacons/local_files_beacon.py

@@ -3,13 +3,14 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-# Custom salt beacon that watches the suricata/strelka rule directories for changes
-# and emits a beacon event per changed directory. This replaces the stock salt
-# `inotify` beacon, which leaks a kernel inotify instance every time the minion
-# rebuilds the beacon loader's __context__ (orphaning the old pyinotify.Notifier
-# without closing it) until fs.inotify.max_user_instances is exhausted and the
-# beacon dies with EMFILE. Polling holds zero inotify instances, so the leak is
-# impossible, and it keeps firing during state runs (no blackout).
+# Custom salt beacon that watches hand-edited directories under
+# /opt/so/saltstack/local/salt/ for changes and emits a beacon event per changed
+# directory. This replaces the stock salt `inotify` beacon, which leaks a kernel
+# inotify instance every time the minion rebuilds the beacon loader's __context__
+# (orphaning the old pyinotify.Notifier without closing it) until
+# fs.inotify.max_user_instances is exhausted and the beacon dies with EMFILE.
+# Polling holds zero inotify instances, so the leak is impossible, and it keeps
+# firing during state runs (no blackout).
 #
 # Detection is poll-based with a per-directory fingerprint persisted to
 # WATERMARK_DIR: each pass walks the directory and hashes every file's
@@ -19,9 +20,10 @@
 # up on the next one).
 #
 # Each emitted event carries the watched directory path under the configured tag
-# (e.g. salt/beacon/<minion>/rules_beacon/suricata); the push_suricata / push_strelka
-# reactors write a push intent, after which the existing so-push-drainer /
-# orch.push_batch pipeline takes over unchanged.
+# (e.g. salt/beacon/<minion>/local_files_beacon/zeek); the push_files reactor
+# looks the tag up in salt/reactor/pillar_push_map.yaml and writes a push intent,
+# after which the existing so-push-drainer / orch.push_batch pipeline takes over
+# unchanged.
 
 import hashlib
 import logging
@@ -77,7 +79,9 @@ def _fingerprint(directory):
     h = hashlib.sha1()
     if os.path.isdir(directory):
         entries = []
-        for root, _dirs, files in os.walk(directory):
+        for root, dirs, files in os.walk(directory):
+            # zkg packages are git clones; .git churn would fire a state apply on its own.
+            dirs[:] = [d for d in dirs if d != '.git']
             for name in files:
                 full = os.path.join(root, name)
                 if _excluded(full):
@@ -94,20 +98,22 @@ def _fingerprint(directory):
     return h.hexdigest()
 
 
-def _watermark_file(tag):
-    return os.path.join(WATERMARK_DIR, 'rules_beacon_%s.hash' % tag)
+def _watermark_file(tag, directory):
+    # Keyed by directory: zeek/policy and zeek/zkg share the tag `zeek`.
+    scope = hashlib.sha1(directory.encode('utf-8', 'surrogateescape')).hexdigest()[:12]
+    return os.path.join(WATERMARK_DIR, 'local_files_beacon_%s_%s.hash' % (tag, scope))
 
 
-def _read_watermark(tag):
+def _read_watermark(tag, directory):
     try:
-        with open(_watermark_file(tag), 'r') as f:
+        with open(_watermark_file(tag, directory), 'r') as f:
             return (f.read() or '').strip() or None
     except IOError:
         return None
 
 
-def _write_watermark(tag, digest):
-    path = _watermark_file(tag)
+def _write_watermark(tag, directory, digest):
+    path = _watermark_file(tag, directory)
     try:
         os.makedirs(WATERMARK_DIR, exist_ok=True)
         tmp = path + '.tmp'
@@ -115,7 +121,7 @@ def _write_watermark(tag, digest):
             f.write(digest)
         os.rename(tmp, path)
     except OSError:
-        log.exception('rules_beacon: failed to persist watermark to %s', path)
+        log.exception('local_files_beacon: failed to persist watermark to %s', path)
 
 
 def beacon(config):
@@ -123,17 +129,17 @@ def beacon(config):
 
     for directory, tag in _paths_from_config(config).items():
         digest = _fingerprint(directory)
-        previous = _read_watermark(tag)
+        previous = _read_watermark(tag, directory)
 
         # First run / missing watermark: seed the digest and emit nothing so a
         # fresh host does not fire a spurious fleetwide push.
         if previous is None:
-            _write_watermark(tag, digest)
+            _write_watermark(tag, directory, digest)
             continue
 
         if digest != previous:
-            _write_watermark(tag, digest)
+            _write_watermark(tag, directory, digest)
             retval.append({'tag': tag, 'path': directory})
-            log.info('rules_beacon: change detected in %s, emitting %s', directory, tag)
+            log.info('local_files_beacon: change detected in %s, emitting %s', directory, tag)
 
     return retval

salt/_beacons/local_files_beacon_test.py

@@ -0,0 +1,221 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+import hashlib
+import os
+import shutil
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import local_files_beacon
+
+
+class TestRulesBeacon(unittest.TestCase):
+
+    def setUp(self):
+        # Isolate all on-disk state (watermarks and the dirs we fingerprint) in a
+        # throwaway tree, and point WATERMARK_DIR at it so the real read/write
+        # helpers run against actual files.
+        self.tmpdir = tempfile.mkdtemp()
+        self.state = os.path.join(self.tmpdir, 'state')
+        patcher = patch.object(local_files_beacon, 'WATERMARK_DIR', self.state)
+        patcher.start()
+        self.addCleanup(patcher.stop)
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def _make_dir(self, name, files=None):
+        path = os.path.join(self.tmpdir, name)
+        os.makedirs(path, exist_ok=True)
+        for fname, content in (files or {}).items():
+            with open(os.path.join(path, fname), 'w') as f:
+                f.write(content)
+        return path
+
+    # -- trivial contract -------------------------------------------------
+
+    def test_virtual_returns_true(self):
+        self.assertTrue(local_files_beacon.__virtual__())
+
+    def test_validate_returns_valid(self):
+        self.assertEqual(local_files_beacon.validate({}), (True, 'valid'))
+
+    # -- _paths_from_config -----------------------------------------------
+
+    def test_paths_from_config_list_of_dicts(self):
+        config = [{'interval': 10}, {'paths': {'/a': 'suricata', '/b': 'strelka'}}]
+        self.assertEqual(
+            local_files_beacon._paths_from_config(config),
+            {'/a': 'suricata', '/b': 'strelka'},
+        )
+
+    def test_paths_from_config_plain_dict(self):
+        self.assertEqual(
+            local_files_beacon._paths_from_config({'paths': {'/a': 'suricata'}}),
+            {'/a': 'suricata'},
+        )
+
+    def test_paths_from_config_skips_non_dict_items(self):
+        self.assertEqual(local_files_beacon._paths_from_config(['bogus', 42]), {})
+
+    def test_paths_from_config_paths_not_a_dict(self):
+        self.assertEqual(local_files_beacon._paths_from_config({'paths': 'nope'}), {})
+
+    def test_paths_from_config_unexpected_type(self):
+        self.assertEqual(local_files_beacon._paths_from_config('nonsense'), {})
+
+    # -- _excluded --------------------------------------------------------
+
+    def test_excluded_matches_temp_and_editor_files(self):
+        for pathname in ('/rules/foo.swp', '/rules/foo~', '/rules/4913', '/rules/.#foo'):
+            self.assertTrue(local_files_beacon._excluded(pathname), pathname)
+
+    def test_excluded_allows_real_rule_files(self):
+        self.assertFalse(local_files_beacon._excluded('/rules/suricata.rules'))
+
+    # -- _fingerprint -----------------------------------------------------
+
+    def test_fingerprint_missing_dir_is_empty_tree_digest(self):
+        missing = os.path.join(self.tmpdir, 'does-not-exist')
+        self.assertEqual(local_files_beacon._fingerprint(missing), hashlib.sha1().hexdigest())
+
+    def test_fingerprint_changes_when_content_changes(self):
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'a.rules'), 'w') as f:
+            f.write('alert tcp any any -> any any')  # different size
+        self.assertNotEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_ignores_excluded_files(self):
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'a.rules.swp'), 'w') as f:
+            f.write('editor swap')
+        self.assertEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_skips_unstatable_entries(self):
+        # A dangling symlink appears in os.walk's file list but os.stat raises
+        # OSError, exercising the except-continue path.
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        good = local_files_beacon._fingerprint(d)
+        os.symlink(os.path.join(d, 'missing-target'), os.path.join(d, 'broken.link'))
+        self.assertEqual(local_files_beacon._fingerprint(d), good)
+
+    def test_fingerprint_prunes_git_metadata(self):
+        # zkg packages are git clones, so the watched tree carries .git.
+        d = self._make_dir('zkg', {'pkg.zeek': 'print 1;'})
+        before = local_files_beacon._fingerprint(d)
+        git_dir = os.path.join(d, 'pkg', '.git', 'refs', 'heads')
+        os.makedirs(git_dir)
+        with open(os.path.join(git_dir, 'main'), 'w') as f:
+            f.write('0' * 40)
+        self.assertEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_still_sees_worktree_next_to_git(self):
+        d = self._make_dir('zkg', {'pkg.zeek': 'print 1;'})
+        os.makedirs(os.path.join(d, 'pkg', '.git'))
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'pkg', 'scripts.zeek'), 'w') as f:
+            f.write('print 2;')
+        self.assertNotEqual(local_files_beacon._fingerprint(d), before)
+
+    # -- _read_watermark / _write_watermark -------------------------------
+
+    def test_watermark_round_trip(self):
+        local_files_beacon._write_watermark('suricata', '/rules/suricata', 'deadbeef')
+        self.assertEqual(
+            local_files_beacon._read_watermark('suricata', '/rules/suricata'), 'deadbeef')
+
+    def test_read_watermark_missing_returns_none(self):
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_read_watermark_empty_file_returns_none(self):
+        os.makedirs(self.state, exist_ok=True)
+        with open(local_files_beacon._watermark_file('suricata', '/rules/suricata'), 'w') as f:
+            f.write('')
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_write_watermark_swallows_oserror(self):
+        with patch.object(local_files_beacon.os, 'makedirs', side_effect=OSError):
+            local_files_beacon._write_watermark('suricata', '/rules/suricata', 'deadbeef')
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_watermark_file_differs_per_directory_within_one_tag(self):
+        # zeek/policy and zeek/zkg share the tag 'zeek'.
+        self.assertNotEqual(
+            local_files_beacon._watermark_file('zeek', '/local/zeek/policy'),
+            local_files_beacon._watermark_file('zeek', '/local/zeek/zkg'),
+        )
+
+    def test_watermarks_are_independent_within_one_tag(self):
+        local_files_beacon._write_watermark('zeek', '/local/zeek/policy', 'policyhash')
+        local_files_beacon._write_watermark('zeek', '/local/zeek/zkg', 'zkghash')
+        self.assertEqual(
+            local_files_beacon._read_watermark('zeek', '/local/zeek/policy'), 'policyhash')
+        self.assertEqual(
+            local_files_beacon._read_watermark('zeek', '/local/zeek/zkg'), 'zkghash')
+
+    # -- beacon -----------------------------------------------------------
+
+    def _config(self, mapping):
+        return [{'paths': mapping}]
+
+    def test_beacon_seeds_first_run_and_emits_nothing(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='hash1'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value=None), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [])
+        mock_write.assert_called_once_with('suricata', '/rules/suricata', 'hash1')
+
+    def test_beacon_emits_on_change(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='newhash'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value='oldhash'), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [{'tag': 'suricata', 'path': '/rules/suricata'}])
+        mock_write.assert_called_once_with('suricata', '/rules/suricata', 'newhash')
+
+    def test_beacon_no_change_emits_nothing(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='samehash'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value='samehash'), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [])
+        mock_write.assert_not_called()
+
+    def test_beacon_end_to_end_with_real_files(self):
+        # Exercise the full stack (real fingerprint + real watermark files) across
+        # two poll passes: first seeds silently, second fires after a write.
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        config = self._config({d: 'suricata'})
+
+        self.assertEqual(local_files_beacon.beacon(config), [])  # seed pass
+        self.assertEqual(local_files_beacon.beacon(config), [])  # unchanged pass
+
+        with open(os.path.join(d, 'b.rules'), 'w') as f:
+            f.write('alert tcp any any -> any any')
+        self.assertEqual(local_files_beacon.beacon(config), [{'tag': 'suricata', 'path': d}])
+
+    def test_beacon_two_dirs_one_tag_do_not_flap(self):
+        # Tag-keyed watermarks would clobber each other and emit on every pass.
+        policy = self._make_dir('zeek/policy', {'intel.dat': '#fields\tindicator'})
+        zkg = self._make_dir('zeek/zkg', {'README': 'place packages here'})
+        config = self._config({policy: 'zeek', zkg: 'zeek'})
+
+        self.assertEqual(local_files_beacon.beacon(config), [])  # seed pass
+        self.assertEqual(local_files_beacon.beacon(config), [])  # idle
+        self.assertEqual(local_files_beacon.beacon(config), [])  # still idle
+
+        with open(os.path.join(policy, 'intel.dat'), 'a') as f:
+            f.write('\nevil.com\tIntel::DOMAIN\tsource\n')
+        self.assertEqual(local_files_beacon.beacon(config), [{'tag': 'zeek', 'path': policy}])
+        self.assertEqual(local_files_beacon.beacon(config), [])  # quiet again
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/_beacons/rules_beacon_test.py

@@ -1,172 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-import hashlib
-import os
-import shutil
-import tempfile
-import unittest
-from unittest.mock import patch
-
-import rules_beacon
-
-
-class TestRulesBeacon(unittest.TestCase):
-
-    def setUp(self):
-        # Isolate all on-disk state (watermarks and the dirs we fingerprint) in a
-        # throwaway tree, and point WATERMARK_DIR at it so the real read/write
-        # helpers run against actual files.
-        self.tmpdir = tempfile.mkdtemp()
-        self.state = os.path.join(self.tmpdir, 'state')
-        patcher = patch.object(rules_beacon, 'WATERMARK_DIR', self.state)
-        patcher.start()
-        self.addCleanup(patcher.stop)
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def _make_dir(self, name, files=None):
-        path = os.path.join(self.tmpdir, name)
-        os.makedirs(path, exist_ok=True)
-        for fname, content in (files or {}).items():
-            with open(os.path.join(path, fname), 'w') as f:
-                f.write(content)
-        return path
-
-    # -- trivial contract -------------------------------------------------
-
-    def test_virtual_returns_true(self):
-        self.assertTrue(rules_beacon.__virtual__())
-
-    def test_validate_returns_valid(self):
-        self.assertEqual(rules_beacon.validate({}), (True, 'valid'))
-
-    # -- _paths_from_config -----------------------------------------------
-
-    def test_paths_from_config_list_of_dicts(self):
-        config = [{'interval': 10}, {'paths': {'/a': 'suricata', '/b': 'strelka'}}]
-        self.assertEqual(
-            rules_beacon._paths_from_config(config),
-            {'/a': 'suricata', '/b': 'strelka'},
-        )
-
-    def test_paths_from_config_plain_dict(self):
-        self.assertEqual(
-            rules_beacon._paths_from_config({'paths': {'/a': 'suricata'}}),
-            {'/a': 'suricata'},
-        )
-
-    def test_paths_from_config_skips_non_dict_items(self):
-        self.assertEqual(rules_beacon._paths_from_config(['bogus', 42]), {})
-
-    def test_paths_from_config_paths_not_a_dict(self):
-        self.assertEqual(rules_beacon._paths_from_config({'paths': 'nope'}), {})
-
-    def test_paths_from_config_unexpected_type(self):
-        self.assertEqual(rules_beacon._paths_from_config('nonsense'), {})
-
-    # -- _excluded --------------------------------------------------------
-
-    def test_excluded_matches_temp_and_editor_files(self):
-        for pathname in ('/rules/foo.swp', '/rules/foo~', '/rules/4913', '/rules/.#foo'):
-            self.assertTrue(rules_beacon._excluded(pathname), pathname)
-
-    def test_excluded_allows_real_rule_files(self):
-        self.assertFalse(rules_beacon._excluded('/rules/suricata.rules'))
-
-    # -- _fingerprint -----------------------------------------------------
-
-    def test_fingerprint_missing_dir_is_empty_tree_digest(self):
-        missing = os.path.join(self.tmpdir, 'does-not-exist')
-        self.assertEqual(rules_beacon._fingerprint(missing), hashlib.sha1().hexdigest())
-
-    def test_fingerprint_changes_when_content_changes(self):
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        before = rules_beacon._fingerprint(d)
-        with open(os.path.join(d, 'a.rules'), 'w') as f:
-            f.write('alert tcp any any -> any any')  # different size
-        self.assertNotEqual(rules_beacon._fingerprint(d), before)
-
-    def test_fingerprint_ignores_excluded_files(self):
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        before = rules_beacon._fingerprint(d)
-        with open(os.path.join(d, 'a.rules.swp'), 'w') as f:
-            f.write('editor swap')
-        self.assertEqual(rules_beacon._fingerprint(d), before)
-
-    def test_fingerprint_skips_unstatable_entries(self):
-        # A dangling symlink appears in os.walk's file list but os.stat raises
-        # OSError, exercising the except-continue path.
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        good = rules_beacon._fingerprint(d)
-        os.symlink(os.path.join(d, 'missing-target'), os.path.join(d, 'broken.link'))
-        self.assertEqual(rules_beacon._fingerprint(d), good)
-
-    # -- _read_watermark / _write_watermark -------------------------------
-
-    def test_watermark_round_trip(self):
-        rules_beacon._write_watermark('suricata', 'deadbeef')
-        self.assertEqual(rules_beacon._read_watermark('suricata'), 'deadbeef')
-
-    def test_read_watermark_missing_returns_none(self):
-        self.assertIsNone(rules_beacon._read_watermark('suricata'))
-
-    def test_read_watermark_empty_file_returns_none(self):
-        os.makedirs(self.state, exist_ok=True)
-        with open(rules_beacon._watermark_file('suricata'), 'w') as f:
-            f.write('')
-        self.assertIsNone(rules_beacon._read_watermark('suricata'))
-
-    def test_write_watermark_swallows_oserror(self):
-        with patch.object(rules_beacon.os, 'makedirs', side_effect=OSError):
-            rules_beacon._write_watermark('suricata', 'deadbeef')
-        self.assertIsNone(rules_beacon._read_watermark('suricata'))
-
-    # -- beacon -----------------------------------------------------------
-
-    def _config(self, mapping):
-        return [{'paths': mapping}]
-
-    def test_beacon_seeds_first_run_and_emits_nothing(self):
-        with patch.object(rules_beacon, '_fingerprint', return_value='hash1'), \
-             patch.object(rules_beacon, '_read_watermark', return_value=None), \
-             patch.object(rules_beacon, '_write_watermark') as mock_write:
-            result = rules_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
-        self.assertEqual(result, [])
-        mock_write.assert_called_once_with('suricata', 'hash1')
-
-    def test_beacon_emits_on_change(self):
-        with patch.object(rules_beacon, '_fingerprint', return_value='newhash'), \
-             patch.object(rules_beacon, '_read_watermark', return_value='oldhash'), \
-             patch.object(rules_beacon, '_write_watermark') as mock_write:
-            result = rules_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
-        self.assertEqual(result, [{'tag': 'suricata', 'path': '/rules/suricata'}])
-        mock_write.assert_called_once_with('suricata', 'newhash')
-
-    def test_beacon_no_change_emits_nothing(self):
-        with patch.object(rules_beacon, '_fingerprint', return_value='samehash'), \
-             patch.object(rules_beacon, '_read_watermark', return_value='samehash'), \
-             patch.object(rules_beacon, '_write_watermark') as mock_write:
-            result = rules_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
-        self.assertEqual(result, [])
-        mock_write.assert_not_called()
-
-    def test_beacon_end_to_end_with_real_files(self):
-        # Exercise the full stack (real fingerprint + real watermark files) across
-        # two poll passes: first seeds silently, second fires after a write.
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        config = self._config({d: 'suricata'})
-
-        self.assertEqual(rules_beacon.beacon(config), [])  # seed pass
-        self.assertEqual(rules_beacon.beacon(config), [])  # unchanged pass
-
-        with open(os.path.join(d, 'b.rules'), 'w') as f:
-            f.write('alert tcp any any -> any any')
-        self.assertEqual(rules_beacon.beacon(config), [{'tag': 'suricata', 'path': d}])
-
-
-if __name__ == '__main__':
-    unittest.main()

salt/common/init.sls

@@ -117,14 +117,25 @@ elastic_curl_config:
 {% endif %}
 
 
+# A non-root owner here can chmod the directory and replace any script in it, including
+# the root-owned ones. 555 is the mode the filesystem RPM ships; root ignores it anyway.
+usr_sbin_perms:
+  file.directory:
+    - name: /usr/sbin
+    - user: root
+    - group: root
+    - mode: 555
+
 common_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - show_changes: False
+    - require:
+      - file: usr_sbin_perms
 {% if GLOBALS.role == 'so-heavynode' %}
     - exclude_pat:
       - so-pcap-import
@@ -141,12 +152,26 @@ pin_nic_names:
       - file: common_sbin
       - file: statedir
 
+# Once a node is actually running UEK8, the stock EL9 (RHCK) kernel packages are dead weight.
+# They can't be removed any earlier -- dnf protects the running kernel -- so the cleanup waits
+# for the reboot, which makes the highstate the natural place to catch it: fresh installs
+# reboot at the end of setup, and upgraded nodes reboot whenever the admin schedules it.
+# so-kernel-upgrade --cleanup checks rpm before touching dnf, so this costs an rpm query on
+# every highstate after the first pass. The package list lives in the script only, so there
+# is nothing here to drift out of sync with it.
+remove_stock_kernel:
+  cmd.run:
+    - name: /usr/sbin/so-kernel-upgrade --cleanup
+    - onlyif: 'uname -r | grep -qE "^6\.[0-9]+.*uek"'
+    - require:
+      - file: common_sbin
+
 common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -159,6 +184,8 @@ so-status_script:
   file.managed:
     - name: /usr/sbin/so-status
     - source: salt://common/tools/sbin/so-status
+    - user: root
+    - group: root
     - mode: 755
 
 {% if GLOBALS.is_sensor %}

salt/common/soup_scripts.sls

@@ -18,47 +18,61 @@ copy_so-common_common_tools_sbin:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_common_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/salt/scripts/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 644
 
 # This section is used to put the new script in place so that it can be called during soup.
 # It is faster than calling the states that normally manage them to put them in place.
@@ -67,46 +81,60 @@ copy_so-common_sbin:
     - name: /usr/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_sbin:
   file.copy:
     - name: /usr/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_sbin:
   file.copy:
     - name: /usr/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_sbin:
   file.copy:
     - name: /usr/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_sbin:
   file.copy:
     - name: /usr/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_sbin:
   file.copy:
     - name: /usr/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_sbin:
   file.copy:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755

salt/common/tools/sbin/so-common

@@ -240,7 +240,8 @@ copy_new_files() {
   cd $UPDATE_DIR
   rsync -a salt $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
   rsync -a pillar $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
-  chown -R socore:socore $DEFAULT_SALT_DIR/
+  # Root-executed code; SOC only needs to read it. Local dirs stay socore-owned.
+  chown -R root:root $DEFAULT_SALT_DIR/
   cd /tmp
 }
 
@@ -418,6 +419,19 @@ is_single_node_grid() {
 	grep "role: so-" /etc/salt/grains | grep -E "eval|standalone|import" &> /dev/null
 }
 
+remove_elasticsearch_index_template() {
+  local template_name=$1
+  local reason=${2:-"Removing index template for upgrade"}
+
+  # check if template exists
+  if so-elasticsearch-query "_index_template/$template_name" --fail --retry 3 --retry-delay 5 >/dev/null 2>&1; then
+    echo "Removing Elasticsearch index template: $template_name ($reason)"
+    if ! so-elasticsearch-query "_index_template/$template_name" -XDELETE --fail --retry 3 --retry-delay 5; then
+      return 1
+    fi
+  fi
+}
+
 initialize_elasticsearch_indices() {
     local index_names=$1
     local default_entry=${2:-'{"@timestamp":"0"}'}

salt/common/tools/sbin/so-kernel-upgrade

@@ -5,10 +5,11 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 #
-# so-kernel-upgrade — install the UEK8 (6.x) kernel and make it the boot default.
+# so-kernel-upgrade — install the UEK8 (6.x) kernel, make it the boot default, and once the
+# node is running it, remove the stock EL9 kernel.
 #
 # Security Onion is moving off the EL9 stock kernel (RHCK, 5.14) and UEK7 (5.15) onto UEK8
-# (6.x). Three things have to happen, and the tool has to drive each one:
+# (6.x). Four things have to happen, and the tool has to drive each one:
 #
 #   1. Populate. The manager mirrors the UEK8 packages into /nsm/kernelrepo via so-repo-sync,
 #      and serves them to the grid over https://<manager>/kernelrepo. Until that sync runs the
@@ -26,10 +27,21 @@
 #        - From the stock EL9 kernel (RHCK, 5.14, no UEK) it is a flavor CROSS that is NOT
 #          auto-promoted, so the box keeps booting RHCK until grubby is told otherwise.
 #      This tool inspects the running kernel and only runs 'grubby --set-default' for RHCK.
+#   4. Clean up. Once the node is actually RUNNING UEK8 the stock kernel packages are dead
+#      weight -- disk in /boot and a stale GRUB entry. They cannot come off any earlier:
+#      dnf's protect_running_kernel refuses to erase the booted kernel-core, so the removal
+#      has to wait for the reboot. Waiting is also the safer sequencing on its own terms --
+#      the node has proven it comes up on UEK8 before its fallback is deleted. That is why
+#      the removal does not happen in the uek7 branch either, where dnf would allow it.
 #
 # Every one of those failure modes is silent by default. This tool handles each case and fails
 # loudly when it cannot, rather than reporting success while changing nothing.
 #
+# Invocation: with no arguments it drives the whole sequence for whatever kernel the node is
+# on. With --cleanup it does the step 4 removal ONLY, and no-ops on a node that isn't running
+# UEK8 yet -- that is the form the common highstate calls (remove_stock_kernel in
+# salt/common/init.sls) so the cleanup lands grid-wide after each node reboots.
+#
 # Manager vs minion: only the manager owns /nsm/kernelrepo, so only the manager can populate
 # it. If the repo is empty here, a manager runs so-repo-sync itself; a minion has no way to
 # fix it and exits non-zero telling the admin to sync the manager first.
@@ -49,6 +61,11 @@ KERNEL_REPO_DIR="/nsm/kernelrepo"
 REPOSYNC_CONF="/opt/so/conf/reposync/repodownload.conf"
 GLOBAL_PILLAR="/opt/so/saltstack/local/pillar/global/soc_global.sls"
 
+# Stock EL9 (RHCK) kernel packages, removed only once the node is running UEK8 (see step 4
+# in the header). Left deliberately narrow: UEK7 kernel-uek builds age out on their own via
+# installonly_limit=3, and kernel-devel/kernel-headers are not touched.
+RHCK_PKGS="kernel kernel-core kernel-modules kernel-modules-core kernel-tools kernel-tools-libs"
+
 log() { echo "[so-kernel-upgrade] $*"; }
 die() { echo "[so-kernel-upgrade] ERROR: $*" >&2; exit 1; }
 
@@ -149,8 +166,13 @@ ensure_kernel_repo() {
 }
 
 reboot_notice() {
-    [ "$(uname -r)" = "$(basename "$1" | sed 's/^vmlinuz-//')" ] \
-        || log "REBOOT REQUIRED to start using the UEK8 kernel (currently running $(uname -r))."
+    [ "$(uname -r)" = "$(basename "$1" | sed 's/^vmlinuz-//')" ] && return 0
+    log "REBOOT REQUIRED to start using the UEK8 kernel (currently running $(uname -r))."
+    # The stock kernel can't be removed until it stops being the running one, so say when
+    # that will happen rather than leaving the admin to wonder if it was missed.
+    [ -n "$(rhck_installed)" ] \
+        && log "The stock EL9 kernel is left in place until then; it is removed by the next highstate after the reboot."
+    return 0
 }
 
 # Keep future kernel updates on the UEK line rather than falling back to RHCK. Oracle ships
@@ -162,6 +184,32 @@ set_default_kernel_conf() {
     fi
 }
 
+# Which of RHCK_PKGS are actually installed, one per line. rpm -qa treats each argument as a
+# name glob and prints only what it finds, so a package that was never installed (or is
+# already gone) simply doesn't appear -- no "not installed" noise and no non-zero exit.
+rhck_installed() {
+    rpm -qa $RHCK_PKGS 2>/dev/null
+}
+
+# Remove the stock EL9 kernel. Only ever called once the running kernel is UEK8. The rpm
+# check above is the idempotency guard, so this is a cheap no-op on every highstate after
+# the first one -- it costs an rpm query, not a dnf transaction.
+remove_rhck() {
+    local installed; installed="$(rhck_installed)"
+    if [ -z "$installed" ]; then
+        log "no stock EL9 (RHCK) kernel packages installed; nothing to remove."
+        return 0
+    fi
+
+    log "running UEK8; removing the stock EL9 (RHCK) kernel packages:"
+    echo "$installed" | sed 's/^/[so-kernel-upgrade]   /'
+    dnf -y remove $RHCK_PKGS || die "failed to remove the stock EL9 kernel packages"
+
+    installed="$(rhck_installed)"
+    [ -z "$installed" ] || die "dnf reported success but these remain: $(echo $installed)"
+    log "stock EL9 kernel packages removed."
+}
+
 # Make sure a UEK8 kernel is installed, leaving its boot entry in INSTALLED_UEK8. If one is
 # already present we leave the repo alone -- it may be disabled or empty and we don't need it
 # just to flip the boot default. Otherwise install the explicit NEVRA, not the bare package
@@ -184,12 +232,38 @@ ensure_uek8_installed() {
     log "installed UEK8 kernel: $INSTALLED_UEK8"
 }
 
+# --cleanup does step 4 and nothing else. It exits 0 rather than failing on a node that
+# isn't on UEK8 yet: the highstate gates on 'uname -r' before calling this, and a state that
+# fails whenever that gate races would be worse than one that says what it's waiting for.
+case "$1" in
+"")
+    ;;
+--cleanup)
+    if [ "$(running_flavor)" != uek8 ]; then
+        log "not running a UEK8 kernel yet (currently $(uname -r)); leaving the stock EL9 kernel in place."
+        log "Run so-kernel-upgrade with no arguments to install UEK8, then reboot."
+        exit 0
+    fi
+    set_default_kernel_conf
+    remove_rhck
+    exit 0
+    ;;
+*)
+    echo "Usage: so-kernel-upgrade [--cleanup]" >&2
+    echo "  (no arguments)  install UEK8, make it the boot default, clean up once it's running" >&2
+    echo "  --cleanup       remove the stock EL9 kernel; no-op unless already running UEK8" >&2
+    exit 1
+    ;;
+esac
+
 case "$(running_flavor)" in
 uek8)
     # Already on the 6.x UEK line. A plain 'dnf update' keeps this node current within the
-    # lineage and auto-promotes newer builds, so there is nothing for this tool to do.
-    log "already running a UEK8 kernel ($(uname -r)); nothing to do."
-    exit 0
+    # lineage and auto-promotes newer builds, so there is no install or grubby work left --
+    # only the step 4 cleanup, which this is the first point in the sequence that can run it.
+    log "already running a UEK8 kernel ($(uname -r)); no kernel install needed."
+    set_default_kernel_conf
+    remove_rhck
     ;;
 
 uek7)

salt/common/tools/sbin/so-log-check

@@ -134,6 +134,7 @@ if [[ $EXCLUDE_STARTUP_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Redis may have been restarted" # Redis likely restarted by salt
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|file already closed"          # Go logging race condition during container restart
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|relation \"audit_settings\" does not exist" # salt checking for changes before SOC starts
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Error in plugin: elasticsearch: Unable to retrieve master node information" # expected error while ES is upgrading/electing a master 
 fi
 
 if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
@@ -154,6 +155,8 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|id.orig_h"                    # false positive (zeek test data)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|emerging-all.rules"           # false positive (error in rulename)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|invalid query input"          # false positive (Invalid user input in hunt query)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|no data available for the requested dates" # false positive (pcap cypress test submits a job with an empty time frame)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|no job processor"             # false positive (same empty-time-frame job on import nodes, where no pcap processor runs)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|example"                      # false positive (example test data)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|status 200"                   # false positive (request successful, contained error string in content)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|app_layer.error"              # false positive (suricata 7) in stats.log e.g. app_layer.error.imap.parser | Total | 0
@@ -169,6 +172,11 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Error while parsing document for index \[.ds-logs-kratos-so-.*object mapping for \[file\]" # false positive (mapping error occuring BEFORE kratos index has rolled over in 2.4.210)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|No such container"            # false positive (telegraf trying to run stats on an old container)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|passwords do not match"       # false positive (automated hydra test)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Request did not pass preprocessing" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing or invalid authorization header for bearer token" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Unexpected authorization header" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing ory_kratos_session cookie" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Static assets preprocessor only supports GET and HEAD requests" # expected WARN log lines indicating invalid auth header
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
@@ -231,8 +239,9 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|from NIC checksum offloading" # zeek reporter.log
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|marked for removal"           # docker container getting recycled
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|tcp 127.0.0.1:6791: bind: address already in use" # so-elastic-fleet agent restarting. Seen starting w/ 8.18.8 https://github.com/elastic/kibana/issues/201459
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-(tychon|aws_billing|microsoft_defender_endpoint|armis|o365_metrics|microsoft_sentinel|snyk|cyera|island_browser).*user so_kibana lacks the required permissions \[(logs|metrics)-\1" # Known issue with integrations starting transform jobs that are explicitly not allowed to start as a system user. This error should not be seen on fresh ES 9.3.3 installs or after SO 3.1.0 with soups addition of check_transform_health_and_reauthorize()
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-.*user so_kibana lacks the required permissions" # Known issue with integrations starting transform jobs that are explicitly not allowed to start as a system user
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # appears in so-dockerregistry log for so-tcpreplay following docker upgrade to 29.2.1-1
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Could not index event to Elasticsearch.*\"version\" => \"9.0.8\"" # Expected during Elastic upgrade temporarily, as policies referencing older pipelines are updated
 fi
 
 RESULT=0
@@ -297,4 +306,4 @@ else
     echo -e "\nResult: One or more errors found"
 fi
 
-exit $RESULT
+exit $RESULT

salt/common/tools/sbin/so-restart

@@ -35,9 +35,6 @@ case $1 in
     "elastic-fleet"|"elasticfleet")
         docker_check_running "elastic-fleet" "--stop"
         docker rm "so-elastic-fleet" 2> /dev/null
-        # Removing the elastic fleet state directory, so that the next startup re-enrolls with a fresh policy
-        rm -rf /opt/so/conf/elastic-fleet/state
-
         salt-call state.apply elasticfleet queue=True
         ;;
     *)

salt/common/tools/sbin/so-sensor-clean

@@ -8,21 +8,37 @@
 # Elastic License 2.0.
 
 
-SENSOR_DIR='/nsm'
+SENSOR_DIR="${SENSOR_DIR:-/nsm}"
 CRIT_DISK_USAGE=90
-CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
-LOG="/opt/so/log/sensor_clean.log"
-TODAY=$(date -u "+%Y-%m-%d")
+LOG="${LOG:-/opt/so/log/sensor_clean.log}"
+LOCK="${LOCK:-/var/tmp/so-sensor-clean.lock}"
+MAX_PASSES=100
 
+ZEEK_LOGS="$SENSOR_DIR/zeek/logs"
+STRELKA_FILES="$SENSOR_DIR/strelka/processed"
+SURICATA_LOGS="$SENSOR_DIR/suricata"
+PCAPS="$SENSOR_DIR/pcapout"
+
+log() {
+	echo "$(date) - $*" >>"$LOG"
+}
+
+disk_usage() {
+	df -P "$SENSOR_DIR" | tail -1 | awk '{print $5}' | tr -d %
+}
+
+disk_avail() {
+	df -P "$SENSOR_DIR" | tail -1 | awk '{print $4}'
+}
+
+# sets REMOVED=1 if anything was actually deleted
 clean() {
 	## find the oldest Zeek logs directory
-	OLDEST_DIR=$(ls /nsm/zeek/logs/ | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
-	if [ -z "$OLDEST_DIR" -o "$OLDEST_DIR" == ".." -o "$OLDEST_DIR" == "." ]; then
-		echo "$(date) - No old Zeek logs available to clean up in /nsm/zeek/logs/" >>$LOG
-		#exit 0
-	else
-		echo "$(date) - Removing directory: /nsm/zeek/logs/$OLDEST_DIR" >>$LOG
-		rm -rf /nsm/zeek/logs/"$OLDEST_DIR"
+	OLDEST_DIR=$(ls "$ZEEK_LOGS" 2>/dev/null | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
+	if [ -n "$OLDEST_DIR" ]; then
+		log "Removing directory: $ZEEK_LOGS/$OLDEST_DIR"
+		rm -rf "$ZEEK_LOGS/$OLDEST_DIR"
+		REMOVED=1
 	fi
 
 	## Remarking for now, as we are moving extracted files to /nsm/strelka/processed
@@ -43,58 +59,73 @@ clean() {
 	#fi
 
 	## Clean up Zeek extracted files processed by Strelka
-	STRELKA_FILES='/nsm/strelka/processed'
-	OLDEST_STRELKA=$(find $STRELKA_FILES -type f -printf '%T+ %p\n' | sort -n | head -n 1)
-	if [ -z "$OLDEST_STRELKA" -o "$OLDEST_STRELKA" == ".." -o "$OLDEST_STRELKA" == "." ]; then
-		echo "$(date) - No old files available to clean up in $STRELKA_FILES" >>$LOG
-	else
+	OLDEST_STRELKA=$(find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_STRELKA" ]; then
 		OLDEST_STRELKA_DATE=$(echo $OLDEST_STRELKA | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_STRELKA_FILE=$(echo $OLDEST_STRELKA | awk '{print $2}')
-		echo "$(date) - Removing extracted files for $OLDEST_STRELKA_DATE" >>$LOG
-		find $STRELKA_FILES -type f -printf '%T+ %p\n' | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+		log "Removing extracted files for $OLDEST_STRELKA_DATE"
+		REMOVED=1
+		find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up Suricata log files
-	SURICATA_LOGS='/nsm/suricata'
-	OLDEST_SURICATA=$(find $SURICATA_LOGS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
-	if [[ -z "$OLDEST_SURICATA" ]] || [[ "$OLDEST_SURICATA" == ".." ]] || [[ "$OLDEST_SURICATA" == "." ]]; then
-		echo "$(date) - No old files available to clean up in $SURICATA_LOGS" >>$LOG
-	else
+	OLDEST_SURICATA=$(find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_SURICATA" ]; then
 		OLDEST_SURICATA_DATE=$(echo $OLDEST_SURICATA | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_SURICATA_FILE=$(echo $OLDEST_SURICATA | awk '{print $2}')
-		echo "$(date) - Removing logs for $OLDEST_SURICATA_DATE" >>$LOG
-		find $SURICATA_LOGS -type f -printf '%T+ %p\n' | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+		log "Removing logs for $OLDEST_SURICATA_DATE"
+		REMOVED=1
+		find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up extracted pcaps
-	PCAPS='/nsm/pcapout'
-	OLDEST_PCAP=$(find $PCAPS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
-	if [ -z "$OLDEST_PCAP" -o "$OLDEST_PCAP" == ".." -o "$OLDEST_PCAP" == "." ]; then
-		echo "$(date) - No old files available to clean up in $PCAPS" >>$LOG
-	else
+	OLDEST_PCAP=$(find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_PCAP" ]; then
 		OLDEST_PCAP_DATE=$(echo $OLDEST_PCAP | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_PCAP_FILE=$(echo $OLDEST_PCAP | awk '{print $2}')
-		echo "$(date) - Removing extracted files for $OLDEST_PCAP_DATE" >>$LOG
-		find $PCAPS -type f -printf '%T+ %p\n' | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+		log "Removing extracted files for $OLDEST_PCAP_DATE"
+		REMOVED=1
+		find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 }
 
-# Check to see if we are already running
-NUM_RUNNING=$(pgrep -cf "/bin/bash /usr/sbin/so-sensor-clean")
-[ "$NUM_RUNNING" -gt 1 ] && echo "$(date) - $NUM_RUNNING sensor clean script processes running...exiting." >>$LOG && exit 0
-
-if [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; then
-	while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
-		clean
-		CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
-	done
+# Only one instance at a time; the lock is the fd, so it releases on any exit
+exec 9>"$LOCK" || exit 1
+if ! flock -n 9; then
+	log "another so-sensor-clean is already running (lock $LOCK held); exiting"
+	exit 0
 fi
+
+CUR_USAGE=$(disk_usage)
+[ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ] || exit 0
+
+log "$SENSOR_DIR at ${CUR_USAGE}% (threshold ${CRIT_DISK_USAGE}%); starting cleanup"
+
+PASS=0
+while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
+	PASS=$((PASS + 1))
+	if [ "$PASS" -gt "$MAX_PASSES" ]; then
+		log "stopping after $MAX_PASSES passes; $SENSOR_DIR still at ${CUR_USAGE}%"
+		break
+	fi
+
+	REMOVED=0
+	BEFORE=$(disk_avail)
+	clean
+	CUR_USAGE=$(disk_usage)
+
+	if [ "$REMOVED" -eq 0 ]; then
+		log "nothing left to remove in $ZEEK_LOGS, $STRELKA_FILES, $SURICATA_LOGS, $PCAPS; $SENSOR_DIR still at ${CUR_USAGE}% - space is consumed outside of NSM cleanup scope"
+		break
+	fi
+	if [ "$(disk_avail)" -le "$BEFORE" ]; then
+		log "pass $PASS freed no space; $SENSOR_DIR still at ${CUR_USAGE}% - stopping until next run"
+		break
+	fi
+done

salt/common/tools/sbin/so-stop

@@ -29,8 +29,6 @@ case $1 in
 	"elasticfleet"|"elastic-fleet")
         docker_check_running "elastic-fleet" "--stop"
         docker rm "so-elastic-fleet" 2> /dev/null
-        # Removing the elastic fleet state directory, so that the next startup re-enrolls with a fresh policy
-        rm -rf /opt/so/conf/elastic-fleet/state
         ;;
     *)
         docker_check_running "$1" "--stop"

salt/common/tools/sbin_jinja/so-salt-minion-check

@@ -25,7 +25,7 @@ LAST_HIGHSTATE_END=$([ -e "/opt/so/log/salt/lasthighstate" ] && date -r /opt/so/
 LAST_HEALTHCHECK_STATE_APPLY=$([ -e "/opt/so/log/salt/state-apply-test" ] && date -r /opt/so/log/salt/state-apply-test +%s || echo 0)
 # SETTING THRESHOLD TO ANYTHING UNDER 600 seconds may cause a lot of salt-minion restarts since the job to touch the file occurs every 5-8 minutes by default
 # THRESHOLD is derived from the salt schedule highstate interval + 1 hour, so the minion-check grace period tracks the schedule automatically.
-THRESHOLD=$(( ({{ SCHEDULEMERGED.highstate_interval_hours }} + 1) * 3600 )) #within how many seconds the file /opt/so/log/salt/state-apply-test must have been touched/modified before the salt minion is restarted
+THRESHOLD=$(( ({{ SCHEDULEMERGED.highstate_interval_minutes }} + 60) * 60 )) #within how many seconds the file /opt/so/log/salt/state-apply-test must have been touched/modified before the salt minion is restarted
 THRESHOLD_DATE=$((LAST_HEALTHCHECK_STATE_APPLY+THRESHOLD))
 
 logCmd() {

salt/docker/defaults.yaml

@@ -1,6 +1,12 @@
 docker:
   range: '172.17.1.0/24'
   gateway: '172.17.1.1'
+  networks:
+    sobridge: {}
+    soauth:
+      range: '172.17.2.0/24'
+      gateway: '172.17.2.1'
+      manager_only: True
   ulimits:
     - name: nofile
       soft: 1048576
@@ -58,18 +64,18 @@ docker:
       ulimits: []
     'so-kratos':
       final_octet: 28
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4433:4433
-        - 0.0.0.0:4434:4434
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
       ulimits: []
     'so-hydra':
       final_octet: 30
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4444:4444
-        - 0.0.0.0:4445:4445
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
@@ -128,6 +134,7 @@ docker:
       ulimits: []
     'so-soc':
       final_octet: 34
+      networks: ['sobridge', 'soauth']
       port_bindings:
         - 0.0.0.0:9822:9822
       custom_bind_mounts: []

salt/docker/docker.map.jinja

@@ -1,8 +1,26 @@
 {% import_yaml 'docker/defaults.yaml' as DOCKERDEFAULTS %}
 {% set DOCKERMERGED = salt['pillar.get']('docker', DOCKERDEFAULTS.docker, merge=True) %}
-{% set RANGESPLIT = DOCKERMERGED.range.split('.') %}
-{% set FIRSTTHREE = RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.' %}
+
+{% if DOCKERMERGED.networks.sobridge is not mapping %}
+{%   do DOCKERMERGED.networks.update({'sobridge': {}}) %}
+{% endif %}
+{% do DOCKERMERGED.networks['sobridge'].update({'range': DOCKERMERGED.range, 'gateway': DOCKERMERGED.gateway}) %}
+
+{% for netname, net in DOCKERMERGED.networks.items() %}
+{%   set RANGESPLIT = net.range.split('.') %}
+{%   do net.update({'prefix': RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.'}) %}
+{% endfor %}
 
 {% for container, vals in DOCKERMERGED.containers.items() %}
-{%   do DOCKERMERGED.containers[container].update({'ip': FIRSTTHREE ~ DOCKERMERGED.containers[container].final_octet}) %}
+{%   set CONTAINER_NETS = vals.get('networks', ['sobridge']) %}
+{%   set IPS = {} %}
+{%   for netname in CONTAINER_NETS %}
+{%     do IPS.update({netname: DOCKERMERGED.networks[netname].prefix ~ vals.final_octet}) %}
+{%   endfor %}
+{%   do DOCKERMERGED.containers[container].update({
+         'networks': CONTAINER_NETS,
+         'ips': IPS,
+         'network': CONTAINER_NETS[0],
+         'ip': IPS[CONTAINER_NETS[0]]
+       }) %}
 {% endfor %}

salt/docker/init.sls

@@ -71,15 +71,19 @@ dockerreserveports:
     - source: salt://common/files/99-reserved-ports.conf
     - name: /etc/sysctl.d/99-reserved-ports.conf
 
-sos_docker_net:
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{% if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+sos_docker_net_{{ NETNAME }}:
   docker_network.present:
-    - name: sobridge
-    - subnet: {{ DOCKERMERGED.range }}
-    - gateway: {{ DOCKERMERGED.gateway }}
+    - name: {{ NETNAME }}
+    - subnet: {{ NETWORK.range }}
+    - gateway: {{ NETWORK.gateway }}
     - options:
-        com.docker.network.bridge.name: 'sobridge'
+        com.docker.network.bridge.name: '{{ NETNAME }}'
         com.docker.network.driver.mtu: '1500'
         com.docker.network.bridge.enable_ip_masquerade: 'true'
         com.docker.network.bridge.enable_icc: 'true'
         com.docker.network.bridge.host_binding_ipv4: '0.0.0.0'
-    - unless: ip l | grep sobridge
+    - unless: ip l | grep {{ NETNAME }}
+{% endif %}
+{% endfor %}

salt/docker/soc_docker.yaml

@@ -7,6 +7,40 @@ docker:
     description: Default docker IP range for containers.
     helpLink: docker
     advanced: True
+  networks:
+    sobridge:
+      description: |
+        The default docker network, carrying most containers. Its range and gateway are taken
+        from the docker.range and docker.gateway settings above rather than set here.
+      helpLink: docker
+      readonly: True
+      advanced: True
+      global: True
+    soauth:
+      range:
+        description: |
+          IP range for the soauth docker network, an isolated network for the authentication
+          services, so that the Kratos and Hydra admin APIs are only reachable from the
+          containers placed on it.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      gateway:
+        description: Gateway for the soauth docker network.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      manager_only:
+        description: |
+          Limits the soauth network to grid members running the authentication containers,
+          instead of creating it on every node.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: bool
   ulimits:
     description: |
       Default ulimit settings applied to all containers via the Docker daemon. Each entry specifies a resource name (e.g. nofile, memlock, core, nproc) with soft and hard limits. Individual container ulimits override these defaults. Valid resource names include: cpu, fsize, data, stack, core, rss, nproc, nofile, memlock, as, locks, sigpending, msgqueue, nice, rtprio, rttime.
@@ -34,6 +68,16 @@ docker:
         readonly: True
         advanced: True
         global: True
+      networks:
+        description: |
+          Docker networks this container is attached to. The first entry is the container's
+          primary network and determines the address its published ports are forwarded to.
+          Defaults to sobridge when unset.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: "[]string"
       port_bindings:
         description: List of port bindings for the container.
         helpLink: docker

salt/elastalert/config.sls

@@ -33,8 +33,8 @@ elastalert_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elastalert/tools/sbin
-    - user: 933
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #elastalert_sbin_jinja:

salt/elasticagent/config.sls

@@ -39,8 +39,8 @@ elasticagent_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticagent/tools/sbin_jinja
-    - user: 949
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/elasticfleet/config.sls

@@ -31,8 +31,8 @@ elasticfleet_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - show_changes: False
 
@@ -40,8 +40,8 @@ elasticfleet_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin_jinja
-    - user: 947
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -81,8 +81,8 @@ eapackageupgrade:
   file.managed:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - source: salt://elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - template: jinja
 

salt/elasticfleet/enabled.sls

@@ -11,10 +11,6 @@
 
 {#   This value is generated during node install and stored in minion pillar #}
 {%   set SERVICETOKEN = salt['pillar.get']('elasticfleet:config:server:es_token','') %}
-{#   Prevent Elastic Agent from re-enrolling with a new agent.id everytime the container starts up.
-       - if a fresh enrollment is needed use 'so-stop elasticfleet'
-       #}
-{%   set ENROLLED = salt['file.file_exists']('/opt/so/conf/elastic-fleet/state/fleet.enc') %}
 
 include:
   - ca
@@ -70,7 +66,6 @@ so-elastic-fleet:
       - /etc/pki/elasticfleet-server.crt:/etc/pki/elasticfleet-server.crt:ro
       - /etc/pki/elasticfleet-server.key:/etc/pki/elasticfleet-server.key:ro
       - /etc/pki/tls/certs/intca.crt:/etc/pki/tls/certs/intca.crt:ro
-      - /opt/so/conf/elastic-fleet/state:/usr/share/elastic-agent/state
       - /opt/so/log/elasticfleet:/usr/share/elastic-agent/logs 
      {% if DOCKERMERGED.containers['so-elastic-fleet'].custom_bind_mounts %}
         {% for BIND in DOCKERMERGED.containers['so-elastic-fleet'].custom_bind_mounts %}
@@ -78,7 +73,6 @@ so-elastic-fleet:
         {% endfor %}
       {% endif %}      
     - environment:
-      {% if not ENROLLED %}
       - FLEET_SERVER_ENABLE=true
       - FLEET_URL=https://{{ GLOBALS.hostname }}:8220
       - FLEET_SERVER_ELASTICSEARCH_HOST=https://{{ GLOBALS.manager }}:9200
@@ -88,9 +82,6 @@ so-elastic-fleet:
       - FLEET_SERVER_CERT_KEY=/etc/pki/elasticfleet-server.key
       - FLEET_CA=/etc/pki/tls/certs/intca.crt     
       - FLEET_SERVER_ELASTICSEARCH_CA=/etc/pki/tls/certs/intca.crt
-      {% endif %}
-      - STATE_PATH=/usr/share/elastic-agent/state
-      - CONFIG_PATH=/usr/share/elastic-agent/state
       - LOGS_PATH=logs
       {% if DOCKERMERGED.containers['so-elastic-fleet'].extra_env %}
         {% for XTRAENV in DOCKERMERGED.containers['so-elastic-fleet'].extra_env %}
@@ -109,7 +100,6 @@ so-elastic-fleet:
       - x509: etc_elasticfleet_crt
     - require:
       - file: trusttheca
-      - file: eastatedir
       - x509: etc_elasticfleet_key
       - x509: etc_elasticfleet_crt
 

salt/elasticfleet/files/integrations/elastic-defend/elastic-defend-endpoints.json

@@ -5,7 +5,7 @@
   "package": {
     "name": "endpoint",
     "title": "Elastic Defend",
-    "version": "9.3.1",
+    "version": "9.4.1",
     "requires_root": true
   },
   "enabled": true,

salt/elasticfleet/files/integrations/grid-nodes_general/import-evtx-logs.json

@@ -29,7 +29,7 @@
               "\\.gz$"
             ],
             "include_files": [],
-            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.20.0\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.8.3\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.20.0\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.20.0\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.8.3\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
+            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.22.3\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.9.0\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.22.3\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.22.3\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.9.0\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
             "tags": [
               "import"
             ],

salt/elasticfleet/install_agent_grid.sls

@@ -14,8 +14,8 @@ so-elastic-agent-install:
   file.managed:
     - name: /usr/sbin/so-elastic-agent-install
     - source: salt://elasticfleet/tools/sbin/so-elastic-agent-install
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 

salt/elasticfleet/integration-defaults.map.jinja

@@ -16,7 +16,6 @@
     'awsfirehose.metrics': 'aws.cloudwatch',
     'cribl.logs': 'cribl',
     'cribl.metrics': 'cribl',
-    'sentinel_one_cloud_funnel.logins': 'sentinel_one_cloud_funnel.login',
     'azure_application_insights.app_insights': 'azure.app_insights',
     'azure_application_insights.app_state': 'azure.app_state',
     'azure_billing.billing': 'azure.billing',

salt/elasticfleet/manager.sls

@@ -68,6 +68,24 @@ so-elastic-fleet-package-upgrade:
     - require:
       - http: wait_for_so-kibana
 
+# initial so-elasticsearch-templates run is earlier, but it can skip over templates that have component templates not yet installed to avoid elasticsearch rejecting the template.
+so-elasticsearch-templates-after-fleet-packages:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-templates-load
+    - cwd: /opt/so
+    - unless: test -f /opt/so/state/estemplates.txt
+    - require:
+      - cmd: so-elastic-fleet-package-upgrade
+
+so-elastic-fleet-integration-upgrade:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-integration-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
+    - require:
+      - cmd: so-elastic-fleet-package-upgrade
+
 so-elastic-fleet-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-integration-policy-load
@@ -86,21 +104,13 @@ so-elastic-agent-grid-upgrade:
     - require:
       - http: wait_for_so-kibana
 
-so-elastic-fleet-integration-upgrade:
-  cmd.run:
-    - name: /usr/sbin/so-elastic-fleet-integration-upgrade
-    - retry:
-        attempts: 3
-        interval: 10
-    - require:
-      - http: wait_for_so-kibana
-
 {# Optional integrations script doesn't need the retries like so-elastic-fleet-integration-upgrade which loads the default integrations #}
 so-elastic-fleet-addon-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-optional-integrations-load
     - require:
       - http: wait_for_so-kibana
+      - cmd: so-elasticsearch-templates-after-fleet-packages
 
 {% if ELASTICFLEETMERGED.config.defend_filters.enable_auto_configuration %}
 so-elastic-defend-manage-filters-file-watch:

salt/elasticfleet/tools/sbin/so-elastic-fleet-common

@@ -30,6 +30,56 @@ fleet_api() {
     curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/${QUERYPATH}" "$@" --retry 3 --retry-delay 10 --fail 2>/dev/null
 }
 
+elastic_fleet_require_agent_policy() {
+    local AGENT_POLICY=$1
+    local POLICY_JSON
+
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY") || [ -z "$POLICY_JSON" ]; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    if ! jq -e '.item.package_policies | type == "array"' <<<"$POLICY_JSON" >/dev/null 2>&1; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    echo "$POLICY_JSON"
+}
+
+# Print the single active enrollment token for POLICY_ID.
+# Exit 1: retryable (API failure, invalid response, no active token)
+# Exit 2: multiple active tokens - Shouldn't get into this state without manual intervention
+elastic_fleet_active_enrollment_token() {
+    local POLICY_ID=$1
+    local RESP TOKEN_COUNT API_KEY
+
+    if ! RESP=$(fleet_api "enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+        echo "Error: Failed to retrieve enrollment tokens for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if ! jq -e '.list' <<<"$RESP" >/dev/null 2>&1; then
+        echo "Error: Invalid enrollment token response for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    TOKEN_COUNT=$(jq --arg pid "$POLICY_ID" '[.list[] | select(.policy_id == $pid and .active == true)] | length' <<<"$RESP")
+
+    if [ "${TOKEN_COUNT:-0}" -eq 0 ]; then
+        echo "Error: No active enrollment token found for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if [ "$TOKEN_COUNT" -gt 1 ]; then
+        echo "Error: Found $TOKEN_COUNT active enrollment tokens for agent policy '$POLICY_ID'; expected exactly one." >&2
+        return 2
+    fi
+
+    API_KEY=$(jq -r --arg pid "$POLICY_ID" '.list[] | select(.policy_id == $pid and .active == true) | .api_key' <<<"$RESP")
+    echo "$API_KEY"
+}
+
 # Max number of concurrent Fleet write jobs (create/update). Override via env if needed.
 MAX_FLEET_JOBS=${MAX_FLEET_JOBS:-10}
 
@@ -62,15 +112,7 @@ elastic_fleet_load_integrations_dir() {
     i=0
 
     # Fetch the agent policy a single time; we look up integration ids locally below.
-    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY"); then
-        echo "Error: Failed to retrieve agent policy '$AGENT_POLICY'."
-        rm -f "$FAIL_FILE"
-        rm -rf "$OUT_DIR"
-        return 1
-    fi
-
-    if ! jq -e '.item.package_policies' <<<"$POLICY_JSON" >/dev/null 2>&1; then
-        echo "Error: Invalid agent policy response for '$AGENT_POLICY'."
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
         rm -f "$FAIL_FILE"
         rm -rf "$OUT_DIR"
         return 1
@@ -124,9 +166,15 @@ elastic_fleet_integration_check() {
 
     JSON_STRING=$2
 
-    NAME=$(jq -r .name $JSON_STRING)
+    NAME=$(jq -r .name "$JSON_STRING")
+    INTEGRATION_ID=""
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
 
 }
 
@@ -148,7 +196,16 @@ elastic_fleet_integration_remove() {
 
     NAME=$2
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: Integration '$NAME' was not found in agent policy '$AGENT_POLICY'." >&2
+        return 1
+    fi
 
     JSON_STRING=$( jq -n \
                     --arg INTEGRATIONID "$INTEGRATION_ID" \

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-defend

@@ -13,7 +13,10 @@ ERROR=false
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
   printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-  elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
+  if ! elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"; then
+    ERROR=true
+    continue
+  fi
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
       if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server

@@ -7,20 +7,35 @@
 . /usr/sbin/so-elastic-fleet-common
 
 # Get all the fleet policies
-json_output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true')
+if ! json_output=$(fleet_api "agent_policies" -H 'kbn-xsrf: true'); then
+    echo "Error: Failed to retrieve Fleet agent policies." >&2
+    exit 1
+fi
+
+if ! jq -e '.items' <<<"$json_output" >/dev/null 2>&1; then
+    echo "Error: Invalid Fleet agent policies response." >&2
+    exit 1
+fi
 
 # Extract the IDs that start with "FleetServer_"
-POLICY=$(echo "$json_output" | jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id')
+POLICY=$(jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id' <<<"$json_output")
 
 # Iterate over each ID in the POLICY variable
 for POLICYNAME in $POLICY; do
     printf "\nUpdating Policy: $POLICYNAME\n"
 
-    # First get the Integration ID
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$POLICYNAME" | jq -r '.item.package_policies[] | select(.package.name == "fleet_server") | .id')  
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$POLICYNAME"); then
+        exit 1
+    fi
+
+    INTEGRATION_ID=$(jq -r '.item.package_policies[]? | select(.package.name == "fleet_server") | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: fleet_server integration was not found in agent policy '$POLICYNAME'." >&2
+        exit 1
+    fi
 
     # Modify the default integration policy to update the policy_id and an with the correct naming
-	UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
+    UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
     .policy_id = $policy_id |
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 

salt/elasticfleet/tools/sbin_jinja/so-elastic-agent-gen-installers

@@ -22,12 +22,19 @@ NUM_RUNNING=$(pgrep -cf "/bin/bash /sbin/so-elastic-agent-gen-installers")
 
 for i in {1..30}
 do
-   ENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+   ENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial")
+   TOKEN_RC=$?
+   if [ "$TOKEN_RC" -eq 2 ]; then
+     exit 1
+   fi
    FLEETHOST=$(curl -K /opt/so/conf/elasticsearch/curl.config 'http://localhost:5601/api/fleet/fleet_server_hosts/grid-default' | jq -r  '.item.host_urls[]' | paste -sd ',')
-if [[ $FLEETHOST ]] && [[  $ENROLLMENTOKEN ]]; then break; else sleep 10; fi
+   if [[ -n "$FLEETHOST" ]] && [[ -n "$ENROLLMENTOKEN" ]]; then
+     break
+   fi
+   sleep 10
 done
 
-if [[ -z $FLEETHOST ]] || [[ -z $ENROLLMENTOKEN ]]; then 
+if [[ -z "$FLEETHOST" ]] || [[ -z "$ENROLLMENTOKEN" ]]; then
   printf "\nFleet Host URL, Enrollment Token or Elastic Version empty - exiting..."
   printf "\nFleet Host: $FLEETHOST, Enrollment Token: $ENROLLMENTOKEN\n"
   exit 1
@@ -67,19 +74,25 @@ for GOOS in "${GOTARGETOS[@]}"; do
     GOARCH="amd64"
     if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin" && GOARCH="arm64"; fi
     printf "\n\n### Generating $GOOS/$GOARCH Installer...\n"
-    docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
+    if ! docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
     --mount type=bind,source=/etc/pki/tls/certs/,target=/workspace/files/cert/ \
     --mount type=bind,source=/nsm/elastic-agent-workspace/,target=/workspace/files/elastic-agent/ \
     --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ \
-    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}
+    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}; then
+        printf "\n### ERROR: Failed to generate $GOOS/$GOARCH installer. Exiting...\n"
+        exit 1
+    fi
     printf "\n### $GOOS/$GOARCH Installer Generated...\n"
 done
 
 printf "\n\n### Generating MSI...\n"
 cp /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
-docker run \
+if ! docker run \
 --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ -w /output \
-{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs
+{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs; then
+    printf "\n### ERROR: Failed to generate MSI. Exiting...\n"
+    exit 1
+fi
 printf "\n### MSI Generated...\n"
 
 # Verify installers were created

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade

@@ -10,6 +10,25 @@
 
 PKG_LOAD_FAILURES=0
 PKG_LOAD_FAILURES_NAMES=()
+PKG_UPGRADED=0
+
+cleanup_elasticsearch_fleet_transforms() {
+    local transforms transform_id attempt
+    
+    if ! transforms=$(so-elasticsearch-query "_transform/logs-elasticsearch.index_pivot-default-*" --retry 1 --retry-delay 5); then
+        return 0
+    fi
+
+    while IFS= read -r transform_id; do
+        [ -n "$transform_id" ] || continue
+        for attempt in {1..3}; do
+            if so-elasticsearch-query "_transform/$transform_id?force=true" -XDELETE --fail --retry 1 --retry-delay 5; then
+                break
+            fi
+            sleep 5
+        done
+    done < <(jq -r '.transforms[]?.id' <<< "$transforms")
+}
 
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
@@ -17,10 +36,25 @@ if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && L
     if [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
         echo "{{ PACKAGE }} integration version $INSTALLED_VERSION is already at the reported latest version $LATEST_VERSION, skipping upgrade."
     else
-        echo "Upgrading {{ PACKAGE }} package to version $LATEST_VERSION..."
+{%- if PACKAGE == 'elasticsearch' %}
+        cleanup_elasticsearch_fleet_transforms
+{%- endif %}
+        echo "Upgrading {{ PACKAGE }} package from $INSTALLED_VERSION to version $LATEST_VERSION..."
         if ! elastic_fleet_package_install "{{ PACKAGE }}" "$LATEST_VERSION"; then
             PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
             PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        # check that package has upgraded to the expected version after install command
+        elif ! LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+            echo "ERROR: Failed to get latest version information for integration {{ PACKAGE }} after upgrade attempt"
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        elif INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
+            echo "{{ PACKAGE }} integration upgraded to version $LATEST_VERSION."
+            PKG_UPGRADED=$((PKG_UPGRADED + 1))
+        else
+            echo "ERROR: {{ PACKAGE }} integration still at ${INSTALLED_VERSION:-unknown}; expected $LATEST_VERSION"
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
         fi
     fi
 else
@@ -30,6 +64,11 @@ else
 fi
 {%- endfor %}
 
+if [ $PKG_UPGRADED -gt 0 ]; then
+    echo "Elasticsearch template statefiles cleared after $PKG_UPGRADED package upgrade(s), so templates can reload."
+    rm -f /opt/so/state/estemplates.txt /opt/so/state/addon_estemplates.txt
+fi
+
 if [ $PKG_LOAD_FAILURES -gt 0 ]; then
     echo "ERROR: Failed to upgrade $PKG_LOAD_FAILURES package(s):"
     for PKG in "${PKG_LOAD_FAILURES_NAMES[@]}"; do

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-setup

@@ -202,26 +202,9 @@ fi
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-if ENDPOINTSENROLLMENTOKEN_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-    ENDPOINTSENROLLMENTOKEN=$(echo "$ENDPOINTSENROLLMENTOKEN_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
-else
-    echo -e "\nFailed to query for Endpoints enrollment token"
-    exit 1
-fi
-
-if GRIDNODESENROLLMENTOKENGENERAL_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-    GRIDNODESENROLLMENTOKENGENERAL=$(echo "$GRIDNODESENROLLMENTOKENGENERAL_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
-else
-    echo -e "\nFailed to query for Grid nodes - General enrollment token"
-    exit 1
-fi
-
-if GRIDNODESENROLLMENTOKENHEAVY_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
-    GRIDNODESENROLLMENTOKENHEAVY=$(echo "$GRIDNODESENROLLMENTOKENHEAVY_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
-else
-    echo -e "\nFailed to query for Grid nodes - Heavy enrollment token"
-    exit 1
-fi
+ENDPOINTSENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial") || exit 1
+GRIDNODESENROLLMENTOKENGENERAL=$(elastic_fleet_active_enrollment_token "so-grid-nodes_general") || exit 1
+GRIDNODESENROLLMENTOKENHEAVY=$(elastic_fleet_active_enrollment_token "so-grid-nodes_heavy") || exit 1
 
 # Store needed data in minion pillar
 pillar_file=/opt/so/saltstack/local/pillar/minions/{{ GLOBALS.minion_id }}.sls

salt/elasticsearch/cluster.sls

@@ -98,6 +98,13 @@ so-es-cluster-settings:
       - docker_container: so-elasticsearch
       - file: elasticsearch_sbin_jinja
       - http: wait_for_so-elasticsearch
+
+so-elasticsearch-system-indices-patch:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-system-indices-patch
+    - require:
+      - http: wait_for_so-elasticsearch
+      - file: so-elasticsearch-system-indices-patch-script
 {%  endif %}
 
 # heavynodes will only load ILM policies for SO managed indices. (Indicies defined in elasticsearch/defaults.yaml)

salt/elasticsearch/config.sls

@@ -37,19 +37,29 @@ elasticsearch_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - so-elasticsearch-pipelines # exclude this because we need to watch it for changes, we sync it in another state
+      - so-elasticsearch-system-indices-patch
+    - show_changes: False
+
+so-elasticsearch-system-indices-patch-script:
+  file.managed:
+    - name: /usr/sbin/so-elasticsearch-system-indices-patch
+    - source: salt://elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch
+    - user: root
+    - group: root
+    - mode: 755
     - show_changes: False
 
 elasticsearch_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -62,8 +72,8 @@ so-elasticsearch-ilm-policy-load-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-ilm-policy-load
     - source: salt://elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 754
     - template: jinja
     - defaults:
@@ -74,8 +84,8 @@ so-elasticsearch-pipelines-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-pipelines
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-pipelines
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 754
     - show_changes: False
 

salt/elasticsearch/defaults.yaml

@@ -1,7 +1,7 @@
 elasticsearch:
   enabled: false
   esheap: '600m'
-  version: 9.3.7
+  version: 9.4.5
   index_clean: true
   data_retention_method: DLM
   vm:
@@ -3454,6 +3454,720 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
+    so-metrics-system_x_core:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.core@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.core@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.core@custom
+        index_patterns:
+        - metrics-system.core-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.core-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_cpu:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.cpu@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.cpu@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.cpu@custom
+        index_patterns:
+        - metrics-system.cpu-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.cpu-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_diskio:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.diskio@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.diskio@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.diskio@custom
+        index_patterns:
+        - metrics-system.diskio-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.diskio-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_filesystem:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.filesystem@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.filesystem@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.filesystem@custom
+        index_patterns:
+        - metrics-system.filesystem-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.filesystem-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_fsstat:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.fsstat@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.fsstat@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.fsstat@custom
+        index_patterns:
+        - metrics-system.fsstat-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.fsstat-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_load:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.load@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.load@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.load@custom
+        index_patterns:
+        - metrics-system.load-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.load-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_memory:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.memory@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.memory@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.memory@custom
+        index_patterns:
+        - metrics-system.memory-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.memory-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_network:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.network@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.network@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.network@custom
+        index_patterns:
+        - metrics-system.network-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.network-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_ntp:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@settings
+        - metrics-system.ntp@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.ntp@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.ntp@custom
+        index_patterns:
+        - metrics-system.ntp-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.ntp-logs
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_process:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.process@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.process@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.process@custom
+        index_patterns:
+        - metrics-system.process-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.process-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_process_x_summary:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.process.summary@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.process.summary@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.process.summary@custom
+        index_patterns:
+        - metrics-system.process.summary-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.process.summary-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_socket_summary:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.socket_summary@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.socket_summary@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.socket_summary@custom
+        index_patterns:
+        - metrics-system.socket_summary-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.socket_summary-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
+    so-metrics-system_x_uptime:
+      data_stream_lifecycle:
+        data_retention: 90d
+      index_template:
+        composed_of:
+        - metrics@tsdb-settings
+        - metrics-system.uptime@package
+        - metrics@custom
+        - system@custom
+        - metrics-system.uptime@custom
+        - ecs@mappings
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - metrics@custom
+        - system@custom
+        - metrics-system.uptime@custom
+        index_patterns:
+        - metrics-system.uptime-*
+        priority: 501
+        template:
+          settings:
+            index:
+              lifecycle:
+                name: so-metrics-system.uptime-logs
+              mode: time_series
+              number_of_replicas: 0
+      policy:
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
     so-logs-windows_x_forwarded:
       index_sorting: false
       data_stream_lifecycle:

salt/elasticsearch/files/ingest/suricata.fileinfo

@@ -5,7 +5,8 @@
     { "rename": 	{ "field": "message2.proto", 			"target_field": "network.transport",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.app_proto", 		"target_field": "network.protocol",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.filename", 	"target_field": "file.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "file.bytes.missing",	"ignore_missing": true 	} },
+    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "suricata.fileinfo.gaps",	"ignore_missing": true 	} },
+    { "set":		{ "if": "ctx.suricata?.fileinfo?.gaps == false", 	"field": "file.bytes.missing",	"value": 0 		} },
     { "rename": 	{ "field": "message2.fileinfo.magic", 		"target_field": "file.mime_type",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.md5", 		"target_field": "hash.md5",		"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.sha1", 		"target_field": "hash.sha1",		"ignore_missing": true 	} },

salt/elasticsearch/files/log4j2.properties

@@ -20,7 +20,8 @@ appender.rolling.strategy.type = DefaultRolloverStrategy
 appender.rolling.strategy.action.type = Delete
 appender.rolling.strategy.action.basepath = /var/log/elasticsearch
 appender.rolling.strategy.action.condition.type = IfFileName
-appender.rolling.strategy.action.condition.glob = *.log.gz
+# age delete regular securityonion.log.gz and gc.log.NN files
+appender.rolling.strategy.action.condition.regex = (?:.*[.]log[.]gz|gc[.]log[.][0-9]+)
 appender.rolling.strategy.action.condition.nested_condition.type = IfLastModified
 appender.rolling.strategy.action.condition.nested_condition.age = 7D
 

salt/elasticsearch/soc_elasticsearch.yaml

@@ -64,6 +64,43 @@ elasticsearch:
               flood_stage:
                 description: The max percentage of used disk space that will cause the node to take protective actions, such as blocking incoming events.
                 helpLink: elasticsearch
+      lifecycle:
+        default:
+          rollover:
+            description: This property accepts a key value pair formatted string and configures the conditions that would trigger a data stream to rollover when it has lifecycle configured.
+            forcedType: string
+            regex: ^max_age=(auto|[1-9][0-9]*[hd]),max_primary_shard_size=[1-9][0-9]*gb,min_docs=(0|[1-9][0-9]*),max_primary_shard_docs=[1-9][0-9]*$
+            regexFailureMessage: Must be in the format of "max_age=auto|<number><h|d>,max_primary_shard_size=<number>gb,min_docs=<number>,max_primary_shard_docs=<number>".
+            advanced: True
+            global: True
+    data_streams:
+      lifecycle:
+        poll_interval:
+          description: How often Elasticsearch checks what the next action is for all data streams with a built-in lifecycle.
+          forcedType: string
+          regex: "^[1-9][0-9]*[mhd]$"
+          regexFailureMessage: Must be a number followed by m, h, or d.
+          advanced: True
+          global: true
+          helpLink: elasticsearch
+        target:
+          merge:
+            policy:
+              merge_factor:
+                description: Data stream lifecycle implements tail merging by updating the Lucene merge policy factor for the target backing index. The merge factor is both the number of segments that should be merged together, and the maximum number of segments that we expect to find.
+                forcedType: int
+                regex: "^[1-9][0-9]*$"
+                advanced: True
+                global: true
+                helpLink: elasticsearch
+              floor_segment:
+                description: Data stream lifecycle implements tail merging by updating the Lucene merge policy floor segment for the target backing index. This floor segment size is a way to prevent indices from having a long tail of very small segments.
+                forcedType: string
+                regex: "^[1-9][0-9]*[MG]B$"
+                regexFailureMessage: Must be a number followed by MB or GB, such as 100MB.
+                advanced: True
+                global: true
+                helpLink: elasticsearch
     action:
       destructive_requires_name:
         description: Requires explicit index names when deleting indices. Prevents accidental deletion of indices via wildcard patterns.
@@ -645,6 +682,9 @@ elasticsearch:
             global: True
             advanced: True
             helpLink: elasticsearch
+    so-assistant-chat: *dataStreamSettings
+    so-assistant-session: *dataStreamSettings
+    so-elastic-agent-monitor: *dataStreamSettings
     so-logs-soc: *dataStreamSettings
     so-logs-system_x_auth: *dataStreamSettings
     so-logs-system_x_syslog: *dataStreamSettings
@@ -667,7 +707,10 @@ elasticsearch:
     so-logs-elastic_agent_x_auditbeat: *dataStreamSettings
     so-logs-elastic_agent_x_cloudbeat: *dataStreamSettings
     so-logs-elastic_agent_x_endpoint_security: *dataStreamSettings
+    so-logs-endpoint_x_actions: *dataStreamSettings
+    so-logs-endpoint_x_action_x_responses: *dataStreamSettings
     so-logs-endpoint_x_alerts: *dataStreamSettings
+    so-logs-endpoint_x_diagnostic_x_collection: *dataStreamSettings
     so-logs-endpoint_x_events_x_api: *dataStreamSettings
     so-logs-endpoint_x_events_x_file: *dataStreamSettings
     so-logs-endpoint_x_events_x_library: *dataStreamSettings
@@ -675,6 +718,7 @@ elasticsearch:
     so-logs-endpoint_x_events_x_process: *dataStreamSettings
     so-logs-endpoint_x_events_x_registry: *dataStreamSettings
     so-logs-endpoint_x_events_x_security: *dataStreamSettings
+    so-logs-endpoint_x_heartbeat: *dataStreamSettings
     so-logs-elastic_agent_x_filebeat: *dataStreamSettings
     so-logs-elastic_agent_x_fleet_server: *dataStreamSettings
     so-logs-elastic_agent_x_heartbeat: *dataStreamSettings
@@ -690,6 +734,19 @@ elasticsearch:
     so-metrics-vsphere_x_datastore: *dataStreamSettings
     so-metrics-vsphere_x_host: *dataStreamSettings
     so-metrics-vsphere_x_virtualmachine: *dataStreamSettings
+    so-metrics-system_x_core: *dataStreamSettings
+    so-metrics-system_x_cpu: *dataStreamSettings
+    so-metrics-system_x_diskio: *dataStreamSettings
+    so-metrics-system_x_filesystem: *dataStreamSettings
+    so-metrics-system_x_fsstat: *dataStreamSettings
+    so-metrics-system_x_load: *dataStreamSettings
+    so-metrics-system_x_memory: *dataStreamSettings
+    so-metrics-system_x_network: *dataStreamSettings
+    so-metrics-system_x_ntp: *dataStreamSettings
+    so-metrics-system_x_process: *dataStreamSettings
+    so-metrics-system_x_process_x_summary: *dataStreamSettings
+    so-metrics-system_x_socket_summary: *dataStreamSettings
+    so-metrics-system_x_uptime: *dataStreamSettings
     so-common: *dataStreamSettings
     so-endgame: *dataStreamSettings
     so-idh: *dataStreamSettings
@@ -880,17 +937,6 @@ elasticsearch:
                   global: True
                   advanced: True
                   helpLink: elasticsearch
-              rollover:
-                max_age:
-                  description: Maximum age of index.  Once an index reaches this limit, it will be rolled over into a new index.
-                  global: True
-                  advanced: True
-                  helpLink: elasticsearch
-                max_primary_shard_size:
-                  description: Maximum primary shard size. Once an index reaches this limit, it will be rolled over into a new index.
-                  global: True
-                  advanced: True
-                  helpLink: elasticsearch
               shrink:
                 method:
                   description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
@@ -987,8 +1033,6 @@ elasticsearch:
             helpLink: elasticsearch
     sos-backup: *indexSettings
     so-detection: *indexSettings
-    so-assistant-chat: *indexSettings
-    so-assistant-session: *indexSettings
     so-metrics-fleet_server_x_agent_status: &fleetMetricsSettings
       index_sorting:
         description: Sorts the index by event time, at the cost of additional processing resource consumption.

salt/elasticsearch/template.map.jinja

@@ -109,9 +109,15 @@
 {%     if not settings.get('index_sorting', False) | to_bool and settings.index_template.template.settings.index.sort is defined %}
 {%       do settings.index_template.template.settings.index.pop('sort') %}
 {%     endif %}
-{%     if DATA_RETENTION_METHOD == 'DLM' and settings.index_template.data_stream is defined and settings.data_stream_lifecycle is defined %}
-{%       if settings.data_stream_lifecycle.data_retention is defined and settings.data_stream_lifecycle.data_retention %}
-{%         do settings.index_template.template.update({'lifecycle': {'data_retention': settings.data_stream_lifecycle.data_retention}}) %}
+{%     if DATA_RETENTION_METHOD == 'DLM' and settings.index_template.data_stream is defined %}
+{#       Addon defaults are generated without data_stream_lifecycle, so fall back to global defaults. #}
+{%       if settings.data_stream_lifecycle is defined %}
+{%         set DATA_STREAM_LIFECYCLE = settings.data_stream_lifecycle %}
+{%       else %}
+{%         set DATA_STREAM_LIFECYCLE = DEFAULT_GLOBAL_OVERRIDES.data_stream_lifecycle %}
+{%       endif %}
+{%       if DATA_STREAM_LIFECYCLE.data_retention is defined and DATA_STREAM_LIFECYCLE.data_retention %}
+{%         do settings.index_template.template.update({'lifecycle': {'data_retention': DATA_STREAM_LIFECYCLE.data_retention}}) %}
 {%       else %}
 {%         do settings.index_template.template.update({'lifecycle': {}}) %}
 {%       endif %}

salt/elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch

@@ -0,0 +1,203 @@
+#!/bin/bash
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+set -eo pipefail
+
+SETTINGS='{"index":{"auto_expand_replicas":"0-1"}}'
+KIBANA_PASSWORD=
+INDEX_PATTERNS=(
+  '.entity_analytics.risk_score.lookup-*'
+  '.entity_analytics.watchlists.*'
+  '.entity_analytics.monitoring.users-*'
+  '.entity_analytics.entity-leads-*'
+  '.asset-criticality.asset-criticality-*'
+  '.workflows-executions'
+  '.workflows-step-executions'
+  '.entities.v2.latest.security_*'
+  '.entities.v2.history.security_*'
+  'risk-score.risk-score-latest-*'
+  '.metrics-endpoint.metadata_united_*'
+  '.metrics-endpoint.metadata_current_*'
+)
+DATA_STREAM_PATTERNS=(
+  '.entities.v2.updates.security_*'
+  'risk-score.risk-score-*'
+  '.rule-events'
+  '.alert-actions'
+)
+TEMPLATE_PATTERNS=(
+  'entities_v2_latest_security_default_index_template'
+  'entities_v2_history_security_default_index_template'
+  '.entities_v2_updates_security_default_index_template'
+  '.risk-score.risk-score-default-index-template'
+  '.rule-events'
+  '.alert-actions'
+  '.metrics-endpoint.metadata_united_default-template'
+  '.metrics-endpoint.metadata_current_default-template'
+)
+
+query_es() {
+  if so-elasticsearch-query "$@" --fail --retry 3 --retry-delay 5; then
+    return 0
+  fi
+
+  # retry failed attempts with so_kibana user (system managed indices reject so_elastic user)
+  local query_path="$1"
+  shift
+
+  if [[ -z "$KIBANA_PASSWORD" ]]; then
+    KIBANA_PASSWORD=$(salt-call pillar.get elasticsearch:auth:users:so_kibana_user:pass --out=newline_values_only)
+  fi
+  [[ -n "$KIBANA_PASSWORD" ]] || return 1
+
+  echo "Retrying ${query_path} as so_kibana." >&2
+  curl -K /opt/so/conf/elasticsearch/curl.config --user "so_kibana:${KIBANA_PASSWORD}" \
+    -s -k -L --fail --retry 3 --retry-delay 5 -H 'Content-Type: application/json' "https://localhost:9200/${query_path}" "$@"
+}
+
+# add auto_expand_replicas=0-1 to given index
+set_auto_expand_replicas() {
+  local index="$1"
+
+  echo "Setting auto_expand_replicas to 0-1 on ${index}."
+  query_es "${index}/_settings" -XPUT -d "$SETTINGS" >/dev/null
+}
+
+# resolve index patterns and find each index with an unassigned replica
+unassigned_replicas() {
+  local pattern="$1"
+  local resolved_indices response index
+
+  if ! resolved_indices=$(query_es "_resolve/index/${pattern}?expand_wildcards=all" 2>/dev/null); then
+    return 0
+  fi
+
+  while read -r index; do
+    if ! response=$(query_es "_cat/shards/${index}?format=json&h=index,prirep,state" 2>/dev/null); then
+      continue
+    fi
+    jq -r '.[]? | objects | select(.prirep == "r" and .state == "UNASSIGNED") | .index' <<<"$response"
+  done < <(jq -r '.indices[]?.name' <<<"$resolved_indices")
+}
+
+data_stream_indices() {
+  local pattern="$1"
+  local response
+
+  if ! response=$(query_es "_data_stream/${pattern}?expand_wildcards=all" 2>/dev/null); then
+    return 0
+  fi
+  jq -r '.data_streams[]?.indices[]?.index_name' <<<"$response"
+}
+
+update_system_indices() {
+  local pattern="$1"
+  local index
+
+  while read -r index; do
+    [[ -n "$index" ]] && set_auto_expand_replicas "$index"
+  done < <(unassigned_replicas "$pattern")
+}
+
+# update data stream backing indices with unassigned replicas
+update_system_ds() {
+  local pattern="$1"
+  local index
+
+  while read -r index; do
+    while read -r unassigned_index; do
+      [[ -n "$unassigned_index" ]] && set_auto_expand_replicas "$unassigned_index"
+    done < <(unassigned_replicas "$index")
+  done < <(data_stream_indices "$pattern")
+}
+
+has_unassigned_replicas() {
+  local pattern="$1"
+  local index
+
+  index=$(unassigned_replicas "$pattern" | sed -n '1p')
+  [[ -n "$index" ]]
+}
+
+data_stream_has_unassigned_replicas() {
+  local pattern="$1"
+  local index
+  while read -r index; do
+    has_unassigned_replicas "$index" && return 0
+  done < <(data_stream_indices "$pattern")
+
+  return 1
+}
+
+needs_patch() {
+  local pattern
+  for pattern in "${INDEX_PATTERNS[@]}"; do
+    has_unassigned_replicas "$pattern" && return 0
+  done
+  for pattern in "${DATA_STREAM_PATTERNS[@]}"; do
+    data_stream_has_unassigned_replicas "$pattern" && return 0
+  done
+
+  return 1
+}
+
+# get index templates, update with auto_expand_replicas=0-1, and PUT back. Keeping mappings/settings/aliases in-place
+update_system_templates() {
+  local pattern="$1"
+  local templates name response template auto_expand_replicas
+
+  if ! templates=$(query_es "_index_template/${pattern}" 2>/dev/null); then
+    return 0
+  fi
+  while read -r name; do
+    response=$(query_es "_index_template/${name}")
+    template=$(jq -c '.index_templates[0].index_template' <<<"$response")
+    auto_expand_replicas=$(jq -r '.template.settings["index.auto_expand_replicas"] // .template.settings.index.auto_expand_replicas // empty' <<<"$template")
+    [[ "$auto_expand_replicas" == "0-1" ]] && continue
+
+    template=$(jq '
+            if (.template.settings.index | type) == "object" then
+                .template.settings.index.auto_expand_replicas = "0-1"
+            else
+                .template.settings["index.auto_expand_replicas"] = "0-1"
+            end
+            | del(.created_date_millis, .modified_date_millis)
+        ' <<<"$template")
+    echo "Setting auto_expand_replicas to 0-1 on index template ${name}."
+    query_es "_index_template/${name}" -XPUT -d "$template" >/dev/null
+  done < <(jq -r '.index_templates[]?.name' <<<"$templates")
+}
+
+if [[ "${1:-}" == "--check" ]]; then
+  needs_patch
+  exit $?
+fi
+
+if [[ $# -ne 0 ]]; then
+  echo "Usage: $0 [--check]" >&2
+  exit 1
+fi
+
+patched=false
+for pattern in "${INDEX_PATTERNS[@]}"; do
+  if has_unassigned_replicas "$pattern"; then
+    update_system_indices "$pattern"
+    patched=true
+  fi
+done
+
+for pattern in "${DATA_STREAM_PATTERNS[@]}"; do
+  if data_stream_has_unassigned_replicas "$pattern"; then
+    update_system_ds "$pattern"
+    patched=true
+  fi
+done
+
+if [[ "$patched" == true ]]; then
+  for pattern in "${TEMPLATE_PATTERNS[@]}"; do
+    update_system_templates "$pattern"
+  done
+fi

salt/firewall/iptables.jinja

@@ -4,11 +4,19 @@
 {%- set role = GLOBALS.role.split('-')[1] %}
 {%- from 'firewall/containers.map.jinja' import NODE_CONTAINERS %}
 
+{%- set NODE_NETWORKS = [] %}
+{%- for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{%-   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+{%-     do NODE_NETWORKS.append(NETNAME) %}
+{%-   endif %}
+{%- endfor %}
+
 {%- set PR = [] %}
 {%- set D1 = [] %}
 {%- set D2 = [] %}
 {%- for container in NODE_CONTAINERS %}
 {%-   set IP = DOCKERMERGED.containers[container].ip %}
+{%-   set BRIDGE = DOCKERMERGED.containers[container].network %}
 {%-   if DOCKERMERGED.containers[container].port_bindings is defined %}
 {%-     for binding in DOCKERMERGED.containers[container].port_bindings %}
 {#-       cant split int so we convert to string #}
@@ -35,11 +43,11 @@
 {%-         endif %}
 {%-         do PR.append("-A POSTROUTING -s " ~ DOCKERMERGED.containers[container].ip ~ "/32 -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 -p " ~  proto ~ " -m " ~ proto  ~ " --dport " ~ containerPort ~ " -j MASQUERADE") %}
 {%-         if bindip | length and bindip != '0.0.0.0' %}
-{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         else %}
-{%-           do D1.append("-A DOCKER ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         endif %}
-{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i sobridge -o sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
+{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i " ~ BRIDGE ~ " -o " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
 {%-     endfor %}
 {%-   endif %}
 {%- endfor %}
@@ -52,11 +60,15 @@
 :DOCKER - [0:0]
 -A PREROUTING -m addrtype --dst-type LOCAL -j DOCKER
 -A OUTPUT ! -d 127.0.0.0/8 -m addrtype --dst-type LOCAL -j DOCKER
--A POSTROUTING -s {{DOCKERMERGED.range}} ! -o sobridge -j MASQUERADE
+{%- for NETNAME in NODE_NETWORKS %}
+-A POSTROUTING -s {{ DOCKERMERGED.networks[NETNAME].range }} ! -o {{ NETNAME }} -j MASQUERADE
+{%- endfor %}
 {%- for rule in PR %}
 {{ rule }}
 {%- endfor %}
--A DOCKER -i sobridge -j RETURN
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER -i {{ NETNAME }} -j RETURN
+{%- endfor %}
 {%- for rule in D1 %}
 {{ rule }}
 {%- endfor %}
@@ -97,10 +109,12 @@ COMMIT
 {%- endif %}
 -A FORWARD -j DOCKER-USER
 -A FORWARD -j DOCKER-ISOLATION-STAGE-1
--A FORWARD -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A FORWARD -o sobridge -j DOCKER
--A FORWARD -i sobridge ! -o sobridge -j ACCEPT
--A FORWARD -i sobridge -o sobridge -j ACCEPT
+{%- for NETNAME in NODE_NETWORKS %}
+-A FORWARD -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A FORWARD -o {{ NETNAME }} -j DOCKER
+-A FORWARD -i {{ NETNAME }} ! -o {{ NETNAME }} -j ACCEPT
+-A FORWARD -i {{ NETNAME }} -o {{ NETNAME }} -j ACCEPT
+{%- endfor %}
 -A FORWARD -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
 -A FORWARD -i lo -j ACCEPT
 -A FORWARD -m conntrack --ctstate INVALID -j DROP
@@ -112,13 +126,18 @@ COMMIT
 {%- for rule in D2 %}
 {{ rule }}
 {%- endfor %}
-
--A DOCKER-ISOLATION-STAGE-1 -i sobridge ! -o sobridge -j DOCKER-ISOLATION-STAGE-2
+{% for NETNAME in NODE_NETWORKS %}
+-A DOCKER-ISOLATION-STAGE-1 -i {{ NETNAME }} ! -o {{ NETNAME }} -j DOCKER-ISOLATION-STAGE-2
+{%- endfor %}
 -A DOCKER-ISOLATION-STAGE-1 -j RETURN
--A DOCKER-ISOLATION-STAGE-2 -o sobridge -j DROP
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER-ISOLATION-STAGE-2 -o {{ NETNAME }} -j DROP
+{%- endfor %}
 -A DOCKER-ISOLATION-STAGE-2 -j RETURN
--A DOCKER-USER ! -i sobridge -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-USER ! -i sobridge -o sobridge -j LOGGING
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -j LOGGING
+{%- endfor %}
 -A DOCKER-USER -j RETURN
 -A LOGGING -m limit --limit 2/min -j LOG --log-prefix "IPTables-dropped: "
 -A LOGGING -j DROP

salt/firewall/map.jinja

@@ -4,8 +4,12 @@
 
 {# add our ip to self #}
 {% do FIREWALL_DEFAULT.firewall.hostgroups.self.append(GLOBALS.node_ip) %}
-{# add dockernet range #}
-{% do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(DOCKERMERGED.range) %}
+{# add dockernet ranges #}
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{%   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+{%     do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(NETWORK.range) %}
+{%   endif %}
+{% endfor %}
 
 {% if GLOBALS.role == 'so-idh' %}
 {%   from 'idh/opencanary_config.map.jinja' import IDH_PORTGROUPS %}

salt/hydra/enabled.sls

@@ -26,8 +26,8 @@ so-hydra:
     - hostname: hydra
     - name: so-hydra
     - networks:
-      - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ip }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}
     - binds:
       - /opt/so/conf/hydra/:/hydra-conf:ro
       - /opt/so/log/hydra/:/hydra-log:rw
@@ -73,7 +73,7 @@ delete_so-hydra_so-status.disabled:
 
 wait_for_hydra:
   http.wait_for_successful_query:
-    - name: 'http://{{ GLOBALS.manager }}:4444/health/alive'
+    - name: 'http://{{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}:4444/health/alive'
     - ssl: True
     - verify_ssl: False
     - status:

salt/hypervisor/init.sls

@@ -21,12 +21,16 @@ hypervisor_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin
+    - user: root
+    - group: root
     - file_mode: 744
 
 hypervisor_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin_jinja
+    - user: root
+    - group: root
     - template: jinja
     - file_mode: 744
 

salt/idh/config.sls

@@ -86,8 +86,8 @@ idh_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://idh/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #idh_sbin_jinja:

salt/influxdb/config.sls

@@ -41,8 +41,8 @@ influxdb_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://influxdb/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #influxdb_sbin_jinja:

salt/kafka/config.sls

@@ -30,16 +30,16 @@ kafka_sbin_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin
-    - user: 960
-    - group: 960
+    - user: root
+    - group: root
     - file_mode: 755
 
 kafka_sbin_jinja_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin_jinja
-    - user: 960
-    - group: 960
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kibana/config.sls

@@ -36,16 +36,16 @@ kibana_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin
-    - user: 932
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 kibana_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin_jinja
-    - user: 932
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kibana/defaults.yaml

@@ -22,7 +22,7 @@ kibana:
           - default
           - file
     migrations:
-      discardCorruptObjects: "9.3.7"
+      discardCorruptObjects: "9.4.5"
     telemetry:
       enabled: False
     xpack:

salt/kibana/tools/sbin_jinja/so-kibana-space-defaults

@@ -9,5 +9,5 @@ SESSIONCOOKIE=$(curl -K /opt/so/conf/elasticsearch/curl.config -c - -X GET http:
 # Disable certain Features from showing up in the Kibana UI
 echo
 echo "Setting up default Kibana Space:"
-curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X PUT "localhost:5601/api/spaces/space/default" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d' {"id":"default","name":"Default","disabledFeatures":["ml","enterpriseSearch","logs","infrastructure","apm","uptime","monitoring","stackAlerts","actions","securitySolutionCasesV3","inventory","dataQuality","searchSynonyms","searchQueryRules","enterpriseSearchApplications","enterpriseSearchAnalytics","securitySolutionTimeline","securitySolutionNotes","securitySolutionRulesV1","entityManager","streams","cloudConnect","slo"]} ' >> /opt/so/log/kibana/misc.log
+curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X PUT "localhost:5601/api/spaces/space/default" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d' {"id":"default","name":"Default","disabledFeatures":["ml","enterpriseSearch","logs","infrastructure","apm","uptime","securitySolutionCasesV3","inventory","searchSynonyms","searchQueryRules","enterpriseSearchApplications","enterpriseSearchAnalytics","securitySolutionTimeline","securitySolutionNotes","securitySolutionRulesV4","securitySolutionAlertsV1","entityManager","slo","streams","anonymization","searchInferenceEndpoints","cloudConnect","queryActivity","automatic_import","stackAlerts","monitoring","dataQuality","actions"]} ' >> /opt/so/log/kibana/misc.log
 echo

salt/kratos/enabled.sls

@@ -19,8 +19,8 @@ so-kratos:
     - hostname: kratos
     - name: so-kratos
     - networks:
-      - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ip }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}
     - binds:
       - /opt/so/conf/kratos/:/kratos-conf:ro
       - /opt/so/log/kratos/:/kratos-log:rw
@@ -71,7 +71,7 @@ delete_so-kratos_so-status.disabled:
 
 wait_for_kratos:
   http.wait_for_successful_query:
-    - name: 'http://{{ GLOBALS.manager }}:4434/'
+    - name: 'http://{{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}:4434/'
     - ssl: True
     - verify_ssl: False
     - status:

salt/libvirt/64962/init.sls

@@ -6,6 +6,8 @@ so-fix-salt-ldap_script:
   file.managed:
     - name: /usr/sbin/so-fix-salt-ldap.py
     - source: salt://libvirt/64962/scripts/so-fix-salt-ldap.py
+    - user: root
+    - group: root
     - mode: 744
 
 fix-salt-ldap:

salt/logrotate/defaults.yaml

@@ -220,6 +220,36 @@ logrotate:
       - extension .log
       - dateext
       - dateyesterday
+    /opt/so/log/salt/virtual_node_manager:
+      - daily
+      - rotate 14
+      - missingok
+      - copytruncate
+      - compress
+      - create
+      - extension .log
+      - dateext
+      - dateyesterday
+    /opt/so/log/salt/so-salt-cloud:
+      - daily
+      - rotate 14
+      - missingok
+      - copytruncate
+      - compress
+      - create
+      - extension .log
+      - dateext
+      - dateyesterday
+    /opt/so/log/salt/so-soup-grid-highstate:
+      - daily
+      - rotate 14
+      - missingok
+      - copytruncate
+      - compress
+      - create
+      - extension .log
+      - dateext
+      - dateyesterday
     /nsm/idh/*_x_log:
       - daily
       - rotate 14

salt/logrotate/soc_logrotate.yaml

@@ -140,6 +140,27 @@ logrotate:
       multiline: True
       global: True
       forcedType: "[]string"
+    "/opt/so/log/salt/virtual_node_manager":
+      description: List of logrotate options for this file.
+      title: /opt/so/log/salt/virtual_node_manager
+      advanced: True
+      multiline: True
+      global: True
+      forcedType: "[]string"
+    "/opt/so/log/salt/so-salt-cloud":
+      description: List of logrotate options for this file.
+      title: /opt/so/log/salt/so-salt-cloud
+      advanced: True
+      multiline: True
+      global: True
+      forcedType: "[]string"
+    "/opt/so/log/salt/so-soup-grid-highstate":
+      description: List of logrotate options for this file.
+      title: /opt/so/log/salt/so-soup-grid-highstate
+      advanced: True
+      multiline: True
+      global: True
+      forcedType: "[]string"
     "/nsm/idh/*_x_log":
       description: List of logrotate options for this file.
       title: /nsm/idh/*.log

salt/logstash/config.sls

@@ -40,8 +40,8 @@ logstash_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://logstash/tools/sbin
-    - user: 931
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #logstash_sbin_jinja:
@@ -81,6 +81,14 @@ ls_custom_pipeline_conf_{{assigned_pipeline}}_{{pipeline}}:
 
 
 {% for assigned_pipeline in ASSIGNED_PIPELINES %}
+{# a blank per-pipeline setting falls back to the global logstash.yml value #}
+{% set PARSED_OVERRIDES = LOGSTASH_MERGED.get('pipeline_settings', {}).get(assigned_pipeline, {}) %}
+{% if PARSED_OVERRIDES is not mapping %}
+{%   do salt.log.warning('logstash: ignoring malformed pipeline_settings for pipeline ' ~ assigned_pipeline ~ '; expected a set of settings') %}
+{% endif %}
+{% set PIPELINE_OVERRIDES = PARSED_OVERRIDES if PARSED_OVERRIDES is mapping else {} %}
+{% set THREADS = PIPELINE_OVERRIDES.get('pipeline_x_workers') or LOGSTASH_MERGED.config.pipeline_x_workers %}
+{% set BATCH = PIPELINE_OVERRIDES.get('pipeline_x_batch_x_size') or LOGSTASH_MERGED.config.pipeline_x_batch_x_size %}
     {% for CONFIGFILE in LOGSTASH_MERGED.defined_pipelines[assigned_pipeline] %}
 ls_pipeline_{{assigned_pipeline}}_{{CONFIGFILE.split('.')[0] | replace("/","_") }}:
   file.managed:
@@ -92,8 +100,8 @@ ls_pipeline_{{assigned_pipeline}}_{{CONFIGFILE.split('.')[0] | replace("/","_")
         GLOBALS: {{ GLOBALS }}
         ES_USER: "{{ salt['pillar.get']('elasticsearch:auth:users:so_elastic_user:user', '') }}"
         ES_PASS: "{{ salt['pillar.get']('elasticsearch:auth:users:so_elastic_user:pass', '') }}"
-        THREADS: {{ LOGSTASH_MERGED.config.pipeline_x_workers }}
-        BATCH: {{ LOGSTASH_MERGED.config.pipeline_x_batch_x_size }}
+        THREADS: {{ THREADS }}
+        BATCH: {{ BATCH }}
       {% else %}
     - name: /opt/so/conf/logstash/pipelines/{{assigned_pipeline}}/{{CONFIGFILE.split('/')[1]}}
       {% endif %}
@@ -125,6 +133,14 @@ lspipelinesyml:
     - defaults:
         ASSIGNED_PIPELINES: {{ ASSIGNED_PIPELINES }}
 
+lslog4j2:
+  file.managed:
+    - name: /opt/so/conf/logstash/etc/log4j2.properties
+    - source: salt://logstash/etc/log4j2.properties.jinja
+    - template: jinja
+    - user: 931
+    - group: 939
+
 lsetcsync:
   file.recurse:
     - name: /opt/so/conf/logstash/etc
@@ -133,7 +149,11 @@ lsetcsync:
     - group: 939
     - template: jinja
     - clean: True
-    - exclude_pat: pipelines*
+{#- both names are matched: the .jinja source so the recurse does not copy it verbatim,
+    and the rendered file so clean: True does not delete what lslog4j2 wrote #}
+    - exclude_pat:
+      - pipelines*
+      - log4j2.properties*
     - defaults:
         LOGSTASH_MERGED: {{ LOGSTASH_MERGED }}
 

salt/logstash/defaults.yaml

@@ -42,6 +42,11 @@ logstash:
     custom2: []
     custom3: []
     custom4: []
+    custom5: []
+    custom6: []
+    custom7: []
+    custom8: []
+    custom9: []
   pipeline_config:
     custom001: |-
       filter {
@@ -60,10 +65,405 @@ logstash:
     custom008: PLACEHOLDER
     custom009: PLACEHOLDER
     custom010: PLACEHOLDER
+  pipeline_settings:
+    fleet:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    manager:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    receiver:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    search:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom0:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom1:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom2:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom3:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom4:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom5:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom6:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom7:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom8:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
+    custom9:
+      pipeline_x_workers: ''
+      pipeline_x_batch_x_size: ''
+      pipeline_x_batch_x_delay: ''
+      pipeline_x_batch_x_metrics_x_sampling_mode: ''
+      pipeline_x_ordered: ''
+      pipeline_x_ecs_compatibility: ''
+      pipeline_x_reloadable: ''
+      queue_x_type: ''
+      queue_x_max_bytes: ''
+      queue_x_page_capacity: ''
+      queue_x_max_events: ''
+      queue_x_checkpoint_x_acks: ''
+      queue_x_checkpoint_x_writes: ''
+      queue_x_checkpoint_x_interval: ''
+      queue_x_checkpoint_x_retry: ''
+      queue_x_compression: ''
+      queue_x_drain: ''
+      dead_letter_queue_x_enable: ''
+      dead_letter_queue_x_max_bytes: ''
+      dead_letter_queue_x_flush_interval: ''
+      dead_letter_queue_x_flush_check_interval: ''
+      dead_letter_queue_x_storage_policy: ''
+      dead_letter_queue_x_retain_x_age: ''
+      path_x_queue: ''
+      path_x_dead_letter_queue: ''
+      config_x_debug: ''
+      config_x_support_escapes: ''
   settings:
     lsheap: 500m
   config:
     api_x_http_x_host: 0.0.0.0
+    log_x_level: info
+    log_x_format: plain
     path_x_logs: /var/log/logstash
     pipeline_x_workers: 1
     pipeline_x_batch_x_size: 125

salt/logstash/enabled.sls

@@ -105,6 +105,8 @@ so-logstash:
     {% endif %}
     - watch:
       - file: lsetcsync
+      - file: lslog4j2
+      - file: lspipelinesyml
       - file: trusttheca
       {% if GLOBALS.is_manager %}
       - file: elasticsearch_cacerts

salt/logstash/etc/log4j2.properties.jinja

@@ -1,3 +1,4 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED -%}
 status = error
 name = LogstashPropertiesConfig
 
@@ -16,8 +17,14 @@ name = LogstashPropertiesConfig
 appender.rolling.type = RollingFile
 appender.rolling.name = rolling
 appender.rolling.fileName = /var/log/logstash/logstash.log
+{%- if LOGSTASH_MERGED.config.get('log_x_format', 'plain') == 'json' %}
+appender.rolling.layout.type = JSONLayout
+appender.rolling.layout.compact = true
+appender.rolling.layout.eventEol = true
+{%- else %}
 appender.rolling.layout.type = PatternLayout
 appender.rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %.10000m%n
+{%- endif %}
 appender.rolling.filePattern = /var/log/logstash/logstash-%d{yyyy-MM-dd}.log.gz
 appender.rolling.policies.type = Policies
 appender.rolling.policies.time.type = TimeBasedTriggeringPolicy
@@ -32,7 +39,5 @@ appender.rolling.strategy.action.condition.type = IfFileName
 appender.rolling.strategy.action.condition.glob = *.gz
 appender.rolling.strategy.action.condition.nested_condition.type = IfLastModified
 appender.rolling.strategy.action.condition.nested_condition.age = 7D
-rootLogger.level = info
+rootLogger.level = ${sys:ls.log.level}
 rootLogger.appenderRef.rolling.ref = rolling
-#rootLogger.level = ${sys:ls.log.level}
-#rootLogger.appenderRef.console.ref = ${sys:ls.log.format}_console

salt/logstash/etc/pipelines.yml.jinja

@@ -1,4 +1,17 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
+{%- set PIPELINE_SETTINGS = LOGSTASH_MERGED.get('pipeline_settings', {}) %}
 {%- for assigned_pipeline in ASSIGNED_PIPELINES %}
 - pipeline.id: {{ assigned_pipeline }}
   path.config: "/usr/share/logstash/pipelines/{{ assigned_pipeline }}/"
+{%-   set extra = PIPELINE_SETTINGS.get(assigned_pipeline, {}) %}
+{%-   if extra is mapping %}
+{#-     values are emitted unquoted so yaml re-infers the type logstash expects:
+        4 as an integer, false as a boolean, 1024mb and auto as strings #}
+{%-     for key, value in extra | dictsort %}
+{%-       set rendered = key | replace('_x_', '.') %}
+{%-       if value not in ['', None] and rendered not in ['pipeline.id', 'path.config'] %}
+  {{ rendered }}: {{ value }}
+{%-       endif %}
+{%-     endfor %}
+{%-   endif %}
 {% endfor -%}

salt/logstash/soc_logstash.yaml

@@ -16,6 +16,7 @@ logstash:
       heavynode: *assigned_pipelines
       searchnode: *assigned_pipelines
       manager: *assigned_pipelines
+      managerhype: *assigned_pipelines
       managersearch: *assigned_pipelines
       fleet: *assigned_pipelines
   defined_pipelines:
@@ -34,6 +35,11 @@ logstash:
     custom2: *defined_pipelines
     custom3: *defined_pipelines
     custom4: *defined_pipelines
+    custom5: *defined_pipelines
+    custom6: *defined_pipelines
+    custom7: *defined_pipelines
+    custom8: *defined_pipelines
+    custom9: *defined_pipelines
   pipeline_config:
     custom001: &pipeline_config
       description: Pipeline configuration for Logstash
@@ -51,6 +57,351 @@ logstash:
     custom008: *pipeline_config
     custom009: *pipeline_config
     custom010: *pipeline_config
+  pipeline_settings:
+    manager: &pipeline_settings
+      pipeline_x_workers:
+        description: >-
+          Number of worker threads that run filters and outputs for this pipeline. May be set higher
+          than the CPU core count when outputs spend time waiting on I/O. Leave blank to use the value
+          from logstash.yml.
+        title: pipeline.workers
+        regex: '^$|^[1-9][0-9]*$'
+        regexFailureMessage: Must be blank, or a positive whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      pipeline_x_batch_x_size:
+        description: >-
+          Maximum number of events an individual worker thread collects before running filters and
+          outputs. Larger batches are more efficient but increase heap use; total in-flight events is
+          workers multiplied by batch size. Leave blank to use the value from logstash.yml.
+        title: pipeline.batch.size
+        regex: '^$|^[1-9][0-9]*$'
+        regexFailureMessage: Must be blank, or a positive whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      pipeline_x_batch_x_delay:
+        description: >-
+          Milliseconds a worker waits for the next event before running a batch that is not yet full.
+          Leave blank to use the value from logstash.yml.
+        title: pipeline.batch.delay
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      pipeline_x_batch_x_metrics_x_sampling_mode:
+        description: >-
+          Controls how often batch size metrics are collected for this pipeline, which helps tune
+          pipeline.batch.size to the batch sizes actually being processed. Fuller sampling consumes
+          additional heap. Elastic marks this setting as a technical preview that may change in a
+          future release. Leave blank to use the value from logstash.yml.
+        title: pipeline.batch.metrics.sampling_mode
+        options:
+        - ''
+        - 'disabled'
+        - 'minimal'
+        - 'full'
+        advanced: True
+        global: False
+        helpLink: logstash
+      pipeline_x_ordered:
+        description: >-
+          Whether event order is preserved through this pipeline. auto enables ordering only when
+          pipeline.workers is explicitly set to 1, and does nothing otherwise. Setting this to true
+          requires pipeline.workers to be 1 as well; with more workers this pipeline fails to start.
+          Leave blank to use the value from logstash.yml.
+        title: pipeline.ordered
+        options:
+        - ''
+        - 'auto'
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+      pipeline_x_ecs_compatibility:
+        description: >-
+          Elastic Common Schema compatibility mode for plugins in this pipeline. Security Onion sets
+          this globally and it should rarely be changed per pipeline. Elastic considers values other
+          than disabled to be BETA, and they may produce unintended consequences when upgrading
+          Logstash. Leave blank to use the value from logstash.yml.
+        title: pipeline.ecs_compatibility
+        options:
+        - ''
+        - 'disabled'
+        - 'v1'
+        - 'v8'
+        advanced: True
+        global: False
+        helpLink: logstash
+      pipeline_x_reloadable:
+        description: >-
+          Whether this pipeline may be reloaded when its configuration changes. Leave blank to use the
+          value from logstash.yml.
+        title: pipeline.reloadable
+        options:
+        - ''
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_type:
+        description: >-
+          Queue backing this pipeline. persisted buffers events to disk under /nsm/logstash so they
+          survive a restart, at some throughput cost; memory does not. Leave blank to use the value
+          from logstash.yml.
+        title: queue.type
+        options:
+        - ''
+        - 'memory'
+        - 'persisted'
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_max_bytes:
+        description: >-
+          Total capacity of the persistent queue for this pipeline, in bytes. Only applies when
+          queue.type is persisted. The disk backing /nsm/logstash must have room for this much data or
+          the pipeline fails to start, reporting that it was unable to allocate the space. If both
+          queue.max_events and queue.max_bytes are set, whichever is reached first applies. Leave
+          blank to use the value from logstash.yml.
+        title: queue.max_bytes
+        regex: '^$|^[0-9]+$|^[0-9]+(\.[0-9]+)?\s*(b|kb?|mb?|gb?|tb?|pb?)$'
+        regexFailureMessage: Must be blank, or a size such as 512mb, 1gb, or 64k. Units are lowercase.
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_page_capacity:
+        description: >-
+          Size of the individual append-only page data files that make up the persistent queue for
+          this pipeline. Only applies when queue.type is persisted. Leave blank to use the value from
+          logstash.yml.
+        title: queue.page_capacity
+        regex: '^$|^[0-9]+$|^[0-9]+(\.[0-9]+)?\s*(b|kb?|mb?|gb?|tb?|pb?)$'
+        regexFailureMessage: Must be blank, or a size such as 512mb, 1gb, or 64k. Units are lowercase.
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_max_events:
+        description: >-
+          Maximum number of unread events in the persistent queue for this pipeline. 0 means
+          unlimited. Only applies when queue.type is persisted. Leave blank to use the value from
+          logstash.yml.
+        title: queue.max_events
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_checkpoint_x_acks:
+        description: >-
+          Maximum number of acknowledged events before a checkpoint is forced. 0 means unlimited. Only
+          applies when queue.type is persisted. Leave blank to use the value from logstash.yml.
+        title: queue.checkpoint.acks
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_checkpoint_x_writes:
+        description: >-
+          Maximum number of written events before a checkpoint is forced. Setting this to 1 gives
+          maximum durability at a severe performance cost. 0 means unlimited. Only applies when
+          queue.type is persisted. Leave blank to use the value from logstash.yml.
+        title: queue.checkpoint.writes
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_checkpoint_x_interval:
+        description: >-
+          Milliseconds between forced checkpoints on the persistent queue head page. 0 eliminates
+          periodic checkpoints. Deprecated by Elastic as of Logstash 9.1. Only applies when queue.type
+          is persisted. Leave blank to use the value from logstash.yml.
+        title: queue.checkpoint.interval
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_checkpoint_x_retry:
+        description: >-
+          When enabled, Logstash retries four times per attempted checkpoint write that fails; later
+          errors are not retried. Elastic describes this as a workaround for failed checkpoint writes
+          seen only on Windows and on filesystems with non-standard behaviour such as SANs, and does
+          not recommend enabling it otherwise. Only applies when queue.type is persisted. Leave blank
+          to use the value from logstash.yml.
+        title: queue.checkpoint.retry
+        options:
+        - ''
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_compression:
+        description: >-
+          Compression applied to persistent queue pages for this pipeline, trading CPU for disk: speed
+          favours the fastest operation, size the smallest files, and balanced sits between them. Once
+          compressed events have been written, that queue cannot be read by Logstash releases earlier
+          than 9.2. Only applies when queue.type is persisted. Leave blank to use the value from
+          logstash.yml.
+        title: queue.compression
+        options:
+        - ''
+        - 'none'
+        - 'speed'
+        - 'balanced'
+        - 'size'
+        advanced: True
+        global: False
+        helpLink: logstash
+      queue_x_drain:
+        description: >-
+          When enabled, Logstash waits for the persistent queue to drain before shutting down this
+          pipeline. Draining a large queue makes shutdown take considerably longer. Only applies when
+          queue.type is persisted. Leave blank to use the value from logstash.yml.
+        title: queue.drain
+        options:
+        - ''
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+      dead_letter_queue_x_enable:
+        description: >-
+          Whether events this pipeline cannot process are written to a dead letter queue instead of
+          being dropped. Leave blank to use the value from logstash.yml.
+        title: dead_letter_queue.enable
+        options:
+        - ''
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+      dead_letter_queue_x_max_bytes:
+        description: >-
+          Total capacity of the dead letter queue for this pipeline, in bytes. Only applies when
+          dead_letter_queue.enable is true. Leave blank to use the value from logstash.yml.
+        title: dead_letter_queue.max_bytes
+        regex: '^$|^[0-9]+$|^[0-9]+(\.[0-9]+)?\s*(b|kb?|mb?|gb?|tb?|pb?)$'
+        regexFailureMessage: Must be blank, or a size such as 512mb, 1gb, or 64k. Units are lowercase.
+        advanced: True
+        global: False
+        helpLink: logstash
+      dead_letter_queue_x_flush_interval:
+        description: >-
+          Milliseconds before an incomplete dead letter queue segment is flushed and made available to
+          the dead_letter_queue input. Lower values write more, smaller segment files; higher values
+          add latency before events can be read. Only applies when dead_letter_queue.enable is true.
+          Leave blank to use the value from logstash.yml.
+        title: dead_letter_queue.flush_interval
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      dead_letter_queue_x_flush_check_interval:
+        description: >-
+          Milliseconds between checks for a stale dead letter queue segment needing a flush. Cannot be
+          set lower than 1000. Smaller values rotate segments sooner at the cost of CPU. Only applies
+          when dead_letter_queue.enable is true. Leave blank to use the value from logstash.yml.
+        title: dead_letter_queue.flush_check_interval
+        regex: '^$|^[0-9]+$'
+        regexFailureMessage: Must be blank, or a whole number.
+        advanced: True
+        global: False
+        helpLink: logstash
+      dead_letter_queue_x_storage_policy:
+        description: >-
+          Action taken when dead_letter_queue.max_bytes is reached: drop_newer stops accepting new
+          events, drop_older removes the oldest events to make room. Only applies when
+          dead_letter_queue.enable is true. Leave blank to use the value from logstash.yml.
+        title: dead_letter_queue.storage_policy
+        options:
+        - ''
+        - 'drop_newer'
+        - 'drop_older'
+        advanced: True
+        global: False
+        helpLink: logstash
+      dead_letter_queue_x_retain_x_age:
+        description: >-
+          How long an event is kept in the dead letter queue before Logstash removes it, such as 5d.
+          Units are d, h, m and s; there is no default unit, so one must be given. Only applies when
+          dead_letter_queue.enable is true. Leave blank to use the value from logstash.yml.
+        title: dead_letter_queue.retain.age
+        regex: '^$|^[0-9]+\s*[dhms]$'
+        regexFailureMessage: Must be blank, or a number followed by d, h, m, or s, such as 5d.
+        advanced: True
+        global: False
+        helpLink: logstash
+      path_x_queue:
+        description: >-
+          Directory inside the Logstash container holding the persistent queue for this pipeline. The
+          default lives under the /nsm/logstash bind mount; a path outside it will not survive a
+          container restart. Logstash creates the directory if it is missing, requires it to be
+          writable, and refuses to start if the path is a symlink. Only applies when queue.type is
+          persisted. Leave blank to use the value from logstash.yml.
+        title: path.queue
+        advanced: True
+        global: False
+        helpLink: logstash
+      path_x_dead_letter_queue:
+        description: >-
+          Directory inside the Logstash container holding the dead letter queue for this pipeline. The
+          default lives under the /nsm/logstash bind mount; a path outside it will not survive a
+          container restart. Logstash creates the directory if it is missing, requires it to be
+          writable, and refuses to start if the path is a symlink. Only applies when
+          dead_letter_queue.enable is true. Leave blank to use the value from logstash.yml.
+        title: path.dead_letter_queue
+        advanced: True
+        global: False
+        helpLink: logstash
+      config_x_debug:
+        description: >-
+          Whether the fully compiled configuration for this pipeline is written to the log. The output
+          may contain sensitive values from the pipeline configuration. Leave blank to use the value
+          from logstash.yml.
+        title: config.debug
+        options:
+        - ''
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+      config_x_support_escapes:
+        description: >-
+          Whether escape sequences such as \n and \t in this pipeline's quoted strings are
+          interpreted. Leave blank to use the value from logstash.yml.
+        title: config.support_escapes
+        options:
+        - ''
+        - 'true'
+        - 'false'
+        advanced: True
+        global: False
+        helpLink: logstash
+    fleet: *pipeline_settings
+    receiver: *pipeline_settings
+    search: *pipeline_settings
+    custom0: *pipeline_settings
+    custom1: *pipeline_settings
+    custom2: *pipeline_settings
+    custom3: *pipeline_settings
+    custom4: *pipeline_settings
+    custom5: *pipeline_settings
+    custom6: *pipeline_settings
+    custom7: *pipeline_settings
+    custom8: *pipeline_settings
+    custom9: *pipeline_settings
   settings:
     lsheap: 
       description: Heap size to use for logstash
@@ -62,6 +413,35 @@ logstash:
       helpLink: logstash
       readonly: True
       advanced: True
+    log_x_level:
+      description: >-
+        Verbosity of the Logstash log at /opt/so/log/logstash/logstash.log. debug and trace produce
+        a very large volume of log data on a busy node and should be used only while troubleshooting;
+        the log rotates at 1GB and rotated files are deleted after 7 days. Setting this to debug is
+        also what makes the per-pipeline config.debug setting emit anything.
+      title: log.level
+      options:
+      - 'fatal'
+      - 'error'
+      - 'warn'
+      - 'info'
+      - 'debug'
+      - 'trace'
+      advanced: True
+      global: False
+      helpLink: logstash
+    log_x_format:
+      description: >-
+        Layout of the Logstash log. plain writes human readable lines; json writes one JSON object
+        per line, which is easier to parse but harder to read directly. The file name and location
+        do not change.
+      title: log.format
+      options:
+      - 'plain'
+      - 'json'
+      advanced: True
+      global: False
+      helpLink: logstash
     path_x_logs: 
       description: Path inside the container to wrote logs.
       helpLink: logstash

salt/manager/files/beacons_pushstate.conf.jinja

@@ -3,9 +3,16 @@ beacons:
   postgres_pillar_beacon:
     - interval: {{ AUTOAPPLY.drain_interval }}
     - disable_during_state_run: False
-  rules_beacon:
+  local_files_beacon:
     - interval: {{ AUTOAPPLY.drain_interval }}
     - disable_during_state_run: False
+    # Tags are app names in salt/reactor/pillar_push_map.yaml.
+    # Allowlist on purpose: salt writes elsewhere under local/salt/ and would self-retrigger.
     - paths:
         /opt/so/saltstack/local/salt/suricata/rules: suricata
         /opt/so/saltstack/local/salt/strelka/rules/compiled: strelka
+        /opt/so/saltstack/local/salt/zeek/policy: zeek
+        /opt/so/saltstack/local/salt/zeek/zkg: zeek
+        /opt/so/saltstack/local/salt/elasticsearch/files/ingest: elasticsearch
+        /opt/so/saltstack/local/salt/elasticsearch/roles: elasticsearch
+        /opt/so/saltstack/local/salt/logstash/pipelines/config/custom: logstash

salt/manager/init.sls

@@ -113,8 +113,8 @@ manager_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://manager/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - "*_test.py"
@@ -124,8 +124,8 @@ manager_sbin_jinja:
   file.recurse:
     - name: /usr/sbin/
     - source: salt://manager/tools/sbin_jinja/
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -190,11 +190,15 @@ so_fleetagent_monitor:
   - month: '*'
   - dayweek: '*'
 
-socore_own_saltstack_default:
+# This tree is the source of every root-executed script (/usr/sbin, reactors, _runners,
+# engines, salt-relay.sh). SOC mounts /opt/so/saltstack rw as uid 939 but only writes
+# under local/. Do not add dir_mode/file_mode here -- SOC reads default/ and 750/640
+# would break its config load.
+root_own_saltstack_default:
   file.directory:
     - name: /opt/so/saltstack/default
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - recurse:
       - user
       - group

salt/manager/tools/sbin/so-client

@@ -106,7 +106,8 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-hydraUrl=${HYDRA_URL:-http://127.0.0.1:4445}
+hydraContainer=${HYDRA_CONTAINER:-so-hydra}
+hydraUrl=${HYDRA_URL:-http://localhost:4445}
 socRolesFile=${SOC_ROLES_FILE:-/opt/so/conf/soc/soc_clients_roles}
 soUID=${SOCORE_UID:-939}
 soGID=${SOCORE_GID:-939}
@@ -124,6 +125,10 @@ function fail() {
   exit 1
 }
 
+function hydraCurl() {
+  docker exec "$hydraContainer" curl "$@"
+}
+
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -133,8 +138,8 @@ function require() {
 # Verify this environment is capable of running this script
 function verifyEnvironment() {
   require "jq"
-  require "curl"
-  response=$(curl -Ss -L ${hydraUrl}/health/alive)
+  require "docker"
+  response=$(hydraCurl -Ss -L ${hydraUrl}/health/alive)
   [[ "$response" != '{"status":"ok"}' ]] && fail "Unable to communicate with Hydra; specify URL via HYDRA_URL environment variable"
 }
 
@@ -164,7 +169,7 @@ function ensureRoleFileExists() {
 }
 
 function listClients() {
-  response=$(curl -Ss -L -f ${hydraUrl}/admin/clients)
+  response=$(hydraCurl -Ss -L -f ${hydraUrl}/admin/clients)
   [[ $? != 0 ]] && fail "Unable to communicate with Hydra"
 
   clientIds=$(echo "${response}" | jq -r ".[] | .client_id" | sort)
@@ -251,7 +256,7 @@ function createClient() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -283,7 +288,7 @@ function update() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -305,7 +310,7 @@ function generateSecret() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -317,7 +322,7 @@ function deleteClient() {
 
   [[ ${identityId} == "" ]] && fail "Client not found"
 
-  response=$(curl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
+  response=$(hydraCurl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"

salt/manager/tools/sbin/so-minion

@@ -121,8 +121,14 @@ for i in "$@"; do
 	esac
 done
 
-PILLARFILE=/opt/so/saltstack/local/pillar/minions/$MINION_ID.sls
-ADVPILLARFILE=/opt/so/saltstack/local/pillar/minions/adv_$MINION_ID.sls
+if [[ -n "$MINION_ID" && ! "$MINION_ID" =~ ^[A-Za-z0-9._-]{1,253}$ ]]; then
+	echo "Invalid minion id: $MINION_ID"
+	log "ERROR" "Invalid minion id: $MINION_ID"
+	exit 1
+fi
+
+readonly PILLARFILE=/opt/so/saltstack/local/pillar/minions/$MINION_ID.sls
+readonly ADVPILLARFILE=/opt/so/saltstack/local/pillar/minions/adv_$MINION_ID.sls
 
 function getinstallinfo() {
 	log "INFO" "Getting install info for minion $MINION_ID"
@@ -133,11 +139,26 @@ function getinstallinfo() {
 		return 1
 	fi
 
-	while read -r var; do export "$var"; done <<< "$INSTALLVARS"
-	if [ $? -ne 0 ]; then
-		log "ERROR" "Failed to source install variables"
-		return 1
+	# install.txt is controlled by the minion; only accept known keys and never eval or export them
+	local line key
+	while IFS= read -r line; do
+		[[ "$line" == *=* ]] || continue
+		key=${line%%=*}
+		case "$key" in
+			MAINIP|MNIC|NODE_DESCRIPTION|ES_HEAP_SIZE|PATCHSCHEDULENAME|INTERFACE|NODETYPE|CORECOUNT|LSHOSTNAME|LSHEAP|CPUCORES|IDH_MGTRESTRICT|IDH_SERVICES)
+				printf -v "$key" '%s' "${line#*=}"
+				;;
+			*)
+				log "WARN" "Ignoring unexpected install var from $MINION_ID: ${key:0:64}"
+				;;
+		esac
+	done <<< "$INSTALLVARS"
+
+	if [[ "$NODE_DESCRIPTION" == \'*\' ]]; then
+		NODE_DESCRIPTION=${NODE_DESCRIPTION:1:-1}
 	fi
+
+	log "INFO" "Fetched install info for $MINION_ID (node type: ${NODETYPE:-unset})"
 }
 
 function pcapspace() {
@@ -174,6 +195,12 @@ function pcapspace() {
 		fi
 	fi
 
+	# Must be checked before arithmetic expansion, which evaluates array subscripts
+	if [[ ! "$SPACESIZE" =~ ^[0-9]+$ ]]; then
+		log "ERROR" "Invalid disk size for $MINION_ID: ${SPACESIZE:0:64}"
+		return 1
+	fi
+
 	local s=$(( $SPACESIZE / 1000000 ))
 	local s1=$(( $s / 4 * $PCAP_PERCENTAGE ))
 
@@ -483,6 +510,7 @@ function add_sensoroni_with_analyze_to_minion() {
 
 # Sensor settings for the minion pillar
 function add_sensor_to_minion() {
+	log "INFO" "Writing sensor configuration for $MINION_ID (interface: ${INTERFACE:-unset})"
     {
         echo "sensor:"
         echo "  interface: '$INTERFACE'"
@@ -509,6 +537,8 @@ function add_sensor_to_minion() {
         log "ERROR" "Failed to add sensor configuration to $PILLARFILE"
         return 1
     fi
+
+	log "INFO" "Wrote sensor configuration for $MINION_ID"
 }
 
 function add_elastalert_to_minion() {
@@ -581,11 +611,14 @@ function add_telegraf_to_minion() {
     # generates a password on first add and is a no-op on re-add so the cred
     # is stable across repeated so-minion runs. postgres.telegraf_users on the
     # manager creates/updates the DB role from the same pillar.
-    so-telegraf-cred add "$MINION_ID"
-    if [ $? -ne 0 ]; then
-        log "ERROR" "Failed to provision postgres telegraf cred for $MINION_ID"
-        return 1
-    fi
+	log "INFO" "Provisioning postgres telegraf credential for $MINION_ID"
+	so-telegraf-cred add "$MINION_ID"
+	local result=$?
+	if [ $result -ne 0 ]; then
+		log "ERROR" "Failed to provision postgres telegraf cred for $MINION_ID (exit code: $result)"
+		return 1
+	fi
+	log "INFO" "Provisioned postgres telegraf credential for $MINION_ID"
 }
 
 function add_influxdb_to_minion() {
@@ -1042,8 +1075,59 @@ function updateMineAndApplyStates() {
 	fi
 }
 
+# Values end up in a Jinja-rendered pillar and in bash, and may come from the minion
+function validate_minion_vars() {
+	local error_msg=""
+	# Inline rather than valid_ip4: so-common is not installed yet when setup runs -o=setup
+	local octet='(25[0-5]|2[0-4][0-9]|1?[0-9]?[0-9])'
+	local ip4_re="^($octet\.){3}$octet$"
+
+	case "$NODETYPE" in
+		EVAL|STANDALONE|MANAGER|MANAGERSEARCH|MANAGERHYPE|IMPORT)
+			# Manager pillars also rewrite the CA pillar, so never accept them from a remote node
+			[[ "$OPERATION" == "setup" ]] || error_msg="Node type $NODETYPE can only be configured during setup"
+			;;
+		FLEET|IDH|HEAVYNODE|SENSOR|SEARCHNODE|RECEIVER|HYPERVISOR|DESKTOP)
+			;;
+		*)
+			error_msg="Invalid node type: ${NODETYPE:0:64}"
+			;;
+	esac
+
+	if [[ -z "$error_msg" ]]; then
+		if [[ ! "$MAINIP" =~ $ip4_re ]]; then
+			error_msg="Invalid MAINIP: ${MAINIP:0:64}"
+		elif [[ ! "$MNIC" =~ ^[A-Za-z0-9._-]*$ ]]; then
+			error_msg="Invalid MNIC: ${MNIC:0:64}"
+		elif [[ ! "$INTERFACE" =~ ^[A-Za-z0-9._-]*$ ]]; then
+			error_msg="Invalid INTERFACE: ${INTERFACE:0:64}"
+		elif [[ ! "$LSHOSTNAME" =~ ^[A-Za-z0-9._-]*$ ]]; then
+			error_msg="Invalid LSHOSTNAME: ${LSHOSTNAME:0:64}"
+		elif [[ ! "$ES_HEAP_SIZE" =~ ^([0-9]+[kKmMgG]?)?$ ]]; then
+			error_msg="Invalid ES_HEAP_SIZE: ${ES_HEAP_SIZE:0:64}"
+		elif [[ ! "$LSHEAP" =~ ^([0-9]+[kKmMgG]?)?$ ]]; then
+			error_msg="Invalid LSHEAP: ${LSHEAP:0:64}"
+		elif [[ ! "$CORECOUNT" =~ ^[0-9]*$ ]]; then
+			error_msg="Invalid CORECOUNT: ${CORECOUNT:0:64}"
+		elif [[ ! "$CPUCORES" =~ ^[0-9]*$ ]]; then
+			error_msg="Invalid CPUCORES: ${CPUCORES:0:64}"
+		elif [[ ! "$IDH_MGTRESTRICT" =~ ^(True|False)?$ ]]; then
+			error_msg="Invalid IDH_MGTRESTRICT: ${IDH_MGTRESTRICT:0:64}"
+		fi
+	fi
+
+	if [[ -n "$error_msg" ]]; then
+		log "ERROR" "$error_msg"
+		echo "$error_msg"
+		return 1
+	fi
+
+	# Free text; removing braces is enough to prevent any Jinja delimiter
+	NODE_DESCRIPTION=${NODE_DESCRIPTION//[\{\}[:cntrl:]]/}
+}
+
 function setupMinionFiles() {
-	log "INFO" "Setting up minion files for $MINION_ID"
+	log "INFO" "Setting up minion files for $MINION_ID (pillar: $PILLARFILE)"
 	
 	# Check to see if nodetype is set
 	if [ -z $NODETYPE ]; then
@@ -1053,6 +1137,8 @@ function setupMinionFiles() {
 		return 1
 	fi
 
+	validate_minion_vars || return 1
+
 	# Create the base minion files
 	create_minion_files || return 1
 
@@ -1069,7 +1155,10 @@ function setupMinionFiles() {
 	fi
 
 	# Create node-specific configuration
-	create$NODETYPE || return 1
+	create$NODETYPE || {
+		log "ERROR" "Failed to create $NODETYPE configuration for $MINION_ID"
+		return 1
+	}
 	
 	# Ensure proper ownership after all content is written
 	ensure_socore_ownership || return 1

salt/manager/tools/sbin/so-push-drainer

@@ -20,7 +20,7 @@ is older than debounce_seconds, this script:
     with the deduped actions list passed as pillar kwargs
   * deletes the contributed intent files on successful dispatch
 
-Reactor sls files (push_suricata, push_strelka, push_pillar) write intents
+Reactor sls files (push_files, push_pillar) write intents
 but never dispatch directly
 """
 

salt/manager/tools/sbin/so-saltstack-update

@@ -124,8 +124,8 @@ copy_new_files() {
   
   rsync -a salt $default_salt_dir/
   rsync -a pillar $default_salt_dir/
-  chown -R socore:socore $default_salt_dir/salt
-  chown -R socore:socore $default_salt_dir/pillar
+  chown -R root:root $default_salt_dir/salt
+  chown -R root:root $default_salt_dir/pillar
   chmod 755 $default_salt_dir/pillar/firewall/addfirewall.sh
 
   rm -rf /tmp/sogh

salt/manager/tools/sbin/so-soup-grid-highstate

@@ -0,0 +1,219 @@
+#!/bin/bash
+#
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+# so-soup-grid-highstate
+# ======================
+# Drives a batched, role-tiered highstate across every non-manager minion in the
+# grid. soup fires this (detached) after it finishes upgrading the manager so the
+# rest of the grid converges immediately instead of waiting for its own scheduled
+# highstate -- which, since the schedule moved from 15 minutes to 120 minutes
+# (salt:schedule:highstate_interval_minutes), could otherwise leave nodes on the
+# old version for up to ~2.5 hours (interval + splay) while the manager runs new code.
+#
+# Work is done by the existing orch.push_batch orchestration (salt/orch/push_batch.sls),
+# the same runner the active-push drainer uses, so batching/queueing behavior matches.
+# Tiers are dispatched in declaration order: searchnodes/heavynodes (Elasticsearch data
+# nodes) first, then receivers, then everything else -- so the data tier converges before
+# the ingest tier before sensors/fleet/idh/etc.
+#
+# When soup also upgraded Salt itself, remote minions must first highstate onto the new
+# salt-minion package (top.sls gates every real state on G@saltversion, so a stale-version
+# minion only gets salt.minion until it upgrades and reconnects). --salt-upgraded runs that
+# preliminary pass and waits for the fleet to settle before the tiered pass.
+#
+# This is best-effort: soup has already completed by the time this runs, and the 120-minute
+# scheduled highstate remains the backstop for any node that is offline or missed a batch.
+
+LOG_FILE=/opt/so/log/salt/so-soup-grid-highstate
+LOCK_FILE=/opt/so/state/so-soup-grid-highstate.lock
+SETTLE_MAX_WAIT=${GRID_HIGHSTATE_SETTLE_WAIT:-900}   # backstop for the post-salt-upgrade settle loop
+SETTLE_INTERVAL=15
+SETTLE_STABLE_CHECKS=3
+# salt-minion on an upgraded node restarts ~30s after the upgrade state runs
+# (salt/salt/minion/init.sls start_minion_post_upgrade); wait past that before sampling
+# so the settle loop sees the drop-off instead of settling on the pre-restart set.
+SETTLE_INITIAL_WAIT=${GRID_HIGHSTATE_SETTLE_INITIAL_WAIT:-45}
+
+BATCH=""
+BATCH_WAIT=""
+SALT_UPGRADED=false
+REASON="manual"
+
+log() {
+  echo "$(date '+%Y-%m-%d %H:%M:%S') | $*" | tee -a "$LOG_FILE"
+}
+
+usage() {
+  echo "Usage: so-soup-grid-highstate [--batch <spec>] [--batch-wait <sec>] [--salt-upgraded] [--reason <text>]"
+  exit 1
+}
+
+while [ $# -gt 0 ]; do
+  case "$1" in
+    --batch)        BATCH="$2"; shift 2 ;;
+    --batch-wait)   BATCH_WAIT="$2"; shift 2 ;;
+    --salt-upgraded) SALT_UPGRADED=true; shift ;;
+    --reason)       REASON="$2"; shift 2 ;;
+    -h|--help)      usage ;;
+    *)              echo "Unknown option: $1"; usage ;;
+  esac
+done
+
+mkdir -p "$(dirname "$LOG_FILE")" "$(dirname "$LOCK_FILE")"
+
+# Serialize: a second invocation (e.g. two soups, or a manual run overlapping soup's)
+# should not dispatch a competing set of batches.
+exec 9>"$LOCK_FILE"
+if ! flock -n 9; then
+  log "another so-soup-grid-highstate is already running (lock $LOCK_FILE held); exiting"
+  exit 0
+fi
+
+# Resolve batch settings from the salt:auto_apply pillar when not overridden on the
+# command line, falling back to the same defaults orch.push_batch/salt.defaults use.
+if [ -z "$BATCH" ]; then
+  BATCH=$(salt-call --out=newline_values_only pillar.get salt:auto_apply:batch 2>/dev/null)
+  [ -z "$BATCH" ] && BATCH='10%'
+fi
+if [ -z "$BATCH_WAIT" ]; then
+  BATCH_WAIT=$(salt-call --out=newline_values_only pillar.get salt:auto_apply:batch_wait 2>/dev/null)
+  [ -z "$BATCH_WAIT" ] && BATCH_WAIT=15
+fi
+
+MINIONID=$(salt-call --local --out=newline_values_only grains.get id 2>/dev/null)
+[ -z "$MINIONID" ] && MINIONID=$(cat /etc/salt/minion_id 2>/dev/null)
+if [ -z "$MINIONID" ]; then
+  log "could not determine this minion's id; aborting"
+  exit 1
+fi
+
+# Single-node grids (eval/standalone/import with no other accepted keys) have nothing
+# remote to push -- the manager already highstated during soup.
+NUM_ACCEPTED=$(salt-key --out=json --list=accepted 2>/dev/null | jq -r '.minions | length' 2>/dev/null)
+NUM_ACCEPTED=${NUM_ACCEPTED:-0}
+if [ "$NUM_ACCEPTED" -le 1 ]; then
+  log "single node grid ($NUM_ACCEPTED accepted minion(s)); nothing to push (reason=$REASON)"
+  exit 0
+fi
+
+log "starting grid highstate: reason=$REASON minion=$MINIONID accepted=$NUM_ACCEPTED batch=$BATCH batch_wait=$BATCH_WAIT salt_upgraded=$SALT_UPGRADED"
+
+# Count minions currently responsive on the bus (includes this manager).
+count_up() {
+  salt-run manage.up --out=json 2>/dev/null \
+    | python3 -c 'import sys,json; print(len(json.load(sys.stdin)))' 2>/dev/null
+}
+
+# Dispatch a single synchronous orch.push_batch run for the given actions JSON.
+# Synchronous is fine: soup launched us detached, so blocking here does not hold soup up.
+# expect_restart=true marks a dispatch (the salt-upgrade pass) where a non-zero rc is normal
+# because targets restart salt-minion mid-run -- so we don't log a misleading failure warning.
+dispatch() {
+  local desc="$1"
+  local actions="$2"
+  local expect_restart="${3:-false}"
+  local rc
+  log "dispatching $desc"
+  salt-run state.orchestrate orch.push_batch pillar="{\"actions\": $actions}" >>"$LOG_FILE" 2>&1
+  rc=$?
+  if [ "$rc" -eq 0 ]; then
+    log "$desc dispatch completed (rc=0)"
+  elif [ "$expect_restart" = "true" ]; then
+    log "$desc returned rc=$rc; this is expected during a salt upgrade (targets restart salt-minion mid-run). Waiting for them to reconnect before the tiered pass."
+  else
+    log "WARNING: $desc dispatch returned rc=$rc; nodes it missed will converge on the scheduled highstate"
+  fi
+}
+
+# Wait for the reachable minion set to recover to its pre-upgrade size and hold steady.
+# Used after the salt-upgrade pass, where targets restart salt-minion (~30s delayed, see
+# salt/salt/minion/init.sls) and drop off the bus before reconnecting on the new version.
+# target = how many minions were reachable just before the pass; requiring up >= target keeps
+# us from releasing the tiered pass while nodes are still down for their restart (settling on
+# the not-yet-restarted subset). We deliberately compare against the pre-upgrade reachable
+# count, not accepted keys, so a node an operator intentionally powered off never stalls us.
+# Bounded by SETTLE_MAX_WAIT.
+wait_for_settle() {
+  local target="$1"
+  local elapsed=0 prev=-1 stable=0 up=0
+  # Let the delayed salt-minion restart begin before we start counting stability, otherwise
+  # we could see the pre-restart set as "stable" and settle before the drop-off even happens.
+  sleep "$SETTLE_INITIAL_WAIT"
+  elapsed=$SETTLE_INITIAL_WAIT
+  while [ "$elapsed" -lt "$SETTLE_MAX_WAIT" ]; do
+    up=$(count_up); up=${up:-0}
+    if [ "$up" -ge "$target" ] && [ "$up" -eq "$prev" ]; then
+      stable=$((stable + 1))
+      [ "$stable" -ge "$SETTLE_STABLE_CHECKS" ] && break
+    else
+      stable=0
+    fi
+    prev=$up
+    sleep "$SETTLE_INTERVAL"
+    elapsed=$((elapsed + SETTLE_INTERVAL))
+  done
+  if [ "$up" -ge "$target" ]; then
+    log "fleet recovered to ${up} minions up (>= pre-upgrade ${target}) after ${elapsed}s"
+  else
+    log "WARNING: ${SETTLE_MAX_WAIT}s settle backstop hit; only ${up}/${target} pre-upgrade minions back up; proceeding (stragglers converge on the scheduled highstate)"
+  fi
+}
+
+# Pass 0: when Salt itself was upgraded, remote minions still on the old version only match
+# top.sls's 'not G@saltversion' block (salt.minion, which performs the package upgrade). Push
+# an untiered highstate so they upgrade+reconnect, then wait for them to come back before the
+# real tiered pass applies the new version's states.
+if [ "$SALT_UPGRADED" = "true" ]; then
+  PRE_UP=$(count_up); PRE_UP=${PRE_UP:-1}
+  log "pre-upgrade reachable minions (incl. this manager): $PRE_UP"
+  dispatch "salt-upgrade pass (all remote minions)" \
+    "[{\"highstate\": true, \"tgt\": \"not $MINIONID\", \"tgt_type\": \"compound\", \"batch\": \"$BATCH\", \"batch_wait\": $BATCH_WAIT}]" \
+    true
+  log "waiting for minions to reconnect on the new salt version"
+  wait_for_settle "$PRE_UP"
+fi
+
+# Tiered pass: Elasticsearch data nodes first, then receivers, then the remainder. The last
+# tier is defined as the complement of the earlier tiers (and of this manager) so coverage is
+# exhaustive -- sensors, fleet, idh, desktop, hypervisor, and any future role are all included.
+TIER_TGTS=(
+  "( *_searchnode or *_heavynode ) and not $MINIONID"
+  "*_receiver and not $MINIONID"
+  "not $MINIONID and not *_searchnode and not *_heavynode and not *_receiver"
+)
+
+# Count minions a compound target matches, using the master's key/cache data (no execution).
+tier_count() {
+  salt --out=json -C "$1" --preview-target 2>/dev/null | jq 'length' 2>/dev/null
+}
+
+# Build the actions JSON, including only tiers that actually match minions. An empty target
+# would make orch.push_batch's salt.state step return "No minions returned" -- a failure --
+# even though nothing needed to run, and grids commonly lack a tier (no receiver, etc.).
+# Keep the JSON on a single line: salt parses `pillar=<value>` kwargs with a non-DOTALL
+# regex, so an embedded newline makes it treat the whole token as a positional saltenv
+# instead ("No matching salt environment for environment 'pillar=...'").
+actions=""
+for tgt in "${TIER_TGTS[@]}"; do
+  n=$(tier_count "$tgt"); n=${n:-0}
+  if [ "$n" -ge 1 ]; then
+    [ -n "$actions" ] && actions="$actions, "
+    actions="$actions{\"highstate\": true, \"tgt\": \"$tgt\", \"tgt_type\": \"compound\", \"batch\": \"$BATCH\", \"batch_wait\": $BATCH_WAIT}"
+    log "tier matched $n minion(s): $tgt"
+  else
+    log "tier matched 0 minions, skipping: $tgt"
+  fi
+done
+
+if [ -z "$actions" ]; then
+  log "no remote minions matched any tier; nothing to push (reason=$REASON)"
+  exit 0
+fi
+dispatch "tiered pass (searchnodes/heavynodes -> receivers -> remainder)" "[$actions]"
+
+log "grid highstate complete (reason=$REASON)"
+exit 0

salt/manager/tools/sbin/so-user

@@ -129,7 +129,8 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-kratosUrl=${KRATOS_URL:-http://127.0.0.1:4434/admin}
+kratosContainer=${KRATOS_CONTAINER:-so-kratos}
+kratosUrl=${KRATOS_URL:-http://localhost:4434/admin}
 databasePath=${KRATOS_DB_PATH:-/nsm/kratos/db/db.sqlite}
 databaseTimeout=${KRATOS_DB_TIMEOUT:-5000}
 bcryptRounds=${BCRYPT_ROUNDS:-12}
@@ -154,6 +155,10 @@ function fail() {
   exit 1
 }
 
+function kratosCurl() {
+  docker exec "$kratosContainer" curl "$@"
+}
+
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -164,18 +169,18 @@ function require() {
 function verifyEnvironment() {
   require "htpasswd"
   require "jq"
-  require "curl"
+  require "docker"
   require "openssl"
   require "sqlite3"
   [[ ! -f $databasePath ]] && fail "Unable to find database file; specify path via KRATOS_DB_PATH environment variable"
-  response=$(curl -Ss -L ${kratosUrl}/)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/)
   [[ "$response" != "404 page not found" ]] && fail "Unable to communicate with Kratos; specify URL via KRATOS_URL environment variable"
 }
 
 function findIdByEmail() {
   email=${1,,}
 
-  response=$(curl -Ss -L ${kratosUrl}/identities)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
   identityId=$(echo "${response}" | jq -r ".[] | select(.verifiable_addresses[0].value == \"$email\") | .id")
   echo $identityId
 }
@@ -416,7 +421,7 @@ function syncAll() {
 }
 
 function listUsers() {
-  response=$(curl -Ss -L ${kratosUrl}/identities)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   users=$(echo "${response}" | jq -r ".[] | .verifiable_addresses[0].value" | sort)
@@ -495,7 +500,7 @@ function createUser() {
 EOF
   )
   
-  response=$(curl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   identityId=$(echo "${response}" | jq -r ".id")
@@ -518,7 +523,7 @@ function updateStatus() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -531,7 +536,7 @@ function updateStatus() {
     state="inactive"
   fi
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -550,7 +555,7 @@ function updateUserProfile() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -559,7 +564,7 @@ function updateUserProfile() {
   traitBlock="{\"email\":\"$email\",\"firstName\":\"$firstName\",\"lastName\":\"$lastName\",\"note\":\"$note\"}"
 
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -569,7 +574,7 @@ function deleteUser() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   rolesTmpFile="${socRolesFile}.tmp"

salt/manager/tools/sbin/soup

@@ -24,7 +24,11 @@ else
   POSTVERSION=$INSTALLEDVERSION
 fi
 INSTALLEDSALTVERSION=$(salt --versions-report | grep Salt: | awk '{print $2}')
-BATCHSIZE=5
+# Optional -b override for the grid highstate batch size (a count like "5" or a
+# percentage like "25%"). Empty means so-soup-grid-highstate uses the salt:auto_apply:batch
+# pillar default.
+BATCHSIZE=
+DEFAULT_DOCKER_RANGE='172.17.1.0/24'
 SOUP_LOG=/root/soup.log
 SOUP_DEBUG_LOG=/root/soup-debug.log
 WHATWOULDYOUSAYYAHDOHERE=soup
@@ -117,6 +121,9 @@ check_err() {
       161)
         echo 'Required intermediate Elasticsearch upgrade not complete'
       ;;
+      162)
+        echo 'One or more Elastic Agent nodes do not support the x86-64-v3 CPU instruction set'
+      ;;
       170)
         echo "Intermediate upgrade completed successfully to $next_step_so_version, but next soup to Security Onion $originally_requested_so_version could not be started automatically."
         echo "Start soup again manually to continue the upgrade to Security Onion $originally_requested_so_version."
@@ -328,14 +335,96 @@ check_pillar_items() {
 }
 
 check_cluster_health() {
+  # Require a 'green' cluster before upgrading
   echo "Checking Elasticsearch cluster health."
-  # Require a 'green' cluster before upgrading; anything less (yellow, red, or
-  # unreachable) blocks. Modeled on the wait used in so-elasticsearch-roles-load.
   if so-elasticsearch-query "_cluster/health?wait_for_status=green&timeout=120s" --fail > /dev/null 2>&1; then
     printf "\nThe Elasticsearch cluster is healthy (green). We can proceed with SOUP.\n\n"
+    return
+  fi
+
+  if command -v so-elasticsearch-troubleshoot > /dev/null 2>&1; then
+    printf "\nRunning so-elasticsearch-troubleshoot for additional detail.\n"
+    so-elasticsearch-troubleshoot || true
+  fi
+
+  printf "\nThe Elasticsearch cluster is not green. Resolve the cluster health issue so the cluster is green before running SOUP again.\n\n"
+  exit 0
+}
+
+no_soup_for_you() {
+  echo ""
+  echo "No soup for you!"
+  exit 162
+}
+
+check_cpu_compatibility() {
+  # Roles running a container built from the so-elastic-agent image; mirrors the
+  # elasticagent and elasticfleet entries in salt/reactor/pillar_push_map.yaml.
+  local cpu_target='G@role:so-heavynode or G@role:so-eval or G@role:so-fleet or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
+  local expected_nodes cpu_results node result confirm
+  local -a unsupported=() offline=()
+
+  echo "Checking that Elastic Agent nodes support the x86-64-v3 CPU instruction set now required by Elastic."
+
+  if [[ "$SKIP_CPU_CHECK" == "true" ]]; then
+    printf "\nSkipping the x86-64-v3 CPU check because --skip-cpu-check was specified.\n\n"
+    return
+  fi
+
+  # Nodes that never answer are absent from the results, so diff against who should have.
+  expected_nodes=$(salt -C "$cpu_target" --preview-target --out=json 2>/dev/null | jq -r '.[]?') || true
+  if [[ -z "$expected_nodes" ]]; then
+    printf "\nCould not determine which nodes run the Elastic Agent, so the x86-64-v3 CPU check cannot run.\n"
+    no_soup_for_you
+  fi
+
+  cpu_results=$(salt -t 30 -C "$cpu_target" cmd.run "/lib64/ld-linux-x86-64.so.2 --help | grep x86-64-v3" --out=json 2>/dev/null) || true
+
+  while IFS= read -r node; do
+    [[ -z "$node" ]] && continue
+    result=$(jq -r --arg node "$node" '.[$node] // empty' <<< "$cpu_results" 2>/dev/null)
+    if [[ -z "$result" || "$result" == *"did not return"* ]]; then
+      offline+=("$node")
+    elif [[ "$result" != *"x86-64-v3 (supported"* ]]; then
+      # glibc appends "(supported, searched)" only when supported; the open paren keeps
+      # this from matching a future "(unsupported".
+      unsupported+=("$node")
+    fi
+  done <<< "$expected_nodes"
+
+  if [[ ${#unsupported[@]} -eq 0 && ${#offline[@]} -eq 0 ]]; then
+    printf "\nAll Elastic Agent nodes support x86-64-v3. We can proceed with SOUP.\n\n"
+    return
+  fi
+
+  echo ""
+  if [[ ${#unsupported[@]} -gt 0 ]]; then
+    echo "The following node(s) do NOT support the x86-64-v3 CPU instruction set:"
+    printf '  %s\n' "${unsupported[@]}"
+    echo ""
+    echo "Upstream Elastic now builds its binaries for x86-64-v3, so these nodes can no"
+    echo "longer run Elastic. Upgrading them WILL BREAK them."
+    echo ""
+  fi
+  if [[ ${#offline[@]} -gt 0 ]]; then
+    echo "The following node(s) did not respond and could not be checked:"
+    printf '  %s\n' "${offline[@]}"
+    echo ""
+    echo "These nodes are offline, so we cannot confirm they support x86-64-v3, which"
+    echo "upstream Elastic now requires."
+    echo ""
+  fi
+
+  if [[ -n $UNATTENDED ]]; then
+    echo "Unattended mode cannot prompt for an override. Re-run soup interactively, or pass --skip-cpu-check to bypass this check."
+    no_soup_for_you
+  fi
+
+  read -rp "Type 'override' to continue anyway, or press Enter to exit: " confirm
+  if [[ "${confirm,,}" == "override" ]]; then
+    printf "\nOverride accepted. Continuing at your own risk.\n\n"
   else
-    printf "\nThe Elasticsearch cluster is not green. Please resolve the cluster health issue so the cluster is green before running SOUP again.\n\n"
-    exit 0
+    no_soup_for_you
   fi
 }
 
@@ -442,18 +531,61 @@ get_soup_script_hashes() {
 }
 
 highstate() {
-  # Run a highstate.
+  # Run a highstate with a retry attempt.
+  if salt-call state.highstate -l info queue=True; then
+    return 0
+  fi
+
+  echo "Initial highstate attempt had a problem; retrying in 30 seconds."
+  sleep 30
   salt-call state.highstate -l info queue=True
 }
 
+upgrade_searchnode_elasticsearch() {
+  # Run the elasticsearch state across the true elastic cluster (non-heavy) with a retry attempt
+  #   Excludes the manager, so that kibana & elasticfleet are not upgraded until searchnodes are upgraded.
+  echo "Getting ready to upgrade Elasticsearch across the grid. This may take a while..."
+  if salt -b 10% -C "I@elasticsearch:enabled and not G@role:so-heavynode and not G@id:${MINIONID}" state.apply elasticsearch queue=True; then
+    return 0
+  fi
+  
+  echo "Initial elasticsearch state attempt had a problem; retrying in 30 seconds."
+  sleep 30
+  salt -b 10% -C "I@elasticsearch:enabled and not G@role:so-heavynode and not G@id:${MINIONID}" state.apply elasticsearch queue=True
+}
+
+push_grid_highstate() {
+  # Drive a batched, role-tiered highstate across the rest of the grid so remote minions
+  # pick up this upgrade now instead of waiting up to ~2.5 hours for their own scheduled
+  # highstate (the schedule moved from 15 to 120 minutes). so-soup-grid-highstate does the work
+  # via orch.push_batch; it only exists once the manager highstate has deployed this
+  # version's sbin files, so guard on it. Launch fully detached (setsid) so it survives an
+  # SSH drop, and never let it affect soup's exit status -- it is best-effort with the
+  # scheduled highstate as backstop.
+  if [[ ! -x /usr/sbin/so-soup-grid-highstate ]]; then
+    echo "so-soup-grid-highstate not present; remote nodes will converge on their scheduled highstate."
+    return 0
+  fi
+
+  local extra_args=()
+  if [[ $SALTUPGRADED == true || $UPGRADESALT -eq 1 ]]; then
+    extra_args+=(--salt-upgraded)
+  fi
+  if [[ -n "$BATCHSIZE" ]]; then
+    extra_args+=(--batch "$BATCHSIZE")
+  fi
+
+  echo "Dispatching a grid-wide highstate to remote nodes. Progress: /opt/so/log/salt/so-soup-grid-highstate"
+  setsid nohup /usr/sbin/so-soup-grid-highstate --reason soup "${extra_args[@]}" >/dev/null 2>&1 &
+}
+
 masterlock() {
   echo "Locking Salt Master"
   mv -v $TOPFILE $BACKUPTOPFILE
-  # Render the real top file only for the host running soup; every other
-  # minion gets an empty top (no states) while the master is upgrading.
-  echo "{% if grains['id'] == '$MINIONID' %}" > $TOPFILE
-  cat $BACKUPTOPFILE >> $TOPFILE
-  echo "{% endif %}" >> $TOPFILE
+  echo "base:" > $TOPFILE
+  echo "  $MINIONID:" >> $TOPFILE
+  echo "    - ca" >> $TOPFILE
+  echo "    - elasticsearch" >> $TOPFILE
 }
 
 masterunlock() {
@@ -473,6 +605,8 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" =~ ^2\.4\.21[0-9]+$ ]] && up_to_3.0.0
     [[ "$INSTALLEDVERSION" == "3.0.0" ]] && up_to_3.1.0
     [[ "$INSTALLEDVERSION" == "3.1.0" ]] && up_to_3.2.0
+    [[ "$INSTALLEDVERSION" == "3.2.0" ]] && up_to_3.3.0
+    [[ "$INSTALLEDVERSION" == "3.3.0" ]] && up_to_3.4.0
     true
 }
 
@@ -490,6 +624,8 @@ postupgrade_changes() {
     [[ "$POSTVERSION" =~ ^2\.4\.21[0-9]+$ ]] && post_to_3.0.0
     [[ "$POSTVERSION" == "3.0.0" ]] && post_to_3.1.0
     [[ "$POSTVERSION" == "3.1.0" ]] && post_to_3.2.0
+    [[ "$POSTVERSION" == "3.2.0" ]] && post_to_3.3.0
+    [[ "$POSTVERSION" == "3.3.0" ]] && post_to_3.4.0
     # All applicable post-upgrade steps completed; clear the resume marker.
     rm -f "$POSTVERSION_FILE"
     true
@@ -872,7 +1008,7 @@ post_to_3.1.0() {
 recollate_postgres() {
   echo ""
   echo "Recollating PostgreSQL databases. The following output may contain warnings about a version mismatch, followed by a note indicating that the collation version has been changed."
-  for db in postgres securityonion so_telegraf; do
+  for db in template1 postgres securityonion so_telegraf; do
     docker exec so-postgres psql -U postgres $db -c "reindex database $db"
     docker exec so-postgres psql -U postgres $db -c "alter database $db refresh collation version"
   done
@@ -967,13 +1103,14 @@ update_kafka_metadata() {
 up_to_3.2.0() {
   ensure_salt_local_pillar
 
-  # download 9.3.7 elastic agent packages
-  determine_elastic_agent_upgrade
-
   fix_logstash_0013_lumberjack_pipeline_name
 
   pin_elasticsearch_data_retention_method
 
+  # Run so-elastic-fleet-es-url update with --force to ensure eval/import have
+  #  configured so-manager_elasicsearch as the default output for both monitoring and logs
+  /usr/sbin/so-elastic-fleet-es-url-update --force
+
   INSTALLEDVERSION=3.2.0
 }
 
@@ -984,19 +1121,137 @@ post_to_3.2.0() {
   # SOC database bootstrap is handled by the postgres.enabled highstate.
   scrub_postgres_log_passwords
 
-  # Generate 9.3.7 elastic agent installers
-  echo "Regenerating Elastic Agent Installers"
-  /sbin/so-elastic-agent-gen-installers
-
   kibana_backport_streams_index_template
 
   update_kafka_metadata "4.3"
 
   set_postversion 3.2.0
 }
-
 ### 3.2.0 End ###
 
+### 3.3.0 Scripts ###
+up_to_3.3.0() {
+  # download 9.4.5 elastic agent packages
+  determine_elastic_agent_upgrade
+  
+  # remove existing (patched) elasticsearch index template to match integration naming change
+  if ! remove_elasticsearch_index_template "so-logs-sentinel_one_cloud_funnel.login" "sentinel_one_cloud_funnel.login changed to sentinel_one_cloud_funnel.logins"; then
+    FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically remove the so-logs-sentinel_one_cloud_funnel.login index template. This step can be performed manually using the following command:")
+    FINAL_MESSAGE_QUEUE+=("    - sudo so-elasticsearch-query _index_template/so-logs-sentinel_one_cloud_funnel.login -XDELETE && so-checkin")
+  fi
+
+  INSTALLEDVERSION=3.3.0
+}
+
+telegraf_repair() {
+  # Only grids whose Telegraf partitions stalled need this; --check exits 1
+  # when there is something to repair, so everyone else is left alone.
+  local repair=/usr/sbin/so-telegraf-repair
+  [[ -x "$repair" ]] || return 0
+  docker ps --format '{{.Names}}' | grep -qx so-postgres || return 0
+
+  echo "Checking Telegraf metric partitions."
+  local status=0
+  "$repair" --check >> "$SOUP_LOG" 2>&1 || status=$?
+  case "$status" in
+    0) echo "  Telegraf partitions are healthy; nothing to repair." ;;
+    1) echo "  Repairing stalled Telegraf partitions."
+       "$repair" --yes \
+         || echo "  warning: so-telegraf-repair failed; run it manually" >&2 ;;
+    *) echo "  Skipping; Telegraf is not storing metrics in Postgres on this host." ;;
+  esac
+}
+
+post_to_3.3.0() {
+  # Recollate again since some internal DBs were excluded during 3.2.0 soup
+  recollate_postgres
+
+  # Generate 9.4.5 elastic agent installers
+  echo "Regenerating Elastic Agent Installers"
+  /sbin/so-elastic-agent-gen-installers
+
+  telegraf_repair
+
+  set_postversion 3.3.0
+}
+### 3.3.0 End ###
+
+### 3.4.0 Scripts ###
+up_to_3.4.0() {
+  set_soauth_range
+
+  echo "Removing so-kratos, so-hydra and so-soc so they are recreated on the soauth network."
+  docker rm -f so-kratos so-hydra so-soc >> $SOUP_LOG 2>&1
+
+  INSTALLEDVERSION=3.4.0
+}
+
+set_soauth_range() {
+  local pillar_file=/opt/so/saltstack/local/pillar/docker/soc_docker.sls
+  local current_range suggested authnet authgw input
+
+  [[ -f "$pillar_file" ]] || return 0
+
+  current_range=$(so-yaml.py get -r "$pillar_file" docker.range 2>/dev/null) || return 0
+
+  # A default range gets the 172.17.2.0/24 from docker/defaults.yaml, same as a fresh
+  # install, so there is nothing to ask about.
+  [[ -n "$current_range" && "$current_range" != "$DEFAULT_DOCKER_RANGE" ]] || return 0
+
+  if so-yaml.py get -r "$pillar_file" docker.networks.soauth.range >/dev/null 2>&1; then
+    return 0
+  fi
+
+  suggested=$(echo "${current_range%%/*}" | awk -F'.' '{ printf "%s.%s.%s.%s", $1, $2, ($3 + 1) % 256, $4 }')
+
+  if [[ -z $UNATTENDED ]]; then
+    echo ""
+    echo "This grid uses a custom Docker range ($current_range). The authentication"
+    echo "services are moving to their own isolated network, which needs a second /24"
+    echo "that does not overlap it."
+    echo ""
+    while :; do
+      read -rp "Enter the network without the /24 suffix, or press Enter for ${suggested}: " input
+      [[ -z "$input" ]] && input="$suggested"
+      if valid_soauth_range "$input" "$current_range"; then
+        authnet="$input"
+        break
+      fi
+      echo "That range must be a valid IPv4 network, must not be within 172.17.0.0/24, and must not overlap ${current_range}."
+    done
+  else
+    if ! valid_soauth_range "$suggested" "$current_range"; then
+      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to pick a range for the authentication network alongside $current_range. Set it manually before the next highstate:")
+      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.range <network>/24")
+      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.gateway <gateway>")
+      return 0
+    fi
+    authnet="$suggested"
+    FINAL_MESSAGE_QUEUE+=("NOTE: The authentication services moved to an isolated Docker network and were assigned ${authnet}/24.")
+    FINAL_MESSAGE_QUEUE+=("    - If that conflicts with your environment, update docker.networks.soauth in $pillar_file and run so-checkin.")
+  fi
+
+  authgw=$(echo "$authnet" | awk -F'.' '{print $1,$2,$3,1}' OFS='.')
+
+  echo "Assigning the authentication network the range ${authnet}/24."
+  so-yaml.py add "$pillar_file" docker.networks.soauth.range "${authnet}/24" >> $SOUP_LOG 2>&1
+  so-yaml.py add "$pillar_file" docker.networks.soauth.gateway "$authgw" >> $SOUP_LOG 2>&1
+}
+
+valid_soauth_range() {
+  local candidate=$1 docker_range=$2
+
+  valid_ip4 "$candidate" || return 1
+  [[ $candidate =~ ^172\.17\.0\. ]] && return 1
+  [[ "${candidate}/24" == "$docker_range" ]] && return 1
+  return 0
+}
+
+post_to_3.4.0() {
+  set_postversion 3.4.0
+}
+### 3.4.0 End ###
+
 
 repo_sync() {
   echo "Sync the local repo."
@@ -1266,11 +1521,12 @@ verify_es_version_compatibility() {
     local is_active_intermediate_upgrade=1
     # supported upgrade paths for SO-ES versions
     declare -A es_upgrade_map=(
-        ["8.18.4"]="8.18.6 8.18.8 9.0.8"
+      ["8.18.4"]="8.18.6 8.18.8 9.0.8"
 	    ["8.18.6"]="8.18.8 9.0.8"
 	    ["8.18.8"]="9.0.8"
-        ["9.0.8"]="9.3.3 9.3.7"
-        ["9.3.3"]="9.3.7"
+      ["9.0.8"]="9.3.3 9.3.7 9.4.5"
+      ["9.3.3"]="9.3.7 9.4.5"
+      ["9.3.7"]="9.4.5"
     )
 
     # Elasticsearch MUST upgrade through these versions
@@ -1880,6 +2136,9 @@ main() {
 
   echo "Let's see if we need to update Security Onion."
   upgrade_check
+
+  check_cpu_compatibility
+
   upgrade_space
 
   echo "Verifying Elasticsearch version compatibility across the grid before upgrading."
@@ -1926,6 +2185,9 @@ main() {
     # rather than reporting "already latest". The soversion/pillar writes in
     # update_version are no-ops here since the version is unchanged for a hotfix.
     update_version
+    # Push the hotfix out to the rest of the grid rather than waiting for the scheduled
+    # highstate. Hotfixes never upgrade Salt, so no --salt-upgraded pass is needed.
+    push_grid_highstate
   else
     SOUP_UPGRADE_STARTED=true
     echo ""
@@ -2043,12 +2305,28 @@ main() {
 
     # ensure the mine is updated and populated before highstates run, following the salt-master restart
     update_salt_mine
-
+    
+    # kick off a searchnode elasticsearch upgrade
+    set +e
+    if [[ "$es_version" != "$target_es_version" ]]; then
+      if salt-key -L accepted | grep -q "_searchnode$" 2>/dev/null; then
+        # only run if there is atleast 1 searchnode
+        upgrade_searchnode_elasticsearch
+      fi
+    fi
+    set -e
+    
     highstate
     check_saltmaster_status
     postupgrade_changes
     [[ $is_airgap -eq 0 ]] && unmount_update
-
+    
+    if [[ "$es_version" != "$target_es_version" ]]; then
+      # Run final elasticsearch / fleet state on manager to ensure addon index templates are created/regenerated and loaded
+      echo "Running final Elastic states at $(date +"%T.%6N"), after upgrade to $NEWVERSION"
+      salt-call state.apply elasticsearch,elasticfleet queue=True
+    fi
+    
     echo ""
     echo "Upgrade to $NEWVERSION complete."
 
@@ -2092,13 +2370,18 @@ main() {
 
     if [[ $NUM_MINIONS -gt 1 ]]; then
 
+      # Actively drive the rest of the grid to this version now. The scheduled highstate
+      # runs only every 120 minutes (salt:schedule:highstate_interval_minutes), so without
+      # this remote nodes could sit on the old version for a couple of hours after soup finishes.
+      push_grid_highstate
+
       cat << EOF
 
 
 
-This appears to be a distributed deployment. Other nodes should update themselves at the next Salt highstate (typically within 15 minutes). Do not manually restart anything until you know that all the search/heavy nodes in your deployment are updated. This is especially important if you are using true clustering for Elasticsearch.
+This appears to be a distributed deployment. soup has dispatched a batched, grid-wide highstate to update the other nodes now: Elasticsearch data nodes (search/heavynodes) first, then receivers, then sensors and the remaining nodes. Progress is logged to /opt/so/log/salt/so-soup-grid-highstate, and you can watch nodes update from the Grid section of SOC. Do not manually restart anything until you know that all the search/heavynodes in your deployment are updated. This is especially important if you are using true clustering for Elasticsearch.
 
-Each minion is on a random 15 minute check-in period and things like network bandwidth can be a factor in how long the actual upgrade takes. If you have a heavy node on a slow link, it is going to take a while to get the containers to it. Depending on what changes happened between the versions, Elasticsearch might not be able to talk to said heavy node until the update is complete.
+Nodes are updated in batches, and things like network bandwidth can be a factor in how long the actual upgrade takes. If you have a heavy node on a slow link, it is going to take a while to get the containers to it. Depending on what changes happened between the versions, Elasticsearch might not be able to talk to said heavy node until the update is complete. Any node that is offline or missed a batch will converge on its own scheduled highstate (every 120 minutes by default).
 
 If it looks like you’re missing data after the upgrade, please avoid restarting services and instead make sure at least one search node has completed its upgrade. The best way to do this is to run 'sudo salt-call state.highstate' from a search node and make sure there are no errors. Typically if it works on one node it will work on the rest. Sensor nodes are less complex and will update as they check in so you can monitor those from the Grid section of SOC.
 
@@ -2134,12 +2417,25 @@ fi
   echo "### soup has been served at $(date) ###"
 }
 
+SKIP_CPU_CHECK=false
+declare -a SOUP_ARGS=()
+for arg in "$@"; do
+  if [[ "$arg" == "--skip-cpu-check" ]]; then
+    SKIP_CPU_CHECK=true
+  else
+    SOUP_ARGS+=("$arg")
+  fi
+done
+set -- "${SOUP_ARGS[@]}"
+
 while getopts ":b:f:y" opt; do
   case ${opt} in
     b )
       BATCHSIZE="$OPTARG"
-      if ! [[ "$BATCHSIZE" =~ ^[1-9][0-9]*$ ]]; then
-        echo "Batch size must be a number greater than 0."
+      # Accept either a plain count (e.g. 5) or a percentage (e.g. 25%); passed through
+      # to so-soup-grid-highstate --batch, which salt's batch/batch_wait accepts in both forms.
+      if ! [[ "$BATCHSIZE" =~ ^[1-9][0-9]*%?$ ]]; then
+        echo "Batch size must be a number greater than 0, optionally with a trailing % (e.g. 5 or 25%)."
         exit 1
       fi
     ;;
@@ -2155,7 +2451,7 @@ while getopts ":b:f:y" opt; do
       ISOLOC="$OPTARG"
     ;;
     \? )
-      echo "Usage: soup [-b] [-y] [-f <iso location>]"
+      echo "Usage: soup [-b] [-y] [-f <iso location>] [--skip-cpu-check]"
       exit 1
     ;;
     : )

salt/nginx/config.sls

@@ -57,8 +57,8 @@ nginx_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://nginx/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #nginx_sbin_jinja:

salt/nginx/etc/nginx.conf

@@ -96,14 +96,14 @@ http {
 		add_header 	X-XSS-Protection            "1; mode=block";
 		add_header 	X-Content-Type-Options      nosniff;
 		add_header 	Strict-Transport-Security   "max-age=31536000; includeSubDomains";
-		add_header 	referrer-Policy             no-referrer;
+		add_header 	Referrer-Policy             no-referrer;
 
 		ssl_certificate "/etc/pki/nginx/server.crt";
 		ssl_certificate_key "/etc/pki/nginx/server.key";
 		ssl_session_cache shared:SSL:1m;
 		ssl_session_timeout  10m;
 		ssl_ciphers TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384:TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305_SHA256:TLS_ECDHE_RSA_WITH_ARIA_256_GCM_SHA384:TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256:TLS_ECDHE_RSA_WITH_ARIA_128_GCM_SHA256:TLS_RSA_WITH_AES_256_GCM_SHA384:TLS_RSA_WITH_AES_256_CCM:TLS_RSA_WITH_ARIA_256_GCM_SHA384:TLS_RSA_WITH_AES_128_GCM_SHA256:TLS_RSA_WITH_AES_128_CCM:TLS_RSA_WITH_ARIA_128_GCM_SHA256;
-		ssl_ecdh_curve secp521r1:secp384r1;
+		ssl_ecdh_curve X25519:secp521r1:secp384r1;
 		ssl_prefer_server_ciphers on;
 		ssl_protocols TLSv1.2 TLSv1.3;
 	}
@@ -138,14 +138,14 @@ http {
 		add_header 	X-XSS-Protection            "1; mode=block";
 		add_header 	X-Content-Type-Options      nosniff;
 		add_header 	Strict-Transport-Security   "max-age=31536000; includeSubDomains";
-		add_header 	referrer-Policy             no-referrer;
+		add_header 	Referrer-Policy             no-referrer;
 
 		ssl_certificate "/etc/pki/nginx/server.crt";
 		ssl_certificate_key "/etc/pki/nginx/server.key";
 		ssl_session_cache shared:SSL:1m;
 		ssl_session_timeout  10m;
 		ssl_ciphers TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384:TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305_SHA256:TLS_ECDHE_RSA_WITH_ARIA_256_GCM_SHA384:TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256:TLS_ECDHE_RSA_WITH_ARIA_128_GCM_SHA256:TLS_RSA_WITH_AES_256_GCM_SHA384:TLS_RSA_WITH_AES_256_CCM:TLS_RSA_WITH_ARIA_256_GCM_SHA384:TLS_RSA_WITH_AES_128_GCM_SHA256:TLS_RSA_WITH_AES_128_CCM:TLS_RSA_WITH_ARIA_128_GCM_SHA256;
-		ssl_ecdh_curve secp521r1:secp384r1;
+		ssl_ecdh_curve X25519:secp521r1:secp384r1;
 		ssl_prefer_server_ciphers on;
 		ssl_protocols TLSv1.2 TLSv1.3;
         location / {
@@ -172,18 +172,18 @@ http {
 		add_header 	X-XSS-Protection            "1; mode=block";
 		add_header 	X-Content-Type-Options      nosniff;
 		add_header 	Strict-Transport-Security   "max-age=31536000; includeSubDomains";
-		add_header 	referrer-Policy             no-referrer;
+		add_header 	Referrer-Policy             no-referrer;
 
 		ssl_certificate "/etc/pki/nginx/server.crt";
 		ssl_certificate_key "/etc/pki/nginx/server.key";
 		ssl_session_cache shared:SSL:1m;
 		ssl_session_timeout  10m;
 		ssl_ciphers TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384:TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305_SHA256:TLS_ECDHE_RSA_WITH_ARIA_256_GCM_SHA384:TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256:TLS_ECDHE_RSA_WITH_ARIA_128_GCM_SHA256:TLS_RSA_WITH_AES_256_GCM_SHA384:TLS_RSA_WITH_AES_256_CCM:TLS_RSA_WITH_ARIA_256_GCM_SHA384:TLS_RSA_WITH_AES_128_GCM_SHA256:TLS_RSA_WITH_AES_128_CCM:TLS_RSA_WITH_ARIA_128_GCM_SHA256;
-		ssl_ecdh_curve secp521r1:secp384r1;
+		ssl_ecdh_curve X25519:secp521r1:secp384r1;
 		ssl_prefer_server_ciphers on;
 		ssl_protocols TLSv1.2 TLSv1.3;
 
-		location ~* (^/login/.*|^/js/.*|^/css/.*|^/images/.*|^/pages/.*|^/docs/.*) {
+		location ~* (^/login|^/login/.*|^/js/.*|^/css/.*|^/images/.*|^/pages/.*|^/docs/.*) {
 			proxy_pass            http://{{ GLOBALS.manager }}:9822;
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
@@ -198,6 +198,10 @@ http {
 		}
 
 		location / {
+			if ($http_authorization ~* "^Bearer .*$") {
+				return 401;
+			}
+
 			auth_request            /auth/sessions/whoami;
 			auth_request_set        $userid $upstream_http_x_kratos_authenticated_identity_id;
 			proxy_set_header        x-user-id $userid;
@@ -218,6 +222,13 @@ http {
 			add_header              Cache-Control "no-cache, no-store, must-revalidate";
 			add_header              Pragma "no-cache";
 			add_header              Expires "0";
+
+			add_header 	Content-Security-Policy     "default-src 'self' 'unsafe-inline' 'unsafe-eval' https: data: blob: wss:; frame-ancestors 'self'";
+			add_header 	X-Frame-Options             SAMEORIGIN;
+			add_header 	X-XSS-Protection            "1; mode=block";
+			add_header 	X-Content-Type-Options      nosniff;
+			add_header 	Strict-Transport-Security   "max-age=31536000; includeSubDomains";
+			add_header 	Referrer-Policy             no-referrer;
 		}
 
 		location ~ ^/auth/.*?(login|oidc/callback) {
@@ -249,7 +260,7 @@ http {
 		}
 
 {%  if 'api' in salt['pillar.get']('features', []) %}
-		location ~* (^/oauth2/token.*|^.well-known/jwks.json|^.well-known/openid-configuration) {
+		location ~* (^/oauth2/token.*|^/\.well-known/jwks.json|^/\.well-known/openid-configuration) {
 			limit_req             zone=auth_throttle burst={{ NGINXMERGED.config.throttle_login_burst }} nodelay;
 			limit_req_status      429;
 			proxy_pass            http://{{ GLOBALS.manager }}:4444;
@@ -383,6 +394,11 @@ http {
 			if ($http_authorization = "") {
 				return 403;
 			}
+
+			if ($http_authorization ~* "^Bearer .*$") {
+				return 401;
+			}
+
 			proxy_pass            http://{{ GLOBALS.manager }}:9822/;
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
@@ -399,7 +415,7 @@ http {
 		error_page 429 = @error429;
 
 		location @error401 {
-			if ($request_uri ~* (^.*/api/.*|^/connect/.*|^/oauth2/.*|^/.*\.map$)) {
+			if ($request_uri ~* (^.*/api/.*|^.*/login.*|^.*/logout.*|^/connect/.*|^/oauth2/.*|^/.*\.map$)) {
 				return    401;
 			}
 

salt/postgres/defaults.yaml

@@ -16,4 +16,4 @@ postgres:
     logging_collector: 'off'
     log_min_messages: 'warning'
     shared_preload_libraries: pg_cron
-    cron.database_name: so_telegraf
+    cron.database_name: postgres

salt/postgres/files/init-db.sh

@@ -29,6 +29,8 @@ psql -v ON_ERROR_STOP=1 --username "$POSTGRES_USER" --dbname "$POSTGRES_DB" <<-E
     -- revoking CONNECT closes the soft edge entirely.
     REVOKE CONNECT ON DATABASE "$POSTGRES_DB" FROM PUBLIC;
     GRANT CONNECT ON DATABASE "$POSTGRES_DB" TO "$SO_POSTGRES_USER";
+
+    CREATE EXTENSION IF NOT EXISTS vector;
 EOSQL
 
 # Bootstrap the Telegraf metrics database. Per-minion roles + schemas are

salt/postgres/soc_postgres.yaml

@@ -83,7 +83,7 @@ postgres:
       advanced: True
       helpLink: postgres
     cron.database_name:
-      description: Database pg_cron schedules jobs in. Must be so_telegraf so partman maintenance runs in the right database context.
+      description: Database pg_cron keeps its job metadata in. Must already exist when PostgreSQL starts, because pg_cron's launcher connects to it at startup and never retries if it is missing. The maintenance job itself targets so_telegraf.
       global: True
       advanced: True
       helpLink: postgres

salt/postgres/tools/sbin/so-postgres-backup

@@ -47,7 +47,12 @@ trap 'rm -f "$TMPFILE"' EXIT
 
 # Dump all databases and roles, compress. Write to a temp file so the final
 # filename only ever appears for a complete, verified backup.
-if ! docker exec so-postgres pg_dumpall -U postgres | gzip > "$TMPFILE"; then
+#
+# so_telegraf is excluded: it is transient metrics on a short retention window,
+# it dominates the dump size, and it is rebuilt automatically after a restore --
+# init-db.sh recreates the database and Telegraf recreates its tables on first
+# write. Roles are globals, so the per-minion telegraf logins are still dumped.
+if ! docker exec so-postgres pg_dumpall -U postgres --exclude-database=so_telegraf | gzip > "$TMPFILE"; then
   log "ERROR: pg_dumpall/gzip failed; backup aborted"
   exit 1
 fi

salt/postgres/tools/sbin/so-telegraf-postgres

@@ -5,11 +5,18 @@ set -e
 # Usage: so-telegraf-postgres <subcommand>
 #   create_db    Ensure the so_telegraf database exists.
 #   group_role   Provision the so_telegraf group role, telegraf/partman schemas,
-#                pg_partman, pg_cron, and the hourly partman maintenance job.
+#                pg_partman, the so_admin maintenance routines, and the hourly
+#                pg_cron maintenance job.
 #   user         Create or update a per-minion login role granted to so_telegraf.
 #                Env: ROLE_USER, ROLE_PASS.
-#   retention    Reconcile partman retention on telegraf parents.
+#   retention    Reconcile partman retention and premake on telegraf parents.
 #                Env: RETENTION_DAYS.
+#   maintenance  Drain default partitions and run partman maintenance.
+#   check        Report partition health. Non-zero if any parent is unhealthy.
+#
+# A default partition holding rows for a day blocks creating that day's child,
+# so maintenance drains defaults before calling partman. Use so-telegraf-repair
+# on a grid already stuck in that state.
 
 cmd="${1:?subcommand required}"
 
@@ -36,7 +43,6 @@ CREATE SCHEMA IF NOT EXISTS telegraf AUTHORIZATION so_telegraf;
 GRANT USAGE, CREATE ON SCHEMA telegraf TO so_telegraf;
 CREATE SCHEMA IF NOT EXISTS partman;
 CREATE EXTENSION IF NOT EXISTS pg_partman SCHEMA partman;
-CREATE EXTENSION IF NOT EXISTS pg_cron;
 -- Telegraf (running as so_telegraf) calls partman.create_parent()
 -- on first write of each metric, which needs USAGE on the partman
 -- schema, EXECUTE on its functions/procedures, and write access to
@@ -51,12 +57,141 @@ ALTER DEFAULT PRIVILEGES IN SCHEMA partman
     GRANT SELECT, INSERT, UPDATE, DELETE ON TABLES TO so_telegraf;
 ALTER DEFAULT PRIVILEGES IN SCHEMA partman
     GRANT USAGE, SELECT, UPDATE ON SEQUENCES TO so_telegraf;
--- Hourly partman maintenance. cron.schedule is idempotent by jobname.
-SELECT cron.schedule(
+
+-- pg_cron runs these as postgres, so they must not sit in a schema any
+-- Telegraf role can create objects in.
+CREATE SCHEMA IF NOT EXISTS so_admin AUTHORIZATION postgres;
+REVOKE ALL ON SCHEMA so_admin FROM PUBLIC;
+
+CREATE OR REPLACE PROCEDURE so_admin.telegraf_maintenance()
+LANGUAGE plpgsql
+AS $proc$
+DECLARE
+    r          record;
+    v_default  text;
+    v_rows     bigint;
+BEGIN
+    -- No per-parent EXCEPTION handler: partition_data_proc commits internally,
+    -- and COMMIT is illegal while a subtransaction is active. A failing parent
+    -- aborts the run and the next pass retries.
+    FOR r IN
+        SELECT parent_table, retention
+        FROM partman.part_config
+        WHERE parent_table LIKE 'telegraf.%'
+        ORDER BY parent_table
+    LOOP
+        v_default := format('%I.%I',
+                            split_part(r.parent_table, '.', 1),
+                            split_part(r.parent_table, '.', 2) || '_default');
+
+        CONTINUE WHEN to_regclass(v_default) IS NULL;
+
+        EXECUTE format('SELECT count(*) FROM %s', v_default) INTO v_rows;
+        CONTINUE WHEN v_rows = 0;
+
+        RAISE WARNING 'so_admin.telegraf_maintenance: % rows stranded in %, draining',
+                      v_rows, v_default;
+
+        -- Cheaper to delete expired rows than to repartition and then drop them.
+        IF r.retention IS NOT NULL THEN
+            EXECUTE format('DELETE FROM %s WHERE "time" < now() - %L::interval',
+                           v_default, r.retention);
+            COMMIT;
+        END IF;
+
+        -- Bounded so a large backlog drains across several runs.
+        CALL partman.partition_data_proc(
+            p_parent_table := r.parent_table,
+            p_loop_count   := 200,
+            p_source_table := v_default
+        );
+        COMMIT;
+    END LOOP;
+
+    CALL partman.run_maintenance_proc();
+END;
+$proc$;
+
+CREATE OR REPLACE FUNCTION so_admin.telegraf_partition_status()
+RETURNS TABLE (
+    parent_table  text,
+    oldest_child  date,
+    newest_child  date,
+    days_ahead    int,
+    retention     text,
+    default_rows  bigint,
+    default_size  text
+)
+LANGUAGE plpgsql
+AS $func$
+DECLARE
+    r          record;
+    v_default  regclass;
+BEGIN
+    FOR r IN
+        SELECT pc.parent_table AS pt, pc.retention AS ret
+        FROM partman.part_config pc
+        WHERE pc.parent_table LIKE 'telegraf.%'
+        ORDER BY pc.parent_table
+    LOOP
+        parent_table := r.pt;
+        retention    := r.ret;
+
+        SELECT min(d), max(d) INTO oldest_child, newest_child
+        FROM (
+            SELECT to_date(substring(c.relname FROM '_p(\d{8})$'), 'YYYYMMDD') AS d
+            FROM pg_inherits i
+            JOIN pg_class c ON c.oid = i.inhrelid
+            WHERE i.inhparent = r.pt::regclass
+              AND pg_get_expr(c.relpartbound, c.oid) <> 'DEFAULT'
+        ) s;
+
+        days_ahead := newest_child - current_date;
+
+        v_default := to_regclass(format('%I.%I',
+                                        split_part(r.pt, '.', 1),
+                                        split_part(r.pt, '.', 2) || '_default'));
+        IF v_default IS NULL THEN
+            default_rows := NULL;
+            default_size := NULL;
+        ELSE
+            EXECUTE format('SELECT count(*) FROM %s', v_default::text) INTO default_rows;
+            default_size := pg_size_pretty(pg_total_relation_size(v_default));
+        END IF;
+
+        RETURN NEXT;
+    END LOOP;
+END;
+$func$;
+
+-- Drop the registration older releases left in so_telegraf.
+SELECT CASE
+         WHEN current_setting('cron.database_name', true) IS DISTINCT FROM current_database()
+              AND EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_cron')
+         THEN 'true' ELSE 'false'
+       END AS drop_stale_cron \gset
+\if :drop_stale_cron
+DROP EXTENSION pg_cron CASCADE;
+\endif
+EOSQL
+
+    # Guarded on the live GUC so applying this before the postgresql.conf change
+    # has restarted the container skips rather than failing.
+    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d postgres <<'EOSQL'
+SELECT CASE WHEN current_setting('cron.database_name', true) = current_database()
+            THEN 'true' ELSE 'false' END AS cron_here \gset
+\if :cron_here
+CREATE EXTENSION IF NOT EXISTS pg_cron;
+-- cron.schedule_in_database is idempotent by jobname.
+SELECT cron.schedule_in_database(
   'telegraf-partman-maintenance',
   '17 * * * *',
-  'CALL partman.run_maintenance_proc()'
+  'CALL so_admin.telegraf_maintenance()',
+  'so_telegraf'
 );
+\else
+\echo 'pg_cron metadata database is not `postgres` yet; skipping job registration.'
+\endif
 EOSQL
     ;;
 
@@ -90,6 +225,8 @@ EOSQL
     : "${RETENTION_DAYS:?RETENTION_DAYS is required}"
     # \gset + \if guards against a missing pg_partman without using a DO
     # block (psql :var substitution doesn't reach into dollar-quoted code).
+    # premake is reconciled here because telegraf.conf only applies it to
+    # parents created from now on.
     docker exec -i so-postgres psql \
       -v ON_ERROR_STOP=1 \
       -v retention_days="$RETENTION_DAYS" \
@@ -97,14 +234,60 @@ EOSQL
 SELECT CASE WHEN EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman')
             THEN 'true' ELSE 'false' END AS has_partman \gset
 \if :has_partman
+-- infinite_time_partitions so a gap in metrics does not stop partman from
+-- premaking forward, which is what leaves everything in the default.
 UPDATE partman.part_config
 SET retention = :'retention_days' || ' days',
-    retention_keep_table = false
+    retention_keep_table = false,
+    premake = 7,
+    infinite_time_partitions = true
 WHERE parent_table LIKE 'telegraf.%';
 \endif
 EOSQL
     ;;
 
+  maintenance)
+    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
+SELECT CASE WHEN to_regproc('so_admin.telegraf_maintenance') IS NOT NULL
+            THEN 'true' ELSE 'false' END AS has_proc \gset
+\if :has_proc
+CALL so_admin.telegraf_maintenance();
+\else
+\echo 'so_admin.telegraf_maintenance() is missing; run so-telegraf-postgres group_role first.'
+\endif
+EOSQL
+    ;;
+
+  check)
+    docker exec -i so-postgres psql -U postgres -d so_telegraf <<'EOSQL'
+\pset border 2
+SELECT * FROM so_admin.telegraf_partition_status();
+EOSQL
+    docker exec -i so-postgres psql -U postgres -d postgres <<'EOSQL'
+\pset border 2
+SELECT CASE WHEN to_regclass('cron.job_run_details') IS NOT NULL
+            THEN 'true' ELSE 'false' END AS has_cron \gset
+\if :has_cron
+SELECT d.status, d.return_message, d.start_time
+FROM cron.job_run_details d
+JOIN cron.job j ON j.jobid = d.jobid
+WHERE j.jobname = 'telegraf-partman-maintenance'
+ORDER BY d.start_time DESC
+LIMIT 5;
+\else
+\echo 'pg_cron is not installed in this database.'
+\endif
+EOSQL
+    unhealthy=$(docker exec so-postgres psql -U postgres -d so_telegraf -tAc \
+      "SELECT count(*) FROM so_admin.telegraf_partition_status()
+       WHERE coalesce(default_rows, 0) > 0 OR coalesce(days_ahead, -1) < 1")
+    if [ "${unhealthy:-1}" != "0" ]; then
+      echo "so-telegraf-postgres check: $unhealthy telegraf parent(s) unhealthy" >&2
+      exit 1
+    fi
+    echo "so-telegraf-postgres check: all telegraf parents healthy"
+    ;;
+
   *)
     echo "Unknown subcommand: $cmd" >&2
     exit 1

salt/postgres/tools/sbin/so-telegraf-repair

@@ -0,0 +1,245 @@
+#!/bin/bash
+
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+# Put Telegraf metrics storage back in service on a grid where pg_partman
+# maintenance stalled: raises premake, discards the rows stranded in default
+# partitions, restarts so-postgres if pg_cron's launcher is dead, and runs
+# maintenance once. Healthy grids are reported and left alone.
+#
+# Usage: so-telegraf-repair [--check] [--yes] [--no-restart]
+#   --check       Report health and change nothing.
+#   --yes         Skip the confirmation prompt (for soup and other automation).
+#   --no-restart  Never restart so-postgres, even if pg_cron's launcher is dead.
+#
+# Exit status:
+#   0  healthy, or repair completed
+#   1  repair is needed (--check only)
+#   2  cannot run here: so-postgres, so_telegraf or pg_partman is missing
+
+set -e
+
+# Matches p_premake in telegraf.conf's create_parent template.
+PREMAKE=7
+JOB_NAME=telegraf-partman-maintenance
+
+CHECK_ONLY=false
+ASSUME_YES=false
+NO_RESTART=false
+
+usage() { sed -n '/^# Usage:/,/^#   2 /p' "$0" | sed 's/^# \?//'; }
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --check|--dry-run) CHECK_ONLY=true ;;
+    --yes|-y)          ASSUME_YES=true ;;
+    --no-restart)      NO_RESTART=true ;;
+    -h|--help)         usage; exit 0 ;;
+    *) echo "Unknown option: $1" >&2; usage >&2; exit 2 ;;
+  esac
+  shift
+done
+
+skip() { echo "$*"; exit 2; }
+
+psql_tg() { docker exec -i so-postgres psql -U postgres -d so_telegraf "$@"; }
+psql_pg() { docker exec -i so-postgres psql -U postgres -d postgres "$@"; }
+
+# query_to_xml so the per-table row counts need no helper function installed.
+REPORT="
+WITH parents AS (
+    SELECT pc.parent_table,
+           pc.premake,
+           split_part(pc.parent_table, '.', 1) AS sch,
+           split_part(pc.parent_table, '.', 2) AS tbl
+    FROM partman.part_config pc
+    WHERE pc.parent_table LIKE 'telegraf.%'
+), children AS (
+    SELECT p.parent_table,
+           max(to_date(substring(c.relname FROM '_p(\d{8})\$'), 'YYYYMMDD')) AS newest_child
+    FROM parents p
+    JOIN pg_class pt ON pt.oid = p.parent_table::regclass
+    JOIN pg_inherits i ON i.inhparent = pt.oid
+    JOIN pg_class c ON c.oid = i.inhrelid
+    WHERE pg_get_expr(c.relpartbound, c.oid) <> 'DEFAULT'
+    GROUP BY p.parent_table
+), defaults AS (
+    SELECT p.parent_table,
+           p.premake,
+           format('%I.%I', p.sch, p.tbl || '_default') AS default_table,
+           to_regclass(format('%I.%I', p.sch, p.tbl || '_default')) AS default_oid
+    FROM parents p
+)
+SELECT d.parent_table,
+       c.newest_child,
+       (c.newest_child - current_date) AS days_ahead,
+       d.premake,
+       CASE WHEN d.default_oid IS NULL THEN NULL ELSE
+            (xpath('/row/cnt/text()',
+                   query_to_xml(format('SELECT count(*) AS cnt FROM %s', d.default_table),
+                                false, true, '')))[1]::text::bigint
+       END AS default_rows,
+       CASE WHEN d.default_oid IS NULL THEN NULL
+            ELSE pg_size_pretty(pg_total_relation_size(d.default_oid)) END AS default_size
+FROM defaults d
+LEFT JOIN children c ON c.parent_table = d.parent_table
+ORDER BY 1
+"
+
+docker ps --format '{{.Names}}' | grep -qx so-postgres \
+  || skip "so-postgres is not running; nothing to repair."
+docker exec so-postgres psql -U postgres -tAc \
+  "SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1 \
+  || skip "The so_telegraf database does not exist; Telegraf is not writing to Postgres."
+psql_tg -tAc "SELECT 1 FROM pg_extension WHERE extname='pg_partman'" | grep -q 1 \
+  || skip "pg_partman is not installed in so_telegraf; nothing to repair."
+
+parents=$(psql_tg -tAc \
+  "SELECT count(*) FROM partman.part_config WHERE parent_table LIKE 'telegraf.%'")
+stranded=$(psql_tg -tAc "SELECT coalesce(sum(default_rows), 0) FROM ( $REPORT ) t")
+behind=$(psql_tg -tAc \
+  "SELECT count(*) FROM ( $REPORT ) t WHERE coalesce(days_ahead, -1) < 1")
+# premake < 7, or infinite_time_partitions off: without the latter partman
+# refuses to premake forward across the gap the stall left behind.
+misconfigured=$(psql_tg -tAc \
+  "SELECT count(*) FROM partman.part_config
+    WHERE parent_table LIKE 'telegraf.%'
+      AND (premake < $PREMAKE OR NOT infinite_time_partitions)")
+
+# Both columns are matched because which one carries the launcher's name varies
+# with the pg_cron version.
+launcher=$(psql_pg -tAc \
+  "SELECT count(*) FROM pg_stat_activity
+    WHERE backend_type ILIKE '%pg_cron%' OR application_name ILIKE '%pg_cron%'")
+
+# so_telegraf before the postgres state lands, postgres after.
+cron_db=$(docker exec so-postgres psql -U postgres -tAc \
+  "SELECT current_setting('cron.database_name', true)" | tr -d '[:space:]')
+last_run=never
+if [[ -n "$cron_db" ]]; then
+  last_run=$(docker exec so-postgres psql -U postgres -d "$cron_db" -tAc \
+    "SELECT coalesce(max(d.start_time)::text, 'never')
+       FROM cron.job_run_details d JOIN cron.job j USING (jobid)
+      WHERE j.jobname = '$JOB_NAME'" 2>/dev/null | tr -d '[:space:]' || echo unknown)
+  [[ -n "$last_run" ]] || last_run=never
+fi
+
+# A grid that has never written a metric has nothing to recover, and an empty
+# cron_db means pg_cron is not loaded at all, which no restart fixes.
+restart_needed=false
+[[ "$launcher" -eq 0 && "$parents" -gt 0 && -n "$cron_db" ]] && restart_needed=true
+
+repair_needed=false
+[[ "$stranded" -gt 0 ]] && repair_needed=true
+[[ "$behind" -gt 0 ]] && repair_needed=true
+[[ "$misconfigured" -gt 0 ]] && repair_needed=true
+$restart_needed && repair_needed=true
+
+echo "Telegraf partition status:"
+psql_tg -c "$REPORT"
+echo "Rows stranded in default partitions: $stranded"
+echo "pg_cron metadata database: ${cron_db:-unset}"
+echo "pg_cron launcher running: $([[ "$launcher" -gt 0 ]] && echo yes || echo no)"
+echo "Last $JOB_NAME run: $last_run"
+echo
+
+if ! $repair_needed; then
+  echo "Telegraf partitions are healthy. Nothing to do."
+  exit 0
+fi
+
+if $CHECK_ONLY; then
+  echo "Repair is needed:"
+  [[ "$stranded" -gt 0 ]]    && echo "  * $stranded row(s) stranded in default partitions"
+  [[ "$behind" -gt 0 ]]      && echo "  * $behind parent(s) with no partition for the current window"
+  [[ "$misconfigured" -gt 0 ]] && echo "  * $misconfigured parent(s) with stale partman settings"
+  $restart_needed            && echo "  * pg_cron's launcher is dead; maintenance is not running at all"
+  echo
+  echo "Re-run without --check to repair."
+  exit 1
+fi
+
+if [[ "$stranded" -gt 0 ]] && ! $ASSUME_YES; then
+  echo "This will permanently discard the $stranded stranded row(s) above."
+  $restart_needed && ! $NO_RESTART && \
+    echo "so-postgres will also be restarted, which briefly interrupts SOC."
+  [[ -t 0 ]] || { echo "Not a terminal; re-run with --yes to confirm." >&2; exit 2; }
+  read -r -p "Continue? [y/N] " answer
+  [[ "$answer" =~ ^[Yy]$ ]] || { echo "Aborted."; exit 0; }
+fi
+
+if [[ "$misconfigured" -gt 0 ]]; then
+  echo "Reconciling partman settings on $misconfigured parent(s)."
+  # GREATEST so an operator who raised premake further keeps their value.
+  psql_tg -v ON_ERROR_STOP=1 -c \
+    "UPDATE partman.part_config
+        SET premake = GREATEST(premake, $PREMAKE),
+            infinite_time_partitions = true
+      WHERE parent_table LIKE 'telegraf.%'"
+fi
+
+if [[ "$stranded" -gt 0 ]]; then
+  echo "Clearing default partitions."
+  # One transaction: Telegraf is still writing, so a default emptied without
+  # its partition in place is refilled before maintenance can attach one.
+  psql_tg -v ON_ERROR_STOP=1 <<'EOSQL'
+DO $$
+DECLARE
+    r record;
+BEGIN
+    FOR r IN
+        SELECT pc.parent_table,
+               format('%I.%I', n.nspname, c.relname) AS default_table
+        FROM partman.part_config pc
+        JOIN pg_class p ON p.oid = pc.parent_table::regclass
+        JOIN pg_inherits i ON i.inhparent = p.oid
+        JOIN pg_class c ON c.oid = i.inhrelid
+        JOIN pg_namespace n ON n.oid = c.relnamespace
+        WHERE pc.parent_table LIKE 'telegraf.%'
+          AND pg_get_expr(c.relpartbound, c.oid) = 'DEFAULT'
+    LOOP
+        EXECUTE format('TRUNCATE TABLE %s', r.default_table);
+        PERFORM partman.create_partition_time(
+            r.parent_table, ARRAY[date_trunc('day', now())]::timestamptz[]);
+    END LOOP;
+END
+$$;
+EOSQL
+fi
+
+if $restart_needed; then
+  if $NO_RESTART; then
+    echo "WARNING: pg_cron's launcher is dead and --no-restart was given."
+    echo "         Maintenance will not run on its own until so-postgres is restarted."
+  else
+    echo "Restarting so-postgres to revive pg_cron's launcher."
+    docker restart so-postgres >/dev/null
+    for _ in $(seq 1 60); do
+      docker exec so-postgres pg_isready -U postgres -q 2>/dev/null && break
+      sleep 2
+    done
+    docker exec so-postgres pg_isready -U postgres -q \
+      || { echo "so-postgres did not come back; check 'docker logs so-postgres'." >&2; exit 1; }
+  fi
+fi
+
+echo "Running partition maintenance."
+# so_admin.telegraf_maintenance() only exists once the postgres state has landed.
+psql_tg -v ON_ERROR_STOP=1 <<'EOSQL'
+SELECT CASE WHEN to_regproc('so_admin.telegraf_maintenance') IS NOT NULL
+            THEN 'true' ELSE 'false' END AS has_proc \gset
+\if :has_proc
+CALL so_admin.telegraf_maintenance();
+\else
+CALL partman.run_maintenance_proc();
+\endif
+EOSQL
+
+echo
+echo "Telegraf partition status after repair:"
+psql_tg -c "$REPORT"
+echo "The $JOB_NAME job runs hourly at :17. Confirm it fired with:"
+echo "  so-telegraf-repair --check"

salt/reactor/pillar_push_map.yaml

@@ -1,3 +1,6 @@
+# Read by push_pillar.sls (SOC config saves) and push_files.sls (local/salt file edits);
+# both key on the app name. An app missing here waits for the next scheduled highstate.
+#
 # One pillar directory can map to multiple (state, tgt) actions.
 # tgt is a raw salt compound expression. tgt_type is always "compound".
 # Per-action `batch` / `batch_wait` override the orch defaults (25% / 15s).
@@ -242,7 +245,7 @@ versionlock:
 # grain (compound supports nested grain matching via G@<key>:<subkey>:<value>).
 # pillar/vm/soc_vm.sls write path is referenced at salt/_runners/setup_hypervisor.py:856.
 vm:
-  - state: vm
+  - state: vm.user
     tgt: 'G@salt-cloud:driver:libvirt'
 
 # zeek: sensor_roles + so-import (5 roles).

salt/reactor/push_files.sls

@@ -0,0 +1,131 @@
+#!py
+
+# Reactor invoked by local_files_beacon when a watched directory under
+# /opt/so/saltstack/local/salt/ changes. The beacon tag is an app name in
+# pillar_push_map.yaml, so file changes and pillar changes route through the same
+# table -- see salt/reactor/push_pillar.sls.
+#
+# The app comes from the event tag, not the payload: salt's beacon loop pops the
+# beacon's 'tag' key off the data and appends it to the event tag instead (see
+# salt/beacons/__init__.py). The reactor renderer sets both `tag` and `data` as
+# module globals.
+#
+# Reactors never dispatch directly. The so-push-drainer schedule picks up ready
+# intents, dedupes across pending files, and dispatches orch.push_batch.
+
+import fcntl
+import json
+import logging
+import os
+import time
+
+from salt.client import Caller
+import yaml
+
+LOG = logging.getLogger(__name__)
+
+PENDING_DIR = '/opt/so/state/push_pending'
+LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
+MAX_PATHS = 20
+
+# The pillar_push_map.yaml is shipped via salt:// but the reactor runs on the
+# master, which mounts the default saltstack tree at this path.
+PUSH_MAP_PATH = '/opt/so/saltstack/default/salt/reactor/pillar_push_map.yaml'
+
+_PUSH_MAP_CACHE = {'mtime': 0, 'data': None}
+
+
+def _load_push_map():
+    try:
+        st = os.stat(PUSH_MAP_PATH)
+    except OSError:
+        LOG.warning('push_files: %s not found', PUSH_MAP_PATH)
+        return {}
+    if _PUSH_MAP_CACHE['mtime'] != st.st_mtime:
+        try:
+            with open(PUSH_MAP_PATH, 'r') as f:
+                _PUSH_MAP_CACHE['data'] = yaml.safe_load(f) or {}
+        except Exception:
+            LOG.exception('push_files: failed to load %s', PUSH_MAP_PATH)
+            _PUSH_MAP_CACHE['data'] = {}
+        _PUSH_MAP_CACHE['mtime'] = st.st_mtime
+    return _PUSH_MAP_CACHE['data'] or {}
+
+
+def _push_enabled():
+    try:
+        caller = Caller()
+        return bool(caller.cmd('pillar.get', 'salt:auto_apply:enabled', True))
+    except Exception:
+        LOG.exception('push_files: pillar.get salt:auto_apply:enabled failed, assuming enabled')
+        return True
+
+
+def _write_intent(key, actions, path):
+    now = time.time()
+    try:
+        os.makedirs(PENDING_DIR, exist_ok=True)
+    except OSError:
+        LOG.exception('push_files: cannot create %s', PENDING_DIR)
+        return
+
+    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
+    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
+    try:
+        fcntl.flock(lock_fd, fcntl.LOCK_EX)
+
+        intent = {}
+        if os.path.exists(intent_path):
+            try:
+                with open(intent_path, 'r') as f:
+                    intent = json.load(f)
+            except (IOError, ValueError):
+                intent = {}
+
+        intent.setdefault('first_touch', now)
+        intent['last_touch'] = now
+        intent['actions'] = actions
+        paths = intent.get('paths', [])
+        if path and path not in paths:
+            paths.append(path)
+            paths = paths[-MAX_PATHS:]
+        intent['paths'] = paths
+
+        tmp_path = intent_path + '.tmp'
+        with open(tmp_path, 'w') as f:
+            json.dump(intent, f)
+        os.rename(tmp_path, intent_path)
+    except Exception:
+        LOG.exception('push_files: failed to write intent %s', intent_path)
+    finally:
+        try:
+            fcntl.flock(lock_fd, fcntl.LOCK_UN)
+        finally:
+            os.close(lock_fd)
+
+
+def run():
+    if not _push_enabled():
+        LOG.info('push_files: push disabled, skipping')
+        return {}
+
+    event = data.get('data', data)  # noqa: F821 -- data provided by reactor
+    path = event.get('path', '')
+    app = tag.rsplit('/', 1)[-1].strip()  # noqa: F821 -- tag provided by reactor
+
+    if not app:
+        LOG.debug('push_files: ignoring event with no app segment: tag=%s', tag)  # noqa: F821
+        return {}
+
+    entry = _load_push_map().get(app)
+    if not entry:
+        LOG.warning(
+            'push_files: app "%s" is not in pillar_push_map.yaml; change will be '
+            'picked up at the next scheduled highstate (path=%s)',
+            app, path,
+        )
+        return {}
+
+    _write_intent('files_{}'.format(app), list(entry), path)
+    LOG.info('push_files: intent updated for %s (path=%s)', app, path)
+    return {}

salt/reactor/push_strelka.sls

@@ -1,96 +0,0 @@
-#!py
-
-# Reactor invoked by the rules_beacon poll beacon (salt/_beacons/rules_beacon.py) on rule
-# file changes under /opt/so/saltstack/local/salt/strelka/rules/compiled/.
-#
-# Writes (or updates) a push intent at /opt/so/state/push_pending/rules_strelka.json
-# and returns {}. The so-push-drainer schedule picks up ready intents, dedupes
-# across pending files, and dispatches orch.push_batch. Reactors never dispatch
-# directly
-
-import fcntl
-import json
-import logging
-import os
-import time
-
-from salt.client import Caller
-
-LOG = logging.getLogger(__name__)
-
-PENDING_DIR = '/opt/so/state/push_pending'
-LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
-MAX_PATHS = 20
-
-# Mirrors GLOBALS.sensor_roles in salt/vars/globals.map.jinja. Sensor-side
-# strelka runs on exactly these four roles; so-import gets strelka.manager
-# instead, which is not fired on pillar changes.
-SENSOR_ROLES = ['so-eval', 'so-heavynode', 'so-sensor', 'so-standalone']
-
-
-def _sensor_compound():
-    return ' or '.join('G@role:{}'.format(r) for r in SENSOR_ROLES)
-
-
-def _push_enabled():
-    try:
-        caller = Caller()
-        return bool(caller.cmd('pillar.get', 'salt:auto_apply:enabled', True))
-    except Exception:
-        LOG.exception('push_strelka: pillar.get salt:auto_apply:enabled failed, assuming enabled')
-        return True
-
-
-def _write_intent(key, actions, path):
-    now = time.time()
-    try:
-        os.makedirs(PENDING_DIR, exist_ok=True)
-    except OSError:
-        LOG.exception('push_strelka: cannot create %s', PENDING_DIR)
-        return
-
-    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
-    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
-    try:
-        fcntl.flock(lock_fd, fcntl.LOCK_EX)
-
-        intent = {}
-        if os.path.exists(intent_path):
-            try:
-                with open(intent_path, 'r') as f:
-                    intent = json.load(f)
-            except (IOError, ValueError):
-                intent = {}
-
-        intent.setdefault('first_touch', now)
-        intent['last_touch'] = now
-        intent['actions'] = actions
-        paths = intent.get('paths', [])
-        if path and path not in paths:
-            paths.append(path)
-            paths = paths[-MAX_PATHS:]
-        intent['paths'] = paths
-
-        tmp_path = intent_path + '.tmp'
-        with open(tmp_path, 'w') as f:
-            json.dump(intent, f)
-        os.rename(tmp_path, intent_path)
-    except Exception:
-        LOG.exception('push_strelka: failed to write intent %s', intent_path)
-    finally:
-        try:
-            fcntl.flock(lock_fd, fcntl.LOCK_UN)
-        finally:
-            os.close(lock_fd)
-
-
-def run():
-    if not _push_enabled():
-        LOG.info('push_strelka: push disabled, skipping')
-        return {}
-
-    path = data.get('path', '')  # noqa: F821 -- data provided by reactor
-    actions = [{'state': 'strelka', 'tgt': _sensor_compound()}]
-    _write_intent('rules_strelka', actions, path)
-    LOG.info('push_strelka: intent updated for path=%s', path)
-    return {}

salt/reactor/push_suricata.sls

@@ -1,95 +0,0 @@
-#!py
-
-# Reactor invoked by the rules_beacon poll beacon (salt/_beacons/rules_beacon.py) on rule
-# file changes under /opt/so/saltstack/local/salt/suricata/rules/.
-#
-# Writes (or updates) a push intent at /opt/so/state/push_pending/rules_suricata.json
-# and returns {}. The so-push-drainer schedule picks up ready intents, dedupes
-# across pending files, and dispatches orch.push_batch. Reactors never dispatch
-# directly
-
-import fcntl
-import json
-import logging
-import os
-import time
-
-from salt.client import Caller
-
-LOG = logging.getLogger(__name__)
-
-PENDING_DIR = '/opt/so/state/push_pending'
-LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
-MAX_PATHS = 20
-
-# Mirrors GLOBALS.sensor_roles in salt/vars/globals.map.jinja. Suricata also
-# runs on so-import per salt/top.sls, so that role is appended below.
-SENSOR_ROLES = ['so-eval', 'so-heavynode', 'so-sensor', 'so-standalone']
-
-
-def _sensor_compound_plus_import():
-    return ' or '.join('G@role:{}'.format(r) for r in SENSOR_ROLES) + ' or G@role:so-import'
-
-
-def _push_enabled():
-    try:
-        caller = Caller()
-        return bool(caller.cmd('pillar.get', 'salt:auto_apply:enabled', True))
-    except Exception:
-        LOG.exception('push_suricata: pillar.get salt:auto_apply:enabled failed, assuming enabled')
-        return True
-
-
-def _write_intent(key, actions, path):
-    now = time.time()
-    try:
-        os.makedirs(PENDING_DIR, exist_ok=True)
-    except OSError:
-        LOG.exception('push_suricata: cannot create %s', PENDING_DIR)
-        return
-
-    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
-    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
-    try:
-        fcntl.flock(lock_fd, fcntl.LOCK_EX)
-
-        intent = {}
-        if os.path.exists(intent_path):
-            try:
-                with open(intent_path, 'r') as f:
-                    intent = json.load(f)
-            except (IOError, ValueError):
-                intent = {}
-
-        intent.setdefault('first_touch', now)
-        intent['last_touch'] = now
-        intent['actions'] = actions
-        paths = intent.get('paths', [])
-        if path and path not in paths:
-            paths.append(path)
-            paths = paths[-MAX_PATHS:]
-        intent['paths'] = paths
-
-        tmp_path = intent_path + '.tmp'
-        with open(tmp_path, 'w') as f:
-            json.dump(intent, f)
-        os.rename(tmp_path, intent_path)
-    except Exception:
-        LOG.exception('push_suricata: failed to write intent %s', intent_path)
-    finally:
-        try:
-            fcntl.flock(lock_fd, fcntl.LOCK_UN)
-        finally:
-            os.close(lock_fd)
-
-
-def run():
-    if not _push_enabled():
-        LOG.info('push_suricata: push disabled, skipping')
-        return {}
-
-    path = data.get('path', '')  # noqa: F821 -- data provided by reactor
-    actions = [{'state': 'suricata', 'tgt': _sensor_compound_plus_import()}]
-    _write_intent('rules_suricata', actions, path)
-    LOG.info('push_suricata: intent updated for path=%s', path)
-    return {}

salt/redis/config.sls

@@ -50,16 +50,16 @@ redis_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 redis_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/repo/client/oracle.sls

@@ -60,6 +60,9 @@ so_repo:
   {% endif %}
     - enabled: 1
     - gpgcheck: 1
+  {% if not GLOBALS.is_manager %}
+    - sslverify: 0
+  {% endif %}
 
 # Only assign the kernel repo once this node's running salt matches the version this
 # SO release ships. During a soup the grid is mid-salt-upgrade; gating here keeps the
@@ -77,6 +80,9 @@ so_kernel_repo:
   {% endif %}
     - enabled: 1
     - gpgcheck: 1
+  {% if not GLOBALS.is_manager %}
+    - sslverify: 0
+  {% endif %}
     # Supplementary kernel repo: tolerate it being empty/unreachable (e.g. before the
     # manager has populated /nsm/kernelrepo) so a missing repomd.xml can't make every
     # dnf/pkg operation on the grid fail.

salt/salt/defaults.yaml

@@ -3,7 +3,7 @@ salt:
     enabled: true
     debounce_seconds: 30
     drain_interval: 15
-    batch: '25%'
+    batch: '10%'
     batch_wait: 15
   schedule:
-    highstate_interval_hours: 2
+    highstate_interval_minutes: 120

salt/salt/files/reactor_pushstate.conf

@@ -1,7 +1,5 @@
 reactor:
-  - 'salt/beacon/*/rules_beacon/suricata':
-    - salt://reactor/push_suricata.sls
-  - 'salt/beacon/*/rules_beacon/strelka':
-    - salt://reactor/push_strelka.sls
+  - 'salt/beacon/*/local_files_beacon/*':
+    - salt://reactor/push_files.sls
   - 'salt/beacon/*/postgres_pillar_beacon/audit_settings':
     - salt://reactor/push_pillar.sls

salt/salt/highstate_schedule.sls

@@ -1,11 +1,15 @@
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 {% from 'salt/schedule.map.jinja' import SCHEDULEMERGED %}
 
+{# splay a quarter of the interval, clamped to [5 min, 30 min], so short intervals
+   don't get jitter larger than the interval itself #}
+{% set SPLAY = [[(SCHEDULEMERGED.highstate_interval_minutes * 60 // 4) | int, 300] | max, 1800] | min %}
+
 highstate_schedule:
   schedule.present:
     - function: state.highstate
-    - hours: {{ SCHEDULEMERGED.highstate_interval_hours }}
+    - minutes: {{ SCHEDULEMERGED.highstate_interval_minutes }}
     - maxrunning: 1
 {% if not GLOBALS.is_manager %}
-    - splay: 1800
+    - splay: {{ SPLAY }}
 {% endif %}

salt/salt/init.sls

@@ -3,6 +3,8 @@ salt_bootstrap:
   file.managed:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: salt://salt/scripts/bootstrap-salt.sh
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 
@@ -10,6 +12,6 @@ salt_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://salt/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755

salt/salt/minion/boot_highstate.sls

@@ -3,6 +3,8 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
+{% from 'vars/globals.map.jinja' import GLOBALS %}
+
 # Manages /etc/systemd/system/so-boot-highstate.service, a Type=oneshot
 # RemainAfterExit=yes unit that runs `salt-call state.highstate` exactly once
 # per system boot. Replaces the legacy `startup_states: highstate` minion
@@ -19,9 +21,25 @@ so_boot_highstate_unit_file:
     - onchanges_in:
       - module: systemd_reload
 
+# Non-managers never apply salt.minion during setup, so reaching this state means
+# setup is finished and the marker is safe to write unconditionally. This also
+# heals nodes installed before this fix, which have no marker and no legacy
+# startup_states line to grep for. Managers do highstate mid-setup, so they only
+# get the marker from the legacy upgrade signal; fresh installs get it from
+# mark_setup_complete in setup/so-functions.
+mark_setup_complete:
+  file.managed:
+    - name: /opt/so/state/setup-complete
+    - replace: false
+    - makedirs: True
+{% if GLOBALS.is_manager %}
+    - onlyif: "grep -qx 'startup_states: highstate' /etc/salt/minion"
+{% endif %}
+    - require_in:
+      - service: so_boot_highstate_service
+
 # Only enable once setup is complete. Until then the gate file is missing and
-# the unit's own ConditionPathExists would no-op it anyway -- this just keeps
-# `systemctl is-enabled` honest for the sync_es_users gate.
+# the unit's own ConditionPathExists would no-op it anyway.
 so_boot_highstate_service:
   service.enabled:
     - name: so-boot-highstate.service

salt/salt/minion/init.sls

@@ -87,27 +87,15 @@ set_log_levels:
 # so-boot-highstate.service (managed in salt.minion.boot_highstate), which
 # runs once per system boot only. Strip the line from /etc/salt/minion on
 # upgrade; both the commented and uncommented forms historically existed.
+# Ordered after mark_setup_complete (salt.minion.boot_highstate); the manager
+# gate there greps for this line, so it must run before we delete it.
 remove_startup_states:
   file.line:
     - name: /etc/salt/minion
     - match: 'startup_states: highstate'
     - mode: delete
-
-# Upgrade-path bridge: systems that already passed setup under the old gate
-# (`grep -x 'startup_states: highstate' /etc/salt/minion`) get a /opt/so/state/setup-complete
-# marker so so-boot-highstate.service can be enabled and the so-user_sync cron
-# in sync_es_users.sls keeps installing. Setup-in-progress systems instead get
-# the marker from `mark_setup_complete` in setup/so-functions at the right
-# moment. `replace: false` means we never overwrite a marker once written.
-mark_setup_complete_for_upgrades:
-  file.managed:
-    - name: /opt/so/state/setup-complete
-    - replace: false
-    - makedirs: True
-    - onlyif: "grep -qx 'startup_states: highstate' /etc/salt/minion"
-    - require_in:
-      - file: remove_startup_states
-      - service: so_boot_highstate_service
+    - require:
+      - file: mark_setup_complete
 
 {% endif %}
 

salt/salt/soc_salt.yaml

@@ -31,9 +31,11 @@ salt:
       global: True
       advanced: True
   schedule:
-    highstate_interval_hours:
-      description: How often every minion in the grid runs a scheduled state.highstate, in hours. Lower values keep minions closer in sync at the cost of more load; higher values reduce load but increase worst-case latency for non-pushed changes. The salt-minion health check restarts a minion if its last highstate is older than this value plus one hour.
+    highstate_interval_minutes:
+      description: How often every minion in the grid runs a scheduled state.highstate, in minutes. Minimum 15 minutes. Lower values keep minions closer in sync at the cost of more load; higher values reduce load but increase worst-case latency for non-pushed changes. If Auto Apply is disabled, set this to the 15-minute minimum so changes are still picked up promptly. The salt-minion health check restarts a minion if its last state apply is older than this value plus one hour.
       forcedType: int
       helpLink: push
       global: True
       advanced: True
+      regex: '^(1[5-9]|[2-9][0-9]|[1-9][0-9]{2,4})$'
+      regexFailureMessage: The value must be an integer of at least 15 minutes (maximum 99999).

salt/sensor/init.sls

@@ -35,6 +35,8 @@ combine_bond_script:
   file.managed:
     - name: /usr/sbin/so-combine-bond
     - source: salt://sensor/tools/sbin_jinja/so-combine-bond
+    - user: root
+    - group: root
     - mode: 755
     - template: jinja
     - defaults:

salt/sensoroni/config.sls

@@ -64,8 +64,8 @@ sensoroni_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://sensoroni/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #sensoroni_sbin_jinja:

salt/sensoroni/files/analyzers/whoislookup/requirements.txt

@@ -1,2 +1,3 @@
-requests>=2.31.0
-whoisit>=2.7.0
+requests>=2.34.0
+whoisit>=4.0.5
+anyio>=4.15.1