Pin NIC names by MAC via udev (run-once) from the common state

Add so-nic-pin, which writes by-MAC persistent-net udev rules pinning each
physical NIC to its current name so a kernel upgrade can't renumber the
interfaces Security Onion binds by name (host:mainint, sensor:mainint, bond0).

Gated by the drop file /opt/so/state/nic_names_pinned: run-once on highstate,
and an admin can pre-create the marker to opt out. Wired into common/init.sls
as pin_nic_names, guarded by a matching unless.

salt/common/init.sls

@@ -130,6 +130,17 @@ common_sbin:
       - so-pcap-import
 {% endif %}
 
+# Pin physical NIC names by MAC (run-once) so a kernel upgrade can't renumber the
+# interfaces SO binds by name. The marker keeps it a one-time setup; an admin can
+# pre-create the marker to opt out.
+pin_nic_names:
+  cmd.run:
+    - name: /usr/sbin/so-nic-pin
+    - unless: 'test -e /opt/so/state/nic_names_pinned'
+    - require:
+      - file: common_sbin
+      - file: statedir
+
 common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin

salt/common/tools/sbin/so-nic-pin

@@ -0,0 +1,76 @@
+#!/bin/bash
+#
+# so-nic-pin — pin physical NIC names by permanent MAC via classic by-MAC udev
+#              rules, so a kernel upgrade can't renumber them.
+#
+# Security Onion binds its management and monitor interfaces BY NAME in pillar
+# (host:mainint, sensor:mainint, and bond0 is built on a specific physical NIC).
+# A kernel upgrade can change the kernel/systemd-udevd predictable-naming output
+# and renumber those NICs (e.g. enp1s0 -> enp2s0), which breaks the grid: the
+# pillar references a name that no longer exists and bond/bridge bring-up fails.
+#
+# This writes /etc/udev/rules.d/70-persistent-net.rules pinning each PHYSICAL NIC
+# to its CURRENT name by its PERMANENT MAC, freezing the names across future kernel
+# changes. It only writes the rules file; it does NOT live-trigger a rename (the
+# rules apply on the next boot/kernel, and a live rename would be disruptive).
+#
+# Run-once: gated by the drop file /opt/so/state/nic_names_pinned. If the marker is
+# present the script does nothing, so an admin can pre-create it to opt out. Invoked
+# from the common state on every highstate; the marker keeps it a one-time setup.
+
+NET_RULES_FILE="/etc/udev/rules.d/70-persistent-net.rules"
+MARKER="/opt/so/state/nic_names_pinned"
+
+log() { echo -e "[so-nic-pin] $*"; }
+
+# Echo "<name> <permanent-mac>" for every PHYSICAL NIC. A physical NIC is backed by a
+# real device (has device/driver), which excludes bond0/sobridge/docker0/veth*/lo whose
+# MACs are dynamic and must never be pinned. The PERMANENT MAC is used (ethtool -P, with
+# fallbacks), not the current one: an enslaved bond member's current MAC is rewritten to
+# the bond's, so matching on it would be wrong/ambiguous.
+physical_nics() {
+    local path n mac
+    for path in /sys/class/net/*; do
+        n="${path##*/}"
+        [ "$n" = "lo" ] && continue
+        [ -e "${path}/device/driver" ] || continue          # real device only
+        mac="$(ethtool -P "$n" 2>/dev/null | awk '/Permanent address/{print $NF}')"
+        case "$mac" in ""|00:00:00:00:00:00) mac="$(cat "${path}/bonding_slave/perm_hwaddr" 2>/dev/null)" ;; esac
+        case "$mac" in ""|00:00:00:00:00:00) mac="$(cat "${path}/address" 2>/dev/null)" ;; esac
+        case "$mac" in ""|00:00:00:00:00:00) continue ;; esac
+        echo "$n $mac"
+    done
+}
+
+# Turn "<name> <mac>" lines on stdin into classic by-MAC persistent-net udev rules.
+render_net_rules() {
+    echo "# Generated by so-nic-pin: pin NIC names by MAC so kernel upgrades can't renumber them."
+    echo "# Security Onion binds its management/monitor interfaces by name; do not hand-edit."
+    local n mac
+    while read -r n mac; do
+        [ -n "$n" ] || continue
+        printf 'SUBSYSTEM=="net", ACTION=="add", DRIVERS=="?*", ATTR{address}=="%s", NAME="%s"\n' \
+            "$mac" "$n"
+    done
+}
+
+[ "$(id -u)" -eq 0 ] || exit 0                   # salt runs us as root; bail quietly otherwise
+[ -e "${MARKER}" ] && exit 0                      # run-once guard (mirrors the state's unless)
+
+nics="$(physical_nics)"
+if [ -z "${nics}" ]; then
+    log "no physical NICs detected — nothing to pin (will retry on next highstate)"
+    exit 0                                         # do NOT drop the marker; let it retry later
+fi
+
+log "pinning physical NICs by permanent MAC:"
+echo "${nics}" | sed 's/^/    /'
+
+[ -f "${NET_RULES_FILE}" ] && cp -f "${NET_RULES_FILE}" "${NET_RULES_FILE}.bak"
+echo "${nics}" | render_net_rules > "${NET_RULES_FILE}" || {
+    log "ERROR: failed to write ${NET_RULES_FILE}"
+    exit 1
+}
+
+mkdir -p "$(dirname "${MARKER}")" && touch "${MARKER}"
+log "wrote ${NET_RULES_FILE} ($(grep -c '^SUBSYSTEM' "${NET_RULES_FILE}") NIC(s) pinned); dropped ${MARKER}"

salt/elasticfleet/enabled.sls

@@ -101,6 +101,17 @@ so-elastic-fleet:
       - file: trusttheca
       - x509: etc_elasticfleet_key
       - x509: etc_elasticfleet_crt
+
+wait_for_so-elastic-fleet:
+  http.wait_for_successful_query:
+    - name: "https://localhost:8220/api/status"
+    - ssl: True
+    - verify_ssl: False
+    - status: 200
+    - wait_for: 300
+    - request_interval: 15
+    - require:
+      - docker_container: so-elastic-fleet
 {%   endif %}
 
 delete_so-elastic-fleet_so-status.disabled:

salt/elasticfleet/manager.sls

@@ -9,16 +9,20 @@
 
 include:
   - elasticfleet.config
+  - kibana.enabled
 
 # If enabled, automatically update Fleet Logstash Outputs
-{% if ELASTICFLEETMERGED.config.server.enable_auto_configuration and grains.role not in ['so-import', 'so-eval'] %}
+{% if ELASTICFLEETMERGED.config.server.enable_auto_configuration %}
+{%   if grains.role not in ['so-import', 'so-eval']%}
 so-elastic-fleet-auto-configure-logstash-outputs:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-outputs-update
     - retry:
         attempts: 4
         interval: 30
-{% endif %}
+    - require:
+      - http: wait_for_so-kibana
+{%   endif %}
 
 # If enabled, automatically update Fleet Server URLs & ES Connection
 so-elastic-fleet-auto-configure-server-urls:
@@ -27,6 +31,9 @@ so-elastic-fleet-auto-configure-server-urls:
     - retry:
         attempts: 4
         interval: 30
+    - require:
+      - http: wait_for_so-kibana
+{% endif %}
 
 # Automatically update Fleet Server Elasticsearch URLs & Agent Artifact URLs
 so-elastic-fleet-auto-configure-elasticsearch-urls:
@@ -35,6 +42,8 @@ so-elastic-fleet-auto-configure-elasticsearch-urls:
     - retry:
         attempts: 4
         interval: 30
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-auto-configure-artifact-urls:
   cmd.run:
@@ -42,6 +51,8 @@ so-elastic-fleet-auto-configure-artifact-urls:
     - retry:
         attempts: 4
         interval: 30
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-package-statefile:
   file.managed:
@@ -53,7 +64,9 @@ so-elastic-fleet-package-upgrade:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - retry:
         attempts: 3
-        interval: 10
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
     - onchanges:
       - file: /opt/so/state/elastic_fleet_packages.txt
 
@@ -63,6 +76,8 @@ so-elastic-fleet-integrations:
     - retry:
         attempts: 3
         interval: 10
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-agent-grid-upgrade:
   cmd.run:
@@ -70,6 +85,8 @@ so-elastic-agent-grid-upgrade:
     - retry:
         attempts: 12
         interval: 5
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-integration-upgrade:
   cmd.run:
@@ -77,16 +94,22 @@ 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
 
 {% if ELASTICFLEETMERGED.config.defend_filters.enable_auto_configuration %}
 so-elastic-defend-manage-filters-file-watch:
   cmd.run:
     - name: python3 /sbin/so-elastic-defend-manage-filters.py -c /opt/so/conf/elasticsearch/curl.config -d /opt/so/conf/elastic-fleet/defend-exclusions/disabled-filters.yaml -i /nsm/securityonion-resources/event_filters/ -i /opt/so/conf/elastic-fleet/defend-exclusions/rulesets/custom-filters/ &>> /opt/so/log/elasticfleet/elastic-defend-manage-filters.log
+    - require:
+      - http: wait_for_so-kibana
     - onchanges:
       - file: elasticdefendcustom
       - file: elasticdefenddisabled

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

@@ -108,9 +108,12 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
   done
 
   # Only create the state file if all policies were created/updated successfully
-  if [[ "$RETURN_CODE" != "1" ]]; then
+  if [[ $RETURN_CODE -eq 0 ]]; then
     touch /opt/so/state/eaintegrations.txt
+  else
+    exit 1
   fi
 else
-  exit $RETURN_CODE
+  echo "Fleet integration policies already loaded."
+  exit 0
 fi

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

@@ -8,18 +8,33 @@
 
 . /usr/sbin/so-elastic-fleet-common
 
+PKG_LOAD_FAILURES=0
+PKG_LOAD_FAILURES_NAMES=()
+
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 echo "Upgrading {{ PACKAGE }} package..."
 if VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
     if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
-        # exit 1 on failure to upgrade a default package, allow salt to handle retries
+        PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
-        echo -e "\nERROR: Failed to upgrade $PACKAGE to version: $VERSION"
+        PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
-        exit 1
     fi
 else
-    echo -e "\nERROR: Failed to get version information for integration $PACKAGE"
+    PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+    PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
 fi
 echo
 {%- endfor %}
+
+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
+        echo " - $PKG"
+    done
+    # exit 1 on failure to upgrade a default package, allow salt to handle retries
+    exit 1
+else
+    echo "Successfully upgraded all packages."
+fi
+
 echo
 /usr/sbin/so-elasticsearch-templates-load

salt/elasticsearch/cluster.sls

@@ -9,9 +9,12 @@
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
 {%   from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS, SO_MANAGED_INDICES %}
 {%   if GLOBALS.role != 'so-heavynode' %}
-{%     from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS %}
+{%     from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS, ADDON_INDICES %}
 {%   endif %}
 
+include:
+  - elasticsearch.enabled
+
 escomponenttemplates:
   file.recurse:
     - name: /opt/so/conf/elasticsearch/templates/component
@@ -35,6 +38,20 @@ so_index_template_dir:
       {%- endfor %}
     {%- endif %}
 
+{%  if GLOBALS.role != "so-heavynode" %}
+# Clean up legacy and non-SO managed templates from the elasticsearch/templates/addon-index/ directory
+addon_index_template_dir:
+  file.directory:
+    - name: /opt/so/conf/elasticsearch/templates/addon-index
+    - clean: True
+    {%- if ADDON_INDICES %}
+    - require:
+      {%- for index in ADDON_INDICES %}
+      - file: addon_index_template_{{index}}
+      {%- endfor %}
+    {%- endif %}
+{%  endif %}
+
 # Auto-generate index templates for SO managed indices (directly defined in elasticsearch/defaults.yaml)
 #   These index templates are for the core SO datasets and are always required
 {%  for index, settings in ES_INDEX_SETTINGS.items() %}

salt/elasticsearch/template.map.jinja

@@ -61,15 +61,25 @@
 {% if ALL_ADDON_SETTINGS_ORIG.keys() | length > 0 %}
 {%   for index in ALL_ADDON_SETTINGS_ORIG.keys() %}
 {%     do ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES.update({index: salt['defaults.merge'](ALL_ADDON_SETTINGS_ORIG[index], PILLAR_GLOBAL_OVERRIDES, in_place=False)}) %}
+{#     Explicitly excluding addon indices from ES_INDEX_SETTINGS_ORIG
+         When manager.soc_managed_annotations runs, new entries are added to the salt/elasticsearch/defaults.yaml file to support 'revert to default' functionality.
+         Subsequent map renders will then incorrectly include 'integration X' in 'ES_INDEX_SETTINGS_ORIG' due to being in the defaults.yaml file. #}
+{%     if index in ES_INDEX_SETTINGS_ORIG.keys() %}
+{%       do ES_INDEX_SETTINGS_ORIG.pop(index) %}
+{%     endif %}
 {%   endfor %}
 {% endif %}
 
 {% set ES_INDEX_SETTINGS = {} %}
-{% macro create_final_index_template(DEFINED_SETTINGS, GLOBAL_OVERRIDES, FINAL_INDEX_SETTINGS) %}
+{% macro create_final_index_template(DEFINED_SETTINGS, GLOBAL_OVERRIDES, FINAL_INDEX_SETTINGS, EXCLUDE_INDICES=[]) %}
 
 {% do GLOBAL_OVERRIDES.update(salt['defaults.merge'](GLOBAL_OVERRIDES, ES_INDEX_PILLAR, in_place=False)) %}
 {% for index, settings in GLOBAL_OVERRIDES.items() %}
 
+{%   if index in EXCLUDE_INDICES %}
+{%     continue %}
+{%   endif %}
+
 {#   prevent this action from being performed on custom defined indices. #}
 {#   the custom defined index is not present in either of the dictionaries and fails to reder. #}
 {%   if index in DEFINED_SETTINGS and index in GLOBAL_OVERRIDES %}
@@ -150,10 +160,19 @@
 {% endfor %}
 {% endmacro %}
 
-{{ create_final_index_template(ES_INDEX_SETTINGS_ORIG, ES_INDEX_SETTINGS_GLOBAL_OVERRIDES, ES_INDEX_SETTINGS) }}
+{# Exclude addon integrations from final ES_INDEX_SETTINGS #}
-{{ create_final_index_template(ALL_ADDON_SETTINGS_ORIG, ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES, ALL_ADDON_SETTINGS) }}
+{{ create_final_index_template(ES_INDEX_SETTINGS_ORIG, ES_INDEX_SETTINGS_GLOBAL_OVERRIDES, ES_INDEX_SETTINGS, ALL_ADDON_SETTINGS_ORIG.keys() | list ) }}
+
+{# Exclude SO managed indices, otherwise ALL_ADDON_SETTINGS will include pillar values
+  of core integrations without merging defaults, resulting in an overlapping, but bad index template being generated. #}
+{{ create_final_index_template(ALL_ADDON_SETTINGS_ORIG, ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES, ALL_ADDON_SETTINGS, ES_INDEX_SETTINGS_ORIG.keys() | list ) }}
 
 {% set SO_MANAGED_INDICES = [] %}
 {% for index, settings in ES_INDEX_SETTINGS.items() %}
 {%   do SO_MANAGED_INDICES.append(index) %}
 {% endfor %}
+
+{% set ADDON_INDICES = [] %}
+{% for index, settings in ALL_ADDON_SETTINGS.items() %}
+{%   do ADDON_INDICES.append(index) %}
+{% endfor %}

salt/kibana/enabled.sls

@@ -6,6 +6,7 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
+{%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
 
 include:
@@ -60,6 +61,19 @@ so-kibana:
     - watch:
       - file: kibanaconfig
 
+wait_for_so-kibana:
+  http.wait_for_successful_query:
+    - name: "http://localhost:5601/api/status"
+    - username: 'so_elastic'
+    - password: '{{ ELASTICSEARCHMERGED.auth.users.so_elastic_user.pass }}'
+    - ssl: True
+    - verify_ssl: False
+    - status: 200
+    - wait_for: 300
+    - request_interval: 15
+    - require:
+      - docker_container: so-kibana
+
 delete_so-kibana_so-status.disabled:
   file.uncomment:
     - name: /opt/so/conf/so-status/so-status.conf

salt/manager/sync_es_users.sls

@@ -31,11 +31,13 @@ sync_es_users:
       - http: wait_for_kratos
       - file: so-user.lock # require so-user.lock file to be missing
 
-# we dont want this added too early in setup, so we add the onlyif to verify 'startup_states: highstate'
+# we dont want this added too early in setup, so the onlyif gates on the
-# is in the minion config. That line is added before the final highstate during setup
+# /opt/so/state/setup-complete marker. The marker is written by
+# mark_setup_complete in setup/so-functions just before the final setup
+# highstate (and by an upgrade-path state for systems set up under the old gate).
 so-user_sync:
   cron.present:
     - user: root
     - name: 'PATH=/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin:/root/bin /usr/sbin/so-user sync &>> /opt/so/log/soc/sync.log'
     - identifier: so-user_sync
-    - onlyif: "grep -x 'startup_states: highstate' /etc/salt/minion"
+    - onlyif: "test -e /opt/so/state/setup-complete"

salt/manager/tools/sbin/so-boot-mine-update

@@ -0,0 +1,117 @@
+#!/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.
+
+# Runs once per boot on managers (via so-boot-mine-update.service), before
+# so-boot-highstate.service. Waits for the responsive minion set to settle, pushes
+# mine.update, waits until every up minion has actually reported to the mine, then
+# warms the master's per-minion pillar cache so the mine-backed node pillars (node
+# IPs, ES/Redis/Logstash/hypervisor discovery -- some glob- and some pillar/grain-
+# targeted) are complete before the boot highstate renders them. Otherwise a node
+# that is up but not yet fully reported gets dropped from those pillars and torn
+# out of the configs they build (e.g. so-elasticsearch ExtraHosts -> container recreate).
+
+MAX_WAIT=${MINE_UPDATE_MAX_WAIT:-180}   # hard backstop only
+INTERVAL=10
+STABLE_CHECKS=3                          # up-count must hold steady this many polls
+elapsed=0
+prev=-1
+stable=0
+up=0
+
+# Wait for the *reachable* minion set to settle rather than for every accepted
+# key to report up: an operator may accept a minion's key and then intentionally
+# power off that host, so requiring up >= accepted would never be satisfied and
+# we'd always burn the full MAX_WAIT. Once the responsive count stops growing we
+# stop waiting and run mine.update against whoever is up.
+while [ "$elapsed" -lt "$MAX_WAIT" ]; do
+  up=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null \
+    | python3 -c 'import sys,json; print(len(json.load(sys.stdin)))' 2>/dev/null)
+  up=${up:-0}
+  if [ "$up" -gt 0 ] && [ "$up" -eq "$prev" ]; then
+    stable=$((stable + 1))
+    [ "$stable" -ge "$STABLE_CHECKS" ] && break
+  else
+    stable=0
+  fi
+  prev=$up
+  sleep "$INTERVAL"
+  elapsed=$((elapsed + INTERVAL))
+done
+
+echo "so-boot-mine-update: ${up} minions up (settled after ${elapsed}s); running mine.update"
+/usr/bin/salt '*' mine.update --out=txt
+
+# A node that is up but has not yet re-reported network.ip_addrs to the mine is
+# silently dropped from mine-backed pillars (elasticsearch:nodes, node_data, ...)
+# when highstate recompiles them -- which e.g. removes it from so-elasticsearch
+# ExtraHosts and forces a container recreate. After the broad mine.update above,
+# wait until every up minion actually has network.ip_addrs in the mine, re-pushing
+# mine.update to stragglers, before releasing the boot highstate. Bounded by the
+# same MAX_WAIT backstop so a slow/down node never blocks boot indefinitely.
+missing=""
+while [ "$elapsed" -lt "$MAX_WAIT" ]; do
+  up_json=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null)
+  mine_json=$(/usr/bin/salt-run mine.get '*' network.ip_addrs tgt_type=glob --out=json 2>/dev/null)
+  missing=$(printf '%s' "$up_json" | python3 -c '
+import sys, json
+up = set(json.load(sys.stdin) or [])
+mine = {k for k, v in (json.loads(sys.argv[1]) or {}).items() if v}
+print("\n".join(sorted(up - mine)))
+' "$mine_json" 2>/dev/null)
+  if [ -z "$missing" ]; then
+    echo "so-boot-mine-update: mine complete for all up minions after ${elapsed}s"
+    break
+  fi
+  echo "so-boot-mine-update: mine missing up minion(s): $(echo $missing); re-running mine.update"
+  for m in $missing; do /usr/bin/salt "$m" mine.update --out=txt; done
+  sleep "$INTERVAL"
+  elapsed=$((elapsed + INTERVAL))
+done
+[ -n "$missing" ] && echo "so-boot-mine-update: WARNING ${MAX_WAIT}s backstop hit; up minion(s) still absent from mine: $(echo $missing); highstate may drop them from configs"
+
+# The pillar/compound-targeted node pillars (elasticsearch:nodes, redis:nodes,
+# logstash:nodes, hypervisor:nodes) resolve their target against the master's
+# per-minion data cache (grains+pillar in .../minions/<id>/data.p), populated only
+# when a minion's pillar is (re)compiled -- separately from the mine. A freshly
+# booted node can be in the mine (glob/node_data sees it) yet absent from that
+# cache, so it is dropped from those pillars and from the configs they build (e.g.
+# so-elasticsearch ExtraHosts). Force a synchronous pillar refresh so the master
+# caches every up node's pillar; refresh_pillar wait=True returns only once the
+# pillar is recompiled (and thus cached for matching). Retry stragglers <= MAX_WAIT.
+echo "so-boot-mine-update: warming master pillar cache for pillar/grain-targeted node pillars"
+/usr/bin/salt '*' saltutil.refresh_pillar wait=True --out=txt
+missing=""
+while [ "$elapsed" -lt "$MAX_WAIT" ]; do
+  up_json=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null)
+  cached_json=$(/usr/bin/salt-run cache.pillar tgt='*' --out=json 2>/dev/null)
+  missing=$(printf '%s' "$up_json" | python3 -c '
+import sys, json
+up = set(json.load(sys.stdin) or [])
+cached = {k for k, v in (json.loads(sys.argv[1]) or {}).items() if v}
+print("\n".join(sorted(up - cached)))
+' "$cached_json" 2>/dev/null)
+  if [ -z "$missing" ]; then
+    echo "so-boot-mine-update: pillar cache warm for all up minions after ${elapsed}s"
+    break
+  fi
+  echo "so-boot-mine-update: pillar not yet cached for: $(echo $missing); refreshing"
+  for m in $missing; do /usr/bin/salt "$m" saltutil.refresh_pillar wait=True --out=txt; done
+  sleep "$INTERVAL"
+  elapsed=$((elapsed + INTERVAL))
+done
+[ -n "$missing" ] && echo "so-boot-mine-update: WARNING ${MAX_WAIT}s backstop hit; pillar not cached for: $(echo $missing); pillar-targeted pillars may drop them"
+
+# Log what the mine-backed pillars render so the boot-time state is inspectable.
+/usr/bin/salt-call saltutil.refresh_pillar >/dev/null 2>&1
+sleep 2
+for key in node_data elasticsearch:nodes; do
+  rendered=$(/usr/bin/salt-call --out=json pillar.get "$key" 2>/dev/null \
+    | python3 -c 'import sys,json; print(json.dumps(json.load(sys.stdin).get("local"), indent=2, sort_keys=True))' 2>/dev/null)
+  echo "so-boot-mine-update: ${key} rendered as:"
+  echo "${rendered:-null}"
+done
+exit 0

salt/salt/master.sls

@@ -14,6 +14,7 @@
 
 include:
   - salt.minion
+  - salt.master.boot_mine_update
 {%   if 'vrt' in salt['pillar.get']('features', []) %}
   - salt.cloud
   - salt.cloud.reactor_config_hypervisor

salt/salt/master/boot_mine_update.sls

@@ -0,0 +1,29 @@
+# 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.
+
+# Manages /etc/systemd/system/so-boot-mine-update.service, a manager-only
+# Type=oneshot unit that pushes `salt '*' mine.update` once per boot, ordered
+# before so-boot-highstate.service so mine-backed pillars (node IPs, ES/Redis/
+# Logstash discovery) are fresh before the boot highstate renders them.
+
+include:
+  - systemd.reload
+
+so_boot_mine_update_unit_file:
+  file.managed:
+    - name: /etc/systemd/system/so-boot-mine-update.service
+    - source: salt://salt/service/so-boot-mine-update.service
+    - onchanges_in:
+      - module: systemd_reload
+
+# Only enable once setup is complete. Until then the gate file is missing and
+# the unit's own ConditionPathExists would no-op it anyway.
+so_boot_mine_update_service:
+  service.enabled:
+    - name: so-boot-mine-update.service
+    - onlyif: test -e /opt/so/state/setup-complete
+    - require:
+      - file: so_boot_mine_update_unit_file
+      - module: systemd_reload

salt/salt/minion/boot_highstate.sls

@@ -0,0 +1,31 @@
+# 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.
+
+# 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
+# config, which fired on every salt-minion service restart (causing a redundant
+# highstate whenever a highstate itself restarted salt-minion).
+
+include:
+  - systemd.reload
+
+so_boot_highstate_unit_file:
+  file.managed:
+    - name: /etc/systemd/system/so-boot-highstate.service
+    - source: salt://salt/service/so-boot-highstate.service
+    - onchanges_in:
+      - module: systemd_reload
+
+# 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.
+so_boot_highstate_service:
+  service.enabled:
+    - name: so-boot-highstate.service
+    - onlyif: test -e /opt/so/state/setup-complete
+    - require:
+      - file: so_boot_highstate_unit_file
+      - module: systemd_reload

salt/salt/minion/init.sls

@@ -17,6 +17,7 @@ include:
   - repo.client
   - salt.mine_functions
   - salt.minion.service_file
+  - salt.minion.boot_highstate
 {% if GLOBALS.is_manager %}
   - ca.signing_policy
 {% endif %}
@@ -80,11 +81,33 @@ set_log_levels:
       - "log_level: info"
       - "log_level_logfile: info"
 
-enable_startup_states:
+# startup_states: highstate caused a full highstate to run on every
-  file.uncomment:
+# salt-minion service start, including the restart triggered when a highstate
+# itself modified the minion config (beacons, mine, unit file). Replaced by
+# 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.
+remove_startup_states:
+  file.line:
     - name: /etc/salt/minion
-    - regex: '^startup_states: highstate$'
+    - match: 'startup_states: highstate'
-    - unless: pgrep so-setup
+    - 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
 
 {% endif %}
 

salt/salt/service/so-boot-highstate.service

@@ -0,0 +1,14 @@
+[Unit]
+Description=Security Onion boot-time highstate (runs once per boot)
+After=salt-minion.service network-online.target docker.service
+Wants=network-online.target docker.service
+Requires=salt-minion.service
+ConditionPathExists=/opt/so/state/setup-complete
+
+[Service]
+Type=oneshot
+RemainAfterExit=yes
+ExecStart=/usr/bin/salt-call state.highstate -l info queue=True
+
+[Install]
+WantedBy=multi-user.target

salt/salt/service/so-boot-mine-update.service

@@ -0,0 +1,15 @@
+[Unit]
+Description=Security Onion boot-time grid mine.update (managers, runs once per boot before highstate)
+After=salt-master.service salt-minion.service network-online.target
+Wants=network-online.target
+Requires=salt-master.service salt-minion.service
+Before=so-boot-highstate.service
+ConditionPathExists=/opt/so/state/setup-complete
+
+[Service]
+Type=oneshot
+RemainAfterExit=yes
+ExecStart=/usr/sbin/so-boot-mine-update
+
+[Install]
+WantedBy=multi-user.target

salt/setup/virt/setSalt.sls

@@ -8,11 +8,6 @@ set_role_grain:
     - name: role
     - value: so-{{ grains.id.split("_") | last }}
 
-set_highstate:
-  file.append:
-    - name: /etc/salt/minion
-    - text: 'startup_states: highstate'
-
 enable_salt_minion:
   service.enabled:
     - name: salt-minion

setup/so-functions

@@ -539,16 +539,19 @@ configure_minion() {
 		"  x509_v2: true"\
 		"log_level: info"\
 		"log_level_logfile: info"\
-		"log_file: /opt/so/log/salt/minion"\
+		"log_file: /opt/so/log/salt/minion" >> "$minion_config"
-		"#startup_states: highstate" >> "$minion_config"
 
 }
 
-checkin_at_boot() {
+mark_setup_complete() {
-	local minion_config=/etc/salt/minion
+	# Writes the setup-complete marker. Salt's so-boot-highstate.service
+	# (boot-time oneshot) and the so-user_sync cron gate in
+	# salt/manager/sync_es_users.sls both key off this file.
+	local marker=/opt/so/state/setup-complete
 
-	info "Enabling checkin at boot"
+	info "Marking setup as complete"
-	sed -i 's/#startup_states: highstate/startup_states: highstate/' "$minion_config"
+	mkdir -p "$(dirname "$marker")"
+	touch "$marker"
 }
 
 check_requirements() {
@@ -977,6 +980,8 @@ docker_seed_registry() {
 		docker_seed_update_percent=25
 
 		update_docker_containers 'netinstall' '' 'docker_seed_update' '/dev/stdout' 2>&1 | tee -a "$setup_log"
+        # Use pipe exit status of 'update_docker_containers' for return code
+		return ${PIPESTATUS[0]}
 	fi
 }
 

setup/so-setup

@@ -769,7 +769,10 @@ if ! [[ -f $install_opt_file ]]; then
 		title "Applying the registry state"
 		logCmd "salt-call state.apply -l info registry"
 		title "Seeding the docker registry"
-		docker_seed_registry
+		if ! docker_seed_registry; then
+			error "Failed to seed the docker registry"
+			fail_setup
+		fi
 		title "Applying the manager state"
 		logCmd "salt-call state.apply -l info manager"
 		logCmd "salt-call state.apply influxdb -l info"
@@ -794,7 +797,7 @@ if ! [[ -f $install_opt_file ]]; then
 			error "Failed to run so-elastic-fleet-setup"
 			fail_setup
 		fi
-		checkin_at_boot
+		mark_setup_complete
 		set_initial_firewall_access
         initialize_elasticsearch_indices "so-case so-casehistory so-assistant-session so-assistant-chat"
 		# run a final highstate before enabling scheduled highstates.