Add cluster_health option to telegraf.conf

Enable cluster health monitoring in Telegraf configuration.

pillar/data/addtotab.sh

@@ -1,59 +0,0 @@
-#!/usr/bin/env bash
-
-# This script adds sensors/nodes/etc to the nodes tab
-default_salt_dir=/opt/so/saltstack/default
-local_salt_dir=/opt/so/saltstack/local
-TYPE=$1
-NAME=$2
-IPADDRESS=$3
-CPUS=$4
-GUID=$5
-MANINT=$6
-ROOTFS=$7
-NSM=$8
-MONINT=$9
-#NODETYPE=$10
-#HOTNAME=$11
-
-echo "Seeing if this host is already in here. If so delete it"
-if grep -q $NAME "$local_salt_dir/pillar/data/$TYPE.sls"; then
-  echo "Node Already Present - Let's re-add it"
-  awk -v blah="  $NAME:" 'BEGIN{ print_flag=1 }
-{
-    if( $0 ~ blah )
-    {
-       print_flag=0;
-       next
-    }
-    if( $0 ~ /^  [a-zA-Z0-9]+:$/ )
-    {
-        print_flag=1;
-    }
-    if ( print_flag == 1 )
-        print $0
-
-} ' $local_salt_dir/pillar/data/$TYPE.sls > $local_salt_dir/pillar/data/tmp.$TYPE.sls
-mv $local_salt_dir/pillar/data/tmp.$TYPE.sls $local_salt_dir/pillar/data/$TYPE.sls
-echo "Deleted $NAME from the tab. Now adding it in again with updated info"
-fi
-echo "  $NAME:" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    ip: $IPADDRESS" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    manint: $MANINT" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    totalcpus: $CPUS" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    guid: $GUID" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    rootfs: $ROOTFS" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    nsmfs: $NSM" >> $local_salt_dir/pillar/data/$TYPE.sls
-if [ $TYPE == 'sensorstab' ]; then
-  echo "    monint: bond0" >> $local_salt_dir/pillar/data/$TYPE.sls
-fi
-if [ $TYPE == 'evaltab' ] || [ $TYPE == 'standalonetab' ]; then
-  echo "    monint: bond0" >> $local_salt_dir/pillar/data/$TYPE.sls
-  if [ ! $10 ]; then
-    salt-call state.apply utility queue=True
-  fi
-fi
-if [ $TYPE == 'nodestab' ]; then
-  salt-call state.apply elasticsearch queue=True
-#  echo "    nodetype: $NODETYPE" >> $local_salt_dir/pillar/data/$TYPE.sls
-#  echo "    hotname: $HOTNAME" >> $local_salt_dir/pillar/data/$TYPE.sls
-fi

salt/allowed_states.map.jinja

@@ -37,8 +37,7 @@
     'elasticfleet',
     'elasticfleet.manager',
     'elasticsearch.cluster',
-    'elastic-fleet-package-registry',
-    'utility'
+    'elastic-fleet-package-registry'
 ] %}
 
 {% set sensor_states = [

salt/common/tools/sbin/so-common

@@ -291,6 +291,20 @@ download_and_verify() {
 	fi
 }
 
+# check if container with name is running and optionally stop it
+docker_check_running() {
+    # show running containers, only names
+    if docker ps --format '{{.Names}}' | grep -q "^so-${1}$"; then
+        if [[ "$2" == "--stop" ]]; then
+            docker stop "so-${1}"
+        fi
+
+        return 0
+    else
+        return 1
+    fi
+}
+
 elastic_license() {
 
 read -r -d '' message <<- EOM

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

@@ -0,0 +1,57 @@
+#!/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-kernel-upgrade — switch the boot default to the installed UEK8 (6.x) kernel.
+#
+# Security Onion is moving off the EL9 stock kernel / UEK7 (5.x) onto UEK8 (6.x).
+# Installing the kernel-uek-core package adds a UEK8 boot entry but does NOT make it the
+# default: kernel-install/grubby only auto-promote a new kernel within the running
+# kernel's flavor lineage, and we're crossing from a 5.x kernel to the new 6.x UEK flavor.
+# So even with UPDATEDEFAULT=yes and DEFAULTKERNEL=kernel-uek-core the box keeps booting
+# the old kernel. This tool finds the newest installed 6.x UEK kernel and makes it the
+# GRUB default via grubby so the next boot comes up on UEK8.
+#
+# Idempotent: if the UEK8 kernel is already the default it does nothing. It only sets the
+# boot default; it does NOT reboot — the admin reboots the node on their own schedule.
+
+log() { echo "[so-kernel-upgrade] $*"; }
+
+[ "$(id -u)" -eq 0 ] || { log "must run as root"; exit 1; }
+command -v grubby >/dev/null 2>&1 || { log "grubby not found"; exit 1; }
+
+# Newest installed UEK8 (6.x) kernel known to the bootloader. UEK8 vmlinuz paths look like
+# /boot/vmlinuz-6.12.0-203.76.7.5.el9uek.x86_64; the 5.x UEK7 and 5.14 RHCK won't match.
+target="$(grubby --info=ALL 2>/dev/null \
+    | sed -n 's/^kernel="\(.*\)"$/\1/p' \
+    | grep -E '/vmlinuz-6\.[0-9]+.*uek' \
+    | sort -V | tail -1)"
+
+if [ -z "$target" ]; then
+    log "no installed 6.x UEK (UEK8) kernel found — confirm the kernel repo is assigned and"
+    log "'dnf update' has installed kernel-uek-core. Nothing to do."
+    exit 0
+fi
+
+current="$(grubby --default-kernel 2>/dev/null)"
+if [ "$current" = "$target" ]; then
+    log "UEK8 kernel is already the boot default: $target"
+    exit 0
+fi
+
+log "current default kernel: ${current:-unknown}"
+log "switching boot default to UEK8 kernel: $target"
+grubby --set-default="$target" || { log "ERROR: grubby --set-default failed for $target"; exit 1; }
+
+# Verify the change actually took before claiming success.
+now="$(grubby --default-kernel 2>/dev/null)"
+if [ "$now" != "$target" ]; then
+    log "ERROR: default kernel is still '${now:-unknown}' after set-default"
+    exit 1
+fi
+
+log "boot default is now $target"
+log "REBOOT REQUIRED to start using the UEK8 kernel (currently running $(uname -r))."

salt/common/tools/sbin/so-restart

@@ -5,27 +5,41 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
-
-# Usage: so-restart  kibana | playbook 
-
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
+usage() {
+    echo "Usage: $0 <component> [args]"
+    echo ""
+    echo "Supported args:"
+    echo "  --force | -f          Force stop all Salt jobs before starting component."
+    echo ""
+    echo "Examples:"
+    echo "  $0 kibana             Restart Kibana"
+    echo "  $0 kibana --force     Force stop all Salt jobs before restarting Kibana"
+    exit 1
+}
 
-        echo $banner
-        printf "Restarting $1...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n"
-        echo $banner
-
-        if [ "$2" = "--force" ]; then
-                printf "\nForce-stopping all Salt jobs before proceeding\n\n"
-                salt-call saltutil.kill_all_jobs
-        fi
-
-        case $1 in
-                "elastic-fleet") docker stop so-elastic-fleet && docker rm so-elastic-fleet && salt-call state.apply elasticfleet queue=True;;
-                *)  docker stop so-$1 ; docker rm so-$1 ; salt-call state.apply $1 queue=True;;
-        esac
-else
-        echo -e "\nPlease provide an argument by running like so-restart $component, or by using the component-specific script.\nEx. so-restart logstash, or so-logstash-restart\n"
+if [[ $# -lt 1 ]]; then
+    usage
 fi
+
+#shellcheck disable=SC2154
+echo "$banner"
+printf "Restarting %s...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n" "$1"
+echo "$banner"
+if [[ "$2" = "--force" ]] || [[ "$2" = "-f" ]]; then
+    printf "\nForce-stopping all Salt jobs before proceeding\n\n"
+    salt-call saltutil.kill_all_jobs
+fi
+case $1 in
+    "elastic-fleet"|"elasticfleet")
+        docker_check_running "elastic-fleet" "--stop"
+        docker rm "so-elastic-fleet" 2> /dev/null
+        salt-call state.apply elasticfleet queue=True
+        ;;
+    *)
+        docker_check_running "$1" "--stop"
+        docker rm "so-${1}" 2> /dev/null
+        salt-call state.apply "$1" queue=True
+        ;;
+esac

salt/common/tools/sbin/so-start

@@ -5,27 +5,54 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
-
-# Usage: so-start  all | kibana | playbook 
-
+# shellcheck disable=SC1091
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
-	echo $banner
-	printf "Starting $1...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n"
-	echo $banner
+usage() {
+    echo "Usage: $0 <component> [args]"
+    echo ""
+    echo "Supported args:"
+    echo "  --force | -f          Force stop all Salt jobs before starting component."
+    echo ""
+    echo "Examples:"
+    echo "  $0 kibana             Start Kibana"
+    echo "  $0 kibana --force     Force stop all Salt jobs before starting Kibana"
+    exit 1
+}
 
-	if [ "$2" = "--force" ]; then
-   		printf "\nForce-stopping all Salt jobs before proceeding\n\n"
-   		salt-call saltutil.kill_all_jobs
-	fi
-
-	case $1 in
-   		"all") salt-call state.highstate queue=True;;
-   		"elastic-fleet") if docker ps | grep -q so-$1; then printf "\n$1 is already running!\n\n"; else docker rm so-$1 >/dev/null 2>&1 ; salt-call state.apply elasticfleet queue=True; fi ;; 
-   		*) if docker ps | grep -E -q '^so-$1$'; then printf "\n$1 is already running\n\n"; else docker rm so-$1 >/dev/null 2>&1 ; salt-call state.apply $1 queue=True; fi ;; 
-	esac
-else
-	echo -e "\nPlease provide an argument by running like so-start $component, or by using the component-specific script.\nEx. so-start logstash, or so-logstash-start\n"	
+if [[ $# -lt 1 ]]; then
+    usage
 fi
+
+#shellcheck disable=SC2154
+echo "$banner"
+printf "Starting %s...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n" "$1"
+echo "$banner"
+if [[ "$2" = "--force" ]] || [[ "$2" == "-f" ]]; then
+	printf "\nForce-stopping all Salt jobs before proceeding\n\n"
+	salt-call saltutil.kill_all_jobs
+fi
+
+case "$1" in
+    "all")
+        salt-call state.highstate queue=True
+        ;;
+   	"elastic-fleet"|"elasticfleet")
+        if docker_check_running "elastic-fleet"; then
+            printf "\nso-%s is already running!\n\n" "elastic-fleet"
+            /usr/sbin/so-status
+        else
+            docker rm "so-elastic-fleet" 2> /dev/null
+            salt-call state.apply elasticfleet queue=True
+        fi
+        ;;
+   	*)
+        if docker_check_running "$1"; then
+            printf "\nso-%s is already running\n\n" "$1"
+            /usr/sbin/so-status
+        else
+            docker rm "so-${1}" 2> /dev/null
+            salt-call state.apply "$1" queue=True
+        fi
+        ;;
+esac

salt/common/tools/sbin/so-stop

@@ -5,21 +5,33 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
-
-# Usage: so-stop kibana | playbook | thehive
-
+# shellcheck disable=SC1091
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
-	echo $banner
-	printf "Stopping $1...\n"
-	echo $banner
+usage() {
+    echo "Usage: $0 <component>"
+    echo ""
+    echo "Examples:"
+    echo "  $0 kibana             Stop Kibana"
+    exit 1
+}
 
-	case $1 in
-    		*) docker stop so-$1 ; docker rm so-$1 ;;
-	esac
-else
-	echo -e "\nPlease provide an argument by running like so-stop $component, or by using the component-specific script.\nEx. so-stop logstash, or so-logstash-stop\n"	
+if [[ $# -lt 1 ]]; then
+    usage
 fi
 
+
+#shellcheck disable=SC2154
+echo "$banner"
+printf "Stopping %s...\n" "$1"
+echo "$banner"
+case $1 in
+	"elasticfleet"|"elastic-fleet")
+        docker_check_running "elastic-fleet" "--stop"
+        docker rm "so-elastic-fleet" 2> /dev/null
+        ;;
+    *)
+        docker_check_running "$1" "--stop"
+        docker rm "so-${1}" 2> /dev/null
+    ;;
+esac

salt/common/tools/sbin_jinja/so-import-pcap

@@ -63,7 +63,8 @@ function status {
 function pcapinfo() {
   PCAP=$1
   ARGS=$2
-  docker run --rm -v "$PCAP:/input.pcap" --entrypoint capinfos {{ MANAGER }}:5000/{{ IMAGEREPO }}/so-pcaptools:{{ VERSION }} /input.pcap -ae $ARGS
+  docker run --rm -v "$PCAP:/input.pcap" --entrypoint capinfos {{ MANAGER }}:5000/{{ IMAGEREPO }}/so-pcaptools:{{ VERSION }} /input.pcap -ae $ARGS |\
+    sed 's/First packet/Earliest packet/g' | sed 's/Last packet/Latest packet/g'
 }
 
 function pcapfix() {

salt/elasticfleet/config.sls

@@ -173,7 +173,7 @@ eaoptionalintegrationsdir:
 
 {% for minion in node_data %}
 {% set role = node_data[minion]["role"] %}
-{% if role in [ "eval","fleet","heavynode","import","manager", "managerhype", "managersearch","standalone" ] %}
+{% if role in [ "eval","fleet","import","manager", "managerhype", "managersearch","standalone" ] %}
 {% set optional_integrations = ELASTICFLEETMERGED.optional_integrations %}
 {% set integration_keys = optional_integrations.keys() %}
 fleet_server_integrations_{{ minion }}:

salt/elasticfleet/manager.sls

@@ -67,8 +67,6 @@ so-elastic-fleet-package-upgrade:
         interval: 30
     - require:
       - http: wait_for_so-kibana
-    - onchanges:
-      - file: /opt/so/state/elastic_fleet_packages.txt
 
 so-elastic-fleet-integrations:
   cmd.run:

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

@@ -30,6 +30,94 @@ 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
 }
 
+# Max number of concurrent Fleet write jobs (create/update). Override via env if needed.
+MAX_FLEET_JOBS=${MAX_FLEET_JOBS:-10}
+
+# Block until fewer than MAX_FLEET_JOBS background jobs are running.
+elastic_fleet_throttle() {
+    while (( $(jobs -rp | wc -l) >= MAX_FLEET_JOBS )); do
+        wait -n || true
+    done
+}
+
+# Load every integration JSON in a directory into a single agent policy.
+# The agent policy is fetched ONCE (not per file), and the create/update writes
+# are dispatched as throttled background jobs.
+#   $1 AGENT_POLICY     - the agent policy id/name to load integrations into
+#   $2 DIR              - directory of integration *.json files
+#   $3 LABEL           - human-readable label for log output
+#   $4 SKIP_CREATE_NAME - (optional) integration name to skip when creating (still updated if present)
+# Returns 1 if the policy cannot be fetched or if any integration failed to create/update.
+elastic_fleet_load_integrations_dir() {
+    local AGENT_POLICY=$1
+    local DIR=$2
+    local LABEL=$3
+    local SKIP_CREATE_NAME=$4
+    local POLICY_JSON FAIL_FILE OUT_DIR INTEGRATION NAME ID i
+
+    FAIL_FILE=$(mktemp)
+    # Each job buffers its full output (header + API response) into its own file so the
+    # parent can print them grouped and in submission order after concurrent writes finish.
+    OUT_DIR=$(mktemp -d)
+    i=0
+
+    # Fetch the agent policy a single time; we look up integration ids locally below.
+    if ! POLICY_JSON=$(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'."
+        rm -f "$FAIL_FILE"
+        rm -rf "$OUT_DIR"
+        return 1
+    fi
+
+    for INTEGRATION in "$DIR"/*.json; do
+        [ -e "$INTEGRATION" ] || continue
+        NAME=$(jq -r .name "$INTEGRATION")
+        ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+
+        elastic_fleet_throttle
+        {
+            local RESP
+            if [ -n "$ID" ]; then
+                printf "\n\n%s - Updating integration %s\n" "$LABEL" "$NAME"
+                if ! RESP=$(elastic_fleet_integration_update "$ID" "@$INTEGRATION"); then
+                    flock 9; echo "update ${INTEGRATION##*/}" >&9
+                fi
+                printf '%s\n' "$RESP"
+            elif [ -n "$SKIP_CREATE_NAME" ] && [ "$NAME" == "$SKIP_CREATE_NAME" ]; then
+                printf "\n\n%s - Skipping creation of %s\n" "$LABEL" "$NAME"
+            else
+                printf "\n\n%s - Creating integration %s\n" "$LABEL" "$NAME"
+                if ! RESP=$(elastic_fleet_integration_create "@$INTEGRATION"); then
+                    flock 9; echo "create ${INTEGRATION##*/}" >&9
+                fi
+                printf '%s\n' "$RESP"
+            fi
+        } >"$OUT_DIR/$(printf '%03d' "$i")" 9>>"$FAIL_FILE" &
+        i=$((i+1))
+    done
+    wait || true
+
+    # Emit per-integration output grouped and in submission order (glob sorts numerically).
+    cat "$OUT_DIR"/* 2>/dev/null
+    rm -rf "$OUT_DIR"
+
+    local rc=0
+    if [ -s "$FAIL_FILE" ]; then
+        printf "\n%s: failed integrations:\n" "$LABEL"
+        cat "$FAIL_FILE"
+        rc=1
+    fi
+    rm -f "$FAIL_FILE"
+    return $rc
+}
+
 elastic_fleet_integration_check() {
 
     AGENT_POLICY=$1
@@ -46,7 +134,9 @@ elastic_fleet_integration_create() {
 
     JSON_STRING=$1
 
-    if ! fleet_api "package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
+    # --retry-all-errors so transient 409 conflicts (concurrent writes to the same agent
+    # policy) are retried; curl --retry alone does not retry 409.
+    if ! fleet_api "package_policies" --retry-all-errors -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
         return 1
     fi
 }
@@ -77,7 +167,9 @@ elastic_fleet_integration_update() {
 
     JSON_STRING=$2
 
-    if ! fleet_api "package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
+    # --retry-all-errors so transient 409 conflicts (concurrent writes to the same agent
+    # policy) are retried; curl --retry alone does not retry 409.
+    if ! fleet_api "package_policies/$UPDATE_ID" --retry-all-errors -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
         return 1
     fi
 }

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

@@ -9,102 +9,36 @@
 RETURN_CODE=0
 
 if [ ! -f /opt/so/state/eaintegrations.txt ]; then
-  # First, check for any package upgrades
-  /usr/sbin/so-elastic-fleet-package-upgrade
 
-  # Second, update Fleet Server policies
+  # update Fleet Server policies
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
 
-  # Third, configure Elastic Defend Integration seperately
+  # configure Elastic Defend Integration separately
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-defend
 
+  # Each group fetches its agent policy once and dispatches create/update writes concurrently.
+
   # Initial Endpoints
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/endpoints-initial/*.json; do
-    printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-    elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
-    if [ -n "$INTEGRATION_ID" ]; then
-      printf "\n\nIntegration $NAME exists - Updating integration\n"
-      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    else
-      printf "\n\nIntegration does not exist - Creating integration\n"
-      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    fi
-  done
+  elastic_fleet_load_integrations_dir "endpoints-initial" \
+    /opt/so/conf/elastic-fleet/integrations/endpoints-initial "Initial Endpoints Policy" || RETURN_CODE=1
 
   # Grid Nodes - General
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_general/*.json; do
-    printf "\n\nGrid Nodes Policy_General - Loading $INTEGRATION\n"
-    elastic_fleet_integration_check "so-grid-nodes_general" "$INTEGRATION"
-    if [ -n "$INTEGRATION_ID" ]; then
-      printf "\n\nIntegration $NAME exists - Updating integration\n"
-      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    else
-      printf "\n\nIntegration does not exist - Creating integration\n"
-      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    fi
-  done
+  elastic_fleet_load_integrations_dir "so-grid-nodes_general" \
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_general "Grid Nodes Policy_General" || RETURN_CODE=1
 
   # Grid Nodes - Heavy
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy/*.json; do
-    printf "\n\nGrid Nodes Policy_Heavy - Loading $INTEGRATION\n"
-    elastic_fleet_integration_check "so-grid-nodes_heavy" "$INTEGRATION"
-    if [ -n "$INTEGRATION_ID" ]; then
-      printf "\n\nIntegration $NAME exists - Updating integration\n"
-      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    else
-      printf "\n\nIntegration does not exist - Creating integration\n"
-      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    fi
-  done
+  elastic_fleet_load_integrations_dir "so-grid-nodes_heavy" \
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy "Grid Nodes Policy_Heavy" || RETURN_CODE=1
 
-  # Fleet Server - Optional integrations
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json; do
-    if ! [ "$INTEGRATION" == "/opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json" ]; then
-      FLEET_POLICY=`echo "$INTEGRATION"| cut -d'/' -f7`
-      printf "\n\nFleet Server Policy - Loading $INTEGRATION\n"
-      elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
-      if [ -n "$INTEGRATION_ID" ]; then
-        printf "\n\nIntegration $NAME exists - Updating integration\n"
-        if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-          echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-          RETURN_CODE=1
-          continue
-        fi
-      else
-        printf "\n\nIntegration does not exist - Creating integration\n"
-        if [ "$NAME" != "elasticsearch-logs" ]; then
-          if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-            echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-            RETURN_CODE=1
-            continue
-          fi
-        fi
-      fi
-    fi
+  # Fleet Server - Optional integrations (adds integration configuration to a given FleetServer_ policy)
+  for FLEET_DIR in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/; do
+    [ -d "$FLEET_DIR" ] || continue
+    INTEGRATIONS=("${FLEET_DIR%/}"/*.json)
+    [ -e "${INTEGRATIONS[0]}" ] || continue
+
+    FLEET_POLICY=$(basename "$FLEET_DIR")
+    elastic_fleet_load_integrations_dir "$FLEET_POLICY" \
+      "${FLEET_DIR%/}" "Fleet Server Policy" "elasticsearch-logs" || RETURN_CODE=1
   done
 
   # Only create the state file if all policies were created/updated successfully

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

@@ -23,73 +23,90 @@ if [ $? -ne 0 ]; then
 fi
 
 default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.last %} {% endif %}{% endfor %})
+# JSON array of the default packages, used by the jq filter below.
+default_packages_json=$(printf '%s\n' "${default_packages[@]}" | jq -R . | jq -s '.')
+
+# Output lock (serializes concurrent job output) and failure file (one marker line per
+# failed integration). Mirrors the pattern used by elastic_fleet_load_integrations_dir.
+OUTPUT_LOCK=$(mktemp)
+FAIL_FILE=$(mktemp)
+trap 'rm -f "$OUTPUT_LOCK" "$FAIL_FILE"' EXIT
+
+# Cache of package name -> latest available version, so the same package is only looked up
+# once instead of once per (policy, integration).
+declare -A LATEST_VERSION_CACHE
 
-ERROR=false
 for AGENT_POLICY in $agent_policies; do
-    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+    # Fetch the agent policy a single time; package name/version and integration id are all
+    # extracted locally below instead of re-fetching the same policy per integration.
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY"); then
         # this script upgrades default integration packages, exit 1 and let salt handle retrying
         exit 1
     fi
-    for INTEGRATION in $integrations; do
-        if ! [[ "$INTEGRATION" == "elastic-defend-endpoints" ]] && ! [[ "$INTEGRATION" == "fleet_server-"* ]]; then
-            # Get package name so we know what package to look for when checking the current and latest available version
-            if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+
+    # One jq pass emits name/package.name/package.version/id for every eligible integration.
+    # The endpoint/fleet_server skips and the default-package gate are applied here in jq.
+    # $defaults (not $def, a jq reserved keyword) holds the default package list.
+    while IFS=$'\t' read -r INTEGRATION PACKAGE_NAME PACKAGE_VERSION INTEGRATION_ID; do
+        [ -n "$INTEGRATION" ] || continue
+
+        # Look up the latest available version once per package, then memoize it.
+        if [[ -z "${LATEST_VERSION_CACHE[$PACKAGE_NAME]+set}" ]]; then
+            if ! AVAILABLE_VERSION=$(elastic_fleet_package_latest_version_check "$PACKAGE_NAME"); then
+                echo "Error: Failed getting latest version for $PACKAGE_NAME"
                 exit 1
             fi
-            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-            if [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
-            {%- endif %}
-                # Get currently installed version of package
-                attempt=0
-                max_attempts=3
-                while [ $attempt -lt $max_attempts ]; do
-                    if PACKAGE_VERSION=$(elastic_fleet_integration_policy_package_version "$AGENT_POLICY" "$INTEGRATION") && AVAILABLE_VERSION=$(elastic_fleet_package_latest_version_check "$PACKAGE_NAME"); then
-                        break
-                    fi
-                    attempt=$((attempt + 1))
-                done
-                if [ $attempt -eq $max_attempts ]; then
-                    echo "Error: Failed getting $PACKAGE_VERSION or $AVAILABLE_VERSION"
-                    exit 1
-                fi
-
-                # Get integration ID
-                if ! INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION"); then
-                    exit 1
-                fi
-
-                if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
-                    # Dry run of the upgrade
-                    echo ""
-                    echo "Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."
-                    echo "Upgrading $INTEGRATION..."
-                    echo "Starting dry run..."
-                    if ! DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID"); then
-                        exit 1
-                    fi
-                    DRYRUN_ERRORS=$(echo "$DRYRUN_OUTPUT" | jq .[].hasErrors)
-
-                    # If no errors with dry run, proceed with actual upgrade
-                    if [[ "$DRYRUN_ERRORS" == "false" ]]; then
-                        echo "No errors detected. Proceeding with upgrade..."
-                        if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
-                            echo "Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."
-                            ERROR=true
-                            continue
-                        fi
-                    else
-                        echo "Errors detected during dry run for $PACKAGE_NAME policy upgrade..."
-                        ERROR=true
-                        continue
-                    fi
-                fi
-            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-            fi
-            {%- endif %}
+            LATEST_VERSION_CACHE[$PACKAGE_NAME]=$AVAILABLE_VERSION
         fi
-    done
+        AVAILABLE_VERSION=${LATEST_VERSION_CACHE[$PACKAGE_NAME]}
+
+        if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
+            # Dry run, then (if clean) the actual upgrade, dispatched as a throttled background
+            # job. Each job builds its full log into one block, then flushes it under a single
+            # shared lock (OUTPUT_LOCK) so concurrent jobs never interleave on stdout; a failed
+            # job also appends a marker line to FAIL_FILE while holding that same lock.
+            elastic_fleet_throttle
+            {
+                block=$'\n'"Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."$'\n'
+                block+="Upgrading $INTEGRATION..."$'\n'"Starting dry run..."$'\n'
+                fail=""
+                if ! DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID"); then
+                    block+="Error: Failed to complete dry run for '$INTEGRATION_ID'."$'\n'
+                    fail="dryrun $INTEGRATION"
+                elif [[ "$(jq .[].hasErrors <<<"$DRYRUN_OUTPUT")" == "false" ]]; then
+                    block+="No errors detected. Proceeding with upgrade..."$'\n'
+                    if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
+                        block+="Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."$'\n'
+                        fail="upgrade $INTEGRATION"
+                    fi
+                else
+                    block+="Errors detected during dry run for $PACKAGE_NAME policy upgrade..."$'\n'
+                    fail="dryrun-errors $INTEGRATION"
+                fi
+                {
+                    flock 9
+                    printf '%s' "$block"
+                    [ -n "$fail" ] && printf '%s\n' "$fail" >>"$FAIL_FILE"
+                } 9>>"$OUTPUT_LOCK"
+            } &
+        fi
+    done < <(jq -r --argjson defaults "$default_packages_json" '
+        .item.package_policies[]
+        | select(.name != "elastic-defend-endpoints")
+        | select(.name | startswith("fleet_server-") | not)
+        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
+        | select(.package.name | IN($defaults[]))
+        {%- endif %}
+        | [.name, .package.name, .package.version, .id] | @tsv
+    ' <<<"$POLICY_JSON")
 done
-if [[ "$ERROR" == "true" ]]; then
+
+# Barrier: wait for every dispatched dry-run/upgrade job to finish.
+wait
+
+if [ -s "$FAIL_FILE" ]; then
+    printf '\nFailed integration upgrades:\n'
+    cat "$FAIL_FILE"
     exit 1
 fi
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-optional-integrations-load

@@ -16,7 +16,6 @@
 STATE_FILE_SUCCESS=/opt/so/state/estemplates.txt
 INSTALLED_PACKAGE_LIST=/tmp/esfleet_installed_packages.json
 BULK_INSTALL_PACKAGE_LIST=/tmp/esfleet_bulk_install.json
-BULK_INSTALL_PACKAGE_TMP=/tmp/esfleet_bulk_install_tmp.json
 BULK_INSTALL_OUTPUT=/opt/so/state/esfleet_bulk_install_results.json
 INTEGRATION_PACKAGE_COMPONENTS=/opt/so/state/esfleet_package_components.json
 INPUT_PACKAGE_COMPONENTS=/opt/so/state/esfleet_input_package_components.json
@@ -29,29 +28,6 @@ PENDING_UPDATE=false
 #   Requiring some level of manual Elastic Stack configuration before installation
 EXCLUDED_INTEGRATIONS=('apm')
 
-version_conversion(){
-    version=$1
-    echo "$version" | awk -F '.' '{ printf("%d%03d%03d\n", $1, $2, $3); }'
-}
-
-compare_versions() {
-    version1=$1
-    version2=$2
-
-    # Convert versions to numbers
-    num1=$(version_conversion "$version1")
-    num2=$(version_conversion "$version2")
-
-    # Compare using bc
-    if (( $(echo "$num1 < $num2" | bc -l) )); then
-        echo "less"
-    elif (( $(echo "$num1 > $num2" | bc -l) )); then
-        echo "greater"
-    else
-        echo "equal"
-    fi
-}
-
 IFS=$'\n'
 agent_policies=$(elastic_fleet_agent_policy_ids)
 if [ $? -ne 0 ]; then
@@ -63,23 +39,23 @@ default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.l
 
 in_use_integrations=()
 
+# Fetch each agent policy once; its package_policies[] already contain both the integration name
+#  and the .package.name, so extract all non-default package names locally in a single jq instead
+#  of re-fetching the same policy per integration.
+default_packages_json=$(printf '%s\n' "${default_packages[@]}" | jq -R . | jq -s '.')
 for AGENT_POLICY in $agent_policies; do
 
-    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+    if ! policy_json=$(fleet_api "agent_policies/$AGENT_POLICY"); then
         # skip the agent policy if we can't get required info, let salt retry. Integrations loaded by this script are non-default integrations.
         echo "Skipping $AGENT_POLICY.. "
         continue
     fi
-    for INTEGRATION in $integrations; do
-        if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
-            echo  "Not adding $INTEGRATION, couldn't get package name"
-            continue
-        fi
-        # non-default integrations that are in-use in any policy
-        if ! [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
-            in_use_integrations+=("$PACKAGE_NAME")
-        fi
-    done
+    # non-default integrations that are in-use in any policy
+    while IFS= read -r PACKAGE_NAME; do
+        [ -n "$PACKAGE_NAME" ] && in_use_integrations+=("$PACKAGE_NAME")
+    done < <(jq -r --argjson defaults "$default_packages_json" \
+        '.item.package_policies[].package.name | select(. as $n | ($defaults | index($n)) | not)' \
+        <<<"$policy_json")
 done
 
 if [[ -f $STATE_FILE_SUCCESS  ]]; then
@@ -90,72 +66,55 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
         rm -f $INSTALLED_PACKAGE_LIST
         echo $latest_package_list | jq '{packages: [.items[] | {name: .name, latest_version: .version, installed_version: .installationInfo.version, subscription: .conditions.elastic.subscription }]}' >> $INSTALLED_PACKAGE_LIST
 
-        while read -r package; do
-            # get package details
-            package_name=$(echo "$package" | jq -r '.name')
-            latest_version=$(echo "$package" | jq -r '.latest_version')
-            installed_version=$(echo "$package" | jq -r '.installed_version')
-            subscription=$(echo "$package" | jq -r '.subscription')
-            bulk_package=$(echo "$package" | jq '{name: .name, version: .latest_version}' )
+        # Build the bulk install list and the per-package status messages with two jq passes
+        #  instead of a per-package bash loop. The old loop forked ~10 processes per package
+        #  (5 jq + awk/bc for the version compare) and re-parsed/rewrote a growing JSON file on
+        #  every add (O(n^2)). Selection and messages below are identical to that logic.
+        SUB={% if SUB %}true{% else %}false{% endif %}
+        AUTOUP={% if AUTO_UPGRADE_INTEGRATIONS %}true{% else %}false{% endif %}
+        EXCLUDED_JSON=$(printf '%s\n' "${EXCLUDED_INTEGRATIONS[@]}" | jq -R 'select(length>0)' | jq -s '.')
+        INUSE_JSON=$(printf '%s\n' "${in_use_integrations[@]}" | jq -R 'select(length>0)' | jq -s 'unique')
 
-            if [[ ! "${EXCLUDED_INTEGRATIONS[@]}" =~ "$package_name" ]]; then
-            {% if not SUB %}
-                if [[ "$subscription" != "basic" && "$subscription" != "null" && -n "$subscription" ]]; then
-                    # pass over integrations that require non-basic elastic license
-                    echo "$package_name integration requires an Elastic license of $subscription or greater... skipping"
-                    continue
-                else
-                    if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
-                        echo "$package_name is not installed... Adding to next update."
-                        jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+        # vnum replicates the previous version_conversion (%d%03d%03d of the first three dotted
+        #  fields); needs() replicates the excluded/subscription/installed/upgrade/in-use logic.
+        JQ_DECISION='
+def vnum:
+  [ (split(".")|.[0:3][] | gsub("[^0-9].*";"") | (if .=="" then "0" else . end) | tonumber) ]
+  | (.[0]//0)*1000000 + (.[1]//0)*1000 + (.[2]//0);
+def needs($sub;$autoup;$excluded;$inuse):
+  .name as $n
+  | ($n | IN($excluded[]) | not)
+  and ( $sub or (.subscription==null or .subscription=="basic" or .subscription=="") )
+  and ( (.installed_version==null or .installed_version=="")
+        or ( ((.latest_version|vnum) > (.installed_version|vnum))
+             and ( $autoup or ($n | IN($inuse[]) | not) ) ) );'
 
-                        PENDING_UPDATE=true
-                    else
-                        results=$(compare_versions "$latest_version" "$installed_version")
-                        if [ $results == "greater" ]; then
-                            {#- When auto_upgrade_integrations is false, skip upgrading in_use_integrations  #}
-                            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                            if ! [[ " ${in_use_integrations[@]} " =~ " $package_name " ]]; then
-                            {%- endif %}
-                                echo "$package_name is at version $installed_version latest version is $latest_version... Adding to next update."
-                                jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+        JQ_ARGS=(--argjson sub "$SUB" --argjson autoup "$AUTOUP" --argjson excluded "$EXCLUDED_JSON" --argjson inuse "$INUSE_JSON")
 
-                                PENDING_UPDATE=true
-                            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                            else
-                                echo "skipping available upgrade for in use integration - $package_name."
-                            fi
-                            {%- endif %}
-                        fi
-                    fi
-                fi
-            {% else %}
-                if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
-                    echo "$package_name is not installed... Adding to next update."
-                    jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
-                    PENDING_UPDATE=true
-                else
-                    results=$(compare_versions "$latest_version" "$installed_version")
-                    if [ $results == "greater" ]; then
-                        {#- When auto_upgrade_integrations is false, skip upgrading in_use_integrations  #}
-                        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                        if ! [[ " ${in_use_integrations[@]} " =~ " $package_name " ]]; then
-                        {%- endif %}
-                            echo "$package_name is at version $installed_version latest version is $latest_version... Adding to next update."
-                            jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
-                            PENDING_UPDATE=true
-                        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                        else
-                            echo "skipping available upgrade for in use integration - $package_name."
-                        fi
-                        {%- endif %}
-                    fi
-                fi
-            {% endif %}
-            else
-                echo "Skipping $package_name..."
-            fi
-        done <<< "$(jq -c '.packages[]' "$INSTALLED_PACKAGE_LIST")"
+        # (a) Per-package status messages (parity with the previous echo output).
+        jq -r "${JQ_ARGS[@]}" "$JQ_DECISION"'
+          .packages[]
+          | .name as $n
+          | if ($n|IN($excluded[])) then "Skipping \($n)..."
+            elif (($sub|not) and (.subscription!=null and .subscription!="basic" and .subscription!="")) then
+                 "\($n) integration requires an Elastic license of \(.subscription) or greater... skipping"
+            elif (.installed_version==null or .installed_version=="") then
+                 "\($n) is not installed... Adding to next update."
+            elif ((.latest_version|vnum) > (.installed_version|vnum)) then
+                 (if ($autoup or ($n|IN($inuse[])|not))
+                  then "\($n) is at version \(.installed_version) latest version is \(.latest_version)... Adding to next update."
+                  else "skipping available upgrade for in use integration - \($n)." end)
+            else empty end
+        ' "$INSTALLED_PACKAGE_LIST"
+
+        # (b) The bulk install list, built in a single pass.
+        jq "${JQ_ARGS[@]}" "$JQ_DECISION"'
+          {packages: [ .packages[] | select(needs($sub;$autoup;$excluded;$inuse)) | {name, version: .latest_version} ]}
+        ' "$INSTALLED_PACKAGE_LIST" > "$BULK_INSTALL_PACKAGE_LIST"
+
+        if jq -e '.packages | length > 0' "$BULK_INSTALL_PACKAGE_LIST" >/dev/null; then
+            PENDING_UPDATE=true
+        fi
 
         if [ "$PENDING_UPDATE" = true ]; then
             # Run chunked install of packages

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

@@ -12,17 +12,22 @@ 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
-        PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
-        PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+
+    if [ "$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 $LATEST_VERSION..."
+        if ! elastic_fleet_package_install "{{ PACKAGE }}" "$LATEST_VERSION"; then
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        fi
     fi
 else
+    echo "ERROR: Failed to get version information for integration {{ PACKAGE }}"
     PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
     PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
 fi
-echo
 {%- endfor %}
 
 if [ $PKG_LOAD_FAILURES -gt 0 ]; then
@@ -35,6 +40,3 @@ if [ $PKG_LOAD_FAILURES -gt 0 ]; then
 else
     echo "Successfully upgraded all packages."
 fi
-
-echo
-/usr/sbin/so-elasticsearch-templates-load

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

@@ -181,6 +181,9 @@ if ! elastic_fleet_policy_create "so-grid-nodes_heavy" "SO Grid Nodes - Heavy No
     exit 1
 fi
 
+# Check for package upgrades
+so-elastic-fleet-package-upgrade
+
 # Load Integrations for default policies
 so-elastic-fleet-integration-policy-load
 

salt/elasticsearch/files/ingest/zeek.ssl

@@ -5,6 +5,7 @@
     { "remove":   { "field": ["host"],     "ignore_failure": true } },
     { "json":             { "field": "message",                 "target_field": "message2",             "ignore_failure": true  } },
     { "rename":         { "field": "message2.version",          "target_field": "ssl.version",          "ignore_missing": true  } },
+    { "set":      { "description": "Set transport for the community_id processor", "if": "ctx.ssl?.version == null || !ctx.ssl.version.startsWith('DTLS')", "field": "network.transport", "value": "tcp", "ignore_failure": true } },
     { "rename":         { "field": "message2.cipher",           "target_field": "ssl.cipher",           "ignore_missing": true  } },
     { "rename":         { "field": "message2.curve",            "target_field": "ssl.curve",            "ignore_missing": true  } },
     { "rename":         { "field": "message2.server_name",      "target_field": "ssl.server_name",              "ignore_missing": true  } },

salt/elasticsearch/tools/sbin/so-elasticsearch-templates-load

@@ -11,10 +11,8 @@ ADDON_STATEFILE_SUCCESS=/opt/so/state/addon_estemplates.txt
 ELASTICSEARCH_TEMPLATES_DIR="/opt/so/conf/elasticsearch/templates"
 SO_TEMPLATES_DIR="${ELASTICSEARCH_TEMPLATES_DIR}/index"
 ADDON_TEMPLATES_DIR="${ELASTICSEARCH_TEMPLATES_DIR}/addon-index"
-SO_LOAD_FAILURES=0
-ADDON_LOAD_FAILURES=0
-SO_LOAD_FAILURES_NAMES=()
-ADDON_LOAD_FAILURES_NAMES=()
+FAILED_NAMES=()
+FAILED_COUNT=0
 IS_HEAVYNODE="false"
 FORCE="false"
 VERBOSE="false"
@@ -46,20 +44,86 @@ while [[ $# -gt 0 ]]; do
     shift
 done
 
+# Max number of concurrent template PUT jobs. Override via env if needed.
+MAX_TEMPLATE_JOBS=${MAX_TEMPLATE_JOBS:-10}
+
+# Block until fewer than MAX_TEMPLATE_JOBS background jobs are running.
+template_throttle() {
+    while (( $(jobs -rp | wc -l) >= MAX_TEMPLATE_JOBS )); do
+        wait -n
+    done
+}
+
+# Per-job failure markers and an output lock for serializing parallel job output.
+# Each failed load drops one file (named after the template) into FAIL_DIR; the
+# output of each job is flushed as a single block under flock so concurrent jobs
+# never interleave their (chatty) retry output.
+FAIL_DIR=$(mktemp -d)
+OUTPUT_LOCK="${FAIL_DIR}/.output.lock"
+: > "$OUTPUT_LOCK"
+trap 'rm -rf "$FAIL_DIR"' EXIT
+
+# Record a failure: $1 = the template name/path to report later. Slashes are
+# encoded so the path becomes a safe single filename.
+record_failure() {
+    local marker="${1//\//__}"
+    : > "${FAIL_DIR}/fail.${marker}"
+}
+
+# Populate FAILED_NAMES and FAILED_COUNT from the current phase's markers.
+# Must run in the current shell (not a command substitution) so the array sticks.
+collect_failures() {
+    FAILED_NAMES=()
+    FAILED_COUNT=0
+    local f name
+    shopt -s nullglob
+    for f in "${FAIL_DIR}"/fail.*; do
+        name="${f##*/fail.}"
+        name="${name//__//}"
+        FAILED_NAMES+=("$name")
+        FAILED_COUNT=$((FAILED_COUNT + 1))
+    done
+    shopt -u nullglob
+}
+
+# Clear markers and names between phases so SO and addon counts stay independent.
+reset_failures() {
+    shopt -s nullglob
+    rm -f "${FAIL_DIR}"/fail.*
+    shopt -u nullglob
+    FAILED_NAMES=()
+    FAILED_COUNT=0
+}
+
+# Print a block of text atomically (under the shared output lock) so the output
+# of concurrent background jobs is not interleaved.
+locked_echo() {
+    { flock 9; printf '%s\n' "$1"; } 9>>"$OUTPUT_LOCK"
+}
+
+# Loads one template file via PUT. Intended to be dispatched as a background job.
+#   $1 uri          - e.g. _component_template/foo or _index_template/foo
+#   $2 file         - path to the template JSON
+#   $3 report_name  - name/path to record if this load fails
 load_template() {
     local uri="$1"
     local file="$2"
+    local report_name="$3"
+    local out rc=0 block
 
-    echo "Loading template file $file"
-    if ! output=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}"); then
-        echo "$output"
-
-        return 1
-
+    # Capture everything (including retry's diagnostic chatter) into one block so
+    # concurrent jobs never interleave; the whole block is flushed under one flock.
+    block="Loading template file $file"$'\n'
+    if ! out=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}" 2>&1); then
+        block+="$out"$'\n'
+        rc=1
     elif [[ "$VERBOSE" == "true" ]]; then
-        echo "$output"
+        block+="$out"$'\n'
     fi
 
+    { flock 9; printf '%s' "$block"; } 9>>"$OUTPUT_LOCK"
+
+    (( rc != 0 )) && record_failure "$report_name"
 }
 
 check_required_component_template_exists() {
@@ -110,6 +174,9 @@ load_component_templates() {
         return
     fi
 
+    # Dispatch loads as throttled background jobs. The barrier (wait) happens in
+    # the caller after all component groups have been dispatched, since index
+    # templates must not load until every component template is in place.
     for component in "$pattern"/*.json; do
         tmpl_name=$(basename "${component%.json}")
 
@@ -118,10 +185,8 @@ load_component_templates() {
             tmpl_name="${tmpl_name%-mappings}-mappings"
         fi
 
-        if ! load_template "_component_template/${tmpl_name}" "$component"; then
-            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
-            SO_LOAD_FAILURES_NAMES+=("$component")
-        fi
+        template_throttle
+        load_template "_component_template/${tmpl_name}" "$component" "$component" &
     done
 }
 
@@ -172,6 +237,9 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
     load_component_templates "Elastic Agent" "elastic-agent"
     load_component_templates "Security Onion" "so"
 
+    # Barrier: every component template PUT must complete before we snapshot the
+    # component template list and start loading index templates that depend on them.
+    wait
     component_templates=$(so-elasticsearch-component-templates-list)
     echo -e "Loading Security Onion index templates...\n"
     for so_idx_tmpl in "${SO_TEMPLATES_DIR}"/*.json; do
@@ -181,7 +249,7 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
             # TODO: Better way to load only heavynode specific templates
             if ! check_heavynode_compatiable_index_template "$tmpl_name"; then
                 if [[ "$VERBOSE" == "true" ]]; then
-                    echo "Skipping over $so_idx_tmpl, template is not a heavynode specific index template."
+                    locked_echo "Skipping over $so_idx_tmpl, template is not a heavynode specific index template."
                 fi
 
                 continue
@@ -189,32 +257,34 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
         fi
 
         if check_required_component_template_exists "$so_idx_tmpl"; then
-            if ! load_template "_index_template/$tmpl_name" "$so_idx_tmpl"; then
-                SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
-                SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
-            fi
+            template_throttle
+            load_template "_index_template/$tmpl_name" "$so_idx_tmpl" "$so_idx_tmpl" &
         else
-            echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
-            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
-            SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
+            locked_echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
+            record_failure "$so_idx_tmpl"
 
             continue
         fi
     done
 
-    if [[ $SO_LOAD_FAILURES -eq 0 ]]; then
+    # Barrier: all SO index template PUTs must finish before tallying failures.
+    wait
+
+    collect_failures
+    if [[ $FAILED_COUNT -eq 0 ]]; then
         echo "All Security Onion core templates loaded successfully."
 
         touch "$SO_STATEFILE_SUCCESS"
     else
-        echo "Encountered $SO_LOAD_FAILURES failure(s) loading templates:"
-        for failed_template in "${SO_LOAD_FAILURES_NAMES[@]}"; do
+        echo "Encountered $FAILED_COUNT failure(s) loading templates:"
+        for failed_template in "${FAILED_NAMES[@]}"; do
             echo "  - $failed_template"
         done
         if [[ "$SHOULD_EXIT_ON_FAILURE" == "true" ]]; then
             fail "Failed to load all Security Onion core templates successfully."
         fi
     fi
+    reset_failures
 elif ! index_templates_exist "$SO_TEMPLATES_DIR"; then
     echo "No Security Onion core index templates found in ${SO_TEMPLATES_DIR}, skipping."
 elif [[ -f "$SO_STATEFILE_SUCCESS" ]]; then
@@ -233,26 +303,27 @@ if should_load_addon_templates; then
         tmpl_name=$(basename "${addon_idx_tmpl%-template.json}")
 
         if check_required_component_template_exists "$addon_idx_tmpl"; then
-            if ! load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl"; then
-                ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
-                ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
-            fi
+            template_throttle
+            load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl" "$addon_idx_tmpl" &
         else
-            echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
-            ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
-            ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
+            locked_echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
+            record_failure "$addon_idx_tmpl"
 
             continue
         fi
     done
 
-    if [[ $ADDON_LOAD_FAILURES -eq 0 ]]; then
+    # Barrier: all addon index template PUTs must finish before tallying failures.
+    wait
+
+    collect_failures
+    if [[ $FAILED_COUNT -eq 0 ]]; then
         echo "All addon integration templates loaded successfully."
 
         touch "$ADDON_STATEFILE_SUCCESS"
     else
-        echo "Encountered $ADDON_LOAD_FAILURES failure(s) loading addon integration templates:"
-        for failed_template in "${ADDON_LOAD_FAILURES_NAMES[@]}"; do
+        echo "Encountered $FAILED_COUNT failure(s) loading addon integration templates:"
+        for failed_template in "${FAILED_NAMES[@]}"; do
             echo "  - $failed_template"
         done
         if [[ "$SHOULD_EXIT_ON_FAILURE" == "true" ]]; then

salt/elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load

@@ -6,6 +6,48 @@
 
 . /usr/sbin/so-common
 
+MAX_JOBS=${MAX_ILM_JOBS:-10}
+
+# Lock used to serialize block writes so concurrent jobs never interleave their output.
+ILM_OUTPUT_LOCK=$(mktemp)
+ILM_FAIL_FILE=$(mktemp)
+trap 'rm -f "$ILM_OUTPUT_LOCK" "$ILM_FAIL_FILE"' EXIT
+
+# Policies are loaded concurrently (up to MAX_JOBS at a time) for speed. Each policy's block is
+# printed the moment its curl returns, so output appears in COMPLETION ORDER, not the order
+# policies are defined in configuration.
+echo "Loading ILM policies concurrently; output below appears in completion order, not configuration order."
+echo
+
+put_policy() {
+  local desc="$1" policyname="$2" data="$3" result rc=0
+  if ! result=$(curl -K /opt/so/conf/elasticsearch/curl.config -s -k -L --fail \
+    -X PUT "https://localhost:9200/_ilm/policy/${policyname}" \
+    -H 'Content-Type: application/json' -d"${data}" 2>&1); then
+    rc=1
+  elif ! jq -e '.acknowledged == true' <<<"$result" >/dev/null 2>&1; then
+    rc=1
+  fi
+
+  # curl above ran in parallel; serialize just this block write so concurrent jobs never interleave.
+  {
+    flock 200
+    printf 'Setting up %s policy...\n%s\n\n' "${desc}" "${result}"
+    if (( rc != 0 )); then
+      printf '%s\n' "${policyname}" >>"$ILM_FAIL_FILE"
+    fi
+  } 200>>"${ILM_OUTPUT_LOCK}"
+
+  return "$rc"
+}
+
+# Block until fewer than MAX_JOBS background curls are running.
+throttle() {
+  while (( $(jobs -rp | wc -l) >= MAX_JOBS )); do
+    wait -n || true
+  done
+}
+
 {%- from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS %}
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS %}
@@ -14,35 +56,36 @@
 {%- for index, settings in ES_INDEX_SETTINGS.items() %}
 {%-   if settings.policy is defined %}
 {%-     if index == 'so-logs-detections.alerts' %}
-  echo
-  echo "Setting up so-logs-detections.alerts-so policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-so" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "so-logs-detections.alerts-so" "{{ index }}-so" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     elif index == 'so-logs-soc' %}
-  echo
-  echo "Setting up so-soc-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/so-soc-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "so-soc-logs" "so-soc-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  throttle
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     else %}
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     endif %}
 {%-   endif %}
 {%- endfor %}
-echo
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   for index, settings in ALL_ADDON_SETTINGS.items() %}
 {%-     if settings.policy is defined %}
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     endif %}
 {%-   endfor %}
 {%- endif %}
+
+wait || true
+
+if [[ -s "$ILM_FAIL_FILE" ]]; then
+  echo "ERROR: Failed to load ILM policy(s):"
+  while read -r POLICY; do
+    echo " - $POLICY"
+  done < "$ILM_FAIL_FILE"
+  exit 1
+else
+  echo "Successfully loaded all ILM policies."
+fi

salt/kibana/enabled.sls

@@ -69,7 +69,7 @@ wait_for_so-kibana:
     - ssl: True
     - verify_ssl: False
     - status: 200
-    - wait_for: 300
+    - wait_for: 600
     - request_interval: 15
     - require:
       - docker_container: so-kibana

salt/manager/files/mirror-kernel.txt

@@ -0,0 +1,2 @@
+https://repo.securityonion.net/file/so-repo/prod/3/oracle/9-uek8
+https://repo-alt.securityonion.net/prod/3/oracle/9-uek8

salt/manager/files/repodownload.conf

@@ -10,4 +10,9 @@ keepcache=0
 name=Security Onion Repo repo
 mirrorlist=file:///opt/so/conf/reposync/mirror.txt
 enabled=1
-gpgcheck=1
+gpgcheck=1
+[securityonionkernelsync]
+name=Security Onion Kernel Repo repo
+mirrorlist=file:///opt/so/conf/reposync/mirror-kernel.txt
+enabled=1
+gpgcheck=1

salt/manager/init.sls

@@ -86,6 +86,28 @@ repo_dir:
       - group
     - show_changes: False
 
+kernelrepo_dir:
+  file.directory:
+    - name: /nsm/kernelrepo
+    - user: socore
+    - group: socore
+    - recurse:
+      - user
+      - group
+    - show_changes: False
+
+# Ensure /nsm/kernelrepo is always a valid (if empty) repo before it is ever assigned to
+# a client. Without repodata/repomd.xml an enabled file:///nsm/kernelrepo repo makes every
+# dnf operation fail; so-repo-sync only populates it after the highstate, so seed an empty
+# repo here. Only runs when repodata is missing, so it won't clobber a synced repo.
+kernelrepo_init_empty:
+  cmd.run:
+    - name: createrepo /nsm/kernelrepo
+    - unless: 'test -e /nsm/kernelrepo/repodata/repomd.xml'
+    - require:
+      - file: kernelrepo_dir
+      - pkg: install_createrepo
+
 manager_sbin:
   file.recurse:
     - name: /usr/sbin
@@ -122,6 +144,13 @@ so-repo-mirrorlist:
     - user: socore
     - group: socore
 
+so-repo-kernel-mirrorlist:
+  file.managed:
+    - name: /opt/so/conf/reposync/mirror-kernel.txt
+    - source: salt://manager/files/mirror-kernel.txt
+    - user: socore
+    - group: socore
+
 so-repo-sync:
   {%     if MANAGERMERGED.reposync.enabled %}
   cron.present:

salt/manager/tools/sbin/so-repo-sync

@@ -10,5 +10,16 @@ NOROOT=1
 set -e
 
 curl --retry 5 --retry-delay 60 -A "reposync/$(sync_options)" https://sigs.securityonion.net/checkup --output /tmp/checkup
+
 dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionsync --download-metadata -p /nsm/repo/
 createrepo /nsm/repo
+
+# The kernel repo section is deployed to repodownload.conf by the manager highstate, which
+# runs AFTER this script during soup. On the first upgrade to a kernel-aware version the
+# on-disk config still predates the section, so guard on its presence to avoid dnf's
+# "Unknown repo: 'securityonionkernelsync'" aborting the sync (set -e). The next sync after the
+# highstate deploys the section will pick it up.
+if grep -q '^\[securityonionkernelsync\]' /opt/so/conf/reposync/repodownload.conf; then
+  dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionkernelsync --download-metadata -p /nsm/kernelrepo/
+  createrepo /nsm/kernelrepo
+fi

salt/manager/tools/sbin/soup

@@ -245,6 +245,7 @@ check_airgap() {
       UPDATE_DIR=/tmp/soagupdate/SecurityOnion
       AGDOCKER=/tmp/soagupdate/docker
       AGREPO=/tmp/soagupdate/minimal/Packages
+      AGUEKREPO=/tmp/soagupdate/uek/Packages
   else
       is_airgap=1
   fi
@@ -386,10 +387,11 @@ highstate() {
 masterlock() {
   echo "Locking Salt Master"
   mv -v $TOPFILE $BACKUPTOPFILE
-  echo "base:" > $TOPFILE
-  echo "  $MINIONID:" >> $TOPFILE
-  echo "    - ca" >> $TOPFILE
-  echo "    - elasticsearch" >> $TOPFILE
+  # Render the real top file only for the host running soup; every other
+  # minion gets an empty top (no states) while the master is upgrading.
+  echo "{% if grains['id'] == '$MINIONID' %}" > $TOPFILE
+  cat $BACKUPTOPFILE >> $TOPFILE
+  echo "{% endif %}" >> $TOPFILE
 }
 
 masterunlock() {
@@ -849,6 +851,28 @@ kibana_backport_streams_index_template() {
 
 }
 
+# Runs kafka-features.sh upgrade --release-version $1
+#   Upgrades Kafka KRaft cluster metadata
+update_kafka_metadata() {
+    metadata_version="$1"
+    global_pillar="/opt/so/saltstack/local/pillar/global/soc_global.sls"
+    if PIPELINE=$(so-yaml.py get -r "$global_pillar" global.pipeline 2> /dev/null) && [[ "$PIPELINE" == "KAFKA" ]]; then
+        kafka_nodes_raw=$(salt-call pillar.get kafka:nodes --out=json)
+        if kafka_nodes=$(jq -er '.local | select(type == "object" and length > 0)' <<< "$kafka_nodes_raw"); then
+            bootstrap_servers=$(jq -r '[to_entries[] | select(.value.role | contains("broker")) | "\(.value.ip):9092"] | join(",")' <<< "$kafka_nodes")
+            echo "Upgrading Kafka KRaft cluster version"
+            so-kafka-cli kafka-features.sh --bootstrap-server "$bootstrap_servers" --command-config /opt/kafka/config/kraft/client.properties upgrade --release-version "$metadata_version" 2>/dev/null || true
+
+            return 0
+        else
+            FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically perform Kafka KRaft cluster metadata update. This step can be performed manually using the following command (replacing \$BROKER_IP with the ip of atleast 1 available Kafka broker):")
+            FINAL_MESSAGE_QUEUE+=("    - so-kafka-cli kafka-features.sh --bootstrap-server \$BROKER_IP:9092 --command-config /opt/kafka/config/kraft/client.properties upgrade --release-version $metadata_version")
+        fi
+    else
+        echo "Nothing to do!"
+    fi
+}
+
 up_to_3.2.0() {
   fix_logstash_0013_lumberjack_pipeline_name
 
@@ -866,6 +890,8 @@ post_to_3.2.0() {
 
   kibana_backport_streams_index_template
 
+  update_kafka_metadata "4.3"
+
   POSTVERSION=3.2.0
 }
 
@@ -979,13 +1005,19 @@ update_airgap_rules() {
   rsync -a $UPDATE_DIR/agrules/securityonion-resources/* /nsm/securityonion-resources/
 }
 
-update_airgap_repo() {
+update_airgap_repos() {
   # Update the files in the repo
-  echo "Syncing new updates to /nsm/repo"
-  rsync -a $AGREPO/* /nsm/repo/
-  echo "Creating repo"
+  echo "Syncing new updates to /nsm/repo & /nsm/kernelrepo"
+  # Airgap soup copies new files into the local repo, but doesn't remove old packages. Retaining the ability to rollback package updates
+  rsync -a "$AGREPO"/ /nsm/repo/
+  rsync -a "$AGUEKREPO"/ /nsm/kernelrepo/
+
   dnf -y install yum-utils createrepo_c
+
+  echo "Running createrepo for /nsm/repo"
   createrepo /nsm/repo
+  echo "Running createrepo for /nsm/kernelrepo"
+  createrepo /nsm/kernelrepo
 }
 
 update_salt_mine() {
@@ -1741,7 +1773,7 @@ main() {
   set -e
 
   if [[ $is_airgap -eq 0 ]]; then
-    update_airgap_repo
+    update_airgap_repos
     dnf clean all
     check_os_updates
   elif [[ $OS == 'oracle' ]]; then

salt/nginx/enabled.sls

@@ -59,6 +59,7 @@ so-nginx:
       - /opt/so/conf/navigator/layers/:/opt/socore/html/navigator/assets/so:ro
       - /opt/so/conf/navigator/config.json:/opt/socore/html/navigator/assets/config.json:ro
       - /nsm/repo:/opt/socore/html/repo:ro
+      - /nsm/kernelrepo:/opt/socore/html/kernelrepo:ro
       - /nsm/rules:/nsm/rules:ro
       {%   if NGINXMERGED.external_suricata %}
       - /opt/so/rules/nids/suri:/surirules:ro

salt/nginx/etc/nginx.conf

@@ -323,6 +323,16 @@ http {
 			autoindex_localtime on;
 		}
 
+		location /kernelrepo/ {
+			allow all;
+			sendfile on;
+			sendfile_max_chunk 1m;
+			autoindex on;
+			autoindex_exact_size off;
+			autoindex_format html;
+			autoindex_localtime on;
+		}
+
 		location /influxdb/ {
 			auth_request          /auth/sessions/whoami;
 			rewrite               /influxdb/api/(.*) /api/$1 break;

salt/registry/enabled.sls

@@ -16,7 +16,7 @@ include:
 # Install the registry container
 so-dockerregistry:
   docker_container.running:
-    - image: ghcr.io/security-onion-solutions/registry:3.0.0
+    - image: ghcr.io/security-onion-solutions/registry:3.1.1
     - hostname: so-registry
     - networks:
       - sobridge:

salt/repo/client/oracle.sls

@@ -6,6 +6,10 @@
 {% from 'repo/client/map.jinja' import REPOPATH with context %}
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 
+{% import_yaml 'salt/minion.defaults.yaml' as saltversion %}
+{% set saltversion = saltversion.salt.minion.version %}
+{% set INSTALLEDSALTVERSION = grains.saltversion %}
+
 {% set role = grains.id.split('_') | last %}
 {% set MANAGER = salt['grains.get']('master') %}
 {% if grains['os'] == 'OEL' %}
@@ -57,6 +61,32 @@ so_repo:
     - enabled: 1
     - gpgcheck: 1
 
+# 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
+# UEK8 kernel repo (and the kernel update it enables) from activating until the node is
+# fully on the target salt, the same way other states defer across the upgrade window.
+{% if saltversion | string == INSTALLEDSALTVERSION | string %}
+so_kernel_repo:
+  pkgrepo.managed:
+    - name: securityonionkernel
+    - humanname: Security Onion Kernel Repo
+  {% if GLOBALS.is_manager %}
+    - baseurl: file:///nsm/kernelrepo/
+  {% else %}
+    - baseurl: https://{{ GLOBALS.repo_host }}/kernelrepo
+  {% endif %}
+    - enabled: 1
+    - gpgcheck: 1
+    # 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.
+    - skip_if_unavailable: 1
+    # Only assign the kernel repo once physical NIC names are pinned by MAC, so the
+    # UEK8 kernel update can't renumber interfaces SO binds by name (see pin_nic_names
+    # in salt/common/init.sls, which drops this marker via /usr/sbin/so-nic-pin).
+    - onlyif: 'test -e /opt/so/state/nic_names_pinned'
+{% endif %}
+
 {% endif %}
   
 # TODO: Add a pillar entry for custom repos

salt/soc/config.sls

@@ -134,6 +134,30 @@ socsigmasopipeline:
     - group: 939
     - mode: 600
 
+socsigmaplaybookpipeline:
+  file.managed:
+    - name: /opt/so/conf/soc/sigma_playbook_pipeline.yaml
+    - source: salt://soc/files/soc/sigma_playbook_pipeline.yaml
+    - user: 939
+    - group: 939
+    - mode: 600
+
+socplaybookplaceholdermap:
+  file.managed:
+    - name: /opt/so/conf/soc/playbook_placeholder_map.yaml
+    - source: salt://soc/files/soc/playbook_placeholder_map.yaml
+    - user: 939
+    - group: 939
+    - mode: 600
+
+socplaybookplaceholdermapcustom:
+  file.managed:
+    - name: /opt/so/conf/soc/playbook_placeholder_map_custom.yaml
+    - source: salt://soc/files/soc/playbook_placeholder_map_custom.yaml
+    - user: 939
+    - group: 939
+    - mode: 600
+
 socbanner:
   file.managed:
     - name: /opt/so/conf/soc/banner.md

salt/soc/defaults.yaml

@@ -1502,6 +1502,9 @@ soc:
               - repo: https://github.com/Security-Onion-Solutions/securityonion-resources-playbooks
                 branch: main
                 folder: securityonion-normalized
+              - repo: https://github.com/Security-Onion-Solutions/securityonion-resources-playbooks
+                branch: published
+                folder: sigma
             airgap:
               - repo: file:///nsm/airgap-resources/playbooks/securityonion-resources-playbooks
                 branch: main
@@ -1771,13 +1774,13 @@ soc:
               enabled: true
           queries:
             - name: Default Query
-              description: Show all events grouped by the observer host
-              query: '* | groupby observer.name'
-              showSubtitle: true
-            - name: Log Type
               description: Show all events grouped by module and dataset
               query: '* | groupby event.module* event.dataset'
               showSubtitle: true
+            - name: Observer
+              description: Show all events grouped by the observer host
+              query: '* | groupby observer.name'
+              showSubtitle: true
             - name: SOC - Auth
               description: Users authenticated to SOC grouped by IP address and identity
               query: 'event.dataset:kratos.audit AND msg:*authenticated* | groupby http.request.headers.x-real-ip user.name'

salt/soc/enabled.sls

@@ -45,7 +45,10 @@ so-soc:
       - /opt/so/conf/soc/motd.md:/opt/sensoroni/html/motd.md:ro
       - /opt/so/conf/soc/banner.md:/opt/sensoroni/html/login/banner.md:ro
       - /opt/so/conf/soc/sigma_so_pipeline.yaml:/opt/sensoroni/sigma_so_pipeline.yaml:ro
-      - /opt/so/conf/soc/sigma_final_pipeline.yaml:/opt/sensoroni/sigma_final_pipeline.yaml:rw
+      - /opt/so/conf/soc/sigma_playbook_pipeline.yaml:/opt/sensoroni/sigma_playbook_pipeline.yaml:ro
+      - /opt/so/conf/soc/sigma_final_pipeline.yaml:/opt/sensoroni/sigma_final_pipeline.yaml:ro
+      - /opt/so/conf/soc/playbook_placeholder_map.yaml:/opt/sensoroni/playbook_placeholder_map.yaml:ro
+      - /opt/so/conf/soc/playbook_placeholder_map_custom.yaml:/opt/sensoroni/playbook_placeholder_map_custom.yaml:ro
       - /opt/so/conf/soc/custom.js:/opt/sensoroni/html/js/custom.js:ro
       - /opt/so/conf/soc/custom_roles:/opt/sensoroni/rbac/custom_roles:ro
       - /opt/so/conf/soc/soc_users_roles:/opt/sensoroni/rbac/users_roles:rw
@@ -99,6 +102,8 @@ so-soc:
       - file: soccustomroles
       - file: socusersroles
       - file: socclientsroles
+      - file: socplaybookplaceholdermap
+      - file: socplaybookplaceholdermapcustom
 
 delete_so-soc_so-status.disabled:
   file.uncomment:

salt/soc/files/soc/playbook_placeholder_map.yaml

@@ -0,0 +1,49 @@
+# Global Playbook placeholder map: %token% -> event field path.
+#
+# Loaded by the SOC Playbook module and used to resolve `field|expand:%placeholder%` values 
+# from an alert when converting playbook questions to OQL. 
+# Left: the %token% used in a question
+# Right: the event field its value is read from (event_data.-nested or bare; the module
+# tries both). 
+#
+# Example: with `src_ip: source.ip` (below), a question that writes
+# `source.ip|expand: '%src_ip%'` resolves %src_ip% to the alert's source.ip at convert time.
+#
+# This is the global base layer. To add or override tokens edit playbook_placeholder_map_custom.yaml.
+# those entries overlay this map and win on conflict.
+
+CommandLine: process.command_line
+CurrentDirectory: process.working_directory
+Image: process.executable
+ImageLoaded: dll.name
+ParentImage: process.parent.executable
+ParentName: process.parent.name
+ParentProcessGuid: process.parent.entity_id
+ProcessGuid: process.entity_id
+TargetFilename: file.name
+TargetObject: registry.path
+TargetUserName: user.target.name
+User: user.name
+community_id: network.community_id
+dns_resolved_ip: dns.resolved_ip
+document_id: soc_id
+dst_ip: destination.ip
+dst_port: destination.port
+event_data_source_ip: source.ip
+file_path: file.path
+file_dirs: process.file_dirs
+file_name: process.name
+file_paths: process.file_paths
+hostname: host.name
+private_ip: network.private_ip
+public_ip: network.public_ip
+related_hosts: related.hosts
+related_ip: related.ip
+src_ip: source.ip
+dns_query_name: dns.query_name
+flow_id: log.id.uid
+payload: network.data.decoded
+rule_category: rule.category
+rule_name: rule.name
+rule_uuid: rule.uuid
+src_port: source.port

salt/soc/files/soc/playbook_placeholder_map_custom.yaml

@@ -0,0 +1,14 @@
+# Custom Playbook placeholder map: %token% -> event field path.
+#
+#
+# Left: the %token% used in a playbook question.
+# Right: the event field its value is read from (event_data.-nested or bare; the module tries
+# both). Note: a token that is simply named after a flat event field resolves automatically
+# without an entry here - only add a mapping when the token name differs from the field name.
+#
+# Example:
+#
+# account_id: cloudflare.account_id
+#
+# A question that writes
+# `account_id|expand: '%account_id%'` resolves %account_id% from the alert at convert time.

salt/soc/files/soc/sigma_playbook_pipeline.yaml

@@ -0,0 +1,12 @@
+name: Security Onion - Playbook Pipeline
+priority: 97
+transformations:
+    # Route string fields to their lowercase-normalized .caseless subfield so wildcard
+    # matches are case-insensitive.
+    - id: case_insensitive_string_fields
+      type: field_name_mapping
+      mapping:
+        process.executable: process.executable.caseless
+        process.parent.executable: process.parent.executable.caseless
+        process.command_line: process.command_line.caseless
+        process.parent.command_line: process.parent.command_line.caseless

salt/soc/files/soc/sigma_so_pipeline.yaml

@@ -63,6 +63,14 @@ transformations:
       rule_conditions:
       - type: logsource
         category: antivirus
+    # OS-agnostic process_creation scoping for product-less (NIDS/host-pivot) rules.
+    - id: process_creation_os_agnostic
+      type: add_condition
+      conditions:
+        event.category: process
+      rule_conditions:
+      - type: logsource
+        category: process_creation
     # Transforms the `Hashes` field to ECS fields
     # ECS fields are used by the hash fields emitted by Elastic Defend
     # If shipped with Elastic Agent, sysmon logs will also have hashes mapped to ECS fields    
@@ -108,6 +116,40 @@ transformations:
       - type: logsource
         product: windows
         category: driver_load
+    - id: ecs_fix_process_creation
+      type: field_name_mapping
+      mapping:
+        # bare `Hashes` (the combined-string case is broken out above)
+        winlog.event_data.Hashes: process.hash.sha256
+        winlog.event_data.IntegrityLevel: process.Ext.token.integrity_level_name
+        winlog.event_data.ParentName: process.parent.name
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: process_creation
+    - id: ecs_fix_registry_set
+      type: field_name_mapping
+      mapping:
+        winlog.event_data.Details: registry.data.strings
+        # field rename only; EventType values (SetValue/CreateKey) still differ from
+        # event.action values (modification/creation)
+        winlog.event_data.EventType: event.action
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: registry_set
+    - id: ecs_fix_image_load
+      type: field_name_mapping
+      mapping:
+        file.path: dll.path
+        file.code_signature.signed: dll.code_signature.exists
+        winlog.event_data.Signature: dll.code_signature.subject_name
+        file.code_signature.status: dll.code_signature.status
+        winlog.event_data.Hashes: dll.hash.sha256
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: image_load
     - id: linux_security_add-fields
       type: add_condition
       conditions:
@@ -281,6 +323,15 @@ transformations:
       rule_conditions:
       - type: logsource
         category: file_event
+    # Scope image_load rules to Elastic Endpoint library events (event.category:library, dll.*
+    # populated).
+    - id: endpoint_image_load_add-fields
+      type: add_condition
+      conditions:
+        event.category: 'library'
+      rule_conditions:
+      - type: logsource
+        category: image_load
     # Maps network rules to all network logs
     # This targets all network logs, all services, generated from endpoints and network
     - id: network_add-fields

salt/soc/soc_soc.yaml

@@ -46,7 +46,15 @@ soc:
         syntax: yaml
         file: True
         global: True
-        advanced: True
+        advanced: False
+        helpLink: security-onion-console-customization
+      playbook_placeholder_map_custom__yaml:
+        title: Playbook Placeholder Map
+        description: Custom mappings of Playbook %placeholder% tokens to event fields.
+        syntax: yaml
+        file: True
+        global: True
+        advanced: False
         helpLink: security-onion-console-customization
   config:
     licenseKey:

salt/suricata/enabled.sls

@@ -65,10 +65,11 @@ so-suricata:
       - file: suriclassifications
 
 surirulereload:
-  cmd.run: 
+  cmd.run:
     - name: /usr/sbin/so-suricata-reload-rules >> /opt/so/log/suricata/reload.log 2>&1
-    - onchanges: 
+    - onchanges:
         - file: surirulesync
+    - onlyif: test -f /opt/so/rules/suricata/all-rulesets.rules
     - require:
         - docker_container: so-suricata
     

salt/suricata/tools/sbin/so-suricata-reload-rules

@@ -7,5 +7,59 @@
 
 . /usr/sbin/so-common
 
-retry 60 3 'docker exec so-suricata /opt/suricata/bin/suricatasc -c reload-rules /var/run/suricata/suricata-command.socket' '{"message":"done","return":"OK"}' || fail "The Suricata container was not ready in time."
-retry 60 3 'docker exec so-suricata /opt/suricata/bin/suricatasc -c ruleset-reload-nonblocking /var/run/suricata/suricata-command.socket' '{"message":"done","return":"OK"}' || fail "The Suricata container was not ready in time."
+RULES_FILE="/opt/so/rules/suricata/all-rulesets.rules"
+SOCKET="/var/run/suricata/suricata-command.socket"
+SURICATASC="docker exec so-suricata /opt/suricata/bin/suricatasc"
+
+# Format an epoch as a human-readable local timestamp for log messages.
+fmt_time() { date -d "@$1" '+%Y-%m-%d %H:%M:%S %Z' 2>/dev/null; }
+
+# Prefix each input line with the current timestamp.
+timestamp_lines() { while IFS= read -r line; do printf '%s %s\n' "$(date '+%Y-%m-%d %H:%M:%S %Z')" "$line"; done; }
+
+# Epoch of Suricata's last *completed* ruleset reload; non-zero return on failure.
+suricata_reload_epoch() {
+  local out ts
+  out=$($SURICATASC -c ruleset-reload-time "$SOCKET" 2>/dev/null)
+  ts=$(echo "$out" | jq -r '.message[0].last_reload // empty' 2>/dev/null)
+  [ -n "$ts" ] || return 1
+  date -d "$ts" +%s 2>/dev/null
+}
+
+# Trigger a fresh reload and confirm Suricata is running a ruleset at least as new
+# as the rules file. Returns 0 only when both hold, so retry keeps going until an
+# in-progress reload clears and our own reload completes.
+reload_and_verify() {
+  local out reload_epoch
+  out=$($SURICATASC -c reload-rules "$SOCKET")
+  echo "reload-rules: $out"
+
+  if [[ "$out" =~ "Reload already in progress" ]]; then
+    echo "A reload is already in progress; waiting for it to clear so a fresh reload can load the current ruleset."
+    return 1
+  fi
+  if [[ ! "$out" =~ '{"message":"done","return":"OK"}' ]]; then
+    echo "Suricata not ready or unexpected reload output; will retry."
+    return 1
+  fi
+
+  reload_epoch=$(suricata_reload_epoch) || { echo "Could not read ruleset-reload-time; will retry."; return 1; }
+  if [ "$reload_epoch" -ge "$target_mtime" ]; then
+    echo "Loaded ruleset is current: last reload ($(fmt_time "$reload_epoch")) is newer than rules file ($(fmt_time "$target_mtime"))."
+    return 0
+  fi
+  echo "Loaded ruleset is stale: last reload ($(fmt_time "$reload_epoch")) is older than rules file ($(fmt_time "$target_mtime")); retrying."
+  return 1
+}
+
+# Run the reload/verify, timestamping every line of output (ours and the
+# retry/fail helpers') so reload.log shows when each step ran. The pipeline is
+# synchronous, so the log is fully flushed and ordered before we exit; the
+# script's real exit code is preserved via PIPESTATUS.
+{
+  # Epoch mtime of the ruleset we need Suricata to have loaded. Captured once so
+  # a file update mid-reload does not move the goalpost.
+  target_mtime=$(stat -c %Y "$RULES_FILE") || fail "Could not stat the Suricata rules file: $RULES_FILE"
+  retry 60 3 'reload_and_verify' || fail "Suricata did not load the current ruleset in time."
+} 2>&1 | timestamp_lines
+exit "${PIPESTATUS[0]}"

salt/telegraf/etc/telegraf.conf

@@ -244,6 +244,7 @@
   username = "{{ ES_USER }}"
   password = "{{ ES_PASS }}"
   insecure_skip_verify = true
+  cluster_health = true
 {%- elif grains['role'] in ['so-searchnode']  %}
 [[inputs.elasticsearch]]
   servers = ["https://{{ NODEIP }}:9200"]

salt/top.sls

@@ -83,7 +83,6 @@ base:
     - zeek
     - strelka
     - elastalert
-    - utility
     - elasticfleet
     - pcap.cleanup
 
@@ -113,7 +112,6 @@ base:
     - zeek
     - strelka
     - elastalert
-    - utility
     - elasticfleet
     - stig
     - kafka
@@ -141,7 +139,6 @@ base:
     - elastic-fleet-package-registry
     - kibana
     - elastalert
-    - utility
     - elasticfleet
     - stig
     - kafka
@@ -168,7 +165,6 @@ base:
     - elastic-fleet-package-registry
     - kibana
     - elastalert
-    - utility
     - elasticfleet
     - kafka
 
@@ -198,7 +194,6 @@ base:
     - elastic-fleet-package-registry
     - kibana
     - elastalert
-    - utility
     - elasticfleet
     - stig
     - kafka
@@ -222,7 +217,6 @@ base:
     - elasticsearch
     - elastic-fleet-package-registry
     - kibana
-    - utility
     - suricata
     - zeek
     - elasticfleet

salt/utility/bin/eval

@@ -1,29 +0,0 @@
-#!/bin/bash
-# Wait for ElasticSearch to come up, so that we can query for version infromation
-echo -n "Waiting for ElasticSearch..."
-COUNT=0
-ELASTICSEARCH_CONNECTED="no"
-while [[ "$COUNT" -le 30 ]]; do
-  curl -K /opt/so/conf/elasticsearch/curl.config -k --output /dev/null --silent --head --fail -L https://{{ GLOBALS.manager_ip }}:9200
-  if [ $? -eq 0 ]; then
-    ELASTICSEARCH_CONNECTED="yes"
-    echo "connected!"
-    break
-  else
-    ((COUNT+=1))
-    sleep 1
-    echo -n "."
-  fi
-done
-if [ "$ELASTICSEARCH_CONNECTED" == "no" ]; then
-  echo
-  echo -e "Connection attempt timed out.  Unable to connect to ElasticSearch.  \nPlease try: \n  -checking log(s) in /var/log/elasticsearch/\n  -running 'docker ps' \n  -running 'sudo so-elastic-restart'"
-  echo
-
-  exit
-fi
-
-echo "Applying cross cluster search config..."
-    curl -K /opt/so/conf/elasticsearch/curl.config -s -k -XPUT -L https://{{ GLOBALS.manager_ip }}:9200/_cluster/settings \
-         -H 'Content-Type: application/json' \
-         -d "{\"persistent\": {\"search\": {\"remote\": {\"{{ grains.host }}\": {\"seeds\": [\"127.0.0.1:9300\"]}}}}}"

salt/utility/init.sls

@@ -1,22 +0,0 @@
-{% from 'allowed_states.map.jinja' import allowed_states %}
-{% from 'vars/globals.map.jinja' import GLOBALS %}
-
-{% if sls in allowed_states %}
-  {% if grains['role'] in ['so-eval', 'so-import'] %}
-fixsearch:
-  cmd.script:
-    - shell: /bin/bash
-    - cwd: /opt/so
-    - source: salt://utility/bin/eval
-    - template: jinja
-    - defaults:
-        GLOBALS: {{ GLOBALS }}
-  {% endif %}
-
-{% else %}
-
-{{sls}}_state_not_allowed:
-  test.fail_without_changes:
-    - name: {{sls}}_state_not_allowed
-
-{% endif %}

setup/so-functions

@@ -29,8 +29,12 @@ title() {
 }
 
 fail_setup() {
+	local err_msg=$1
+	if [[ -n "$err_msg" ]]; then
+		error "$err_msg"
+	fi
 	error "Setup encountered an unrecoverable failure, exiting"
-	touch /root/failure
+	echo "setup incomplete: $err_msg" > /root/failure
 	exit 1
 }
 
@@ -697,7 +701,7 @@ compare_main_nic_ip() {
 			EOM
 
 		  [[ -n $TESTING ]] || whiptail --title "$whiptail_title" --msgbox "$message" 11 75
-		  kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup
+		  kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup "Main IP mismatch"
 	  fi
 	else
 		# Setup uses MAINIP, but since we ignore the equality condition when using a VPN 
@@ -755,8 +759,7 @@ configure_management_bond() {
 	info "Setting up $bond_name management interface with mode $bond_mode"
 
 	if [[ ${#MBNICS[@]} -eq 0 ]]; then
-		error "[ERROR] No management bond NICs were selected."
-		fail_setup
+		fail_setup "No management bond NICs selected"
 	fi
 
 	nmcli -t -f NAME con show | grep -Fxq "$bond_name"
@@ -886,6 +889,7 @@ create_repo() {
 	title "Create the repo directory"
 	logCmd "dnf -y install yum-utils createrepo_c"
 	logCmd "createrepo /nsm/repo"
+	logCmd "createrepo /nsm/kernelrepo"
 }
 
 
@@ -913,8 +917,7 @@ detect_os() {
 		is_rpm=true
 		is_supported=true
 	else
-		info "This OS is not supported. Security Onion requires Oracle Linux 9."
-		fail_setup
+		fail_setup "This OS is not supported. Security Onion requires Oracle Linux 9."
 	fi
 
 	info "Found OS: $OS $OSVER"
@@ -922,7 +925,7 @@ detect_os() {
 
 download_elastic_agent_artifacts() {
 	if ! update_elastic_agent 2>&1 | tee -a "$setup_log"; then
-		fail_setup
+		fail_setup "Failed to update Elastic Agent"
 	fi
 }
 
@@ -1566,7 +1569,7 @@ proxy_validate() {
 		error "Received error: $proxy_test_err"
 		if [[ -n $TESTING ]]; then
 			error "Exiting setup"
-			kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup
+			kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup "Proxy validation failed"
 		fi
 	fi
 	return $ret
@@ -1773,8 +1776,7 @@ ensure_pyyaml() {
 	local result=$?
 	set +o pipefail
 	if [[ $result -ne 0 ]] || ! rpm -q python3-pyyaml >/dev/null 2>&1; then
-		error "Failed to install python3-pyyaml (exit=$result)"
-		fail_setup
+		fail_setup "Failed to install python3-pyyaml (exit=$result)"
 	fi
 	info "python3-pyyaml installed successfully"
 }
@@ -1812,6 +1814,16 @@ securityonion_repo() {
 			echo "mirrorlist=file:///etc/yum/mirror.txt" >> /etc/yum.repos.d/securityonion.repo
 			echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
+			echo "https://repo.securityonion.net/file/so-repo/prod/3/oracle/9-uek8" > /etc/yum/mirror-kernel.txt
+			echo "https://so-repo-east.s3.us-east-005.backblazeb2.com/prod/3/oracle/9-uek8" >> /etc/yum/mirror-kernel.txt
+			echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
+			echo "name=Security Onion Kernel Repo repo" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "mirrorlist=file:///etc/yum/mirror-kernel.txt" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
+			# Supplementary kernel repo: tolerate it being empty/unreachable so a missing
+			# repomd.xml can't make every dnf operation fail before the repo is populated.
+			echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 			logCmd "dnf repolist"
 		else
 			echo "[securityonion]" > /etc/yum.repos.d/securityonion.repo
@@ -1820,6 +1832,13 @@ securityonion_repo() {
 			echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
 			echo "sslverify=0" >> /etc/yum.repos.d/securityonion.repo
+			echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
+			echo "name=Security Onion Kernel Repo" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "baseurl=https://$MSRV/kernelrepo" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "sslverify=0" >> /etc/yum.repos.d/securityonionkernel.repo
+			echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 			logCmd "dnf repolist"
 		fi
 	elif [[ ! $waitforstate ]]; then
@@ -1829,12 +1848,25 @@ securityonion_repo() {
 		echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
 		echo "sslverify=0" >> /etc/yum.repos.d/securityonion.repo
+		echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
+		echo "name=Security Onion Kernel Repo" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "baseurl=https://$MSRV/kernelrepo" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "sslverify=0" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 	elif [[ $waitforstate ]]; then
 		echo "[securityonion]" > /etc/yum.repos.d/securityonion.repo
 		echo "name=Security Onion Repo" >> /etc/yum.repos.d/securityonion.repo
 		echo "baseurl=file:///nsm/repo/" >> /etc/yum.repos.d/securityonion.repo
 		echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
+		echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
+		echo "name=Security Onion Kernel Repo" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "baseurl=file:///nsm/kernelrepo/" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
+		echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 	fi
 	logCmd "dnf repolist all"
 	if [[ $waitforstate ]]; then
@@ -1850,9 +1882,12 @@ repo_sync_local() {
 	# Sync the repo from the SO repo locally.
 	info "Adding Repo Download Configuration"
 	mkdir -p /nsm/repo
+	mkdir -p /nsm/kernelrepo
 	mkdir -p /opt/so/conf/reposync/cache
 	echo "https://repo.securityonion.net/file/so-repo/prod/3/oracle/9" > /opt/so/conf/reposync/mirror.txt
 	echo "https://repo-alt.securityonion.net/prod/3/oracle/9" >> /opt/so/conf/reposync/mirror.txt
+	echo "https://repo.securityonion.net/file/so-repo/prod/3/oracle/9-uek8" > /opt/so/conf/reposync/mirror-kernel.txt
+	echo "https://repo-alt.securityonion.net/prod/3/oracle/9-uek8" >> /opt/so/conf/reposync/mirror-kernel.txt
 	echo "[main]" > /opt/so/conf/reposync/repodownload.conf
 	echo "gpgcheck=1" >> /opt/so/conf/reposync/repodownload.conf
 	echo "installonly_limit=3" >> /opt/so/conf/reposync/repodownload.conf
@@ -1866,12 +1901,18 @@ repo_sync_local() {
 	echo "mirrorlist=file:///opt/so/conf/reposync/mirror.txt" >> /opt/so/conf/reposync/repodownload.conf
 	echo "enabled=1" >> /opt/so/conf/reposync/repodownload.conf
 	echo "gpgcheck=1" >> /opt/so/conf/reposync/repodownload.conf
+	echo "[securityonionkernel]" >> /opt/so/conf/reposync/repodownload.conf
+	echo "name=Security Onion Kernel Repo repo" >> /opt/so/conf/reposync/repodownload.conf
+	echo "mirrorlist=file:///opt/so/conf/reposync/mirror-kernel.txt" >> /opt/so/conf/reposync/repodownload.conf
+	echo "enabled=1" >> /opt/so/conf/reposync/repodownload.conf
+	echo "gpgcheck=1" >> /opt/so/conf/reposync/repodownload.conf
 
 	logCmd "dnf repolist"
 
 	if [[ ! $is_airgap ]]; then
 		curl --retry 5 --retry-delay 60 -A "netinstall/$SOVERSION/$OS/$(uname -r)/1" https://sigs.securityonion.net/checkup --output /tmp/install
-		retry 5 60 "dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionsync --download-metadata -p /nsm/repo/" >> "$setup_log" 2>&1 || fail_setup
+		retry 5 60 "dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionsync --download-metadata -p /nsm/repo/" >> "$setup_log" 2>&1 || fail_setup "Failed to sync repos"
+		retry 5 60 "dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionkernel --download-metadata -p /nsm/kernelrepo/" >> "$setup_log" 2>&1 || fail_setup "Failed to sync kernel repos"
 		# After the download is complete run createrepo
 		create_repo
 	fi
@@ -1884,10 +1925,10 @@ saltify() {
 
 	if [[ $waitforstate ]]; then
 		# install all for a manager
-		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh -r -M -X stable $SALTVERSION" || fail_setup
+		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh -r -M -X stable $SALTVERSION" || fail_setup "Failed to install salt master"
 	else
 		# just a minion
-		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh -r -X stable $SALTVERSION" || fail_setup
+		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh -r -X stable $SALTVERSION" || fail_setup "Failed to install salt minion"
 	fi
 
 	salt_install_module_deps
@@ -1959,7 +2000,7 @@ set_main_ip() {
 			info "MAINIP=$MAINIP"
 			info "MNIC_IP=$MNIC_IP"
 			whiptail_error_message "The management IP could not be determined. Please check the log at /root/sosetup.log and verify the network configuration. Select OK to exit."
-			fail_setup
+			fail_setup "Could not determine MAINIP or MNIC_IP"
 		fi
 		sleep 1
 	done
@@ -2163,7 +2204,7 @@ set_initial_firewall_access() {
 set_management_interface() {
 	title "Setting up the main interface"
 	if [[ $MNIC == "bond1" ]]; then
-		configure_management_bond || fail_setup
+		configure_management_bond || fail_setup "Failed to configure management bond"
 	fi
 
 	if [ "$address_type" = 'DHCP' ]; then
@@ -2228,6 +2269,13 @@ update_sudoers_for_testing() {
 }
 
 update_packages() {
+	# Pin physical NIC names by MAC BEFORE pulling packages, so the UEK8 kernel that
+	# the update below installs can't renumber the interfaces SO binds by name. Doing
+	# it here (instead of waiting for the common highstate) also drops the
+	# /opt/so/state/nic_names_pinned marker that gates the kernel repo, so the kernel
+	# repo is assigned on the very first highstate and the kernel isn't downgraded and
+	# then re-upgraded. Run-once: so-nic-pin no-ops if the marker already exists.
+	logCmd "bash ../salt/common/tools/sbin/so-nic-pin"
 	logCmd "dnf repolist"
 	logCmd "dnf -y update --allowerasing --exclude=salt*,docker*,containerd*"
 	RMREPOFILES=("oracle-linux-ol9.repo" "uek-ol9.repo" "virt-ol9.repo")

setup/so-setup

@@ -9,14 +9,17 @@
 # Make sure you are root before doing anything
 uid="$(id -u)"
 if [ "$uid" -ne 0 ]; then
-	echo "This script must be run using sudo!"
-	fail_setup
+	echo "This script must be run using sudo!" >&2
+	exit 1
 fi
 
 # Save the original argument array since we modify it
 original_args=("$@")
 
-cd "$(dirname "$0")" || fail_setup
+cd "$(dirname "$0")" || {
+	echo "Unable to change to setup directory" >&2
+	exit 1
+}
 
 echo "Getting started..."
 
@@ -87,8 +90,7 @@ if [[ "$setup_type" == 'iso' ]]; then
 	if [[ $is_rpm ]]; then
 		is_iso=true
 	else
-		echo "Only use 'so-setup iso' for an ISO install on Security Onion ISO images. Please run 'so-setup network' instead."
-		fail_setup
+		fail_setup "Only use 'so-setup iso' for an ISO install on Security Onion ISO images. Please run 'so-setup network' instead."
 	fi
 fi
 
@@ -127,7 +129,7 @@ catch() {
 	info "Fatal error occurred at $1 in so-setup, failing setup."
 	grep --color=never "ERROR" "$setup_log" > "$error_log"
 	whiptail_setup_failed
-	fail_setup
+	fail_setup "Fatal error occurred at $1 in so-setup"
 }
 
 # Add the progress function for manager node type installs
@@ -235,8 +237,7 @@ case "$setup_type" in
 		info "Beginning Security Onion $setup_type install"
 		;;
 	*)
-		error "Invalid install type, must be 'iso', 'network' or 'desktop'."
-		fail_setup
+		fail_setup "Invalid install type, must be 'iso', 'network' or 'desktop'."
 		;;
 esac
 
@@ -770,8 +771,7 @@ if ! [[ -f $install_opt_file ]]; then
 		logCmd "salt-call state.apply -l info registry"
 		title "Seeding the docker registry"
 		if ! docker_seed_registry; then
-			error "Failed to seed the docker registry"
-			fail_setup
+			fail_setup "Failed to seed the docker registry"
 		fi
 		title "Applying the manager state"
 		logCmd "salt-call state.apply -l info manager"
@@ -794,8 +794,7 @@ if ! [[ -f $install_opt_file ]]; then
 		title "Setting up Elastic Fleet"
 		logCmd "salt-call state.apply elasticfleet.config"	
 		if ! logCmd so-elastic-fleet-setup; then
-			error "Failed to run so-elastic-fleet-setup"
-			fail_setup
+			fail_setup "Failed to run so-elastic-fleet-setup"
 		fi
 		mark_setup_complete
 		set_initial_firewall_access

setup/so-verify

@@ -143,15 +143,15 @@ main() {
         cat $error_log
         echo "--------------------------"
         exit_code=1
-        touch /root/failure
+        echo "Found setup errors. Check $error_log for details" > /root/failure
     elif using_iso && cron_error_in_mail_spool; then
         echo "WARNING: Unexpected cron job output in mail spool"
         exit_code=1
-        touch /root/failure
+        echo "Unexpected cron job output found in /var/spool/mail/" > /root/failure
     elif is_manager_node && status_failed; then
         echo "WARNING: Containers are not in a healthy state"
         exit_code=1
-        touch /root/failure
+        echo "Containers are not in a healthy state. Check so-status for details" > /root/failure
     else
         echo "Successfully completed setup!"
         touch /root/success