Gracefully skip SSL cert states when the CA is unavailable

The *.ssl x509.certificate_managed states hard-failed the state run when
the CA/manager minion was unreachable (ca_server did not respond), and the
paired private_key_managed states then failed on the prereq requisite. The
- timeout: 30 on these states was a no-op (Salt has no per-state timeout
requisite; only retry accepts until/attempts/interval/splay).

Add an onlyif CA-reachability gate to every certificate_managed state so the
state is skipped as a clean success when the CA does not answer a peer
test.ping within 3s and the cert already exists. When the cert is missing
(initial provisioning) the state still runs so the existing retry waits for
the CA. The reachability command is centralized as CA.reachable_cmd in
ca/map.jinja, and the master peer config now permits test.ping. The no-op
- timeout: 30 is removed from all cert states.

files/salt/master/master

@@ -64,5 +64,6 @@ pillar_roots:
 peer:
   .*:
     - x509.sign_remote_certificate
+    - test.ping
 
 

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/_beacons/pillar_db.py

@@ -1,142 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-# Custom salt beacon that watches the SOC audit_settings table in postgres for
-# new settings changes and emits a beacon event per new row. This replaces the
-# inotify watch on /opt/so/saltstack/local/pillar -- instead of monitoring pillar
-# files on disk, we monitor the so_soc.audit_settings table that SOC writes to.
-#
-# Detection is poll-based with a monotonic `id` watermark persisted to
-# WATERMARK_FILE: each pass selects rows with id greater than the last id seen,
-# which makes it self-healing (a missed poll simply catches up on the next one).
-#
-# Each emitted event carries setting_id and node_id; the push_pillar reactor maps
-# setting_id -> app via pillar_push_map.yaml and writes a push intent, after which
-# the existing so-push-drainer / orch.push_batch pipeline takes over unchanged.
-
-import logging
-import os
-import subprocess
-
-log = logging.getLogger(__name__)
-
-WATERMARK_FILE = '/opt/so/state/pillar_db_watch.id'
-CONTAINER = 'so-postgres'
-DATABASE = 'so_soc'
-
-# Unaligned, tuples-only psql output with a field separator that cannot appear in
-# an id/setting_id/node_id, so we can split each row reliably.
-FIELD_SEP = '\x1f'
-
-
-def __virtual__():
-    return True
-
-
-def validate(config):
-    return True, 'valid'
-
-
-def _read_watermark():
-    # Returns the last processed id, or None if the watermark has not been seeded.
-    try:
-        with open(WATERMARK_FILE, 'r') as f:
-            return int((f.read() or '').strip())
-    except (IOError, ValueError):
-        return None
-
-
-def _write_watermark(value):
-    try:
-        os.makedirs(os.path.dirname(WATERMARK_FILE), exist_ok=True)
-        tmp = WATERMARK_FILE + '.tmp'
-        with open(tmp, 'w') as f:
-            f.write(str(int(value)))
-        os.rename(tmp, WATERMARK_FILE)
-    except OSError:
-        log.exception('pillar_db beacon: failed to persist watermark to %s', WATERMARK_FILE)
-
-
-def _query(sql):
-    # Run a query against so_soc inside the so-postgres container over the unix
-    # socket (trust auth, no password). Returns stdout on success, or None on any
-    # failure so the caller can no-op and retry on the next interval.
-    cmd = [
-        'docker', 'exec', CONTAINER,
-        'psql', '-U', 'postgres', '-d', DATABASE,
-        '-tA', '-F', FIELD_SEP, '-c', sql,
-    ]
-    try:
-        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
-    except subprocess.TimeoutExpired:
-        log.warning('pillar_db beacon: psql timed out')
-        return None
-    except Exception:
-        log.exception('pillar_db beacon: failed to exec psql')
-        return None
-    if result.returncode != 0:
-        log.warning('pillar_db beacon: psql failed (rc=%s): %s',
-                    result.returncode, (result.stderr or '').strip())
-        return None
-    return result.stdout
-
-
-def beacon(config):
-    retval = []
-
-    watermark = _read_watermark()
-
-    # First run / missing watermark: seed to the current MAX(id) and emit nothing
-    # so we never replay the entire settings history into a fleetwide push.
-    if watermark is None:
-        seed = _query('SELECT COALESCE(MAX(id), 0) FROM audit_settings;')
-        if seed is None:
-            return retval  # postgres not ready yet; retry next interval
-        try:
-            _write_watermark(int((seed or '0').strip() or 0))
-        except ValueError:
-            log.warning('pillar_db beacon: could not parse MAX(id) seed: %r', seed)
-        return retval
-
-    rows = _query(
-        "SELECT id, setting_id, COALESCE(node_id, '') FROM audit_settings "
-        "WHERE id > %d ORDER BY id;" % watermark
-    )
-    if rows is None:
-        return retval
-
-    max_id = watermark
-    for line in rows.splitlines():
-        # Do NOT str.strip() the whole line: Python treats the \x1f field
-        # separator (and \x1c-\x1e) as whitespace, so stripping would eat an
-        # empty trailing node_id field and make the row look malformed.
-        if not line.strip():
-            continue
-        parts = line.split(FIELD_SEP)
-        if len(parts) < 3:
-            log.warning('pillar_db beacon: skipping malformed row: %r', line)
-            continue
-        try:
-            row_id = int(parts[0])
-        except ValueError:
-            log.warning('pillar_db beacon: skipping row with non-int id: %r', line)
-            continue
-        setting_id = parts[1]
-        node_id = parts[2]
-        retval.append({
-            'tag': 'audit_settings',
-            'id': row_id,
-            'setting_id': setting_id,
-            'node_id': node_id,
-        })
-        if row_id > max_id:
-            max_id = row_id
-
-    if max_id > watermark:
-        _write_watermark(max_id)
-        log.info('pillar_db beacon: emitted %d change(s), watermark %d -> %d',
-                 len(retval), watermark, max_id)
-
-    return retval

salt/allowed_states.map.jinja

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

salt/ca/map.jinja

@@ -1,3 +1,7 @@
 {% set CA = {
     'server': pillar.ca.server
 }%}
+{# reachable_cmd: shell test used by the *.ssl cert states' onlyif to skip cert
+   management gracefully when the CA minion is unreachable. Returns exit 0 when
+   the CA answers a peer test.ping within 3s, non-zero otherwise. #}
+{% do CA.update({'reachable_cmd': "salt-call --out=json publish.publish '" ~ CA.server ~ "' test.ping timeout=3 2>/dev/null | grep -q true"}) %}

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 +1,243 @@
+#!/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 — install the UEK8 (6.x) kernel and make it the boot default.
+#
+# Security Onion is moving off the EL9 stock kernel (RHCK, 5.14) and UEK7 (5.15) onto UEK8
+# (6.x). Three things have to happen, and the tool has to drive each one:
+#
+#   1. Populate. The manager mirrors the UEK8 packages into /nsm/kernelrepo via so-repo-sync,
+#      and serves them to the grid over https://<manager>/kernelrepo. Until that sync runs the
+#      repo is valid but EMPTY -- dnf resolves it happily and installs nothing, with no error.
+#   2. Install. A node on RHCK has no kernel-uek* package at all, so there is nothing for
+#      'dnf update' to upgrade. A node on UEK7 does have kernel-uek installed, so
+#      'dnf install kernel-uek' reports "Nothing to do" and exits 0 without installing 6.x.
+#      Both cases need an explicit install of the UEK8 NEVRA.
+#   3. Boot it. Whether a newly installed UEK8 kernel becomes the boot default depends on the
+#      RUNNING kernel's flavor. kernel-install/grubby (with UPDATEDEFAULT=yes) only auto-promote
+#      within the running kernel's flavor lineage:
+#        - From UEK7 (5.x, kernel-uek) the install stays in the kernel-uek lineage and IS
+#          auto-promoted, so no grubby change is needed -- just make sure the repo is populated
+#          and install UEK8.
+#        - From the stock EL9 kernel (RHCK, 5.14, no UEK) it is a flavor CROSS that is NOT
+#          auto-promoted, so the box keeps booting RHCK until grubby is told otherwise.
+#      This tool inspects the running kernel and only runs 'grubby --set-default' for RHCK.
+#
+# Every one of those failure modes is silent by default. This tool handles each case and fails
+# loudly when it cannot, rather than reporting success while changing nothing.
+#
+# Manager vs minion: only the manager owns /nsm/kernelrepo, so only the manager can populate
+# it. If the repo is empty here, a manager runs so-repo-sync itself; a minion has no way to
+# fix it and exits non-zero telling the admin to sync the manager first.
+#
+# Idempotent: an already-installed, already-default UEK8 kernel is left alone. It only sets
+# the boot default; it does NOT reboot -- the admin reboots the node on their own schedule.
+
+. /usr/sbin/so-common
+
+# Client-side repo id (what dnf enables on this node, from repo/client/oracle.sls) vs the
+# reposync-side section in repodownload.conf that the manager mirrors from (mirrors the
+# securityonion/securityonionsync split for the main repo).
+KERNEL_REPO="securityonionkernel"
+KERNEL_REPO_SYNC="securityonionkernelsync"
+KERNEL_PKG="kernel-uek"
+KERNEL_REPO_DIR="/nsm/kernelrepo"
+REPOSYNC_CONF="/opt/so/conf/reposync/repodownload.conf"
+GLOBAL_PILLAR="/opt/so/saltstack/local/pillar/global/soc_global.sls"
+
+log() { echo "[so-kernel-upgrade] $*"; }
+die() { echo "[so-kernel-upgrade] ERROR: $*" >&2; exit 1; }
+
+command -v grubby >/dev/null 2>&1 || die "grubby not found"
+command -v dnf >/dev/null 2>&1 || die "dnf not found"
+
+ARCH="$(rpm -E '%{_arch}')"
+
+is_airgap() {
+    [ -f "$GLOBAL_PILLAR" ] && grep -q 'airgap: *[Tt]rue' "$GLOBAL_PILLAR"
+}
+
+# Newest installed UEK8 (6.x) kernel known to the bootloader. UEK8 vmlinuz paths look like
+# /boot/vmlinuz-6.12.0-204.92.4.2.el9uek.x86_64; UEK7 (5.15) and RHCK (5.14) won't match.
+find_uek8() {
+    grubby --info=ALL 2>/dev/null \
+        | sed -n 's/^kernel="\(.*\)"$/\1/p' \
+        | grep -E '/vmlinuz-6\.[0-9]+.*uek' \
+        | sort -V | tail -1
+}
+
+# Classify the RUNNING kernel (uname -r) -- this, not what's installed, is what decides whether
+# a UEK8 install auto-promotes to the boot default:
+#   uek8  6.x UEK    already on the target line; nothing to do
+#   uek7  5.x UEK    a UEK8 install stays in the kernel-uek lineage and auto-promotes (no grubby)
+#   rhck  5.14 EL9   crossing into the UEK flavor does NOT auto-promote (needs grubby --set-default)
+running_flavor() {
+    case "$(uname -r)" in
+        6.*uek*) echo uek8 ;;
+        *uek*)   echo uek7 ;;
+        *)       echo rhck ;;
+    esac
+}
+
+# Newest UEK8 kernel-uek NEVRA offered by the kernel repo, empty if the repo has none.
+# Restricted to the kernel repo so a UEK7 kernel-uek in the main repo can't be picked up,
+# and filtered to 6.x so we never "succeed" by reinstalling the 5.15 we already have.
+uek8_available() {
+    dnf -q repoquery --disablerepo='*' --enablerepo="$KERNEL_REPO" \
+        --arch="$ARCH" --latest-limit=1 \
+        --qf '%{name}-%{evr}.%{arch}\n' "$KERNEL_PKG" 2>/dev/null \
+        | grep -E "^${KERNEL_PKG}-6\." | tail -1
+}
+
+kernelrepo_rpm_count() {
+    find "$KERNEL_REPO_DIR" -maxdepth 1 -name '*.rpm' 2>/dev/null | wc -l
+}
+
+# The kernel repo starts life as valid-but-empty (kernelrepo_init_empty in
+# salt/manager/init.sls) and is filled by so-repo-sync. During a soup, so-repo-sync runs
+# BEFORE the highstate deploys the [securityonionkernelsync] section into repodownload.conf, so
+# the first kernel-aware soup leaves the repo empty until the next nightly sync.
+sync_kernel_repo() {
+    if is_airgap; then
+        log "airgap install: $KERNEL_REPO_DIR is populated from the airgap ISO, not by so-repo-sync."
+        return 1
+    fi
+    if ! grep -q "^\[${KERNEL_REPO_SYNC}\]" "$REPOSYNC_CONF" 2>/dev/null; then
+        log "$REPOSYNC_CONF has no [${KERNEL_REPO_SYNC}] section -- run a highstate to deploy it."
+        return 1
+    fi
+
+    log "populating $KERNEL_REPO_DIR with so-repo-sync (mirrors upstream; can take several minutes)"
+    su socore -c '/usr/sbin/so-repo-sync' || { log "so-repo-sync failed"; return 1; }
+
+    dnf -q clean expire-cache >/dev/null 2>&1
+    return 0
+}
+
+# Make the kernel repo actually able to serve a UEK8 package, or fail trying.
+ensure_kernel_repo() {
+    # The repo is assigned by the repo.client highstate, and only once NICs are pinned by MAC
+    # (/opt/so/state/nic_names_pinned) so the kernel swap can't renumber interfaces SO binds
+    # by name. skip_if_unavailable=1 means a broken repo is silently ignored, so check first.
+    if ! dnf -q repolist --enabled 2>/dev/null | awk '{print $1}' | grep -qx "$KERNEL_REPO"; then
+        log "repo '$KERNEL_REPO' is not enabled on this node."
+        log "Run a highstate first; the repo is skipped until /opt/so/state/nic_names_pinned"
+        log "exists (run so-nic-pin) and this node's salt matches the version this release ships."
+        die "kernel repo unavailable"
+    fi
+
+    [ -n "$(uek8_available)" ] && return 0
+
+    log "repo '$KERNEL_REPO' is enabled but offers no UEK8 $KERNEL_PKG package"
+
+    if ! is_manager_node; then
+        log "This is a minion; it consumes the kernel repo from the manager and cannot populate it."
+        log "On the manager, run:  su socore -c /usr/sbin/so-repo-sync"
+        log "then re-run this script here."
+        die "manager's kernel repo is empty"
+    fi
+
+    log "this is a manager and $KERNEL_REPO_DIR holds $(kernelrepo_rpm_count) rpm(s)"
+    sync_kernel_repo || die "could not populate $KERNEL_REPO_DIR"
+
+    [ -n "$(uek8_available)" ] \
+        || die "so-repo-sync completed but $KERNEL_REPO still offers no UEK8 $KERNEL_PKG"
+}
+
+reboot_notice() {
+    [ "$(uname -r)" = "$(basename "$1" | sed 's/^vmlinuz-//')" ] \
+        || log "REBOOT REQUIRED to start using the UEK8 kernel (currently running $(uname -r))."
+}
+
+# Keep future kernel updates on the UEK line rather than falling back to RHCK. Oracle ships
+# /etc/sysconfig/kernel; only rewrite it when it's actually pointing somewhere else.
+set_default_kernel_conf() {
+    if [ -f /etc/sysconfig/kernel ] && ! grep -q '^DEFAULTKERNEL=kernel-uek-core$' /etc/sysconfig/kernel; then
+        log "setting DEFAULTKERNEL=kernel-uek-core in /etc/sysconfig/kernel"
+        sed -i 's/^DEFAULTKERNEL=.*/DEFAULTKERNEL=kernel-uek-core/' /etc/sysconfig/kernel
+    fi
+}
+
+# Make sure a UEK8 kernel is installed, leaving its boot entry in INSTALLED_UEK8. If one is
+# already present we leave the repo alone -- it may be disabled or empty and we don't need it
+# just to flip the boot default. Otherwise install the explicit NEVRA, not the bare package
+# name: on a UEK7 node 'dnf install kernel-uek' sees 5.15 already present, prints "Nothing to
+# do" and exits 0 without installing 6.x.
+ensure_uek8_installed() {
+    INSTALLED_UEK8="$(find_uek8)"
+    if [ -n "$INSTALLED_UEK8" ]; then
+        log "UEK8 kernel already installed: $INSTALLED_UEK8"
+        return 0
+    fi
+
+    ensure_kernel_repo
+    local nevra; nevra="$(uek8_available)"
+    log "installing $nevra from $KERNEL_REPO"
+    dnf -y install "$nevra" || die "failed to install $nevra"
+
+    INSTALLED_UEK8="$(find_uek8)"
+    [ -n "$INSTALLED_UEK8" ] || die "$nevra installed but no 6.x UEK boot entry appeared -- check 'grubby --info=ALL'"
+    log "installed UEK8 kernel: $INSTALLED_UEK8"
+}
+
+case "$(running_flavor)" in
+uek8)
+    # Already on the 6.x UEK line. A plain 'dnf update' keeps this node current within the
+    # lineage and auto-promotes newer builds, so there is nothing for this tool to do.
+    log "already running a UEK8 kernel ($(uname -r)); nothing to do."
+    exit 0
+    ;;
+
+uek7)
+    # On a 5.x UEK kernel. Installing UEK8 stays inside the kernel-uek lineage, so dnf/grubby
+    # (UPDATEDEFAULT=yes) auto-promote it and we do NOT touch grubby. A node still on UEK7
+    # usually means the kernel repo was empty when it last updated, so populate it and install.
+    log "running UEK7 kernel ($(uname -r)); the kernel repo was likely not yet populated when"
+    log "this node last updated. Populating it and installing UEK8 -- the update stays on the"
+    log "kernel-uek line, so it becomes the boot default automatically (no grubby change needed)."
+    set_default_kernel_conf
+    ensure_uek8_installed
+
+    now="$(grubby --default-kernel 2>/dev/null)"
+    if [ "$now" = "$INSTALLED_UEK8" ]; then
+        log "boot default auto-promoted to UEK8 kernel: $INSTALLED_UEK8"
+    else
+        log "WARNING: expected the UEK8 kernel to auto-promote but the default is still"
+        log "'${now:-unknown}'. Run 'grubby --set-default=$INSTALLED_UEK8' to force it."
+    fi
+    reboot_notice "$INSTALLED_UEK8"
+    ;;
+
+rhck)
+    # On the stock EL9 kernel (5.14, no UEK installed). Crossing from RHCK into the UEK flavor
+    # does NOT auto-promote -- kernel-install/grubby only auto-promote within the running
+    # kernel's flavor lineage -- so after installing we must set the boot default explicitly.
+    log "running stock EL9 (RHCK) kernel ($(uname -r)); installing UEK8 and setting it as the"
+    log "boot default explicitly (a RHCK->UEK flavor change does not auto-promote)."
+    set_default_kernel_conf
+    ensure_uek8_installed
+    target="$INSTALLED_UEK8"
+
+    current="$(grubby --default-kernel 2>/dev/null)"
+    if [ "$current" = "$target" ]; then
+        log "UEK8 kernel is already the boot default: $target"
+        reboot_notice "$target"
+        exit 0
+    fi
+
+    log "current default kernel: ${current:-unknown}"
+    log "switching boot default to UEK8 kernel: $target"
+    grubby --set-default="$target" || die "grubby --set-default failed for $target"
+
+    # Verify the change actually took before claiming success.
+    now="$(grubby --default-kernel 2>/dev/null)"
+    [ "$now" = "$target" ] || die "default kernel is still '${now:-unknown}' after set-default"
+
+    log "boot default is now $target"
+    reboot_notice "$target"
+    ;;
+esac

salt/common/tools/sbin/so-restart

@@ -5,27 +5,44 @@
 # 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
+if [[ $# -lt 1 ]]; then
-        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"
+    usage
-        echo $banner
+fi
 
-        if [ "$2" = "--force" ]; then
+#shellcheck disable=SC2154
+echo "$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") docker stop so-elastic-fleet && docker rm so-elastic-fleet && salt-call state.apply elasticfleet queue=True;;
+    "elastic-fleet"|"elasticfleet")
-                *)  docker stop so-$1 ; docker rm so-$1 ; salt-call state.apply $1 queue=True;;
+        docker_check_running "elastic-fleet" "--stop"
+        docker rm "so-elastic-fleet" 2> /dev/null
+        # Removing the elastic fleet state directory, so that the next startup re-enrolls with a fresh policy
+        rm -rf /opt/so/conf/elastic-fleet/state
+
+        salt-call state.apply elasticfleet queue=True
+        ;;
+    *)
+        docker_check_running "$1" "--stop"
+        docker rm "so-${1}" 2> /dev/null
+        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"
-fi

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.
 
-
+# shellcheck disable=SC1091
-
-# Usage: so-start  all | kibana | playbook 
-
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
+usage() {
-	echo $banner
+    echo "Usage: $0 <component> [args]"
-	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 ""
-	echo $banner
+    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
+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
+case "$1" in
-   		"all") salt-call state.highstate queue=True;;
+    "all")
-   		"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 ;; 
+        salt-call state.highstate queue=True
-   		*) 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
+   	"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
-	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"	
+            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 +5,35 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
+# shellcheck disable=SC1091
-
-# Usage: so-stop kibana | playbook | thehive
-
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
+usage() {
-	echo $banner
+    echo "Usage: $0 <component>"
-	printf "Stopping $1...\n"
+    echo ""
-	echo $banner
+    echo "Examples:"
+    echo "  $0 kibana             Stop Kibana"
+    exit 1
+}
 
-	case $1 in
+if [[ $# -lt 1 ]]; then
-    		*) docker stop so-$1 ; docker rm so-$1 ;;
+    usage
-	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"	
 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
+        # Removing the elastic fleet state directory, so that the next startup re-enrolls with a fresh policy
+        rm -rf /opt/so/conf/elastic-fleet/state
+        ;;
+    *)
+        docker_check_running "$1" "--stop"
+        docker rm "so-${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/common/tools/sbin_jinja/so-salt-minion-check

@@ -1,3 +1,5 @@
+{% import_yaml 'salt/minion.defaults.yaml' as SALT_MINION_DEFAULTS -%}
+
 #!/bin/bash
 #
 # Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
@@ -23,8 +25,7 @@ SYSTEM_START_TIME=$(date -d "$(</proc/uptime awk '{print $1}') seconds ago" +%s)
 LAST_HIGHSTATE_END=$([ -e "/opt/so/log/salt/lasthighstate" ] && date -r /opt/so/log/salt/lasthighstate +%s || echo 0)
 LAST_HEALTHCHECK_STATE_APPLY=$([ -e "/opt/so/log/salt/state-apply-test" ] && date -r /opt/so/log/salt/state-apply-test +%s || echo 0)
 # SETTING THRESHOLD TO ANYTHING UNDER 600 seconds may cause a lot of salt-minion restarts since the job to touch the file occurs every 5-8 minutes by default
-# THRESHOLD is derived from the global push highstate interval + 1 hour, so the minion-check grace period tracks the schedule automatically.
+THRESHOLD={{SALT_MINION_DEFAULTS.salt.minion.check_threshold}} #within how many seconds the file /opt/so/log/salt/state-apply-test must have been touched/modified before the salt minion is restarted
-THRESHOLD=$(( ({{ salt['pillar.get']('global:push:highstate_interval_hours', 2) }} + 1) * 3600 )) #within how many seconds the file /opt/so/log/salt/state-apply-test must have been touched/modified before the salt minion is restarted
 THRESHOLD_DATE=$((LAST_HEALTHCHECK_STATE_APPLY+THRESHOLD))
 
 logCmd() {

salt/docker_clean/init.sls

@@ -9,8 +9,7 @@
 prune_images:
   cmd.run:
     - name: so-docker-prune
-    - onlyif: command -v /usr/sbin/so-docker-prune >/dev/null 2>&1
+    - order: last
-    - order: 9000
 
 {% else %}
 

salt/elastalert/enabled.sls

@@ -19,7 +19,6 @@ wait_for_elasticsearch:
 so-elastalert:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastalert:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: elastalert
     - name: so-elastalert
     - user: so-elastalert

salt/elastic-fleet-package-registry/enabled.sls

@@ -15,7 +15,6 @@ include:
 so-elastic-fleet-package-registry:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-fleet-package-registry:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - name: so-elastic-fleet-package-registry
     - hostname: Fleet-package-reg-{{ GLOBALS.hostname }}
     - detach: True

salt/elasticagent/enabled.sls

@@ -16,7 +16,6 @@ include:
 so-elastic-agent:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - name: so-elastic-agent
     - hostname: {{ GLOBALS.hostname }}
     - detach: True

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/defaults.yaml

@@ -1,6 +1,5 @@
 elasticfleet:
   enabled: False
-  patch_version: 9.3.3+build202604082258 # Elastic Agent specific patch release.
   enable_manager_output: True
   config:
     server:

salt/elasticfleet/enabled.sls

@@ -11,6 +11,10 @@
 
 {#   This value is generated during node install and stored in minion pillar #}
 {%   set SERVICETOKEN = salt['pillar.get']('elasticfleet:config:server:es_token','') %}
+{#   Prevent Elastic Agent from re-enrolling with a new agent.id everytime the container starts up.
+       - if a fresh enrollment is needed use 'so-stop elasticfleet'
+       #}
+{%   set ENROLLED = salt['file.file_exists']('/opt/so/conf/elastic-fleet/state/fleet.enc') %}
 
 include:
   - ca
@@ -42,7 +46,6 @@ elasticagent_syncartifacts:
 so-elastic-fleet:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - name: so-elastic-fleet
     - hostname: FleetServer-{{ GLOBALS.hostname }}
     - detach: True
@@ -66,6 +69,7 @@ so-elastic-fleet:
       - /etc/pki/elasticfleet-server.crt:/etc/pki/elasticfleet-server.crt:ro
       - /etc/pki/elasticfleet-server.key:/etc/pki/elasticfleet-server.key:ro
       - /etc/pki/tls/certs/intca.crt:/etc/pki/tls/certs/intca.crt:ro
+      - /opt/so/conf/elastic-fleet/state:/usr/share/elastic-agent/state
       - /opt/so/log/elasticfleet:/usr/share/elastic-agent/logs 
      {% if DOCKERMERGED.containers['so-elastic-fleet'].custom_bind_mounts %}
         {% for BIND in DOCKERMERGED.containers['so-elastic-fleet'].custom_bind_mounts %}
@@ -73,6 +77,7 @@ so-elastic-fleet:
         {% endfor %}
       {% endif %}      
     - environment:
+      {% if not ENROLLED %}
       - FLEET_SERVER_ENABLE=true
       - FLEET_URL=https://{{ GLOBALS.hostname }}:8220
       - FLEET_SERVER_ELASTICSEARCH_HOST=https://{{ GLOBALS.manager }}:9200
@@ -82,6 +87,9 @@ so-elastic-fleet:
       - FLEET_SERVER_CERT_KEY=/etc/pki/elasticfleet-server.key
       - FLEET_CA=/etc/pki/tls/certs/intca.crt     
       - FLEET_SERVER_ELASTICSEARCH_CA=/etc/pki/tls/certs/intca.crt
+      {% endif %}
+      - STATE_PATH=/usr/share/elastic-agent/state
+      - CONFIG_PATH=/usr/share/elastic-agent/state
       - LOGS_PATH=logs
       {% if DOCKERMERGED.containers['so-elastic-fleet'].extra_env %}
         {% for XTRAENV in DOCKERMERGED.containers['so-elastic-fleet'].extra_env %}
@@ -100,6 +108,7 @@ so-elastic-fleet:
       - x509: etc_elasticfleet_crt
     - require:
       - file: trusttheca
+      - file: eastatedir
       - x509: etc_elasticfleet_key
       - x509: etc_elasticfleet_crt
 

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

@@ -5,7 +5,7 @@
   "package": {
     "name": "endpoint",
     "title": "Elastic Defend",
-    "version": "9.3.0",
+    "version": "9.3.1",
     "requires_root": true
   },
   "enabled": true,

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

@@ -29,7 +29,7 @@
               "\\.gz$"
             ],
             "include_files": [],
-            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.15.0\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.8.0\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.15.0\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.15.0\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.8.0\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
+            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.20.0\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.8.3\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.20.0\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.20.0\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.8.3\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
             "tags": [
               "import"
             ],

salt/elasticfleet/install_agent_grid.sls

@@ -10,6 +10,15 @@
 {% set AGENT_STATUS = salt['service.available']('elastic-agent') %}
 {% set AGENT_EXISTS = salt['file.file_exists']('/opt/Elastic/Agent/elastic-agent') %}
 
+so-elastic-agent-install:
+  file.managed:
+    - name: /usr/sbin/so-elastic-agent-install
+    - source: salt://elasticfleet/tools/sbin/so-elastic-agent-install
+    - user: 947
+    - group: 939
+    - mode: 755
+    - show_changes: False
+
 {% if not AGENT_STATUS or not AGENT_EXISTS %}
 
 pull_agent_installer:
@@ -21,11 +30,9 @@ pull_agent_installer:
 
 run_installer:
   cmd.run:
-    - name: ./so-elastic-agent_linux_amd64 -token={{ GRIDNODETOKEN }} -force
+    - name: /usr/sbin/so-elastic-agent-install "{{ GRIDNODETOKEN }}"
-    - cwd: /opt/so
+    - require:
-    - retry:
+      - file: pull_agent_installer
-        attempts: 3
-        interval: 20
 
 cleanup_agent_installer:
   file.absent:

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/ssl.sls

@@ -38,7 +38,8 @@ etc_elasticfleet_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/elasticfleet-server.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -94,7 +95,8 @@ etc_elasticfleet_agent_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/elasticfleet-agent.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -155,7 +157,8 @@ elasticfleet_kafka_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/elasticfleet-kafka.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/elasticfleet/tools/sbin/so-elastic-agent-install

@@ -0,0 +1,100 @@
+#!/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.
+
+. /usr/sbin/so-elastic-fleet-common
+
+
+# passed in as arg from elasticfleet/install_agent_grid.sls, else pulled from pillar later
+GRIDNODETOKEN="$1"
+LOGFILE="/opt/so/SO-Elastic-Agent_Installer_Health.log"
+
+check_agent_health() {
+    timeout=300
+    interval=10
+    start=$SECONDS
+
+    while (( SECONDS - start < timeout )); do
+        agent_status=$(elastic-agent status 2>&1)
+        echo -e "\n$(date)\n$agent_status\n" >> "$LOGFILE"
+        if echo "$agent_status" | grep -A1 'elastic-agent$' | grep -q 'status: (HEALTHY)'; then
+            return 0
+        fi
+        echo "The Elastic Agent is not yet healthy. Waiting for ${interval} seconds before checking again..."
+        sleep "$interval"
+    done
+
+    echo "The Elastic Agent did not become healthy within ${timeout} seconds"
+    return 1
+}
+
+uninstall_agent() {
+    if command -v elastic-agent >/dev/null 2>&1; then
+        elastic-agent uninstall -f
+    fi
+}
+
+if [[ -z "$GRIDNODETOKEN" ]]; then
+    noderole=$(so-yaml.py get -r /etc/salt/grains role)
+    if [[ "$noderole" == "so-heavynode" ]]; then
+        GRIDNODETOKEN=$(salt-call pillar.get global:fleet_grid_enrollment_token_heavy --out=newline_values_only)
+    else
+        GRIDNODETOKEN=$(salt-call pillar.get global:fleet_grid_enrollment_token_general --out=newline_values_only)
+    fi
+fi
+
+if [[ -z "$GRIDNODETOKEN" ]]; then
+    echo "Unable to determine Elastic Fleet enrollment token. Exiting."
+
+    exit 1
+fi
+
+if [[ ! -x /opt/so/so-elastic-agent_linux_amd64 ]]; then
+    echo "Downloading so-elastic-agent installer... This could take a while if another Salt job is running."
+
+    # When running outside of elasticfleet/install_agent_grid.sls we need to download the installer independently.
+    #  PYTHONWARNINGS="ignore" to avoid messages like the following when running salt-call:
+    #  '/opt/saltstack/salt/lib/python3.10/site-packages/salt/transport/base.py:129: TransportWarning: Unclosed transport! <salt.transport.zeromq.RequestClient object at 0x7fc5f0ee7a30>
+    #    File "/bin/salt-call", line 12, in <module>
+    #      sys.exit(salt_call())'
+
+    PYTHONWARNINGS="ignore" salt-call state.single file.managed name=/opt/so/so-elastic-agent_linux_amd64 source=salt://elasticfleet/files/so_agent-installers/so-elastic-agent_linux_amd64 mode=755 makedirs=True queue=True
+
+fi
+
+if [[ -x /opt/so/so-elastic-agent_linux_amd64 ]]; then
+    attempts=0
+    cd /opt/so/ || exit 1
+
+    truncate -s 0 "$LOGFILE"
+
+    uninstall_agent
+
+    while [[ $attempts -lt 3 ]]; do
+        if ./so-elastic-agent_linux_amd64 -token="$GRIDNODETOKEN" -force && echo "Verifying Elastic Agent health..." && check_agent_health; then
+            rm -f /opt/so/so-elastic-agent_linux_amd64
+            elastic-agent status
+
+            exit 0
+        fi
+
+        attempts=$((attempts + 1))
+
+        if [[ $attempts -lt 3 ]]; then
+            echo "Unable to verify Elastic Agent health... Retrying in 20 seconds..."
+            sleep 20
+        fi
+    done
+
+    uninstall_agent
+    rm -f /opt/so/so-elastic-agent_linux_amd64
+    echo "The so-elastic-agent installer failed after 3 attempts. Exiting."
+
+    exit 1
+else
+    echo "Unable to locate so-elastic-agent installer. Exiting."
+
+    exit 1
+fi

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
+  elastic_fleet_load_integrations_dir "endpoints-initial" \
-    printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
+    /opt/so/conf/elastic-fleet/integrations/endpoints-initial "Initial Endpoints Policy" || RETURN_CODE=1
-    elastic_fleet_integration_check "endpoints-initial" "$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
 
   # Grid Nodes - General
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_general/*.json; do
+  elastic_fleet_load_integrations_dir "so-grid-nodes_general" \
-    printf "\n\nGrid Nodes Policy_General - Loading $INTEGRATION\n"
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_general "Grid Nodes Policy_General" || RETURN_CODE=1
-    elastic_fleet_integration_check "so-grid-nodes_general" "$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
 
   # Grid Nodes - Heavy
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy/*.json; do
+  elastic_fleet_load_integrations_dir "so-grid-nodes_heavy" \
-    printf "\n\nGrid Nodes Policy_Heavy - Loading $INTEGRATION\n"
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy "Grid Nodes Policy_Heavy" || RETURN_CODE=1
-    elastic_fleet_integration_check "so-grid-nodes_heavy" "$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
 
-  # Fleet Server - Optional integrations
+  # Fleet Server - Optional integrations (adds integration configuration to a given FleetServer_ policy)
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json; do
+  for FLEET_DIR in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/; do
-    if ! [ "$INTEGRATION" == "/opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json" ]; then
+    [ -d "$FLEET_DIR" ] || continue
-      FLEET_POLICY=`echo "$INTEGRATION"| cut -d'/' -f7`
+    INTEGRATIONS=("${FLEET_DIR%/}"/*.json)
-      printf "\n\nFleet Server Policy - Loading $INTEGRATION\n"
+    [ -e "${INTEGRATIONS[0]}" ] || continue
-      elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
+
-      if [ -n "$INTEGRATION_ID" ]; then
+    FLEET_POLICY=$(basename "$FLEET_DIR")
-        printf "\n\nIntegration $NAME exists - Updating integration\n"
+    elastic_fleet_load_integrations_dir "$FLEET_POLICY" \
-        if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+      "${FLEET_DIR%/}" "Fleet Server Policy" "elasticsearch-logs" || RETURN_CODE=1
-          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
   done
 
   # Only create the state file if all policies were created/updated successfully

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

@@ -30,7 +30,7 @@ done
 if [[ -z $FLEETHOST ]] || [[ -z $ENROLLMENTOKEN ]]; then 
   printf "\nFleet Host URL, Enrollment Token or Elastic Version empty - exiting..."
   printf "\nFleet Host: $FLEETHOST, Enrollment Token: $ENROLLMENTOKEN\n"
-  exit 
+  exit 1
 fi
 
 OSARCH=( "linux-x86_64" "windows-x86_64" "darwin-x86_64" "darwin-aarch64" )
@@ -62,31 +62,54 @@ do
 done 
 
 GOTARGETOS=( "linux" "windows" "darwin" "darwin/arm64" )
-GOARCH="amd64"
 printf "\n### Generating OS packages using the cleaned up tarballs"
-for GOOS in "${GOTARGETOS[@]}"
+for GOOS in "${GOTARGETOS[@]}"; do
-do
+    GOARCH="amd64"
     if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin" && GOARCH="arm64"; fi
     printf "\n\n### Generating $GOOS/$GOARCH Installer...\n"
     docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
     --mount type=bind,source=/etc/pki/tls/certs/,target=/workspace/files/cert/ \
     --mount type=bind,source=/nsm/elastic-agent-workspace/,target=/workspace/files/elastic-agent/ \
-    --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/,target=/output/ \
+    --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ \
     {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}
     printf "\n### $GOOS/$GOARCH Installer Generated...\n"
 done
 
 printf "\n\n### Generating MSI...\n"
-cp /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/so-elastic-agent_windows_amd64.exe
+cp /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
 docker run \
---mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/,target=/output/ -w /output \
+--mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ -w /output \
 {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs
 printf "\n### MSI Generated...\n"
 
+# Verify installers were created
+for GOOS in "${GOTARGETOS[@]}"; do
+    GOARCH="amd64"
+    if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin"; GOARCH="arm64"; fi
+    if [[ ! -f /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_${GOOS}_${GOARCH} ]]; then
+        printf "\n### ERROR: Installer for %s/%s was not generated. Exiting...\n" "$GOOS" "$GOARCH"
+        exit 1
+    fi
+    # After verifying new installer was generated, move it to so_agent-installers directory
+    mv /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_${GOOS}_${GOARCH} /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/
+done
+
+# Verify MSI installer
+if [[ ! -f /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64_msi ]]; then
+    printf "\n### ERROR: Installer MSI was not generated. Exiting...\n"
+    exit 1
+else
+    # After verifying new installer MSI was generated, move it to so_agent-installers directory
+    mv /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64_msi /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/
+fi
+
 printf "\n### Cleaning up temp files \n"
 rm -rf /nsm/elastic-agent-workspace
-rm -rf /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/so-elastic-agent_windows_amd64.exe
+rm -rf /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
 
 printf "\n### Copying so_agent-installers to /nsm/elastic-fleet/ for nginx.\n"
 \cp -vr /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/ /nsm/elastic-fleet/
 chmod 644 /nsm/elastic-fleet/so_agent-installers/*
+
+# if we got here all installers have been generated successfully
+exit 0

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
-                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
+    # One jq pass emits name/package.name/package.version/id for every eligible integration.
-                if ! INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION"); then
+    # 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 $PACKAGE_NAME"
                 exit 1
             fi
+            LATEST_VERSION_CACHE[$PACKAGE_NAME]=$AVAILABLE_VERSION
+        fi
+        AVAILABLE_VERSION=${LATEST_VERSION_CACHE[$PACKAGE_NAME]}
 
         if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
-                    # Dry run of the upgrade
+            # Dry run, then (if clean) the actual upgrade, dispatched as a throttled background
-                    echo ""
+            # job. Each job builds its full log into one block, then flushes it under a single
-                    echo "Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."
+            # shared lock (OUTPUT_LOCK) so concurrent jobs never interleave on stdout; a failed
-                    echo "Upgrading $INTEGRATION..."
+            # job also appends a marker line to FAIL_FILE while holding that same lock.
-                    echo "Starting dry run..."
+            elastic_fleet_throttle
+            {
+                block=$'\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 "$INTEGRATION_ID"); then
-                        exit 1
+                    block+="Error: Failed to complete dry run for '$INTEGRATION_ID'."$'\n'
-                    fi
+                    fail="dryrun $INTEGRATION"
-                    DRYRUN_ERRORS=$(echo "$DRYRUN_OUTPUT" | jq .[].hasErrors)
+                elif [[ "$(jq .[].hasErrors <<<"$DRYRUN_OUTPUT")" == "false" ]]; then
-
+                    block+="No errors detected. Proceeding with upgrade..."$'\n'
-                    # 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'."
+                        block+="Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."$'\n'
-                            ERROR=true
+                        fail="upgrade $INTEGRATION"
-                            continue
                     fi
                 else
-                        echo "Errors detected during dry run for $PACKAGE_NAME policy upgrade..."
+                    block+="Errors detected during dry run for $PACKAGE_NAME policy upgrade..."$'\n'
-                        ERROR=true
+                    fail="dryrun-errors $INTEGRATION"
-                        continue
                 fi
+                {
+                    flock 9
+                    printf '%s' "$block"
+                    [ -n "$fail" ] && printf '%s\n' "$fail" >>"$FAIL_FILE"
+                } 9>>"$OUTPUT_LOCK"
+            } &
         fi
+    done < <(jq -r --argjson defaults "$default_packages_json" '
+        .item.package_policies[]
+        | select(.name != "elastic-defend-endpoints")
+        | select(.name | startswith("fleet_server-") | not)
         {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-            fi
+        | select(.package.name | IN($defaults[]))
         {%- endif %}
-        fi
+        | [.name, .package.name, .package.version, .id] | @tsv
+    ' <<<"$POLICY_JSON")
 done
-done
+
-if [[ "$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[@]} " =~ " $PACKAGE_NAME " ]]; then
+    while IFS= read -r PACKAGE_NAME; do
-            in_use_integrations+=("$PACKAGE_NAME")
+        [ -n "$PACKAGE_NAME" ] && in_use_integrations+=("$PACKAGE_NAME")
-        fi
+    done < <(jq -r --argjson defaults "$default_packages_json" \
-    done
+        '.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
+        # Build the bulk install list and the per-package status messages with two jq passes
-            # get package details
+        #  instead of a per-package bash loop. The old loop forked ~10 processes per package
-            package_name=$(echo "$package" | jq -r '.name')
+        #  (5 jq + awk/bc for the version compare) and re-parsed/rewrote a growing JSON file on
-            latest_version=$(echo "$package" | jq -r '.latest_version')
+        #  every add (O(n^2)). Selection and messages below are identical to that logic.
-            installed_version=$(echo "$package" | jq -r '.installed_version')
+        SUB={% if SUB %}true{% else %}false{% endif %}
-            subscription=$(echo "$package" | jq -r '.subscription')
+        AUTOUP={% if AUTO_UPGRADE_INTEGRATIONS %}true{% else %}false{% endif %}
-            bulk_package=$(echo "$package" | jq '{name: .name, version: .latest_version}' )
+        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
+        # vnum replicates the previous version_conversion (%d%03d%03d of the first three dotted
-            {% if not SUB %}
+        #  fields); needs() replicates the excluded/subscription/installed/upgrade/in-use logic.
-                if [[ "$subscription" != "basic" && "$subscription" != "null" && -n "$subscription" ]]; then
+        JQ_DECISION='
-                    # pass over integrations that require non-basic elastic license
+def vnum:
-                    echo "$package_name integration requires an Elastic license of $subscription or greater... skipping"
+  [ (split(".")|.[0:3][] | gsub("[^0-9].*";"") | (if .=="" then "0" else . end) | tonumber) ]
-                    continue
+  | (.[0]//0)*1000000 + (.[1]//0)*1000 + (.[2]//0);
-                else
+def needs($sub;$autoup;$excluded;$inuse):
-                    if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
+  .name as $n
-                        echo "$package_name is not installed... Adding to next update."
+  | ($n | IN($excluded[]) | not)
-                        jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+  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
+        JQ_ARGS=(--argjson sub "$SUB" --argjson autoup "$AUTOUP" --argjson excluded "$EXCLUDED_JSON" --argjson inuse "$INUSE_JSON")
-                    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
 
+        # (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
-                            {%- 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")"
 
         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 INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
-if VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+
-    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; 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
 
@@ -241,11 +244,37 @@ printf '%s\n'\
     "" >> "$global_pillar_file"
 
 # Call Elastic-Fleet Salt State
-printf "\nApplying elasticfleet state"
+printf "\nApplying elasticfleet state\n"
-salt-call state.apply elasticfleet queue=True
+for state_attempt in {1..3}; do
+    if salt-call state.apply elasticfleet queue=True; then
+        break
+    elif [[ $state_attempt -lt 3 ]]; then
+        printf "\nElasticfleet state did not complete successfully... Attempt (%s/3). Retrying...\n" "$state_attempt"
+        sleep 10
+    else
+        printf "\nFailure(s) in elasticfleet state... Exiting...\n"
+        exit 1
+    fi
+done
 
+printf "\nRunning so-elastic-agent-gen-installers\n"
 # Generate installers & install Elastic Agent on the node
-so-elastic-agent-gen-installers
+for agent_gen_attempt in {1..3}; do
-printf "\nApplying elasticfleet.install_agent_grid state"
+    if so-elastic-agent-gen-installers; then
-salt-call state.apply elasticfleet.install_agent_grid queue=True
+        break
-exit 0
+    elif [[ $agent_gen_attempt -lt 3 ]]; then
+        printf "\nUnable to generate Elastic Agent installers... Attempt (%s/3). Retrying...\n" "$agent_gen_attempt"
+        sleep 10
+    else
+        printf "\nFailed to generate Elastic Agent installers after 3 attempts. Exiting...\n"
+        exit 1
+    fi
+done
+
+printf "\nApplying elasticfleet.install_agent_grid state\n"
+if ! salt-call state.apply elasticfleet.install_agent_grid queue=True; then
+    printf "\nFailure(s) in elasticfleet.install_agent_grid state... Exiting...\n"
+    exit 1
+fi
+
+printf "\nElastic Fleet setup completed successfully\n"

salt/elasticsearch/defaults.yaml

@@ -1,6 +1,6 @@
 elasticsearch:
   enabled: false
-  version: 9.3.3
+  version: 9.3.7
   index_clean: true
   data_retention_method: DLM
   vm:

salt/elasticsearch/enabled.sls

@@ -24,7 +24,6 @@ include:
 so-elasticsearch:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elasticsearch:{{ ELASTICSEARCHMERGED.version }}
-    - restart_policy: unless-stopped
     - hostname: elasticsearch
     - name: so-elasticsearch
     - user: elasticsearch

salt/elasticsearch/files/ingest/logs-pfsense.log-1.25.4

@@ -118,70 +118,70 @@
     {
       "pipeline": {
         "tag": "pipeline_e16851a7",
-        "name": "logs-pfsense.log-1.25.2-firewall",
+        "name": "logs-pfsense.log-1.25.4-firewall",
         "if": "ctx.event.provider == 'filterlog'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_828590b5",
-        "name": "logs-pfsense.log-1.25.2-openvpn",
+        "name": "logs-pfsense.log-1.25.4-openvpn",
         "if": "ctx.event.provider == 'openvpn'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_9d37039c",
-        "name": "logs-pfsense.log-1.25.2-ipsec",
+        "name": "logs-pfsense.log-1.25.4-ipsec",
         "if": "ctx.event.provider == 'charon'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_ad56bbca",
-        "name": "logs-pfsense.log-1.25.2-dhcp",
+        "name": "logs-pfsense.log-1.25.4-dhcp",
         "if": "[\"dhcpd\", \"dhclient\", \"dhcp6c\", \"dnsmasq-dhcp\"].contains(ctx.event.provider)"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_dd85553d",
-        "name": "logs-pfsense.log-1.25.2-unbound",
+        "name": "logs-pfsense.log-1.25.4-unbound",
         "if": "ctx.event.provider == 'unbound'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_720ed255",
-        "name": "logs-pfsense.log-1.25.2-haproxy",
+        "name": "logs-pfsense.log-1.25.4-haproxy",
         "if": "ctx.event.provider == 'haproxy'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_456beba5",
-        "name": "logs-pfsense.log-1.25.2-php-fpm",
+        "name": "logs-pfsense.log-1.25.4-php-fpm",
         "if": "ctx.event.provider == 'php-fpm'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_a0d89375",
-        "name": "logs-pfsense.log-1.25.2-squid",
+        "name": "logs-pfsense.log-1.25.4-squid",
         "if": "ctx.event.provider == 'squid'"
       }
     },
     {
       "pipeline": {
         "tag": "pipeline_c2f1ed55",
-        "name": "logs-pfsense.log-1.25.2-snort",
+        "name": "logs-pfsense.log-1.25.4-snort",
         "if": "ctx.event.provider == 'snort'"
       }
     },
     {
       "pipeline": {
         "tag":"pipeline_33db1c9e",
-        "name": "logs-pfsense.log-1.25.2-suricata",
+        "name": "logs-pfsense.log-1.25.4-suricata",
         "if": "ctx.event.provider == 'suricata'"
       }
     },

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/soc_elasticsearch.yaml

@@ -645,6 +645,7 @@ elasticsearch:
             global: True
             advanced: True
             helpLink: elasticsearch
+    so-logs-soc: *dataStreamSettings
     so-logs-system_x_auth: *dataStreamSettings
     so-logs-system_x_syslog: *dataStreamSettings
     so-logs-system_x_system: *dataStreamSettings

salt/elasticsearch/ssl.sls

@@ -34,7 +34,8 @@ elasticsearch_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/elasticsearch.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

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
+FAILED_NAMES=()
-ADDON_LOAD_FAILURES=0
+FAILED_COUNT=0
-SO_LOAD_FAILURES_NAMES=()
-ADDON_LOAD_FAILURES_NAMES=()
 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 $file"
+    # Capture everything (including retry's diagnostic chatter) into one block so
-    if ! output=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}"); then
+    # concurrent jobs never interleave; the whole block is flushed under one flock.
-        echo "$output"
+    block="Loading template file $file"$'\n'
-
+    if ! out=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}" 2>&1); then
-        return 1
+        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
+        template_throttle
-            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
+        load_template "_component_template/${tmpl_name}" "$component" "$component" &
-            SO_LOAD_FAILURES_NAMES+=("$component")
-        fi
     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" "$so_idx_tmpl"; then
+            template_throttle
-                SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
+            load_template "_index_template/$tmpl_name" "$so_idx_tmpl" "$so_idx_tmpl" &
-                SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
-            fi
         else
-            echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
+            locked_echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
-            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
+            record_failure "$so_idx_tmpl"
-            SO_LOAD_FAILURES_NAMES+=("$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:"
+        echo "Encountered $FAILED_COUNT failure(s) loading templates:"
-        for failed_template in "${SO_LOAD_FAILURES_NAMES[@]}"; do
+        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}" "$addon_idx_tmpl"; then
+            template_throttle
-                ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
+            load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl" "$addon_idx_tmpl" &
-                ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
-            fi
         else
-            echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
+            locked_echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
-            ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
+            record_failure "$addon_idx_tmpl"
-            ADDON_LOAD_FAILURES_NAMES+=("$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:"
+        echo "Encountered $FAILED_COUNT failure(s) loading addon integration templates:"
-        for failed_template in "${ADDON_LOAD_FAILURES_NAMES[@]}"; do
+        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 (( $(jobs -rp | wc -l) >= MAX_JOBS )); do
+    wait -n || true
+  done
+}
+
 {%- from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS %}
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS %}
@@ -14,35 +56,36 @@
 {%- for index, settings in ES_INDEX_SETTINGS.items() %}
 {%-   if settings.policy is defined %}
 {%-     if index == 'so-logs-detections.alerts' %}
-  echo
+  throttle
-  echo "Setting up so-logs-detections.alerts-so policy..."
+  put_policy "so-logs-detections.alerts-so" "{{ index }}-so" '{ "policy": {{ settings.policy | tojson(true) }} }' &
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$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
 {%-     elif index == 'so-logs-soc' %}
-  echo
+  throttle
-  echo "Setting up so-soc-logs policy..."
+  put_policy "so-soc-logs" "so-soc-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/so-soc-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
+  throttle
-  echo
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$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
 {%-     else %}
-  echo
+  throttle
-  echo "Setting up {{ index }}-logs policy..."
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
 {%-     endif %}
 {%-   endif %}
 {%- endfor %}
-echo
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   for index, settings in ALL_ADDON_SETTINGS.items() %}
 {%-     if settings.policy is defined %}
-  echo
+  throttle
-  echo "Setting up {{ index }}-logs policy..."
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$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
 {%-     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/global/defaults.yaml

@@ -1,10 +1,3 @@
 global:
   pcapengine: SURICATA
   pipeline: REDIS
-  push:
-    enabled: true
-    highstate_interval_hours: 2
-    debounce_seconds: 30
-    drain_interval: 15
-    batch: '25%'
-    batch_wait: 15

salt/global/soc_global.yaml

@@ -59,41 +59,4 @@ global:
     description: Allows use of Endgame with Security Onion. This feature requires a license from Endgame.
     global: True
     advanced: True
-  push:
-    enabled:
-      description: Master kill-switch for the active push feature. When disabled, rule and pillar changes are picked up at the next scheduled highstate instead of being pushed immediately.
-      forcedType: bool
-      helpLink: push
-      global: True
-    highstate_interval_hours:
-      description: How often every minion in the grid runs a scheduled state.highstate, in hours. Lower values keep minions closer in sync at the cost of more load; higher values reduce load but increase worst-case latency for non-pushed changes. The salt-minion health check restarts a minion if its last highstate is older than this value plus one hour.
-      forcedType: int
-      helpLink: push
-      global: True
-      advanced: True
-    debounce_seconds:
-      description: Trailing-edge debounce window in seconds. A push intent must be quiet for this long before the drainer dispatches. Rapid bursts of edits within this window coalesce into one dispatch.
-      forcedType: int
-      helpLink: push
-      global: True
-      advanced: True
-    drain_interval:
-      description: How often the push drainer checks for ready intents, in seconds. Small values lower dispatch latency at the cost of more background work on the manager.
-      forcedType: int
-      helpLink: push
-      global: True
-      advanced: True
-    batch:
-      description: "Host batch size for push orchestrations. A number (e.g. '10') or a percentage (e.g. '25%'). Limits how many minions run the push state at once so large fleets don't thundering-herd."
-      helpLink: push
-      global: True
-      advanced: True
-      regex: '^([0-9]+%?)$'
-      regexFailureMessage: Enter a whole number or a whole-number percentage (e.g. 10 or 25%).
-    batch_wait:
-      description: Seconds to wait between host batches in a push orchestration. Gives the fleet time to breathe between waves.
-      forcedType: int
-      helpLink: push
-      global: True
-      advanced: True
 

salt/hydra/enabled.sls

@@ -58,7 +58,6 @@ so-hydra:
       - {{ ULIMIT.name }}={{ ULIMIT.soft }}:{{ ULIMIT.hard }}
     {%   endfor %}
     {% endif %}
-    # Intentionally unless-stopped -- matches the fleet default.
     - restart_policy: unless-stopped
     - watch:
       - file: hydraconfig

salt/idh/enabled.sls

@@ -15,7 +15,6 @@ include:
 so-idh:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-idh:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - name: so-idh
     - detach: True
     - network_mode: host

salt/influxdb/enabled.sls

@@ -18,7 +18,6 @@ include:
 so-influxdb:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-influxdb:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: influxdb
     - networks:
       - sobridge:

salt/influxdb/ssl.sls

@@ -34,7 +34,8 @@ influxdb_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/influxdb.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/kafka/enabled.sls

@@ -27,7 +27,6 @@ include:
 so-kafka:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-kafka:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: so-kafka
     - name: so-kafka
     - networks:

salt/kafka/ssl.sls

@@ -38,7 +38,8 @@ kafka_client_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/kafka-client.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -86,7 +87,8 @@ kafka_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/kafka.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -148,7 +150,8 @@ kafka_logstash_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/kafka-logstash.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/kibana/defaults.yaml

@@ -22,7 +22,7 @@ kibana:
           - default
           - file
     migrations:
-      discardCorruptObjects: "9.3.3"
+      discardCorruptObjects: "9.3.7"
     telemetry:
       enabled: False
     xpack:

salt/kibana/enabled.sls

@@ -17,7 +17,6 @@ include:
 so-kibana:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-kibana:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: kibana
     - user: "932:0"
     - networks:
@@ -70,7 +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/kratos/enabled.sls

@@ -51,7 +51,6 @@ so-kratos:
       - {{ ULIMIT.name }}={{ ULIMIT.soft }}:{{ ULIMIT.hard }}
     {%   endfor %}
     {% endif %}
-    # Intentionally unless-stopped -- matches the fleet default.
     - restart_policy: unless-stopped
     - watch:
       - file: kratosschema

salt/logstash/enabled.sls

@@ -28,7 +28,6 @@ include:
 so-logstash:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-logstash:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: so-logstash
     - name: so-logstash
     - networks:

salt/logstash/ssl.sls

@@ -38,7 +38,8 @@ etc_elasticfleet_logstash_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/elasticfleet-logstash.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -99,7 +100,8 @@ etc_elasticfleetlumberjack_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/elasticfleet-lumberjack.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -168,7 +170,8 @@ etc_filebeat_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/filebeat.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30
@@ -249,7 +252,8 @@ conf_filebeat_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /opt/so/conf/filebeat/etc/pki/filebeat.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/manager/beacons.sls

@@ -1,21 +0,0 @@
-{% from 'vars/globals.map.jinja' import GLOBALS %}
-{% from 'global/map.jinja' import GLOBALMERGED %}
-
-include:
-  - salt.minion
-
-{% if GLOBALS.is_manager and GLOBALMERGED.push.enabled %}
-salt_beacons_pushstate:
-  file.managed:
-    - name: /etc/salt/minion.d/beacons_pushstate.conf
-    - source: salt://manager/files/beacons_pushstate.conf.jinja
-    - template: jinja
-    - watch_in:
-      - service: salt_minion_service
-{% else %}
-salt_beacons_pushstate:
-  file.absent:
-    - name: /etc/salt/minion.d/beacons_pushstate.conf
-    - watch_in:
-      - service: salt_minion_service
-{% endif %}

salt/manager/files/beacons_pushstate.conf.jinja

@@ -1,41 +0,0 @@
-{% from 'global/map.jinja' import GLOBALMERGED %}
-beacons:
-  pillar_db:
-    - interval: {{ GLOBALMERGED.push.drain_interval }}
-    - disable_during_state_run: True
-  inotify:
-    - disable_during_state_run: True
-    - coalesce: True
-    - files:
-        /opt/so/saltstack/local/salt/suricata/rules:
-          mask:
-            - close_write
-            - moved_to
-            - delete
-          recurse: True
-          auto_add: True
-          exclude:
-            - '\.sw[a-z]$':
-                regex: True
-            - '~$':
-                regex: True
-            - '/4913$':
-                regex: True
-            - '/\.#':
-                regex: True
-        /opt/so/saltstack/local/salt/strelka/rules/compiled:
-          mask:
-            - close_write
-            - moved_to
-            - delete
-          recurse: True
-          auto_add: True
-          exclude:
-            - '\.sw[a-z]$':
-                regex: True
-            - '~$':
-                regex: True
-            - '/4913$':
-                regex: True
-            - '/\.#':
-                regex: True

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

@@ -11,3 +11,8 @@ name=Security Onion Repo repo
 mirrorlist=file:///opt/so/conf/reposync/mirror.txt
 enabled=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

@@ -15,7 +15,6 @@ include:
   - manager.elasticsearch
   - manager.kibana
   - manager.managed_soc_annotations
-  - manager.beacons
 
 repo_log_dir:
   file.directory:
@@ -87,6 +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
@@ -123,6 +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:
@@ -232,7 +260,6 @@ surifiltersrules:
     - user: 939
     - group: 939
 
-
 {% else %}
 
 {{sls}}_state_not_allowed:

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

@@ -1,232 +0,0 @@
-#!/opt/saltstack/salt/bin/python3
-
-# 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-push-drainer
-===============
-
-Scheduled drainer for the active-push feature. Runs on the manager every
-drain_interval seconds (default 15) via a salt schedule in salt/schedule.sls.
-
-For each intent file under /opt/so/state/push_pending/*.json whose last_touch
-is older than debounce_seconds, this script:
-  * concatenates the actions lists from every ready intent
-  * dedupes by (state or __highstate__, tgt, tgt_type)
-  * dispatches a single `salt-run state.orchestrate orch.push_batch --async`
-    with the deduped actions list passed as pillar kwargs
-  * deletes the contributed intent files on successful dispatch
-
-Reactor sls files (push_suricata, push_strelka, push_pillar) write intents
-but never dispatch directly -- see plan
-/home/mreeves/.claude/plans/goofy-marinating-hummingbird.md for the full design.
-"""
-
-import fcntl
-import glob
-import json
-import logging
-import logging.handlers
-import os
-import subprocess
-import sys
-import time
-
-import salt.client
-
-PENDING_DIR = '/opt/so/state/push_pending'
-LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
-LOG_FILE = '/opt/so/log/salt/so-push-drainer.log'
-
-HIGHSTATE_SENTINEL = '__highstate__'
-
-
-def _make_logger():
-    logger = logging.getLogger('so-push-drainer')
-    logger.setLevel(logging.INFO)
-    if not logger.handlers:
-        os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True)
-        handler = logging.handlers.RotatingFileHandler(
-            LOG_FILE, maxBytes=5 * 1024 * 1024, backupCount=3,
-        )
-        handler.setFormatter(logging.Formatter(
-            '%(asctime)s | %(levelname)s | %(message)s',
-        ))
-        logger.addHandler(handler)
-    return logger
-
-
-def _load_push_cfg():
-    """Read the global:push pillar subtree via salt-call. Returns a dict."""
-    caller = salt.client.Caller()
-    cfg = caller.cmd('pillar.get', 'global:push', {})
-    return cfg if isinstance(cfg, dict) else {}
-
-
-def _read_intent(path, log):
-    try:
-        with open(path, 'r') as f:
-            return json.load(f)
-    except (IOError, ValueError) as exc:
-        log.warning('cannot read intent %s: %s', path, exc)
-        return None
-    except Exception:
-        log.exception('unexpected error reading %s', path)
-        return None
-
-
-def _dedupe_actions(actions):
-    seen = set()
-    deduped = []
-    for action in actions:
-        if not isinstance(action, dict):
-            continue
-        state_key = HIGHSTATE_SENTINEL if action.get('highstate') else action.get('state')
-        tgt = action.get('tgt')
-        tgt_type = action.get('tgt_type', 'compound')
-        if not state_key or not tgt:
-            continue
-        key = (state_key, tgt, tgt_type)
-        if key in seen:
-            continue
-        seen.add(key)
-        deduped.append(action)
-    return deduped
-
-
-def _dispatch(actions, log):
-    pillar_arg = json.dumps({'actions': actions})
-    cmd = [
-        'salt-run',
-        'state.orchestrate',
-        'orch.push_batch',
-        'pillar={}'.format(pillar_arg),
-        '--async',
-    ]
-    log.info('dispatching: %s', ' '.join(cmd[:3]) + ' pillar=<{} actions>'.format(len(actions)))
-    try:
-        result = subprocess.run(
-            cmd, check=True, capture_output=True, text=True, timeout=60,
-        )
-    except subprocess.CalledProcessError as exc:
-        log.error('dispatch failed (rc=%s): stdout=%s stderr=%s',
-                  exc.returncode, exc.stdout, exc.stderr)
-        return False
-    except subprocess.TimeoutExpired:
-        log.error('dispatch timed out after 60s')
-        return False
-    except Exception:
-        log.exception('dispatch raised')
-        return False
-    log.info('dispatch accepted: %s', (result.stdout or '').strip())
-    return True
-
-
-def main():
-    log = _make_logger()
-
-    if not os.path.isdir(PENDING_DIR):
-        # Nothing to do; reactors create the dir on first use.
-        return 0
-
-    try:
-        push = _load_push_cfg()
-    except Exception:
-        log.exception('failed to read global:push pillar; aborting drain pass')
-        return 1
-
-    if not push.get('enabled', True):
-        log.debug('push disabled; exiting')
-        return 0
-
-    debounce_seconds = int(push.get('debounce_seconds', 30))
-
-    os.makedirs(PENDING_DIR, exist_ok=True)
-    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
-    try:
-        fcntl.flock(lock_fd, fcntl.LOCK_EX)
-
-        intent_files = [
-            p for p in sorted(glob.glob(os.path.join(PENDING_DIR, '*.json')))
-            if os.path.basename(p) != '.lock'
-        ]
-        if not intent_files:
-            return 0
-
-        now = time.time()
-        ready = []
-        skipped = 0
-        broken = []
-        for path in intent_files:
-            intent = _read_intent(path, log)
-            if not isinstance(intent, dict):
-                broken.append(path)
-                continue
-            last_touch = intent.get('last_touch', 0)
-            if now - last_touch < debounce_seconds:
-                skipped += 1
-                continue
-            ready.append((path, intent))
-
-        for path in broken:
-            try:
-                os.unlink(path)
-            except OSError:
-                pass
-
-        if not ready:
-            if skipped:
-                log.debug('no ready intents (%d still in debounce window)', skipped)
-            return 0
-
-        combined_actions = []
-        oldest_first_touch = now
-        all_paths = []
-        for path, intent in ready:
-            combined_actions.extend(intent.get('actions', []) or [])
-            first = intent.get('first_touch', now)
-            if first < oldest_first_touch:
-                oldest_first_touch = first
-            all_paths.extend(intent.get('paths', []) or [])
-
-        deduped = _dedupe_actions(combined_actions)
-        if not deduped:
-            log.warning('%d intent(s) had no usable actions; clearing', len(ready))
-            for path, _ in ready:
-                try:
-                    os.unlink(path)
-                except OSError:
-                    pass
-            return 0
-
-        debounce_duration = now - oldest_first_touch
-        log.info(
-            'draining %d intent(s): %d action(s) after dedupe (raw=%d), '
-            'debounce_duration=%.1fs, paths=%s',
-            len(ready), len(deduped), len(combined_actions),
-            debounce_duration, all_paths[:20],
-        )
-
-        if not _dispatch(deduped, log):
-            log.warning('dispatch failed; leaving intent files in place for retry')
-            return 1
-
-        for path, _ in ready:
-            try:
-                os.unlink(path)
-            except OSError:
-                log.exception('failed to remove drained intent %s', path)
-
-        return 0
-    finally:
-        try:
-            fcntl.flock(lock_fd, fcntl.LOCK_UN)
-        finally:
-            os.close(lock_fd)
-
-
-if __name__ == '__main__':
-    sys.exit(main())

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

@@ -12,7 +12,17 @@
 UPDATE_DIR=/tmp/sogh/securityonion
 DEFAULT_SALT_DIR=/opt/so/saltstack/default
 INSTALLEDVERSION=$(cat /etc/soversion)
+# /etc/sopostversion is a soup-owned marker (no salt state manages it) tracking how
+# far the post-upgrade walk has progressed. Its presence means a prior upgrade did
+# not finish its post-upgrade steps; its contents are the resume point. It is read
+# here before preupgrade_changes mutates INSTALLEDVERSION and before any highstate
+# stamps /etc/soversion from the pillar.
+POSTVERSION_FILE=/etc/sopostversion
+if [ -f "$POSTVERSION_FILE" ]; then
+  POSTVERSION=$(cat "$POSTVERSION_FILE")
+else
   POSTVERSION=$INSTALLEDVERSION
+fi
 INSTALLEDSALTVERSION=$(salt --versions-report | grep Salt: | awk '{print $2}')
 BATCHSIZE=5
 SOUP_LOG=/root/soup.log
@@ -23,6 +33,10 @@ NOTIFYCUSTOMELASTICCONFIG=false
 TOPFILE=/opt/so/saltstack/default/salt/top.sls
 BACKUPTOPFILE=/opt/so/saltstack/default/salt/top.sls.backup
 SALTUPGRADED=false
+# Set true once soup begins modifying the system (past the pre-flight checks), so the
+# EXIT trap can tell the user the update did not finish and must be re-run. Only the
+# pre-flight gates (ES compatibility, disk, network) fail before this is set.
+SOUP_UPGRADE_STARTED=false
 SALT_CLOUD_INSTALLED=false
 SALT_CLOUD_CONFIGURED=false
 # Check if salt-cloud is installed
@@ -123,6 +137,28 @@ check_err() {
 
     echo "SOUP XTRACE debug log (if enabled) at $SOUP_DEBUG_LOG. Re-run soup with SOUP_DEBUG=1 to create $SOUP_DEBUG_LOG"
 
+    # If soup had already started modifying the system, make it unmistakable that the
+    # update is incomplete and must be re-run. soup is resumable: a version upgrade
+    # picks up from the /etc/sopostversion marker, and a hotfix re-applies because
+    # /etc/sohotfix is only advanced after a successful highstate.
+    if [[ "$SOUP_UPGRADE_STARTED" == "true" ]]; then
+      echo ""
+      echo "=============================================================================="
+      echo " UPGRADE INCOMPLETE"
+      echo "=============================================================================="
+      echo " This soup run did NOT finish. Your Security Onion installation may be in a"
+      echo " partially-updated state and is not yet fully upgraded."
+      echo ""
+      echo " Review the error above and $SOUP_LOG, resolve the underlying problem, then"
+      echo " run soup again to resume and complete the update:"
+      echo ""
+      echo "     sudo soup"
+      echo ""
+      echo " soup is resumable -- re-running it continues from where this run stopped."
+      echo "=============================================================================="
+      echo ""
+    fi
+
     exit $exit_code
   fi
 
@@ -245,6 +281,7 @@ 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
@@ -290,6 +327,30 @@ check_pillar_items() {
   fi
 }
 
+check_cluster_health() {
+  echo "Checking Elasticsearch cluster health."
+  # Require a 'green' cluster before upgrading; anything less (yellow, red, or
+  # unreachable) blocks. Modeled on the wait used in so-elasticsearch-roles-load.
+  if so-elasticsearch-query "_cluster/health?wait_for_status=green&timeout=120s" --fail > /dev/null 2>&1; then
+    printf "\nThe Elasticsearch cluster is healthy (green). We can proceed with SOUP.\n\n"
+  else
+    printf "\nThe Elasticsearch cluster is not green. Please resolve the cluster health issue so the cluster is green before running SOUP again.\n\n"
+    exit 0
+  fi
+}
+
+check_fleet_server() {
+  echo "Checking that Elastic Fleet Server is responding."
+  # Modeled on the wait_for_so-elastic-fleet state check in elasticfleet/enabled.sls,
+  # which waits for HTTP 200 from the Fleet Server status API.
+  if curl -sk --fail --retry 3 --retry-delay 10 --max-time 30 "https://localhost:8220/api/status" > /dev/null 2>&1; then
+    printf "\nElastic Fleet Server is responding. We can proceed with SOUP.\n\n"
+  else
+    printf "\nElastic Fleet Server is not responding at https://localhost:8220/api/status. Please ensure Elastic Fleet is healthy before running SOUP again.\n\n"
+    exit 0
+  fi
+}
+
 check_saltmaster_status() {
   set +e
   echo "Waiting on the Salt Master service to be ready."
@@ -413,6 +474,13 @@ preupgrade_changes() {
     true
 }
 
+set_postversion() {
+    # Persist post-upgrade walk progress so an interrupted upgrade can resume the
+    # remaining steps on the next soup run (see /etc/sopostversion handling).
+    POSTVERSION="$1"
+    echo "$POSTVERSION" > "$POSTVERSION_FILE"
+}
+
 postupgrade_changes() {
     # This function is to add any new pillar items if needed.
     echo "Running post upgrade processes."
@@ -420,6 +488,8 @@ postupgrade_changes() {
     [[ "$POSTVERSION" =~ ^2\.4\.21[0-9]+$ ]] && post_to_3.0.0
     [[ "$POSTVERSION" == "3.0.0" ]] && post_to_3.1.0
     [[ "$POSTVERSION" == "3.1.0" ]] && post_to_3.2.0
+    # All applicable post-upgrade steps completed; clear the resume marker.
+    rm -f "$POSTVERSION_FILE"
     true
 }
 
@@ -512,7 +582,7 @@ post_to_3.0.0() {
   # convert yes/no in suricata pillars to true/false
   convert_suricata_yes_no
 
-  POSTVERSION=3.0.0
+  set_postversion 3.0.0
 }
 
 ### 3.0.0 End ###
@@ -739,7 +809,6 @@ fix_logstash_0013_lumberjack_pipeline_name() {
 up_to_3.1.0() {
   ensure_postgres_local_pillar
   ensure_postgres_secret
-  determine_elastic_agent_upgrade
   elasticsearch_backup_index_templates
   # Clear existing component template state file.
   rm -f /opt/so/state/esfleet_component_templates.json
@@ -776,19 +845,30 @@ post_to_3.1.0() {
   # Check for unhealthy / unauthorized integration transform jobs and attempt reauthorizations
   check_transform_health_and_reauthorize || true
 
-  POSTVERSION=3.1.0
+  set_postversion 3.1.0
 }
 
 ### 3.1.0 End ###
 
 ### 3.2.0 Scripts ###
 
+recollate_postgres() {
+  echo ""
+  echo "Recollating PostgreSQL databases. The following output may contain warnings about a version mismatch, followed by a note indicating that the collation version has been changed."
+  for db in postgres securityonion so_telegraf; do
+    docker exec so-postgres psql -U postgres $db -c "reindex database $db"
+    docker exec so-postgres psql -U postgres $db -c "alter database $db refresh collation version"
+  done
+  echo "Recollating PostgreSQL databases complete."
+  echo ""
+}
+
 bootstrap_so_soc_database() {
   # init-db.sh is mounted into so-postgres at /docker-entrypoint-initdb.d/init-db.sh
   # and runs automatically only on a fresh data directory. Hosts upgrading from
   # 3.1.0 already have /nsm/postgres populated, so the so_soc bootstrap block
   # added in 3.2 never fires. Re-run the script explicitly; it's idempotent.
-  echo "Bootstrapping so_soc database via init-db.sh."
+  echo "Bootstrapping database via init-db.sh."
   # The postgres image has no USER directive, so `docker exec` defaults to
   # root, and the container env intentionally omits POSTGRES_USER (the upstream
   # entrypoint defaults it transiently during first-init only). Recreate both
@@ -799,10 +879,13 @@ bootstrap_so_soc_database() {
     return 0
   fi
   if ! $exec_cmd; then
-    FINAL_MESSAGE_QUEUE+=("WARNING: init-db.sh failed inside so-postgres during the 3.2.0 upgrade; the so_soc database may not have been bootstrapped. Re-run manually: $exec_cmd")
+    FINAL_MESSAGE_QUEUE+=("WARNING: init-db.sh failed inside so-postgres during the 3.2.0 upgrade; the database may not have been bootstrapped. Re-run manually: $exec_cmd")
     return 0
   fi
-  echo "so_soc bootstrap complete."
+  echo "Database bootstrap complete."
+
+  echo "Restarting so-soc container to pick up database changes"
+  docker restart so-soc
 }
 
 # Existing grids should keep ILM unless an admin explicitly opts in to DLM.
@@ -850,7 +933,32 @@ 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() {
+  # download 9.3.7 elastic agent packages
+  determine_elastic_agent_upgrade
+
   fix_logstash_0013_lumberjack_pipeline_name
 
   pin_elasticsearch_data_retention_method
@@ -859,15 +967,20 @@ up_to_3.2.0() {
 }
 
 post_to_3.2.0() {
+  # Recollate due to image OS rebase
+  recollate_postgres
+
   bootstrap_so_soc_database
 
-  # Including agent regen script here since it was missed in post_to_3.1.0
+  # Generate 9.3.7 elastic agent installers
   echo "Regenerating Elastic Agent Installers"
   /sbin/so-elastic-agent-gen-installers
 
   kibana_backport_streams_index_template
 
-  POSTVERSION=3.2.0
+  update_kafka_metadata "4.3"
+
+  set_postversion 3.2.0
 }
 
 ### 3.2.0 End ###
@@ -980,13 +1093,19 @@ 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"
+  echo "Syncing new updates to /nsm/repo & /nsm/kernelrepo"
-  rsync -a $AGREPO/* /nsm/repo/
+  # Airgap soup copies new files into the local repo, but doesn't remove old packages. Retaining the ability to rollback package updates
-  echo "Creating repo"
+  rsync -a "$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() {
@@ -1013,8 +1132,20 @@ upgrade_check() {
   fi
   [[ -f /etc/sohotfix ]] && CURRENTHOTFIX=$(cat /etc/sohotfix)
   if [ "$INSTALLEDVERSION" == "$NEWVERSION" ]; then
+    # A leftover post-version marker means a previous upgrade to this version
+    # advanced /etc/soversion (the highstate stamps it from the pillar) but did not
+    # finish its post-upgrade steps. Resume the upgrade instead of reporting "latest".
+    if [ -f "$POSTVERSION_FILE" ] && [ "$(cat "$POSTVERSION_FILE")" != "$NEWVERSION" ]; then
+      echo "A previous upgrade to $NEWVERSION did not complete its post-upgrade steps; resuming."
+      is_hotfix=false
+      return 0
+    fi
     echo "Checking to see if there are hotfixes needed"
     if [ "$HOTFIXVERSION" == "$CURRENTHOTFIX" ]; then
+      # Reaching here means we are at the target version and NOT resuming (the resume
+      # check above returned otherwise). Clear any stale resume marker so a completed
+      # upgrade is never mistaken for a partial one and re-run on a later invocation.
+      rm -f "$POSTVERSION_FILE"
       echo "You are already running the latest version of Security Onion."
       exit 0
     else
@@ -1126,7 +1257,8 @@ verify_es_version_compatibility() {
         ["8.18.4"]="8.18.6 8.18.8 9.0.8"
 	    ["8.18.6"]="8.18.8 9.0.8"
 	    ["8.18.8"]="9.0.8"
-        ["9.0.8"]="9.3.3"
+        ["9.0.8"]="9.3.3 9.3.7"
+        ["9.3.3"]="9.3.7"
     )
 
     # Elasticsearch MUST upgrade through these versions
@@ -1709,6 +1841,15 @@ main() {
   set_minionid
   MINION_ROLE=$(lookup_role)
   echo "Found that Security Onion $INSTALLEDVERSION is currently installed."
+  # /etc/soversion is stamped to the target version before the upgrade fully
+  # completes, so a lingering resume marker means this grid is only partially
+  # upgraded even though the line above shows the target version. Make that explicit
+  # so it is not mistaken for a finished upgrade.
+  if [ -f "$POSTVERSION_FILE" ] && [ "$(cat "$POSTVERSION_FILE")" != "$INSTALLEDVERSION" ]; then
+    echo ""
+    echo "NOTE: A previous upgrade to $INSTALLEDVERSION did not finish. This grid is"
+    echo "      partially upgraded and this soup run will resume and complete it."
+  fi
   echo ""
   check_minimum_version
 
@@ -1737,12 +1878,18 @@ main() {
   echo "Verifying Elasticsearch version compatibility across the grid before upgrading."
   verify_es_version_compatibility
 
+  # Pre-flight health checks: confirm the grid is in a good state before we change
+  # anything. These run before any modifications, so a failure exits cleanly and the
+  # operator can fix the issue and re-run soup.
+  check_cluster_health
+  check_fleet_server
+
   echo "Checking for Salt Master and Minion updates."
   upgrade_check_salt
   set -e
 
   if [[ $is_airgap -eq 0 ]]; then
-    update_airgap_repo
+    update_airgap_repos
     dnf clean all
     check_os_updates
   elif [[ $OS == 'oracle' ]]; then
@@ -1753,6 +1900,7 @@ main() {
   fi
 
   if [ "$is_hotfix" == "true" ]; then
+    SOUP_UPGRADE_STARTED=true
     echo "Applying $HOTFIXVERSION hotfix"
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
     if [[ ! "$MINION_ROLE" == "import" ]]; then
@@ -1763,10 +1911,16 @@ main() {
     create_local_directories "/opt/so/saltstack/default"
     apply_hotfix
     echo "Hotfix applied"
-    update_version
     enable_highstate
     highstate
+    # Record the hotfix only after the highstate succeeds. /etc/sohotfix is written
+    # solely by soup (no salt state manages it), so deferring the write means a failed
+    # hotfix highstate leaves the old hotfix value and re-running soup re-applies it,
+    # rather than reporting "already latest". The soversion/pillar writes in
+    # update_version are no-ops here since the version is unchanged for a hotfix.
+    update_version
   else
+    SOUP_UPGRADE_STARTED=true
     echo ""
     echo "Performing upgrade from Security Onion $INSTALLEDVERSION to Security Onion $NEWVERSION."
     echo ""
@@ -1822,6 +1976,10 @@ main() {
     copy_new_files
     echo ""
     create_local_directories "/opt/so/saltstack/default"
+    # Seed the resume marker before the highstate stamps /etc/soversion to the new
+    # version, so an interrupted upgrade is detectable as "not finished" on re-run.
+    # POSTVERSION still holds the pre-upgrade (or prior resume) version here.
+    [ -f "$POSTVERSION_FILE" ] || echo "$POSTVERSION" > "$POSTVERSION_FILE"
     update_version
 
     echo ""
@@ -1850,9 +2008,6 @@ main() {
 
     enable_highstate
 
-    echo "salt-call state.show_top"
-    salt-call state.show_top
-
     echo ""
     echo "Running a highstate. This could take several minutes."
     set +e
@@ -1860,9 +2015,6 @@ main() {
     highstate
     set -e
 
-    echo "salt-call saltutil.running"
-    salt-call saltutil.running
-
     stop_salt_master
 
     masterunlock
@@ -1885,9 +2037,6 @@ main() {
     # ensure the mine is updated and populated before highstates run, following the salt-master restart
     update_salt_mine
 
-    echo "salt-call state.show_top"
-    salt-call state.show_top
-
     highstate
     check_saltmaster_status
     postupgrade_changes

salt/nginx/enabled.sls

@@ -34,7 +34,6 @@ make-rule-dir-nginx:
 so-nginx:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-nginx:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: so-nginx
     - networks:
       - sobridge:
@@ -60,6 +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;
@@ -389,7 +399,7 @@ http {
 		error_page 429 = @error429;
 
 		location @error401 {
-			if ($request_uri ~* (^/api/.*|^/connect/.*|^/oauth2/.*|^/.*\.map$)) {
+			if ($request_uri ~* (^.*/api/.*|^/connect/.*|^/oauth2/.*|^/.*\.map$)) {
 				return    401;
 			}
 

salt/nginx/ssl.sls

@@ -71,7 +71,8 @@ managerssl_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/managerssl.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/orch/push_batch.sls

@@ -1,37 +0,0 @@
-{% from 'global/map.jinja' import GLOBALMERGED %}
-{% set actions = salt['pillar.get']('actions', []) %}
-{% set BATCH = GLOBALMERGED.push.batch %}
-{% set BATCH_WAIT = GLOBALMERGED.push.batch_wait %}
-
-{% for action in actions %}
-{%   if action.get('highstate') %}
-apply_highstate_{{ loop.index }}:
-  salt.state:
-    - tgt: '{{ action.tgt }}'
-    - tgt_type: {{ action.get('tgt_type', 'compound') }}
-    - highstate: True
-    - batch: {{ action.get('batch', BATCH) }}
-    - batch_wait: {{ action.get('batch_wait', BATCH_WAIT) }}
-    - kwarg:
-        queue: 2
-{%   else %}
-refresh_pillar_{{ loop.index }}:
-  salt.function:
-    - name: saltutil.refresh_pillar
-    - tgt: '{{ action.tgt }}'
-    - tgt_type: {{ action.get('tgt_type', 'compound') }}
-
-apply_{{ action.state | replace('.', '_') }}_{{ loop.index }}:
-  salt.state:
-    - tgt: '{{ action.tgt }}'
-    - tgt_type: {{ action.get('tgt_type', 'compound') }}
-    - sls:
-      - {{ action.state }}
-    - batch: {{ action.get('batch', BATCH) }}
-    - batch_wait: {{ action.get('batch_wait', BATCH_WAIT) }}
-    - kwarg:
-        queue: 2
-    - require:
-      - salt: refresh_pillar_{{ loop.index }}
-{%   endif %}
-{% endfor %}

salt/postgres/ssl.sls

@@ -33,7 +33,8 @@ postgres_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/postgres.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/reactor/pillar_push_map.yaml

@@ -1,240 +0,0 @@
-# One pillar directory can map to multiple (state, tgt) actions.
-# tgt is a raw salt compound expression. tgt_type is always "compound".
-# Per-action `batch` / `batch_wait` override the orch defaults (25% / 15s).
-# An action with `highstate: True` triggers state.highstate instead of
-# state.apply -- see salt/orch/push_batch.sls.
-#
-# Notes:
-#   - `bpf` is a pillar-only dir (no state of its own) consumed by both
-#     zeek and suricata via macros, so a bpf pillar change re-applies both.
-#   - suricata/strelka/zeek/elasticsearch/redis/kafka/logstash etc. have
-#     their own pillar dirs AND their own state, so they map 1:1 (or 1:2
-#     in strelka's case, because of the split init.sls / manager.sls).
-#
-# Intentional omissions (these will log a "not in pillar_push_map.yaml"
-# warning in push_pillar.sls and wait for the next scheduled highstate):
-#   - `data` and `node_data`: pillar-only data consumed by many states;
-#     handling them generically would amount to a fleetwide highstate.
-#   - `host`: soc_host describes mainint/mainip; a change is a re-IP and
-#     needs a coordinated procedure, not an immediate state push.
-#   - `hypervisor`: state changes touch libvirt and are disruptive; leave
-#     to the next scheduled highstate.
-#   - `sensor`: every field in soc_sensor.yaml is `readonly: True` or
-#     per-minion (`node: True`). Per-minion edits are persisted under
-#     pillar/minions/<id>.sls and are handled by Branch A of push_pillar.sls
-#     (per-minion highstate intent), not by this app-pillar map.
-#
-# The role sets here were verified line-by-line against salt/top.sls. If
-# salt/top.sls changes how an app is targeted, update the corresponding
-# compound here.
-
-# firewall: the one pillar everyone touches. Applied everywhere intentionally
-# because every host's iptables needs to know about every other host in the
-# grid. Salt's firewall state is idempotent (file.managed + iptables-restore
-# onchanges in salt/firewall/init.sls), so hosts whose rendered firewall is
-# unchanged do a file comparison and no-op without touching iptables -- actual
-# reload happens only on the hosts whose rules actually changed. Fleetwide
-# blast radius is intentional and matches the pre-plan behavior via highstate.
-# Adding N sensors in a burst coalesces into one dispatch via the drainer.
-firewall:
-  - state: firewall
-    tgt: '*'
-
-# backup: backup.config_backup runs on eval, standalone, manager, managerhype,
-# managersearch (NOT import -- the backup pillar is included on import per
-# pillar/top.sls but the backup state is not run there per salt/top.sls).
-backup:
-  - state: backup.config_backup
-    tgt: 'G@role:so-eval or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# bpf is pillar-only (no state); consumed by both zeek and suricata as macros.
-# Both states run on sensor_roles + so-import per salt/top.sls.
-bpf:
-  - state: zeek
-    tgt: 'G@role:so-eval or G@role:so-heavynode or G@role:so-import or G@role:so-sensor or G@role:so-standalone'
-  - state: suricata
-    tgt: 'G@role:so-eval or G@role:so-heavynode or G@role:so-import or G@role:so-sensor or G@role:so-standalone'
-
-# ca is applied universally.
-ca:
-  - state: ca
-    tgt: '*'
-
-# docker: universal. The docker state is in both the all-non-managers and
-# all-managers branches of salt/top.sls.
-docker:
-  - state: docker
-    tgt: '*'
-
-# elastalert: eval, standalone, manager, managerhype, managersearch (NOT import).
-elastalert:
-  - state: elastalert
-    tgt: 'G@role:so-eval or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# elastic-fleet-package-registry: manager_roles exactly.
-elastic-fleet-package-registry:
-  - state: elastic-fleet-package-registry
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# elasticsearch: 8 roles.
-elasticsearch:
-  - state: elasticsearch
-    tgt: 'G@role:so-eval or G@role:so-heavynode or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-searchnode or G@role:so-standalone'
-
-# elasticagent: so-heavynode only.
-elasticagent:
-  - state: elasticagent
-    tgt: 'G@role:so-heavynode'
-
-# elasticfleet: base state only on pillar change. elasticfleet.install_agent_grid
-# is a deploy/enrollment step, not a config reload; leave it to the next highstate.
-elasticfleet:
-  - state: elasticfleet
-    tgt: 'G@role:so-eval or G@role:so-fleet or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# global: fanout to a fleetwide highstate. The global pillar (soc_global.sls)
-# carries cross-cutting settings (pipeline, url_base, imagerepo, mdengine, ...)
-# that are consumed by virtually every state, so a targeted re-apply isn't
-# meaningful. The drainer's batch/batch_wait throttling controls blast radius.
-global:
-  - highstate: True
-    tgt: '*'
-
-# healthcheck: eval, sensor, standalone only.
-healthcheck:
-  - state: healthcheck
-    tgt: 'G@role:so-eval or G@role:so-sensor or G@role:so-standalone'
-
-# hydra: manager_roles exactly.
-hydra:
-  - state: hydra
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# idh: so-idh only.
-idh:
-  - state: idh
-    tgt: 'G@role:so-idh'
-
-# influxdb: manager_roles exactly.
-influxdb:
-  - state: influxdb
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# kafka: standalone, manager, managerhype, managersearch, searchnode, receiver.
-kafka:
-  - state: kafka
-    tgt: 'G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-receiver or G@role:so-searchnode or G@role:so-standalone'
-
-# kibana: manager_roles exactly.
-kibana:
-  - state: kibana
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# kratos: manager_roles exactly.
-kratos:
-  - state: kratos
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# logrotate: universal (top-of-file '*' branch in salt/top.sls).
-logrotate:
-  - state: logrotate
-    tgt: '*'
-
-# logstash: 8 roles, no eval/import.
-logstash:
-  - state: logstash
-    tgt: 'G@role:so-fleet or G@role:so-heavynode or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-receiver or G@role:so-searchnode or G@role:so-standalone'
-
-# manager: manager_roles exactly. The manager state is also referenced under
-# *_sensor / *_heavynode top.sls blocks via `sensor`, but the standalone
-# `manager` state itself runs only on manager_roles.
-manager:
-  - state: manager
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# nginx: 10 specific roles. NOT receiver, idh, hypervisor, desktop.
-nginx:
-  - state: nginx
-    tgt: 'G@role:so-eval or G@role:so-fleet or G@role:so-heavynode or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-searchnode or G@role:so-sensor or G@role:so-standalone'
-
-# ntp: universal (top-of-file '*' branch in salt/top.sls).
-ntp:
-  - state: ntp
-    tgt: '*'
-
-# patch: universal. soc_patch carries the OS update schedule, applied via
-# patch.os.schedule on every node (it's in both the all-non-managers and
-# all-managers branches of salt/top.sls).
-patch:
-  - state: patch.os.schedule
-    tgt: '*'
-
-# postgres: manager_roles exactly.
-postgres:
-  - state: postgres
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# redis: 6 roles. standalone, manager, managerhype, managersearch, heavynode, receiver.
-# (NOT eval, NOT import, NOT searchnode.)
-redis:
-  - state: redis
-    tgt: 'G@role:so-heavynode or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-receiver or G@role:so-standalone'
-
-# registry: manager_roles exactly.
-registry:
-  - state: registry
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# sensoroni: universal.
-sensoroni:
-  - state: sensoroni
-    tgt: '*'
-
-# soc: manager_roles exactly.
-soc:
-  - state: soc
-    tgt: 'G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
-
-# stig: broad. Runs on standalone, manager, managerhype, managersearch,
-# searchnode, sensor, receiver, fleet, hypervisor, desktop.
-# NOT eval, NOT import, NOT heavynode, NOT idh (the *_idh block in
-# salt/top.sls intentionally omits stig).
-stig:
-  - state: stig
-    tgt: 'G@role:so-desktop or G@role:so-fleet or G@role:so-hypervisor or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-receiver or G@role:so-searchnode or G@role:so-sensor or G@role:so-standalone'
-
-# strelka: sensor-side only on pillar change (sensor_roles). strelka.manager is
-# intentionally NOT fired on pillar changes -- YARA rule and strelka config
-# pillar changes are consumed by the sensor-side strelka backend, and re-running
-# strelka.manager on managers is both unnecessary and disruptive. strelka.manager
-# is left to the 2-hour highstate.
-strelka:
-  - state: strelka
-    tgt: 'G@role:so-eval or G@role:so-heavynode or G@role:so-sensor or G@role:so-standalone'
-
-# suricata: sensor_roles + so-import (5 roles).
-suricata:
-  - state: suricata
-    tgt: 'G@role:so-eval or G@role:so-heavynode or G@role:so-import or G@role:so-sensor or G@role:so-standalone'
-
-# telegraf: universal.
-telegraf:
-  - state: telegraf
-    tgt: '*'
-
-# versionlock: universal (top-of-file '*' branch in salt/top.sls).
-versionlock:
-  - state: versionlock
-    tgt: '*'
-
-# vm: libvirt-driver hypervisors only. Matched by the salt-cloud:driver:libvirt
-# grain (compound supports nested grain matching via G@<key>:<subkey>:<value>).
-# pillar/vm/soc_vm.sls write path is referenced at salt/_runners/setup_hypervisor.py:856.
-vm:
-  - state: vm
-    tgt: 'G@salt-cloud:driver:libvirt'
-
-# zeek: sensor_roles + so-import (5 roles).
-zeek:
-  - state: zeek
-    tgt: 'G@role:so-eval or G@role:so-heavynode or G@role:so-import or G@role:so-sensor or G@role:so-standalone'

salt/reactor/push_pillar.sls

@@ -1,176 +0,0 @@
-#!py
-
-# Reactor invoked by the pillar_db beacon when SOC records settings changes in
-# the so_soc.audit_settings table (see salt/_beacons/pillar_db.py). The beacon
-# emits one event per new row carrying setting_id and node_id.
-#
-# Two branches, keyed on node_id:
-#   A) node_id populated -> the change is scoped to that one minion. Look up the
-#      app in pillar_push_map.yaml and write an intent that runs the app's mapped
-#      state(s) targeted to just that node.
-#   B) node_id empty -> grid-wide app change. Look up the app in
-#      pillar_push_map.yaml and write an intent with the entry's actions as-is.
-#
-# The app name is the first dotted segment of setting_id (e.g. "telegraf.output"
-# -> "telegraf"), which matches the pillar_push_map.yaml keys 1:1.
-#
-# Reactors never dispatch directly. The so-push-drainer schedule picks up
-# ready intents, dedupes across pending files, and dispatches orch.push_batch.
-
-import fcntl
-import json
-import logging
-import os
-import time
-
-from salt.client import Caller
-import yaml
-
-LOG = logging.getLogger(__name__)
-
-PENDING_DIR = '/opt/so/state/push_pending'
-LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
-MAX_PATHS = 20
-
-# The pillar_push_map.yaml is shipped via salt:// but the reactor runs on the
-# master, which mounts the default saltstack tree at this path.
-PUSH_MAP_PATH = '/opt/so/saltstack/default/salt/reactor/pillar_push_map.yaml'
-
-_PUSH_MAP_CACHE = {'mtime': 0, 'data': None}
-
-
-def _load_push_map():
-    try:
-        st = os.stat(PUSH_MAP_PATH)
-    except OSError:
-        LOG.warning('push_pillar: %s not found', PUSH_MAP_PATH)
-        return {}
-    if _PUSH_MAP_CACHE['mtime'] != st.st_mtime:
-        try:
-            with open(PUSH_MAP_PATH, 'r') as f:
-                _PUSH_MAP_CACHE['data'] = yaml.safe_load(f) or {}
-        except Exception:
-            LOG.exception('push_pillar: failed to load %s', PUSH_MAP_PATH)
-            _PUSH_MAP_CACHE['data'] = {}
-        _PUSH_MAP_CACHE['mtime'] = st.st_mtime
-    return _PUSH_MAP_CACHE['data'] or {}
-
-
-def _push_enabled():
-    try:
-        caller = Caller()
-        return bool(caller.cmd('pillar.get', 'global:push:enabled', True))
-    except Exception:
-        LOG.exception('push_pillar: pillar.get global:push:enabled failed, assuming enabled')
-        return True
-
-
-def _write_intent(key, actions, path):
-    now = time.time()
-    try:
-        os.makedirs(PENDING_DIR, exist_ok=True)
-    except OSError:
-        LOG.exception('push_pillar: cannot create %s', PENDING_DIR)
-        return
-
-    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
-    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
-    try:
-        fcntl.flock(lock_fd, fcntl.LOCK_EX)
-
-        intent = {}
-        if os.path.exists(intent_path):
-            try:
-                with open(intent_path, 'r') as f:
-                    intent = json.load(f)
-            except (IOError, ValueError):
-                intent = {}
-
-        intent.setdefault('first_touch', now)
-        intent['last_touch'] = now
-        intent['actions'] = actions
-        paths = intent.get('paths', [])
-        if path and path not in paths:
-            paths.append(path)
-            paths = paths[-MAX_PATHS:]
-        intent['paths'] = paths
-
-        tmp_path = intent_path + '.tmp'
-        with open(tmp_path, 'w') as f:
-            json.dump(intent, f)
-        os.rename(tmp_path, intent_path)
-    except Exception:
-        LOG.exception('push_pillar: failed to write intent %s', intent_path)
-    finally:
-        try:
-            fcntl.flock(lock_fd, fcntl.LOCK_UN)
-        finally:
-            os.close(lock_fd)
-
-
-def _app_from_setting(setting_id):
-    # setting_id is e.g. 'telegraf.output' -> 'telegraf', 'ntp.config.servers' -> 'ntp'
-    if not setting_id:
-        return None
-    return setting_id.split('.', 1)[0] or None
-
-
-def _node_actions(entry, node_id):
-    # Copy the app's mapped actions but retarget each one to the single node.
-    # Preserves the state/highstate selection and any batch/batch_wait overrides.
-    actions = []
-    for action in entry:
-        if not isinstance(action, dict):
-            continue
-        node_action = dict(action)
-        node_action['tgt'] = node_id
-        node_action['tgt_type'] = 'glob'
-        actions.append(node_action)
-    return actions
-
-
-def run():
-    if not _push_enabled():
-        LOG.info('push_pillar: push disabled, skipping')
-        return {}
-
-    # The pillar_db beacon nests its payload under data['data']; fall back to the
-    # top level so the reactor is robust to either shape.
-    event = data.get('data', data)  # noqa: F821 -- data provided by reactor
-    setting_id = event.get('setting_id', '')
-    node_id = (event.get('node_id') or '').strip()
-
-    app = _app_from_setting(setting_id)
-    if not app:
-        LOG.debug('push_pillar: ignoring event with no app segment: setting_id=%s', setting_id)
-        return {}
-
-    push_map = _load_push_map()
-    entry = push_map.get(app)
-    if not entry:
-        LOG.warning(
-            'push_pillar: app "%s" is not in pillar_push_map.yaml; change will be '
-            'picked up at the next scheduled highstate (setting_id=%s)',
-            app, setting_id,
-        )
-        return {}
-
-    # Branch A: per-node change -> retarget the app's states to just that node.
-    if node_id:
-        actions = _node_actions(entry, node_id)
-        if not actions:
-            LOG.warning('push_pillar: no usable actions for app "%s" (setting_id=%s)', app, setting_id)
-            return {}
-        _write_intent(
-            'node_{}_{}'.format(node_id, app), actions,
-            'audit:{}@{}'.format(setting_id, node_id),
-        )
-        LOG.info('push_pillar: per-node intent updated for %s on %s (setting_id=%s)',
-                 app, node_id, setting_id)
-        return {}
-
-    # Branch B: grid-wide app change -> use the map entry's actions as-is.
-    actions = list(entry)  # copy to avoid mutating the cache
-    _write_intent('pillar_{}'.format(app), actions, 'audit:{}'.format(setting_id))
-    LOG.info('push_pillar: app intent updated for %s (setting_id=%s)', app, setting_id)
-    return {}

salt/reactor/push_strelka.sls

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

salt/reactor/push_suricata.sls

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

salt/redis/enabled.sls

@@ -17,7 +17,6 @@ include:
 so-redis:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-redis:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: so-redis
     - user: socore
     - networks:

salt/redis/ssl.sls

@@ -33,7 +33,8 @@ redis_crt:
     - days_remaining: 7
     - days_valid: 820
     - backup: True
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/redis.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 5
         interval: 30

salt/registry/enabled.sls

@@ -16,14 +16,11 @@ 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:
         - ipv4_address: {{ DOCKERMERGED.containers['so-dockerregistry'].ip }}
-    # Intentionally `always` (not unless-stopped) -- registry is critical infra
-    # and must come back up even if it was manually stopped. Do not homogenize
-    # to unless-stopped; see the container auto-restart section of the plan.
     - restart_policy: always
     - port_bindings:
       {% for BINDING in DOCKERMERGED.containers['so-dockerregistry'].port_bindings %}

salt/registry/ssl.sls

@@ -55,7 +55,8 @@ registry_crt:
     - backup: True
     - require:
       - file: registry_crt_cleanup
-    - timeout: 30
+    - onlyif:
+      - test ! -f /etc/pki/registry.crt || {{ CA.reachable_cmd }}
     - retry:
         attempts: 15
         interval: 10

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/salt/beacons.sls

@@ -3,7 +3,7 @@
 {% set SCHEDULE = salt['pillar.get']('healthcheck:schedule', 30) %}
 
 include:
-  - salt.minion
+  - salt
 
 {% if CHECKS and ENABLED %}
 salt_beacons:
@@ -23,4 +23,3 @@ salt_beacons:
     - watch_in: 
       - service: salt_minion_service
 {% endif %}
-

salt/salt/files/reactor_pushstate.conf

@@ -1,11 +0,0 @@
-reactor:
-  - 'salt/beacon/*/inotify//opt/so/saltstack/local/salt/suricata/rules':
-    - salt://reactor/push_suricata.sls
-  - 'salt/beacon/*/inotify//opt/so/saltstack/local/salt/suricata/rules/*':
-    - salt://reactor/push_suricata.sls
-  - 'salt/beacon/*/inotify//opt/so/saltstack/local/salt/strelka/rules/compiled':
-    - salt://reactor/push_strelka.sls
-  - 'salt/beacon/*/inotify//opt/so/saltstack/local/salt/strelka/rules/compiled/*':
-    - salt://reactor/push_strelka.sls
-  - 'salt/beacon/*/pillar_db/audit_settings':
-    - salt://reactor/push_pillar.sls

salt/salt/init.sls

@@ -5,11 +5,3 @@ salt_bootstrap:
     - source: salt://salt/scripts/bootstrap-salt.sh
     - mode: 755
     - show_changes: False
-
-salt_sbin:
-  file.recurse:
-    - name: /usr/sbin
-    - source: salt://salt/tools/sbin
-    - user: 939
-    - group: 939
-    - file_mode: 755

salt/salt/lasthighstate.sls

@@ -1,4 +1,4 @@
 lasthighstate:
   file.touch:
     - name: /opt/so/log/salt/lasthighstate
-    - order: 9001
+    - order: last

salt/salt/master.sls

@@ -10,12 +10,10 @@
 #    software that is protected by the license key."
 
 {% from 'allowed_states.map.jinja' import allowed_states %}
-{% from 'global/map.jinja' import GLOBALMERGED %}
 {% if sls in allowed_states %}
 
 include:
   - salt.minion
-  - salt.master.pyinotify
   - salt.master.boot_mine_update
 {%   if 'vrt' in salt['pillar.get']('features', []) %}
   - salt.cloud
@@ -65,21 +63,6 @@ engines_config:
     - name: /etc/salt/master.d/engines.conf
     - source: salt://salt/files/engines.conf
 
-{% if GLOBALMERGED.push.enabled %}
-reactor_pushstate_config:
-  file.managed:
-    - name: /etc/salt/master.d/reactor_pushstate.conf
-    - source: salt://salt/files/reactor_pushstate.conf
-    - watch_in:
-      - service: salt_master_service
-{% else %}
-reactor_pushstate_config:
-  file.absent:
-    - name: /etc/salt/master.d/reactor_pushstate.conf
-    - watch_in:
-      - service: salt_master_service
-{% endif %}
-
 # update the bootstrap script when used for salt-cloud
 salt_bootstrap_cloud:
   file.managed:
@@ -95,7 +78,7 @@ salt_master_service:
       - file: checkmine_engine
       - file: pillarWatch_engine
       - file: engines_config
-    - order: 9002
+    - order: last
 
 {% else %}
 

salt/salt/master/pyinotify.sls

@@ -1,20 +0,0 @@
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-pyinotify_module_package:
-  file.recurse:
-    - name: /opt/so/conf/salt/module_packages/pyinotify
-    - source: salt://salt/module_packages/pyinotify
-    - clean: True
-    - makedirs: True
-
-pyinotify_python_module_install:
-  cmd.run:
-    - name: /opt/saltstack/salt/bin/python3.10 -m pip install pyinotify --no-index --find-links=/opt/so/conf/salt/module_packages/pyinotify/ --upgrade
-    - onchanges:
-      - file: pyinotify_module_package
-    - failhard: True
-    - watch_in:
-      - service: salt_minion_service

salt/salt/minion.defaults.yaml

@@ -2,3 +2,4 @@
 salt:
   minion:
     version: '3006.19'
+    check_threshold: 3600 # in seconds, threshold used for so-salt-minion-check. any value less than 600 seconds may cause a lot of salt-minion restarts since the job to touch the file occurs every 5-8 minutes by default

salt/salt/minion/init.sls

@@ -111,17 +111,13 @@ mark_setup_complete_for_upgrades:
 
 {% endif %}
 
-# this has to be outside the if statement above since there are <requisite>_in calls to this state.
+# this has to be outside the if statement above since there are <requisite>_in calls to this state
-# uses watch (not listen) so the restart fires in-state and its result lands on this state's
-# running entry; that is what lets wait_for_salt_minion_ready below detect any restart
-# uniformly via onchanges, regardless of whether the trigger came from these files or from
-# external watch_in's (e.g. beacons, master/pyinotify).
 salt_minion_service:
   service.running:
     - name: salt-minion
     - enable: True
     - onlyif: test "{{INSTALLEDSALTVERSION}}" == "{{SALTVERSION}}"
-    - watch:
+    - listen:
       - file: mine_functions
 {% if INSTALLEDSALTVERSION|string == SALTVERSION|string %}
       - file: set_log_levels
@@ -130,17 +126,3 @@ salt_minion_service:
       - file: signing_policy
 {% endif %}
     - order: last
-
-# block until the just-restarted salt-minion is back and can execute modules locally, so
-# follow-on jobs and the next highstate iteration do not race the restart. onchanges +
-# require on salt_minion_service catches every restart trigger uniformly because watch
-# mod_watch results replace the service state's running entry. wait logic lives in
-# /usr/sbin/so-salt-minion-wait (deployed by common_sbin from common/tools/sbin/).
-wait_for_salt_minion_ready:
-  cmd.run:
-    - name: /usr/sbin/so-salt-minion-wait
-    - onchanges:
-      - service: salt_minion_service
-    - require:
-      - service: salt_minion_service
-    - order: last

salt/salt/tools/sbin/so-salt-minion-wait

@@ -1,35 +0,0 @@
-#!/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.
-
-# Block until the local salt-minion service is back up and can execute modules locally.
-# Invoked from the wait_for_salt_minion_ready state in salt/minion/init.sls after
-# salt_minion_service fires its watch-driven mod_watch (a non-blocking systemctl restart),
-# so follow-on jobs and the next highstate iteration do not race the in-flight restart.
-
-. /usr/sbin/so-common
-
-# Initial sleep gives the systemctl restart (--no-block by default for salt-minion on
-# >=3006.15) time to begin tearing down the old process before we probe for readiness.
-INITIAL_SLEEP=3
-TIMEOUT=120
-PING_TIMEOUT=5
-
-sleep "$INITIAL_SLEEP"
-
-elapsed="$INITIAL_SLEEP"
-while [ "$elapsed" -lt "$TIMEOUT" ]; do
-  if systemctl is-active --quiet salt-minion \
-     && salt-call --local --timeout="$PING_TIMEOUT" --out=quiet test.ping >/dev/null 2>&1; then
-    echo "salt-minion ready after ${elapsed}s"
-    exit 0
-  fi
-  sleep 1
-  elapsed=$((elapsed + 1))
-done
-
-echo "salt-minion did not become ready within ${TIMEOUT}s" >&2
-exit 1

salt/schedule.sls

@@ -1,26 +1,10 @@
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
-{% from 'global/map.jinja' import GLOBALMERGED %}
 
 highstate_schedule:
   schedule.present:
     - function: state.highstate
-    - hours: {{ GLOBALMERGED.push.highstate_interval_hours }}
+    - minutes: 15
     - maxrunning: 1
 {% if not GLOBALS.is_manager %}
-    - splay: 1800
+    - splay: 120
-{% endif %}
-
-{% if GLOBALS.is_manager and GLOBALMERGED.push.enabled %}
-push_drain_schedule:
-  schedule.present:
-    - function: cmd.run
-    - job_args:
-      - /usr/sbin/so-push-drainer
-    - seconds: {{ GLOBALMERGED.push.drain_interval }}
-    - maxrunning: 1
-    - return_job: False
-{% elif GLOBALS.is_manager %}
-push_drain_schedule:
-  schedule.absent:
-    - name: push_drain_schedule
 {% endif %}

salt/sensoroni/enabled.sls

@@ -14,7 +14,6 @@ include:
 so-sensoroni:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-soc:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - network_mode: host
     - binds:
       - /nsm/import:/nsm/import:rw

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.map.jinja

@@ -8,6 +8,7 @@
 {% from 'docker/docker.map.jinja' import DOCKERMERGED -%}
 {% set INFLUXDB_TOKEN = salt['pillar.get']('influxdb:token') %}
 {% import_text 'influxdb/metrics_link.txt' as METRICS_LINK %}
+{% from 'telegraf/map.jinja' import TELEGRAFMERGED %}
 
 {% for module, application_url in GLOBALS.application_urls.items() %}
 {%   do SOCDEFAULTS.soc.config.server.modules[module].update({'hostUrl': application_url}) %}
@@ -24,6 +25,14 @@
 
 {% do SOCDEFAULTS.soc.config.server.modules.elastic.update({'username': GLOBALS.elasticsearch.auth.users.so_elastic_user.user, 'password': GLOBALS.elasticsearch.auth.users.so_elastic_user.pass}) %}
 
+{% if TELEGRAFMERGED.output == 'POSTGRES' %}
+{%   for tool in SOCDEFAULTS.soc.config.server.client.tools %}
+{%     if tool.name == "toolInfluxDb" %}
+{%       do SOCDEFAULTS.soc.config.server.client.tools.remove(tool) %}
+{%     endif %}
+{%   endfor %}
+
+{% else %}
 {%   do SOCDEFAULTS.soc.config.server.modules.influxdb.update({'hostUrl': 'https://' ~ GLOBALS.influxdb_host ~ ':8086'}) %}
 {%   do SOCDEFAULTS.soc.config.server.modules.influxdb.update({'token': INFLUXDB_TOKEN}) %}
 {%   for tool in SOCDEFAULTS.soc.config.server.client.tools %}
@@ -31,6 +40,7 @@
 {%       do tool.update({'link': METRICS_LINK}) %}
 {%     endif %}
 {%   endfor %}
+{% endif %}
 
 {% do SOCDEFAULTS.soc.config.server.modules.statickeyauth.update({'anonymousCidr': DOCKERMERGED.range, 'apiKey': pillar.sensoroni.config.sensoronikey}) %}
 

salt/soc/defaults.yaml

@@ -1500,15 +1500,23 @@ soc:
           playbookRepos:
             default:
               - repo: https://github.com/Security-Onion-Solutions/securityonion-resources-playbooks
+                rulesetName: sos-playbook-resources
                 branch: main
                 folder: securityonion-normalized
+              - repo: https://github.com/Security-Onion-Solutions/securityonion-resources-playbooks
+                rulesetName: sos-published
+                branch: published
+                folder: sigma
             airgap:
               - repo: file:///nsm/airgap-resources/playbooks/securityonion-resources-playbooks
+                rulesetName: sos-resources-ag
                 branch: main
                 folder: securityonion-normalized
         assistant:
           systemPromptAddendum: ""
           systemPromptAddendumMaxLength: 50000
+          maxSubSessionTokens: 0
+          maxDelegationDepth: 5
           adapters:
             - name: SOAI
               protocol: securityonion_ai_cloud
@@ -1520,6 +1528,10 @@ soc:
               serviceAccountJSON: ""
               serviceAccountLocation: ""
               healthTimeoutSeconds: 5
+          agentic: false
+          agentMapping:
+            Orchestrator: sonnet
+            Hunter: sonnet
         onionconfig:
           saltstackDir: /opt/so/saltstack
           bypassEnabled: false
@@ -1771,13 +1783,13 @@ 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'
@@ -2689,6 +2701,8 @@ soc:
           thresholdColorRatioLow: 0.5
           thresholdColorRatioMed: 0.75
           thresholdColorRatioMax: 1
+          toolBusyMaxRetries: 30
+          toolBusyRetryDelayMs: 1000
           availableModels:
             - id: sonnet
               displayName: Claude Sonnet

salt/soc/enabled.sls

@@ -18,7 +18,6 @@ include:
 so-soc:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-soc:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - hostname: soc
     - name: so-soc
     - networks:
@@ -46,7 +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
@@ -100,6 +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/merged.map.jinja

@@ -7,6 +7,11 @@
 {% from 'soc/defaults.map.jinja' import SOCDEFAULTS with context %}
 {% from 'elasticsearch/config.map.jinja' import ELASTICSEARCH_NODES %}
 {% from 'manager/map.jinja' import MANAGERMERGED %}
+{% from 'telegraf/map.jinja' import TELEGRAFMERGED %}
+{%- set PG_ENTRY = salt['pillar.get']('telegraf:postgres_creds:' ~ grains.id, {}) %}
+{%- set PG_USER = PG_ENTRY.get('user', '') %}
+{%- set PG_PASS = PG_ENTRY.get('pass', '') %}
+
 {% set DOCKER_EXTRA_HOSTS = ELASTICSEARCH_NODES %}
 {% do DOCKER_EXTRA_HOSTS.append({GLOBALS.influxdb_host:pillar.node_data[GLOBALS.influxdb_host].ip}) %}
 
@@ -75,6 +80,20 @@
 {%   do SOCMERGED.config.server.update({'airgapEnabled': false}) %}
 {% endif %}
 
+{# Define the postgresmetrics module if telegraf is setup to only use Postgres #}
+{% if TELEGRAFMERGED.output != 'INFLUXDB' and PG_USER and PG_PASS %}
+{%   do SOCMERGED.config.server.modules.update({
+        'postgresmetrics': {
+          'database': 'so_telegraf',
+          'host': GLOBALS.manager_ip,
+          'password': PG_PASS,
+          'port': 5432,
+          'sslMode': 'allow',
+          'user': PG_USER,
+        }
+      }) %}
+{%   do SOCMERGED.config.server.modules.pop('influxdb') %}
+{% endif %}
 
 {# Define the Detections custom ruleset that should always be present #}
 {% set CUSTOM_RULESET = {

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:
@@ -719,6 +727,16 @@ soc:
             description: Maximum length of the system prompt addendum. Longer prompts will be truncated.
             global: True
             advanced: True
+          maxSubSessionTokens:
+            description: Maximum number of output tokens a delegated sub-session may generate across all of its turns. When the budget is reached, the sub-agent is halted and its result is returned to the parent agent. Set to 0 to disable the limit.
+            global: True
+            advanced: True
+            forcedType: int
+          maxDelegationDepth:
+            description: Maximum delegation nesting depth for sub-agents. For example, a value of 2 lets the main agent delegate to a sub-agent that may itself delegate one level deeper. Any deeper delegation is refused and the requesting agent continues without it. Set to 0 to disable the limit.
+            global: True
+            advanced: True
+            forcedType: int
           adapters:
             description: Configuration for AI adapters used by the Onion AI assistant. Please see documentation for help on which fields are required for which protocols.
             global: True
@@ -757,12 +775,29 @@ soc:
               label: Health Timeout Seconds
               required: False
               forcedType: int
+          agentic:
+            description: Indicates if the Assistant Module should operate in agentic mode or not. If true, agents can work together to solve tasks.
+            global: True
+            forcedType: bool
+          agentMapping:
+            Orchestrator:
+              description: The initial agent in most agentic conversations. This agent will delegate requests to specialized agents.
+              global: True
+            Hunter:
+              description: This agent is specialized in querying events.
+              global: True
       client:
         assistant:
           enabled:
             description: Set to true to enable the Onion AI assistant in SOC.
             global: True
             forcedType: bool
+          toolBusyMaxRetries:
+            description: How many times to retry auto approving a tool while a tool is already running.
+            global: True
+          toolBusyRetryDelayMs:
+            description: How long in milliseconds to wait between each retry when auto approving a tool.
+            global: True
           investigationPrompt: 
             description: Prompt given to Onion AI when beginning an investigation.
             global: True

salt/strelka/backend/enabled.sls

@@ -47,10 +47,6 @@ strelka_backend:
       - {{ ULIMIT.name }}={{ ULIMIT.soft }}:{{ ULIMIT.hard }}
     {%   endfor %}
     {% endif %}
-    # Intentionally `on-failure` (not unless-stopped) -- strelka backend shuts
-    # down cleanly during rule reloads and we do not want those clean exits to
-    # trigger an auto-restart. Do not homogenize; see the container
-    # auto-restart section of the plan.
     - restart_policy: on-failure
     - watch:
       - file: strelkasensorcompiledrules

salt/strelka/coordinator/enabled.sls

@@ -15,7 +15,6 @@ include:
 strelka_coordinator:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-redis:{{ GLOBALS.so_version }}
-    - restart_policy: unless-stopped
     - name: so-strelka-coordinator
     - networks:
       - sobridge: